diff options
257 files changed, 24835 insertions, 4186 deletions
diff --git a/.editorconfig b/.editorconfig new file mode 100644 index 000000000..5f40572b0 --- /dev/null +++ b/.editorconfig @@ -0,0 +1,16 @@ +root = true + +[*] +charset = utf-8 +end_of_line = lf +indent_style = space +indent_size = 2 +insert_final_newline = true +trim_trailing_whitespace = true + +[*.{markdown,md}] +trim_trailing_whitespace = false + +[tests/*] +insert_final_newline = false +trim_trailing_whitespace = false diff --git a/.gitignore b/.gitignore index 98fe2fd6d..97150be15 100644 --- a/.gitignore +++ b/.gitignore @@ -4,11 +4,13 @@ README.* !README.Debian INSTALL.* .configure-stamp +.cabal-sandbox +cabal.sandbox.config +pandoc.cabal.orig man/man?/*.1 man/man?/*.5 man/man?/*.html *.diff -pandoc.cabal.orig *.o *.hi *.pyc diff --git a/.travis.yml b/.travis.yml index 487e3cb98..1ca7a1228 100644 --- a/.travis.yml +++ b/.travis.yml @@ -1,8 +1,28 @@ -language: haskell +# NB: don't set `language: haskell` here + +# The following enables several GHC versions to be tested; often it's enough to test only against the last release in a major GHC version. Feel free to omit lines listings versions you don't need/want testing for. +env: +# - GHCVER=6.12.3 + - GHCVER=7.4.2 + - GHCVER=7.6.3 + - GHCVER=7.8.2 # see note about Alex/Happy +# - GHCVER=head # see section about GHC HEAD snapshots + +# Note: the distinction between `before_install` and `install` is not important. before_install: - - cabal install cabal-dev - - 'git clone https://github.com/jgm/pandoc-types && cabal-dev add-source pandoc-types' + - travis_retry sudo add-apt-repository -y ppa:hvr/ghc + - travis_retry sudo apt-get update + - travis_retry sudo apt-get install cabal-install-1.18 ghc-$GHCVER + - export PATH=/opt/ghc/$GHCVER/bin:$PATH + install: - - cabal-dev install-deps --enable-tests + - cabal-1.18 update +# - git clone https://github.com/jgm/pandoc-types && cd pandoc-types && cabal-1.18 install && cd .. + - cabal-1.18 install --only-dependencies --enable-tests + +# Here starts the actual work to be performed for the package under test; any command which exits with a non-zero exit code causes the build to fail. script: - - 'cabal-dev configure --enable-tests && cabal-dev build && cabal-dev test' + - cabal-1.18 configure --enable-tests -v2 # -v2 provides useful information for debugging + - cabal-1.18 build --ghc-options=-Werror # this builds all libraries and executables (including tests/benchmarks) + - cabal-1.18 test + - cabal-1.18 check diff --git a/CONTRIBUTING.md b/CONTRIBUTING.md index eeee77b25..824d1465e 100644 --- a/CONTRIBUTING.md +++ b/CONTRIBUTING.md @@ -60,6 +60,8 @@ Please follow these guidelines: 3. Follow the stylistic conventions you find in the existing pandoc code. Use spaces, not tabs, and wrap code to 80 columns. Always include type signatures for top-level functions. + Consider installing [EditorConfig], this will help you to follow the + coding style prevalent in pandoc. 4. Your code should compile without warnings (`-Wall` clean). @@ -177,5 +179,6 @@ The library is structured as follows: [issue tracker]: https://github.com/jgm/pandoc/issues [User's Guide]: http://johnmacfarlane.net/pandoc/README.html [FAQs]: http://johnmacfarlane.net/pandoc/faqs.html +[EditorConfig]: http://editorconfig.org/ [Haskell platform]: http://www.haskell.org/platform/ [hsb2hs]: http://hackage.haskell.org/package/hsb2hs @@ -1,5 +1,5 @@ Pandoc -Copyright (C) 2006-2013 John MacFarlane <jgm at berkeley dot edu> +Copyright (C) 2006-2014 John MacFarlane <jgm at berkeley dot edu> This code is released under the [GPL], version 2 or later: @@ -33,33 +33,34 @@ licenses. ---------------------------------------------------------------------- src/Text/Pandoc/Writers/Texinfo.hs -Copyright (C) 2008-2010 John MacFarlane and Peter Wang +Copyright (C) 2008-2014 John MacFarlane and Peter Wang -Released under the GPL. +Released under the GNU General Public License version 2 or later. ---------------------------------------------------------------------- src/Text/Pandoc/Writers/OpenDocument.hs -Copyright (C) 2008-2010 Andrea Rossato and John MacFarlane +Copyright (C) 2008-2014 Andrea Rossato and John MacFarlane -Released under the GPL. +Released under the GNU General Public License version 2 or later. ---------------------------------------------------------------------- src/Text/Pandoc/Writers/Org.hs -Copyright (C) 2010 Puneeth Chaganti +Copyright (C) 2010-2014 Puneeth Chaganti and JohnMacFarlane -Released under the GPL. +Released under the GNU General Public License version 2 or later. ---------------------------------------------------------------------- src/Text/Pandoc/Readers/Textile.hs -Copyright (C) 2010 Paul Rivier +Copyright (C) 2010-2014 Paul Rivier and John MacFarlane -Released under the GPL. +Released under the GNU General Public License version 2 or later. ---------------------------------------------------------------------- -src/Text/Pandoc/Biblio.hs -Copyright (C) 2008-2010 Andrea Rossato +src/Text/Pandoc/Readers/Org.hs +tests/Tests/Readers/Org.hs +Copyright (C) 2014 Albert Krewinkel -Released under the GPL. +Released under the GNU General Public License version 2 or later. ---------------------------------------------------------------------- data/LaTeXMathML.js @@ -67,46 +68,13 @@ Adapted by Jeff Knisely and Douglas Woodall from ASCIIMathML.js v. 1.4.7 Copyright (C) 2005 Peter Jipsen -Released under the GPL. +Released under the GNU General Public License version 2 or later. ---------------------------------------------------------------------- -data/MathMLInHTML.js +data/MathMLinHTML.js Copyright (C) 2004 Peter Jipsen http://www.chapman.edu/~jipsen Released under the GNU General Public License version 2 or later. -See the GNU General Public License -(at http://www.gnu.org/copyleft/gpl.html) for more details. - ----------------------------------------------------------------------- -s5/default -S5 slides.js and css files -by Eric A. Meyer -<http://meyerweb.com/eric/tools/s5 - -Released under an explicit Public Domain License - ----------------------------------------------------------------------- -slidy/default -Slidy javascript and CSS -by Dave Raggett -http://www.w3.org/Talks/Tools/Slidy2 - -Released under W3C document and software licenses - ----------------------------------------------------------------------- -slideous/default -Slideous javascript and CSS -by Stefan Gössner -http://goessner.net/ - -Released under Creative Commons GNU LGPL License - ------------------------------------------------------------------------- -windows/modpath.iss -Copyright (c) 2007 Jared Breland -http://legroom.net/software - -Released under the GPL. ------------------------------------------------------------------------ The dzslides template contains javascript and CSS from Paul Rouget's @@ -12,11 +12,7 @@ Quick install ------------- 1. Install the [Haskell platform]. This will give you [GHC] and - the [cabal-install] build tool, as well as `alex` and `happy`. - If you do not use the Haskell platform, you'll need to install - `alex` and `happy` separately: - - cabal install alex happy + the [cabal-install] build tool. 2. Update your package database: @@ -48,12 +44,7 @@ Quick install [Not sure where `$CABALDIR` is?](http://www.haskell.org/haskellwiki/Cabal-Install#The_cabal-install_configuration_file) -5. Make sure the `$CABALDIR/share/man/man1` directory is in your `MANPATH`. - You should now be able to access the `pandoc` man page: - - man pandoc - -6. If you want to process citations with pandoc, you will also need to +5. If you want to process citations with pandoc, you will also need to install a separate package, `pandoc-citeproc`. This can be installed using cabal: @@ -75,6 +66,20 @@ Quick install --extra-include-dirs=/usr/local/Cellar/icu4c/51.1/include \ -funicode_collation text-icu pandoc-citeproc +The cabal installation procedure does not generate man pages. +To build the `pandoc` man pages, build pandoc with the +`make-pandoc-man-pages` flag, and then use the command +`make-pandoc-man-pages` from the pandoc source directory. +This will create the man pages in `man/man1` and `man/man5`. + +To build the `pandoc-citeproc` man pages, go to the pandoc-citeproc +build directory, and + + cd man + make + +The man page will be created in the `man1` subdirectory. + [GHC]: http://www.haskell.org/ghc/ [Haskell platform]: http://hackage.haskell.org/platform/ [cabal-install]: http://hackage.haskell.org/trac/hackage/wiki/CabalInstall @@ -116,9 +121,8 @@ assume that the pandoc source directory is your working directory. cabal install hsb2hs - - `http-conduit`: use the `http-conduit` library to fetch external - resources (default yes -- without this, pandoc cannot make SSL - connections) + - `https`: enable support for downloading resources over https + (using the `http-client` and `http-client-tls` libraries). 3. Build: @@ -1,51 +1,57 @@ -# This Makefile is for development only. It requires cabal-dev. -# To get started, do 'make prep' and then 'make' or 'make quick'. +version=$(shell grep '^Version:' pandoc.cabal | awk '{print $$2;}') +makemanpages=$(shell find dist -type f -name make-pandoc-man-pages) +ifeq "${makemanpages}" "" + makemanpages=@echo "You need to 'cabal configure -fmake-pandoc-man-pages && cabal build'" && exit 1 +endif +setup=dist/setup/setup +MANPAGES=man/man1/pandoc.1 man/man5/pandoc_markdown.5 -.PHONY: prep submodules all quick bench clean veryclean install sdist +quick: + cabal configure --enable-tests --disable-optimization + cabal build -all: - cabal-dev configure --enable-tests --enable-benchmarks && cabal-dev build +full: + cabal configure --enable-tests --enable-optimization -ftrypandoc -fmake-pandoc-man-pages -fembed_data_files --enable-benchmarks + cabal build + cabal haddock -test: all - cabal test +deps: + cabal install --only-dependencies --enable-tests -ftrypandoc -fmake-pandoc-man-pages -fembed_data_files --enable-benchmarks prof: - cabal-dev configure --disable-tests --enable-library-profiling --enable-executable-profiling && cabal-dev build - -prep: submodules pandoc-types citeproc-hs - (cabal-dev --version || (cabal update && cabal install cabal-dev)) && \ - cabal-dev update && \ - cabal-dev install-deps --enable-library-profiling --enable-tests --enable-benchmarks + cabal configure --enable-library-profiling --enable-executable-profiling --enable-optimization --enable-tests + cabal build -submodules: - git submodule update --init +test: + cabal test -quick: - cabal-dev configure --enable-tests --disable-optimization && cabal-dev build +bench: + cabal bench -relocatable: - cabal-dev configure -fembed_data_files && cabal-dev build +install: full + cabal copy + cabal register -bench: - cabal-dev configure --enable-benchmarks && cabal-dev build +dist: man + cabal sdist + rm -rf "pandoc-${version}" + tar xvzf dist/pandoc-${version}.tar.gz + cd pandoc-${version} + cabal configure ${CABALARGS} && cabal build && cabal test && cd .. && rm -rf "pandoc-${version}" -sdist: - dist/setup/setup sdist - # cabal sdist won't work, see https://github.com/haskell/cabal/issues/403 +man: ${MANPAGES} -clean: - cabal-dev clean +osxpkg: + ./make_osx_package.sh -veryclean: clean - rm -rf pandoc-types citeproc-hs dist cabal-dev +%.1: %.1.template README + ${makemanpages} -pandoc-types: - git clone https://github.com/jgm/pandoc-types && \ - cabal-dev add-source pandoc-types +%.5: %.5.template README + ${makemanpages} -citeproc-hs: pandoc-types - darcs get --lazy http://gorgias.mine.nu/repos/citeproc-hs && \ - cabal-dev add-source citeproc-hs +clean: + cabal clean + -rm ${MANPAGES} -install: - cabal-dev install --enable-tests +.PHONY: deps quick full install man clean test bench haddock osxpkg dist prof @@ -1,6 +1,6 @@ % Pandoc User's Guide % John MacFarlane -% January 19, 2013 +% August 30, 2014 Synopsis ======== @@ -13,14 +13,16 @@ Description Pandoc is a [Haskell] library for converting from one markup format to another, and a command-line tool that uses this library. It can read [markdown] and (subsets of) [Textile], [reStructuredText], [HTML], -[LaTeX], [MediaWiki markup], [Haddock markup], [OPML], and [DocBook]; and -it can write plain text, [markdown], [reStructuredText], [XHTML], [HTML 5], -[LaTeX] (including [beamer] slide shows), [ConTeXt], [RTF], [OPML], [DocBook], -[OpenDocument], [ODT], [Word docx], [GNU Texinfo], [MediaWiki markup], -[EPUB] (v2 or v3), [FictionBook2], [Textile], [groff man] pages, [Emacs -Org-Mode], [AsciiDoc], and [Slidy], [Slideous], [DZSlides], [reveal.js] -or [S5] HTML slide shows. It can also produce [PDF] output on systems -where LaTeX is installed. +[LaTeX], [MediaWiki markup], [TWiki markup], [Haddock markup], [OPML], +[Emacs Org-mode], [DocBook], [txt2tags], [EPUB] and [Word docx]; and +it can write plain text, [markdown], [reStructuredText], [XHTML], +[HTML 5], [LaTeX] (including [beamer] slide shows), [ConTeXt], [RTF], +[OPML], [DocBook], [OpenDocument], [ODT], [Word docx], [GNU Texinfo], +[MediaWiki markup], [DokuWiki markup], [Haddock markup], [EPUB] (v2 or v3), +[FictionBook2], [Textile], [groff man] pages, [Emacs Org-Mode], [AsciiDoc], +[InDesign ICML], and [Slidy], [Slideous], [DZSlides], [reveal.js] or +[S5] HTML slide shows. It can also produce [PDF] output on systems where +LaTeX is installed. Pandoc's enhanced version of markdown includes syntax for footnotes, tables, flexible ordered lists, definition lists, fenced code blocks, @@ -49,13 +51,23 @@ default (though output to *stdout* is disabled for the `odt`, `docx`, pandoc -o output.html input.txt +By default, pandoc produces a document fragment, not a standalone +document with a proper header and footer. To produce a standalone +document, use the `-s` or `--standalone` flag: + + pandoc -s -o output.html input.txt + +For more information on how standalone documents are produced, see +[Templates](#templates), below. + Instead of a file, an absolute URI may be given. In this case pandoc will fetch the content using HTTP: pandoc -f html -t markdown http://www.fsf.org If multiple input files are given, `pandoc` will concatenate them all (with -blank lines between them) before parsing. +blank lines between them) before parsing. This feature is disabled for + binary input formats such as `EPUB` and `docx`. The format of the input and output can be specified explicitly using command-line options. The input format can be specified using the @@ -93,6 +105,11 @@ should pipe input and output through `iconv`: iconv -t utf-8 input.txt | pandoc | iconv -f utf-8 +Note that in some output formats (such as HTML, LaTeX, ConTeXt, +RTF, OPML, DocBook, and Texinfo), information about +the character encoding is included in the document header, which +will only be included if you use the `-s/--standalone` option. + Creating a PDF -------------- @@ -143,14 +160,15 @@ General options `markdown_phpextra` (PHP Markdown Extra extended markdown), `markdown_github` (github extended markdown), `textile` (Textile), `rst` (reStructuredText), `html` (HTML), - `docbook` (DocBook), `opml` (OPML), `mediawiki` (MediaWiki markup), - `haddock` (Haddock markup), or `latex` (LaTeX). - If `+lhs` is appended to `markdown`, `rst`, `latex`, or `html`, - the input will be treated as literate Haskell source: - see [Literate Haskell support](#literate-haskell-support), below. - Markdown syntax extensions can be individually enabled or disabled - by appending `+EXTENSION` or `-EXTENSION` to the format name. - So, for example, `markdown_strict+footnotes+definition_lists` + `docbook` (DocBook), `t2t` (txt2tags), `docx` (docx), `epub` (EPUB), + `opml` (OPML), `org` (Emacs Org-mode), `mediawiki` (MediaWiki markup), + `twiki` (TWiki markup), `haddock` (Haddock markup), or `latex` (LaTeX). + If `+lhs` is appended to `markdown`, `rst`, + `latex`, or `html`, the input will be treated as literate Haskell + source: see [Literate Haskell support](#literate-haskell-support), + below. Markdown syntax extensions can be individually enabled or + disabled by appending `+EXTENSION` or `-EXTENSION` to the format + name. So, for example, `markdown_strict+footnotes+definition_lists` is strict markdown with footnotes and definition lists enabled, and `markdown-pipe_tables+hard_line_breaks` is pandoc's markdown without pipe tables and with hard line breaks. See [Pandoc's @@ -166,24 +184,25 @@ General options `rst` (reStructuredText), `html` (XHTML 1), `html5` (HTML 5), `latex` (LaTeX), `beamer` (LaTeX beamer slide show), `context` (ConTeXt), `man` (groff man), `mediawiki` (MediaWiki markup), + `dokuwiki` (DokuWiki markup), `textile` (Textile), `org` (Emacs Org-Mode), `texinfo` (GNU Texinfo), `opml` (OPML), `docbook` (DocBook), `opendocument` (OpenDocument), `odt` - (OpenOffice text document), `docx` (Word docx), - `rtf` (rich text format), `epub` (EPUB v2 book), `epub3` - (EPUB v3), `fb2` (FictionBook2 e-book), `asciidoc` (AsciiDoc), `slidy` - (Slidy HTML and javascript slide show), `slideous` (Slideous HTML and - javascript slide show), `dzslides` (DZSlides HTML5 + javascript slide - show), `revealjs` (reveal.js HTML5 + javascript slide show), `s5` - (S5 HTML and javascript slide show), or the path of a custom - lua writer (see [Custom writers](#custom-writers), below). Note that - `odt`, `epub`, and `epub3` output will not be directed to *stdout*; an - output filename must be specified using the `-o/--output` option. If - `+lhs` is appended to `markdown`, `rst`, `latex`, `beamer`, `html`, or - `html5`, the output will be rendered as literate Haskell source: see - [Literate Haskell support](#literate-haskell-support), below. Markdown - syntax extensions can be individually enabled or disabled by appending - `+EXTENSION` or `-EXTENSION` to the format name, as described above - under `-f`. + (OpenOffice text document), `docx` (Word docx), `haddock` (Haddock + markup), `rtf` (rich text format), `epub` (EPUB v2 book), `epub3` + (EPUB v3), `fb2` (FictionBook2 e-book), `asciidoc` (AsciiDoc), + `icml` (InDesign ICML), `slidy` (Slidy HTML and javascript slide show), + `slideous` (Slideous HTML and javascript slide show), `dzslides` + (DZSlides HTML5 + javascript slide show), `revealjs` (reveal.js + HTML5 + javascript slide show), `s5` (S5 HTML and javascript slide show), + or the path of a custom lua writer (see [Custom writers](#custom-writers), + below). Note that `odt`, `epub`, and `epub3` output will not be directed + to *stdout*; an output filename must be specified using the `-o/--output` + option. If `+lhs` is appended to `markdown`, `rst`, `latex`, `beamer`, + `html`, or `html5`, the output will be rendered as literate Haskell + source: see [Literate Haskell support](#literate-haskell-support), below. + Markdown syntax extensions can be individually enabled or disabled by + appending `+EXTENSION` or `-EXTENSION` to the format name, as described + above under `-f`. `-o` *FILE*, `--output=`*FILE* : Write output to *FILE* instead of *stdout*. If *FILE* is @@ -235,8 +254,8 @@ Reader options to curly quotes, `---` to em-dashes, `--` to en-dashes, and `...` to ellipses. Nonbreaking spaces are inserted after certain abbreviations, such as "Mr." (Note: This option is significant only when - the input format is `markdown`, `markdown_strict`, or `textile`. It - is selected automatically when the input format is `textile` or the + the input format is `markdown`, `markdown_strict`, `textile` or `twiki`. + It is selected automatically when the input format is `textile` or the output format is `latex` or `context`, unless `--no-tex-ligatures` is used.) @@ -307,6 +326,23 @@ Reader options `--tab-stop=`*NUMBER* : Specify the number of spaces per tab (default is 4). +`--track-changes=`*accept|reject|all* +: Specifies what to do with insertions and deletions produced by the MS + Word "track-changes" feature. *accept* (the default), inserts all + insertions, and ignores all deletions. *reject* inserts all + deletions and ignores insertions. *all* puts in both insertions + and deletions, wrapped in spans with `insertion` and `deletion` + classes, respectively. The author and time of change is + included. *all* is useful for scripting: only accepting changes + from a certain reviewer, say, or before a certain date. This + option only affects the docx reader. + +`--extract-media=`*DIR* +: Extract images and other media contained in a docx or epub container + to the path *DIR*, creating it if necessary, and adjust the images + references in the document so they point to the extracted files. + This option only affects the docx and epub readers. + General writer options ---------------------- @@ -403,10 +439,9 @@ Options affecting specific writers formats, including `html`, `html5`, `html+lhs`, `html5+lhs`, `s5`, `slidy`, `slideous`, `dzslides`, and `revealjs`. Scripts, images, and stylesheets at absolute URLs will be downloaded; those at relative URLs - will be sought first relative to the working directory, then relative to - the user data directory (see `--data-dir`), and finally relative to - pandoc's default data directory. `--self-contained` does not - work with `--mathjax`. + will be sought relative to the working directory (if the first source + file is local) or relative to the base URL (if the first source + file is remote). `--self-contained` does not work with `--mathjax`. `--offline` : Deprecated synonym for `--self-contained`. @@ -506,7 +541,7 @@ Options affecting specific writers `-c` *URL*, `--css=`*URL* : Link to a CSS style sheet. This option can be be used repeatedly to - include multiple files. They will be included in the order specified. + include multiple files. They will be included in the order specified. `--reference-odt=`*FILE* : Use the specified file as a style reference in producing an ODT. @@ -522,16 +557,17 @@ Options affecting specific writers : Use the specified file as a style reference in producing a docx file. For best results, the reference docx should be a modified version of a docx file produced using pandoc. The contents of the reference docx - are ignored, but its stylesheets are used in the new docx. If no + are ignored, but its stylesheets and document properties (including + margins, page size, header, and footer) are used in the new docx. If no reference docx is specified on the command line, pandoc will look for a file `reference.docx` in the user data directory (see `--data-dir`). If this is not found either, sensible defaults will be used. The following styles are used by pandoc: [paragraph] - Normal, Compact, Title, Authors, Date, Heading 1, Heading 2, Heading 3, - Heading 4, Heading 5, Block Quote, Definition Term, Definition, - Body Text, Table Caption, Image Caption; [character] Default - Paragraph Font, Body Text Char, Verbatim Char, Footnote Ref, - Link. + Normal, Compact, Title, Subtitle, Authors, Date, Abstract, Heading 1, + Heading 2, Heading 3, Heading 4, Heading 5, Block Quote, Definition Term, + Definition, Bibliography, Body Text, Table Caption, Image Caption; + [character] Default Paragraph Font, Body Text Char, Verbatim Char, + Footnote Ref, Link. `--epub-stylesheet=`*FILE* : Use the specified CSS file to style the EPUB. If no stylesheet @@ -632,10 +668,16 @@ Citation rendering `--metadata citation-abbreviations=FILE`.) `--natbib` -: Use natbib for citations in LaTeX output. +: Use natbib for citations in LaTeX output. This option is not for use + with the `pandoc-citeproc` filter or with PDF output. It is intended for + use in producing a LaTeX file that can be processed with pdflatex and + bibtex. `--biblatex` -: Use biblatex for citations in LaTeX output. +: Use biblatex for citations in LaTeX output. This option is not for use + with the `pandoc-citeproc` filter or with PDF output. It is intended for + use in producing a LaTeX file that can be processed with pdflatex and + bibtex or biber. Math rendering in HTML ---------------------- @@ -683,6 +725,16 @@ Math rendering in HTML formulas to images. The formula will be concatenated with the URL provided. If *URL* is not specified, the Google Chart API will be used. +`--katex`[=*URL*] +: Use [KaTeX] to display embedded TeX math in HTML output. + The *URL* should point to the `katex.js` load script. If a *URL* is + not provided, a link to the KaTeX CDN will be inserted. + +`--katex-stylesheet=*URL*` +: The *URL* should point to the `katex.css` stylesheet. If this option is + not specified, a link to the KaTeX CDN will be inserted. Note that this + option does not imply `--katex`. + Options for wrapper scripts --------------------------- @@ -748,65 +800,115 @@ as `title`, `author`, and `date`) as well as the following: `header-includes` : contents specified by `-H/--include-in-header` (may have multiple values) + `toc` : non-null value if `--toc/--table-of-contents` was specified + `include-before` : contents specified by `-B/--include-before-body` (may have multiple values) + `include-after` : contents specified by `-A/--include-after-body` (may have multiple values) + `body` : body of document + `lang` : language code for HTML or LaTeX documents + `slidy-url` : base URL for Slidy documents (defaults to `http://www.w3.org/Talks/Tools/Slidy2`) + `slideous-url` -: base URL for Slideous documents (defaults to `default`) +: base URL for Slideous documents (defaults to `slideous`) + `s5-url` -: base URL for S5 documents (defaults to `ui/default`) +: base URL for S5 documents (defaults to `s5/default`) + `revealjs-url` : base URL for reveal.js documents (defaults to `reveal.js`) + `theme` : reveal.js or LaTeX beamer theme + `transition` : reveal.js transition + `fontsize` : font size (10pt, 11pt, 12pt) for LaTeX documents + `documentclass` : document class for LaTeX documents + `classoption` : option for LaTeX documentclass, e.g. `oneside`; may be repeated for multiple options + `geometry` : options for LaTeX `geometry` class, e.g. `margin=1in`; may be repeated for multiple options + +`linestretch` +: adjusts line spacing (requires the `setspace` package) + +`fontfamily` +: font package to use for LaTeX documents (with pdflatex): + TeXLive has `bookman` (Bookman), `utopia` or `fourier` (Utopia), + `fouriernc` (New Century Schoolbook), `times` or `txfonts` (Times), + `mathpazo` or `pxfonts` or `mathpple` (Palatino), + `libertine` (Linux Libertine), `arev` (Arev Sans), + and the default `lmodern`, among others. + `mainfont`, `sansfont`, `monofont`, `mathfont` : fonts for LaTeX documents (works only with xelatex and lualatex) + `colortheme` : colortheme for LaTeX beamer documents + `fonttheme` : fonttheme for LaTeX beamer documents + `linkcolor` : color for internal links in LaTeX documents (`red`, `green`, `magenta`, `cyan`, `blue`, `black`) + `urlcolor` : color for external links in LaTeX documents + `citecolor` : color for citation links in LaTeX documents + `links-as-notes` : causes links to be printed as footnotes in LaTeX documents + +`toc` +: include table of contents in LaTeX documents + +`toc-depth` +: level of section to include in table of contents in LaTeX documents + +`lof` +: include list of figures in LaTeX documents + +`lot` +: include list of tables in LaTeX documents + `biblio-style` : bibliography style in LaTeX, when used with `--natbib` + `biblio-files` : bibliography files to use in LaTeX, with `--natbib` or `--biblatex` + `section` : section number in man pages + `header` : header in man pages + `footer` : footer in man pages @@ -893,7 +995,7 @@ A paragraph is one or more lines of text followed by one or more blank line. Newlines are treated as spaces, so you can reflow your paragraphs as you like. If you need a hard line break, put two or more spaces at the end of a line. -**Extension: `escaped_line_breaks`** +#### Extension: `escaped_line_breaks` #### A backslash followed by a newline is also a hard line break. Note: in multiline and grid table cells, this is the only way @@ -934,7 +1036,7 @@ As with setext-style headers, the header text can contain formatting: # A level-one header with a [link](/url) and *emphasis* -**Extension: `blank_before_header`** +#### Extension: `blank_before_header` #### Standard markdown syntax does not require a blank line before a header. Pandoc does require this (except, of course, at the beginning of the @@ -948,17 +1050,15 @@ wrapping). Consider, for example: ### Header identifiers in HTML, LaTeX, and ConTeXt ### -**Extension: `header_attributes`** +#### Extension: `header_attributes` #### Headers can be assigned attributes using this syntax at the end of the line containing the header text: {#identifier .class .class key=value key=value} -Although this syntax allows assignment of classes and key/value attributes, -only identifiers currently have any affect in the writers (and only in some -writers: HTML, LaTeX, ConTeXt, Textile, AsciiDoc). Thus, for example, -the following headers will all be assigned the identifier `foo`: +Thus, for example, the following headers will all be assigned the identifier +`foo`: # My header {#foo} @@ -969,6 +1069,12 @@ the following headers will all be assigned the identifier `foo`: (This syntax is compatible with [PHP Markdown Extra].) +Note that although this syntax allows assignment of classes and key/value +attributes, writers generally don't use all of this information. Identifiers, +classes, and key/value attributes are used in HTML and HTML-based formats such +as EPUB and slidy. Identifiers are used for labels and link anchors in the +LaTeX, ConTeXt, Textile, and AsciiDoc writers. + Headers with the class `unnumbered` will not be numbered, even if `--number-sections` is specified. A single hyphen (`-`) in an attribute context is equivalent to `.unnumbered`, and preferable in non-English @@ -980,7 +1086,7 @@ is just the same as # My header {.unnumbered} -**Extension: `auto_identifiers`** +#### Extension: `auto_identifiers` #### A header without an explicitly specified identifier will be automatically assigned a unique identifier based on the header text. @@ -1029,7 +1135,7 @@ and the identifier will be attached to the enclosing `<div>` sections to be manipulated using javascript or treated differently in CSS. -**Extension: `implicit_header_references`** +#### Extension: `implicit_header_references` #### Pandoc behaves as if reference links have been defined for each header. So, instead of @@ -1088,7 +1194,7 @@ other block quotes. That is, block quotes can be nested: > > > A block quote within a block quote. -**Extension: `blank_before_blockquote`** +#### Extension: `blank_before_blockquote` #### Standard markdown syntax does not require a blank line before a block quote. Pandoc does require this (except, of course, at the beginning of the @@ -1122,7 +1228,7 @@ Note: blank lines in the verbatim text need not begin with four spaces. ### Fenced code blocks ### -**Extension: `fenced_code_blocks`** +#### Extension: `fenced_code_blocks` #### In addition to standard indented code blocks, Pandoc supports *fenced* code blocks. These begin with a row of three or more @@ -1148,6 +1254,8 @@ row of tildes or backticks at the start and end: ~~~~~~~~~~ ~~~~~~~~~~~~~~~~ +#### Extension: `fenced_code_attributes` #### + Optionally, you may attach attributes to the code block using this syntax: @@ -1184,13 +1292,18 @@ This is equivalent to: qsort [] = [] ``` +If the `fenced_code_attributes` extension is disabled, but +input contains class attribute(s) for the codeblock, the first +class attribute will be printed after the opening fence as a bare +word. + To prevent all highlighting, use the `--no-highlight` flag. To set the highlighting style, use `--highlight-style`. Line blocks ----------- -**Extension: `line_blocks`** +#### Extension: `line_blocks` #### A line block is a sequence of lines beginning with a vertical bar (`|`) followed by a space. The division into lines will be preserved in @@ -1332,7 +1445,7 @@ and this one: 7. two 1. three -**Extension: `fancy_lists`** +#### Extension: `fancy_lists` #### Unlike standard markdown, Pandoc allows ordered list items to be marked with uppercase and lowercase letters and roman numerals, in addition to @@ -1363,7 +1476,7 @@ ordered list marker in place of a numeral: #. one #. two -**Extension: `startnum`** +#### Extension: `startnum` #### Pandoc also pays attention to the type of list marker used, and to the starting number, and both of these are preserved where possible in the @@ -1395,10 +1508,10 @@ If default list markers are desired, use `#.`: ### Definition lists ### -**Extension: `definition_lists`** +#### Extension: `definition_lists` #### -Pandoc supports definition lists, using a syntax inspired by -[PHP Markdown Extra] and [reStructuredText]:[^3] +Pandoc supports definition lists, using the syntax of +[PHP Markdown Extra] with some extensions.[^3] Term 1 @@ -1415,32 +1528,48 @@ Pandoc supports definition lists, using a syntax inspired by Each term must fit on one line, which may optionally be followed by a blank line, and must be followed by one or more definitions. A definition begins with a colon or tilde, which may be indented one -or two spaces. The body of the definition (including the first line, -aside from the colon or tilde) should be indented four spaces. A term may have -multiple definitions, and each definition may consist of one or more block -elements (paragraph, code block, list, etc.), each indented four spaces or one -tab stop. - -If you leave space after the definition (as in the example above), -the blocks of the definitions will be considered paragraphs. In some +or two spaces. + +A term may have multiple definitions, and each definition may consist of one or +more block elements (paragraph, code block, list, etc.), each indented four +spaces or one tab stop. The body of the definition (including the first line, +aside from the colon or tilde) should be indented four spaces. However, +as with other markdown lists, you can "lazily" omit indentation except +at the beginning of a paragraph or other block element: + + Term 1 + + : Definition + with lazy continuation. + + Second paragraph of the definition. + +If you leave space before the definition (as in the example above), +the text of the definition will be treated as a paragraph. In some output formats, this will mean greater spacing between term/definition -pairs. For a compact definition list, do not leave space between the -definition and the next term: +pairs. For a more compact definition list, omit the space before the +definition: Term 1 ~ Definition 1 + Term 2 ~ Definition 2a ~ Definition 2b -[^3]: I have also been influenced by the suggestions of [David Wheeler](http://www.justatheory.com/computers/markup/modest-markdown-proposal.html). +Note that space between items in a definition list is required. +(A variant that loosens this requirement, but disallows "lazy" +hard wrapping, can be activated with `compact_definition_lists`: see +[Non-pandoc extensions](#non-pandoc-extensions), below.) + +[^3]: I have been influenced by the suggestions of [David Wheeler](http://www.justatheory.com/computers/markup/modest-markdown-proposal.html). [PHP Markdown Extra]: http://www.michelf.com/projects/php-markdown/extra/ ### Numbered example lists ### -**Extension: `example_lists`** +#### Extension: `example_lists` #### The special list marker `@` can be used for sequentially numbered examples. The first list item with a `@` marker will be numbered '1', @@ -1546,9 +1675,14 @@ Four kinds of tables may be used. The first three kinds presuppose the use of a fixed-width font, such as Courier. The fourth kind can be used with proportionally spaced fonts, as it does not require lining up columns. -### Simple tables +#### Extension: `table_captions` #### + +A caption may optionally be provided with all 4 kinds of tables (as +illustrated in the examples below). A caption is a paragraph beginning +with the string `Table:` (or just `:`), which will be stripped off. +It may appear either before or after the table. -**Extension: `simple_tables`, `table_captions`** +#### Extension: `simple_tables` #### Simple tables look like this: @@ -1577,10 +1711,7 @@ to the dashed line below it:[^4] [Markdown discussion list](http://six.pairlist.net/pipermail/markdown-discuss/2005-March/001097.html). The table must end with a blank line, or a line of dashes followed by -a blank line. A caption may optionally be provided (as illustrated in -the example above). A caption is a paragraph beginning with the string -`Table:` (or just `:`), which will be stripped off. It may appear either -before or after the table. +a blank line. The column headers may be omitted, provided a dashed line is used to end the table. For example: @@ -1595,9 +1726,7 @@ When headers are omitted, column alignments are determined on the basis of the first line of the table body. So, in the tables above, the columns would be right, left, center, and right aligned, respectively. -### Multiline tables - -**Extension: `multiline_tables`, `table_captions`** +#### Extension: `multiline_tables` #### Multiline tables allow headers and table rows to span multiple lines of text (but cells that span multiple columns or rows of the table are @@ -1647,9 +1776,7 @@ It is possible for a multiline table to have just one row, but the row should be followed by a blank line (and then the row of dashes that ends the table), or the table may be interpreted as a simple table. -### Grid tables - -**Extension: `grid_tables`, `table_captions`** +#### Extension: `grid_tables` #### Grid tables look like this: @@ -1673,9 +1800,7 @@ columns or rows. Grid tables can be created easily using [Emacs table mode]. [Emacs table mode]: http://table.sourceforge.net/ -### Pipe tables - -**Extension: `pipe_tables`, `table_captions`** +#### Extension: `pipe_tables` #### Pipe tables look like this: @@ -1685,7 +1810,7 @@ Pipe tables look like this: | 123 | 123 | 123 | 123 | | 1 | 1 | 1 | 1 | - : Demonstration of simple table syntax. + : Demonstration of pipe table syntax. The syntax is [the same as in PHP markdown extra]. The beginning and ending pipe characters are optional, but pipes are required between all @@ -1704,7 +1829,10 @@ legal (though ugly) pipe table: orange|3.09 The cells of pipe tables cannot contain block elements like paragraphs -and lists, and cannot span multiple lines. +and lists, and cannot span multiple lines. Note also that in LaTeX/PDF +output, the cells produced by pipe tables will not wrap, since there +is no information available about relative widths. If you want content +to wrap within cells, use multiline or grid tables. [the same as in PHP markdown extra]: http://michelf.ca/projects/php-markdown/extra/#table @@ -1721,10 +1849,10 @@ The difference is that `+` is used instead of `|`. Other orgtbl features are not supported. In particular, to get non-default column alignment, you'll need to add colons as above. -Title block ------------ +Metadata blocks +--------------- -**Extension: `pandoc_title_block`** +#### Extension: `pandoc_title_block` #### If the file begins with a title block @@ -1800,16 +1928,20 @@ will also have "Pandoc User Manuals" in the footer. will also have "Version 4.0" in the header. -YAML metadata block -------------------- - -**Extension: `yaml_metadata_block`** +#### Extension: `yaml_metadata_block` #### A YAML metadata block is a valid YAML object, delimited by a line of three hyphens (`---`) at the top and a line of three hyphens (`---`) or three dots (`...`) at the bottom. A YAML metadata block may occur anywhere in the document, but if it is not at the beginning, it must be preceded by a blank -line. +line. (Note that, because of the way pandoc concatenates input files when +several are provided, you may also keep the metadata in a separate YAML file +and pass it to pandoc as an argument, along with your markdown files: + + pandoc chap1.md chap2.md chap3.md metadata.yaml -s -o book.html + +Just be sure that the YAML file begins with `---` and ends with `---` or +`...`.) Metadata will be taken from the fields of the YAML object and added to any existing document metadata. Metadata can contain lists and objects (nested @@ -1821,6 +1953,11 @@ A document may contain multiple metadata blocks. The metadata fields will be combined through a *left-biased union*: if two metadata blocks attempt to set the same field, the value from the first block will be taken. +When pandoc is used with `-t markdown` to create a markdown document, +a YAML metadata block will be produced only if the `-s/--standalone` +option is used. All of the metadata will appear in a single block +at the beginning of the document. + Note that YAML escaping rules must be followed. Thus, for example, if a title contains a colon, it must be quoted. The pipe character (`|`) can be used to begin an indented block that will be interpreted @@ -1864,7 +2001,7 @@ custom template. For example: Backslash escapes ----------------- -**Extension: `all_symbols_escapable`** +#### Extension: `all_symbols_escapable` #### Except inside a code block or inline code, any punctuation or space character preceded by a backslash will be treated literally, even if it @@ -1903,7 +2040,7 @@ Backslash escapes do not work in verbatim contexts. Smart punctuation ----------------- -**Extension** +#### Extension #### If the `--smart` option is specified, pandoc will produce typographically correct output, converting straight quotes to curly quotes, `---` to @@ -1932,7 +2069,7 @@ will not trigger emphasis: This is * not emphasized *, and \*neither is this\*. -**Extension: `intraword_underscores`** +#### Extension: `intraword_underscores` #### Because `_` is sometimes used inside words and identifiers, pandoc does not interpret a `_` surrounded by alphanumeric @@ -1944,7 +2081,7 @@ just part of a word, use `*`: ### Strikeout ### -**Extension: `strikeout`** +#### Extension: `strikeout` #### To strikeout a section of text with a horizontal line, begin and end it with `~~`. Thus, for example, @@ -1954,7 +2091,7 @@ with `~~`. Thus, for example, ### Superscripts and subscripts ### -**Extension: `superscript`, `subscript`** +#### Extension: `superscript`, `subscript` #### Superscripts may be written by surrounding the superscripted text by `^` characters; subscripts may be written by surrounding the subscripted @@ -1992,21 +2129,31 @@ work in verbatim contexts: This is a backslash followed by an asterisk: `\*`. -**Extension: `inline_code_attributes`** +#### Extension: `inline_code_attributes` #### Attributes can be attached to verbatim text, just as with [fenced code blocks](#fenced-code-blocks): `<$>`{.haskell} +### Small caps ### + +To write small caps, you can use an HTML span tag: + + <span style="font-variant:small-caps;">Small caps</span> + +(The semicolon is optional and there may be space after the +colon.) This will work in all output formats that support small caps. + Math ---- -**Extension: `tex_math_dollars`** +#### Extension: `tex_math_dollars` #### Anything between two `$` characters will be treated as TeX math. The -opening `$` must have a character immediately to its right, while the -closing `$` must have a character immediately to its left. Thus, +opening `$` must have a non-space character immediately to its right, +while the closing `$` must have a non-space character immediately to its +left, and must not be followed immediately by a digit. Thus, `$20,000 and $30,000` won't parse as math. If for some reason you need to enclose text in literal `$` characters, backslash-escape them and they won't be treated as math delimiters. @@ -2030,7 +2177,7 @@ Texinfo groff man ~ It will be rendered verbatim without `$`'s. -MediaWiki +MediaWiki, DokuWiki ~ It will be rendered inside `<math>` tags. Textile @@ -2104,7 +2251,7 @@ HTML, Slidy, DZSlides, S5, EPUB Raw HTML -------- -**Extension: `raw_html`** +#### Extension: `raw_html` #### Markdown allows you to insert raw HTML (or DocBook) anywhere in a document (except verbatim contexts, where `<`, `>`, and `&` are interpreted @@ -2116,7 +2263,7 @@ The raw HTML is passed through unchanged in HTML, S5, Slidy, Slideous, DZSlides, EPUB, Markdown, and Textile output, and suppressed in other formats. -**Extension: `markdown_in_html_blocks`** +#### Extension: `markdown_in_html_blocks` #### Standard markdown allows you to include HTML "blocks": blocks of HTML between balanced tags that are separated from the surrounding text @@ -2154,10 +2301,24 @@ markdown with HTML block elements. For example, one can surround a block of markdown text with `<div>` tags without preventing it from being interpreted as markdown. +#### Extension: `native_divs` #### + +Use native pandoc `Div` blocks for content inside `<div>` tags. +For the most part this should give the same output as +`markdown_in_html_blocks`, but it makes it easier to write pandoc +filters to manipulate groups of blocks. + +#### Extension: `native_spans` #### + +Use native pandoc `Span` blocks for content inside `<span>` tags. +For the most part this should give the same output as `raw_html`, +but it makes it easier to write pandoc filters to manipulate groups +of inlines. + Raw TeX ------- -**Extension: `raw_tex`** +#### Extension: `raw_tex` #### In addition to raw HTML, pandoc allows raw LaTeX, TeX, and ConTeXt to be included in a document. Inline TeX commands will be preserved and passed @@ -2184,7 +2345,7 @@ and ConTeXt. LaTeX macros ------------ -**Extension: `latex_macros`** +#### Extension: `latex_macros` #### For output formats other than LaTeX, pandoc will parse LaTeX `\newcommand` and `\renewcommand` definitions and apply the resulting macros to all LaTeX @@ -2224,6 +2385,10 @@ be followed by a link title, in quotes.) There can be no space between the bracketed part and the parenthesized part. The link text can contain formatting (such as emphasis), but the title cannot. +Email addresses in inline links are not autodetected, so they have to be +prefixed with `mailto`: + + [Write me!](mailto:sam@green.eggs.ham) ### Reference links ### @@ -2276,7 +2441,7 @@ not in most other implementations: > > [quote]: /foo -### Internal links +### Internal links ### To link to another section of the same document, use the automatically generated identifier (see [Header identifiers in HTML, LaTeX, and @@ -2306,9 +2471,7 @@ The link text will be used as the image's alt text: [movie reel]: movie.gif -### Pictures with captions ### - -**Extension: `implicit_figures`** +#### Extension: `implicit_figures` #### An image occurring by itself in a paragraph will be rendered as a figure with a caption.[^5] (In LaTeX, a figure environment will be @@ -2332,7 +2495,7 @@ nonbreaking space after the image: Footnotes --------- -**Extension: `footnotes`** +#### Extension: `footnotes` #### Pandoc's markdown allows footnotes, using the following syntax: @@ -2363,7 +2526,7 @@ The footnotes themselves need not be placed at the end of the document. They may appear anywhere except inside other block elements (lists, block quotes, tables, etc.). -**Extension: `inline_notes`** +#### Extension: `inline_notes` #### Inline footnotes are also allowed (though, unlike regular notes, they cannot contain multiple paragraphs). The syntax is as follows: @@ -2378,7 +2541,7 @@ Inline and regular footnotes may be mixed freely. Citations --------- -**Extension: `citations`** +#### Extension: `citations` #### Using an external filter, `pandoc-citeproc`, pandoc can automatically generate citations and a bibliography in a number of styles. Basic usage is @@ -2443,7 +2606,9 @@ can be found at <https://github.com/citation-style-language/styles>. See also Citations go inside square brackets and are separated by semicolons. Each citation must have a key, composed of '@' + the citation identifier from the database, and may optionally have a prefix, -a locator, and a suffix. Here are some examples: +a locator, and a suffix. The citation key must begin with a letter +or `_`, and may contain alphanumerics, `_`, and internal punctuation +characters (`:.#$%&-+?<>~/`). Here are some examples: Blah blah [see @doe99, pp. 33-35; also @smith04, ch. 1]. @@ -2471,7 +2636,24 @@ document with an appropriate header: # References -The bibliography will be inserted after this header. +The bibliography will be inserted after this header. Note that +the `unnumbered` class will be added to this header, so that the +section will not be numbered. + +If you want to include items in the bibliography without actually +citing them in the body text, you can define a dummy `nocite` metadata +field and put the citations there: + + --- + nocite: | + @item1, @item2 + ... + + @item3 + +In this example, the document will contain a citation for `item3` +only, but the bibliography will contain entries for `item1`, `item2`, and +`item3`. Non-pandoc extensions --------------------- @@ -2481,37 +2663,44 @@ in pandoc, but may be enabled by adding `+EXTENSION` to the format name, where `EXTENSION` is the name of the extension. Thus, for example, `markdown+hard_line_breaks` is markdown with hard line breaks. -**Extension: `lists_without_preceding_blankline`**\ +#### Extension: `lists_without_preceding_blankline` #### + Allow a list to occur right after a paragraph, with no intervening blank space. -**Extension: `hard_line_breaks`**\ +#### Extension: `hard_line_breaks` #### + Causes all newlines within a paragraph to be interpreted as hard line breaks instead of spaces. -**Extension: `ignore_line_breaks`**\ +#### Extension: `ignore_line_breaks` #### + Causes newlines within a paragraph to be ignored, rather than being treated as spaces or as hard line breaks. This option is intended for use with East Asian languages where spaces are not used between words, but text is divided into lines for readability. -**Extension: `tex_math_single_backslash`**\ +#### Extension: `tex_math_single_backslash` #### + Causes anything between `\(` and `\)` to be interpreted as inline TeX math, and anything between `\[` and `\]` to be interpreted as display TeX math. Note: a drawback of this extension is that it precludes escaping `(` and `[`. -**Extension: `tex_math_double_backslash`**\ +#### Extension: `tex_math_double_backslash` #### + Causes anything between `\\(` and `\\)` to be interpreted as inline TeX math, and anything between `\\[` and `\\]` to be interpreted as display TeX math. -**Extension: `markdown_attribute`**\ +#### Extension: `markdown_attribute` #### + By default, pandoc interprets material inside block-level tags as markdown. This extension changes the behavior so that markdown is only parsed inside block-level tags if the tags have the attribute `markdown=1`. -**Extension: `mmd_title_block`**\ +#### Extension: `mmd_title_block` #### + Enables a [MultiMarkdown] style title block at the top of the document, for example: @@ -2527,7 +2716,8 @@ See the MultiMarkdown documentation for details. If `pandoc_title_block` or [MultiMarkdown]: http://fletcherpenney.net/multimarkdown/ -**Extension: `abbreviations`**\ +#### Extension: `abbreviations` #### + Parses PHP Markdown Extra abbreviation keys, like *[HTML]: Hyper Text Markup Language @@ -2536,24 +2726,55 @@ Note that the pandoc document model does not support abbreviations, so if this extension is enabled, abbreviation keys are simply skipped (as opposed to being parsed as paragraphs). -**Extension: `autolink_bare_uris`**\ +#### Extension: `autolink_bare_uris` #### + Makes all absolute URIs into links, even when not surrounded by pointy braces `<...>`. -**Extension: `ascii_identifiers`**\ +#### Extension: `ascii_identifiers` #### + Causes the identifiers produced by `auto_identifiers` to be pure ASCII. Accents are stripped off of accented latin letters, and non-latin letters are omitted. -**Extension: `link_attributes`**\ +#### Extension: `link_attributes` #### + Parses multimarkdown style key-value attributes on link and image references. Note that pandoc's internal document model provides nowhere to put these, so they are presently just ignored. -**Extension: `mmd_header_identifiers`**\ +#### Extension: `mmd_header_identifiers` #### + Parses multimarkdown style header identifiers (in square brackets, after the header but before any trailing `#`s in an ATX header). +#### Extension: `compact_definition_lists` #### + +Activates the definition list syntax of pandoc 1.12.x and earlier. +This syntax differs from the one described [above](#definition-lists) +in several respects: + + - No blank line is required between consecutive items of the + definition list. + - To get a "tight" or "compact" list, omit space between consecutive + items; the space between a term and its definition does not affect + anything. + - Lazy wrapping of paragraphs is not allowed: the entire definition must + be indented four spaces.[^6] + +[^6]: To see why laziness is incompatible with relaxing the requirement + of a blank line between items, consider the following example: + + bar + : definition + foo + : definition + + Is this a single list item with two definitions of "bar," the first of + which is lazily wrapped, or two list items? To remove the ambiguity + we must either disallow lazy wrapping or require a blank line between + list items. + Markdown variants ----------------- @@ -2567,7 +2788,7 @@ variants are supported: `markdown_github` (Github-flavored Markdown) : `pipe_tables`, `raw_html`, `tex_math_single_backslash`, - `fenced_code_blocks`, `fenced_code_attributes`, `auto_identifiers`, + `fenced_code_blocks`, `auto_identifiers`, `ascii_identifiers`, `backtick_code_blocks`, `autolink_bare_uris`, `intraword_underscores`, `strikeout`, `hard_line_breaks` @@ -2807,7 +3028,7 @@ block. Here is an example: - scheme: DOI text: doi:10.234234.234/33 publisher: My Press - rights: (c) 2007 John Smith, CC BY-NC + rights: © 2007 John Smith, CC BY-NC ... The following fields are recognized: @@ -2818,43 +3039,61 @@ The following fields are recognized: `GTIN-13`, `UPC`, `ISMN-10`, `DOI`, `LCCN`, `GTIN-14`, `ISBN-13`, `Legal deposit number`, `URN`, `OCLC`, `ISMN-13`, `ISBN-A`, `JP`, `OLCC`. + `title` ~ Either a string value, or an object with fields `file-as` and `type`, or a list of such objects. Valid values for `type` are `main`, `subtitle`, `short`, `collection`, `edition`, `extended`. + `creator` ~ Either a string value, or an object with fields `role`, `file-as`, and `text`, or a list of such objects. Valid values for `role` are [marc relators](http://www.loc.gov/marc/relators/relaterm.html), but pandoc will attempt to translate the human-readable versions (like "author" and "editor") to the appropriate marc relators. + `contributor` ~ Same format as `creator`. + `date` ~ A string value in `YYYY-MM-DD` format. (Only the year is necessary.) Pandoc will attempt to convert other common date formats. + `language` ~ A string value in [RFC5646] format. Pandoc will default to the local language if nothing is specified. + `subject` ~ A string value or a list of such values. + `description` ~ A string value. + `type` ~ A string value. + `format` ~ A string value. + `relation` ~ A string value. + `coverage` ~ A string value. + `rights` ~ A string value. + `cover-image` ~ A string value (path to cover image). + `stylesheet` ~ A string value (path to CSS stylesheet). +`page-progression-direction` + ~ Either `ltr` or `rtl`. Specifies the `page-progression-direction` + spine [attribute][EPUBspine]. + Literate Haskell support ======================== @@ -2931,7 +3170,8 @@ Nathan Gass, Jonathan Daugherty, Jérémy Bobbio, Justin Bogner, qerub, Christopher Sawicki, Kelsey Hightower, Masayoshi Takahashi, Antoine Latter, Ralf Stephan, Eric Seidel, B. Scott Michel, Gavin Beatty, Sergey Astanin, Arlo O'Keeffe, Denis Laxalde, Brent Yorgey, David Lazar, -Jamie F. Olson. +Jamie F. Olson, Matthew Pickering, Albert Krewinkel, mb21, Jesse +Rosenthal. [markdown]: http://daringfireball.net/projects/markdown/ [reStructuredText]: http://docutils.sourceforge.net/docs/ref/rst/introduction.html @@ -2951,13 +3191,14 @@ Jamie F. Olson. [ODT]: http://en.wikipedia.org/wiki/OpenDocument [Textile]: http://redcloth.org/textile [MediaWiki markup]: http://www.mediawiki.org/wiki/Help:Formatting +[DokuWiki markup]: https://www.dokuwiki.org/dokuwiki +[TWiki markup]: http://twiki.org/cgi-bin/view/TWiki/TextFormattingRules [Haddock markup]: http://www.haskell.org/haddock/doc/html/ch03s08.html [groff man]: http://developer.apple.com/DOCUMENTATION/Darwin/Reference/ManPages/man7/groff_man.7.html [Haskell]: http://www.haskell.org/ [GNU Texinfo]: http://www.gnu.org/software/texinfo/ [Emacs Org-Mode]: http://orgmode.org [AsciiDoc]: http://www.methods.co.nz/asciidoc/ -[EPUB]: http://www.idpf.org/ [GPL]: http://www.gnu.org/copyleft/gpl.html "GNU General Public License" [DZSlides]: http://paulrouget.com/dzslides/ [ISO 8601 format]: http://www.w3.org/TR/NOTE-datetime @@ -2968,3 +3209,8 @@ Jamie F. Olson. [lua]: http://www.lua.org [marc relators]: http://www.loc.gov/marc/relators/relaterm.html [RFC5646]: http://tools.ietf.org/html/rfc5646 +[InDesign ICML]: https://www.adobe.com/content/dam/Adobe/en/devnet/indesign/cs55-docs/IDML/idml-specification.pdf +[txt2tags]: http://txt2tags.org/ +[EPUB]: http://idpf.org/epub +[EPUBspine]: http://www.idpf.org/epub/301/spec/epub-publications.html#sec-spine-elem +[KaTeX]: https://github.com/Khan/KaTeX diff --git a/RELEASE-CHECKLIST b/RELEASE-CHECKLIST index af0102622..0663e3f3a 100644 --- a/RELEASE-CHECKLIST +++ b/RELEASE-CHECKLIST @@ -6,16 +6,12 @@ _ Tag release in git _ Tag templates -_ 'make sdist' to generate tarball +_ 'make dist' to generate tarball _ Generate Windows package and copy to directory. _ Generate Mac OSX package. -_ Upload to Google Code (googlecode-upload.sh) - -_ Go to Google code and deprecate the old versions - - Add release on github (and upload files) _ Upload to HackageDB @@ -24,9 +20,8 @@ _ Update website, including short description of changes _ Announce on pandoc-announce, pandoc-discuss -_ recompile trypandoc - -_ recompile pandoc-dingus +_ on server, 'cabal install --enable-tests -ftrypandoc' + and then 'cd trypandoc; sudo make install' _ recompile gitit @@ -1,66 +1,41 @@ -{-# LANGUAGE CPP #-} +{- +Copyright (C) 2006-2014 John MacFarlane <jgm@berkeley.edu> + +This program is free software; you can redistribute it and/or modify +it under the terms of the GNU General Public License as published by +the Free Software Foundation; either version 2 of the License, or +(at your option) any later version. + +This program is distributed in the hope that it will be useful, +but WITHOUT ANY WARRANTY; without even the implied warranty of +MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the +GNU General Public License for more details. + +You should have received a copy of the GNU General Public License +along with this program; if not, write to the Free Software +Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA +-} import Distribution.Simple import Distribution.Simple.PreProcess -import Distribution.Simple.Setup - (copyDest, copyVerbosity, fromFlag, installVerbosity, BuildFlags(..), - TestFlags(..)) import Distribution.PackageDescription (PackageDescription(..), Executable(..)) -import Distribution.Simple.LocalBuildInfo - (LocalBuildInfo(..), absoluteInstallDirs) -import Distribution.Verbosity ( Verbosity, silent ) -import Distribution.Simple.InstallDirs (mandir, CopyDest (NoCopyDest), toPathTemplate) -import Distribution.Simple.Utils (installOrdinaryFiles, info) -import Distribution.Simple.Test (test) -import Prelude hiding (catch) import System.Process ( rawSystem ) import System.FilePath ( (</>) ) import System.Directory ( findExecutable ) -import System.Exit +import Distribution.Simple.Utils (info) main :: IO () -main = do - defaultMainWithHooks $ simpleUserHooks { - postBuild = makeManPages - , testHook = \pkg lbi _ flags -> - -- pass build directory as first argument to test program - test pkg lbi flags{ testOptions = - toPathTemplate (buildDir lbi) : testOptions flags } - , postCopy = \ _ flags pkg lbi -> - installManpages pkg lbi (fromFlag $ copyVerbosity flags) - (fromFlag $ copyDest flags) - , postInst = \ _ flags pkg lbi -> - installManpages pkg lbi (fromFlag $ installVerbosity flags) NoCopyDest +main = defaultMainWithHooks $ simpleUserHooks { + -- enable hsb2hs preprocessor for .hsb files + hookedPreProcessors = [ppBlobSuffixHandler] + -- ensure that make-pandoc-man-pages doesn't get installed to bindir , copyHook = \pkgdescr -> (copyHook simpleUserHooks) pkgdescr{ executables = [x | x <- executables pkgdescr, exeName x /= "make-pandoc-man-pages"] } , instHook = \pkgdescr -> (instHook simpleUserHooks) pkgdescr{ executables = [x | x <- executables pkgdescr, exeName x /= "make-pandoc-man-pages"] } - , hookedPreProcessors = [ppBlobSuffixHandler] } - exitWith ExitSuccess - --- | Build man pages from markdown sources in man/ -makeManPages :: Args -> BuildFlags -> PackageDescription -> LocalBuildInfo -> IO () -makeManPages _ flags _ lbi = do - let verbosity = fromFlag $ buildVerbosity flags - let args = ["--verbose" | verbosity /= silent] - rawSystem (buildDir lbi </> "make-pandoc-man-pages" </> "make-pandoc-man-pages") - args >>= exitWith - -manpages :: [FilePath] -manpages = ["man1" </> "pandoc.1" - ,"man5" </> "pandoc_markdown.5"] - -manDir :: FilePath -manDir = "man" - -installManpages :: PackageDescription -> LocalBuildInfo - -> Verbosity -> CopyDest -> IO () -installManpages pkg lbi verbosity copy = - installOrdinaryFiles verbosity (mandir (absoluteInstallDirs pkg lbi copy)) - (zip (repeat manDir) manpages) ppBlobSuffixHandler :: PPSuffixHandler ppBlobSuffixHandler = ("hsb", \_ _ -> @@ -73,5 +48,4 @@ ppBlobSuffixHandler = ("hsb", \_ _ -> Just p -> rawSystem p [infile, infile, outfile] Nothing -> error "hsb2hs is needed to build this program: cabal install hsb2hs" return () - }) diff --git a/benchmark/benchmark-pandoc.hs b/benchmark/benchmark-pandoc.hs index 2eaaf91a1..bf67eaa4d 100644 --- a/benchmark/benchmark-pandoc.hs +++ b/benchmark/benchmark-pandoc.hs @@ -1,21 +1,37 @@ +{- +Copyright (C) 2012-2014 John MacFarlane <jgm@berkeley.edu> + +This program is free software; you can redistribute it and/or modify +it under the terms of the GNU General Public License as published by +the Free Software Foundation; either version 2 of the License, or +(at your option) any later version. + +This program is distributed in the hope that it will be useful, +but WITHOUT ANY WARRANTY; without even the implied warranty of +MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the +GNU General Public License for more details. + +You should have received a copy of the GNU General Public License +along with this program; if not, write to the Free Software +Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA +-} import Text.Pandoc import Criterion.Main import Criterion.Config import System.Environment (getArgs) import Data.Monoid +import Data.Maybe (mapMaybe) +import Debug.Trace (trace) readerBench :: Pandoc -> (String, ReaderOptions -> String -> IO Pandoc) - -> Benchmark -readerBench doc (name, reader) = - let writer = case lookup name writers of - Just (PureStringWriter w) -> w - _ -> error $ "Could not find writer for " ++ name - inp = writer def{ writerWrapText = True } doc - -- we compute the length to force full evaluation - getLength (Pandoc (Meta _) d) = length d - in bench (name ++ " reader") $ whnfIO $ getLength `fmap` - (reader def{ readerSmart = True }) inp + -> Maybe Benchmark +readerBench doc (name, reader) = case lookup name writers of + Just (PureStringWriter writer) -> + let inp = writer def{ writerWrapText = True} doc + in return $ bench (name ++ " reader") $ nfIO $ + (reader def{ readerSmart = True }) inp + _ -> trace ("\nCould not find writer for " ++ name ++ "\n") Nothing writerBench :: Pandoc -> (String, WriterOptions -> Pandoc -> String) @@ -26,14 +42,16 @@ writerBench doc (name, writer) = bench (name ++ " writer") $ nf main :: IO () main = do args <- getArgs - (conf,_) <- parseArgs defaultConfig{ cfgSamples = Last $ Just 20 } defaultOptions args - inp <- readFile "README" - inp2 <- readFile "tests/testsuite.txt" + (conf,_) <- parseArgs defaultConfig{ cfgSamples = Last $ Just 20 } + defaultOptions args + inp <- readFile "tests/testsuite.txt" let opts = def{ readerSmart = True } - let doc = readMarkdown opts $ inp ++ unlines (drop 3 $ lines inp2) - let readerBs = map (readerBench doc) - $ filter (\(n,_) -> n /="haddock") readers + let doc = readMarkdown opts inp + let readers' = [(n,r) | (n, StringReader r) <- readers] + let readerBs = mapMaybe (readerBench doc) + $ filter (\(n,_) -> n /="haddock") readers' let writers' = [(n,w) | (n, PureStringWriter w) <- writers] + let writerBs = map (writerBench doc) + $ writers' defaultMainWith conf (return ()) $ - map (writerBench doc) writers' ++ readerBs - + writerBs ++ readerBs @@ -1,3 +1,1053 @@ +pandoc (1.13.1) + + * Fixed `--self-contained` with Windows paths (#1558). + Previously `C:\foo.js` was being wrongly interpreted as a URI. + + * HTML reader: improved handling of tags that can be block or inline. + Previously a section like this would be enclosed in a paragraph, + with RawInline for the video tags (since video is a tag that can + be either block or inline): + + <video controls="controls"> + <source src="../videos/test.mp4" type="video/mp4" /> + <source src="../videos/test.webm" type="video/webm" /> + <p> + The videos can not be played back on your system.<br/> + Try viewing on Youtube (requires Internet connection): + <a href="http://youtu.be/etE5urBps_w">Relative Velocity on + Youtube</a>. + </p> + </video> + + This change will cause the video and source tags to be parsed + as RawBlock instead, giving better output. + The general change is this: when we're parsing a "plain" sequence + of inlines, we don't parse anything that COULD be a block-level tag. + + * Docx reader: + + + Be sensitive to user styles. Note that "Hyperlink" is + "blacklisted," as we don't want the default underline styling to be + inherited by all links by default (Jesse Rosenthal). + + Read single paragraph in table cell as `Plain` (Jesse Rosenthal). + This makes to docx reader's native output fit with the way the markdown + reader understands its markdown output. + + * Textile writer: Extended the range of cases where native textile + tables will be used (as opposed to raw HTML): we now handle any + alignment type, but only for simple tables with no captions. + + * Txt2Tags reader: + + + Header is now parsed only if standalone flag is set (Matthew Pickering). + + The header is now parsed as meta information. The first line is the + `title`, the second is the `author` and third line is the `date` + (Matthew Pickering). + + Corrected formatting of `%%mtime` macro (Matthew Pickering). + + Fixed crash when reading from stdin. + + * EPUB writer: Don't use page-progression-direction in EPUB2, which + doesn't support it. Also, if page-progression-direction not specified + in metadata, don't include the attribute even in EPUB3; not including it + is the same as including it with the value "default", as we did before. + (#1550) + + * Org writer: Accept example lines with indentation at the beginning + (Calvin Beck). + + * DokuWiki writer: + + + Refactor to use Reader monad (Matthew Pickering). + + Avoid using raw HTML in table cells; instead, use `\\` + instead of newlines (Jesse Rosenthal). + + Properly handle HTML table cell alignments, and use spacing + to make the tables look prettier (#1566). + + * Docx writer: + + + Bibliography entries get `Bibliography` style (#1559). + + Implement change tracking (Jesse Rosenthal). + + * LaTeX writer: + + + Fixed a bug that caused a table caption to repeat across all pages + (Jose Luis Duran). + + Improved vertical spacing in tables and made it customizable using + standard lengths set by booktab. See + <https://groups.google.com/forum/#!msg/pandoc-discuss/qMu6_5lYy0o/ZAU7lzAIKw0J> + (Jose Luis Duran). + + Added `\strut` to fix spacing in multiline tables (Jose Luis Duran). + + Use `\tabularnewline` instead of `\\` in table cells (Jose Luis Duran). + + Made horizontal rules more flexible (Jose Luis Duran). + + * Text.Pandoc.MIME: + + + Added `MimeType` (type synonym for `String`) and `getMimeTypeDef`. + Code cleanups (Artyom Kazak). + + * Templates: + + + LaTeX template: disable microtype protrusion for typewriter font (#1549, + thanks lemzwerg). + + * Improved OSX build procedure. + + * Added `network-uri` flag, to deal with split of `network-uri` from + `network`. + + * Fix build dependencies for the `trypandoc` flag, so that they are + ignored if `trypandoc` flag is set to False (Gabor Pali). + + * Updated README to remove outdated claim that `--self-contained` + looks in the user data directory for missing files. + +pandoc (1.13.0.1) + + * Docx writer: + + + Fixed regression which bungled list numbering (#1544), causing + all lists to appear as basic ordered lists. + + Include row width in table rows (Christoffer Ackelman, Viktor Kronvall). + Added a property to all table rows where the sum of column widths + is specified in pct (fraction of 5000). This helps persuade Word + to lay out the table with the widths we specify. + + * Fixed a bug in Windows 8 which caused pandoc not to find the + `pandoc-citeproc` filter (#1542). + + * Docx reader: miscellaneous under-the-hood improvements (Jesse Rosenthal). + Most significantly, the reader now uses Builder, leading to some + performance improvements. + + * HTML reader: Parse appropriately styled span as SmallCaps. + + * Markdown writer: don't escape `$`, `^`, `~` when `tex_math_dollars`, + `superscript`, and `subscript` extensions, respectively, are + deactivated (#1127). + + * Added `trypandoc` flag to build CGI executable used in the online + demo. + + * Makefile: Added 'quick', 'osxpkg' targets. + + * Updated README in templates to indicate templates license. + The templates are dual-licensed, BSD3 and GPL2+. + +pandoc (1.13) + + [new features] + + * Added `docx` as an input format (Jesse Rosenthal). The docx + reader includes conversion of native Word equations to pandoc + LaTeX `Math` elements. Metadata is taken from paragraphs at the + beginning of the document with styles `Author`, `Title`, `Subtitle`, + `Date`, and `Abstract`. + + * Added `epub` as an input format (Matthew Pickering). The epub + reader includes conversion of MathML to pandoc LaTeX `Math` + elements. + + * Added `t2t` (Txt2Tags) as an input format (Matthew Pickering). + Txt2tags is a lightweight markup format described at + <http://txt2tags.org/>. + + * Added `dokuwiki` as an output format (Clare Macrae). + + * Added `haddock` as an output format. + + * Added `--extract-media` option to extract media contained in a zip + container (docx or epub) while adjusting image paths to point to the + extracted images. + + * Added a new markdown extension, `compact_definition_lists`, that + restores the syntax for definition lists of pandoc 1.12.x, allowing + tight definition lists with no blank space between items, and + disallowing lazy wrapping. (See below under behavior changes.) + + * Added an extension `epub_html_exts` for parsing HTML in EPUBs. + + * Added extensions `native_spans` and `native_divs` to activate + parsing of material in HTML span or div tags as Pandoc Span + inlines or Div blocks. + + * `--trace` now works with the Markdown, HTML, Haddock, EPUB, + Textile, and MediaWiki readers. This is an option intended + for debugging parsing problems; ordinary users should not need + to use it. + + [behavior changes] + + * Changed behavior of the `markdown_attribute` extension, to bring + it in line with PHP markdown extra and multimarkdown. Setting + `markdown="1"` on an outer tag affects all contained tags, + recursively, until it is reversed with `markdown="0"` (#1378). + + * Revised markdown definition list syntax (#1429). Both the reader + and writer are affected. This change brings pandoc's definition list + syntax into alignment with that used in PHP markdown extra and + multimarkdown (with the exception that pandoc is more flexible about + the definition markers, allowing tildes as well as colons). Lazily + wrapped definitions are now allowed. Blank space is required + between list items. The space before a definition is used to determine + whether it is a paragraph or a "plain" element. **WARNING: This change + may break existing documents!** Either check your documents for + definition lists without blank space between items, or use + `markdown+compact_definition_lists` for the old behavior. + + * `.numberLines` now works in fenced code blocks even if no language + is given (#1287, jgm/highlighting-kate#40). + + * Improvements to `--filter`: + + + Don't search PATH for a filter with an explicit path. + This fixed a bug wherein `--filter ./caps.py` would run `caps.py` from + the system path, even if there was a `caps.py` in the working directory. + + Respect shebang if filter is executable (#1389). + + Don't print misleading error message. + Previously pandoc would say that a filter was not found, + even in a case where the filter had a syntax error. + + * HTML reader: + + + Parse `div` and `span` elements even without `--parse-raw`, + provided `native_divs` and `native_spans` extensions are set. + Motivation: these now generate native pandoc Div and Span + elements, not raw HTML. + + Parse EPUB-specific elements if the `epub_html_exts` + extension is enabled. These include `switch`, `footnote`, + `rearnote`, `noteref`. + + * Org reader: + + + Support for inline LaTeX. Inline LaTeX is now accepted and parsed by the + org-mode reader. Both math symbols (like `\tau`) and LaTeX commands (like + `\cite{Coffee}`), can be used without any further escaping (Albert + Krewinkel). + + * Textile reader and writer: + + + The `raw_tex` extension is no longer set by default. You can + enable it with `textile+raw_tex`. + + * DocBook reader: + + + Support `equation`, `informalequation`, `inlineequation` elements with + `mml:math` content. This is converted into LaTeX and put into a Pandoc + Math inline. + + * Revised `plain` output, largely following the style of Project + Gutenberg: + + + Emphasis is rendered with `_underscores_`, strong emphasis + with ALL CAPS. + + Headings are rendered differently, with space to set them off, + not with setext style underlines. Level 1 headers are ALL CAPS. + + Math is rendered using unicode when possible, but without the + distracting emphasis markers around variables. + + Footnotes use a regular `[n]` style. + + * Markdown writer: + + + Horizontal rules are now a line across the whole page. + + Prettier pipe tables. Columns are now aligned (#1323). + + Respect the `raw_html` extension. `pandoc -t markdown-raw_html` + no longer emits any raw HTML, including span and div tags + generated by Span and Div elements. + + Use span with style for `SmallCaps` (#1360). + + * HTML writer: + + + Autolinks now have class `uri`, and email autolinks have class + `email`, so they can be styled. + + * Docx writer: + + + Document formatting is carried over from `reference.docx`. + This includes margins, page size, page orientation, header, + and footer, including images in headers and footers. + + Include abstract (if present) with `Abstract` style (#1451). + + Include subtitle (if present) with `Subtitle` style, rather + than tacking it on to the title (#1451). + + * Org writer: + + + Write empty span elements with an id attribute as org anchors. + For example `Span ("uid",[],[]) []` becomes `<<uid>>`. + + * LaTeX writer: + + + Put table captions above tables, to match the conventional + standard. (Previously they appeared below tables.) + + Use `\(..\)` instead of `$..$` for inline math (#1464). + + Use `\nolinkurl` in email autolinks. This allows them to be styled + using `\urlstyle{tt}`. Thanks to Ulrike Fischer for the solution. + + Use `\textquotesingle` for `'` in inline code. Otherwise we get + curly quotes in the PDF output (#1364). + + Use `\footnote<.>{..}` for notes in beamer, so that footnotes + do not appear before the overlays in which their markers appear + (#1525). + + Don't produce a `\label{..}` for a Div or Span element. Do produce + a `\hyperdef{..}` (#1519). + + * EPUB writer: + + + If the metadata includes `page-progression-direction` (which can be + `ltr` or `rtl`, the `page-progression-direction` attribute will + be set in the EPUB spine (#1455). + + * Custom lua writers: + + + Custom writers now work with `--template`. + + Removed HTML header scaffolding from `sample.lua`. + + Made citation information available in lua writers. + + * `--normalize` and `Text.Pandoc.Shared.normalize` now consolidate + adjacent `RawBlock`s when possible. + + [API changes] + + * Added `Text.Pandoc.Readers.Docx`, exporting `readDocx` (Jesse Rosenthal). + + * Added `Text.Pandoc.Readers.EPUB`, exporting `readEPUB` (Matthew + Pickering). + + * Added `Text.Pandoc.Readers.Txt2Tags`, exporting `readTxt2Tags` (Matthew + Pickering). + + * Added `Text.Pandoc.Writers.DokuWiki`, exporting `writeDokuWiki` + (Clare Macrae). + + * Added `Text.Pandoc.Writers.Haddock`, exporting `writeHaddock`. + + * Added `Text.Pandoc.MediaBag`, exporting `MediaBag`, `lookupMedia`, + `insertMedia`, `mediaDirectory`, `extractMediaBag`. The docx and epub + readers return a pair of a `Pandoc` document and a `MediaBag` with + the media resources they contain. This can be extracted using + `--extract-media`. Writers that incorporate media (PDF, Docx, + ODT, EPUB, RTF, or HTML formats with `--self-contained`) will look + for resources in the `MediaBag` generated by the reader, in addition to + the file system or web. + + * `Text.Pandoc.Readers.TexMath`: Removed deprecated `readTeXMath`. + Renamed `readTeXMath'` to `texMathToInlines`. + + * `Text.Pandoc`: Added `Reader` data type (Matthew Pickering). + `readers` now associates names of readers with `Reader` + structures. This allows inclusion of readers, like the docx + reader, that take binary rather than textual input. + + * `Text.Pandoc.Shared`: + + + Added `capitalize` (Artyom Kazak), and replaced uses of + `map toUpper` (which give bad results for many languages). + + Added `collapseFilePath`, which removes intermediate `.` and + `..` from a path (Matthew Pickering). + + Added `fetchItem'`, which works like `fetchItem` but searches + a `MediaBag` before looking on the net or file system. + + Added `withTempDir`. + + Added `removeFormatting`. + + Added `extractSpaces` (from HTML reader) and generalized its type + so that it can be used by the docx reader (Matthew Pickering). + + Added `ordNub`. + + Added `normalizeInlines`, `normalizeBlocks`. + + `normalize` is now `Pandoc -> Pandoc` instead of + `Data a :: a -> a`. Some users may need to change their uses of + `normalize` to the newly exported `normalizeInlines` or + `normalizeBlocks`. + + * `Text.Pandoc.Options`: + + + Added `writerMediaBag` to `WriterOptions`. + + Removed deprecated and no longer used `readerStrict` in + `ReaderOptions`. This is handled by `readerExtensions` now. + + Added `Ext_compact_definition_lists`. + + Added `Ext_epub_html_exts`. + + Added `Ext_native_divs` and `Ext_native_spans`. + This allows users to turn off the default pandoc behavior of + parsing contents of div and span tags in markdown and HTML + as native pandoc Div blocks and Span inlines. + + * `Text.Pandoc.Parsing`: + + + Generalized `readWith` to `readWithM` (Matthew Pickering). + + Export `runParserT` and `Stream` (Matthew Pickering). + + Added `HasQuoteContext` type class (Matthew Pickering). + + Generalized types of `mathInline`, `smartPunctuation`, `quoted`, + `singleQuoted`, `doubleQuoted`, `failIfInQuoteContext`, + `applyMacros` (Matthew Pickering). + + Added custom `token` (Matthew Pickering). + + Added `stateInHtmlBlock` to `ParserState`. This is used to keep + track of the ending tag we're waiting for when we're parsing inside + HTML block tags. + + Added `stateMarkdownAttribute` to `ParserState`. This is used + to keep track of whether the markdown attribute has been set in + an enclosing tag. + + Generalized type of `registerHeader`, using new type classes + `HasReaderOptions`, `HasIdentifierList`, `HasHeaderMap` (Matthew + Pickering). These allow certain common functions to be reused + even in parsers that use custom state (instead of `ParserState`), + such as the MediaWiki reader. + + Moved `inlineMath`, `displayMath` from Markdown reader to Parsing, + and generalized their types (Matthew Pickering). + + * `Text.Pandoc.Pretty`: + + + Added `nestle`. + + Added `blanklines`, which guarantees a certain number of blank lines + (and no more). + + [bug fixes] + + * Markdown reader: + + + Fixed parsing of indented code in list items. Indented code + at the beginning of a list item must be indented eight spaces + from the margin (or edge of the container), or four spaces + from the list marker, whichever is greater. + + Fixed small bug in HTML parsing with `markdown_attribute`, which + caused incorrect tag nesting for input like + `<aside markdown="1">*hi*</aside>`. + + Fixed regression with intraword underscores (#1121). + + Improved parsing of inline links containing quote characters (#1534). + + Slight rewrite of `enclosure`/`emphOrStrong` code. + + Revamped raw HTML block parsing in markdown (#1330). + We no longer include trailing spaces and newlines in the + raw blocks. We look for closing tags for elements (but without + backtracking). Each block-level tag is its own `RawBlock`; + we no longer try to consolidate them (though `--normalize` will do so). + + Combine consecutive latex environments. This helps when you have + two minipages which can't have blank lines between them (#690, #1196). + + Support smallcaps through span. + `<span style="font-variant:small-caps;">foo</span>` will be + parsed as a `SmallCaps` inline, and will work in all output + formats that support small caps (#1360). + + Prevent spurious line breaks after list items (#1137). When the + `hard_line_breaks` option was specified, pandoc would formerly + produce a spurious line break after a tight list item. + + Fixed table parsing bug (#1333). + + Handle `c++` and `objective-c` as language identifiers in + github-style fenced blocks (#1318). + + Inline math must have nonspace before final `$` (#1313). + + * LaTeX reader: + + + Handle comments at the end of tables. This resolves the issue + illustrated in <http://stackoverflow.com/questions/24009489>. + + Correctly handle table rows with too few cells. LaTeX seems to + treat them as if they have empty cells at the end (#241). + + Handle leading/trailing spaces in `\emph` better. + `\emph{ hi }` gets parsed as `[Space, Emph [Str "hi"], Space]` + so that we don't get things like `* hi *` in markdown output. + Also applies to `\textbf` and some other constructions (#1146). + + Don't assume preamble doesn't contain environments (#1338). + + Allow (and discard) optional argument for `\caption` (James Aspnes). + + * HTML reader: + + + Fixed major parsing problem with HTML tables. Table cells were + being combined into one cell (#1341). + + Fixed performance issue with malformed HTML tables. + We let a `</table>` tag close an open `<tr>` or `<td>` (#1167). + + Allow space between `<col>` and `</col>`. + + Added `audio` and `source` in `eitherBlockOrInline`. + + Moved `video`, `svg`, `progress`, `script`, `noscript`, `svg` from + `blockTags` to `eitherBlockOrInline`. + + `map` and `object` were mistakenly in both lists; they have been removed + from `blockTags`. + + Ignore `DOCTYPE` and `xml` declarations. + + * MediaWiki reader: + + + Don't parse backslash escapes inside `<source>` (#1445). + + Tightened up template parsing. + The opening `{{` must be followed by an alphanumeric or `:`. + This prevents the exponential slowdown in #1033. + + Support "Bild" for images. + + * DocBook reader: + + + Better handle elements inside code environments. Pandoc's document + model does not allow structure inside code blocks, but at least this way + we preserve the text (#1449). + + Support `<?asciidoc-br?>` (#1236). + + * Textile reader: + + + Fixed list parsing. Lists can now start without an intervening + blank line (#1513). + + HTML block-level tags that do not start a line are parsed as + inline HTML and do not interrupt paragraphs (as in RedCloth). + + * Org reader: + + + Make tildes create inline code (#1345). Also relabeled `code` and + `verbatim` parsers to accord with the org-mode manual. + + Respect `:exports` header argument in code blocks (Craig Bosma). + + Fixed tight lists with sublists (#1437). + + * EPUB writer: + + + Avoid excess whitespace in `nav.xhtml`. This should improve + TOC view in iBooks (#1392). + + Fixed regression on cover image. + In 1.12.4 and 1.12.4.2, the cover image would not appear properly, + because the metadata id was not correct. Now we derive the id from the + actual cover image filename, which we preserve rather than using + "cover-image." + + Keep newlines between block elements. This allows + easier diff-ability (#1424). + + Use `stringify` instead of custom `plainify`. + + Use `renderTags'` for all tag rendering. This properly handles tags + that should be self-closing. Previously `<hr/>` would appear in EPUB + output as `<hr></hr>` (#1420). + + Better handle HTML media tags. + + Handle multiple dates with OPF `event` attributes. Note: in EPUB3 we + can have only one dc:date, so only the first one is used. + + * LaTeX writer: + + + Correctly handle figures in notes. Notes can't contain figures in + LaTeX, so we fake it to avoid an error (#1053). + + Fixed strikeout + highlighted code (#1294). + Previously strikeout highlighted code caused an error. + + * ConTeXt writer: + + + Improved detection of autolinks with URLs containing escapes. + + * RTF writer: + + + Improved image embedding: `fetchItem'` is now used to get the + images, and calculated image sizes are indicated in the RTF. + + Avoid extra paragraph tags in metadata (#1421). + + * HTML writer: + + + Deactivate "incremental" inside slide speaker notes (#1394). + + Don't include empty items in the table of contents for + slide shows. (These would result from creating a slide + using a horizontal rule.) + + * MediaWiki writer: + + + Minor renaming of `st` prefixed names. + + * AsciiDoc writer: + + + Double up emphasis and strong emphasis markers in intraword + contexts, as required by asciidoc (#1441). + + * Markdown writer: + + + Avoid wrapping that might start a list, blockquote, or header (#1013). + + Use Span instead of (hackish) `SmallCaps` in `plainify`. + + Don't use braced attributes for fenced code (#1416). + If `Ext_fenced_code_attributes` is not set, the first class + attribute will be printed after the opening fence as a bare word. + + Separate adjacent lists of the same kind with an HTML comment (#1458). + + * PDF writer: + + + Fixed treatment of data uris for images (#1062). + + * Docx writer: + + + Use Compact style for empty table cells (#1353). + Otherwise we get overly tall lines when there are empty + table cells and the other cells are compact. + + Create overrides per-image for `media/` in reference docx. + This should be somewhat more robust and cover more types of images. + + Improved `entryFromArchive` to avoid an unneeded parse. + + Section numbering carries over from reference.docx (#1305). + + Simplified `abstractNumId` numbering. Instead of sequential numbering, + we assign numbers based on the list marker styles. + + * `Text.Pandoc.Options`: + + + Removed `Ext_fenced_code_attributes` from `markdown_github` + extensions. + + * `Text.Pandoc.ImageSize`: + + + Use default instead of failing if image size not found + in exif header (#1358). + + ignore unknown exif header tag rather than crashing. + Some images seem to have tag type of 256, which was causing + a runtime error. + + * `Text.Pandoc.Shared`: + + + `fetchItem`: unescape URI encoding before reading local file (#1427). + + `fetchItem`: strip a fragment like `?#iefix` from the extension before + doing mime lookup, to improve mime type guessing. + + Improved logic of `fetchItem`: absolute URIs are fetched from the net; + other things are treated as relative URIs if `sourceURL` is `Just _`, + otherwise as file paths on the local file system. + + `fetchItem` now properly handles links without a protocol (#1477). + + `fetchItem` now escapes characters not allowed in URIs before trying + to parse the URIs. + + Fixed runtime error with `compactify'DL` on certain lists (#1452). + + * `pandoc.hs`: Don't strip path off of `writerSourceURL`: the path is + needed to resolve relative URLs when we fetch resources (#750). + + * `Text.Pandoc.Parsing` + + + Simplified `dash` and `ellipsis` (#1419). + + Removed `(>>~)` in favor of the equivalent `(<*)` (Matthew Pickering). + + Generalized functions to use `ParsecT` (Matthew Pickering). + + Added `isbn` and `pmid` to list of recognized schemes (Matthew + Pickering). + + [template changes] + + * Added haddock template. + * EPUB3: Added `type` attribute to `link` tags. They are supposed to + be "advisory" in HTML5, but kindlegen seems to require them. + * EPUB3: Put title page in section with `epub:type="titlepage"`. + * LaTeX: Made `\subtitle` work properly (#1327). + * LaTeX/Beamer: remove conditional around date (#1321). + * LaTeX: Added `lot` and `lof` variables, which can be set to + get `\listoftables` and `\listoffigures` (#1407). Note that + these variables can be set at the command line with `-Vlot -Vlof` + or in YAML metadata. + + [under the hood improvements] + + * Rewrote normalize for efficiency (#1385). + + * Rewrote Haddock reader to use `haddock-library` (#1346). + + + This brings pandoc's rendering of haddock markup in line + with the new haddock. + + Fixed line breaks in `@` code blocks. + + alex and happy are no longer build-depends. + + * Added `Text.Pandoc.Compat.Directory` to allow building against + different versions of the `directory` library. + + + Added `Text.Pandoc.Compat.Except` to allow building against + different verions of `mtl`. + + * Code cleanup in some writers, using Reader monad to avoid + passing options parameter around (Matej Kollar). + + * Improved readability in `pandoc.hs`. + + * Miscellaneous code cleanups (Artyom Kazak). + + * Avoid `import Prelude hiding (catch)` (#1309, thanks to Michael + Thompson). + + * Changed `http-conduit` flag to `https`. Depend on `http-client` + and `http-client-tls` instead of `http-conduit`. (Note: pandoc still + depends on `conduit` via `yaml`.) + + * Require `highlighting-kate >= 0.5.8.5` (#1271, #1317, Debian #753299). + This change to highlighting-kate means that PHP fragments no longer need + to start with `<?php`. It also fixes a serious bug causing failures with + ocaml and fsharp. + + * Require latest `texmath`. This fixes `\tilde{E}` and allows + `\left` to be used with `]`, `)` etc. (#1319), among many other + improvements. + + * Require latest `zip-archive`. This has fixes for unicode path names. + + * Added tests for plain writer. + + * `Text.Pandoc.Templates`: + + + Fail informatively on template syntax errors. + With the move from parsec to attoparsec, we lost good error + reporting. In fact, since we weren't testing for end of input, + malformed templates would fail silently. Here we revert back to + Parsec for better error messages. + + Use `ordNub` (#1022). + + * Benchmarks: + + + Made benchmarks compile again (Artyom Kazak). + + Fixed so that the failure of one benchmark does not prevent others + from running (Artyom Kazak). + + Use `nfIO` instead of the `getLength` trick to force full evaluation. + + Changed benchmark to use only the test suite, so that benchmarks + run more quickly. + + * Windows build script: + + + Add `-windows` to file name. + + Use one install command for pandoc, pandoc-citeproc. + + Force install of pandoc-citeproc. + + * `make_osx_package`: Call zip file `pandoc-VERSION-osx.zip`. + The zip should not be named `SOMETHING.pkg.zip`, or OSX finder + will extract it into a folder named `SOMETHING.pkg`, which it + will interpret as a defective package (#1308). + + * `README`: + + + Made headers for all extensions so they have IDs and can be + linked to (Beni Cherniavsky-Paskin). + + Fixed typos (Phillip Alday). + + Fixed documentation of attributes (#1315). + + Clarified documentation on small caps (#1360). + + Better documentation for `fenced_code_attributes` extension + (Caleb McDaniel). + + Documented fact that you can put YAML metadata in a separate file + (#1412). + + +pandoc (1.12.4.2) + + * Require highlighting-kate >= 0.5.8. Fixes a performance regression. + + * Shared: `addMetaValue` now behaves slightly differently: + if both the new and old values are lists, it concatenates their + contents to form a new list. + + * LaTeX reader: + + + Set `bibliography` in metadata from `\bibliography` or + `\addbibresource` command. + + Don't error on `%foo` with no trailing newline. + + * Org reader: + + + Support code block headers (`#+BEGIN_SRC ...`) (Albert Krewinkel). + + Fix parsing of blank lines within blocks (Albert Krewinkel). + + Support pandoc citation extension (Albert Krewinkel). This can + be turned off by specifying `org-citations` as the input format. + + * Markdown reader: + + + `citeKey` moved to `Text.Pandoc.Parsing` so it can be used by + other readers (Albert Krewinkel). + + * `Text.Pandoc.Parsing`: + + + Added `citeKey` (see above). + + Added `HasLastStrPosition` type class and `updateLastStrPos` + and `notAfterString` functions. + + * Updated copyright notices (Albert Krewinkel). + + * Added default.icml to data files so it installs with the package. + + * OSX package: + + + The binary is now built with options to ensure that it can be + used with OSX 10.6+. + + Moved OSX package materials to osx directory. + + Added OSX package uninstall script, included in the zip container + (thanks to Daniel T. Staal). + +pandoc (1.12.4) + + * Made it possible to run filters that aren't executable (#1096). + Pandoc first tries to find the executable (searching the path + if path isn't given). If it fails, but the file exists and has + a `.py`, `.pl`, `.rb`, `.hs`, or `.php` extension, pandoc runs the filter + using the appropriate interpreter. This should make it easier to + use filters on Windows, and make it more convenient for everyone. + + * Added Emacs org-mode reader (Albert Krewinkel). + + * Added InDesign ICML Writer (mb21). + + * MediaWiki reader: + + + Accept image links in more languages (Jaime Marquínez Ferrándiz). + + Fixed bug in certain nested lists (#1213). If a level 2 list was + followed by a level 1 list, the first item of the level 1 list + would be lost. + + Handle table rows containing just an HTML comment (#1230). + + * LaTeX reader: + + + Give better location information on errors, pointing to line + numbers within included files (#1274). + + LaTeX reader: Better handling of `table` environment (#1204). + Positioning options no longer rendered verbatim. + + Better handling of figure and table with caption (#1204). + + Handle `@{}` and `p{length}` in tabular. The length is not actually + recorded, but at least we get a table (#1180). + + Properly handle `\nocite`. It now adds a `nocite` metadata + field. Citations there will appear in the bibliography but not + in the text (unless you explicitly put a `$nocite$` variable + in your template). + + * Markdown reader: + + + Ensure that whole numbers in YAML metadata are rendered without + decimal points. (This became necessary with changes to aeson + and yaml libraries. aeson >= 0.7 and yaml >= 0.8.8.2 are now required.) + + Fixed regression on line breaks in strict mode (#1203). + + Small efficiency improvements. + + Improved parsing of nested `div`s. Formerly a closing `div` tag + would be missed if it came right after other block-level tags. + + Avoid backtracking when closing `</div>` not found. + + Fixed bug in reference link parsing in `markdown_mmd`. + + Fixed a bug in list parsing (#1154). When reading a raw list + item, we now strip off up to 4 spaces. + + Fixed parsing of empty reference link definitions (#1186). + + Made one-column pipe tables work (#1218). + + * Textile reader: + + + Better support for attributes. Instead of being ignored, attributes + are now parsed and included in Span inlines. The output will be a bit + different from stock textile: e.g. for `*(foo)hi*`, we'll get + `<em><span class="foo">hi</span></em>` instead of + `<em class="foo">hi</em>`. But at least the data is not lost. + + Improved treatment of HTML spans (%) (#1115). + + Improved link parsing. In particular we now pick up on attributes. + Since pandoc links can't have attributes, we enclose the whole link in + a span if there are attributes (#1008). + + Implemented correct parsing rules for inline markup (#1175, Matthew + Pickering). + + Use Builder (Matthew Pickering). + + Fixed list parsing bug (#1500). + + Don't allow inline formatting to extend over newlines. + This matches the behavior of RedCarpet, avoids some ugly bugs, + and improves performance. + + * DocBook reader: + + + Better treatment of `formalpara`. We now emit the title (if present) + as a separate paragraph with boldface text (#1215). + + Set metadata `author` not `authors`. + + Added recognition of `authorgroup` and `releaseinfo` elements (#1214, + Matthew Pickering). + + Converted current meta information parsing in DocBook to a more + extensible version which is aware of the more recent meta + representation (Matthew Pickering). + + * HTML reader: + + + Require tagsoup 0.13.1, to fix a bug with parsing of script tags + (#1248). + + Treat processing instructions & declarations as block. Previously + these were treated as inline, and included in paragraph tags in HTML + or DocBook output, which is generally not what is wanted (#1233). + + Updated `closes` with rules from HTML5 spec. + + Use Builder (Matthew Pickering, #1162). + + * RST reader: + + + Remove duplicate `http` in PEP links (Albert Krewinkel). + + Make rst figures true figures (#1168, CasperVector) + + Enhanced Pandoc's support for rST roles (Merijn Verstaaten). + rST parser now supports: all built-in rST roles, new role definition, + role inheritance, though with some limitations. + + Use `author` rather than `authors` in metadata. + + Better handling of directives. We now correctly handle field + lists that are indented more than three spaces. We treat an + `aafig` directive as a code block with attributes, so it can be + processed in a filter (#1212). + + * LaTeX writer: + + + Mark span contents with label if span has an ID (Albert Krewinkel). + + Made `--toc-depth` work well with books in latex/pdf output (#1210). + + Handle line breaks in simple table cells (#1217). + + Workaround for level 4-5 headers in quotes. These previously produced + invalid LaTeX: `\paragraph` or `\subparagraph` in a `quote` environment. + This adds an `mbox{}` in these contexts to work around the problem. + See <http://tex.stackexchange.com/a/169833/22451> (#1221). + + Use `\/` to avoid en-dash ligature instead of `-{}-` (Vaclav Zeman). + This is to fix LuaLaTeX output. The `-{}-` sequence does not avoid the + ligature with LuaLaTeX but `\/` does. + + Fixed string escaping in `hyperref` and `hyperdef` (#1130). + + * ConTeXt writer: Improved autolinks (#1270). + + * DocBook writer: + + + Improve handling of hard line breaks in Docbook writer + (Neil Mayhew). Use a `<literallayout>` for the entire paragraph, not + just for the newline character. + + Don't let line breaks inside footnotes influence the enclosing + paragraph (Neil Mayhew). + + Distinguish tight and loose lists in DocBook output, using + `spacing="compact"` (Neil Mayhew, #1250). + + * Docx writer: When needed files are not present in the user's + `reference.docx`, fall back on the versions in the `reference.docx` + in pandoc's data files. This fixes a bug that occurs when a + `reference.docx` saved by LibreOffice is used. (#1185) + + * EPUB writer: + + + Include extension in epub ids. This fixes a problem with duplicate + extensions for fonts and images with the same base name but different + extensions (#1254). + + Handle files linked in raw `img` tags (#1170). + + Handle media in `audio` source tags (#1170). + Note that we now use a `media` directory rather than `images`. + + Incorporate files linked in `video` tags (#1170). `src` and `poster` + will both be incorporated into `content.opf` and the epub container. + + * HTML writer: + + + Add colgroup around col tags (#877). Also affects EPUB writer. + + Fixed bug with unnumbered section headings. Unnumbered section + headings (with class `unnumbered`) were getting numbers. + + Improved detection of image links. Previously image links with + queries were not recognized, causing `<embed>` to be used instead + of `<img>`. + + * Man writer: Ensure that terms in definition lists aren't line wrapped + (#1195). + + * Markdown writer: + + + Use proper escapes to avoid unwanted lists (#980). Previously we used + 0-width spaces, an ugly hack. + + Use longer backtick fences if needed (#1206). If the content contains a + backtick fence and there are attributes, make sure longer fences are + used to delimit the code. Note: This works well in pandoc, but github + markdown is more limited, and will interpret the first string of three + or more backticks as ending the code block. + + * RST writer: Avoid stack overflow with certain tables (#1197). + + * RTF writer: Fixed table cells containing paragraphs. + + * Custom writer: + + + Correctly handle UTF-8 in custom lua scripts (#1189). + + Fix bugs with lua scripts with mixed-case filenames and + paths containing `+` or `-` (#1267). Note that `getWriter` + in `Text.Pandoc` no longer returns a custom writer on input + `foo.lua`. + + * AsciiDoc writer: Handle multiblock and empty table cells + (#1245, #1246). Added tests. + + * `Text.Pandoc.Options`: Added `readerTrace` to `ReaderOptions` + + * `Text.Pandoc.Shared`: + + + Added `compactify'DL` (formerly in markdown reader) (Albert Krewinkel). + + Fixed bug in `toRomanNumeral`: numbers ending with '9' would + be rendered as Roman numerals ending with 'IXIV' (#1249). Thanks to + Jesse Rosenthal. + + `openURL`: set proxy with value of http_proxy env variable (#1211). + Note: proxies with non-root paths are not supported, due to + limitations in `http-conduit`. + + * `Text.Pandoc.PDF`: + + + Ensure that temp directories deleted on Windows (#1192). The PDF is + now read as a strict bytestring, ensuring that process ownership will + be terminated, so the temp directory can be deleted. + + Use `/` as path separators in a few places, even on Windows. + This seems to be necessary for texlive (#1151, thanks to Tim Lin). + + Use `;` for `TEXINPUTS` separator on Windows (#1151). + + Changes to error reporting, to handle non-UTF8 error output. + + * `Text.Pandoc.Templates`: + + + Removed unneeded datatype context (Merijn Verstraaten). + + + YAML objects resolve to "true" in conditionals (#1133). + Note: If `address` is a YAML object and you just have `$address$` + in your template, the word `true` will appear, which may be + unexpected. (Previously nothing would appear.) + + * `Text.Pandoc.SelfContained`: + + + `mkSelfContained` now takes just two arguments, `WriterOptions` and + the string. + * It no longer looks in data files. This only made sense when we + had copies of slidy and S5 code there. + * `fetchItem'` is used instead of the nearly duplicate `getItem`. + + Handle `poster` attribute in `video` tags (#1188). + + * `Text.Pandoc.Parsing`: + + + Made `F` an instance of Applicative (#1138). + + Added `stateCaption`. + + Added `HasMacros`, simplified other typeclasses. + Removed `updateHeaderMap`, `setHeaderMap`, `getHeaderMap`, + `updateIdentifierList`, `setIdentifierList`, `getIdentifierList`. + + Changed the smart punctuation parser to return `Inlines` + rather than `Inline` (Matthew Pickering). + + Changed `HasReaderOptions`, `HasHeaderMap`, `HasIdentifierList` + from typeclasses of monads to typeclasses of states. This simplifies + the instance definitions and provides more flexibility. Generalized + type of `getOption` and added a default definition. Removed + `askReaderOption`. Added `extractReaderOption`. Added + `extractHeaderMap` and `updateHeaderMap` in `HasHeaderMap`. + Gave default definitions for `getHeaderMap`, `putHeaderMap`, + `modifyHeaderMap`. Added `extractIdentifierList` and + `updateIdentifierList` in `HasIdentifierList`. Gave defaults + for `getIdentifierList`, `putIdentifierList`, and + `modifyIdentifierList`. The ultimate goal here is to allow different + parsers to use their own, tailored parser states (instead of + `ParserState`) while still using shared functions. + + * Template changes: + + + LaTeX template: Use `fontenc` package only with `pdflatex` (#1164). + + LaTeX template: Add `linestretch` and `fontfamily` variables. + + LaTeX template: Conditionalize author and date commands. + + Beamer template: Consistent styles for figure and table captions + (aaronwolen). + + LaTeX and beamer template: Adjust widths correctly for oversized + images. Use `\setkeys{Gin}{}` to set appropriate defaults for + `\includegraphics` (Yihui Xie, Garrick Aden-Buie). Load + `upquote` only after `fontenc` (Yihui Xie). + + Beamer template: Added caption package (#1200). + + Beamer template: changes for better unicode handling (KarolS). + + DocBook template: use `authorgroup` if there are authors. + + revealjs template: Move `include-after` to end (certainlyakey). + + revealjs template: Fixed PDF print function (#1220, kevinkenan). + + * Bumped version bounds of dependencies. + + * Added a `--trace` command line option, for debugging backtracking + bugs. So far this only works with the markdown reader. + + * MathMLinHTML: Fixed deprecation warning (#362, gwern, Albert Krewinkel). + + * Updated travis script to test with multiple GHC versions. + + * Force failure of a Travis build if GHC produces warnings (Albert + Krewinkel). + + * Add `.editorconfig` (Albert Krewinkel). + See <http://editorconfig.org/> for details. + + * Give more useful error message if '-t pdf' is specified (#1155). + + * Added `Cite`, `SmallCaps` to `Arbitrary` instance (#1269). + + * Allow `html4` as a synonym of `html` as a reader (it already works + as a writer). + + * README: + + + Added an explanation of how to use YAML metadata to + force items to appear in the bibliography without citations in + the text (like LaTeX `\nocite`). + + Added note to `--bibtex/--natbib`: not for use in making PDF + (#1194, thanks to nahoj). + + Added explanatory notes about `--natbib` and `--biblatex`. + + Added specification of legal syntax for citation keys. + + Fixed variable defaults documentation (Albert Krewinkel). + + * Removed copyright statements for files that have been removed + (Albert Krewinkel). + + * Moved some doc files from `data-files` to `extra-source-files` (#1123). + They aren't needed at runtime. We keep README and COPYRIGHT in data + to ensure that they'll be available on all systems on which pandoc + is installed. + + * Use cabal sandboxes in Windows build script. + pandoc (1.12.3.3) * To changes to source; recompiled tarball with latest alex and @@ -53,7 +1103,7 @@ pandoc (1.12.3) * Added `Cite` function to `sample.lua`. * Markdown reader: - + + Fixed regression in title blocks (#1089). If author field was empty, date was being ignored. + Allow backslash-newline hard line breaks in grid and @@ -120,8 +1170,6 @@ pandoc (1.12.3) should again work, and take precedence over a stylesheet specified in the metadata. - * `Text.Pandoc.Pretty`: Added `nestle`. API change. - * `Text.Pandoc.MIME`: Added `wmf`, `emf`. * `Text.Pandoc.Shared`: `fetchItem` now handles image URLs beginning @@ -132,7 +1180,7 @@ pandoc (1.12.3) to squished images in Word documents. Closes #976. * Removed old `MarkdownTest_1.0.3` directory (#1104). - + pandoc (1.12.2.1) * Markdown reader: Fixed regression in list parser, involving @@ -264,7 +1312,7 @@ pandoc (1.12.2) * Slides: Preserve `<div class="references">` in references slide. * `Text.Pandoc.Writer.Shared`: - + + Fixed bug in `tagWithAttrs`. A space was omitted before key-value attributes, leading to invalid HTML. + `normalizeDate`: Allow dates with year only (thanks to Shaun Attfield). @@ -275,16 +1323,6 @@ pandoc (1.12.2) * DocBook reader: Handle numerical attributes starting with decimal. Also use `safeRead` instead of `read`. - * `Text.Pandoc.Parsing`: - - + Generalized type of `registerHeader`, using new type classes - `HasReadeOptions`, `HasIdentifierList`, `HasHeaderMap`. - These allow certain common functions to be reused - even in parsers that use custom state (instead of `ParserState`), - such as the MediaWiki reader. - + Moved inlineMath, displayMath from Markdown reader to Parsing. - Generalize their types and export them from Parsing. (API change.) - * `Text.Pandoc.Readers.TexMath`: Export `readTeXMath'`, which attends to display/inline. Deprecate `readTeXMath`, and use `readTeXMath'` in all the writers. Require `texmath >= 0.6.5.2`. @@ -303,7 +1341,7 @@ pandoc (1.12.2) over the values using `$for(foo)$`. This has the result that you can override earlier settings using `-V` by putting new values later on the command line, which is useful for many purposes. - + * `Text.Pandoc`: Don't default to `pandocExtensions` for all writers. * Allow "epub2" as synonym for "epub", "html4" for "html". @@ -664,7 +1702,7 @@ pandoc (1.12) * The `Text.Pandoc.Biblio` module has been removed. Users of the pandoc library who want citation support will need to use `Text.CSL.Pandoc` from `pandoc-citeproc`. - + [bug fixes] diff --git a/data/MathMLinHTML.js b/data/MathMLinHTML.js index ad718cf7e..2ab05c686 100644 --- a/data/MathMLinHTML.js +++ b/data/MathMLinHTML.js @@ -1,4 +1,4 @@ -/* +/* March 19, 2004 MathHTML (c) Peter Jipsen http://www.chapman.edu/~jipsen Released under the GNU General Public License version 2 or later. See the GNU General Public License (at http://www.gnu.org/copyleft/gpl.html) @@ -7,15 +7,15 @@ for more details. function convertMath(node) {// for Gecko if (node.nodeType==1) { - var newnode = + var newnode = document.createElementNS("http://www.w3.org/1998/Math/MathML", node.nodeName.toLowerCase()); for(var i=0; i < node.attributes.length; i++) newnode.setAttribute(node.attributes[i].nodeName, - node.attributes[i].nodeValue); + node.attributes[i].value); for (var i=0; i<node.childNodes.length; i++) { var st = node.childNodes[i].nodeValue; - if (st==null || st.slice(0,1)!=" " && st.slice(0,1)!="\n") + if (st==null || st.slice(0,1)!=" " && st.slice(0,1)!="\n") newnode.appendChild(convertMath(node.childNodes[i])); } return newnode; @@ -37,14 +37,14 @@ function convert() { if (st=="#text") str += node.nodeValue; else { str += (st.slice(0,1)=="/" ? "</m:"+st.slice(1) : "<m:"+st); - if (st.slice(0,1)!="/") + if (st.slice(0,1)!="/") for(var j=0; j < node.attributes.length; j++) - if (node.attributes[j].nodeValue!="italic" && - node.attributes[j].nodeValue!="" && - node.attributes[j].nodeValue!="inherit" && - node.attributes[j].nodeValue!=undefined) + if (node.attributes[j].value!="italic" && + node.attributes[j].value!="" && + node.attributes[j].value!="inherit" && + node.attributes[j].value!=undefined) str += " "+node.attributes[j].nodeName+"="+ - "\""+node.attributes[j].nodeValue+"\""; + "\""+node.attributes[j].value+"\""; str += ">"; } node = node.nextSibling; diff --git a/data/reference.docx b/data/reference.docx Binary files differindex a9c268b9f..0c717b3b6 100644 --- a/data/reference.docx +++ b/data/reference.docx diff --git a/data/sample.lua b/data/sample.lua index a0c3c29a2..f5c17839e 100644 --- a/data/sample.lua +++ b/data/sample.lua @@ -67,28 +67,15 @@ end -- This function is called once for the whole document. Parameters: -- body is a string, metadata is a table, variables is a table. --- One could use some kind of templating --- system here; this just gives you a simple standalone HTML file. +-- This gives you a fragment. You could use the metadata table to +-- fill variables in a custom lua template. Or, pass `--template=...` +-- to pandoc, and pandoc will add do the template processing as +-- usual. function Doc(body, metadata, variables) local buffer = {} local function add(s) table.insert(buffer, s) end - add('<!DOCTYPE html>') - add('<html>') - add('<head>') - add('<title>' .. (metadata['title'] or '') .. '</title>') - add('</head>') - add('<body>') - if metadata['title'] and metadata['title'] ~= "" then - add('<h1 class="title">' .. metadata['title'] .. '</h1>') - end - for _, author in pairs(metadata['author'] or {}) do - add('<h2 class="author">' .. author .. '</h2>') - end - if metadata['date'] and metadata['date'] ~= "" then - add('<h3 class="date">' .. metadata.date .. '</h3>') - end add(body) if #notes > 0 then add('<ol class="footnotes">') @@ -97,8 +84,6 @@ function Doc(body, metadata, variables) end add('</ol>') end - add('</body>') - add('</html>') return table.concat(buffer,'\n') end @@ -181,8 +166,13 @@ function Span(s, attr) return "<span" .. attributes(attr) .. ">" .. s .. "</span>" end -function Cite(s) - return "<span class=\"cite\">" .. s .. "</span>" +function Cite(s, cs) + local ids = {} + for _,cit in ipairs(cs) do + table.insert(ids, cit.citationId) + end + return "<span class=\"cite\" data-citation-ids=\"" .. table.concat(ids, ",") .. + "\">" .. s .. "</span>" end function Plain(s) diff --git a/data/templates b/data/templates -Subproject 50ca8c85d9abfb7918cb78015bcc6d6fec02ce7 +Subproject c76c6c52249118e49c5dd1b99fe916724350a59 diff --git a/lib/fonts/Makefile b/lib/fonts/Makefile new file mode 100644 index 000000000..5693ee054 --- /dev/null +++ b/lib/fonts/Makefile @@ -0,0 +1,6 @@ +symbol.hs: symbol.txt + runghc parseUnicodeMapping.hs symbol.txt + +.PHONY: clean +clean: + -rm symbol.hs diff --git a/lib/fonts/parseUnicodeMapping.hs b/lib/fonts/parseUnicodeMapping.hs new file mode 100644 index 000000000..4f7ff692b --- /dev/null +++ b/lib/fonts/parseUnicodeMapping.hs @@ -0,0 +1,40 @@ +import System.FilePath +import Text.Parsec +import Data.Char +import System.Environment +import Control.Applicative hiding (many) +import Data.List + +main :: IO () +main = (head <$> getArgs) >>= parseUnicodeMapping + + +parseUnicodeMapping :: FilePath -> IO () +parseUnicodeMapping fname = do + fin <- readFile fname + let mapname = dropExtension . takeFileName $ fname + let res = runParse fin + let header = "-- Generated from " ++ fname ++ "\n" ++ + mapname ++ " :: [(Char, Char)]\n" ++ mapname ++" =\n [ " + let footer = "]" + writeFile (replaceExtension fname ".hs") + (header ++ (concat $ intersperse "\n , " (map show res)) ++ footer) + +type Unicode = Char + +runParse :: String -> [(Char, Unicode)] +runParse s= either (error . show) id (parse parseMap "" s) + +anyline = manyTill anyChar newline + +getHexChar :: Parsec String () Char +getHexChar = do + [(c,_)] <- readLitChar . ("\\x" ++) <$> many1 hexDigit + return c + +parseMap :: Parsec String () [(Char, Unicode)] +parseMap = do + skipMany (char '#' >> anyline) + many (flip (,) <$> getHexChar <* tab <*> getHexChar <* anyline) + + diff --git a/lib/fonts/symbol.txt b/lib/fonts/symbol.txt new file mode 100644 index 000000000..b98baf6cf --- /dev/null +++ b/lib/fonts/symbol.txt @@ -0,0 +1,256 @@ +# +# Name: Adobe Symbol Encoding to Unicode +# Unicode version: 2.0 +# Table version: 1.0 +# Date: 2011 July 12 +# +# Copyright (c) 1991-2011 Unicode, Inc. All Rights reserved. +# +# This file is provided as-is by Unicode, Inc. (The Unicode Consortium). No +# claims are made as to fitness for any particular purpose. No warranties of +# any kind are expressed or implied. The recipient agrees to determine +# applicability of information provided. If this file has been provided on +# magnetic media by Unicode, Inc., the sole remedy for any claim will be +# exchange of defective media within 90 days of receipt. +# +# Unicode, Inc. hereby grants the right to freely use the information +# supplied in this file in the creation of products supporting the +# Unicode Standard, and to make copies of this file in any form for +# internal or external distribution as long as this notice remains +# attached. +# +# Format: 4 tab-delimited fields: +# +# (1) The Unicode value (in hexadecimal) +# (2) The Symbol Encoding code point (in hexadecimal) +# (3) # Unicode name +# (4) # PostScript character name +# +# General Notes: +# +# The Unicode values in this table were produced as the result of applying +# the algorithm described in the section "Populating a Unicode space" in the +# document "Unicode and Glyph Names," at +# http://partners.adobe.com/asn/developer/typeforum/unicodegn.html +# to the characters in Symbol. Note that some characters, such as "space", +# are mapped to 2 Unicode values. 29 characters have assignments in the +# Corporate Use Subarea; these are indicated by "(CUS)" in field 4. Refer to +# the above document for more details. +# +# 2011 July 12: The above link is no longer valid. For comparable, +# more current information, see the document, "Glyph", at: +# <http://www.adobe.com/devnet/opentype/archives/glyph.html> +# +# Revision History: +# +# [v1.0, 2011 July 12] +# Updated terms of use to current wording. +# Updated contact information and document link. +# No changes to the mapping data. +# +# [v0.2, 30 March 1999] +# Different algorithm to produce Unicode values (see notes above) results in +# some character codes being mapped to 2 Unicode values; use of Corporate +# Use subarea values; addition of the euro character; changed assignments of +# some characters such as the COPYRIGHT SIGNs and RADICAL EXTENDER. Updated +# Unicode names to Unicode 2.0 names. +# +# [v0.1, 5 May 1995] First release. +# +# Use the Unicode reporting form <http://www.unicode.org/reporting.html> +# for any questions or comments or to report errors in the data. +# +0020 20 # SPACE # space +00A0 20 # NO-BREAK SPACE # space +0021 21 # EXCLAMATION MARK # exclam +2200 22 # FOR ALL # universal +0023 23 # NUMBER SIGN # numbersign +2203 24 # THERE EXISTS # existential +0025 25 # PERCENT SIGN # percent +0026 26 # AMPERSAND # ampersand +220B 27 # CONTAINS AS MEMBER # suchthat +0028 28 # LEFT PARENTHESIS # parenleft +0029 29 # RIGHT PARENTHESIS # parenright +2217 2A # ASTERISK OPERATOR # asteriskmath +002B 2B # PLUS SIGN # plus +002C 2C # COMMA # comma +2212 2D # MINUS SIGN # minus +002E 2E # FULL STOP # period +002F 2F # SOLIDUS # slash +0030 30 # DIGIT ZERO # zero +0031 31 # DIGIT ONE # one +0032 32 # DIGIT TWO # two +0033 33 # DIGIT THREE # three +0034 34 # DIGIT FOUR # four +0035 35 # DIGIT FIVE # five +0036 36 # DIGIT SIX # six +0037 37 # DIGIT SEVEN # seven +0038 38 # DIGIT EIGHT # eight +0039 39 # DIGIT NINE # nine +003A 3A # COLON # colon +003B 3B # SEMICOLON # semicolon +003C 3C # LESS-THAN SIGN # less +003D 3D # EQUALS SIGN # equal +003E 3E # GREATER-THAN SIGN # greater +003F 3F # QUESTION MARK # question +2245 40 # APPROXIMATELY EQUAL TO # congruent +0391 41 # GREEK CAPITAL LETTER ALPHA # Alpha +0392 42 # GREEK CAPITAL LETTER BETA # Beta +03A7 43 # GREEK CAPITAL LETTER CHI # Chi +0394 44 # GREEK CAPITAL LETTER DELTA # Delta +2206 44 # INCREMENT # Delta +0395 45 # GREEK CAPITAL LETTER EPSILON # Epsilon +03A6 46 # GREEK CAPITAL LETTER PHI # Phi +0393 47 # GREEK CAPITAL LETTER GAMMA # Gamma +0397 48 # GREEK CAPITAL LETTER ETA # Eta +0399 49 # GREEK CAPITAL LETTER IOTA # Iota +03D1 4A # GREEK THETA SYMBOL # theta1 +039A 4B # GREEK CAPITAL LETTER KAPPA # Kappa +039B 4C # GREEK CAPITAL LETTER LAMDA # Lambda +039C 4D # GREEK CAPITAL LETTER MU # Mu +039D 4E # GREEK CAPITAL LETTER NU # Nu +039F 4F # GREEK CAPITAL LETTER OMICRON # Omicron +03A0 50 # GREEK CAPITAL LETTER PI # Pi +0398 51 # GREEK CAPITAL LETTER THETA # Theta +03A1 52 # GREEK CAPITAL LETTER RHO # Rho +03A3 53 # GREEK CAPITAL LETTER SIGMA # Sigma +03A4 54 # GREEK CAPITAL LETTER TAU # Tau +03A5 55 # GREEK CAPITAL LETTER UPSILON # Upsilon +03C2 56 # GREEK SMALL LETTER FINAL SIGMA # sigma1 +03A9 57 # GREEK CAPITAL LETTER OMEGA # Omega +2126 57 # OHM SIGN # Omega +039E 58 # GREEK CAPITAL LETTER XI # Xi +03A8 59 # GREEK CAPITAL LETTER PSI # Psi +0396 5A # GREEK CAPITAL LETTER ZETA # Zeta +005B 5B # LEFT SQUARE BRACKET # bracketleft +2234 5C # THEREFORE # therefore +005D 5D # RIGHT SQUARE BRACKET # bracketright +22A5 5E # UP TACK # perpendicular +005F 5F # LOW LINE # underscore +F8E5 60 # RADICAL EXTENDER # radicalex (CUS) +03B1 61 # GREEK SMALL LETTER ALPHA # alpha +03B2 62 # GREEK SMALL LETTER BETA # beta +03C7 63 # GREEK SMALL LETTER CHI # chi +03B4 64 # GREEK SMALL LETTER DELTA # delta +03B5 65 # GREEK SMALL LETTER EPSILON # epsilon +03C6 66 # GREEK SMALL LETTER PHI # phi +03B3 67 # GREEK SMALL LETTER GAMMA # gamma +03B7 68 # GREEK SMALL LETTER ETA # eta +03B9 69 # GREEK SMALL LETTER IOTA # iota +03D5 6A # GREEK PHI SYMBOL # phi1 +03BA 6B # GREEK SMALL LETTER KAPPA # kappa +03BB 6C # GREEK SMALL LETTER LAMDA # lambda +00B5 6D # MICRO SIGN # mu +03BC 6D # GREEK SMALL LETTER MU # mu +03BD 6E # GREEK SMALL LETTER NU # nu +03BF 6F # GREEK SMALL LETTER OMICRON # omicron +03C0 70 # GREEK SMALL LETTER PI # pi +03B8 71 # GREEK SMALL LETTER THETA # theta +03C1 72 # GREEK SMALL LETTER RHO # rho +03C3 73 # GREEK SMALL LETTER SIGMA # sigma +03C4 74 # GREEK SMALL LETTER TAU # tau +03C5 75 # GREEK SMALL LETTER UPSILON # upsilon +03D6 76 # GREEK PI SYMBOL # omega1 +03C9 77 # GREEK SMALL LETTER OMEGA # omega +03BE 78 # GREEK SMALL LETTER XI # xi +03C8 79 # GREEK SMALL LETTER PSI # psi +03B6 7A # GREEK SMALL LETTER ZETA # zeta +007B 7B # LEFT CURLY BRACKET # braceleft +007C 7C # VERTICAL LINE # bar +007D 7D # RIGHT CURLY BRACKET # braceright +223C 7E # TILDE OPERATOR # similar +20AC A0 # EURO SIGN # Euro +03D2 A1 # GREEK UPSILON WITH HOOK SYMBOL # Upsilon1 +2032 A2 # PRIME # minute +2264 A3 # LESS-THAN OR EQUAL TO # lessequal +2044 A4 # FRACTION SLASH # fraction +2215 A4 # DIVISION SLASH # fraction +221E A5 # INFINITY # infinity +0192 A6 # LATIN SMALL LETTER F WITH HOOK # florin +2663 A7 # BLACK CLUB SUIT # club +2666 A8 # BLACK DIAMOND SUIT # diamond +2665 A9 # BLACK HEART SUIT # heart +2660 AA # BLACK SPADE SUIT # spade +2194 AB # LEFT RIGHT ARROW # arrowboth +2190 AC # LEFTWARDS ARROW # arrowleft +2191 AD # UPWARDS ARROW # arrowup +2192 AE # RIGHTWARDS ARROW # arrowright +2193 AF # DOWNWARDS ARROW # arrowdown +00B0 B0 # DEGREE SIGN # degree +00B1 B1 # PLUS-MINUS SIGN # plusminus +2033 B2 # DOUBLE PRIME # second +2265 B3 # GREATER-THAN OR EQUAL TO # greaterequal +00D7 B4 # MULTIPLICATION SIGN # multiply +221D B5 # PROPORTIONAL TO # proportional +2202 B6 # PARTIAL DIFFERENTIAL # partialdiff +2022 B7 # BULLET # bullet +00F7 B8 # DIVISION SIGN # divide +2260 B9 # NOT EQUAL TO # notequal +2261 BA # IDENTICAL TO # equivalence +2248 BB # ALMOST EQUAL TO # approxequal +2026 BC # HORIZONTAL ELLIPSIS # ellipsis +F8E6 BD # VERTICAL ARROW EXTENDER # arrowvertex (CUS) +F8E7 BE # HORIZONTAL ARROW EXTENDER # arrowhorizex (CUS) +21B5 BF # DOWNWARDS ARROW WITH CORNER LEFTWARDS # carriagereturn +2135 C0 # ALEF SYMBOL # aleph +2111 C1 # BLACK-LETTER CAPITAL I # Ifraktur +211C C2 # BLACK-LETTER CAPITAL R # Rfraktur +2118 C3 # SCRIPT CAPITAL P # weierstrass +2297 C4 # CIRCLED TIMES # circlemultiply +2295 C5 # CIRCLED PLUS # circleplus +2205 C6 # EMPTY SET # emptyset +2229 C7 # INTERSECTION # intersection +222A C8 # UNION # union +2283 C9 # SUPERSET OF # propersuperset +2287 CA # SUPERSET OF OR EQUAL TO # reflexsuperset +2284 CB # NOT A SUBSET OF # notsubset +2282 CC # SUBSET OF # propersubset +2286 CD # SUBSET OF OR EQUAL TO # reflexsubset +2208 CE # ELEMENT OF # element +2209 CF # NOT AN ELEMENT OF # notelement +2220 D0 # ANGLE # angle +2207 D1 # NABLA # gradient +F6DA D2 # REGISTERED SIGN SERIF # registerserif (CUS) +F6D9 D3 # COPYRIGHT SIGN SERIF # copyrightserif (CUS) +F6DB D4 # TRADE MARK SIGN SERIF # trademarkserif (CUS) +220F D5 # N-ARY PRODUCT # product +221A D6 # SQUARE ROOT # radical +22C5 D7 # DOT OPERATOR # dotmath +00AC D8 # NOT SIGN # logicalnot +2227 D9 # LOGICAL AND # logicaland +2228 DA # LOGICAL OR # logicalor +21D4 DB # LEFT RIGHT DOUBLE ARROW # arrowdblboth +21D0 DC # LEFTWARDS DOUBLE ARROW # arrowdblleft +21D1 DD # UPWARDS DOUBLE ARROW # arrowdblup +21D2 DE # RIGHTWARDS DOUBLE ARROW # arrowdblright +21D3 DF # DOWNWARDS DOUBLE ARROW # arrowdbldown +25CA E0 # LOZENGE # lozenge +2329 E1 # LEFT-POINTING ANGLE BRACKET # angleleft +F8E8 E2 # REGISTERED SIGN SANS SERIF # registersans (CUS) +F8E9 E3 # COPYRIGHT SIGN SANS SERIF # copyrightsans (CUS) +F8EA E4 # TRADE MARK SIGN SANS SERIF # trademarksans (CUS) +2211 E5 # N-ARY SUMMATION # summation +F8EB E6 # LEFT PAREN TOP # parenlefttp (CUS) +F8EC E7 # LEFT PAREN EXTENDER # parenleftex (CUS) +F8ED E8 # LEFT PAREN BOTTOM # parenleftbt (CUS) +F8EE E9 # LEFT SQUARE BRACKET TOP # bracketlefttp (CUS) +F8EF EA # LEFT SQUARE BRACKET EXTENDER # bracketleftex (CUS) +F8F0 EB # LEFT SQUARE BRACKET BOTTOM # bracketleftbt (CUS) +F8F1 EC # LEFT CURLY BRACKET TOP # bracelefttp (CUS) +F8F2 ED # LEFT CURLY BRACKET MID # braceleftmid (CUS) +F8F3 EE # LEFT CURLY BRACKET BOTTOM # braceleftbt (CUS) +F8F4 EF # CURLY BRACKET EXTENDER # braceex (CUS) +232A F1 # RIGHT-POINTING ANGLE BRACKET # angleright +222B F2 # INTEGRAL # integral +2320 F3 # TOP HALF INTEGRAL # integraltp +F8F5 F4 # INTEGRAL EXTENDER # integralex (CUS) +2321 F5 # BOTTOM HALF INTEGRAL # integralbt +F8F6 F6 # RIGHT PAREN TOP # parenrighttp (CUS) +F8F7 F7 # RIGHT PAREN EXTENDER # parenrightex (CUS) +F8F8 F8 # RIGHT PAREN BOTTOM # parenrightbt (CUS) +F8F9 F9 # RIGHT SQUARE BRACKET TOP # bracketrighttp (CUS) +F8FA FA # RIGHT SQUARE BRACKET EXTENDER # bracketrightex (CUS) +F8FB FB # RIGHT SQUARE BRACKET BOTTOM # bracketrightbt (CUS) +F8FC FC # RIGHT CURLY BRACKET TOP # bracerighttp (CUS) +F8FD FD # RIGHT CURLY BRACKET MID # bracerightmid (CUS) +F8FE FE # RIGHT CURLY BRACKET BOTTOM # bracerightbt (CUS) diff --git a/make_osx_package.sh b/make_osx_package.sh index 6c943c84a..6030f7032 100755 --- a/make_osx_package.sh +++ b/make_osx_package.sh @@ -5,80 +5,63 @@ SANDBOX=`pwd`/.cabal-sandbox VERSION=$(grep -e '^Version' pandoc.cabal | awk '{print $2}') RESOURCES=$DIST/Resources ROOT=$DIST/pandoc +MANDIR=`pwd`/man DEST=$ROOT/usr/local -SCRIPTS=osx-resources +OSX=osx +SCRIPTS=$OSX/osx-resources BASE=pandoc-$VERSION ME=$(whoami) -CODESIGNID="Developer ID Application: John Macfarlane" PACKAGEMAKER=/Applications/PackageMaker.app/Contents/MacOS/PackageMaker -EXES="pandoc pandoc-citeproc" +CPPHS=$SANDBOX/bin/cpphs -read -s -p "sudo password: " PASSWORD -echo $PASSWORD | sudo -S echo "Password valid, continuing." - -echo Removing old files... +# echo Removing old files... rm -rf $DIST mkdir -p $RESOURCES +cabal sandbox init echo Updating database cabal update echo Building pandoc... -cabal sandbox init cabal clean -cabal install --reinstall --flags="embed_data_files" -cabal install --reinstall --flags="embed_data_files" pandoc-citeproc +# Use cpphs to avoid problems with clang cpp on ghc 7.8 osx: +cabal install cpphs hsb2hs +cabal install --ghc-options="-optl-mmacosx-version-min=10.6" --reinstall --flags="embed_data_files make-pandoc-man-pages" --ghc-options "-pgmP$CPPHS -optP--cpp" . pandoc-citeproc + +make man +# get pandoc-citeproc man page: +PANDOC_CITEPROC_PATH=`cabal unpack -d $DIST pandoc-citeproc | awk '{print $3;}'` +cp $PANDOC_CITEPROC_PATH/man/man1/pandoc-citeproc.1 $MANDIR/man1/ mkdir -p $DEST/bin mkdir -p $DEST/share/man/man1 mkdir -p $DEST/share/man/man5 -for f in $EXES; do +for f in pandoc pandoc-citeproc; do cp $SANDBOX/bin/$f $DEST/bin/; - cp $SANDBOX/share/man/man1/$f.1 $DEST/share/man/man1/ + cp $MANDIR/man1/$f.1 $DEST/share/man/man1/ done -cp $SANDBOX/share/man/man5/pandoc_markdown.5 $DEST/share/man/man5/ +cp $MANDIR/man5/pandoc_markdown.5 $DEST/share/man/man5/ chown -R $ME:staff $DIST -# gzip $DEST/share/man/man?/*.* -# cabal gives man pages the wrong permissions -chmod +r $DEST/share/man/man?/*.* echo Copying license... -$SANDBOX/bin/pandoc --data data -t rtf -s COPYING -o $RESOURCES/License.rtf +$SANDBOX/bin/pandoc --data data -t html5 -s COPYING -o $RESOURCES/license.html echo Signing pandoc executable... -codesign --force --sign "$CODESIGNID" $DEST/bin/pandoc +codesign --force --sign "Developer ID Application: John Macfarlane" $DEST/bin/pandoc # make sure it's valid... returns nonzero exit code if it isn't: spctl --assess --type execute $DEST/bin/pandoc echo Creating OSX package... # remove old package first -echo $PASSWORD | sudo -S rm -rf $BASE.pkg $BASE.dmg - -sudo $PACKAGEMAKER \ - --root $ROOT \ - --id net.johnmacfarlane.pandoc \ - --resources $RESOURCES \ - --version $VERSION \ - --scripts $SCRIPTS \ - --out $BASE.pkg - - # --no-relocate - -echo Signing package... - -sudo codesign --force --sign "$CODESIGNID" $BASE.pkg -# make sure it's valid... -spctl --assess --type install $BASE.pkg +rm -rf $BASE.pkg -echo Creating zip... -zip -9 -r $BASE.pkg.zip $BASE.pkg +pkgbuild --root $DIST/pandoc --identifier net.johnmacfarlane.pandoc --version 1.13 --ownership recommended $DIST/pandoc.pkg +productbuild --distribution osx/distribution.xml --resources $DIST/Resources --package-path $DIST --version 1.13 --sign "Developer ID Installer: John Macfarlane" $BASE-osx.pkg -# echo Creating disk image... -# sudo hdiutil create "$BASE.dmg" \ -# -format UDZO -ov \ -# -volname "pandoc $VERSION" \ -# -srcfolder $BASE.pkg -# sudo hdiutil internet-enable "$BASE.dmg" +# verify signature +spctl --assess --type install $BASE-osx.pkg +# cleanup +rm -r $DIST diff --git a/man/make-pandoc-man-pages.hs b/man/make-pandoc-man-pages.hs index 008294433..65178a15b 100644 --- a/man/make-pandoc-man-pages.hs +++ b/man/make-pandoc-man-pages.hs @@ -27,7 +27,7 @@ main = do unless (null ds1 && null ds2) $ do rmContents <- UTF8.readFile "README" - let (Pandoc meta blocks) = readMarkdown def rmContents + let (Pandoc meta blocks) = normalize $ readMarkdown def rmContents let manBlocks = removeSect [Str "Wrappers"] $ removeSect [Str "Pandoc's",Space,Str "markdown"] blocks let syntaxBlocks = extractSect [Str "Pandoc's",Space,Str "markdown"] blocks @@ -47,8 +47,10 @@ makeManPage verbose page meta blocks = do writeManPage :: FilePath -> String -> Pandoc -> IO () writeManPage page templ doc = do + let version = pandocVersion let opts = def{ writerStandalone = True - , writerTemplate = templ } + , writerTemplate = templ + , writerVariables = [("version",version)] } let manPage = writeMan opts $ bottomUp (concatMap removeLinks) $ bottomUp capitalizeHeaders doc @@ -67,13 +69,13 @@ capitalize (Str xs) = Str $ map toUpper xs capitalize x = x removeSect :: [Inline] -> [Block] -> [Block] -removeSect ils (Header 1 _ x:xs) | normalize x == normalize ils = +removeSect ils (Header 1 _ x:xs) | x == ils = dropWhile (not . isHeader1) xs removeSect ils (x:xs) = x : removeSect ils xs removeSect _ [] = [] extractSect :: [Inline] -> [Block] -> [Block] -extractSect ils (Header 1 _ z:xs) | normalize z == normalize ils = +extractSect ils (Header 1 _ z:xs) | z == ils = bottomUp promoteHeader $ takeWhile (not . isHeader1) xs where promoteHeader (Header n attr x) = Header (n-1) attr x promoteHeader x = x diff --git a/man/man1/pandoc.1.template b/man/man1/pandoc.1.template index 167d6ed8c..00e7675e7 100644 --- a/man/man1/pandoc.1.template +++ b/man/man1/pandoc.1.template @@ -1,7 +1,7 @@ $if(has-tables)$ .\"t $endif$ -.TH PANDOC 1 "$date$" "$title$" +.TH PANDOC 1 "$date$" "$version$" .SH NAME pandoc - general markup converter $body$ diff --git a/man/man5/pandoc_markdown.5.template b/man/man5/pandoc_markdown.5.template index f775a4683..6006e90c4 100644 --- a/man/man5/pandoc_markdown.5.template +++ b/man/man5/pandoc_markdown.5.template @@ -1,7 +1,7 @@ $if(has-tables)$ .\"t $endif$ -.TH PANDOC_MARKDOWN 5 "$date$" "$title$" +.TH PANDOC_MARKDOWN 5 "$date$" "$version$" .SH NAME pandoc_markdown - markdown syntax for pandoc(1) .SH DESCRIPTION diff --git a/osx-resources/InstallationCheck b/osx-resources/InstallationCheck deleted file mode 100755 index 2bd691f5c..000000000 --- a/osx-resources/InstallationCheck +++ /dev/null @@ -1,14 +0,0 @@ -#!/bin/sh -cputype=`/usr/sbin/sysctl -n hw.cputype` -sixtyfourbit=`/usr/sbin/sysctl -n hw.cpu64bit_capable` - -if [ "x$cputype" != "x7" ] # x86 -then - exit 112 -fi - -if [ "x$sixtyfourbit" != "x1" ] # 64 bit -then - exit 113 -fi - diff --git a/osx-resources/InstallationCheck.strings b/osx-resources/InstallationCheck.strings deleted file mode 100644 index 6c8efe0d4..000000000 --- a/osx-resources/InstallationCheck.strings +++ /dev/null @@ -1,3 +0,0 @@ -"16" = "This installer works only on Intel Macs."; -"17" = "This installer requires a 64-bit processor."; - diff --git a/osx/distribution.xml b/osx/distribution.xml new file mode 100644 index 000000000..024a25bd1 --- /dev/null +++ b/osx/distribution.xml @@ -0,0 +1,30 @@ +<?xml version="1.0" encoding="utf-8" standalone="no"?> +<installer-gui-script minSpecVersion="1"> + <title>pandoc</title> + <organization>net.johnmacfarlane.pandoc</organization> + <domains enable_localSystem="true"/> + <options customize="never" require-scripts="true" rootVolumeOnly="true" /> + <!-- Define documents displayed at various steps --> + <!-- <welcome file="welcome.html" mime-type="text/html" /> --> + <license file="license.html" mime-type="text/html" /> + <!-- <conclusion file="conclusion.html" mime-type="text/html" /> --> + <options hostArchitectures="x86_64" /> + <!-- List all component packages --> + <pkg-ref id="net.johnmacfarlane.pandoc" + version="1.13" + auth="root">pandoc.pkg</pkg-ref> + <!-- List them again here. They can now be organized + as a hierarchy if you want. --> + <choices-outline> + <line choice="net.johnmacfarlane.pandoc"/> + </choices-outline> + <!-- Define each choice above --> + <choice + id="net.johnmacfarlane.pandoc" + visible="false" + title="pandoc" + description="pandoc - universal text converter" + start_selected="true"> + <pkg-ref id="net.johnmacfarlane.pandoc"/> + </choice> +</installer-gui-script> diff --git a/osx/uninstall-pandoc.pl b/osx/uninstall-pandoc.pl new file mode 100755 index 000000000..a5194d9bd --- /dev/null +++ b/osx/uninstall-pandoc.pl @@ -0,0 +1,79 @@ +#!/usr/bin/perl + +# Script to remove all files installed by the OSX pandoc installer +# and unregister the package. Modified from a script contributed +# by Daniel T. Staal. + +use warnings; +use strict; + +use File::Spec; + +# The main info: this is the list of files to remove and the pkg_id. +my $pkg_id = 'net.johnmacfarlane.pandoc'; + +# Find which, if any, volume Pandoc is installed on. +my $volume; + +# First check /, then other volumes on the box. +my $cur_test = `pkgutil --pkgs=$pkg_id`; +if ( $cur_test =~ m/$pkg_id/ ) { + $volume = '/'; +} else { + opendir( my $dh, '/Volumes' ) or die "Can't list Volumes: $!\n"; + foreach my $dir ( readdir($dh) ) { + next if $dir =~ m/^\./; # Skip dotfiles. + + my $path = File::Spec->rel2abs( $dir, '/Volumes' ); + next if !( -d $path ); # Skip anything that isn't a directory. + + my $cur_test = `pkgutil --pkgs=$pkg_id --volume '$path'`; + if ( $cur_test =~ m/$pkg_id/ ) { + $volume = $path; + last; + } + } +} + +die "Pandoc not installed.\n" if !( defined($volume) ); + +# Get the list of files to remove. +my @pkg_files = `pkgutil --volume '$volume' --only-files --files '$pkg_id'`; +@pkg_files = map { chomp; File::Spec->rel2abs($_, $volume) } @pkg_files; + +# Confirm uninistall with the user. +print "The following files will be deleted:\n\n"; +print join("\n", @pkg_files); +print "\n\n"; +print "Do you want to proceed and uninstall pandoc (Y/N)?"; +my $input = <STDIN>; + +if ($input =~ m/^[Yy]/) { + + # Actually remove the files. + foreach my $file (@pkg_files) { + if ( -e $file ) { + if ( system( 'sudo', 'rm', $file ) == 0 ) { + warn "Deleted $file\n"; + } else { + warn "Unable to delete $file: $?\n"; + die "Aborting Uninstall.\n"; + } + } else { + warn "File $file does not exist. Skipping.\n"; + } + } + + # Clean up the install. + if (system('sudo', 'pkgutil', '--forget', $pkg_id, '--volume', $volume) != 0) { + die "Unable to clean up install: $?\n"; + } + +} else { + + print "OK, aborting uninstall.\n"; + exit; +} + +print "Pandoc has been successfully uninstalled.\n"; +exit; diff --git a/pandoc.cabal b/pandoc.cabal index b99eb5420..6abc8b0bc 100644 --- a/pandoc.cabal +++ b/pandoc.cabal @@ -1,29 +1,30 @@ Name: pandoc -Version: 1.12.3.3 +Version: 1.13.2 Cabal-Version: >= 1.10 Build-Type: Custom License: GPL License-File: COPYING -Copyright: (c) 2006-2013 John MacFarlane +Copyright: (c) 2006-2014 John MacFarlane Author: John MacFarlane <jgm@berkeley.edu> Maintainer: John MacFarlane <jgm@berkeley.edu> Bug-Reports: https://github.com/jgm/pandoc/issues Stability: alpha Homepage: http://johnmacfarlane.net/pandoc Category: Text -Tested-With: GHC == 7.4.2, GHC == 7.6.1 +Tested-With: GHC == 7.4.2, GHC == 7.6.3, GHC == 7.8.2 Synopsis: Conversion between markup formats Description: Pandoc is a Haskell library for converting from one markup format to another, and a command-line tool that uses this library. It can read markdown and (subsets of) HTML, - reStructuredText, LaTeX, DocBook, MediaWiki markup, Haddock - markup, OPML, and Textile, and it can write markdown, - reStructuredText, HTML, LaTeX, ConTeXt, Docbook, OPML, - OpenDocument, ODT, Word docx, RTF, MediaWiki, Textile, - groff man pages, plain text, Emacs Org-Mode, AsciiDoc, - EPUB (v2 and v3), FictionBook2, and several kinds of - HTML/javascript slide shows (S5, Slidy, Slideous, DZSlides, - reveal.js). + reStructuredText, LaTeX, DocBook, MediaWiki markup, TWiki + markup, Haddock markup, OPML, Emacs Org-Mode, txt2tags and + Textile, and it can write markdown, reStructuredText, XHTML, + HTML 5, LaTeX, ConTeXt, DocBook, OPML, OpenDocument, ODT, + Word docx, RTF, MediaWiki, DokuWiki, Textile, groff man + pages, plain text, Emacs Org-Mode, AsciiDoc, Haddock markup, + EPUB (v2 and v3), FictionBook2, InDesign ICML, and several + kinds of HTML/javascript slide shows (S5, Slidy, Slideous, + DZSlides, reveal.js). . Pandoc extends standard markdown syntax with footnotes, embedded LaTeX, definition lists, tables, and other @@ -40,150 +41,151 @@ Description: Pandoc is a Haskell library for converting from one markup only adding a reader or writer. Data-Files: -- templates - data/templates/default.html, - data/templates/default.html5, - data/templates/default.docbook, - data/templates/default.beamer, - data/templates/default.opendocument, - data/templates/default.opml, - data/templates/default.latex, - data/templates/default.context, - data/templates/default.texinfo, - data/templates/default.man, - data/templates/default.markdown, - data/templates/default.rst, - data/templates/default.plain, - data/templates/default.mediawiki, - data/templates/default.rtf, - data/templates/default.s5, - data/templates/default.slidy, - data/templates/default.slideous, - data/templates/default.revealjs, - data/templates/default.dzslides, - data/templates/default.asciidoc, - data/templates/default.textile, - data/templates/default.org, - data/templates/default.epub, - data/templates/default.epub3, + data/templates/default.html + data/templates/default.html5 + data/templates/default.docbook + data/templates/default.beamer + data/templates/default.opendocument + data/templates/default.icml + data/templates/default.opml + data/templates/default.latex + data/templates/default.context + data/templates/default.texinfo + data/templates/default.man + data/templates/default.markdown + data/templates/default.rst + data/templates/default.plain + data/templates/default.mediawiki + data/templates/default.dokuwiki + data/templates/default.rtf + data/templates/default.s5 + data/templates/default.slidy + data/templates/default.slideous + data/templates/default.revealjs + data/templates/default.dzslides + data/templates/default.asciidoc + data/templates/default.haddock + data/templates/default.textile + data/templates/default.org + data/templates/default.epub + data/templates/default.epub3 -- data for ODT writer - data/reference.odt, + data/reference.odt -- data for docx writer - data/reference.docx, + data/reference.docx -- stylesheet for EPUB writer - data/epub.css, + data/epub.css -- data for LaTeXMathML writer - data/LaTeXMathML.js, - data/MathMLinHTML.js, + data/LaTeXMathML.js + data/MathMLinHTML.js -- data for dzslides writer - data/dzslides/template.html, + data/dzslides/template.html -- sample lua custom writer data/sample.lua -- documentation - README, INSTALL, COPYRIGHT, BUGS, CONTRIBUTING.md, changelog + README, COPYRIGHT Extra-Source-Files: + -- documentation + INSTALL, BUGS, CONTRIBUTING.md, changelog -- code to create pandoc.1 man page - man/man1/pandoc.1.template, - man/man5/pandoc_markdown.5.template, + Makefile + man/man1/pandoc.1.template + man/man5/pandoc_markdown.5.template -- generated man pages (produced post-build) - man/man1/pandoc.1, - man/man5/pandoc_markdown.5, + man/man1/pandoc.1 + man/man5/pandoc_markdown.5 + -- trypandoc + trypandoc/Makefile + trypandoc/index.html -- tests - tests/bodybg.gif, + tests/bodybg.gif + tests/*.native tests/docbook-reader.docbook - tests/docbook-reader.native - tests/html-reader.html, - tests/html-reader.native, - tests/opml-reader.opml, - tests/opml-reader.native, - tests/haddock-reader.haddock, - tests/haddock-reader.native, - tests/insert, - tests/lalune.jpg, - tests/movie.jpg, - tests/latex-reader.latex, - tests/latex-reader.native, - tests/textile-reader.textile, - tests/textile-reader.native, - tests/markdown-reader-more.txt, - tests/markdown-reader-more.native, - tests/markdown-citations.txt, - tests/markdown-citations.native, - tests/textile-reader.textile, - tests/mediawiki-reader.wiki, - tests/mediawiki-reader.native, - tests/rst-reader.native, - tests/rst-reader.rst, - tests/s5.basic.html, - tests/s5.fancy.html, - tests/s5.fragment.html, - tests/s5.inserts.html, - tests/s5.native, - tests/tables.context, - tests/tables.docbook, - tests/tables.html, - tests/tables.latex, - tests/tables.man, - tests/tables.plain, - tests/tables.markdown, - tests/tables.mediawiki, - tests/tables.textile, - tests/tables.native, - tests/tables.opendocument, - tests/tables.org, - tests/tables.asciidoc, - tests/tables.texinfo, - tests/tables.rst, - tests/tables.rtf, - tests/tables.txt, - tests/tables-rstsubset.native, - tests/tables.fb2, - tests/testsuite.native, - tests/testsuite.txt, - tests/writer.latex, - tests/writer.context, - tests/writer.docbook, - tests/writer.html, - tests/writer.man, - tests/writer.markdown, - tests/writer.plain, - tests/writer.mediawiki, - tests/writer.textile, - tests/writer.native, - tests/writer.opendocument, - tests/writer.org, - tests/writer.asciidoc, - tests/writer.rst, - tests/writer.rtf, - tests/writer.texinfo, - tests/writer.fb2, - tests/writer.opml, - tests/lhs-test.native, - tests/lhs-test-markdown.native, - tests/lhs-test.markdown, - tests/lhs-test.markdown+lhs, - tests/lhs-test.rst, - tests/lhs-test.rst+lhs, - tests/lhs-test.latex, - tests/lhs-test.latex+lhs, - tests/lhs-test.html, - tests/lhs-test.html+lhs, - tests/lhs-test.fragment.html+lhs, - tests/pipe-tables.txt, - tests/pipe-tables.native, - tests/fb2.basic.markdown, - tests/fb2.basic.fb2, - tests/fb2.titles.markdown, - tests/fb2.titles.fb2, - tests/fb2.images.markdown, - tests/fb2.images.fb2, - tests/fb2.images-embedded.html, - tests/fb2.images-embedded.fb2, - tests/fb2.math.markdown, - tests/fb2.math.fb2, - tests/fb2.test-small.png, - tests/fb2.test.jpg -Extra-Tmp-Files: man/man1/pandoc.1, - man/man5/pandoc_markdown.5 + tests/html-reader.html + tests/opml-reader.opml + tests/haddock-reader.haddock + tests/insert + tests/lalune.jpg + tests/movie.jpg + tests/latex-reader.latex + tests/textile-reader.textile + tests/markdown-reader-more.txt + tests/markdown-citations.txt + tests/textile-reader.textile + tests/mediawiki-reader.wiki + tests/rst-reader.rst + tests/s5-basic.html + tests/s5-fancy.html + tests/s5-fragment.html + tests/s5-inserts.html + tests/tables.context + tests/tables.docbook + tests/tables.dokuwiki + tests/tables.icml + tests/tables.html + tests/tables.latex + tests/tables.man + tests/tables.plain + tests/tables.markdown + tests/tables.mediawiki + tests/tables.textile + tests/tables.opendocument + tests/tables.org + tests/tables.asciidoc + tests/tables.haddock + tests/tables.texinfo + tests/tables.rst + tests/tables.rtf + tests/tables.txt + tests/tables.fb2 + tests/testsuite.txt + tests/writer.latex + tests/writer.context + tests/writer.docbook + tests/writer.html + tests/writer.man + tests/writer.markdown + tests/writer.plain + tests/writer.mediawiki + tests/writer.textile + tests/writer.opendocument + tests/writer.org + tests/writer.asciidoc + tests/writer.haddock + tests/writer.rst + tests/writer.icml + tests/writer.rtf + tests/writer.texinfo + tests/writer.fb2 + tests/writer.opml + tests/writer.dokuwiki + tests/dokuwiki_inline_formatting.dokuwiki + tests/lhs-test.markdown + tests/lhs-test.markdown+lhs + tests/lhs-test.rst + tests/lhs-test.rst+lhs + tests/lhs-test.latex + tests/lhs-test.latex+lhs + tests/lhs-test.html + tests/lhs-test.html+lhs + tests/lhs-test.fragment.html+lhs + tests/pipe-tables.txt + tests/dokuwiki_external_images.dokuwiki + tests/dokuwiki_external_images.native + tests/dokuwiki_multiblock_table.dokuwiki + tests/dokuwiki_multiblock_table.native + tests/fb2/*.markdown + tests/fb2/*.fb2 + tests/fb2/images-embedded.html + tests/fb2/images-embedded.fb2 + tests/fb2/test-small.png + tests/fb2/test.jpg + tests/docx/*.docx + tests/docx/*.native + tests/epub/*.epub + tests/epub/*.native + tests/txt2tags.t2t + tests/twiki-reader.twiki Source-repository head type: git @@ -193,10 +195,22 @@ Flag embed_data_files Description: Embed data files in binary for relocatable executable. Default: False -Flag http-conduit - Description: Enable downloading of resources over https. +Flag trypandoc + Description: Build trypandoc cgi executable. + Default: False + +Flag https + Description: Enable support for downloading of resources over https. Default: True +Flag make-pandoc-man-pages + Description: Build program to regenerate pandoc man pages from README. + Default: False + +Flag network-uri + Description: Get Network.URI from the network-uri package + Default: True + Library Build-Depends: base >= 4.2 && <5, syb >= 0.1 && < 0.5, @@ -204,45 +218,55 @@ Library unordered-containers >= 0.2 && < 0.3, array >= 0.3 && < 0.6, parsec >= 3.1 && < 3.2, - mtl >= 1.1 && < 2.2, - network >= 2 && < 2.5, + mtl >= 1.1 && < 2.3, filepath >= 1.1 && < 1.4, process >= 1 && < 1.3, directory >= 1 && < 1.3, bytestring >= 0.9 && < 0.11, - text >= 0.11 && < 1.2, - zip-archive >= 0.1.3.3 && < 0.3, + text >= 0.11 && < 1.3, + zip-archive >= 0.2.3.4 && < 0.3, old-locale >= 1 && < 1.1, time >= 1.2 && < 1.5, HTTP >= 4000.0.5 && < 4000.3, - texmath >= 0.6.6 && < 0.7, + texmath >= 0.8 && < 0.9, xml >= 1.3.12 && < 1.4, - random >= 1 && < 1.1, + random >= 1 && < 1.2, extensible-exceptions >= 0.1 && < 0.2, - pandoc-types >= 1.12.3 && < 1.13, - aeson >= 0.6 && < 0.8, - tagsoup >= 0.12.5 && < 0.14, + pandoc-types >= 1.12.4 && < 1.13, + aeson >= 0.7 && < 0.9, + tagsoup >= 0.13.1 && < 0.14, base64-bytestring >= 0.1 && < 1.1, zlib >= 0.5 && < 0.6, - highlighting-kate >= 0.5.6 && < 0.6, + highlighting-kate >= 0.5.8.5 && < 0.6, data-default >= 0.4 && < 0.6, temporary >= 1.1 && < 1.3, blaze-html >= 0.5 && < 0.8, blaze-markup >= 0.5.1 && < 0.7, - attoparsec >= 0.10 && < 0.12, - yaml >= 0.8.3 && < 0.9, + yaml >= 0.8.8.2 && < 0.9, + scientific >= 0.2 && < 0.4, vector >= 0.10 && < 0.11, hslua >= 0.3 && < 0.4, - binary >= 0.5 && < 0.8 - Build-Tools: alex, happy - if flag(http-conduit) - Build-Depends: http-conduit >= 1.9 && < 2.1, + binary >= 0.5 && < 0.8, + SHA >= 1.6 && < 1.7, + haddock-library >= 1.1 && < 1.2, + old-time, + deepseq-generics >= 0.1 && < 0.2, + JuicyPixels >= 3.1.6.1 && < 3.3 + if flag(network-uri) + Build-Depends: network-uri >= 2.6 && < 2.7, network >= 2.6 + else + Build-Depends: network >= 2 && < 2.6 + if flag(https) + Build-Depends: http-client >= 0.3.2 && < 0.5, + http-client-tls >= 0.2 && < 0.3, http-types >= 0.8 && < 0.9 - cpp-options: -DHTTP_CONDUIT + cpp-options: -DHTTP_CLIENT if flag(embed_data_files) cpp-options: -DEMBED_DATA_FILES -- Build-Tools: hsb2hs -- not yet recognized by cabal other-modules: Text.Pandoc.Data + if os(windows) + Cpp-options: -D_WINDOWS Ghc-Options: -rtsopts -Wall -fno-warn-unused-do-bind Ghc-Prof-Options: -auto-all -caf-all -rtsopts Default-Language: Haskell98 @@ -256,33 +280,41 @@ Library Text.Pandoc.Options, Text.Pandoc.Pretty, Text.Pandoc.Shared, + Text.Pandoc.MediaBag, Text.Pandoc.Readers.HTML, Text.Pandoc.Readers.LaTeX, Text.Pandoc.Readers.Markdown, Text.Pandoc.Readers.MediaWiki, Text.Pandoc.Readers.RST, + Text.Pandoc.Readers.Org, Text.Pandoc.Readers.DocBook, Text.Pandoc.Readers.OPML, Text.Pandoc.Readers.TeXMath, Text.Pandoc.Readers.Textile, Text.Pandoc.Readers.Native, Text.Pandoc.Readers.Haddock, + Text.Pandoc.Readers.TWiki, + Text.Pandoc.Readers.Docx, + Text.Pandoc.Readers.EPUB, Text.Pandoc.Writers.Native, Text.Pandoc.Writers.Docbook, Text.Pandoc.Writers.OPML, Text.Pandoc.Writers.HTML, + Text.Pandoc.Writers.ICML, Text.Pandoc.Writers.LaTeX, Text.Pandoc.Writers.ConTeXt, Text.Pandoc.Writers.OpenDocument, Text.Pandoc.Writers.Texinfo, Text.Pandoc.Writers.Man, Text.Pandoc.Writers.Markdown, + Text.Pandoc.Writers.Haddock, Text.Pandoc.Writers.RST, Text.Pandoc.Writers.Org, Text.Pandoc.Writers.AsciiDoc, Text.Pandoc.Writers.Custom, Text.Pandoc.Writers.Textile, Text.Pandoc.Writers.MediaWiki, + Text.Pandoc.Writers.DokuWiki, Text.Pandoc.Writers.RTF, Text.Pandoc.Writers.ODT, Text.Pandoc.Writers.Docx, @@ -293,9 +325,12 @@ Library Text.Pandoc.Templates, Text.Pandoc.XML, Text.Pandoc.SelfContained, - Text.Pandoc.Process - Other-Modules: Text.Pandoc.Readers.Haddock.Lex, - Text.Pandoc.Readers.Haddock.Parse, + Text.Pandoc.Process, + Text.Pandoc.Readers.Txt2Tags + Other-Modules: Text.Pandoc.Readers.Docx.Lists, + Text.Pandoc.Readers.Docx.Reducible, + Text.Pandoc.Readers.Docx.Parse, + Text.Pandoc.Readers.Docx.Fonts Text.Pandoc.Writers.Shared, Text.Pandoc.Asciify, Text.Pandoc.MIME, @@ -305,26 +340,31 @@ Library Text.Pandoc.Slides, Text.Pandoc.Highlighting, Text.Pandoc.Compat.Monoid, + Text.Pandoc.Compat.Except, Text.Pandoc.Compat.TagSoupEntity, + Text.Pandoc.Compat.Directory Paths_pandoc Buildable: True Executable pandoc Build-Depends: pandoc, - pandoc-types >= 1.12.3 && < 1.13, + pandoc-types >= 1.12.4 && < 1.13, base >= 4.2 && <5, directory >= 1 && < 1.3, filepath >= 1.1 && < 1.4, - network >= 2 && < 2.5, - text >= 0.11 && < 1.2, + text >= 0.11 && < 1.3, bytestring >= 0.9 && < 0.11, extensible-exceptions >= 0.1 && < 0.2, - highlighting-kate >= 0.5.6 && < 0.6, - aeson >= 0.6 && < 0.8, - yaml >= 0.8.3 && < 0.9, + highlighting-kate >= 0.5.8.5 && < 0.6, + aeson >= 0.7.0.5 && < 0.9, + yaml >= 0.8.8.2 && < 0.9, containers >= 0.1 && < 0.6, HTTP >= 4000.0.5 && < 4000.3 + if flag(network-uri) + Build-Depends: network-uri >= 2.6 && < 2.7, network >= 2.6 + else + Build-Depends: network >= 2 && < 2.6 Ghc-Options: -rtsopts -with-rtsopts=-K16m -Wall -fno-warn-unused-do-bind Ghc-Prof-Options: -auto-all -caf-all -rtsopts -with-rtsopts=-K16m if os(windows) @@ -338,6 +378,17 @@ Executable pandoc Main-Is: pandoc.hs Buildable: True +Executable trypandoc + Main-Is: trypandoc.hs + Hs-Source-Dirs: trypandoc + default-language: Haskell2010 + if flag(trypandoc) + Build-Depends: base, aeson, pandoc, highlighting-kate, + text, wai-extra, wai >= 0.3, http-types + Buildable: True + else + Buildable: False + -- NOTE: A trick in Setup.hs makes sure this won't be installed: Executable make-pandoc-man-pages Main-Is: make-pandoc-man-pages.hs @@ -349,6 +400,10 @@ Executable make-pandoc-man-pages old-time >= 1.0 && < 1.2, time >= 1.2 && < 1.5 Default-Language: Haskell98 + if flag(make-pandoc-man-pages) + Buildable: True + else + Buildable: False Test-Suite test-pandoc Type: exitcode-stdio-1.0 @@ -357,21 +412,23 @@ Test-Suite test-pandoc Build-Depends: base >= 4.2 && < 5, syb >= 0.1 && < 0.5, pandoc, - pandoc-types >= 1.12.3 && < 1.13, + pandoc-types >= 1.12.4 && < 1.13, bytestring >= 0.9 && < 0.11, - text >= 0.11 && < 1.2, + text >= 0.11 && < 1.3, directory >= 1 && < 1.3, filepath >= 1.1 && < 1.4, process >= 1 && < 1.3, - highlighting-kate >= 0.5.6 && < 0.6, + highlighting-kate >= 0.5.8.5 && < 0.6, Diff >= 0.2 && < 0.4, test-framework >= 0.3 && < 0.9, test-framework-hunit >= 0.2 && < 0.4, test-framework-quickcheck2 >= 0.2.9 && < 0.4, - QuickCheck >= 2.4 && < 2.7, + QuickCheck >= 2.4 && < 2.8, HUnit >= 1.2 && < 1.3, containers >= 0.1 && < 0.6, - ansi-terminal >= 0.5 && < 0.7 + ansi-terminal >= 0.5 && < 0.7, + executable-path >= 0.0 && < 0.1, + zip-archive >= 0.2.3.4 && < 0.3 Other-Modules: Tests.Old Tests.Helpers Tests.Arbitrary @@ -379,13 +436,20 @@ Test-Suite test-pandoc Tests.Walk Tests.Readers.LaTeX Tests.Readers.Markdown + Tests.Readers.Org Tests.Readers.RST + Tests.Readers.Docx + Tests.Readers.Txt2Tags + Tests.Readers.EPUB Tests.Writers.Native Tests.Writers.ConTeXt + Tests.Writers.Docbook Tests.Writers.HTML Tests.Writers.Markdown + Tests.Writers.Plain + Tests.Writers.AsciiDoc Tests.Writers.LaTeX - Ghc-Options: -rtsopts -Wall -fno-warn-unused-do-bind + Ghc-Options: -rtsopts -Wall -fno-warn-unused-do-bind -threaded Default-Language: Haskell98 benchmark benchmark-pandoc @@ -1,6 +1,6 @@ -{-# LANGUAGE CPP #-} +{-# LANGUAGE CPP, TupleSections #-} {- -Copyright (C) 2006-2013 John MacFarlane <jgm@berkeley.edu> +Copyright (C) 2006-2014 John MacFarlane <jgm@berkeley.edu> This program is free software; you can redistribute it and/or modify it under the terms of the GNU General Public License as published by @@ -19,7 +19,7 @@ Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA {- | Module : Main - Copyright : Copyright (C) 2006-2013 John MacFarlane + Copyright : Copyright (C) 2006-2014 John MacFarlane License : GNU GPL, version 2 or above Maintainer : John MacFarlane <jgm@berkeley@edu> @@ -33,10 +33,12 @@ module Main where import Text.Pandoc import Text.Pandoc.Builder (setMeta) import Text.Pandoc.PDF (makePDF) +import Text.Pandoc.Walk (walk) import Text.Pandoc.Readers.LaTeX (handleIncludes) import Text.Pandoc.Shared ( tabFilter, readDataFileUTF8, readDataFile, safeRead, headerShift, normalize, err, warn, openURL ) +import Text.Pandoc.MediaBag ( mediaDirectory, extractMediaBag, MediaBag ) import Text.Pandoc.XML ( toEntities ) import Text.Pandoc.SelfContained ( makeSelfContained ) import Text.Pandoc.Process (pipeProcess) @@ -47,31 +49,39 @@ import System.Exit ( exitWith, ExitCode (..) ) import System.FilePath import System.Console.GetOpt import Data.Char ( toLower ) -import Data.List ( intercalate, isPrefixOf, sort ) -import System.Directory ( getAppUserDataDirectory, findExecutable ) +import Data.List ( intercalate, isPrefixOf, isSuffixOf, sort ) +import System.Directory ( getAppUserDataDirectory, findExecutable, + doesFileExist, Permissions(..), getPermissions ) import System.IO ( stdout, stderr ) import System.IO.Error ( isDoesNotExistError ) import qualified Control.Exception as E import Control.Exception.Extensible ( throwIO ) import qualified Text.Pandoc.UTF8 as UTF8 -import Control.Monad (when, unless, liftM) +import Control.Monad (when, unless, (>=>)) +import Data.Maybe (isJust, fromMaybe) import Data.Foldable (foldrM) import Network.URI (parseURI, isURI, URI(..)) import qualified Data.ByteString.Lazy as B import qualified Data.ByteString as BS import Data.Aeson (eitherDecode', encode) import qualified Data.Map as M -import System.IO.Error(ioeGetErrorType) -import GHC.IO.Exception (IOErrorType(ResourceVanished)) import Data.Yaml (decode) import qualified Data.Yaml as Yaml import qualified Data.Text as T +import Control.Applicative ((<$>), (<|>)) +import Text.Pandoc.Readers.Txt2Tags (getT2TMeta) +import Data.Monoid + +type Transform = Pandoc -> Pandoc copyrightMessage :: String -copyrightMessage = "\nCopyright (C) 2006-2013 John MacFarlane\n" ++ - "Web: http://johnmacfarlane.net/pandoc\n" ++ - "This is free software; see the source for copying conditions. There is no\n" ++ - "warranty, not even for merchantability or fitness for a particular purpose." +copyrightMessage = intercalate "\n" [ + "", + "Copyright (C) 2006-2014 John MacFarlane", + "Web: http://johnmacfarlane.net/pandoc", + "This is free software; see the source for copying conditions.", + "There is no warranty, not even for merchantability or fitness", + "for a particular purpose." ] compileInfo :: String compileInfo = @@ -85,30 +95,60 @@ compileInfo = -- comma separated words in lines with a maximum line length. wrapWords :: Int -> Int -> [String] -> String wrapWords indent c = wrap' (c - indent) (c - indent) - where wrap' _ _ [] = "" - wrap' cols remaining (x:xs) = if remaining == cols - then x ++ wrap' cols (remaining - length x) xs - else if (length x + 1) > remaining - then ",\n" ++ replicate indent ' ' ++ x ++ wrap' cols (cols - length x) xs - else ", " ++ x ++ wrap' cols (remaining - (length x + 2)) xs + where + wrap' _ _ [] = "" + wrap' cols remaining (x:xs) + | remaining == cols = + x ++ wrap' cols (remaining - length x) xs + | (length x + 1) > remaining = + ",\n" ++ replicate indent ' ' ++ x ++ + wrap' cols (cols - length x) xs + | otherwise = + ", " ++ x ++ + wrap' cols (remaining - length x - 2) xs isTextFormat :: String -> Bool -isTextFormat s = takeWhile (`notElem` "+-") s `notElem` ["odt","docx","epub","epub3"] +isTextFormat s = takeWhile (`notElem` "+-") s `notElem` binaries + where binaries = ["odt","docx","epub","epub3"] externalFilter :: FilePath -> [String] -> Pandoc -> IO Pandoc externalFilter f args' d = do + mbexe <- if '/' `elem` f + -- don't check PATH if filter name has a path + then return Nothing + -- we catch isDoesNotExistError because this will + -- be triggered if PATH not set: + else E.catch (findExecutable f) + (\e -> if isDoesNotExistError e + then return Nothing + else throwIO e) + (f', args'') <- case mbexe of + Just x -> return (x, args') + Nothing -> do + exists <- doesFileExist f + if exists + then do + isExecutable <- executable `fmap` + getPermissions f + return $ + case map toLower $ takeExtension f of + _ | isExecutable -> (f, args') + ".py" -> ("python", f:args') + ".hs" -> ("runhaskell", f:args') + ".pl" -> ("perl", f:args') + ".rb" -> ("ruby", f:args') + ".php" -> ("php", f:args') + _ -> (f, args') + else err 85 $ "Filter " ++ f ++ " not found" (exitcode, outbs, errbs) <- E.handle filterException $ - pipeProcess Nothing f args' $ encode d + pipeProcess Nothing f' args'' $ encode d when (not $ B.null errbs) $ B.hPutStr stderr errbs case exitcode of ExitSuccess -> return $ either error id $ eitherDecode' outbs ExitFailure _ -> err 83 $ "Error running filter " ++ f where filterException :: E.SomeException -> IO a filterException e = err 83 $ "Error running filter " ++ f ++ "\n" ++ - if ioeGetErrorType `fmap` E.fromException e == - Just ResourceVanished - then f ++ " not found in path" - else show e + show e -- | Data structure for command line options. data Opt = Opt @@ -119,7 +159,7 @@ data Opt = Opt , optWriter :: String -- ^ Writer format , optParseRaw :: Bool -- ^ Parse unconvertable HTML and TeX , optTableOfContents :: Bool -- ^ Include table of contents - , optTransforms :: [Pandoc -> Pandoc] -- ^ Doc transforms to apply + , optTransforms :: [Transform] -- ^ Doc transforms to apply , optTemplate :: Maybe FilePath -- ^ Custom template , optVariables :: [(String,String)] -- ^ Template variables to set , optMetadata :: M.Map String MetaValue -- ^ Metadata fields to set @@ -162,6 +202,11 @@ data Opt = Opt , optAscii :: Bool -- ^ Use ascii characters only in html , optTeXLigatures :: Bool -- ^ Use TeX ligatures for quotes/dashes , optDefaultImageExtension :: String -- ^ Default image extension + , optExtractMedia :: Maybe FilePath -- ^ Path to extract embedded media + , optTrace :: Bool -- ^ Print debug information + , optTrackChanges :: TrackChanges -- ^ Accept or reject MS Word track-changes. + , optKaTeXStylesheet :: Maybe String -- ^ Path to stylesheet for KaTeX + , optKaTeXJS :: Maybe String -- ^ Path to js file for KaTeX } -- | Defaults for command-line options. @@ -217,6 +262,11 @@ defaultOpts = Opt , optAscii = False , optTeXLigatures = True , optDefaultImageExtension = "" + , optExtractMedia = Nothing + , optTrace = False + , optTrackChanges = AcceptChanges + , optKaTeXStylesheet = Nothing + , optKaTeXJS = Nothing } -- | A list of functions, each transforming the options data structure @@ -225,13 +275,13 @@ options :: [OptDescr (Opt -> IO Opt)] options = [ Option "fr" ["from","read"] (ReqArg - (\arg opt -> return opt { optReader = map toLower arg }) + (\arg opt -> return opt { optReader = arg }) "FORMAT") "" , Option "tw" ["to","write"] (ReqArg - (\arg opt -> return opt { optWriter = map toLower arg }) + (\arg opt -> return opt { optWriter = arg }) "FORMAT") "" @@ -319,6 +369,26 @@ options = "NUMBER") "" -- "Tab stop (default 4)" + , Option "" ["track-changes"] + (ReqArg + (\arg opt -> do + action <- case arg of + "accept" -> return AcceptChanges + "reject" -> return RejectChanges + "all" -> return AllChanges + _ -> err 6 + ("Unknown option for track-changes: " ++ arg) + return opt { optTrackChanges = action }) + "accept|reject|all") + "" -- "Accepting or reject MS Word track-changes."" + + , Option "" ["extract-media"] + (ReqArg + (\arg opt -> do + return opt { optExtractMedia = Just arg }) + "PATH") + "" -- "Directory to which to extract embedded media" + , Option "s" ["standalone"] (NoArg (\opt -> return opt { optStandalone = True })) @@ -748,16 +818,36 @@ options = (\arg opt -> do let url' = case arg of Just u -> u - Nothing -> "http://cdn.mathjax.org/mathjax/latest/MathJax.js?config=TeX-AMS-MML_HTMLorMML" + Nothing -> "//cdn.mathjax.org/mathjax/latest/MathJax.js?config=TeX-AMS-MML_HTMLorMML" return opt { optHTMLMathMethod = MathJax url'}) "URL") "" -- "Use MathJax for HTML math" + , Option "" ["katex"] + (OptArg + (\arg opt -> + return opt + { optKaTeXJS = + arg <|> Just "http://cdnjs.cloudflare.com/ajax/libs/KaTeX/0.1.0/katex.min.js"}) + "URL") + "" -- Use KaTeX for HTML Math + + , Option "" ["katex-stylesheet"] + (ReqArg + (\arg opt -> + return opt { optKaTeXStylesheet = Just arg }) + "URL") + "" -- Set the KaTeX Stylesheet location , Option "" ["gladtex"] (NoArg (\opt -> return opt { optHTMLMathMethod = GladTeX })) "" -- "Use gladtex for HTML math" + , Option "" ["trace"] + (NoArg + (\opt -> return opt { optTrace = True })) + "" -- "Turn on diagnostic tracing in readers." + , Option "" ["dump-args"] (NoArg (\opt -> return opt { optDumpArgs = True })) @@ -789,6 +879,7 @@ options = ] + addMetadata :: String -> MetaValue -> M.Map String MetaValue -> M.Map String MetaValue addMetadata k v m = case M.lookup k m of @@ -827,13 +918,21 @@ defaultReaderName fallback (x:xs) = ".latex" -> "latex" ".ltx" -> "latex" ".rst" -> "rst" + ".org" -> "org" ".lhs" -> "markdown+lhs" ".db" -> "docbook" ".opml" -> "opml" ".wiki" -> "mediawiki" + ".dokuwiki" -> "dokuwiki" ".textile" -> "textile" ".native" -> "native" ".json" -> "json" + ".docx" -> "docx" + ".t2t" -> "t2t" + ".epub" -> "epub" + ".odt" -> "odt" -- so we get an "unknown reader" error + ".pdf" -> "pdf" -- so we get an "unknown reader" error + ".doc" -> "doc" -- so we get an "unknown reader" error _ -> defaultReaderName fallback xs -- Returns True if extension of first source is .lhs @@ -874,13 +973,39 @@ defaultWriterName x = ".pdf" -> "latex" ".fb2" -> "fb2" ".opml" -> "opml" + ".icml" -> "icml" ['.',y] | y `elem` ['1'..'9'] -> "man" - _ -> "html" + _ -> "html" + +-- Transformations of a Pandoc document post-parsing: + +extractMedia :: MediaBag -> FilePath -> Pandoc -> IO Pandoc +extractMedia media dir d = + case [fp | (fp, _, _) <- mediaDirectory media] of + [] -> return d + fps -> do + extractMediaBag True dir media + return $ walk (adjustImagePath dir fps) d + +adjustImagePath :: FilePath -> [FilePath] -> Inline -> Inline +adjustImagePath dir paths (Image lab (src, tit)) + | src `elem` paths = Image lab (dir ++ "/" ++ src, tit) +adjustImagePath _ _ x = x + +adjustMetadata :: M.Map String MetaValue -> Pandoc -> IO Pandoc +adjustMetadata metadata d = return $ M.foldWithKey setMeta d metadata + +applyTransforms :: [Transform] -> Pandoc -> IO Pandoc +applyTransforms transforms d = return $ foldr ($) d transforms + +applyFilters :: [FilePath] -> [String] -> Pandoc -> IO Pandoc +applyFilters filters args d = + foldrM ($) d $ map (flip externalFilter args) filters main :: IO () main = do - rawArgs <- liftM (map UTF8.decodeArg) getArgs + rawArgs <- map UTF8.decodeArg <$> getArgs prg <- getProgName let compatMode = (prg == "hsmarkdown") @@ -915,7 +1040,7 @@ main = do , optTemplate = templatePath , optOutputFile = outputFile , optNumberSections = numberSections - , optNumberOffset = numberFrom + , optNumberOffset = numberFrom , optSectionDivs = sectionDivs , optIncremental = incremental , optSelfContained = selfContained @@ -926,7 +1051,7 @@ main = do , optHighlight = highlight , optHighlightStyle = highlightStyle , optChapters = chapters - , optHTMLMathMethod = mathMethod + , optHTMLMathMethod = mathMethod' , optReferenceODT = referenceODT , optReferenceDocx = referenceDocx , optEpubStylesheet = epubStylesheet @@ -952,6 +1077,11 @@ main = do , optAscii = ascii , optTeXLigatures = texLigatures , optDefaultImageExtension = defaultImageExtension + , optExtractMedia = mbExtractMedia + , optTrace = trace + , optTrackChanges = trackChanges + , optKaTeXStylesheet = katexStylesheet + , optKaTeXJS = katexJS } = opts when dumpArgs $ @@ -959,59 +1089,78 @@ main = do mapM_ (\arg -> UTF8.hPutStrLn stdout arg) args exitWith ExitSuccess + let csscdn = "http://cdnjs.cloudflare.com/ajax/libs/KaTeX/0.1.0/katex.min.css" + let mathMethod = + case (katexJS, katexStylesheet) of + (Nothing, _) -> mathMethod' + (Just js, ss) -> KaTeX js (fromMaybe csscdn ss) + + -- --bibliography implies -F pandoc-citeproc for backwards compatibility: - let filters' = case M.lookup "bibliography" metadata of - Just _ | optCiteMethod opts /= Natbib && - optCiteMethod opts /= Biblatex && - all (\f -> takeBaseName f /= "pandoc-citeproc") - filters -> "pandoc-citeproc" : filters - _ -> filters - let plugins = map externalFilter filters' + let needsCiteproc = isJust (M.lookup "bibliography" metadata) && + optCiteMethod opts `notElem` [Natbib, Biblatex] && + "pandoc-citeproc" `notElem` map takeBaseName filters + let filters' = if needsCiteproc then "pandoc-citeproc" : filters + else filters let sources = if ignoreArgs then [] else args datadir <- case mbDataDir of Nothing -> E.catch - (liftM Just $ getAppUserDataDirectory "pandoc") + (Just <$> getAppUserDataDirectory "pandoc") (\e -> let _ = (e :: E.SomeException) in return Nothing) Just _ -> return mbDataDir -- assign reader and writer based on options and filenames - let readerName' = if null readerName - then let fallback = if any isURI sources - then "html" - else "markdown" - in defaultReaderName fallback sources - else readerName - - let writerName' = if null writerName - then defaultWriterName outputFile - else case writerName of - "epub2" -> "epub" - "html4" -> "html" - x -> x + let readerName' = case map toLower readerName of + [] -> defaultReaderName + (if any isURI sources + then "html" + else "markdown") sources + "html4" -> "html" + x -> x + + let writerName' = case map toLower writerName of + [] -> defaultWriterName outputFile + "epub2" -> "epub" + "html4" -> "html" + x -> x let pdfOutput = map toLower (takeExtension outputFile) == ".pdf" let laTeXOutput = "latex" `isPrefixOf` writerName' || "beamer" `isPrefixOf` writerName' - when pdfOutput $ do - -- make sure writer is latex or beamer - unless laTeXOutput $ - err 47 $ "cannot produce pdf output with " ++ writerName' ++ " writer" - -- check for latex program - mbLatex <- findExecutable latexEngine - case mbLatex of - Nothing -> err 41 $ - latexEngine ++ " not found. " ++ - latexEngine ++ " is needed for pdf output." - Just _ -> return () - - reader <- case getReader readerName' of - Right r -> return r - Left e -> err 7 e + writer <- if ".lua" `isSuffixOf` writerName' + -- note: use non-lowercased version writerName + then return $ IOStringWriter $ writeCustom writerName + else case getWriter writerName' of + Left e -> err 9 $ + if writerName' == "pdf" + then e ++ + "\nTo create a pdf with pandoc, use " ++ + "the latex or beamer writer and specify\n" ++ + "an output file with .pdf extension " ++ + "(pandoc -t latex -o filename.pdf)." + else e + Right w -> return w + + reader <- if "t2t" == readerName' + then (mkStringReader . + readTxt2Tags) <$> + (getT2TMeta sources outputFile) + else case getReader readerName' of + Right r -> return r + Left e -> err 7 e' + where e' = case readerName' of + "odt" -> e ++ + "\nPandoc can convert to ODT, but not from ODT.\nTry using LibreOffice to export as HTML, and convert that with pandoc." + "pdf" -> e ++ + "\nPandoc can convert to PDF, but not from PDF." + "doc" -> e ++ + "\nPandoc can convert from DOCX, but not from DOC.\nTry using Word to save your DOC file as DOCX, and convert that with pandoc." + _ -> e let standalone' = standalone || not (isTextFormat writerName') || pdfOutput @@ -1050,19 +1199,21 @@ main = do then do dztempl <- readDataFileUTF8 datadir ("dzslides" </> "template.html") - let dzcore = unlines $ dropWhile (not . isPrefixOf "<!-- {{{{ dzslides core") - $ lines dztempl + let dzline = "<!-- {{{{ dzslides core" + let dzcore = unlines + $ dropWhile (not . (dzline `isPrefixOf`)) + $ lines dztempl return $ ("dzslides-core", dzcore) : variables' else return variables' + let sourceURL = case sources of - [] -> Nothing - (x:_) -> case parseURI x of - Just u - | uriScheme u `elem` ["http:","https:"] -> - Just $ show u{ uriPath = "", - uriQuery = "", - uriFragment = "" } - _ -> Nothing + [] -> Nothing + (x:_) -> case parseURI x of + Just u + | uriScheme u `elem` ["http:","https:"] -> + Just $ show u{ uriQuery = "", + uriFragment = "" } + _ -> Nothing let readerOpts = def{ readerSmart = smart || (texLigatures && (laTeXOutput || "context" `isPrefixOf` writerName')) @@ -1074,8 +1225,47 @@ main = do , readerIndentedCodeClasses = codeBlockClasses , readerApplyMacros = not laTeXOutput , readerDefaultImageExtension = defaultImageExtension + , readerTrace = trace + , readerTrackChanges = trackChanges } + when (not (isTextFormat writerName') && outputFile == "-") $ + err 5 $ "Cannot write " ++ writerName' ++ " output to stdout.\n" ++ + "Specify an output file using the -o option." + + let readSources [] = mapM readSource ["-"] + readSources srcs = mapM readSource srcs + readSource "-" = UTF8.getContents + readSource src = case parseURI src of + Just u | uriScheme u `elem` ["http:","https:"] -> + readURI src + _ -> UTF8.readFile src + readURI src = do + res <- openURL src + case res of + Left e -> throwIO e + Right (bs,_) -> return $ UTF8.toString bs + + let readFiles [] = error "Cannot read archive from stdin" + readFiles (x:_) = B.readFile x + + let convertTabs = tabFilter (if preserveTabs || readerName' == "t2t" + then 0 + else tabStop) + + let handleIncludes' = if readerName' == "latex" || + readerName' == "latex+lhs" + then handleIncludes + else return + + (doc, media) <- + case reader of + StringReader r-> (, mempty) <$> + ( readSources >=> + handleIncludes' . convertTabs . intercalate "\n" >=> + r readerOpts ) sources + ByteStringReader r -> readFiles sources >>= r readerOpts + let writerOptions = def { writerStandalone = standalone', writerTemplate = templ, writerVariables = variables'', @@ -1111,40 +1301,15 @@ main = do writerEpubChapterLevel = epubChapterLevel, writerTOCDepth = epubTOCDepth, writerReferenceODT = referenceODT, - writerReferenceDocx = referenceDocx + writerReferenceDocx = referenceDocx, + writerMediaBag = media } - when (not (isTextFormat writerName') && outputFile == "-") $ - err 5 $ "Cannot write " ++ writerName' ++ " output to stdout.\n" ++ - "Specify an output file using the -o option." - - let readSources [] = mapM readSource ["-"] - readSources srcs = mapM readSource srcs - readSource "-" = UTF8.getContents - readSource src = case parseURI src of - Just u | uriScheme u `elem` ["http:","https:"] -> - readURI src - _ -> UTF8.readFile src - readURI src = do - res <- openURL src - case res of - Left e -> throwIO e - Right (bs,_) -> return $ UTF8.toString bs - - let convertTabs = tabFilter (if preserveTabs then 0 else tabStop) - - let handleIncludes' = if readerName' == "latex" || readerName' == "latex+lhs" - then handleIncludes - else return - - doc <- readSources sources >>= - handleIncludes' . convertTabs . intercalate "\n" >>= - reader readerOpts - - let doc0 = M.foldWithKey setMeta doc metadata - let doc1 = foldr ($) doc0 transforms - doc2 <- foldrM ($) doc1 $ map ($ [writerName']) plugins + doc' <- (maybe return (extractMedia media) mbExtractMedia >=> + adjustMetadata metadata >=> + applyTransforms transforms >=> + applyFilters filters' [writerName']) doc let writeBinary :: B.ByteString -> IO () writeBinary = B.writeFile (UTF8.encodePath outputFile) @@ -1153,24 +1318,37 @@ main = do writerFn "-" = UTF8.putStr writerFn f = UTF8.writeFile f - case getWriter writerName' of - Left e -> err 9 e - Right (IOStringWriter f) -> f writerOptions doc2 >>= writerFn outputFile - Right (IOByteStringWriter f) -> f writerOptions doc2 >>= writeBinary - Right (PureStringWriter f) + case writer of + IOStringWriter f -> f writerOptions doc' >>= writerFn outputFile + IOByteStringWriter f -> f writerOptions doc' >>= writeBinary + PureStringWriter f | pdfOutput -> do - res <- makePDF latexEngine f writerOptions doc2 + -- make sure writer is latex or beamer + unless laTeXOutput $ + err 47 $ "cannot produce pdf output with " ++ writerName' ++ + " writer" + + -- check for latex program + mbLatex <- findExecutable latexEngine + when (mbLatex == Nothing) $ + err 41 $ latexEngine ++ " not found. " ++ + latexEngine ++ " is needed for pdf output." + + res <- makePDF latexEngine f writerOptions doc' case res of Right pdf -> writeBinary pdf - Left err' -> err 43 $ UTF8.toStringLazy err' - | otherwise -> selfcontain (f writerOptions doc2 ++ + Left err' -> do + B.hPutStr stderr $ err' + B.hPut stderr $ B.pack [10] + err 43 "Error producing PDF from TeX source" + | otherwise -> selfcontain (f writerOptions doc' ++ ['\n' | not standalone']) >>= writerFn outputFile . handleEntities where htmlFormat = writerName' `elem` ["html","html+lhs","html5","html5+lhs", "s5","slidy","slideous","dzslides","revealjs"] selfcontain = if selfContained && htmlFormat - then makeSelfContained datadir + then makeSelfContained writerOptions else return handleEntities = if htmlFormat && ascii then toEntities diff --git a/src/Text/Pandoc.hs b/src/Text/Pandoc.hs index 3ae81db00..d2bb85699 100644 --- a/src/Text/Pandoc.hs +++ b/src/Text/Pandoc.hs @@ -1,6 +1,6 @@ {-# LANGUAGE ScopedTypeVariables, FlexibleInstances #-} {- -Copyright (C) 2006-2010 John MacFarlane <jgm@berkeley.edu> +Copyright (C) 2006-2014 John MacFarlane <jgm@berkeley.edu> This program is free software; you can redistribute it and/or modify it under the terms of the GNU General Public License as published by @@ -19,7 +19,7 @@ Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA {- | Module : Text.Pandoc - Copyright : Copyright (C) 2006-2010 John MacFarlane + Copyright : Copyright (C) 2006-2014 John MacFarlane License : GNU GPL, version 2 or above Maintainer : John MacFarlane <jgm@berkeley.edu> @@ -62,9 +62,13 @@ module Text.Pandoc , readers , writers -- * Readers: converting /to/ Pandoc format + , Reader (..) + , mkStringReader + , readDocx , readMarkdown , readMediaWiki , readRST + , readOrg , readLaTeX , readHtml , readTextile @@ -73,6 +77,10 @@ module Text.Pandoc , readHaddock , readNative , readJSON + , readTWiki + , readTxt2Tags + , readTxt2TagsNoMacros + , readEPUB -- * Writers: converting /from/ Pandoc format , Writer (..) , writeNative @@ -85,11 +93,13 @@ module Text.Pandoc , writeTexinfo , writeHtml , writeHtmlString + , writeICML , writeDocbook , writeOPML , writeOpenDocument , writeMan , writeMediaWiki + , writeDokuWiki , writeTextile , writeRTF , writeODT @@ -98,6 +108,7 @@ module Text.Pandoc , writeFB2 , writeOrg , writeAsciiDoc + , writeHaddock , writeCustom -- * Rendering templates and default templates , module Text.Pandoc.Templates @@ -115,6 +126,7 @@ import Text.Pandoc.JSON import Text.Pandoc.Readers.Markdown import Text.Pandoc.Readers.MediaWiki import Text.Pandoc.Readers.RST +import Text.Pandoc.Readers.Org import Text.Pandoc.Readers.DocBook import Text.Pandoc.Readers.OPML import Text.Pandoc.Readers.LaTeX @@ -122,6 +134,10 @@ import Text.Pandoc.Readers.HTML import Text.Pandoc.Readers.Textile import Text.Pandoc.Readers.Native import Text.Pandoc.Readers.Haddock +import Text.Pandoc.Readers.TWiki +import Text.Pandoc.Readers.Docx +import Text.Pandoc.Readers.Txt2Tags +import Text.Pandoc.Readers.EPUB import Text.Pandoc.Writers.Native import Text.Pandoc.Writers.Markdown import Text.Pandoc.Writers.RST @@ -133,22 +149,26 @@ import Text.Pandoc.Writers.ODT import Text.Pandoc.Writers.Docx import Text.Pandoc.Writers.EPUB import Text.Pandoc.Writers.FB2 +import Text.Pandoc.Writers.ICML import Text.Pandoc.Writers.Docbook import Text.Pandoc.Writers.OPML import Text.Pandoc.Writers.OpenDocument import Text.Pandoc.Writers.Man import Text.Pandoc.Writers.RTF import Text.Pandoc.Writers.MediaWiki +import Text.Pandoc.Writers.DokuWiki import Text.Pandoc.Writers.Textile import Text.Pandoc.Writers.Org import Text.Pandoc.Writers.AsciiDoc +import Text.Pandoc.Writers.Haddock import Text.Pandoc.Writers.Custom import Text.Pandoc.Templates import Text.Pandoc.Options import Text.Pandoc.Shared (safeRead, warn) +import Text.Pandoc.MediaBag (MediaBag) import Data.Aeson import qualified Data.ByteString.Lazy as BL -import Data.List (intercalate, isSuffixOf) +import Data.List (intercalate) import Data.Version (showVersion) import Data.Set (Set) import qualified Data.Set as Set @@ -181,30 +201,43 @@ parseFormatSpec = parse formatSpec "" '-' -> Set.delete ext _ -> Set.insert ext --- auxiliary function for readers: -markdown :: ReaderOptions -> String -> IO Pandoc -markdown o s = do - let (doc, warnings) = readMarkdownWithWarnings o s - mapM_ warn warnings - return doc +data Reader = StringReader (ReaderOptions -> String -> IO Pandoc) + | ByteStringReader (ReaderOptions -> BL.ByteString -> IO (Pandoc, MediaBag)) + +mkStringReader :: (ReaderOptions -> String -> Pandoc) -> Reader +mkStringReader r = StringReader (\o s -> return $ r o s) + +mkStringReaderWithWarnings :: (ReaderOptions -> String -> (Pandoc, [String])) -> Reader +mkStringReaderWithWarnings r = StringReader $ \o s -> do + let (doc, warnings) = r o s + mapM_ warn warnings + return doc + +mkBSReader :: (ReaderOptions -> BL.ByteString -> (Pandoc, MediaBag)) -> Reader +mkBSReader r = ByteStringReader (\o s -> return $ r o s) -- | Association list of formats and readers. -readers :: [(String, ReaderOptions -> String -> IO Pandoc)] -readers = [ ("native" , \_ s -> return $ readNative s) - ,("json" , \o s -> return $ readJSON o s) - ,("markdown" , markdown) - ,("markdown_strict" , markdown) - ,("markdown_phpextra" , markdown) - ,("markdown_github" , markdown) - ,("markdown_mmd", markdown) - ,("rst" , \o s -> return $ readRST o s) - ,("mediawiki" , \o s -> return $ readMediaWiki o s) - ,("docbook" , \o s -> return $ readDocBook o s) - ,("opml" , \o s -> return $ readOPML o s) - ,("textile" , \o s -> return $ readTextile o s) -- TODO : textile+lhs - ,("html" , \o s -> return $ readHtml o s) - ,("latex" , \o s -> return $ readLaTeX o s) - ,("haddock" , \o s -> return $ readHaddock o s) +readers :: [(String, Reader)] +readers = [ ("native" , StringReader $ \_ s -> return $ readNative s) + ,("json" , mkStringReader readJSON ) + ,("markdown" , mkStringReaderWithWarnings readMarkdownWithWarnings) + ,("markdown_strict" , mkStringReaderWithWarnings readMarkdownWithWarnings) + ,("markdown_phpextra" , mkStringReaderWithWarnings readMarkdownWithWarnings) + ,("markdown_github" , mkStringReaderWithWarnings readMarkdownWithWarnings) + ,("markdown_mmd", mkStringReaderWithWarnings readMarkdownWithWarnings) + ,("rst" , mkStringReaderWithWarnings readRSTWithWarnings ) + ,("mediawiki" , mkStringReader readMediaWiki) + ,("docbook" , mkStringReader readDocBook) + ,("opml" , mkStringReader readOPML) + ,("org" , mkStringReader readOrg) + ,("textile" , mkStringReader readTextile) -- TODO : textile+lhs + ,("html" , mkStringReader readHtml) + ,("latex" , mkStringReader readLaTeX) + ,("haddock" , mkStringReader readHaddock) + ,("twiki" , mkStringReader readTWiki) + ,("docx" , mkBSReader readDocx) + ,("t2t" , mkStringReader readTxt2TagsNoMacros) + ,("epub" , mkBSReader readEPUB) ] data Writer = PureStringWriter (WriterOptions -> Pandoc -> String) @@ -226,6 +259,7 @@ writers = [ ,("html" , PureStringWriter writeHtmlString) ,("html5" , PureStringWriter $ \o -> writeHtmlString o{ writerHtml5 = True }) + ,("icml" , PureStringWriter writeICML) ,("s5" , PureStringWriter $ \o -> writeHtmlString o{ writerSlideVariant = S5Slides , writerTableOfContents = False }) @@ -256,10 +290,12 @@ writers = [ ,("plain" , PureStringWriter writePlain) ,("rst" , PureStringWriter writeRST) ,("mediawiki" , PureStringWriter writeMediaWiki) + ,("dokuwiki" , PureStringWriter writeDokuWiki) ,("textile" , PureStringWriter writeTextile) ,("rtf" , IOStringWriter writeRTFWithEmbeddedImages) ,("org" , PureStringWriter writeOrg) ,("asciidoc" , PureStringWriter writeAsciiDoc) + ,("haddock" , PureStringWriter writeHaddock) ] getDefaultExtensions :: String -> Set Extension @@ -269,41 +305,51 @@ getDefaultExtensions "markdown_mmd" = multimarkdownExtensions getDefaultExtensions "markdown_github" = githubMarkdownExtensions getDefaultExtensions "markdown" = pandocExtensions getDefaultExtensions "plain" = pandocExtensions -getDefaultExtensions "textile" = Set.fromList [Ext_auto_identifiers, Ext_raw_tex] +getDefaultExtensions "org" = Set.fromList [Ext_citations] +getDefaultExtensions "textile" = Set.fromList [Ext_auto_identifiers] +getDefaultExtensions "html" = Set.fromList [Ext_auto_identifiers, + Ext_native_divs, + Ext_native_spans] +getDefaultExtensions "html5" = getDefaultExtensions "html" +getDefaultExtensions "epub" = Set.fromList [Ext_auto_identifiers, + Ext_raw_html, + Ext_native_divs, + Ext_native_spans, + Ext_epub_html_exts] getDefaultExtensions _ = Set.fromList [Ext_auto_identifiers] -- | Retrieve reader based on formatSpec (format+extensions). -getReader :: String -> Either String (ReaderOptions -> String -> IO Pandoc) +getReader :: String -> Either String Reader getReader s = case parseFormatSpec s of Left e -> Left $ intercalate "\n" $ [m | Message m <- errorMessages e] Right (readerName, setExts) -> case lookup readerName readers of Nothing -> Left $ "Unknown reader: " ++ readerName - Just r -> Right $ \o -> + Just (StringReader r) -> Right $ StringReader $ \o -> + r o{ readerExtensions = setExts $ + getDefaultExtensions readerName } + Just (ByteStringReader r) -> Right $ ByteStringReader $ \o -> r o{ readerExtensions = setExts $ getDefaultExtensions readerName } -- | Retrieve writer based on formatSpec (format+extensions). getWriter :: String -> Either String Writer -getWriter s = - case parseFormatSpec s of - Left e -> Left $ intercalate "\n" $ [m | Message m <- errorMessages e] - Right (writerName, setExts) -> - case lookup writerName writers of - Nothing - | ".lua" `isSuffixOf` s -> - Right $ IOStringWriter $ writeCustom s - | otherwise -> Left $ "Unknown writer: " ++ writerName - Just (PureStringWriter r) -> Right $ PureStringWriter $ - \o -> r o{ writerExtensions = setExts $ - getDefaultExtensions writerName } - Just (IOStringWriter r) -> Right $ IOStringWriter $ - \o -> r o{ writerExtensions = setExts $ - getDefaultExtensions writerName } - Just (IOByteStringWriter r) -> Right $ IOByteStringWriter $ - \o -> r o{ writerExtensions = setExts $ - getDefaultExtensions writerName } +getWriter s + = case parseFormatSpec s of + Left e -> Left $ intercalate "\n" $ [m | Message m <- errorMessages e] + Right (writerName, setExts) -> + case lookup writerName writers of + Nothing -> Left $ "Unknown writer: " ++ writerName + Just (PureStringWriter r) -> Right $ PureStringWriter $ + \o -> r o{ writerExtensions = setExts $ + getDefaultExtensions writerName } + Just (IOStringWriter r) -> Right $ IOStringWriter $ + \o -> r o{ writerExtensions = setExts $ + getDefaultExtensions writerName } + Just (IOByteStringWriter r) -> Right $ IOByteStringWriter $ + \o -> r o{ writerExtensions = setExts $ + getDefaultExtensions writerName } {-# DEPRECATED toJsonFilter "Use 'toJSONFilter' from 'Text.Pandoc.JSON' instead" #-} -- | Deprecated. Use @toJSONFilter@ from @Text.Pandoc.JSON@ instead. @@ -316,4 +362,3 @@ readJSON _ = either error id . eitherDecode' . UTF8.fromStringLazy writeJSON :: WriterOptions -> Pandoc -> String writeJSON _ = UTF8.toStringLazy . encode - diff --git a/src/Text/Pandoc/Asciify.hs b/src/Text/Pandoc/Asciify.hs index 1c177da90..66490d5c6 100644 --- a/src/Text/Pandoc/Asciify.hs +++ b/src/Text/Pandoc/Asciify.hs @@ -1,5 +1,5 @@ {- -Copyright (C) 2013 John MacFarlane <jgm@berkeley.edu> +Copyright (C) 2013-2014 John MacFarlane <jgm@berkeley.edu> This program is free software; you can redistribute it and/or modify it under the terms of the GNU General Public License as published by @@ -17,8 +17,8 @@ Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA -} {- | - Module : Text.Pandoc.SelfContained - Copyright : Copyright (C) 2013 John MacFarlane + Module : Text.Pandoc.Asciify + Copyright : Copyright (C) 2013-2014 John MacFarlane License : GNU GPL, version 2 or above Maintainer : John MacFarlane <jgm@berkeley.edu> diff --git a/src/Text/Pandoc/Compat/Directory.hs b/src/Text/Pandoc/Compat/Directory.hs new file mode 100644 index 000000000..61dd5c525 --- /dev/null +++ b/src/Text/Pandoc/Compat/Directory.hs @@ -0,0 +1,21 @@ +{-# LANGUAGE CPP #-} +module Text.Pandoc.Compat.Directory ( getModificationTime ) + where + +#if MIN_VERSION_directory(1,2,0) +import System.Directory + + +#else +import qualified System.Directory as S +import Data.Time.Clock (UTCTime) +import Data.Time.Clock.POSIX +import System.Time + +getModificationTime :: FilePath -> IO UTCTime +getModificationTime fp = convert `fmap` S.getModificationTime fp + where + convert (TOD x _) = posixSecondsToUTCTime (realToFrac x) + +#endif + diff --git a/src/Text/Pandoc/Compat/Except.hs b/src/Text/Pandoc/Compat/Except.hs new file mode 100644 index 000000000..9ce7c0d36 --- /dev/null +++ b/src/Text/Pandoc/Compat/Except.hs @@ -0,0 +1,37 @@ +{-# LANGUAGE CPP #-} +module Text.Pandoc.Compat.Except ( ExceptT + , Except + , Error(..) + , runExceptT + , runExcept + , MonadError + , throwError + , catchError ) + where + +#if MIN_VERSION_mtl(2,2,1) +import Control.Monad.Except + +class Error a where + noMsg :: a + strMsg :: String -> a + + noMsg = strMsg "" + strMsg _ = noMsg + +#else +import Control.Monad.Error +import Control.Monad.Identity (Identity, runIdentity) + +type ExceptT = ErrorT + +type Except s a = ErrorT s Identity a + +runExceptT :: ExceptT e m a -> m (Either e a) +runExceptT = runErrorT + +runExcept :: ExceptT e Identity a -> Either e a +runExcept = runIdentity . runExceptT +#endif + + diff --git a/src/Text/Pandoc/Highlighting.hs b/src/Text/Pandoc/Highlighting.hs index 11d608db6..7f975d4c6 100644 --- a/src/Text/Pandoc/Highlighting.hs +++ b/src/Text/Pandoc/Highlighting.hs @@ -1,5 +1,5 @@ {- -Copyright (C) 2008 John MacFarlane <jgm@berkeley.edu> +Copyright (C) 2008-2014 John MacFarlane <jgm@berkeley.edu> This program is free software; you can redistribute it and/or modify it under the terms of the GNU General Public License as published by @@ -18,7 +18,7 @@ Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA {- | Module : Text.Pandoc.Highlighting - Copyright : Copyright (C) 2008 John MacFarlane + Copyright : Copyright (C) 2008-2014 John MacFarlane License : GNU GPL, version 2 or above Maintainer : John MacFarlane <jgm@berkeley.edu> @@ -74,7 +74,12 @@ highlight formatter (_, classes, keyvals) rawCode = ["number","numberLines", "number-lines"]) classes } lcclasses = map (map toLower) classes in case find (`elem` lcLanguages) lcclasses of - Nothing -> Nothing + Nothing + | numberLines fmtOpts -> Just + $ formatter fmtOpts{ codeClasses = [], + containerClasses = classes } + $ map (\ln -> [(NormalTok, ln)]) $ lines rawCode + | otherwise -> Nothing Just language -> Just $ formatter fmtOpts{ codeClasses = [language], containerClasses = classes } diff --git a/src/Text/Pandoc/ImageSize.hs b/src/Text/Pandoc/ImageSize.hs index 3c9623b3c..68b34dcf3 100644 --- a/src/Text/Pandoc/ImageSize.hs +++ b/src/Text/Pandoc/ImageSize.hs @@ -1,6 +1,6 @@ {-# LANGUAGE OverloadedStrings, ScopedTypeVariables #-} {- - Copyright (C) 2011 John MacFarlane <jgm@berkeley.edu> + Copyright (C) 2011-2014 John MacFarlane <jgm@berkeley.edu> This program is free software; you can redistribute it and/or modify it under the terms of the GNU General Public License as published by @@ -19,7 +19,7 @@ {- | Module : Text.Pandoc.ImageSize -Copyright : Copyright (C) 2011 John MacFarlane +Copyright : Copyright (C) 2011-2014 John MacFarlane License : GNU GPL, version 2 or above Maintainer : John MacFarlane <jgm@berkeley.edu> @@ -76,6 +76,9 @@ imageSize img = do Eps -> epsSize img Pdf -> Nothing -- TODO +defaultSize :: (Integer, Integer) +defaultSize = (72, 72) + sizeInPixels :: ImageSize -> (Integer, Integer) sizeInPixels s = (pxX s, pxY s) @@ -217,7 +220,7 @@ exifHeader hdr = do numentries <- getWord16 let ifdEntry = do tag <- getWord16 >>= \t -> - maybe (fail $ "Unknown tag type " ++ show t) return + maybe (return UnknownTagType) return (M.lookup t tagTypeTable) dataFormat <- getWord16 numComponents <- getWord32 @@ -260,7 +263,9 @@ exifHeader hdr = do lookup ExifImageHeight allentries) of (Just (UnsignedLong w), Just (UnsignedLong h)) -> return (fromIntegral w, fromIntegral h) - _ -> fail "Could not determine image width, height" + _ -> return defaultSize + -- we return a default width and height when + -- the exif header doesn't contain these let resfactor = case lookup ResolutionUnit allentries of Just (UnsignedShort 1) -> (100 / 254) _ -> 1 @@ -337,6 +342,7 @@ data TagType = ImageDescription | SensingMethod | FileSource | SceneType + | UnknownTagType deriving (Show, Eq, Ord) tagTypeTable :: M.Map Word16 TagType diff --git a/src/Text/Pandoc/MIME.hs b/src/Text/Pandoc/MIME.hs index 44989ee94..2fdba93e0 100644 --- a/src/Text/Pandoc/MIME.hs +++ b/src/Text/Pandoc/MIME.hs @@ -1,5 +1,5 @@ {- -Copyright (C) 2011 John MacFarlane <jgm@berkeley.edu> +Copyright (C) 2011-2014 John MacFarlane <jgm@berkeley.edu> This program is free software; you can redistribute it and/or modify it under the terms of the GNU General Public License as published by @@ -18,7 +18,7 @@ Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA {- | Module : Text.Pandoc.MIME - Copyright : Copyright (C) 2011 John MacFarlane + Copyright : Copyright (C) 2011-2014 John MacFarlane License : GNU GPL, version 2 or above Maintainer : John MacFarlane <jgm@berkeley.edu> @@ -27,24 +27,44 @@ Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA Mime type lookup for ODT writer. -} -module Text.Pandoc.MIME ( getMimeType, extensionFromMimeType ) -where +module Text.Pandoc.MIME ( MimeType, getMimeType, getMimeTypeDef, + extensionFromMimeType )where import System.FilePath import Data.Char ( toLower ) +import Data.List (isPrefixOf, isSuffixOf) +import Data.Maybe (fromMaybe) import qualified Data.Map as M +type MimeType = String + -- | Determine mime type appropriate for file path. -getMimeType :: FilePath -> Maybe String -getMimeType "layout-cache" = Just "application/binary" -- in ODT -getMimeType f = M.lookup (map toLower $ drop 1 $ takeExtension f) mimeTypes - where mimeTypes = M.fromList mimeTypesList +getMimeType :: FilePath -> Maybe MimeType +getMimeType fp + -- ODT + | fp == "layout-cache" = + Just "application/binary" + | "Formula-" `isPrefixOf` fp && "/" `isSuffixOf` fp = + Just "application/vnd.oasis.opendocument.formula" + -- generic + | otherwise = M.lookup (map toLower $ drop 1 $ takeExtension fp) mimeTypes + +-- | Determime mime type appropriate for file path, defaulting to +-- “application/octet-stream” if nothing else fits. +getMimeTypeDef :: FilePath -> MimeType +getMimeTypeDef = fromMaybe "application/octet-stream" . getMimeType -extensionFromMimeType :: String -> Maybe String -extensionFromMimeType mimetype = M.lookup (takeWhile (/=';') mimetype) reverseMimeTypes +extensionFromMimeType :: MimeType -> Maybe String +extensionFromMimeType mimetype = + M.lookup (takeWhile (/=';') mimetype) reverseMimeTypes -- note: we just look up the basic mime type, dropping the content-encoding etc. - where reverseMimeTypes = M.fromList $ map (\(k,v) -> (v,k)) mimeTypesList -mimeTypesList :: [(String, String)] +reverseMimeTypes :: M.Map MimeType String +reverseMimeTypes = M.fromList $ map (\(k,v) -> (v,k)) mimeTypesList + +mimeTypes :: M.Map String MimeType +mimeTypes = M.fromList mimeTypesList + +mimeTypesList :: [(String, MimeType)] mimeTypesList = -- List borrowed from happstack-server. [("gz","application/x-gzip") ,("cabal","application/x-cabal") @@ -246,6 +266,7 @@ mimeTypesList = -- List borrowed from happstack-server. ,("lzx","application/x-lzx") ,("m3u","audio/mpegurl") ,("m4a","audio/mpeg") + ,("m4v","video/x-m4v") ,("maker","application/x-maker") ,("man","application/x-troff-man") ,("mcif","chemical/x-mmcif") @@ -307,7 +328,7 @@ mimeTypesList = -- List borrowed from happstack-server. ,("oth","application/vnd.oasis.opendocument.text-web") ,("otp","application/vnd.oasis.opendocument.presentation-template") ,("ots","application/vnd.oasis.opendocument.spreadsheet-template") - ,("otf","application/x-font-opentype") + ,("otf","application/vnd.ms-opentype") ,("ott","application/vnd.oasis.opendocument.text-template") ,("oza","application/x-oz-application") ,("p","text/x-pascal") @@ -456,6 +477,7 @@ mimeTypesList = -- List borrowed from happstack-server. ,("vrml","model/vrml") ,("vs","text/plain") ,("vsd","application/vnd.visio") + ,("vtt","text/vtt") ,("wad","application/x-doom") ,("wav","audio/x-wav") ,("wax","audio/x-ms-wax") diff --git a/src/Text/Pandoc/MediaBag.hs b/src/Text/Pandoc/MediaBag.hs new file mode 100644 index 000000000..a55d5417e --- /dev/null +++ b/src/Text/Pandoc/MediaBag.hs @@ -0,0 +1,107 @@ +{-# LANGUAGE GeneralizedNewtypeDeriving #-} +{- +Copyright (C) 2014 John MacFarlane <jgm@berkeley.edu> + +This program is free software; you can redistribute it and/or modify +it under the terms of the GNU General Public License as published by +the Free Software Foundation; either version 2 of the License, or +(at your option) any later version. + +This program is distributed in the hope that it will be useful, +but WITHOUT ANY WARRANTY; without even the implied warranty of +MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the +GNU General Public License for more details. + +You should have received a copy of the GNU General Public License +along with this program; if not, write to the Free Software +Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA +-} + +{- | + Module : Text.Pandoc.MediaBag + Copyright : Copyright (C) 2014 John MacFarlane + License : GNU GPL, version 2 or above + + Maintainer : John MacFarlane <jgm@berkeley.edu> + Stability : alpha + Portability : portable + +Definition of a MediaBag object to hold binary resources, and an +interface for interacting with it. +-} +module Text.Pandoc.MediaBag ( + MediaBag, + lookupMedia, + insertMedia, + mediaDirectory, + extractMediaBag + ) where +import System.FilePath +import System.Directory (createDirectoryIfMissing) +import qualified Data.Map as M +import qualified Data.ByteString.Lazy as BL +import Data.Monoid (Monoid) +import Control.Monad (when) +import Text.Pandoc.MIME (MimeType, getMimeTypeDef) +import qualified Text.Pandoc.UTF8 as UTF8 +import Data.Maybe (fromMaybe) +import System.IO (stderr) + +-- | A container for a collection of binary resources, with names and +-- mime types. Note that a 'MediaBag' is a Monoid, so 'mempty' +-- can be used for an empty 'MediaBag', and '<>' can be used to append +-- two 'MediaBag's. +newtype MediaBag = MediaBag (M.Map [String] (MimeType, BL.ByteString)) + deriving (Monoid) + +instance Show MediaBag where + show bag = "MediaBag " ++ show (mediaDirectory bag) + +-- | Insert a media item into a 'MediaBag', replacing any existing +-- value with the same name. +insertMedia :: FilePath -- ^ relative path and canonical name of resource + -> Maybe MimeType -- ^ mime type (Nothing = determine from extension) + -> BL.ByteString -- ^ contents of resource + -> MediaBag + -> MediaBag +insertMedia fp mbMime contents (MediaBag mediamap) = + MediaBag (M.insert (splitPath fp) (mime, contents) mediamap) + where mime = fromMaybe fallback mbMime + fallback = case takeExtension fp of + ".gz" -> getMimeTypeDef $ dropExtension fp + _ -> getMimeTypeDef fp + +-- | Lookup a media item in a 'MediaBag', returning mime type and contents. +lookupMedia :: FilePath + -> MediaBag + -> Maybe (MimeType, BL.ByteString) +lookupMedia fp (MediaBag mediamap) = M.lookup (splitPath fp) mediamap + +-- | Get a list of the file paths stored in a 'MediaBag', with +-- their corresponding mime types and the lengths in bytes of the contents. +mediaDirectory :: MediaBag -> [(String, MimeType, Int)] +mediaDirectory (MediaBag mediamap) = + M.foldWithKey (\fp (mime,contents) -> + (((joinPath fp), mime, fromIntegral $ BL.length contents):)) [] mediamap + +-- | Extract contents of MediaBag to a given directory. Print informational +-- messages if 'verbose' is true. +extractMediaBag :: Bool + -> FilePath + -> MediaBag + -> IO () +extractMediaBag verbose dir (MediaBag mediamap) = do + sequence_ $ M.foldWithKey + (\fp (_ ,contents) -> + ((writeMedia verbose dir (joinPath fp, contents)):)) [] mediamap + +writeMedia :: Bool -> FilePath -> (FilePath, BL.ByteString) -> IO () +writeMedia verbose dir (subpath, bs) = do + -- we join and split to convert a/b/c to a\b\c on Windows; + -- in zip containers all paths use / + let fullpath = dir </> normalise subpath + createDirectoryIfMissing True $ takeDirectory fullpath + when verbose $ UTF8.hPutStrLn stderr $ "pandoc: extracting " ++ fullpath + BL.writeFile fullpath bs + + diff --git a/src/Text/Pandoc/Options.hs b/src/Text/Pandoc/Options.hs index 5f65abdde..ebfd8f8a9 100644 --- a/src/Text/Pandoc/Options.hs +++ b/src/Text/Pandoc/Options.hs @@ -1,5 +1,5 @@ {- -Copyright (C) 2012 John MacFarlane <jgm@berkeley.edu> +Copyright (C) 2012-2014 John MacFarlane <jgm@berkeley.edu> This program is free software; you can redistribute it and/or modify it under the terms of the GNU General Public License as published by @@ -18,7 +18,7 @@ Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA {- | Module : Text.Pandoc.Options - Copyright : Copyright (C) 2012 John MacFarlane + Copyright : Copyright (C) 2012-2014 John MacFarlane License : GNU GPL, version 2 or above Maintainer : John MacFarlane <jgm@berkeley.edu> @@ -41,6 +41,7 @@ module Text.Pandoc.Options ( Extension(..) , HTMLSlideVariant (..) , EPUBVersion (..) , WriterOptions (..) + , TrackChanges (..) , def , isEnabled ) where @@ -48,6 +49,8 @@ import Data.Set (Set) import qualified Data.Set as Set import Data.Default import Text.Pandoc.Highlighting (Style, pygments) +import Text.Pandoc.MediaBag (MediaBag) +import Data.Monoid -- | Individually selectable syntax extensions. data Extension = @@ -74,6 +77,8 @@ data Extension = | Ext_backtick_code_blocks -- ^ Github style ``` code blocks | Ext_inline_code_attributes -- ^ Allow attributes on inline code | Ext_markdown_in_html_blocks -- ^ Interpret as markdown inside HTML blocks + | Ext_native_divs -- ^ Use Div blocks for contents of <div> tags + | Ext_native_spans -- ^ Use Span inlines for contents of <span> | Ext_markdown_attribute -- ^ Interpret text inside HTML as markdown -- iff container has attribute 'markdown' | Ext_escaped_line_breaks -- ^ Treat a backslash at EOL as linebreak @@ -83,6 +88,8 @@ data Extension = | Ext_lists_without_preceding_blankline -- ^ Allow lists without preceding blank | Ext_startnum -- ^ Make start number of ordered list significant | Ext_definition_lists -- ^ Definition lists as in pandoc, mmd, php + | Ext_compact_definition_lists -- ^ Definition lists without + -- space between items, and disallow laziness | Ext_example_lists -- ^ Markdown-style numbered examples | Ext_all_symbols_escapable -- ^ Make all non-alphanumerics escapable | Ext_intraword_underscores -- ^ Treat underscore inside word as literal @@ -101,6 +108,7 @@ data Extension = | Ext_mmd_header_identifiers -- ^ Multimarkdown style header identifiers [myid] | Ext_implicit_header_references -- ^ Implicit reference links for headers | Ext_line_blocks -- ^ RST style line blocks + | Ext_epub_html_exts -- ^ Recognise the EPUB extended version of HTML deriving (Show, Read, Enum, Eq, Ord, Bounded) pandocExtensions :: Set Extension @@ -125,6 +133,8 @@ pandocExtensions = Set.fromList , Ext_backtick_code_blocks , Ext_inline_code_attributes , Ext_markdown_in_html_blocks + , Ext_native_divs + , Ext_native_spans , Ext_escaped_line_breaks , Ext_fancy_lists , Ext_startnum @@ -162,7 +172,6 @@ githubMarkdownExtensions = Set.fromList , Ext_raw_html , Ext_tex_math_single_backslash , Ext_fenced_code_blocks - , Ext_fenced_code_attributes , Ext_auto_identifiers , Ext_ascii_identifiers , Ext_backtick_code_blocks @@ -198,7 +207,6 @@ strictExtensions = Set.fromList data ReaderOptions = ReaderOptions{ readerExtensions :: Set Extension -- ^ Syntax extensions , readerSmart :: Bool -- ^ Smart punctuation - , readerStrict :: Bool -- ^ FOR TRANSITION ONLY , readerStandalone :: Bool -- ^ Standalone document with header , readerParseRaw :: Bool -- ^ Parse raw HTML, LaTeX , readerColumns :: Int -- ^ Number of columns in terminal @@ -210,13 +218,14 @@ data ReaderOptions = ReaderOptions{ , readerIndentedCodeClasses :: [String] -- ^ Default classes for -- indented code blocks , readerDefaultImageExtension :: String -- ^ Default extension for images + , readerTrace :: Bool -- ^ Print debugging info + , readerTrackChanges :: TrackChanges } deriving (Show, Read) instance Default ReaderOptions where def = ReaderOptions{ readerExtensions = pandocExtensions , readerSmart = False - , readerStrict = False , readerStandalone = False , readerParseRaw = False , readerColumns = 80 @@ -225,6 +234,8 @@ instance Default ReaderOptions , readerApplyMacros = True , readerIndentedCodeClasses = [] , readerDefaultImageExtension = "" + , readerTrace = False + , readerTrackChanges = AcceptChanges } -- @@ -240,6 +251,7 @@ data HTMLMathMethod = PlainMath | WebTeX String -- url of TeX->image script. | MathML (Maybe String) -- url of MathMLinHTML.js | MathJax String -- url of MathJax.js + | KaTeX String String -- url of stylesheet and katex.js deriving (Show, Read, Eq) data CiteMethod = Citeproc -- use citeproc to render them @@ -262,6 +274,12 @@ data HTMLSlideVariant = S5Slides | NoSlides deriving (Show, Read, Eq) +-- | Options for accepting or rejecting MS Word track-changes. +data TrackChanges = AcceptChanges + | RejectChanges + | AllChanges + deriving (Show, Read, Eq) + -- | Options for writers data WriterOptions = WriterOptions { writerStandalone :: Bool -- ^ Include header and footer @@ -303,7 +321,8 @@ data WriterOptions = WriterOptions , writerEpubChapterLevel :: Int -- ^ Header level for chapters (separate files) , writerTOCDepth :: Int -- ^ Number of levels to include in TOC , writerReferenceODT :: Maybe FilePath -- ^ Path to reference ODT if specified - , writerReferenceDocx :: Maybe FilePath -- ^ Ptah to reference DOCX if specified + , writerReferenceDocx :: Maybe FilePath -- ^ Path to reference DOCX if specified + , writerMediaBag :: MediaBag -- ^ Media collected by docx or epub reader } deriving Show instance Default WriterOptions where @@ -346,6 +365,7 @@ instance Default WriterOptions where , writerTOCDepth = 3 , writerReferenceODT = Nothing , writerReferenceDocx = Nothing + , writerMediaBag = mempty } -- | Returns True if the given extension is enabled. diff --git a/src/Text/Pandoc/PDF.hs b/src/Text/Pandoc/PDF.hs index 360338f8f..d5f7c609d 100644 --- a/src/Text/Pandoc/PDF.hs +++ b/src/Text/Pandoc/PDF.hs @@ -1,6 +1,6 @@ -{-# LANGUAGE OverloadedStrings, CPP #-} +{-# LANGUAGE OverloadedStrings, CPP, ScopedTypeVariables #-} {- -Copyright (C) 2012 John MacFarlane <jgm@berkeley.edu> +Copyright (C) 2012-2014 John MacFarlane <jgm@berkeley.edu> This program is free software; you can redistribute it and/or modify it under the terms of the GNU General Public License as published by @@ -19,7 +19,7 @@ Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA {- | Module : Text.Pandoc.PDF - Copyright : Copyright (C) 2012 John MacFarlane + Copyright : Copyright (C) 2012-2014 John MacFarlane License : GNU GPL, version 2 or above Maintainer : John MacFarlane <jgm@berkeley.edu> @@ -30,7 +30,6 @@ Conversion of LaTeX documents to PDF. -} module Text.Pandoc.PDF ( makePDF ) where -import System.IO.Temp import Data.ByteString.Lazy (ByteString) import qualified Data.ByteString.Lazy as B import qualified Data.ByteString.Lazy.Char8 as BC @@ -38,26 +37,29 @@ import qualified Data.ByteString as BS import System.Exit (ExitCode (..)) import System.FilePath import System.Directory +import Data.Digest.Pure.SHA (showDigest, sha1) import System.Environment -import Control.Monad (unless) +import Control.Monad (unless, (<=<)) +import qualified Control.Exception as E +import Control.Applicative ((<$)) import Data.List (isInfixOf) import Data.Maybe (fromMaybe) -import qualified Data.ByteString.Base64 as B64 import qualified Text.Pandoc.UTF8 as UTF8 import Text.Pandoc.Definition import Text.Pandoc.Walk (walkM) -import Text.Pandoc.Shared (fetchItem, warn) +import Text.Pandoc.Shared (fetchItem', warn, withTempDir) import Text.Pandoc.Options (WriterOptions(..)) -import Text.Pandoc.MIME (extensionFromMimeType) +import Text.Pandoc.MIME (extensionFromMimeType, getMimeType) import Text.Pandoc.Process (pipeProcess) import qualified Data.ByteString.Lazy as BL +import qualified Codec.Picture as JP +#ifdef _WINDOWS +import Data.List (intercalate) +#endif -withTempDir :: String -> (FilePath -> IO a) -> IO a -withTempDir = #ifdef _WINDOWS - withTempDirectory "." -#else - withSystemTempDirectory +changePathSeparators :: FilePath -> FilePath +changePathSeparators = intercalate "/" . splitDirectories #endif makePDF :: String -- ^ pdf creator (pdflatex, lualatex, xelatex) @@ -66,31 +68,31 @@ makePDF :: String -- ^ pdf creator (pdflatex, lualatex, xelatex) -> Pandoc -- ^ document -> IO (Either ByteString ByteString) makePDF program writer opts doc = withTempDir "tex2pdf." $ \tmpdir -> do - doc' <- handleImages (writerSourceURL opts) tmpdir doc + doc' <- handleImages opts tmpdir doc let source = writer opts doc' tex2pdf' tmpdir program source -handleImages :: Maybe String -- ^ source base URL +handleImages :: WriterOptions -> FilePath -- ^ temp dir to store images -> Pandoc -- ^ document -> IO Pandoc -handleImages baseURL tmpdir = walkM (handleImage' baseURL tmpdir) +handleImages opts tmpdir = walkM (convertImages tmpdir) <=< walkM (handleImage' opts tmpdir) -handleImage' :: Maybe String +handleImage' :: WriterOptions -> FilePath -> Inline -> IO Inline -handleImage' baseURL tmpdir (Image ils (src,tit)) = do +handleImage' opts tmpdir (Image ils (src,tit)) = do exists <- doesFileExist src if exists then return $ Image ils (src,tit) else do - res <- fetchItem baseURL src + res <- fetchItem' (writerMediaBag opts) (writerSourceURL opts) src case res of Right (contents, Just mime) -> do let ext = fromMaybe (takeExtension src) $ extensionFromMimeType mime - let basename = UTF8.toString $ B64.encode $ UTF8.fromString src + let basename = showDigest $ sha1 $ BL.fromChunks [contents] let fname = tmpdir </> basename <.> ext BS.writeFile fname contents return $ Image ils (fname,tit) @@ -99,6 +101,35 @@ handleImage' baseURL tmpdir (Image ils (src,tit)) = do return $ Image ils (src,tit) handleImage' _ _ x = return x +convertImages :: FilePath -> Inline -> IO Inline +convertImages tmpdir (Image ils (src, tit)) = do + img <- convertImage tmpdir src + newPath <- + case img of + Left e -> src <$ + warn ("Unable to convert image `" ++ src ++ "':\n" ++ e) + Right fp -> return fp + return (Image ils (newPath, tit)) +convertImages _ x = return x + +-- Convert formats which do not work well in pdf to png +convertImage :: FilePath -> FilePath -> IO (Either String FilePath) +convertImage tmpdir fname = + case mime of + Just "image/png" -> doNothing + Just "image/jpeg" -> doNothing + Just "application/pdf" -> doNothing + _ -> JP.readImage fname >>= \res -> + case res of + Left msg -> return $ Left msg + Right img -> + E.catch (Right fileOut <$ JP.savePngImage fileOut img) $ + \(e :: E.SomeException) -> return (Left (show e)) + where + fileOut = replaceDirectory (replaceExtension fname (".png")) tmpdir + mime = getMimeType fname + doNothing = return (Right fname) + tex2pdf' :: FilePath -- ^ temp directory for output -> String -- ^ tex program -> String -- ^ tex source @@ -108,7 +139,6 @@ tex2pdf' tmpDir program source = do then 3 -- to get page numbers else 2 -- 1 run won't give you PDF bookmarks (exit, log', mbPdf) <- runTeXProgram program numruns tmpDir source - let msg = "Error producing PDF from TeX source.\n" case (exit, mbPdf) of (ExitFailure _, _) -> do let logmsg = extractMsg log' @@ -117,8 +147,8 @@ tex2pdf' tmpDir program source = do x | "! Package inputenc Error" `BC.isPrefixOf` x -> "\nTry running pandoc with --latex-engine=xelatex." _ -> "" - return $ Left $ msg <> logmsg <> extramsg - (ExitSuccess, Nothing) -> return $ Left msg + return $ Left $ logmsg <> extramsg + (ExitSuccess, Nothing) -> return $ Left "" (ExitSuccess, Just pdf) -> return $ Right pdf (<>) :: ByteString -> ByteString -> ByteString @@ -146,10 +176,19 @@ runTeXProgram program runsLeft tmpDir source = do let file = tmpDir </> "input.tex" exists <- doesFileExist file unless exists $ UTF8.writeFile file source +#ifdef _WINDOWS + -- note: we want / even on Windows, for TexLive + let tmpDir' = changePathSeparators tmpDir + let file' = changePathSeparators file +#else + let tmpDir' = tmpDir + let file' = file +#endif let programArgs = ["-halt-on-error", "-interaction", "nonstopmode", - "-output-directory", tmpDir, file] + "-output-directory", tmpDir', file'] env' <- getEnvironment - let texinputs = maybe (tmpDir ++ ":") ((tmpDir ++ ":") ++) + let sep = searchPathSeparator:[] + let texinputs = maybe (tmpDir' ++ sep) ((tmpDir' ++ sep) ++) $ lookup "TEXINPUTS" env' let env'' = ("TEXINPUTS", texinputs) : [(k,v) | (k,v) <- env', k /= "TEXINPUTS"] @@ -160,7 +199,10 @@ runTeXProgram program runsLeft tmpDir source = do let pdfFile = replaceDirectory (replaceExtension file ".pdf") tmpDir pdfExists <- doesFileExist pdfFile pdf <- if pdfExists - then Just `fmap` B.readFile pdfFile + -- We read PDF as a strict bytestring to make sure that the + -- temp directory is removed on Windows. + -- See https://github.com/jgm/pandoc/issues/1192. + then (Just . B.fromChunks . (:[])) `fmap` BS.readFile pdfFile else return Nothing return (exit, out <> err, pdf) diff --git a/src/Text/Pandoc/Parsing.hs b/src/Text/Pandoc/Parsing.hs index 2f21e1253..18f38e564 100644 --- a/src/Text/Pandoc/Parsing.hs +++ b/src/Text/Pandoc/Parsing.hs @@ -1,7 +1,11 @@ -{-# LANGUAGE GeneralizedNewtypeDeriving, TypeSynonymInstances, - FlexibleInstances#-} +{-# LANGUAGE + FlexibleContexts +, GeneralizedNewtypeDeriving +, TypeSynonymInstances +, MultiParamTypeClasses +, FlexibleInstances #-} {- -Copyright (C) 2006-2010 John MacFarlane <jgm@berkeley.edu> +Copyright (C) 2006-2014 John MacFarlane <jgm@berkeley.edu> This program is free software; you can redistribute it and/or modify it under the terms of the GNU General Public License as published by @@ -20,7 +24,7 @@ Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA {- | Module : Text.Pandoc.Parsing - Copyright : Copyright (C) 2006-2010 John MacFarlane + Copyright : Copyright (C) 2006-2014 John MacFarlane License : GNU GPL, version 2 or above Maintainer : John MacFarlane <jgm@berkeley.edu> @@ -29,8 +33,7 @@ Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA A utility library with parsers used in pandoc readers. -} -module Text.Pandoc.Parsing ( (>>~), - anyLine, +module Text.Pandoc.Parsing ( anyLine, many1Till, notFollowedBy', oneOfStrings, @@ -54,7 +57,6 @@ module Text.Pandoc.Parsing ( (>>~), withRaw, escaped, characterReference, - updateLastStrPos, anyOrderedListMarker, orderedListMarker, charRef, @@ -63,18 +65,24 @@ module Text.Pandoc.Parsing ( (>>~), widthsFromIndices, gridTableWith, readWith, + readWithWarnings, + readWithM, testStringWith, - getOption, guardEnabled, guardDisabled, + updateLastStrPos, + notAfterString, ParserState (..), HasReaderOptions (..), HasHeaderMap (..), HasIdentifierList (..), + HasMacros (..), + HasLastStrPosition (..), defaultParserState, HeaderType (..), ParserContext (..), QuoteContext (..), + HasQuoteContext (..), NoteTable, NoteTable', KeyTable, @@ -83,7 +91,6 @@ module Text.Pandoc.Parsing ( (>>~), toKey, registerHeader, smartPunctuation, - withQuoteContext, singleQuoteStart, singleQuoteEnd, doubleQuoteStart, @@ -92,15 +99,20 @@ module Text.Pandoc.Parsing ( (>>~), apostrophe, dash, nested, + citeKey, macro, applyMacros', Parser, + ParserT, F(..), runF, askF, asksF, + token, -- * Re-exports from Text.Pandoc.Parsec + Stream, runParser, + runParserT, parse, anyToken, getInput, @@ -151,7 +163,7 @@ module Text.Pandoc.Parsing ( (>>~), setSourceColumn, setSourceLine, newPos, - token + addWarning ) where @@ -161,26 +173,30 @@ import Text.Pandoc.Builder (Blocks, Inlines, rawBlock, HasMeta(..)) import qualified Text.Pandoc.Builder as B import Text.Pandoc.XML (fromEntities) import qualified Text.Pandoc.UTF8 as UTF8 (putStrLn) -import Text.Parsec +import Text.Parsec hiding (token) import Text.Parsec.Pos (newPos) -import Data.Char ( toLower, toUpper, ord, chr, isAscii, isAlphaNum, isDigit, +import Data.Char ( toLower, toUpper, ord, chr, isAscii, isAlphaNum, isHexDigit, isSpace ) import Data.List ( intercalate, transpose ) import Text.Pandoc.Shared import qualified Data.Map as M -import Text.TeXMath.Macros (applyMacros, Macro, parseMacroDefinitions) +import Text.TeXMath.Readers.TeX.Macros (applyMacros, Macro, + parseMacroDefinitions) import Text.Pandoc.Compat.TagSoupEntity ( lookupEntity ) import Text.Pandoc.Asciify (toAsciiChar) import Data.Default import qualified Data.Set as Set import Control.Monad.Reader -import Control.Applicative ((*>), (<*), (<$), liftA2) +import Control.Monad.Identity +import Control.Applicative ((<$>), (<*>), (*>), (<*), (<$), Applicative) import Data.Monoid import Data.Maybe (catMaybes) type Parser t s = Parsec t s -newtype F a = F { unF :: Reader ParserState a } deriving (Monad, Functor) +type ParserT = ParsecT + +newtype F a = F { unF :: Reader ParserState a } deriving (Monad, Applicative, Functor) runF :: F a -> ParserState -> a runF = runReader . unF @@ -196,13 +212,8 @@ instance Monoid a => Monoid (F a) where mappend = liftM2 mappend mconcat = liftM mconcat . sequence --- | Like >>, but returns the operation on the left. --- (Suggested by Tillmann Rendel on Haskell-cafe list.) -(>>~) :: (Monad m) => m a -> m b -> m a -a >>~ b = a >>= \x -> b >> return x - -- | Parse any line of text -anyLine :: Parser [Char] st [Char] +anyLine :: Stream [Char] m Char => ParserT [Char] st m [Char] anyLine = do -- This is much faster than: -- manyTill anyChar newline @@ -218,9 +229,10 @@ anyLine = do _ -> mzero -- | Like @manyTill@, but reads at least one item. -many1Till :: Parser [tok] st a - -> Parser [tok] st end - -> Parser [tok] st [a] +many1Till :: Stream s m t + => ParserT s st m a + -> ParserT s st m end + -> ParserT s st m [a] many1Till p end = do first <- p rest <- manyTill p end @@ -229,21 +241,21 @@ many1Till p end = do -- | A more general form of @notFollowedBy@. This one allows any -- type of parser to be specified, and succeeds only if that parser fails. -- It does not consume any input. -notFollowedBy' :: Show b => Parser [a] st b -> Parser [a] st () +notFollowedBy' :: (Show b, Stream s m a) => ParserT s st m b -> ParserT s st m () notFollowedBy' p = try $ join $ do a <- try p return (unexpected (show a)) <|> return (return ()) -- (This version due to Andrew Pimlott on the Haskell mailing list.) -oneOfStrings' :: (Char -> Char -> Bool) -> [String] -> Parser [Char] st String +oneOfStrings' :: Stream s m Char => (Char -> Char -> Bool) -> [String] -> ParserT s st m String oneOfStrings' _ [] = fail "no strings" oneOfStrings' matches strs = try $ do c <- anyChar let strs' = [xs | (x:xs) <- strs, x `matches` c] case strs' of [] -> fail "not found" - _ -> (c:) `fmap` oneOfStrings' matches strs' + _ -> (c:) <$> oneOfStrings' matches strs' <|> if "" `elem` strs' then return [c] else fail "not found" @@ -251,11 +263,11 @@ oneOfStrings' matches strs = try $ do -- | Parses one of a list of strings. If the list contains -- two strings one of which is a prefix of the other, the longer -- string will be matched if possible. -oneOfStrings :: [String] -> Parser [Char] st String +oneOfStrings :: Stream s m Char => [String] -> ParserT s st m String oneOfStrings = oneOfStrings' (==) -- | Parses one of a list of strings (tried in order), case insensitive. -oneOfStringsCI :: [String] -> Parser [Char] st String +oneOfStringsCI :: Stream s m Char => [String] -> ParserT s st m String oneOfStringsCI = oneOfStrings' ciMatch where ciMatch x y = toLower' x == toLower' y -- this optimizes toLower by checking common ASCII case @@ -266,35 +278,35 @@ oneOfStringsCI = oneOfStrings' ciMatch | otherwise = toLower c -- | Parses a space or tab. -spaceChar :: Parser [Char] st Char +spaceChar :: Stream s m Char => ParserT s st m Char spaceChar = satisfy $ \c -> c == ' ' || c == '\t' -- | Parses a nonspace, nonnewline character. -nonspaceChar :: Parser [Char] st Char +nonspaceChar :: Stream s m Char => ParserT s st m Char nonspaceChar = satisfy $ flip notElem ['\t', '\n', ' ', '\r'] -- | Skips zero or more spaces or tabs. -skipSpaces :: Parser [Char] st () +skipSpaces :: Stream s m Char => ParserT s st m () skipSpaces = skipMany spaceChar -- | Skips zero or more spaces or tabs, then reads a newline. -blankline :: Parser [Char] st Char +blankline :: Stream s m Char => ParserT s st m Char blankline = try $ skipSpaces >> newline -- | Parses one or more blank lines and returns a string of newlines. -blanklines :: Parser [Char] st [Char] +blanklines :: Stream s m Char => ParserT s st m [Char] blanklines = many1 blankline -- | Parses material enclosed between start and end parsers. -enclosed :: Parser [Char] st t -- ^ start parser - -> Parser [Char] st end -- ^ end parser - -> Parser [Char] st a -- ^ content parser (to be used repeatedly) - -> Parser [Char] st [a] +enclosed :: Stream s m Char => ParserT s st m t -- ^ start parser + -> ParserT s st m end -- ^ end parser + -> ParserT s st m a -- ^ content parser (to be used repeatedly) + -> ParserT s st m [a] enclosed start end parser = try $ start >> notFollowedBy space >> many1Till parser end -- | Parse string, case insensitive. -stringAnyCase :: [Char] -> Parser [Char] st String +stringAnyCase :: Stream s m Char => [Char] -> ParserT s st m String stringAnyCase [] = string "" stringAnyCase (x:xs) = do firstChar <- char (toUpper x) <|> char (toLower x) @@ -302,7 +314,7 @@ stringAnyCase (x:xs) = do return (firstChar:rest) -- | Parse contents of 'str' using 'parser' and return result. -parseFromString :: Parser [tok] st a -> [tok] -> Parser [tok] st a +parseFromString :: Stream s m t => ParserT s st m a -> s -> ParserT s st m a parseFromString parser str = do oldPos <- getPosition oldInput <- getInput @@ -313,7 +325,7 @@ parseFromString parser str = do return result -- | Parse raw line block up to and including blank lines. -lineClump :: Parser [Char] st String +lineClump :: Stream [Char] m Char => ParserT [Char] st m String lineClump = blanklines <|> (many1 (notFollowedBy blankline >> anyLine) >>= return . unlines) @@ -322,8 +334,8 @@ lineClump = blanklines -- pairs of open and close, which must be different. For example, -- @charsInBalanced '(' ')' anyChar@ will parse "(hello (there))" -- and return "hello (there)". -charsInBalanced :: Char -> Char -> Parser [Char] st Char - -> Parser [Char] st String +charsInBalanced :: Stream s m Char => Char -> Char -> ParserT s st m Char + -> ParserT s st m String charsInBalanced open close parser = try $ do char open let isDelim c = c == open || c == close @@ -347,8 +359,8 @@ uppercaseRomanDigits :: [Char] uppercaseRomanDigits = map toUpper lowercaseRomanDigits -- | Parses a roman numeral (uppercase or lowercase), returns number. -romanNumeral :: Bool -- ^ Uppercase if true - -> Parser [Char] st Int +romanNumeral :: Stream s m Char => Bool -- ^ Uppercase if true + -> ParserT s st m Int romanNumeral upperCase = do let romanDigits = if upperCase then uppercaseRomanDigits @@ -380,12 +392,12 @@ romanNumeral upperCase = do -- | Parses an email address; returns original and corresponding -- escaped mailto: URI. -emailAddress :: Parser [Char] st (String, String) -emailAddress = try $ liftA2 toResult mailbox (char '@' *> domain) +emailAddress :: Stream s m Char => ParserT s st m (String, String) +emailAddress = try $ toResult <$> mailbox <*> (char '@' *> domain) where toResult mbox dom = let full = fromEntities $ mbox ++ '@':dom in (full, escapeURI $ "mailto:" ++ full) - mailbox = intercalate "." `fmap` (emailWord `sepby1` dot) - domain = intercalate "." `fmap` (subdomain `sepby1` dot) + mailbox = intercalate "." <$> (emailWord `sepby1` dot) + domain = intercalate "." <$> (subdomain `sepby1` dot) dot = char '.' subdomain = many1 $ alphaNum <|> innerPunct innerPunct = try (satisfy (\c -> isEmailPunct c || c == '@') <* @@ -395,11 +407,11 @@ emailAddress = try $ liftA2 toResult mailbox (char '@' *> domain) isEmailPunct c = c `elem` "!\"#$%&'*+-/=?^_{|}~;" -- note: sepBy1 from parsec consumes input when sep -- succeeds and p fails, so we use this variant here. - sepby1 p sep = liftA2 (:) p (many (try $ sep >> p)) + sepby1 p sep = (:) <$> p <*> (many (try $ sep >> p)) -- Schemes from http://www.iana.org/assignments/uri-schemes.html plus --- the unofficial schemes coap, doi, javascript. +-- the unofficial schemes coap, doi, javascript, isbn, pmid schemes :: [String] schemes = ["coap","doi","javascript","aaa","aaas","about","acap","cap","cid", "crid","data","dav","dict","dns","file","ftp","geo","go","gopher", @@ -421,13 +433,13 @@ schemes = ["coap","doi","javascript","aaa","aaas","about","acap","cap","cid", "rtmp","secondlife","sftp","sgn","skype","smb","soldat","spotify", "ssh","steam","svn","teamspeak","things","udp","unreal","ut2004", "ventrilo","view-source","webcal","wtai","wyciwyg","xfire","xri", - "ymsgr"] + "ymsgr", "isbn", "pmid"] -uriScheme :: Parser [Char] st String +uriScheme :: Stream s m Char => ParserT s st m String uriScheme = oneOfStringsCI schemes -- | Parses a URI. Returns pair of original and URI-escaped version. -uri :: Parser [Char] st (String, String) +uri :: Stream [Char] m Char => ParserT [Char] st m (String, String) uri = try $ do scheme <- uriScheme char ':' @@ -442,13 +454,13 @@ uri = try $ do let percentEscaped = try $ char '%' >> skipMany1 (satisfy isHexDigit) let entity = () <$ characterReference let punct = skipMany1 (char ',') - <|> () <$ (satisfy (\c -> not (isSpace c) && c /= '<')) + <|> () <$ (satisfy (\c -> not (isSpace c) && c /= '<' && c /= '>')) let uriChunk = skipMany1 wordChar <|> percentEscaped <|> entity <|> (try $ punct >> lookAhead (void (satisfy isWordChar) <|> percentEscaped)) - str <- snd `fmap` withRaw (skipMany1 ( () <$ + str <- snd <$> withRaw (skipMany1 ( () <$ (enclosed (char '(') (char ')') uriChunk <|> enclosed (char '{') (char '}') uriChunk <|> enclosed (char '[') (char ']') uriChunk) @@ -457,24 +469,49 @@ uri = try $ do let uri' = scheme ++ ":" ++ fromEntities str' return (uri', escapeURI uri') -mathInlineWith :: String -> String -> Parser [Char] st String +mathInlineWith :: Stream s m Char => String -> String -> ParserT s st m String mathInlineWith op cl = try $ do string op notFollowedBy space - words' <- many1Till (count 1 (noneOf "\n\\") - <|> (char '\\' >> anyChar >>= \c -> return ['\\',c]) - <|> count 1 newline <* notFollowedBy' blankline - *> return " ") - (try $ string cl) + words' <- many1Till (count 1 (noneOf " \t\n\\") + <|> (char '\\' >> + -- This next clause is needed because \text{..} can + -- contain $, \(\), etc. + (try (string "text" >> + (("\\text" ++) <$> inBalancedBraces 0 "")) + <|> (\c -> ['\\',c]) <$> anyChar)) + <|> do (blankline <* notFollowedBy' blankline) <|> + (oneOf " \t" <* skipMany (oneOf " \t")) + notFollowedBy (char '$') + return " " + ) (try $ string cl) notFollowedBy digit -- to prevent capture of $5 return $ concat words' - -mathDisplayWith :: String -> String -> Parser [Char] st String + where + inBalancedBraces :: Stream s m Char => Int -> String -> ParserT s st m String + inBalancedBraces 0 "" = do + c <- anyChar + if c == '{' + then inBalancedBraces 1 "{" + else mzero + inBalancedBraces 0 s = return $ reverse s + inBalancedBraces numOpen ('\\':xs) = do + c <- anyChar + inBalancedBraces numOpen (c:'\\':xs) + inBalancedBraces numOpen xs = do + c <- anyChar + case c of + '}' -> inBalancedBraces (numOpen - 1) (c:xs) + '{' -> inBalancedBraces (numOpen + 1) (c:xs) + _ -> inBalancedBraces numOpen (c:xs) + +mathDisplayWith :: Stream s m Char => String -> String -> ParserT s st m String mathDisplayWith op cl = try $ do string op - many1Till (noneOf "\n" <|> (newline >>~ notFollowedBy' blankline)) (try $ string cl) + many1Till (noneOf "\n" <|> (newline <* notFollowedBy' blankline)) (try $ string cl) -mathDisplay :: Parser [Char] ParserState String +mathDisplay :: (HasReaderOptions st, Stream s m Char) + => ParserT s st m String mathDisplay = (guardEnabled Ext_tex_math_dollars >> mathDisplayWith "$$" "$$") <|> (guardEnabled Ext_tex_math_single_backslash >> @@ -482,7 +519,8 @@ mathDisplay = <|> (guardEnabled Ext_tex_math_double_backslash >> mathDisplayWith "\\\\[" "\\\\]") -mathInline :: Parser [Char] ParserState String +mathInline :: (HasReaderOptions st , Stream s m Char) + => ParserT s st m String mathInline = (guardEnabled Ext_tex_math_dollars >> mathInlineWith "$" "$") <|> (guardEnabled Ext_tex_math_single_backslash >> @@ -494,8 +532,9 @@ mathInline = -- displacement (the difference between the source column at the end -- and the source column at the beginning). Vertical displacement -- (source row) is ignored. -withHorizDisplacement :: Parser [Char] st a -- ^ Parser to apply - -> Parser [Char] st (a, Int) -- ^ (result, displacement) +withHorizDisplacement :: Stream s m Char + => ParserT s st m a -- ^ Parser to apply + -> ParserT s st m (a, Int) -- ^ (result, displacement) withHorizDisplacement parser = do pos1 <- getPosition result <- parser @@ -504,7 +543,7 @@ withHorizDisplacement parser = do -- | Applies a parser and returns the raw string that was parsed, -- along with the value produced by the parser. -withRaw :: Parser [Char] st a -> Parser [Char] st (a, [Char]) +withRaw :: Stream [Char] m Char => ParsecT [Char] st m a -> ParsecT [Char] st m (a, [Char]) withRaw parser = do pos1 <- getPosition inp <- getInput @@ -520,12 +559,13 @@ withRaw parser = do return (result, raw) -- | Parses backslash, then applies character parser. -escaped :: Parser [Char] st Char -- ^ Parser for character to escape - -> Parser [Char] st Char +escaped :: Stream s m Char + => ParserT s st m Char -- ^ Parser for character to escape + -> ParserT s st m Char escaped parser = try $ char '\\' >> parser -- | Parse character entity. -characterReference :: Parser [Char] st Char +characterReference :: Stream s m Char => ParserT s st m Char characterReference = try $ do char '&' ent <- many1Till nonspaceChar (char ';') @@ -534,19 +574,19 @@ characterReference = try $ do Nothing -> fail "entity not found" -- | Parses an uppercase roman numeral and returns (UpperRoman, number). -upperRoman :: Parser [Char] st (ListNumberStyle, Int) +upperRoman :: Stream s m Char => ParserT s st m (ListNumberStyle, Int) upperRoman = do num <- romanNumeral True return (UpperRoman, num) -- | Parses a lowercase roman numeral and returns (LowerRoman, number). -lowerRoman :: Parser [Char] st (ListNumberStyle, Int) +lowerRoman :: Stream s m Char => ParserT s st m (ListNumberStyle, Int) lowerRoman = do num <- romanNumeral False return (LowerRoman, num) -- | Parses a decimal numeral and returns (Decimal, number). -decimal :: Parser [Char] st (ListNumberStyle, Int) +decimal :: Stream s m Char => ParserT s st m (ListNumberStyle, Int) decimal = do num <- many1 digit return (Decimal, read num) @@ -555,7 +595,8 @@ decimal = do -- returns (DefaultStyle, [next example number]). The next -- example number is incremented in parser state, and the label -- (if present) is added to the label table. -exampleNum :: Parser [Char] ParserState (ListNumberStyle, Int) +exampleNum :: Stream s m Char + => ParserT s ParserState m (ListNumberStyle, Int) exampleNum = do char '@' lab <- many (alphaNum <|> satisfy (\c -> c == '_' || c == '-')) @@ -569,38 +610,39 @@ exampleNum = do return (Example, num) -- | Parses a '#' returns (DefaultStyle, 1). -defaultNum :: Parser [Char] st (ListNumberStyle, Int) +defaultNum :: Stream s m Char => ParserT s st m (ListNumberStyle, Int) defaultNum = do char '#' return (DefaultStyle, 1) -- | Parses a lowercase letter and returns (LowerAlpha, number). -lowerAlpha :: Parser [Char] st (ListNumberStyle, Int) +lowerAlpha :: Stream s m Char => ParserT s st m (ListNumberStyle, Int) lowerAlpha = do ch <- oneOf ['a'..'z'] return (LowerAlpha, ord ch - ord 'a' + 1) -- | Parses an uppercase letter and returns (UpperAlpha, number). -upperAlpha :: Parser [Char] st (ListNumberStyle, Int) +upperAlpha :: Stream s m Char => ParserT s st m (ListNumberStyle, Int) upperAlpha = do ch <- oneOf ['A'..'Z'] return (UpperAlpha, ord ch - ord 'A' + 1) -- | Parses a roman numeral i or I -romanOne :: Parser [Char] st (ListNumberStyle, Int) +romanOne :: Stream s m Char => ParserT s st m (ListNumberStyle, Int) romanOne = (char 'i' >> return (LowerRoman, 1)) <|> (char 'I' >> return (UpperRoman, 1)) -- | Parses an ordered list marker and returns list attributes. -anyOrderedListMarker :: Parser [Char] ParserState ListAttributes +anyOrderedListMarker :: Stream s m Char => ParserT s ParserState m ListAttributes anyOrderedListMarker = choice $ [delimParser numParser | delimParser <- [inPeriod, inOneParen, inTwoParens], numParser <- [decimal, exampleNum, defaultNum, romanOne, lowerAlpha, lowerRoman, upperAlpha, upperRoman]] -- | Parses a list number (num) followed by a period, returns list attributes. -inPeriod :: Parser [Char] st (ListNumberStyle, Int) - -> Parser [Char] st ListAttributes +inPeriod :: Stream s m Char + => ParserT s st m (ListNumberStyle, Int) + -> ParserT s st m ListAttributes inPeriod num = try $ do (style, start) <- num char '.' @@ -610,16 +652,18 @@ inPeriod num = try $ do return (start, style, delim) -- | Parses a list number (num) followed by a paren, returns list attributes. -inOneParen :: Parser [Char] st (ListNumberStyle, Int) - -> Parser [Char] st ListAttributes +inOneParen :: Stream s m Char + => ParserT s st m (ListNumberStyle, Int) + -> ParserT s st m ListAttributes inOneParen num = try $ do (style, start) <- num char ')' return (start, style, OneParen) -- | Parses a list number (num) enclosed in parens, returns list attributes. -inTwoParens :: Parser [Char] st (ListNumberStyle, Int) - -> Parser [Char] st ListAttributes +inTwoParens :: Stream s m Char + => ParserT s st m (ListNumberStyle, Int) + -> ParserT s st m ListAttributes inTwoParens num = try $ do char '(' (style, start) <- num @@ -628,9 +672,10 @@ inTwoParens num = try $ do -- | Parses an ordered list marker with a given style and delimiter, -- returns number. -orderedListMarker :: ListNumberStyle +orderedListMarker :: Stream s m Char + => ListNumberStyle -> ListNumberDelim - -> Parser [Char] ParserState Int + -> ParserT s ParserState m Int orderedListMarker style delim = do let num = defaultNum <|> -- # can continue any kind of list case style of @@ -650,12 +695,12 @@ orderedListMarker style delim = do return start -- | Parses a character reference and returns a Str element. -charRef :: Parser [Char] st Inline +charRef :: Stream s m Char => ParserT s st m Inline charRef = do c <- characterReference return $ Str [c] -lineBlockLine :: Parser [Char] st String +lineBlockLine :: Stream [Char] m Char => ParserT [Char] st m String lineBlockLine = try $ do char '|' char ' ' @@ -666,7 +711,7 @@ lineBlockLine = try $ do return $ white ++ unwords (line : continuations) -- | Parses an RST-style line block and returns a list of strings. -lineBlockLines :: Parser [Char] st [String] +lineBlockLines :: Stream [Char] m Char => ParserT [Char] st m [String] lineBlockLines = try $ do lines' <- many1 lineBlockLine skipMany1 $ blankline <|> try (char '|' >> blankline) @@ -674,11 +719,12 @@ lineBlockLines = try $ do -- | Parse a table using 'headerParser', 'rowParser', -- 'lineParser', and 'footerParser'. -tableWith :: Parser [Char] ParserState ([[Block]], [Alignment], [Int]) - -> ([Int] -> Parser [Char] ParserState [[Block]]) - -> Parser [Char] ParserState sep - -> Parser [Char] ParserState end - -> Parser [Char] ParserState Block +tableWith :: Stream s m Char + => ParserT s ParserState m ([[Block]], [Alignment], [Int]) + -> ([Int] -> ParserT s ParserState m [[Block]]) + -> ParserT s ParserState m sep + -> ParserT s ParserState m end + -> ParserT s ParserState m Block tableWith headerParser rowParser lineParser footerParser = try $ do (heads, aligns, indices) <- headerParser lines' <- rowParser indices `sepEndBy1` lineParser @@ -720,9 +766,10 @@ widthsFromIndices numColumns' indices = -- (which may be grid), then the rows, -- which may be grid, separated by blank lines, and -- ending with a footer (dashed line followed by blank line). -gridTableWith :: Parser [Char] ParserState [Block] -- ^ Block list parser +gridTableWith :: Stream [Char] m Char + => ParserT [Char] ParserState m [Block] -- ^ Block list parser -> Bool -- ^ Headerless table - -> Parser [Char] ParserState Block + -> ParserT [Char] ParserState m Block gridTableWith blocks headless = tableWith (gridTableHeader headless blocks) (gridTableRow blocks) (gridTableSep '-') gridTableFooter @@ -731,27 +778,28 @@ gridTableSplitLine :: [Int] -> String -> [String] gridTableSplitLine indices line = map removeFinalBar $ tail $ splitStringByIndices (init indices) $ trimr line -gridPart :: Char -> Parser [Char] st (Int, Int) +gridPart :: Stream s m Char => Char -> ParserT s st m (Int, Int) gridPart ch = do dashes <- many1 (char ch) char '+' return (length dashes, length dashes + 1) -gridDashedLines :: Char -> Parser [Char] st [(Int,Int)] -gridDashedLines ch = try $ char '+' >> many1 (gridPart ch) >>~ blankline +gridDashedLines :: Stream s m Char => Char -> ParserT s st m [(Int,Int)] +gridDashedLines ch = try $ char '+' >> many1 (gridPart ch) <* blankline removeFinalBar :: String -> String removeFinalBar = reverse . dropWhile (`elem` " \t") . dropWhile (=='|') . reverse -- | Separator between rows of grid table. -gridTableSep :: Char -> Parser [Char] ParserState Char +gridTableSep :: Stream s m Char => Char -> ParserT s ParserState m Char gridTableSep ch = try $ gridDashedLines ch >> return '\n' -- | Parse header for a grid table. -gridTableHeader :: Bool -- ^ Headerless table - -> Parser [Char] ParserState [Block] - -> Parser [Char] ParserState ([[Block]], [Alignment], [Int]) +gridTableHeader :: Stream [Char] m Char + => Bool -- ^ Headerless table + -> ParserT [Char] ParserState m [Block] + -> ParserT [Char] ParserState m ([[Block]], [Alignment], [Int]) gridTableHeader headless blocks = try $ do optional blanklines dashes <- gridDashedLines '-' @@ -774,16 +822,17 @@ gridTableHeader headless blocks = try $ do heads <- mapM (parseFromString blocks) $ map trim rawHeads return (heads, aligns, indices) -gridTableRawLine :: [Int] -> Parser [Char] ParserState [String] +gridTableRawLine :: Stream s m Char => [Int] -> ParserT s ParserState m [String] gridTableRawLine indices = do char '|' line <- many1Till anyChar newline return (gridTableSplitLine indices line) -- | Parse row of grid table. -gridTableRow :: Parser [Char] ParserState [Block] +gridTableRow :: Stream [Char] m Char + => ParserT [Char] ParserState m [Block] -> [Int] - -> Parser [Char] ParserState [[Block]] + -> ParserT [Char] ParserState m [[Block]] gridTableRow blocks indices = do colLines <- many1 (gridTableRawLine indices) let cols = map ((++ "\n") . unlines . removeOneLeadingSpace) $ @@ -802,19 +851,21 @@ compactifyCell :: [Block] -> [Block] compactifyCell bs = head $ compactify [bs] -- | Parse footer for a grid table. -gridTableFooter :: Parser [Char] ParserState [Char] +gridTableFooter :: Stream s m Char => ParserT s ParserState m [Char] gridTableFooter = blanklines --- --- | Parse a string with a given parser and state. -readWith :: Parser [Char] st a -- ^ parser - -> st -- ^ initial state - -> [Char] -- ^ input - -> a -readWith parser state input = - case runParser parser state "source" input of - Left err' -> +-- | Removes the ParsecT layer from the monad transformer stack +readWithM :: (Monad m, Functor m) + => ParserT [Char] st m a -- ^ parser + -> st -- ^ initial state + -> String -- ^ input + -> m a +readWithM parser state input = + handleError <$> (runParserT parser state "source" input) + where + handleError (Left err') = let errPos = errorPos err' errLine = sourceLine errPos errColumn = sourceColumn errPos @@ -822,11 +873,28 @@ readWith parser state input = in error $ "\nError at " ++ show err' ++ "\n" ++ theline ++ "\n" ++ replicate (errColumn - 1) ' ' ++ "^" - Right result -> result + handleError (Right result) = result + +-- | Parse a string with a given parser and state +readWith :: Parser [Char] st a + -> st + -> String + -> a +readWith p t inp = runIdentity $ readWithM p t inp + +readWithWarnings :: Parser [Char] ParserState a + -> ParserState + -> String + -> (a, [String]) +readWithWarnings p = readWith $ do + doc <- p + warnings <- stateWarnings <$> getState + return (doc, warnings) -- | Parse a string with @parser@ (for testing). -testStringWith :: (Show a) => Parser [Char] ParserState a - -> String +testStringWith :: (Show a, Stream [Char] Identity Char) + => ParserT [Char] ParserState Identity a + -> [Char] -> IO () testStringWith parser str = UTF8.putStrLn $ show $ readWith parser defaultParserState str @@ -853,6 +921,12 @@ data ParserState = ParserState stateHasChapters :: Bool, -- ^ True if \chapter encountered stateMacros :: [Macro], -- ^ List of macros defined so far stateRstDefaultRole :: String, -- ^ Current rST default interpreted text role + stateRstCustomRoles :: M.Map String (String, Maybe String, Attr), -- ^ Current rST custom text roles + -- Triple represents: 1) Base role, 2) Optional format (only for :raw: + -- roles), 3) Additional classes (rest of Attr is unused)). + stateCaption :: Maybe Inlines, -- ^ Caption in current environment + stateInHtmlBlock :: Maybe String, -- ^ Tag type of HTML block being parsed + stateMarkdownAttribute :: Bool, -- ^ True if in markdown=1 context stateWarnings :: [String] -- ^ Warnings generated by the parser } @@ -865,33 +939,62 @@ instance HasMeta ParserState where deleteMeta field st = st{ stateMeta = deleteMeta field $ stateMeta st } -class Monad m => HasReaderOptions m where - askReaderOption :: (ReaderOptions -> b) -> m b - -class Monad m => HasHeaderMap m where - getHeaderMap :: m (M.Map Inlines String) - putHeaderMap :: M.Map Inlines String -> m () - modifyHeaderMap :: (M.Map Inlines String -> M.Map Inlines String) -> m () - -- default - modifyHeaderMap f = getHeaderMap >>= putHeaderMap . f - -class Monad m => HasIdentifierList m where - getIdentifierList :: m [String] - putIdentifierList :: [String] -> m () - modifyIdentifierList :: ([String] -> [String]) -> m () +class HasReaderOptions st where + extractReaderOptions :: st -> ReaderOptions + getOption :: (Stream s m t) => (ReaderOptions -> b) -> ParserT s st m b -- default - modifyIdentifierList f = getIdentifierList >>= putIdentifierList . f - -instance HasReaderOptions (Parser s ParserState) where - askReaderOption = getOption - -instance HasHeaderMap (Parser s ParserState) where - getHeaderMap = fmap stateHeaders getState - putHeaderMap hm = updateState $ \st -> st{ stateHeaders = hm } - -instance HasIdentifierList (Parser s ParserState) where - getIdentifierList = fmap stateIdentifiers getState - putIdentifierList l = updateState $ \st -> st{ stateIdentifiers = l } + getOption f = (f . extractReaderOptions) <$> getState + +class HasQuoteContext st m where + getQuoteContext :: (Stream s m t) => ParsecT s st m QuoteContext + withQuoteContext :: QuoteContext -> ParsecT s st m a -> ParsecT s st m a + +instance Monad m => HasQuoteContext ParserState m where + getQuoteContext = stateQuoteContext <$> getState + withQuoteContext context parser = do + oldState <- getState + let oldQuoteContext = stateQuoteContext oldState + setState oldState { stateQuoteContext = context } + result <- parser + newState <- getState + setState newState { stateQuoteContext = oldQuoteContext } + return result + +instance HasReaderOptions ParserState where + extractReaderOptions = stateOptions + +class HasHeaderMap st where + extractHeaderMap :: st -> M.Map Inlines String + updateHeaderMap :: (M.Map Inlines String -> M.Map Inlines String) -> + st -> st + +instance HasHeaderMap ParserState where + extractHeaderMap = stateHeaders + updateHeaderMap f st = st{ stateHeaders = f $ stateHeaders st } + +class HasIdentifierList st where + extractIdentifierList :: st -> [String] + updateIdentifierList :: ([String] -> [String]) -> st -> st + +instance HasIdentifierList ParserState where + extractIdentifierList = stateIdentifiers + updateIdentifierList f st = st{ stateIdentifiers = f $ stateIdentifiers st } + +class HasMacros st where + extractMacros :: st -> [Macro] + updateMacros :: ([Macro] -> [Macro]) -> st -> st + +instance HasMacros ParserState where + extractMacros = stateMacros + updateMacros f st = st{ stateMacros = f $ stateMacros st } + +class HasLastStrPosition st where + setLastStrPos :: SourcePos -> st -> st + getLastStrPos :: st -> Maybe SourcePos + +instance HasLastStrPosition ParserState where + setLastStrPos pos st = st{ stateLastStrPos = Just pos } + getLastStrPos st = stateLastStrPos st defaultParserState :: ParserState defaultParserState = @@ -915,19 +1018,31 @@ defaultParserState = stateHasChapters = False, stateMacros = [], stateRstDefaultRole = "title-reference", + stateRstCustomRoles = M.empty, + stateCaption = Nothing, + stateInHtmlBlock = Nothing, + stateMarkdownAttribute = False, stateWarnings = []} -getOption :: (ReaderOptions -> a) -> Parser s ParserState a -getOption f = (f . stateOptions) `fmap` getState - -- | Succeed only if the extension is enabled. -guardEnabled :: Extension -> Parser s ParserState () +guardEnabled :: (Stream s m a, HasReaderOptions st) => Extension -> ParserT s st m () guardEnabled ext = getOption readerExtensions >>= guard . Set.member ext -- | Succeed only if the extension is disabled. -guardDisabled :: Extension -> Parser s ParserState () +guardDisabled :: (Stream s m a, HasReaderOptions st) => Extension -> ParserT s st m () guardDisabled ext = getOption readerExtensions >>= guard . not . Set.member ext +-- | Update the position on which the last string ended. +updateLastStrPos :: (Stream s m a, HasLastStrPosition st) => ParserT s st m () +updateLastStrPos = getPosition >>= updateState . setLastStrPos + +-- | Whether we are right after the end of a string. +notAfterString :: (Stream s m a, HasLastStrPosition st) => ParserT s st m Bool +notAfterString = do + pos <- getPosition + st <- getState + return $ getLastStrPos st /= Just pos + data HeaderType = SingleHeader Char -- ^ Single line of characters underneath | DoubleHeader Char -- ^ Lines of characters above and below @@ -962,11 +1077,11 @@ type SubstTable = M.Map Key Inlines -- and the auto_identifers extension is set, generate a new -- unique identifier, and update the list of identifiers -- in state. -registerHeader :: (HasReaderOptions m, HasHeaderMap m, HasIdentifierList m) - => Attr -> Inlines -> m Attr +registerHeader :: (Stream s m a, HasReaderOptions st, HasHeaderMap st, HasIdentifierList st) + => Attr -> Inlines -> ParserT s st m Attr registerHeader (ident,classes,kvs) header' = do - ids <- getIdentifierList - exts <- askReaderOption readerExtensions + ids <- extractIdentifierList <$> getState + exts <- getOption readerExtensions let insert' = M.insertWith (\_new old -> old) if null ident && Ext_auto_identifiers `Set.member` exts then do @@ -974,158 +1089,149 @@ registerHeader (ident,classes,kvs) header' = do let id'' = if Ext_ascii_identifiers `Set.member` exts then catMaybes $ map toAsciiChar id' else id' - putIdentifierList $ if id' == id'' - then id' : ids - else id' : id'' : ids - modifyHeaderMap $ insert' header' id' + updateState $ updateIdentifierList $ + if id' == id'' then (id' :) else ([id', id''] ++) + updateState $ updateHeaderMap $ insert' header' id' return (id'',classes,kvs) else do - unless (null ident) $ modifyHeaderMap $ insert' header' ident + unless (null ident) $ + updateState $ updateHeaderMap $ insert' header' ident return (ident,classes,kvs) -- | Fail unless we're in "smart typography" mode. -failUnlessSmart :: Parser [tok] ParserState () +failUnlessSmart :: (Stream s m a, HasReaderOptions st) => ParserT s st m () failUnlessSmart = getOption readerSmart >>= guard -smartPunctuation :: Parser [Char] ParserState Inline - -> Parser [Char] ParserState Inline +smartPunctuation :: (HasReaderOptions st, HasLastStrPosition st, HasQuoteContext st m, Stream s m Char) + => ParserT s st m Inlines + -> ParserT s st m Inlines smartPunctuation inlineParser = do failUnlessSmart choice [ quoted inlineParser, apostrophe, dash, ellipses ] -apostrophe :: Parser [Char] ParserState Inline -apostrophe = (char '\'' <|> char '\8217') >> return (Str "\x2019") +apostrophe :: Stream s m Char => ParserT s st m Inlines +apostrophe = (char '\'' <|> char '\8217') >> return (B.str "\x2019") -quoted :: Parser [Char] ParserState Inline - -> Parser [Char] ParserState Inline +quoted :: (HasLastStrPosition st, HasQuoteContext st m, Stream s m Char) + => ParserT s st m Inlines + -> ParserT s st m Inlines quoted inlineParser = doubleQuoted inlineParser <|> singleQuoted inlineParser -withQuoteContext :: QuoteContext - -> Parser [tok] ParserState a - -> Parser [tok] ParserState a -withQuoteContext context parser = do - oldState <- getState - let oldQuoteContext = stateQuoteContext oldState - setState oldState { stateQuoteContext = context } - result <- parser - newState <- getState - setState newState { stateQuoteContext = oldQuoteContext } - return result - -singleQuoted :: Parser [Char] ParserState Inline - -> Parser [Char] ParserState Inline +singleQuoted :: (HasLastStrPosition st, HasQuoteContext st m, Stream s m Char) + => ParserT s st m Inlines + -> ParserT s st m Inlines singleQuoted inlineParser = try $ do singleQuoteStart withQuoteContext InSingleQuote $ many1Till inlineParser singleQuoteEnd >>= - return . Quoted SingleQuote . normalizeSpaces + return . B.singleQuoted . mconcat -doubleQuoted :: Parser [Char] ParserState Inline - -> Parser [Char] ParserState Inline +doubleQuoted :: (HasQuoteContext st m, Stream s m Char) + => ParserT s st m Inlines + -> ParserT s st m Inlines doubleQuoted inlineParser = try $ do doubleQuoteStart - withQuoteContext InDoubleQuote $ do - contents <- manyTill inlineParser doubleQuoteEnd - return . Quoted DoubleQuote . normalizeSpaces $ contents + withQuoteContext InDoubleQuote $ manyTill inlineParser doubleQuoteEnd >>= + return . B.doubleQuoted . mconcat -failIfInQuoteContext :: QuoteContext -> Parser [tok] ParserState () +failIfInQuoteContext :: (HasQuoteContext st m, Stream s m t) + => QuoteContext + -> ParserT s st m () failIfInQuoteContext context = do - st <- getState - if stateQuoteContext st == context + context' <- getQuoteContext + if context' == context then fail "already inside quotes" else return () -charOrRef :: [Char] -> Parser [Char] st Char +charOrRef :: Stream s m Char => String -> ParserT s st m Char charOrRef cs = oneOf cs <|> try (do c <- characterReference guard (c `elem` cs) return c) -updateLastStrPos :: Parser [Char] ParserState () -updateLastStrPos = getPosition >>= \p -> - updateState $ \s -> s{ stateLastStrPos = Just p } - -singleQuoteStart :: Parser [Char] ParserState () +singleQuoteStart :: (HasLastStrPosition st, HasQuoteContext st m, Stream s m Char) + => ParserT s st m () singleQuoteStart = do failIfInQuoteContext InSingleQuote - pos <- getPosition - st <- getState -- single quote start can't be right after str - guard $ stateLastStrPos st /= Just pos + guard =<< notAfterString () <$ charOrRef "'\8216\145" -singleQuoteEnd :: Parser [Char] st () +singleQuoteEnd :: Stream s m Char + => ParserT s st m () singleQuoteEnd = try $ do charOrRef "'\8217\146" notFollowedBy alphaNum -doubleQuoteStart :: Parser [Char] ParserState () +doubleQuoteStart :: (HasQuoteContext st m, Stream s m Char) + => ParserT s st m () doubleQuoteStart = do failIfInQuoteContext InDoubleQuote try $ do charOrRef "\"\8220\147" notFollowedBy . satisfy $ flip elem [' ', '\t', '\n'] -doubleQuoteEnd :: Parser [Char] st () -doubleQuoteEnd = do - charOrRef "\"\8221\148" - return () +doubleQuoteEnd :: Stream s m Char + => ParserT s st m () +doubleQuoteEnd = void (charOrRef "\"\8221\148") -ellipses :: Parser [Char] st Inline -ellipses = do - try (charOrRef "\8230\133") <|> try (string "..." >> return '…') - return (Str "\8230") +ellipses :: Stream s m Char + => ParserT s st m Inlines +ellipses = try (string "..." >> return (B.str "\8230")) -dash :: Parser [Char] ParserState Inline -dash = do +dash :: (HasReaderOptions st, Stream s m Char) + => ParserT s st m Inlines +dash = try $ do oldDashes <- getOption readerOldDashes if oldDashes - then emDashOld <|> enDashOld - else Str `fmap` (hyphenDash <|> emDash <|> enDash) - --- Two hyphens = en-dash, three = em-dash -hyphenDash :: Parser [Char] st String -hyphenDash = do - try $ string "--" - option "\8211" (char '-' >> return "\8212") - -emDash :: Parser [Char] st String -emDash = do - try (charOrRef "\8212\151") - return "\8212" - -enDash :: Parser [Char] st String -enDash = do - try (charOrRef "\8212\151") - return "\8211" - -enDashOld :: Parser [Char] st Inline -enDashOld = do - try (charOrRef "\8211\150") <|> - try (char '-' >> lookAhead (satisfy isDigit) >> return '–') - return (Str "\8211") - -emDashOld :: Parser [Char] st Inline -emDashOld = do - try (charOrRef "\8212\151") <|> (try $ string "--" >> optional (char '-') >> return '-') - return (Str "\8212") + then do + char '-' + (char '-' >> return (B.str "\8212")) + <|> (lookAhead digit >> return (B.str "\8211")) + else do + string "--" + (char '-' >> return (B.str "\8212")) + <|> return (B.str "\8211") -- This is used to prevent exponential blowups for things like: -- a**a*a**a*a**a*a**a*a**a*a**a*a** -nested :: Parser s ParserState a - -> Parser s ParserState a +nested :: Stream s m a + => ParserT s ParserState m a + -> ParserT s ParserState m a nested p = do - nestlevel <- stateMaxNestingLevel `fmap` getState + nestlevel <- stateMaxNestingLevel <$> getState guard $ nestlevel > 0 updateState $ \st -> st{ stateMaxNestingLevel = stateMaxNestingLevel st - 1 } res <- p updateState $ \st -> st{ stateMaxNestingLevel = nestlevel } return res +citeKey :: (Stream s m Char, HasLastStrPosition st) + => ParserT s st m (Bool, String) +citeKey = try $ do + guard =<< notAfterString + suppress_author <- option False (char '-' *> return True) + char '@' + firstChar <- letter <|> char '_' + let regchar = satisfy (\c -> isAlphaNum c || c == '_') + let internal p = try $ p <* lookAhead regchar + rest <- many $ regchar <|> internal (oneOf ":.#$%&-+?<>~/") + let key = firstChar:rest + return (suppress_author, key) + + +token :: (Stream s m t) + => (t -> String) + -> (t -> SourcePos) + -> (t -> Maybe a) + -> ParsecT s st m a +token pp pos match = tokenPrim pp (\_ t _ -> pos t) match + -- -- Macros -- -- | Parse a \newcommand or \renewcommand macro definition. -macro :: Parser [Char] ParserState Blocks +macro :: (Stream [Char] m Char, HasMacros st, HasReaderOptions st) + => ParserT [Char] st m Blocks macro = do apply <- getOption readerApplyMacros inp <- getInput @@ -1135,16 +1241,24 @@ macro = do if apply then do updateState $ \st -> - st { stateMacros = ms ++ stateMacros st } + updateMacros (ms ++) st return mempty else return $ rawBlock "latex" def' -- | Apply current macros to string. -applyMacros' :: String -> Parser [Char] ParserState String +applyMacros' :: (HasReaderOptions st, HasMacros st, Stream [Char] m Char) + => String + -> ParserT [Char] st m String applyMacros' target = do apply <- getOption readerApplyMacros if apply - then do macros <- liftM stateMacros getState + then do macros <- extractMacros <$> getState return $ applyMacros macros target else return target +-- | Append a warning to the log. +addWarning :: Maybe SourcePos -> String -> Parser [Char] ParserState () +addWarning mbpos msg = + updateState $ \st -> st{ + stateWarnings = (msg ++ maybe "" (\pos -> " " ++ show pos) mbpos) : + stateWarnings st } diff --git a/src/Text/Pandoc/Pretty.hs b/src/Text/Pandoc/Pretty.hs index 5331587ce..2f2656086 100644 --- a/src/Text/Pandoc/Pretty.hs +++ b/src/Text/Pandoc/Pretty.hs @@ -1,6 +1,6 @@ {-# LANGUAGE GeneralizedNewtypeDeriving, CPP #-} {- -Copyright (C) 2010 John MacFarlane <jgm@berkeley.edu> +Copyright (C) 2010-2014 John MacFarlane <jgm@berkeley.edu> This program is free software; you can redistribute it and/or modify it under the terms of the GNU General Public License as published by @@ -19,7 +19,7 @@ Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111(-1)307 USA {- | Module : Text.Pandoc.Pretty - Copyright : Copyright (C) 2010 John MacFarlane + Copyright : Copyright (C) 2010-2014 John MacFarlane License : GNU GPL, version 2 or above Maintainer : John MacFarlane <jgm@berkeley.edu> @@ -35,6 +35,7 @@ module Text.Pandoc.Pretty ( , render , cr , blankline + , blanklines , space , text , char @@ -100,7 +101,7 @@ data D = Text Int String | BreakingSpace | CarriageReturn | NewLine - | BlankLine + | BlankLines Int -- number of blank lines deriving (Show) newtype Doc = Doc { unDoc :: Seq D } @@ -113,7 +114,7 @@ isBlank :: D -> Bool isBlank BreakingSpace = True isBlank CarriageReturn = True isBlank NewLine = True -isBlank BlankLine = True +isBlank (BlankLines _) = True isBlank (Text _ (c:_)) = isSpace c isBlank _ = False @@ -190,7 +191,7 @@ vsep = foldr ($+$) empty nestle :: Doc -> Doc nestle (Doc d) = Doc $ go d where go x = case viewl x of - (BlankLine :< rest) -> go rest + (BlankLines _ :< rest) -> go rest (NewLine :< rest) -> go rest _ -> x @@ -203,7 +204,7 @@ chomp d = Doc (fromList dl') go (BreakingSpace : xs) = go xs go (CarriageReturn : xs) = go xs go (NewLine : xs) = go xs - go (BlankLine : xs) = go xs + go (BlankLines _ : xs) = go xs go (Prefixed s d' : xs) = Prefixed s (chomp d') : xs go xs = xs @@ -216,9 +217,10 @@ outp off s | off < 0 = do -- offset < 0 means newline characters let pref = reverse $ dropWhile isSpace $ reverse rawpref modify $ \st -> st{ output = fromString pref : output st , column = column st + realLength pref } + let numnewlines = length $ takeWhile (=='\n') $ reverse s modify $ \st -> st { output = fromString s : output st , column = 0 - , newlines = newlines st + 1 } + , newlines = newlines st + numnewlines } outp off s = do -- offset >= 0 (0 might be combining char) st' <- get let pref = prefix st' @@ -277,17 +279,16 @@ renderList (BeforeNonBlank d : xs) = | otherwise -> renderDoc d >> renderList xs [] -> renderList xs -renderList (BlankLine : xs) = do +renderList (BlankLines num : xs) = do st <- get case output st of - _ | newlines st > 1 || null xs -> return () - _ | column st == 0 -> do - outp (-1) "\n" - _ -> do - outp (-1) "\n" - outp (-1) "\n" + _ | newlines st > num || null xs -> return () + | otherwise -> replicateM_ (1 + num - newlines st) (outp (-1) "\n") renderList xs +renderList (CarriageReturn : BlankLines m : xs) = + renderList (BlankLines m : xs) + renderList (CarriageReturn : xs) = do st <- get if newlines st > 0 || null xs @@ -302,7 +303,7 @@ renderList (NewLine : xs) = do renderList (BreakingSpace : CarriageReturn : xs) = renderList (CarriageReturn:xs) renderList (BreakingSpace : NewLine : xs) = renderList (NewLine:xs) -renderList (BreakingSpace : BlankLine : xs) = renderList (BlankLine:xs) +renderList (BreakingSpace : BlankLines n : xs) = renderList (BlankLines n:xs) renderList (BreakingSpace : BreakingSpace : xs) = renderList (BreakingSpace:xs) renderList (BreakingSpace : xs) = do let isText (Text _ _) = True @@ -383,9 +384,13 @@ cr = Doc $ singleton CarriageReturn -- | Inserts a blank line unless one exists already. -- (@blankline <> blankline@ has the same effect as @blankline@. --- If you want multiple blank lines, use @text "\\n\\n"@. blankline :: Doc -blankline = Doc $ singleton BlankLine +blankline = Doc $ singleton (BlankLines 1) + +-- | Inserts a blank lines unless they exists already. +-- (@blanklines m <> blanklines n@ has the same effect as @blankline (max m n)@. +blanklines :: Int -> Doc +blanklines n = Doc $ singleton (BlankLines n) -- | Uses the specified string as a prefix for every line of -- the inside document (except the first, if not at the beginning @@ -529,4 +534,4 @@ charWidth c = -- | Get real length of string, taking into account combining and double-wide -- characters. realLength :: String -> Int -realLength = sum . map charWidth +realLength = foldr (\a b -> charWidth a + b) 0 diff --git a/src/Text/Pandoc/Process.hs b/src/Text/Pandoc/Process.hs index 112c5b974..19872b405 100644 --- a/src/Text/Pandoc/Process.hs +++ b/src/Text/Pandoc/Process.hs @@ -1,5 +1,5 @@ {- -Copyright (C) 2013 John MacFarlane <jgm@berkeley.edu> +Copyright (C) 2013-2014 John MacFarlane <jgm@berkeley.edu> This program is free software; you can redistribute it and/or modify it under the terms of the GNU General Public License as published by @@ -18,7 +18,7 @@ Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA {- | Module : Text.Pandoc.Process - Copyright : Copyright (C) 2013 John MacFarlane + Copyright : Copyright (C) 2013-2014 John MacFarlane License : GNU GPL, version 2 or above Maintainer : John MacFarlane <jgm@berkeley.edu> @@ -47,7 +47,7 @@ terminates, and then returns the 'ExitCode' of the process, the standard output, and the standard error. If an asynchronous exception is thrown to the thread executing -@readProcessWithExitCode@. The forked process will be terminated and +@readProcessWithExitCode@, the forked process will be terminated and @readProcessWithExitCode@ will wait (block) until the process has been terminated. -} @@ -102,4 +102,3 @@ forkWait a = do res <- newEmptyMVar _ <- mask $ \restore -> forkIO $ try (restore a) >>= putMVar res return (takeMVar res >>= either (\ex -> throwIO (ex :: SomeException)) return) - diff --git a/src/Text/Pandoc/Readers/DocBook.hs b/src/Text/Pandoc/Readers/DocBook.hs index 56cb16b20..663960a87 100644 --- a/src/Text/Pandoc/Readers/DocBook.hs +++ b/src/Text/Pandoc/Readers/DocBook.hs @@ -6,6 +6,7 @@ import Text.Pandoc.Definition import Text.Pandoc.Builder import Text.XML.Light import Text.Pandoc.Compat.TagSoupEntity (lookupEntity) +import Data.Either (rights) import Data.Generics import Data.Monoid import Data.Char (isSpace) @@ -13,6 +14,7 @@ import Control.Monad.State import Control.Applicative ((<$>)) import Data.List (intersperse) import Data.Maybe (fromMaybe) +import Text.TeXMath (readMathML, writeTeX) {- @@ -45,7 +47,7 @@ List of all DocBook tags, with [x] indicating implemented, [ ] audioobject - A wrapper for audio data and its associated meta-information [x] author - The name of an individual author [ ] authorblurb - A short description or note about an author -[ ] authorgroup - Wrapper for author information when a document has +[x] authorgroup - Wrapper for author information when a document has multiple authors or collabarators [x] authorinitials - The initials or other short identifier for an author [o] beginpage - The location of a page break in a print version of the document @@ -68,8 +70,8 @@ List of all DocBook tags, with [x] indicating implemented, [x] book - A book [x] bookinfo - Meta-information for a Book [x] bridgehead - A free-floating heading -[ ] callout - A “called out” description of a marked Area -[ ] calloutlist - A list of Callouts +[x] callout - A “called out” description of a marked Area +[x] calloutlist - A list of Callouts [x] caption - A caption [x] caution - A note of caution [x] chapter - A chapter, as of a book @@ -79,7 +81,7 @@ List of all DocBook tags, with [x] indicating implemented, [ ] citerefentry - A citation to a reference page [ ] citetitle - The title of a cited work [ ] city - The name of a city in an address -[ ] classname - The name of a class, in the object-oriented programming sense +[x] classname - The name of a class, in the object-oriented programming sense [ ] classsynopsis - The syntax summary for a class definition [ ] classsynopsisinfo - Information supplementing the contents of a ClassSynopsis @@ -126,7 +128,7 @@ List of all DocBook tags, with [x] indicating implemented, [ ] envar - A software environment variable [x] epigraph - A short inscription at the beginning of a document or component note: also handle embedded attribution tag -[ ] equation - A displayed mathematical equation +[x] equation - A displayed mathematical equation [ ] errorcode - An error code [ ] errorname - An error name [ ] errortext - An error message. @@ -167,9 +169,9 @@ List of all DocBook tags, with [x] indicating implemented, [ ] guibutton - The text on a button in a GUI [ ] guiicon - Graphic and/or text appearing as a icon in a GUI [ ] guilabel - The text of a label in a GUI -[ ] guimenu - The name of a menu in a GUI -[ ] guimenuitem - The name of a terminal menu item in a GUI -[ ] guisubmenu - The name of a submenu in a GUI +[x] guimenu - The name of a menu in a GUI +[x] guimenuitem - The name of a terminal menu item in a GUI +[x] guisubmenu - The name of a submenu in a GUI [ ] hardware - A physical part of a computer system [ ] highlights - A summary of the main points of the discussed component [ ] holder - The name of the individual or organization that holds a copyright @@ -185,12 +187,12 @@ List of all DocBook tags, with [x] indicating implemented, [x] indexinfo - Meta-information for an Index [x] indexterm - A wrapper for terms to be indexed [x] info - A wrapper for information about a component or other block. (DocBook v5) -[ ] informalequation - A displayed mathematical equation without a title +[x] informalequation - A displayed mathematical equation without a title [ ] informalexample - A displayed example without a title [ ] informalfigure - A untitled figure [ ] informaltable - A table without a title [ ] initializer - The initializer for a FieldSynopsis -[ ] inlineequation - A mathematical equation or expression occurring inline +[x] inlineequation - A mathematical equation or expression occurring inline [ ] inlinegraphic - An object containing or pointing to graphical data that will be rendered inline [x] inlinemediaobject - An inline media object (video, audio, image, and so on) @@ -204,10 +206,10 @@ List of all DocBook tags, with [x] indicating implemented, other dingbat [ ] itermset - A set of index terms in the meta-information of a document [ ] jobtitle - The title of an individual in an organization -[ ] keycap - The text printed on a key on a keyboard +[x] keycap - The text printed on a key on a keyboard [ ] keycode - The internal, frequently numeric, identifier for a key on a keyboard -[ ] keycombo - A combination of input actions +[x] keycombo - A combination of input actions [ ] keysym - The symbolic name of a key on a keyboard [ ] keyword - One of a set of keywords describing the content of a document [ ] keywordset - A set of keywords describing the content of a document @@ -235,11 +237,11 @@ List of all DocBook tags, with [x] indicating implemented, [x] mediaobject - A displayed media object (video, audio, image, etc.) [ ] mediaobjectco - A media object that contains callouts [x] member - An element of a simple list -[ ] menuchoice - A selection or series of selections from a menu +[x] menuchoice - A selection or series of selections from a menu [ ] methodname - The name of a method [ ] methodparam - Parameters to a method [ ] methodsynopsis - A syntax summary for a method -[ ] mml:math - A MathML equation +[x] mml:math - A MathML equation [ ] modespec - Application-specific information necessary for the completion of an OLink [ ] modifier - Modifiers in a synopsis @@ -341,7 +343,7 @@ List of all DocBook tags, with [x] indicating implemented, [x] refsectioninfo - Meta-information for a refsection [ ] refsynopsisdiv - A syntactic synopsis of the subject of the reference page [ ] refsynopsisdivinfo - Meta-information for a RefSynopsisDiv -[ ] releaseinfo - Information about a particular release of a document +[x] releaseinfo - Information about a particular release of a document [ ] remark - A remark (or comment) intended for presentation in a draft manuscript [ ] replaceable - Content that may or must be replaced by the user @@ -469,7 +471,7 @@ List of all DocBook tags, with [x] indicating implemented, [ ] token - A unit of information [x] tr - A row in an HTML table [ ] trademark - A trademark -[ ] type - The classification of a value +[x] type - The classification of a value [x] ulink - A link that addresses its target by means of a URL (Uniform Resource Locator) [x] uri - A Uniform Resource Identifier @@ -492,34 +494,40 @@ List of all DocBook tags, with [x] indicating implemented, anything else [ ] xref - A cross reference to another part of the document [ ] year - The year of publication of a document - +[x] ?asciidoc-br? - line break from asciidoc docbook output -} type DB = State DBState data DBState = DBState{ dbSectionLevel :: Int , dbQuoteType :: QuoteType - , dbDocTitle :: Inlines - , dbDocAuthors :: [Inlines] - , dbDocDate :: Inlines + , dbMeta :: Meta + , dbAcceptsMeta :: Bool , dbBook :: Bool , dbFigureTitle :: Inlines } deriving Show readDocBook :: ReaderOptions -> String -> Pandoc -readDocBook _ inp = setTitle (dbDocTitle st') - $ setAuthors (dbDocAuthors st') - $ setDate (dbDocDate st') - $ doc $ mconcat bs - where (bs, st') = runState (mapM parseBlock $ normalizeTree $ parseXML inp) +readDocBook _ inp = Pandoc (dbMeta st') (toList $ mconcat bs) + where (bs, st') = runState (mapM parseBlock $ normalizeTree $ parseXML inp') DBState{ dbSectionLevel = 0 , dbQuoteType = DoubleQuote - , dbDocTitle = mempty - , dbDocAuthors = [] - , dbDocDate = mempty + , dbMeta = mempty + , dbAcceptsMeta = False , dbBook = False , dbFigureTitle = mempty } + inp' = handleInstructions inp + +-- We treat <?asciidoc-br?> specially (issue #1236), converting it +-- to <br/>, since xml-light doesn't parse the instruction correctly. +-- Other xml instructions are simply removed from the input stream. +handleInstructions :: String -> String +handleInstructions ('<':'?':'a':'s':'c':'i':'i':'d':'o':'c':'-':'b':'r':'?':'>':xs) = '<':'b':'r':'/':'>': handleInstructions xs +handleInstructions xs = case break (=='<') xs of + (ys, []) -> ys + ([], '<':zs) -> '<' : handleInstructions zs + (ys, zs) -> ys ++ handleInstructions zs getFigure :: Element -> DB Blocks getFigure e = do @@ -560,6 +568,30 @@ attrValue attr elt = named :: String -> Element -> Bool named s e = qName (elName e) == s +-- + +acceptingMetadata :: DB a -> DB a +acceptingMetadata p = do + modify (\s -> s { dbAcceptsMeta = True } ) + res <- p + modify (\s -> s { dbAcceptsMeta = False }) + return res + +checkInMeta :: Monoid a => DB () -> DB a +checkInMeta p = do + accepts <- dbAcceptsMeta <$> get + when accepts p + return mempty + + + +addMeta :: ToMetaValue a => String -> a -> DB () +addMeta field val = modify (setMeta field val) + +instance HasMeta DBState where + setMeta field v s = s {dbMeta = setMeta field v (dbMeta s)} + deleteMeta field s = s {dbMeta = deleteMeta field (dbMeta s)} + isBlockElement :: Content -> Bool isBlockElement (Elem e) = qName (elName e) `elem` blocktags where blocktags = ["toc","index","para","formalpara","simpara", @@ -571,7 +603,7 @@ isBlockElement (Elem e) = qName (elName e) `elem` blocktags "important","caution","note","tip","warning","qandadiv", "question","answer","abstract","itemizedlist","orderedlist", "variablelist","article","book","table","informaltable", - "screen","programlisting","example"] + "screen","programlisting","example","calloutlist"] isBlockElement _ = False -- Trim leading and trailing newline characters @@ -606,6 +638,7 @@ getImage e = do getBlocks :: Element -> DB Blocks getBlocks e = mconcat <$> (mapM parseBlock $ elContent e) + parseBlock :: Content -> DB Blocks parseBlock (Text (CData CDataRaw _ _)) = return mempty -- DOCTYPE parseBlock (Text (CData _ s _)) = if all isSpace s @@ -619,10 +652,10 @@ parseBlock (Elem e) = "para" -> parseMixed para (elContent e) "formalpara" -> do tit <- case filterChild (named "title") e of - Just t -> (<> str "." <> linebreak) <$> emph - <$> getInlines t + Just t -> (para . strong . (<> str ".")) <$> + getInlines t Nothing -> return mempty - addToStart tit <$> parseMixed para (elContent e) + (tit <>) <$> parseMixed para (elContent e) "simpara" -> parseMixed para (elContent e) "ackno" -> parseMixed para (elContent e) "epigraph" -> parseBlockquote @@ -630,7 +663,11 @@ parseBlock (Elem e) = "attribution" -> return mempty "titleabbrev" -> return mempty "authorinitials" -> return mempty - "title" -> return mempty -- handled by getTitle or sect or figure + "title" -> checkInMeta getTitle + "author" -> checkInMeta getAuthor + "authorgroup" -> checkInMeta getAuthorGroup + "releaseinfo" -> checkInMeta (getInlines e >>= addMeta "release") + "date" -> checkInMeta getDate "bibliography" -> sect 0 "bibliodiv" -> sect 1 "biblioentry" -> parseMixed para (elContent e) @@ -675,6 +712,7 @@ parseBlock (Elem e) = "question" -> addToStart (strong (str "Q:") <> str " ") <$> getBlocks e "answer" -> addToStart (strong (str "A:") <> str " ") <$> getBlocks e "abstract" -> blockQuote <$> getBlocks e + "calloutlist" -> bulletList <$> callouts "itemizedlist" -> bulletList <$> listitems "orderedlist" -> do let listStyle = case attrValue "numeration" e of @@ -693,8 +731,8 @@ parseBlock (Elem e) = "figure" -> getFigure e "mediaobject" -> para <$> getImage e "caption" -> return mempty - "info" -> getTitle >> getAuthors >> getDate >> return mempty - "articleinfo" -> getTitle >> getAuthors >> getDate >> return mempty + "info" -> metaBlock + "articleinfo" -> metaBlock "sectioninfo" -> return mempty -- keywords & other metadata "refsectioninfo" -> return mempty -- keywords & other metadata "refsect1info" -> return mempty -- keywords & other metadata @@ -708,10 +746,10 @@ parseBlock (Elem e) = "chapterinfo" -> return mempty -- keywords & other metadata "glossaryinfo" -> return mempty -- keywords & other metadata "appendixinfo" -> return mempty -- keywords & other metadata - "bookinfo" -> getTitle >> getAuthors >> getDate >> return mempty + "bookinfo" -> metaBlock "article" -> modify (\st -> st{ dbBook = False }) >> - getTitle >> getBlocks e - "book" -> modify (\st -> st{ dbBook = True }) >> getTitle >> getBlocks e + getBlocks e + "book" -> modify (\st -> st{ dbBook = True }) >> getBlocks e "table" -> parseTable "informaltable" -> parseTable "literallayout" -> codeBlockWithLang @@ -734,7 +772,7 @@ parseBlock (Elem e) = "" -> [] x -> [x] return $ codeBlockWith (attrValue "id" e, classes', []) - $ trimNl $ strContent e + $ trimNl $ strContentRecursive e parseBlockquote = do attrib <- case filterChild (named "attribution") e of Nothing -> return mempty @@ -743,6 +781,7 @@ parseBlock (Elem e) = contents <- getBlocks e return $ blockQuote (contents <> attrib) listitems = mapM getBlocks $ filterChildren (named "listitem") e + callouts = mapM getBlocks $ filterChildren (named "callout") e deflistitems = mapM parseVarListEntry $ filterChildren (named "varlistentry") e parseVarListEntry e' = do @@ -757,24 +796,19 @@ parseBlock (Elem e) = terms' <- mapM getInlines terms items' <- mapM getBlocks items return (mconcat $ intersperse (str "; ") terms', items') - getTitle = case filterChild (named "title") e of - Just t -> do - tit <- getInlines t - subtit <- case filterChild (named "subtitle") e of - Just s -> (text ": " <>) <$> - getInlines s - Nothing -> return mempty - modify $ \st -> st{dbDocTitle = tit <> subtit} - Nothing -> return () - getAuthors = do - auths <- mapM getInlines - $ filterChildren (named "author") e - modify $ \st -> st{dbDocAuthors = auths} - getDate = case filterChild (named "date") e of - Just t -> do - dat <- getInlines t - modify $ \st -> st{dbDocDate = dat} - Nothing -> return () + getTitle = do + tit <- getInlines e + subtit <- case filterChild (named "subtitle") e of + Just s -> (text ": " <>) <$> + getInlines s + Nothing -> return mempty + addMeta "title" (tit <> subtit) + + getAuthor = (:[]) <$> getInlines e >>= addMeta "author" + getAuthorGroup = do + let terms = filterChildren (named "author") e + mapM getInlines terms >>= addMeta "author" + getDate = getInlines e >>= addMeta "date" parseTable = do let isCaption x = named "title" x || named "caption" x caption <- case filterChild isCaption e of @@ -834,18 +868,31 @@ parseBlock (Elem e) = Nothing -> return mempty modify $ \st -> st{ dbSectionLevel = n } b <- getBlocks e + let ident = attrValue "id" e modify $ \st -> st{ dbSectionLevel = n - 1 } - return $ header n' headerText <> b + return $ headerWith (ident,[],[]) n' headerText <> b + metaBlock = acceptingMetadata (getBlocks e) >> return mempty getInlines :: Element -> DB Inlines getInlines e' = (trimInlines . mconcat) <$> (mapM parseInline $ elContent e') +strContentRecursive :: Element -> String +strContentRecursive = strContent . + (\e' -> e'{ elContent = map elementToStr $ elContent e' }) + +elementToStr :: Content -> Content +elementToStr (Elem e') = Text $ CData CDataText (strContentRecursive e') Nothing +elementToStr x = x + parseInline :: Content -> DB Inlines parseInline (Text (CData _ s _)) = return $ text s parseInline (CRef ref) = return $ maybe (text $ map toUpper ref) (text . (:[])) $ lookupEntity ref parseInline (Elem e) = case qName (elName e) of + "equation" -> equation displayMath + "informalequation" -> equation displayMath + "inlineequation" -> equation math "subscript" -> subscript <$> innerInlines "superscript" -> superscript <$> innerInlines "inlinemediaobject" -> getImage e @@ -860,6 +907,7 @@ parseInline (Elem e) = else doubleQuoted contents "simplelist" -> simpleList "segmentedlist" -> segmentedList + "classname" -> codeWithLang "code" -> codeWithLang "filename" -> codeWithLang "literal" -> codeWithLang @@ -879,6 +927,10 @@ parseInline (Elem e) = "constant" -> codeWithLang "userinput" -> codeWithLang "varargs" -> return $ code "(...)" + "keycap" -> return (str $ strContent e) + "keycombo" -> keycombo <$> (mapM parseInline $ elContent e) + "menuchoice" -> menuchoice <$> (mapM parseInline $ + filter isGuiMenu $ elContent e) "xref" -> return $ str "?" -- so at least you know something is there "email" -> return $ link ("mailto:" ++ strContent e) "" $ str $ strContent e @@ -899,14 +951,26 @@ parseInline (Elem e) = _ -> emph <$> innerInlines "footnote" -> (note . mconcat) <$> (mapM parseBlock $ elContent e) "title" -> return mempty + "affiliation" -> return mempty + -- Note: this isn't a real docbook tag; it's what we convert + -- <?asciidor-br?> to in handleInstructions, above. A kludge to + -- work around xml-light's inability to parse an instruction. + "br" -> return linebreak _ -> innerInlines where innerInlines = (trimInlines . mconcat) <$> (mapM parseInline $ elContent e) + equation constructor = return $ mconcat $ + map (constructor . writeTeX) + $ rights + $ map (readMathML . showElement . everywhere (mkT removePrefix)) + $ filterChildren (\x -> qName (elName x) == "math" && + qPrefix (elName x) == Just "mml") e + removePrefix elname = elname { qPrefix = Nothing } codeWithLang = do let classes' = case attrValue "language" e of "" -> [] l -> [l] - return $ codeWith (attrValue "id" e,classes',[]) $ strContent e + return $ codeWith (attrValue "id" e,classes',[]) $ strContentRecursive e simpleList = (mconcat . intersperse (str "," <> space)) <$> mapM getInlines (filterChildren (named "member") e) segmentedList = do @@ -921,3 +985,10 @@ parseInline (Elem e) = then mempty else strong tit <> linebreak return $ linebreak <> tit' <> segs + keycombo = spanWith ("",["keycombo"],[]) . + mconcat . intersperse (str "+") + menuchoice = spanWith ("",["menuchoice"],[]) . + mconcat . intersperse (text " > ") + isGuiMenu (Elem x) = named "guimenu" x || named "guisubmenu" x || + named "guimenuitem" x + isGuiMenu _ = False diff --git a/src/Text/Pandoc/Readers/Docx.hs b/src/Text/Pandoc/Readers/Docx.hs new file mode 100644 index 000000000..64eb0322f --- /dev/null +++ b/src/Text/Pandoc/Readers/Docx.hs @@ -0,0 +1,549 @@ +{-# LANGUAGE PatternGuards, OverloadedStrings #-} + +{- +Copyright (C) 2014 Jesse Rosenthal <jrosenthal@jhu.edu> + +This program is free software; you can redistribute it and/or modify +it under the terms of the GNU General Public License as published by +the Free Software Foundation; either version 2 of the License, or +(at your option) any later version. + +This program is distributed in the hope that it will be useful, +but WITHOUT ANY WARRANTY; without even the implied warranty of +MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the +GNU General Public License for more details. + +You should have received a copy of the GNU General Public License +along with this program; if not, write to the Free Software +Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA +-} + +{- | + Module : Text.Pandoc.Readers.Docx + Copyright : Copyright (C) 2014 Jesse Rosenthal + License : GNU GPL, version 2 or above + + Maintainer : Jesse Rosenthal <jrosenthal@jhu.edu> + Stability : alpha + Portability : portable + +Conversion of Docx type (defined in Text.Pandoc.Readers.Docx.Parse) +to 'Pandoc' document. -} + +{- +Current state of implementation of Docx entities ([x] means +implemented, [-] means partially implemented): + +* Blocks + + - [X] Para + - [X] CodeBlock (styled with `SourceCode`) + - [X] BlockQuote (styled with `Quote`, `BlockQuote`, or, optionally, + indented) + - [X] OrderedList + - [X] BulletList + - [X] DefinitionList (styled with adjacent `DefinitionTerm` and `Definition`) + - [X] Header (styled with `Heading#`) + - [ ] HorizontalRule + - [-] Table (column widths and alignments not yet implemented) + +* Inlines + + - [X] Str + - [X] Emph (From italics. `underline` currently read as span. In + future, it might optionally be emph as well) + - [X] Strong + - [X] Strikeout + - [X] Superscript + - [X] Subscript + - [X] SmallCaps + - [ ] Quoted + - [ ] Cite + - [X] Code (styled with `VerbatimChar`) + - [X] Space + - [X] LineBreak (these are invisible in Word: entered with Shift-Return) + - [ ] Math + - [X] Link (links to an arbitrary bookmark create a span with the target as + id and "anchor" class) + - [-] Image (Links to path in archive. Future option for + data-encoded URI likely.) + - [X] Note (Footnotes and Endnotes are silently combined.) +-} + +module Text.Pandoc.Readers.Docx + ( readDocx + ) where + +import Codec.Archive.Zip +import Text.Pandoc.Definition +import Text.Pandoc.Options +import Text.Pandoc.Builder +import Text.Pandoc.Walk +import Text.Pandoc.Readers.Docx.Parse +import Text.Pandoc.Readers.Docx.Lists +import Text.Pandoc.Readers.Docx.Reducible +import Text.Pandoc.Shared +import Text.Pandoc.MediaBag (insertMedia, MediaBag) +import Data.List (delete, (\\), intersect) +import Data.Monoid +import Text.TeXMath (writeTeX) +import Data.Default (Default) +import qualified Data.ByteString.Lazy as B +import qualified Data.Map as M +import Control.Monad.Reader +import Control.Monad.State +import Control.Applicative ((<$>)) +import Data.Sequence (ViewL(..), viewl) +import qualified Data.Sequence as Seq (null) + +readDocx :: ReaderOptions + -> B.ByteString + -> (Pandoc, MediaBag) +readDocx opts bytes = + case archiveToDocx (toArchive bytes) of + Right docx -> (Pandoc meta blks, mediaBag) where + (meta, blks, mediaBag) = (docxToOutput opts docx) + Left _ -> error $ "couldn't parse docx file" + +data DState = DState { docxAnchorMap :: M.Map String String + , docxMediaBag :: MediaBag + , docxDropCap :: Inlines + } + +instance Default DState where + def = DState { docxAnchorMap = M.empty + , docxMediaBag = mempty + , docxDropCap = mempty + } + +data DEnv = DEnv { docxOptions :: ReaderOptions + , docxInHeaderBlock :: Bool } + +instance Default DEnv where + def = DEnv def False + +type DocxContext = ReaderT DEnv (State DState) + +evalDocxContext :: DocxContext a -> DEnv -> DState -> a +evalDocxContext ctx env st = evalState (runReaderT ctx env) st + +-- This is empty, but we put it in for future-proofing. +spansToKeep :: [String] +spansToKeep = [] + +divsToKeep :: [String] +divsToKeep = ["list-item", "Definition", "DefinitionTerm"] + +metaStyles :: M.Map String String +metaStyles = M.fromList [ ("Title", "title") + , ("Subtitle", "subtitle") + , ("Author", "author") + , ("Date", "date") + , ("Abstract", "abstract")] + +sepBodyParts :: [BodyPart] -> ([BodyPart], [BodyPart]) +sepBodyParts = span (\bp -> (isMetaPar bp || isEmptyPar bp)) + +isMetaPar :: BodyPart -> Bool +isMetaPar (Paragraph pPr _) = + not $ null $ intersect (pStyle pPr) (M.keys metaStyles) +isMetaPar _ = False + +isEmptyPar :: BodyPart -> Bool +isEmptyPar (Paragraph _ parParts) = + all isEmptyParPart parParts + where + isEmptyParPart (PlainRun (Run _ runElems)) = all isEmptyElem runElems + isEmptyParPart _ = False + isEmptyElem (TextRun s) = trim s == "" + isEmptyElem _ = True +isEmptyPar _ = False + +bodyPartsToMeta' :: [BodyPart] -> DocxContext (M.Map String MetaValue) +bodyPartsToMeta' [] = return M.empty +bodyPartsToMeta' (bp : bps) + | (Paragraph pPr parParts) <- bp + , (c : _)<- intersect (pStyle pPr) (M.keys metaStyles) + , (Just metaField) <- M.lookup c metaStyles = do + inlines <- concatReduce <$> mapM parPartToInlines parParts + remaining <- bodyPartsToMeta' bps + let + f (MetaInlines ils) (MetaInlines ils') = MetaBlocks [Para ils, Para ils'] + f (MetaInlines ils) (MetaBlocks blks) = MetaBlocks ((Para ils) : blks) + f m (MetaList mv) = MetaList (m : mv) + f m n = MetaList [m, n] + return $ M.insertWith f metaField (MetaInlines (toList inlines)) remaining +bodyPartsToMeta' (_ : bps) = bodyPartsToMeta' bps + +bodyPartsToMeta :: [BodyPart] -> DocxContext Meta +bodyPartsToMeta bps = do + mp <- bodyPartsToMeta' bps + let mp' = + case M.lookup "author" mp of + Just mv -> M.insert "author" (fixAuthors mv) mp + Nothing -> mp + return $ Meta mp' + +fixAuthors :: MetaValue -> MetaValue +fixAuthors (MetaBlocks blks) = + MetaList $ map g $ filter f blks + where f (Para _) = True + f _ = False + g (Para ils) = MetaInlines ils + g _ = MetaInlines [] +fixAuthors mv = mv + +codeStyles :: [String] +codeStyles = ["VerbatimChar"] + +codeDivs :: [String] +codeDivs = ["SourceCode"] + +runElemToInlines :: RunElem -> Inlines +runElemToInlines (TextRun s) = text s +runElemToInlines (LnBrk) = linebreak +runElemToInlines (Tab) = space + +runElemToString :: RunElem -> String +runElemToString (TextRun s) = s +runElemToString (LnBrk) = ['\n'] +runElemToString (Tab) = ['\t'] + +runToString :: Run -> String +runToString (Run _ runElems) = concatMap runElemToString runElems +runToString _ = "" + +parPartToString :: ParPart -> String +parPartToString (PlainRun run) = runToString run +parPartToString (InternalHyperLink _ runs) = concatMap runToString runs +parPartToString (ExternalHyperLink _ runs) = concatMap runToString runs +parPartToString _ = "" + +blacklistedCharStyles :: [String] +blacklistedCharStyles = ["Hyperlink"] + +resolveDependentRunStyle :: RunStyle -> RunStyle +resolveDependentRunStyle rPr + | Just (s, _) <- rStyle rPr, s `elem` blacklistedCharStyles = + rPr + | Just (_, cs) <- rStyle rPr = + let rPr' = resolveDependentRunStyle cs + in + RunStyle { isBold = case isBold rPr of + Just bool -> Just bool + Nothing -> isBold rPr' + , isItalic = case isItalic rPr of + Just bool -> Just bool + Nothing -> isItalic rPr' + , isSmallCaps = case isSmallCaps rPr of + Just bool -> Just bool + Nothing -> isSmallCaps rPr' + , isStrike = case isStrike rPr of + Just bool -> Just bool + Nothing -> isStrike rPr' + , rVertAlign = case rVertAlign rPr of + Just valign -> Just valign + Nothing -> rVertAlign rPr' + , rUnderline = case rUnderline rPr of + Just ulstyle -> Just ulstyle + Nothing -> rUnderline rPr' + , rStyle = rStyle rPr } + | otherwise = rPr + +runStyleToTransform :: RunStyle -> (Inlines -> Inlines) +runStyleToTransform rPr + | Just (s, _) <- rStyle rPr + , s `elem` spansToKeep = + let rPr' = rPr{rStyle = Nothing} + in + (spanWith ("", [s], [])) . (runStyleToTransform rPr') + | Just True <- isItalic rPr = + emph . (runStyleToTransform rPr {isItalic = Nothing}) + | Just True <- isBold rPr = + strong . (runStyleToTransform rPr {isBold = Nothing}) + | Just True <- isSmallCaps rPr = + smallcaps . (runStyleToTransform rPr {isSmallCaps = Nothing}) + | Just True <- isStrike rPr = + strikeout . (runStyleToTransform rPr {isStrike = Nothing}) + | Just SupScrpt <- rVertAlign rPr = + superscript . (runStyleToTransform rPr {rVertAlign = Nothing}) + | Just SubScrpt <- rVertAlign rPr = + subscript . (runStyleToTransform rPr {rVertAlign = Nothing}) + | Just "single" <- rUnderline rPr = + emph . (runStyleToTransform rPr {rUnderline = Nothing}) + | otherwise = id + +runToInlines :: Run -> DocxContext Inlines +runToInlines (Run rs runElems) + | Just (s, _) <- rStyle rs + , s `elem` codeStyles = + return $ code $ concatMap runElemToString runElems + | otherwise = do + let ils = concatReduce (map runElemToInlines runElems) + return $ (runStyleToTransform $ resolveDependentRunStyle rs) ils +runToInlines (Footnote bps) = do + blksList <- concatReduce <$> (mapM bodyPartToBlocks bps) + return $ note blksList +runToInlines (Endnote bps) = do + blksList <- concatReduce <$> (mapM bodyPartToBlocks bps) + return $ note blksList +runToInlines (InlineDrawing fp bs) = do + mediaBag <- gets docxMediaBag + modify $ \s -> s { docxMediaBag = insertMedia fp Nothing bs mediaBag } + return $ image fp "" "" + +parPartToInlines :: ParPart -> DocxContext Inlines +parPartToInlines (PlainRun r) = runToInlines r +parPartToInlines (Insertion _ author date runs) = do + opts <- asks docxOptions + case readerTrackChanges opts of + AcceptChanges -> concatReduce <$> mapM runToInlines runs + RejectChanges -> return mempty + AllChanges -> do + ils <- concatReduce <$> mapM runToInlines runs + let attr = ("", ["insertion"], [("author", author), ("date", date)]) + return $ spanWith attr ils +parPartToInlines (Deletion _ author date runs) = do + opts <- asks docxOptions + case readerTrackChanges opts of + AcceptChanges -> return mempty + RejectChanges -> concatReduce <$> mapM runToInlines runs + AllChanges -> do + ils <- concatReduce <$> mapM runToInlines runs + let attr = ("", ["deletion"], [("author", author), ("date", date)]) + return $ spanWith attr ils +parPartToInlines (BookMark _ anchor) | anchor `elem` dummyAnchors = + return mempty +parPartToInlines (BookMark _ anchor) = + -- We record these, so we can make sure not to overwrite + -- user-defined anchor links with header auto ids. + do + -- get whether we're in a header. + inHdrBool <- asks docxInHeaderBlock + -- Get the anchor map. + anchorMap <- gets docxAnchorMap + -- We don't want to rewrite if we're in a header, since we'll take + -- care of that later, when we make the header anchor. If the + -- bookmark were already in uniqueIdent form, this would lead to a + -- duplication. Otherwise, we check to see if the id is already in + -- there. Rewrite if necessary. This will have the possible effect + -- of rewriting user-defined anchor links. However, since these + -- are not defined in pandoc, it seems like a necessary evil to + -- avoid an extra pass. + let newAnchor = + if not inHdrBool && anchor `elem` (M.elems anchorMap) + then uniqueIdent [Str anchor] (M.elems anchorMap) + else anchor + unless inHdrBool + (modify $ \s -> s { docxAnchorMap = M.insert anchor newAnchor anchorMap}) + return $ spanWith (newAnchor, ["anchor"], []) mempty +parPartToInlines (Drawing fp bs) = do + mediaBag <- gets docxMediaBag + modify $ \s -> s { docxMediaBag = insertMedia fp Nothing bs mediaBag } + return $ image fp "" "" +parPartToInlines (InternalHyperLink anchor runs) = do + ils <- concatReduce <$> mapM runToInlines runs + return $ link ('#' : anchor) "" ils +parPartToInlines (ExternalHyperLink target runs) = do + ils <- concatReduce <$> mapM runToInlines runs + return $ link target "" ils +parPartToInlines (PlainOMath exps) = do + return $ math $ writeTeX exps + +isAnchorSpan :: Inline -> Bool +isAnchorSpan (Span (_, classes, kvs) ils) = + classes == ["anchor"] && + null kvs && + null ils +isAnchorSpan _ = False + +dummyAnchors :: [String] +dummyAnchors = ["_GoBack"] + +makeHeaderAnchor :: Blocks -> DocxContext Blocks +makeHeaderAnchor bs = case viewl $ unMany bs of + (x :< xs) -> do + x' <- (makeHeaderAnchor' x) + xs' <- (makeHeaderAnchor $ Many xs) + return $ (singleton x') <> xs' + EmptyL -> return mempty + +makeHeaderAnchor' :: Block -> DocxContext Block +-- If there is an anchor already there (an anchor span in the header, +-- to be exact), we rename and associate the new id with the old one. +makeHeaderAnchor' (Header n (_, classes, kvs) ils) + | (c:cs) <- filter isAnchorSpan ils + , (Span (ident, ["anchor"], _) _) <- c = do + hdrIDMap <- gets docxAnchorMap + let newIdent = uniqueIdent ils (M.elems hdrIDMap) + modify $ \s -> s {docxAnchorMap = M.insert ident newIdent hdrIDMap} + return $ Header n (newIdent, classes, kvs) (ils \\ (c:cs)) +-- Otherwise we just give it a name, and register that name (associate +-- it with itself.) +makeHeaderAnchor' (Header n (_, classes, kvs) ils) = + do + hdrIDMap <- gets docxAnchorMap + let newIdent = uniqueIdent ils (M.elems hdrIDMap) + modify $ \s -> s {docxAnchorMap = M.insert newIdent newIdent hdrIDMap} + return $ Header n (newIdent, classes, kvs) ils +makeHeaderAnchor' blk = return blk + +-- Rewrite a standalone paragraph block as a plain +singleParaToPlain :: Blocks -> Blocks +singleParaToPlain blks + | (Para (ils) :< seeq) <- viewl $ unMany blks + , Seq.null seeq = + singleton $ Plain ils +singleParaToPlain blks = blks + +cellToBlocks :: Cell -> DocxContext Blocks +cellToBlocks (Cell bps) = concatReduce <$> mapM bodyPartToBlocks bps + +rowToBlocksList :: Row -> DocxContext [Blocks] +rowToBlocksList (Row cells) = do + blksList <- mapM cellToBlocks cells + return $ map singleParaToPlain blksList + +trimLineBreaks :: [Inline] -> [Inline] +trimLineBreaks [] = [] +trimLineBreaks (LineBreak : ils) = trimLineBreaks ils +trimLineBreaks ils + | (LineBreak : ils') <- reverse ils = trimLineBreaks (reverse ils') +trimLineBreaks ils = ils + +parStyleToTransform :: ParagraphStyle -> (Blocks -> Blocks) +parStyleToTransform pPr + | (c:cs) <- pStyle pPr + , c `elem` divsToKeep = + let pPr' = pPr { pStyle = cs } + in + (divWith ("", [c], [])) . (parStyleToTransform pPr') + | (c:cs) <- pStyle pPr, + c `elem` listParagraphDivs = + let pPr' = pPr { pStyle = cs, indentation = Nothing} + in + (divWith ("", [c], [])) . (parStyleToTransform pPr') + | (_:cs) <- pStyle pPr + , Just True <- pBlockQuote pPr = + let pPr' = pPr { pStyle = cs } + in + blockQuote . (parStyleToTransform pPr') + | (_:cs) <- pStyle pPr = + let pPr' = pPr { pStyle = cs} + in + parStyleToTransform pPr' + | null (pStyle pPr) + , Just left <- indentation pPr >>= leftParIndent + , Just hang <- indentation pPr >>= hangingParIndent = + let pPr' = pPr { indentation = Nothing } + in + case (left - hang) > 0 of + True -> blockQuote . (parStyleToTransform pPr') + False -> parStyleToTransform pPr' + | null (pStyle pPr), + Just left <- indentation pPr >>= leftParIndent = + let pPr' = pPr { indentation = Nothing } + in + case left > 0 of + True -> blockQuote . (parStyleToTransform pPr') + False -> parStyleToTransform pPr' +parStyleToTransform _ = id + +bodyPartToBlocks :: BodyPart -> DocxContext Blocks +bodyPartToBlocks (Paragraph pPr parparts) + | not $ null $ codeDivs `intersect` (pStyle pPr) = + return + $ parStyleToTransform pPr + $ codeBlock + $ concatMap parPartToString parparts + | Just (style, n) <- pHeading pPr = do + ils <- local (\s-> s{docxInHeaderBlock=True}) $ + (concatReduce <$> mapM parPartToInlines parparts) + makeHeaderAnchor $ + headerWith ("", delete style (pStyle pPr), []) n ils + | otherwise = do + ils <- concatReduce <$> mapM parPartToInlines parparts >>= + (return . fromList . trimLineBreaks . normalizeSpaces . toList) + dropIls <- gets docxDropCap + let ils' = dropIls <> ils + if dropCap pPr + then do modify $ \s -> s { docxDropCap = ils' } + return mempty + else do modify $ \s -> s { docxDropCap = mempty } + return $ case isNull ils' of + True -> mempty + _ -> parStyleToTransform pPr $ para ils' +bodyPartToBlocks (ListItem pPr numId lvl levelInfo parparts) = do + let + kvs = case levelInfo of + (_, fmt, txt, Just start) -> [ ("level", lvl) + , ("num-id", numId) + , ("format", fmt) + , ("text", txt) + , ("start", (show start)) + ] + + (_, fmt, txt, Nothing) -> [ ("level", lvl) + , ("num-id", numId) + , ("format", fmt) + , ("text", txt) + ] + blks <- bodyPartToBlocks (Paragraph pPr parparts) + return $ divWith ("", ["list-item"], kvs) blks +bodyPartToBlocks (Tbl _ _ _ []) = + return $ para mempty +bodyPartToBlocks (Tbl cap _ look (r:rs)) = do + let caption = text cap + (hdr, rows) = case firstRowFormatting look of + True -> (Just r, rs) + False -> (Nothing, r:rs) + hdrCells <- case hdr of + Just r' -> rowToBlocksList r' + Nothing -> return [] + + cells <- mapM rowToBlocksList rows + + let size = case null hdrCells of + True -> length $ head cells + False -> length $ hdrCells + -- + -- The two following variables (horizontal column alignment and + -- relative column widths) go to the default at the + -- moment. Width information is in the TblGrid field of the Tbl, + -- so should be possible. Alignment might be more difficult, + -- since there doesn't seem to be a column entity in docx. + alignments = replicate size AlignDefault + widths = replicate size 0 :: [Double] + + return $ table caption (zip alignments widths) hdrCells cells +bodyPartToBlocks (OMathPara e) = do + return $ para $ displayMath (writeTeX e) + + +-- replace targets with generated anchors. +rewriteLink' :: Inline -> DocxContext Inline +rewriteLink' l@(Link ils ('#':target, title)) = do + anchorMap <- gets docxAnchorMap + return $ case M.lookup target anchorMap of + Just newTarget -> (Link ils ('#':newTarget, title)) + Nothing -> l +rewriteLink' il = return il + +rewriteLinks :: [Block] -> DocxContext [Block] +rewriteLinks = mapM (walkM rewriteLink') + +bodyToOutput :: Body -> DocxContext (Meta, [Block], MediaBag) +bodyToOutput (Body bps) = do + let (metabps, blkbps) = sepBodyParts bps + meta <- bodyPartsToMeta metabps + blks <- concatReduce <$> mapM bodyPartToBlocks blkbps + blks' <- rewriteLinks $ blocksToDefinitions $ blocksToBullets $ toList blks + mediaBag <- gets docxMediaBag + return $ (meta, + blks', + mediaBag) + +docxToOutput :: ReaderOptions -> Docx -> (Meta, [Block], MediaBag) +docxToOutput opts (Docx (Document _ body)) = + let dEnv = def { docxOptions = opts} in + evalDocxContext (bodyToOutput body) dEnv def diff --git a/src/Text/Pandoc/Readers/Docx/Fonts.hs b/src/Text/Pandoc/Readers/Docx/Fonts.hs new file mode 100644 index 000000000..b44c71412 --- /dev/null +++ b/src/Text/Pandoc/Readers/Docx/Fonts.hs @@ -0,0 +1,238 @@ +{- +Copyright (C) 2014 Matthew Pickering <matthewtpickering@gmail.com> + +This program is free software; you can redistribute it and/or modify +it under the terms of the GNU General Public License as published by +the Free Software Foundation; either version 2 of the License, or +(at your option) any later version. + +This program is distributed in the hope that it will be useful, +but WITHOUT ANY WARRANTY; without even the implied warranty of +MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the +GNU General Public License for more details. + +You should have received a copy of the GNU General Public License +along with this program; if not, write to the Free Software +Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA +-} + +{- | + Module : Text.Pandoc.Readers.Docx.Fonts + Copyright : Copyright (C) 2014 Matthew Pickering + License : GNU GPL, version 2 or above + + Maintainer : Matthew Pickering <matthewtpickering@gmail.com> + Stability : alpha + Portability : portable + +Utilities to convert between font codepoints and unicode characters. +-} +module Text.Pandoc.Readers.Docx.Fonts (getUnicode, Font(..)) where + + +-- | Enumeration of recognised fonts +data Font = Symbol -- ^ <http://en.wikipedia.org/wiki/Symbol_(typeface) Adobe Symbol> + deriving (Show, Eq) + +-- | Given a font and codepoint, returns the corresponding unicode +-- character +getUnicode :: Font -> Char -> Maybe Char +getUnicode Symbol c = lookup c symbol + +-- Generated from lib/fonts/symbol.txt +symbol :: [(Char, Char)] +symbol = + [ (' ',' ') + , (' ','\160') + , ('!','!') + , ('"','\8704') + , ('#','#') + , ('$','\8707') + , ('%','%') + , ('&','&') + , ('\'','\8715') + , ('(','(') + , (')',')') + , ('*','\8727') + , ('+','+') + , (',',',') + , ('-','\8722') + , ('.','.') + , ('/','/') + , ('0','0') + , ('1','1') + , ('2','2') + , ('3','3') + , ('4','4') + , ('5','5') + , ('6','6') + , ('7','7') + , ('8','8') + , ('9','9') + , (':',':') + , (';',';') + , ('<','<') + , ('=','=') + , ('>','>') + , ('?','?') + , ('@','\8773') + , ('A','\913') + , ('B','\914') + , ('C','\935') + , ('D','\916') + , ('D','\8710') + , ('E','\917') + , ('F','\934') + , ('G','\915') + , ('H','\919') + , ('I','\921') + , ('J','\977') + , ('K','\922') + , ('L','\923') + , ('M','\924') + , ('N','\925') + , ('O','\927') + , ('P','\928') + , ('Q','\920') + , ('R','\929') + , ('S','\931') + , ('T','\932') + , ('U','\933') + , ('V','\962') + , ('W','\937') + , ('W','\8486') + , ('X','\926') + , ('Y','\936') + , ('Z','\918') + , ('[','[') + , ('\\','\8756') + , (']',']') + , ('^','\8869') + , ('_','_') + , ('`','\63717') + , ('a','\945') + , ('b','\946') + , ('c','\967') + , ('d','\948') + , ('e','\949') + , ('f','\966') + , ('g','\947') + , ('h','\951') + , ('i','\953') + , ('j','\981') + , ('k','\954') + , ('l','\955') + , ('m','\181') + , ('m','\956') + , ('n','\957') + , ('o','\959') + , ('p','\960') + , ('q','\952') + , ('r','\961') + , ('s','\963') + , ('t','\964') + , ('u','\965') + , ('v','\982') + , ('w','\969') + , ('x','\958') + , ('y','\968') + , ('z','\950') + , ('{','{') + , ('|','|') + , ('}','}') + , ('~','\8764') + , ('\160','\8364') + , ('\161','\978') + , ('\162','\8242') + , ('\163','\8804') + , ('\164','\8260') + , ('\164','\8725') + , ('\165','\8734') + , ('\166','\402') + , ('\167','\9827') + , ('\168','\9830') + , ('\169','\9829') + , ('\170','\9824') + , ('\171','\8596') + , ('\172','\8592') + , ('\173','\8593') + , ('\174','\8594') + , ('\175','\8595') + , ('\176','\176') + , ('\177','\177') + , ('\178','\8243') + , ('\179','\8805') + , ('\180','\215') + , ('\181','\8733') + , ('\182','\8706') + , ('\183','\8226') + , ('\184','\247') + , ('\185','\8800') + , ('\186','\8801') + , ('\187','\8776') + , ('\188','\8230') + , ('\189','\63718') + , ('\190','\63719') + , ('\191','\8629') + , ('\192','\8501') + , ('\193','\8465') + , ('\194','\8476') + , ('\195','\8472') + , ('\196','\8855') + , ('\197','\8853') + , ('\198','\8709') + , ('\199','\8745') + , ('\200','\8746') + , ('\201','\8835') + , ('\202','\8839') + , ('\203','\8836') + , ('\204','\8834') + , ('\205','\8838') + , ('\206','\8712') + , ('\207','\8713') + , ('\208','\8736') + , ('\209','\8711') + , ('\210','\63194') + , ('\211','\63193') + , ('\212','\63195') + , ('\213','\8719') + , ('\214','\8730') + , ('\215','\8901') + , ('\216','\172') + , ('\217','\8743') + , ('\218','\8744') + , ('\219','\8660') + , ('\220','\8656') + , ('\221','\8657') + , ('\222','\8658') + , ('\223','\8659') + , ('\224','\9674') + , ('\225','\9001') + , ('\226','\63720') + , ('\227','\63721') + , ('\228','\63722') + , ('\229','\8721') + , ('\230','\63723') + , ('\231','\63724') + , ('\232','\63725') + , ('\233','\63726') + , ('\234','\63727') + , ('\235','\63728') + , ('\236','\63729') + , ('\237','\63730') + , ('\238','\63731') + , ('\239','\63732') + , ('\241','\9002') + , ('\242','\8747') + , ('\243','\8992') + , ('\244','\63733') + , ('\245','\8993') + , ('\246','\63734') + , ('\247','\63735') + , ('\248','\63736') + , ('\249','\63737') + , ('\250','\63738') + , ('\251','\63739') + , ('\252','\63740') + , ('\253','\63741') + , ('\254','\63742')] diff --git a/src/Text/Pandoc/Readers/Docx/Lists.hs b/src/Text/Pandoc/Readers/Docx/Lists.hs new file mode 100644 index 000000000..c265ad074 --- /dev/null +++ b/src/Text/Pandoc/Readers/Docx/Lists.hs @@ -0,0 +1,229 @@ +{- +Copyright (C) 2014 Jesse Rosenthal <jrosenthal@jhu.edu> + +This program is free software; you can redistribute it and/or modify +it under the terms of the GNU General Public License as published by +the Free Software Foundation; either version 2 of the License, or +(at your option) any later version. + +This program is distributed in the hope that it will be useful, +but WITHOUT ANY WARRANTY; without even the implied warranty of +MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the +GNU General Public License for more details. + +You should have received a copy of the GNU General Public License +along with this program; if not, write to the Free Software +Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA +-} + +{- | + Module : Text.Pandoc.Readers.Docx.Lists + Copyright : Copyright (C) 2014 Jesse Rosenthal + License : GNU GPL, version 2 or above + + Maintainer : Jesse Rosenthal <jrosenthal@jhu.edu> + Stability : alpha + Portability : portable + +Functions for converting flat docx paragraphs into nested lists. +-} + +module Text.Pandoc.Readers.Docx.Lists ( blocksToBullets + , blocksToDefinitions + , listParagraphDivs + ) where + +import Text.Pandoc.JSON +import Text.Pandoc.Generic (bottomUp) +import Text.Pandoc.Shared (trim) +import Control.Monad +import Data.List +import Data.Maybe + +isListItem :: Block -> Bool +isListItem (Div (_, classes, _) _) | "list-item" `elem` classes = True +isListItem _ = False + +getLevel :: Block -> Maybe Integer +getLevel (Div (_, _, kvs) _) = liftM read $ lookup "level" kvs +getLevel _ = Nothing + +getLevelN :: Block -> Integer +getLevelN b = case getLevel b of + Just n -> n + Nothing -> -1 + +getNumId :: Block -> Maybe Integer +getNumId (Div (_, _, kvs) _) = liftM read $ lookup "num-id" kvs +getNumId _ = Nothing + +getNumIdN :: Block -> Integer +getNumIdN b = case getNumId b of + Just n -> n + Nothing -> -1 + +getText :: Block -> Maybe String +getText (Div (_, _, kvs) _) = lookup "text" kvs +getText _ = Nothing + +data ListType = Itemized | Enumerated ListAttributes + +listStyleMap :: [(String, ListNumberStyle)] +listStyleMap = [("upperLetter", UpperAlpha), + ("lowerLetter", LowerAlpha), + ("upperRoman", UpperRoman), + ("lowerRoman", LowerRoman), + ("decimal", Decimal)] + +listDelimMap :: [(String, ListNumberDelim)] +listDelimMap = [("%1)", OneParen), + ("(%1)", TwoParens), + ("%1.", Period)] + +getListType :: Block -> Maybe ListType +getListType b@(Div (_, _, kvs) _) | isListItem b = + let + start = lookup "start" kvs + frmt = lookup "format" kvs + txt = lookup "text" kvs + in + case frmt of + Just "bullet" -> Just Itemized + Just f -> + case txt of + Just t -> Just $ Enumerated ( + read (fromMaybe "1" start) :: Int, + fromMaybe DefaultStyle (lookup f listStyleMap), + fromMaybe DefaultDelim (lookup t listDelimMap)) + Nothing -> Nothing + _ -> Nothing +getListType _ = Nothing + +listParagraphDivs :: [String] +listParagraphDivs = ["ListParagraph"] + +-- This is a first stab at going through and attaching meaning to list +-- paragraphs, without an item marker, following a list item. We +-- assume that these are paragraphs in the same item. + +handleListParagraphs :: [Block] -> [Block] +handleListParagraphs [] = [] +handleListParagraphs ( + (Div attr1@(_, classes1, _) blks1) : + (Div (ident2, classes2, kvs2) blks2) : + blks + ) | "list-item" `elem` classes1 && + not ("list-item" `elem` classes2) && + (not . null) (listParagraphDivs `intersect` classes2) = + -- We don't want to keep this indent. + let newDiv2 = + (Div (ident2, classes2, filter (\kv -> fst kv /= "indent") kvs2) blks2) + in + handleListParagraphs ((Div attr1 (blks1 ++ [newDiv2])) : blks) +handleListParagraphs (blk:blks) = blk : (handleListParagraphs blks) + +separateBlocks' :: Block -> [[Block]] -> [[Block]] +separateBlocks' blk ([] : []) = [[blk]] +separateBlocks' b@(BulletList _) acc = (init acc) ++ [(last acc) ++ [b]] +separateBlocks' b@(OrderedList _ _) acc = (init acc) ++ [(last acc) ++ [b]] +-- The following is for the invisible bullet lists. This is how +-- pandoc-generated ooxml does multiparagraph item lists. +separateBlocks' b acc | liftM trim (getText b) == Just "" = + (init acc) ++ [(last acc) ++ [b]] +separateBlocks' b acc = acc ++ [[b]] + +separateBlocks :: [Block] -> [[Block]] +separateBlocks blks = foldr separateBlocks' [[]] (reverse blks) + +flatToBullets' :: Integer -> [Block] -> [Block] +flatToBullets' _ [] = [] +flatToBullets' num xs@(b : elems) + | getLevelN b == num = b : (flatToBullets' num elems) + | otherwise = + let bNumId = getNumIdN b + bLevel = getLevelN b + (children, remaining) = + span + (\b' -> + ((getLevelN b') > bLevel || + ((getLevelN b') == bLevel && (getNumIdN b') == bNumId))) + xs + in + case getListType b of + Just (Enumerated attr) -> + (OrderedList attr (separateBlocks $ flatToBullets' bLevel children)) : + (flatToBullets' num remaining) + _ -> + (BulletList (separateBlocks $ flatToBullets' bLevel children)) : + (flatToBullets' num remaining) + +flatToBullets :: [Block] -> [Block] +flatToBullets elems = flatToBullets' (-1) elems + +singleItemHeaderToHeader :: Block -> Block +singleItemHeaderToHeader (OrderedList _ [[h@(Header _ _ _)]]) = h +singleItemHeaderToHeader blk = blk + + +blocksToBullets :: [Block] -> [Block] +blocksToBullets blks = + map singleItemHeaderToHeader $ + bottomUp removeListDivs $ + flatToBullets $ (handleListParagraphs blks) + +plainParaInlines :: Block -> [Inline] +plainParaInlines (Plain ils) = ils +plainParaInlines (Para ils) = ils +plainParaInlines _ = [] + +blocksToDefinitions' :: [([Inline], [[Block]])] -> [Block] -> [Block] -> [Block] +blocksToDefinitions' [] acc [] = reverse acc +blocksToDefinitions' defAcc acc [] = + reverse $ (DefinitionList (reverse defAcc)) : acc +blocksToDefinitions' defAcc acc + ((Div (_, classes1, _) blks1) : (Div (ident2, classes2, kvs2) blks2) : blks) + | "DefinitionTerm" `elem` classes1 && "Definition" `elem` classes2 = + let remainingAttr2 = (ident2, delete "Definition" classes2, kvs2) + pair = case remainingAttr2 == ("", [], []) of + True -> (concatMap plainParaInlines blks1, [blks2]) + False -> (concatMap plainParaInlines blks1, [[Div remainingAttr2 blks2]]) + in + blocksToDefinitions' (pair : defAcc) acc blks +blocksToDefinitions' defAcc acc + ((Div (ident2, classes2, kvs2) blks2) : blks) + | (not . null) defAcc && "Definition" `elem` classes2 = + let remainingAttr2 = (ident2, delete "Definition" classes2, kvs2) + defItems2 = case remainingAttr2 == ("", [], []) of + True -> blks2 + False -> [Div remainingAttr2 blks2] + ((defTerm, defItems):defs) = defAcc + defAcc' = case null defItems of + True -> (defTerm, [defItems2]) : defs + False -> (defTerm, init defItems ++ [last defItems ++ defItems2]) : defs + in + blocksToDefinitions' defAcc' acc blks +blocksToDefinitions' [] acc (b:blks) = + blocksToDefinitions' [] (b:acc) blks +blocksToDefinitions' defAcc acc (b:blks) = + blocksToDefinitions' [] (b : (DefinitionList (reverse defAcc)) : acc) blks + +removeListDivs' :: Block -> [Block] +removeListDivs' (Div (ident, classes, kvs) blks) + | "list-item" `elem` classes = + case delete "list-item" classes of + [] -> blks + classes' -> [Div (ident, classes', kvs) $ blks] +removeListDivs' (Div (ident, classes, kvs) blks) + | not $ null $ listParagraphDivs `intersect` classes = + case classes \\ listParagraphDivs of + [] -> blks + classes' -> [Div (ident, classes', kvs) blks] +removeListDivs' blk = [blk] + +removeListDivs :: [Block] -> [Block] +removeListDivs = concatMap removeListDivs' + + + +blocksToDefinitions :: [Block] -> [Block] +blocksToDefinitions = blocksToDefinitions' [] [] diff --git a/src/Text/Pandoc/Readers/Docx/Parse.hs b/src/Text/Pandoc/Readers/Docx/Parse.hs new file mode 100644 index 000000000..5fd6b7a81 --- /dev/null +++ b/src/Text/Pandoc/Readers/Docx/Parse.hs @@ -0,0 +1,911 @@ +{-# LANGUAGE PatternGuards, ViewPatterns, FlexibleInstances #-} + +{- +Copyright (C) 2014 Jesse Rosenthal <jrosenthal@jhu.edu> + +This program is free software; you can redistribute it and/or modify +it under the terms of the GNU General Public License as published by +the Free Software Foundation; either version 2 of the License, or +(at your option) any later version. + +This program is distributed in the hope that it will be useful, +but WITHOUT ANY WARRANTY; without even the implied warranty of +MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the +GNU General Public License for more details. + +You should have received a copy of the GNU General Public License +along with this program; if not, write to the Free Software +Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA +-} + +{- | + Module : Text.Pandoc.Readers.Docx.Parse + Copyright : Copyright (C) 2014 Jesse Rosenthal + License : GNU GPL, version 2 or above + + Maintainer : Jesse Rosenthal <jrosenthal@jhu.edu> + Stability : alpha + Portability : portable + +Conversion of docx archive into Docx haskell type +-} + +module Text.Pandoc.Readers.Docx.Parse ( Docx(..) + , Document(..) + , Body(..) + , BodyPart(..) + , TblLook(..) + , ParPart(..) + , Run(..) + , RunElem(..) + , Notes + , Numbering + , Relationship + , Media + , RunStyle(..) + , VertAlign(..) + , ParIndentation(..) + , ParagraphStyle(..) + , Row(..) + , Cell(..) + , archiveToDocx + ) where +import Codec.Archive.Zip +import Text.XML.Light +import Data.Maybe +import Data.List +import System.FilePath +import Data.Bits ((.|.)) +import qualified Data.ByteString.Lazy as B +import qualified Text.Pandoc.UTF8 as UTF8 +import Control.Monad.Reader +import Control.Applicative ((<$>), (<|>)) +import qualified Data.Map as M +import Text.Pandoc.Compat.Except +import Text.TeXMath.Readers.OMML (readOMML) +import Text.Pandoc.Readers.Docx.Fonts (getUnicode, Font(..)) +import Text.TeXMath (Exp) +import Data.Char (readLitChar, ord, chr, isDigit) + +data ReaderEnv = ReaderEnv { envNotes :: Notes + , envNumbering :: Numbering + , envRelationships :: [Relationship] + , envMedia :: Media + , envFont :: Maybe Font + , envCharStyles :: CharStyleMap + , envParStyles :: ParStyleMap + } + deriving Show + +data DocxError = DocxError | WrongElem + deriving Show + +instance Error DocxError where + noMsg = WrongElem + +type D = ExceptT DocxError (Reader ReaderEnv) + +runD :: D a -> ReaderEnv -> Either DocxError a +runD dx re = runReader (runExceptT dx ) re + +maybeToD :: Maybe a -> D a +maybeToD (Just a) = return a +maybeToD Nothing = throwError DocxError + +eitherToD :: Either a b -> D b +eitherToD (Right b) = return b +eitherToD (Left _) = throwError DocxError + +concatMapM :: (Monad m) => (a -> m [b]) -> [a] -> m [b] +concatMapM f xs = liftM concat (mapM f xs) + + +-- This is similar to `mapMaybe`: it maps a function returning the D +-- monad over a list, and only keeps the non-erroring return values. +mapD :: (a -> D b) -> [a] -> D [b] +mapD f xs = + let handler x = (f x >>= (\y-> return [y])) `catchError` (\_ -> return []) + in + concatMapM handler xs + +type NameSpaces = [(String, String)] + +data Docx = Docx Document + deriving Show + +data Document = Document NameSpaces Body + deriving Show + +data Body = Body [BodyPart] + deriving Show + +type Media = [(FilePath, B.ByteString)] + +type CharStyle = (String, RunStyle) + +type ParStyle = (String, ParStyleData) + +type CharStyleMap = M.Map String RunStyle + +type ParStyleMap = M.Map String ParStyleData + +data Numbering = Numbering NameSpaces [Numb] [AbstractNumb] + deriving Show + +data Numb = Numb String String -- right now, only a key to an abstract num + deriving Show + +data AbstractNumb = AbstractNumb String [Level] + deriving Show + +-- (ilvl, format, string, start) +type Level = (String, String, String, Maybe Integer) + +data Relationship = Relationship (RelId, Target) + deriving Show + +data Notes = Notes NameSpaces + (Maybe (M.Map String Element)) + (Maybe (M.Map String Element)) + deriving Show + +data ParIndentation = ParIndentation { leftParIndent :: Maybe Integer + , rightParIndent :: Maybe Integer + , hangingParIndent :: Maybe Integer} + deriving Show + +data ParagraphStyle = ParagraphStyle { pStyle :: [String] + , indentation :: Maybe ParIndentation + , dropCap :: Bool + , pHeading :: Maybe (String, Int) + , pBlockQuote :: Maybe Bool + } + deriving Show + +defaultParagraphStyle :: ParagraphStyle +defaultParagraphStyle = ParagraphStyle { pStyle = [] + , indentation = Nothing + , dropCap = False + , pHeading = Nothing + , pBlockQuote = Nothing + } + + +data BodyPart = Paragraph ParagraphStyle [ParPart] + | ListItem ParagraphStyle String String Level [ParPart] + | Tbl String TblGrid TblLook [Row] + | OMathPara [Exp] + deriving Show + +type TblGrid = [Integer] + +data TblLook = TblLook {firstRowFormatting::Bool} + deriving Show + +defaultTblLook :: TblLook +defaultTblLook = TblLook{firstRowFormatting = False} + +data Row = Row [Cell] + deriving Show + +data Cell = Cell [BodyPart] + deriving Show + +data ParPart = PlainRun Run + | Insertion ChangeId Author ChangeDate [Run] + | Deletion ChangeId Author ChangeDate [Run] + | BookMark BookMarkId Anchor + | InternalHyperLink Anchor [Run] + | ExternalHyperLink URL [Run] + | Drawing FilePath B.ByteString + | PlainOMath [Exp] + deriving Show + +data Run = Run RunStyle [RunElem] + | Footnote [BodyPart] + | Endnote [BodyPart] + | InlineDrawing FilePath B.ByteString + deriving Show + +data RunElem = TextRun String | LnBrk | Tab + deriving Show + +data VertAlign = BaseLn | SupScrpt | SubScrpt + deriving Show + +data RunStyle = RunStyle { isBold :: Maybe Bool + , isItalic :: Maybe Bool + , isSmallCaps :: Maybe Bool + , isStrike :: Maybe Bool + , rVertAlign :: Maybe VertAlign + , rUnderline :: Maybe String + , rStyle :: Maybe CharStyle} + deriving Show + +data ParStyleData = ParStyleData { headingLev :: Maybe (String, Int) + , isBlockQuote :: Maybe Bool + , psStyle :: Maybe ParStyle} + deriving Show + +defaultRunStyle :: RunStyle +defaultRunStyle = RunStyle { isBold = Nothing + , isItalic = Nothing + , isSmallCaps = Nothing + , isStrike = Nothing + , rVertAlign = Nothing + , rUnderline = Nothing + , rStyle = Nothing} + + +type Target = String +type Anchor = String +type URL = String +type BookMarkId = String +type RelId = String +type ChangeId = String +type Author = String +type ChangeDate = String + +attrToNSPair :: Attr -> Maybe (String, String) +attrToNSPair (Attr (QName s _ (Just "xmlns")) val) = Just (s, val) +attrToNSPair _ = Nothing + +archiveToDocx :: Archive -> Either DocxError Docx +archiveToDocx archive = do + let notes = archiveToNotes archive + numbering = archiveToNumbering archive + rels = archiveToRelationships archive + media = archiveToMedia archive + (styles, parstyles) = archiveToStyles archive + rEnv = ReaderEnv notes numbering rels media Nothing styles parstyles + doc <- runD (archiveToDocument archive) rEnv + return $ Docx doc + + +archiveToDocument :: Archive -> D Document +archiveToDocument zf = do + entry <- maybeToD $ findEntryByPath "word/document.xml" zf + docElem <- maybeToD $ (parseXMLDoc . UTF8.toStringLazy . fromEntry) entry + let namespaces = mapMaybe attrToNSPair (elAttribs docElem) + bodyElem <- maybeToD $ findChild (elemName namespaces "w" "body") docElem + body <- elemToBody namespaces bodyElem + return $ Document namespaces body + +elemToBody :: NameSpaces -> Element -> D Body +elemToBody ns element | isElem ns "w" "body" element = + mapD (elemToBodyPart ns) (elChildren element) >>= + (\bps -> return $ Body bps) +elemToBody _ _ = throwError WrongElem + +archiveToStyles :: Archive -> (CharStyleMap, ParStyleMap) +archiveToStyles zf = + let stylesElem = findEntryByPath "word/styles.xml" zf >>= + (parseXMLDoc . UTF8.toStringLazy . fromEntry) + in + case stylesElem of + Nothing -> (M.empty, M.empty) + Just styElem -> + let namespaces = mapMaybe attrToNSPair (elAttribs styElem) + in + ( M.fromList $ buildBasedOnList namespaces styElem + (Nothing :: Maybe CharStyle), + M.fromList $ buildBasedOnList namespaces styElem + (Nothing :: Maybe ParStyle) ) + +isBasedOnStyle :: (ElemToStyle a) => NameSpaces -> Element -> Maybe a -> Bool +isBasedOnStyle ns element parentStyle + | isElem ns "w" "style" element + , Just styleType <- findAttr (elemName ns "w" "type") element + , styleType == cStyleType parentStyle + , Just basedOnVal <- findChild (elemName ns "w" "basedOn") element >>= + findAttr (elemName ns "w" "val") + , Just ps <- parentStyle = (basedOnVal == getStyleId ps) + | isElem ns "w" "style" element + , Just styleType <- findAttr (elemName ns "w" "type") element + , styleType == cStyleType parentStyle + , Nothing <- findChild (elemName ns "w" "basedOn") element + , Nothing <- parentStyle = True + | otherwise = False + +class ElemToStyle a where + cStyleType :: Maybe a -> String + elemToStyle :: NameSpaces -> Element -> Maybe a -> Maybe a + getStyleId :: a -> String + +instance ElemToStyle CharStyle where + cStyleType _ = "character" + elemToStyle ns element parentStyle + | isElem ns "w" "style" element + , Just "character" <- findAttr (elemName ns "w" "type") element + , Just styleId <- findAttr (elemName ns "w" "styleId") element = + Just (styleId, elemToRunStyle ns element parentStyle) + | otherwise = Nothing + getStyleId s = fst s + +instance ElemToStyle ParStyle where + cStyleType _ = "paragraph" + elemToStyle ns element parentStyle + | isElem ns "w" "style" element + , Just "paragraph" <- findAttr (elemName ns "w" "type") element + , Just styleId <- findAttr (elemName ns "w" "styleId") element = + Just (styleId, elemToParStyleData ns element parentStyle) + | otherwise = Nothing + getStyleId s = fst s + +getStyleChildren :: (ElemToStyle a) => NameSpaces -> Element -> Maybe a -> [a] +getStyleChildren ns element parentStyle + | isElem ns "w" "styles" element = + mapMaybe (\e -> elemToStyle ns e parentStyle) $ + filterChildren (\e' -> isBasedOnStyle ns e' parentStyle) element + | otherwise = [] + +buildBasedOnList :: (ElemToStyle a) => NameSpaces -> Element -> Maybe a -> [a] +buildBasedOnList ns element rootStyle = + case (getStyleChildren ns element rootStyle) of + [] -> [] + stys -> stys ++ + (concatMap (\s -> buildBasedOnList ns element (Just s)) stys) + +archiveToNotes :: Archive -> Notes +archiveToNotes zf = + let fnElem = findEntryByPath "word/footnotes.xml" zf + >>= (parseXMLDoc . UTF8.toStringLazy . fromEntry) + enElem = findEntryByPath "word/endnotes.xml" zf + >>= (parseXMLDoc . UTF8.toStringLazy . fromEntry) + fn_namespaces = case fnElem of + Just e -> mapMaybe attrToNSPair (elAttribs e) + Nothing -> [] + en_namespaces = case enElem of + Just e -> mapMaybe attrToNSPair (elAttribs e) + Nothing -> [] + ns = unionBy (\x y -> fst x == fst y) fn_namespaces en_namespaces + fn = fnElem >>= (elemToNotes ns "footnote") + en = enElem >>= (elemToNotes ns "endnote") + in + Notes ns fn en + +filePathIsRel :: FilePath -> Bool +filePathIsRel fp = + let (dir, name) = splitFileName fp + in + (dir == "word/_rels/") && ((takeExtension name) == ".rels") + +relElemToRelationship :: Element -> Maybe Relationship +relElemToRelationship element | qName (elName element) == "Relationship" = + do + relId <- findAttr (QName "Id" Nothing Nothing) element + target <- findAttr (QName "Target" Nothing Nothing) element + return $ Relationship (relId, target) +relElemToRelationship _ = Nothing + + +archiveToRelationships :: Archive -> [Relationship] +archiveToRelationships archive = + let relPaths = filter filePathIsRel (filesInArchive archive) + entries = mapMaybe (\f -> findEntryByPath f archive) relPaths + relElems = mapMaybe (parseXMLDoc . UTF8.toStringLazy . fromEntry) entries + rels = mapMaybe relElemToRelationship $ concatMap elChildren relElems + in + rels + +filePathIsMedia :: FilePath -> Bool +filePathIsMedia fp = + let (dir, _) = splitFileName fp + in + (dir == "word/media/") + +getMediaPair :: Archive -> FilePath -> Maybe (FilePath, B.ByteString) +getMediaPair zf fp = + case findEntryByPath fp zf of + Just e -> Just (fp, fromEntry e) + Nothing -> Nothing + +archiveToMedia :: Archive -> Media +archiveToMedia zf = + mapMaybe (getMediaPair zf) (filter filePathIsMedia (filesInArchive zf)) + +lookupLevel :: String -> String -> Numbering -> Maybe Level +lookupLevel numId ilvl (Numbering _ numbs absNumbs) = do + absNumId <- lookup numId $ map (\(Numb nid absnumid) -> (nid, absnumid)) numbs + lvls <- lookup absNumId $ map (\(AbstractNumb aid ls) -> (aid, ls)) absNumbs + lvl <- lookup ilvl $ map (\l@(i, _, _, _) -> (i, l)) lvls + return lvl + +numElemToNum :: NameSpaces -> Element -> Maybe Numb +numElemToNum ns element | + qName (elName element) == "num" && + qURI (elName element) == (lookup "w" ns) = do + numId <- findAttr (QName "numId" (lookup "w" ns) (Just "w")) element + absNumId <- findChild (QName "abstractNumId" (lookup "w" ns) (Just "w")) element + >>= findAttr (QName "val" (lookup "w" ns) (Just "w")) + return $ Numb numId absNumId +numElemToNum _ _ = Nothing + +absNumElemToAbsNum :: NameSpaces -> Element -> Maybe AbstractNumb +absNumElemToAbsNum ns element | + qName (elName element) == "abstractNum" && + qURI (elName element) == (lookup "w" ns) = do + absNumId <- findAttr + (QName "abstractNumId" (lookup "w" ns) (Just "w")) + element + let levelElems = findChildren + (QName "lvl" (lookup "w" ns) (Just "w")) + element + levels = mapMaybe (levelElemToLevel ns) levelElems + return $ AbstractNumb absNumId levels +absNumElemToAbsNum _ _ = Nothing + +levelElemToLevel :: NameSpaces -> Element -> Maybe Level +levelElemToLevel ns element | + qName (elName element) == "lvl" && + qURI (elName element) == (lookup "w" ns) = do + ilvl <- findAttr (QName "ilvl" (lookup "w" ns) (Just "w")) element + fmt <- findChild (QName "numFmt" (lookup "w" ns) (Just "w")) element + >>= findAttr (QName "val" (lookup "w" ns) (Just "w")) + txt <- findChild (QName "lvlText" (lookup "w" ns) (Just "w")) element + >>= findAttr (QName "val" (lookup "w" ns) (Just "w")) + let start = findChild (QName "start" (lookup "w" ns) (Just "w")) element + >>= findAttr (QName "val" (lookup "w" ns) (Just "w")) + >>= (\s -> listToMaybe (map fst (reads s :: [(Integer, String)]))) + return (ilvl, fmt, txt, start) +levelElemToLevel _ _ = Nothing + +archiveToNumbering' :: Archive -> Maybe Numbering +archiveToNumbering' zf = do + case findEntryByPath "word/numbering.xml" zf of + Nothing -> Just $ Numbering [] [] [] + Just entry -> do + numberingElem <- (parseXMLDoc . UTF8.toStringLazy . fromEntry) entry + let namespaces = mapMaybe attrToNSPair (elAttribs numberingElem) + numElems = findChildren + (QName "num" (lookup "w" namespaces) (Just "w")) + numberingElem + absNumElems = findChildren + (QName "abstractNum" (lookup "w" namespaces) (Just "w")) + numberingElem + nums = mapMaybe (numElemToNum namespaces) numElems + absNums = mapMaybe (absNumElemToAbsNum namespaces) absNumElems + return $ Numbering namespaces nums absNums + +archiveToNumbering :: Archive -> Numbering +archiveToNumbering archive = + fromMaybe (Numbering [] [] []) (archiveToNumbering' archive) + +elemToNotes :: NameSpaces -> String -> Element -> Maybe (M.Map String Element) +elemToNotes ns notetype element + | isElem ns "w" (notetype ++ "s") element = + let pairs = mapMaybe + (\e -> findAttr (elemName ns "w" "id") e >>= + (\a -> Just (a, e))) + (findChildren (elemName ns "w" notetype) element) + in + Just $ M.fromList $ pairs +elemToNotes _ _ _ = Nothing + +--------------------------------------------- +--------------------------------------------- + +elemName :: NameSpaces -> String -> String -> QName +elemName ns prefix name = (QName name (lookup prefix ns) (Just prefix)) + +isElem :: NameSpaces -> String -> String -> Element -> Bool +isElem ns prefix name element = + qName (elName element) == name && + qURI (elName element) == (lookup prefix ns) + + +elemToTblGrid :: NameSpaces -> Element -> D TblGrid +elemToTblGrid ns element | isElem ns "w" "tblGrid" element = + let cols = findChildren (elemName ns "w" "gridCol") element + in + mapD (\e -> maybeToD (findAttr (elemName ns "w" "val") e >>= stringToInteger)) + cols +elemToTblGrid _ _ = throwError WrongElem + +elemToTblLook :: NameSpaces -> Element -> D TblLook +elemToTblLook ns element | isElem ns "w" "tblLook" element = + let firstRow = findAttr (elemName ns "w" "firstRow") element + val = findAttr (elemName ns "w" "val") element + firstRowFmt = + case firstRow of + Just "1" -> True + Just _ -> False + Nothing -> case val of + Just bitMask -> testBitMask bitMask 0x020 + Nothing -> False + in + return $ TblLook{firstRowFormatting = firstRowFmt} +elemToTblLook _ _ = throwError WrongElem + +elemToRow :: NameSpaces -> Element -> D Row +elemToRow ns element | isElem ns "w" "tr" element = + do + let cellElems = findChildren (elemName ns "w" "tc") element + cells <- mapD (elemToCell ns) cellElems + return $ Row cells +elemToRow _ _ = throwError WrongElem + +elemToCell :: NameSpaces -> Element -> D Cell +elemToCell ns element | isElem ns "w" "tc" element = + do + cellContents <- mapD (elemToBodyPart ns) (elChildren element) + return $ Cell cellContents +elemToCell _ _ = throwError WrongElem + +elemToParIndentation :: NameSpaces -> Element -> Maybe ParIndentation +elemToParIndentation ns element | isElem ns "w" "ind" element = + Just $ ParIndentation { + leftParIndent = + findAttr (QName "left" (lookup "w" ns) (Just "w")) element >>= + stringToInteger + , rightParIndent = + findAttr (QName "right" (lookup "w" ns) (Just "w")) element >>= + stringToInteger + , hangingParIndent = + findAttr (QName "hanging" (lookup "w" ns) (Just "w")) element >>= + stringToInteger} +elemToParIndentation _ _ = Nothing + + +elemToNumInfo :: NameSpaces -> Element -> Maybe (String, String) +elemToNumInfo ns element | isElem ns "w" "p" element = do + let pPr = findChild (elemName ns "w" "pPr") element + numPr = pPr >>= findChild (elemName ns "w" "numPr") + lvl <- numPr >>= + findChild (elemName ns "w" "ilvl") >>= + findAttr (elemName ns "w" "val") + numId <- numPr >>= + findChild (elemName ns "w" "numId") >>= + findAttr (elemName ns "w" "val") + return (numId, lvl) +elemToNumInfo _ _ = Nothing + +testBitMask :: String -> Int -> Bool +testBitMask bitMaskS n = + case (reads ("0x" ++ bitMaskS) :: [(Int, String)]) of + [] -> False + ((n', _) : _) -> ((n' .|. n) /= 0) + +stringToInteger :: String -> Maybe Integer +stringToInteger s = listToMaybe $ map fst (reads s :: [(Integer, String)]) + +elemToBodyPart :: NameSpaces -> Element -> D BodyPart +elemToBodyPart ns element + | isElem ns "w" "p" element + , (c:_) <- findChildren (elemName ns "m" "oMathPara") element = + do + expsLst <- eitherToD $ readOMML $ showElement c + return $ OMathPara expsLst +elemToBodyPart ns element + | isElem ns "w" "p" element + , Just (numId, lvl) <- elemToNumInfo ns element = do + sty <- asks envParStyles + let parstyle = elemToParagraphStyle ns element sty + parparts <- mapD (elemToParPart ns) (elChildren element) + num <- asks envNumbering + case lookupLevel numId lvl num of + Just levelInfo -> return $ ListItem parstyle numId lvl levelInfo parparts + Nothing -> throwError WrongElem +elemToBodyPart ns element + | isElem ns "w" "p" element = do + sty <- asks envParStyles + let parstyle = elemToParagraphStyle ns element sty + parparts <- mapD (elemToParPart ns) (elChildren element) + return $ Paragraph parstyle parparts +elemToBodyPart ns element + | isElem ns "w" "tbl" element = do + let caption' = findChild (elemName ns "w" "tblPr") element + >>= findChild (elemName ns "w" "tblCaption") + >>= findAttr (elemName ns "w" "val") + caption = (fromMaybe "" caption') + grid' = case findChild (elemName ns "w" "tblGrid") element of + Just g -> elemToTblGrid ns g + Nothing -> return [] + tblLook' = case findChild (elemName ns "w" "tblPr") element >>= + findChild (elemName ns "w" "tblLook") + of + Just l -> elemToTblLook ns l + Nothing -> return defaultTblLook + + grid <- grid' + tblLook <- tblLook' + rows <- mapD (elemToRow ns) (elChildren element) + return $ Tbl caption grid tblLook rows +elemToBodyPart _ _ = throwError WrongElem + +lookupRelationship :: RelId -> [Relationship] -> Maybe Target +lookupRelationship relid rels = + lookup relid (map (\(Relationship pair) -> pair) rels) + +expandDrawingId :: String -> D (FilePath, B.ByteString) +expandDrawingId s = do + target <- asks (lookupRelationship s . envRelationships) + case target of + Just filepath -> do + bytes <- asks (lookup ("word/" ++ filepath) . envMedia) + case bytes of + Just bs -> return (filepath, bs) + Nothing -> throwError DocxError + Nothing -> throwError DocxError + +elemToParPart :: NameSpaces -> Element -> D ParPart +elemToParPart ns element + | isElem ns "w" "r" element + , Just _ <- findChild (elemName ns "w" "drawing") element = + let a_ns = "http://schemas.openxmlformats.org/drawingml/2006/main" + drawing = findElement (QName "blip" (Just a_ns) (Just "a")) element + >>= findAttr (QName "embed" (lookup "r" ns) (Just "r")) + in + case drawing of + Just s -> expandDrawingId s >>= (\(fp, bs) -> return $ Drawing fp bs) + Nothing -> throwError WrongElem +elemToParPart ns element + | isElem ns "w" "r" element = + elemToRun ns element >>= (\r -> return $ PlainRun r) +elemToParPart ns element + | isElem ns "w" "ins" element + , Just cId <- findAttr (elemName ns "w" "id") element + , Just cAuthor <- findAttr (elemName ns "w" "author") element + , Just cDate <- findAttr (elemName ns "w" "date") element = do + runs <- mapD (elemToRun ns) (elChildren element) + return $ Insertion cId cAuthor cDate runs +elemToParPart ns element + | isElem ns "w" "del" element + , Just cId <- findAttr (elemName ns "w" "id") element + , Just cAuthor <- findAttr (elemName ns "w" "author") element + , Just cDate <- findAttr (elemName ns "w" "date") element = do + runs <- mapD (elemToRun ns) (elChildren element) + return $ Deletion cId cAuthor cDate runs +elemToParPart ns element + | isElem ns "w" "bookmarkStart" element + , Just bmId <- findAttr (elemName ns "w" "id") element + , Just bmName <- findAttr (elemName ns "w" "name") element = + return $ BookMark bmId bmName +elemToParPart ns element + | isElem ns "w" "hyperlink" element + , Just relId <- findAttr (elemName ns "r" "id") element = do + runs <- mapD (elemToRun ns) (elChildren element) + rels <- asks envRelationships + case lookupRelationship relId rels of + Just target -> do + case findAttr (elemName ns "w" "anchor") element of + Just anchor -> return $ ExternalHyperLink (target ++ '#':anchor) runs + Nothing -> return $ ExternalHyperLink target runs + Nothing -> return $ ExternalHyperLink "" runs +elemToParPart ns element + | isElem ns "w" "hyperlink" element + , Just anchor <- findAttr (elemName ns "w" "anchor") element = do + runs <- mapD (elemToRun ns) (elChildren element) + return $ InternalHyperLink anchor runs +elemToParPart ns element + | isElem ns "m" "oMath" element = + (eitherToD $ readOMML $ showElement element) >>= (return . PlainOMath) +elemToParPart _ _ = throwError WrongElem + +lookupFootnote :: String -> Notes -> Maybe Element +lookupFootnote s (Notes _ fns _) = fns >>= (M.lookup s) + +lookupEndnote :: String -> Notes -> Maybe Element +lookupEndnote s (Notes _ _ ens) = ens >>= (M.lookup s) + +elemToRun :: NameSpaces -> Element -> D Run +elemToRun ns element + | isElem ns "w" "r" element + , Just drawingElem <- findChild (elemName ns "w" "drawing") element = + let a_ns = "http://schemas.openxmlformats.org/drawingml/2006/main" + drawing = findElement (QName "blip" (Just a_ns) (Just "a")) drawingElem + >>= findAttr (QName "embed" (lookup "r" ns) (Just "r")) + in + case drawing of + Just s -> expandDrawingId s >>= + (\(fp, bs) -> return $ InlineDrawing fp bs) + Nothing -> throwError WrongElem +elemToRun ns element + | isElem ns "w" "r" element + , Just ref <- findChild (elemName ns "w" "footnoteReference") element + , Just fnId <- findAttr (elemName ns "w" "id") ref = do + notes <- asks envNotes + case lookupFootnote fnId notes of + Just e -> do bps <- mapD (elemToBodyPart ns) (elChildren e) + return $ Footnote bps + Nothing -> return $ Footnote [] +elemToRun ns element + | isElem ns "w" "r" element + , Just ref <- findChild (elemName ns "w" "endnoteReference") element + , Just enId <- findAttr (elemName ns "w" "id") ref = do + notes <- asks envNotes + case lookupEndnote enId notes of + Just e -> do bps <- mapD (elemToBodyPart ns) (elChildren e) + return $ Endnote bps + Nothing -> return $ Endnote [] +elemToRun ns element + | isElem ns "w" "r" element = do + runElems <- elemToRunElems ns element + runStyle <- elemToRunStyleD ns element + return $ Run runStyle runElems +elemToRun _ _ = throwError WrongElem + +getParentStyleValue :: (ParStyleData -> Maybe a) -> ParStyleData -> Maybe a +getParentStyleValue field style + | Just value <- field style = Just value + | Just parentStyle <- psStyle style + = getParentStyleValue field (snd parentStyle) +getParentStyleValue _ _ = Nothing + +getParStyleField :: (ParStyleData -> Maybe a) -> ParStyleMap -> [String] -> + Maybe a +getParStyleField field stylemap styles + | x <- mapMaybe (\x -> M.lookup x stylemap) styles + , (y:_) <- mapMaybe (getParentStyleValue field) x + = Just y +getParStyleField _ _ _ = Nothing + +elemToParagraphStyle :: NameSpaces -> Element -> ParStyleMap -> ParagraphStyle +elemToParagraphStyle ns element sty + | Just pPr <- findChild (elemName ns "w" "pPr") element = + let style = + mapMaybe + (findAttr (elemName ns "w" "val")) + (findChildren (elemName ns "w" "pStyle") pPr) + in ParagraphStyle + {pStyle = style + , indentation = + findChild (elemName ns "w" "ind") pPr >>= + elemToParIndentation ns + , dropCap = + case + findChild (elemName ns "w" "framePr") pPr >>= + findAttr (elemName ns "w" "dropCap") + of + Just "none" -> False + Just _ -> True + Nothing -> False + , pHeading = getParStyleField headingLev sty style + , pBlockQuote = getParStyleField isBlockQuote sty style + } +elemToParagraphStyle _ _ _ = defaultParagraphStyle + +checkOnOff :: NameSpaces -> Element -> QName -> Maybe Bool +checkOnOff ns rPr tag + | Just t <- findChild tag rPr + , Just val <- findAttr (elemName ns "w" "val") t = + Just $ case val of + "true" -> True + "false" -> False + "on" -> True + "off" -> False + "1" -> True + "0" -> False + _ -> False + | Just _ <- findChild tag rPr = Just True +checkOnOff _ _ _ = Nothing + +elemToRunStyleD :: NameSpaces -> Element -> D RunStyle +elemToRunStyleD ns element + | Just rPr <- findChild (elemName ns "w" "rPr") element = do + charStyles <- asks envCharStyles + let parentSty = case + findChild (elemName ns "w" "rStyle") rPr >>= + findAttr (elemName ns "w" "val") + of + Just styName | Just style <- M.lookup styName charStyles -> + Just (styName, style) + _ -> Nothing + return $ elemToRunStyle ns element parentSty +elemToRunStyleD _ _ = return defaultRunStyle + +elemToRunStyle :: NameSpaces -> Element -> Maybe CharStyle -> RunStyle +elemToRunStyle ns element parentStyle + | Just rPr <- findChild (elemName ns "w" "rPr") element = + RunStyle + { + isBold = checkOnOff ns rPr (elemName ns "w" "b") + , isItalic = checkOnOff ns rPr (elemName ns "w" "i") + , isSmallCaps = checkOnOff ns rPr (elemName ns "w" "smallCaps") + , isStrike = checkOnOff ns rPr (elemName ns "w" "strike") + , rVertAlign = + findChild (elemName ns "w" "vertAlign") rPr >>= + findAttr (elemName ns "w" "val") >>= + \v -> Just $ case v of + "superscript" -> SupScrpt + "subscript" -> SubScrpt + _ -> BaseLn + , rUnderline = + findChild (elemName ns "w" "u") rPr >>= + findAttr (elemName ns "w" "val") + , rStyle = parentStyle + } +elemToRunStyle _ _ _ = defaultRunStyle + +isNumericNotNull :: String -> Bool +isNumericNotNull str = (str /= []) && (all isDigit str) + +getHeaderLevel :: NameSpaces -> Element -> Maybe (String,Int) +getHeaderLevel ns element + | Just styleId <- findAttr (elemName ns "w" "styleId") element + , Just index <- stripPrefix "Heading" styleId + , isNumericNotNull index = Just (styleId, read index) + | Just styleId <- findAttr (elemName ns "w" "styleId") element + , Just index <- findChild (elemName ns "w" "name") element >>= + findAttr (elemName ns "w" "val") >>= + stripPrefix "heading " + , isNumericNotNull index = Just (styleId, read index) +getHeaderLevel _ _ = Nothing + +blockQuoteStyleIds :: [String] +blockQuoteStyleIds = ["Quote", "BlockQuote", "BlockQuotation"] + +blockQuoteStyleNames :: [String] +blockQuoteStyleNames = ["Quote", "Block Text"] + +getBlockQuote :: NameSpaces -> Element -> Maybe Bool +getBlockQuote ns element + | Just styleId <- findAttr (elemName ns "w" "styleId") element + , styleId `elem` blockQuoteStyleIds = Just True + | Just styleName <- findChild (elemName ns "w" "name") element >>= + findAttr (elemName ns "w" "val") + , styleName `elem` blockQuoteStyleNames = Just True +getBlockQuote _ _ = Nothing + +elemToParStyleData :: NameSpaces -> Element -> Maybe ParStyle -> ParStyleData +elemToParStyleData ns element parentStyle = + ParStyleData + { + headingLev = getHeaderLevel ns element + , isBlockQuote = getBlockQuote ns element + , psStyle = parentStyle + } + +elemToRunElem :: NameSpaces -> Element -> D RunElem +elemToRunElem ns element + | isElem ns "w" "t" element + || isElem ns "w" "delText" element + || isElem ns "m" "t" element = do + let str = strContent element + font <- asks envFont + case font of + Nothing -> return $ TextRun str + Just f -> return . TextRun $ + map (\x -> fromMaybe x . getUnicode f . lowerFromPrivate $ x) str + | isElem ns "w" "br" element = return LnBrk + | isElem ns "w" "tab" element = return Tab + | isElem ns "w" "sym" element = return (getSymChar ns element) + | otherwise = throwError WrongElem + where + lowerFromPrivate (ord -> c) + | c >= ord '\xF000' = chr $ c - ord '\xF000' + | otherwise = chr c + +-- The char attribute is a hex string +getSymChar :: NameSpaces -> Element -> RunElem +getSymChar ns element + | Just s <- lowerFromPrivate <$> getCodepoint + , Just font <- getFont = + let [(char, _)] = readLitChar ("\\x" ++ s) in + TextRun . maybe "" (:[]) $ getUnicode font char + where + getCodepoint = findAttr (elemName ns "w" "char") element + getFont = stringToFont =<< findAttr (elemName ns "w" "font") element + lowerFromPrivate ('F':xs) = '0':xs + lowerFromPrivate xs = xs +getSymChar _ _ = TextRun "" + +stringToFont :: String -> Maybe Font +stringToFont "Symbol" = Just Symbol +stringToFont _ = Nothing + +elemToRunElems :: NameSpaces -> Element -> D [RunElem] +elemToRunElems ns element + | isElem ns "w" "r" element + || isElem ns "m" "r" element = do + let qualName = elemName ns "w" + let font = do + fontElem <- findElement (qualName "rFonts") element + stringToFont =<< + (foldr (<|>) Nothing $ + map (flip findAttr fontElem . qualName) ["ascii", "hAnsi"]) + local (setFont font) (mapD (elemToRunElem ns) (elChildren element)) +elemToRunElems _ _ = throwError WrongElem + +setFont :: Maybe Font -> ReaderEnv -> ReaderEnv +setFont f s = s{envFont = f} diff --git a/src/Text/Pandoc/Readers/Docx/Reducible.hs b/src/Text/Pandoc/Readers/Docx/Reducible.hs new file mode 100644 index 000000000..8269ca88d --- /dev/null +++ b/src/Text/Pandoc/Readers/Docx/Reducible.hs @@ -0,0 +1,182 @@ +{-# LANGUAGE TypeSynonymInstances, FlexibleInstances, + PatternGuards #-} + +module Text.Pandoc.Readers.Docx.Reducible ( concatReduce + , (<+>) + ) + where + + +import Text.Pandoc.Builder +import Data.Monoid +import Data.List +import Data.Sequence (ViewR(..), ViewL(..), viewl, viewr) +import qualified Data.Sequence as Seq (null) + +data Modifier a = Modifier (a -> a) + | AttrModifier (Attr -> a -> a) Attr + | NullModifier + +class (Eq a) => Modifiable a where + modifier :: a -> Modifier a + innards :: a -> a + getL :: a -> (a, a) + getR :: a -> (a, a) + spaceOut :: a -> (a, a, a) + +spaceOutL :: (Monoid a, Modifiable a) => a -> (a, a) +spaceOutL ms = (l, stack fs (m' <> r)) + where (l, m, r) = spaceOut ms + (fs, m') = unstack m + +spaceOutR :: (Monoid a, Modifiable a) => a -> (a, a) +spaceOutR ms = (stack fs (l <> m'), r) + where (l, m, r) = spaceOut ms + (fs, m') = unstack m + +instance (Monoid a, Show a) => Show (Modifier a) where + show (Modifier f) = show $ f mempty + show (AttrModifier f attr) = show $ f attr mempty + show (NullModifier) = "NullModifier" + +instance (Monoid a, Eq a) => Eq (Modifier a) where + (Modifier f) == (Modifier g) = (f mempty == g mempty) + (AttrModifier f attr) == (AttrModifier g attr') = (f attr mempty == g attr' mempty) + (NullModifier) == (NullModifier) = True + _ == _ = False + +instance Modifiable Inlines where + modifier ils = case viewl (unMany ils) of + (x :< xs) | Seq.null xs -> case x of + (Emph _) -> Modifier emph + (Strong _) -> Modifier strong + (SmallCaps _) -> Modifier smallcaps + (Strikeout _) -> Modifier strikeout + (Superscript _) -> Modifier superscript + (Subscript _) -> Modifier subscript + (Span attr _) -> AttrModifier spanWith attr + _ -> NullModifier + _ -> NullModifier + + innards ils = case viewl (unMany ils) of + (x :< xs) | Seq.null xs -> case x of + (Emph lst) -> fromList lst + (Strong lst) -> fromList lst + (SmallCaps lst) -> fromList lst + (Strikeout lst) -> fromList lst + (Superscript lst) -> fromList lst + (Subscript lst) -> fromList lst + (Span _ lst) -> fromList lst + _ -> ils + _ -> ils + + getL ils = case viewl $ unMany ils of + (s :< sq) -> (singleton s, Many sq) + _ -> (mempty, ils) + + getR ils = case viewr $ unMany ils of + (sq :> s) -> (Many sq, singleton s) + _ -> (ils, mempty) + + spaceOut ils = + let (fs, ils') = unstack ils + contents = unMany ils' + left = case viewl contents of + (Space :< _) -> space + _ -> mempty + right = case viewr contents of + (_ :> Space) -> space + _ -> mempty in + (left, (stack fs $ trimInlines .Many $ contents), right) + +instance Modifiable Blocks where + modifier blks = case viewl (unMany blks) of + (x :< xs) | Seq.null xs -> case x of + (BlockQuote _) -> Modifier blockQuote + -- (Div attr _) -> AttrModifier divWith attr + _ -> NullModifier + _ -> NullModifier + + innards blks = case viewl (unMany blks) of + (x :< xs) | Seq.null xs -> case x of + (BlockQuote lst) -> fromList lst + -- (Div attr lst) -> fromList lst + _ -> blks + _ -> blks + + spaceOut blks = (mempty, blks, mempty) + + getL ils = case viewl $ unMany ils of + (s :< sq) -> (singleton s, Many sq) + _ -> (mempty, ils) + + getR ils = case viewr $ unMany ils of + (sq :> s) -> (Many sq, singleton s) + _ -> (ils, mempty) + + +unstack :: (Modifiable a) => a -> ([Modifier a], a) +unstack ms = case modifier ms of + NullModifier -> ([], ms) + _ -> (f : fs, ms') where + f = modifier ms + (fs, ms') = unstack $ innards ms + +stack :: (Monoid a, Modifiable a) => [Modifier a] -> a -> a +stack [] ms = ms +stack (NullModifier : fs) ms = stack fs ms +stack ((Modifier f) : fs) ms = + if isEmpty ms + then stack fs ms + else f $ stack fs ms +stack ((AttrModifier f attr) : fs) ms = f attr $ stack fs ms + +isEmpty :: (Monoid a, Eq a) => a -> Bool +isEmpty x = x == mempty + + +combine :: (Monoid a, Modifiable a, Eq a) => a -> a -> a +combine x y = + let (xs', x') = getR x + (y', ys') = getL y + in + xs' <> (combineSingleton x' y') <> ys' + +isAttrModifier :: Modifier a -> Bool +isAttrModifier (AttrModifier _ _) = True +isAttrModifier _ = False + +combineSingleton :: (Monoid a, Modifiable a, Eq a) => a -> a -> a +combineSingleton x y = + let (xfs, xs) = unstack x + (yfs, ys) = unstack y + shared = xfs `intersect` yfs + x_remaining = xfs \\ shared + y_remaining = yfs \\ shared + x_rem_attr = filter isAttrModifier x_remaining + y_rem_attr = filter isAttrModifier y_remaining + in + case null shared of + True | isEmpty xs && isEmpty ys -> + stack (x_rem_attr ++ y_rem_attr) mempty + | isEmpty xs -> + let (sp, y') = spaceOutL y in + (stack x_rem_attr mempty) <> sp <> y' + | isEmpty ys -> + let (x', sp) = spaceOutR x in + x' <> sp <> (stack y_rem_attr mempty) + | otherwise -> + let (x', xsp) = spaceOutR x + (ysp, y') = spaceOutL y + in + x' <> xsp <> ysp <> y' + False -> stack shared $ + combine + (stack x_remaining xs) + (stack y_remaining ys) + +(<+>) :: (Monoid a, Modifiable a, Eq a) => a -> a -> a +x <+> y = combine x y + +concatReduce :: (Monoid a, Modifiable a) => [a] -> a +concatReduce xs = foldl combine mempty xs diff --git a/src/Text/Pandoc/Readers/EPUB.hs b/src/Text/Pandoc/Readers/EPUB.hs new file mode 100644 index 000000000..b061d8683 --- /dev/null +++ b/src/Text/Pandoc/Readers/EPUB.hs @@ -0,0 +1,283 @@ +{-# LANGUAGE + ViewPatterns + , StandaloneDeriving + , TupleSections + , FlexibleContexts #-} + +module Text.Pandoc.Readers.EPUB + (readEPUB) + where + +import Text.XML.Light +import Text.Pandoc.Definition hiding (Attr) +import Text.Pandoc.Walk (walk, query) +import Text.Pandoc.Readers.HTML (readHtml) +import Text.Pandoc.Options ( ReaderOptions(..), readerTrace) +import Text.Pandoc.Shared (escapeURI, collapseFilePath, addMetaField) +import Text.Pandoc.MediaBag (MediaBag, insertMedia) +import Text.Pandoc.Compat.Except (MonadError, throwError, runExcept, Except) +import Text.Pandoc.MIME (MimeType) +import qualified Text.Pandoc.Builder as B +import Codec.Archive.Zip ( Archive (..), toArchive, fromEntry + , findEntryByPath, Entry) +import qualified Data.ByteString.Lazy as BL (ByteString) +import System.FilePath ( takeFileName, (</>), dropFileName, normalise + , dropFileName + , splitFileName ) +import qualified Text.Pandoc.UTF8 as UTF8 (toStringLazy) +import Control.Applicative ((<$>)) +import Control.Monad (guard, liftM, when) +import Data.Monoid (mempty, (<>)) +import Data.List (isPrefixOf, isInfixOf) +import Data.Maybe (mapMaybe, fromMaybe) +import qualified Data.Map as M (Map, lookup, fromList, elems) +import Control.DeepSeq.Generics (deepseq, NFData) + +import Debug.Trace (trace) + +type Items = M.Map String (FilePath, MimeType) + +readEPUB :: ReaderOptions -> BL.ByteString -> (Pandoc, MediaBag) +readEPUB opts bytes = runEPUB (archiveToEPUB opts $ toArchive bytes) + +runEPUB :: Except String a -> a +runEPUB = either error id . runExcept + +-- Note that internal reference are aggresively normalised so that all ids +-- are of the form "filename#id" +-- +archiveToEPUB :: (MonadError String m) => ReaderOptions -> Archive -> m (Pandoc, MediaBag) +archiveToEPUB os archive = do + -- root is path to folder with manifest file in + (root, content) <- getManifest archive + meta <- parseMeta content + (cover, items) <- parseManifest content + -- No need to collapse here as the image path is from the manifest file + let coverDoc = fromMaybe mempty (imageToPandoc <$> cover) + spine <- parseSpine items content + let escapedSpine = map (escapeURI . takeFileName . fst) spine + Pandoc _ bs <- + foldM' (\a b -> ((a <>) . walk (prependHash escapedSpine)) + `liftM` parseSpineElem root b) mempty spine + let ast = coverDoc <> (Pandoc meta bs) + let mediaBag = fetchImages (M.elems items) root archive ast + return $ (ast, mediaBag) + where + os' = os {readerParseRaw = True} + parseSpineElem :: MonadError String m => FilePath -> (FilePath, MimeType) -> m Pandoc + parseSpineElem (normalise -> r) (normalise -> path, mime) = do + when (readerTrace os) (traceM path) + doc <- mimeToReader mime r path + let docSpan = B.doc $ B.para $ B.spanWith (takeFileName path, [], []) mempty + return $ docSpan <> doc + mimeToReader :: MonadError String m => MimeType -> FilePath -> FilePath -> m Pandoc + mimeToReader "application/xhtml+xml" (normalise -> root) (normalise -> path) = do + fname <- findEntryByPathE (root </> path) archive + return $ fixInternalReferences path . + readHtml os' . + UTF8.toStringLazy $ + fromEntry fname + mimeToReader s _ path + | s `elem` imageMimes = return $ imageToPandoc path + | otherwise = return $ mempty + +-- paths should be absolute when this function is called +-- renameImages should do this +fetchImages :: [(FilePath, MimeType)] + -> FilePath -- ^ Root + -> Archive + -> Pandoc + -> MediaBag +fetchImages mimes root arc (query iq -> links) = + foldr (uncurry3 insertMedia) mempty + (mapMaybe getEntry links) + where + getEntry link = + let abslink = normalise (root </> link) in + (link , lookup link mimes, ) . fromEntry + <$> findEntryByPath abslink arc + +iq :: Inline -> [FilePath] +iq (Image _ (url, _)) = [url] +iq _ = [] + +-- Remove relative paths +renameImages :: FilePath -> Inline -> Inline +renameImages root (Image a (url, b)) = Image a (collapseFilePath (root </> url), b) +renameImages _ x = x + +imageToPandoc :: FilePath -> Pandoc +imageToPandoc s = B.doc . B.para $ B.image s "" mempty + +imageMimes :: [MimeType] +imageMimes = ["image/gif", "image/jpeg", "image/png"] + +type CoverImage = FilePath + +parseManifest :: (MonadError String m) => Element -> m (Maybe CoverImage, Items) +parseManifest content = do + manifest <- findElementE (dfName "manifest") content + let items = findChildren (dfName "item") manifest + r <- mapM parseItem items + let cover = findAttr (emptyName "href") =<< filterChild findCover manifest + return (cover, (M.fromList r)) + where + findCover e = maybe False (isInfixOf "cover-image") + (findAttr (emptyName "properties") e) + parseItem e = do + uid <- findAttrE (emptyName "id") e + href <- findAttrE (emptyName "href") e + mime <- findAttrE (emptyName "media-type") e + return (uid, (href, mime)) + +parseSpine :: MonadError String m => Items -> Element -> m [(FilePath, MimeType)] +parseSpine is e = do + spine <- findElementE (dfName "spine") e + let itemRefs = findChildren (dfName "itemref") spine + mapM (mkE "parseSpine" . (flip M.lookup is)) $ mapMaybe parseItemRef itemRefs + where + parseItemRef ref = do + let linear = maybe True (== "yes") (findAttr (emptyName "linear") ref) + guard linear + findAttr (emptyName "idref") ref + +parseMeta :: MonadError String m => Element -> m Meta +parseMeta content = do + meta <- findElementE (dfName "metadata") content + let dcspace (QName _ (Just "http://purl.org/dc/elements/1.1/") (Just "dc")) = True + dcspace _ = False + let dcs = filterChildrenName dcspace meta + let r = foldr parseMetaItem nullMeta dcs + return r + +-- http://www.idpf.org/epub/30/spec/epub30-publications.html#sec-metadata-elem +parseMetaItem :: Element -> Meta -> Meta +parseMetaItem e@(stripNamespace . elName -> field) meta = + addMetaField (renameMeta field) (B.str $ strContent e) meta + +renameMeta :: String -> String +renameMeta "creator" = "author" +renameMeta s = s + +getManifest :: MonadError String m => Archive -> m (String, Element) +getManifest archive = do + metaEntry <- findEntryByPathE ("META-INF" </> "container.xml") archive + docElem <- (parseXMLDocE . UTF8.toStringLazy . fromEntry) metaEntry + let namespaces = mapMaybe attrToNSPair (elAttribs docElem) + ns <- mkE "xmlns not in namespaces" (lookup "xmlns" namespaces) + as <- liftM ((map attrToPair) . elAttribs) + (findElementE (QName "rootfile" (Just ns) Nothing) docElem) + manifestFile <- mkE "Root not found" (lookup "full-path" as) + let rootdir = dropFileName manifestFile + --mime <- lookup "media-type" as + manifest <- findEntryByPathE manifestFile archive + liftM ((,) rootdir) (parseXMLDocE . UTF8.toStringLazy . fromEntry $ manifest) + +-- Fixup + +fixInternalReferences :: FilePath -> Pandoc -> Pandoc +fixInternalReferences pathToFile = + (walk $ renameImages root) + . (walk normalisePath) + . (walk $ fixBlockIRs filename) + . (walk $ fixInlineIRs filename) + where + (root, escapeURI -> filename) = splitFileName pathToFile + +fixInlineIRs :: String -> Inline -> Inline +fixInlineIRs s (Span as v) = + Span (fixAttrs s as) v +fixInlineIRs s (Code as code) = + Code (fixAttrs s as) code +fixInlineIRs s (Link t ('#':url, tit)) = + Link t (addHash s url, tit) +fixInlineIRs _ v = v + +normalisePath :: Inline -> Inline +normalisePath (Link t (url, tit)) = + let (path, uid) = span (/= '#') url in + Link t (takeFileName path ++ uid, tit) +normalisePath s = s + +prependHash :: [String] -> Inline -> Inline +prependHash ps l@(Link is (url, tit)) + | or [s `isPrefixOf` url | s <- ps] = + Link is ('#':url, tit) + | otherwise = l +prependHash _ i = i + +fixBlockIRs :: String -> Block -> Block +fixBlockIRs s (Div as b) = + Div (fixAttrs s as) b +fixBlockIRs s (Header i as b) = + Header i (fixAttrs s as) b +fixBlockIRs s (CodeBlock as code) = + CodeBlock (fixAttrs s as) code +fixBlockIRs _ b = b + +fixAttrs :: FilePath -> B.Attr -> B.Attr +fixAttrs s (ident, cs, kvs) = (addHash s ident, filter (not . null) cs, removeEPUBAttrs kvs) + +addHash :: String -> String -> String +addHash _ "" = "" +addHash s ident = s ++ "#" ++ ident + +removeEPUBAttrs :: [(String, String)] -> [(String, String)] +removeEPUBAttrs kvs = filter (not . isEPUBAttr) kvs + +isEPUBAttr :: (String, String) -> Bool +isEPUBAttr (k, _) = "epub:" `isPrefixOf` k + +-- Library + +-- Strict version of foldM +foldM' :: (Monad m, NFData a) => (a -> b -> m a) -> a -> [b] -> m a +foldM' _ z [] = return z +foldM' f z (x:xs) = do + z' <- f z x + z' `deepseq` foldM' f z' xs + +uncurry3 :: (a -> b -> c -> d) -> (a, b, c) -> d +uncurry3 f (a, b, c) = f a b c + +traceM :: Monad m => String -> m () +traceM = flip trace (return ()) + +-- Utility + +stripNamespace :: QName -> String +stripNamespace (QName v _ _) = v + +attrToNSPair :: Attr -> Maybe (String, String) +attrToNSPair (Attr (QName "xmlns" _ _) val) = Just ("xmlns", val) +attrToNSPair _ = Nothing + +attrToPair :: Attr -> (String, String) +attrToPair (Attr (QName name _ _) val) = (name, val) + +defaultNameSpace :: Maybe String +defaultNameSpace = Just "http://www.idpf.org/2007/opf" + +dfName :: String -> QName +dfName s = QName s defaultNameSpace Nothing + +emptyName :: String -> QName +emptyName s = QName s Nothing Nothing + +-- Convert Maybe interface to Either + +findAttrE :: MonadError String m => QName -> Element -> m String +findAttrE q e = mkE "findAttr" $ findAttr q e + +findEntryByPathE :: MonadError String m => FilePath -> Archive -> m Entry +findEntryByPathE (normalise -> path) a = + mkE ("No entry on path: " ++ path) $ findEntryByPath path a + +parseXMLDocE :: MonadError String m => String -> m Element +parseXMLDocE doc = mkE "Unable to parse XML doc" $ parseXMLDoc doc + +findElementE :: MonadError String m => QName -> Element -> m Element +findElementE e x = mkE ("Unable to find element: " ++ show e) $ findElement e x + +mkE :: MonadError String m => String -> Maybe a -> m a +mkE s = maybe (throwError s) return diff --git a/src/Text/Pandoc/Readers/HTML.hs b/src/Text/Pandoc/Readers/HTML.hs index d1e4d0024..2a23f2a62 100644 --- a/src/Text/Pandoc/Readers/HTML.hs +++ b/src/Text/Pandoc/Readers/HTML.hs @@ -1,5 +1,6 @@ +{-# LANGUAGE FlexibleContexts, FlexibleInstances, MultiParamTypeClasses #-} {- -Copyright (C) 2006-2010 John MacFarlane <jgm@berkeley.edu> +Copyright (C) 2006-2014 John MacFarlane <jgm@berkeley.edu> This program is free software; you can redistribute it and/or modify it under the terms of the GNU General Public License as published by @@ -18,7 +19,7 @@ Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA {- | Module : Text.Pandoc.Readers.HTML - Copyright : Copyright (C) 2006-2010 John MacFarlane + Copyright : Copyright (C) 2006-2014 John MacFarlane License : GNU GPL, version 2 or above Maintainer : John MacFarlane <jgm@berkeley.edu> @@ -40,58 +41,102 @@ import Text.HTML.TagSoup import Text.HTML.TagSoup.Match import Text.Pandoc.Definition import qualified Text.Pandoc.Builder as B -import Text.Pandoc.Shared -import Text.Pandoc.Options -import Text.Pandoc.Parsing -import Data.Maybe ( fromMaybe, isJust ) -import Data.List ( intercalate ) +import Text.Pandoc.Builder (Blocks, Inlines, trimInlines, HasMeta(..)) +import Text.Pandoc.Shared ( extractSpaces, renderTags' + , escapeURI, safeRead ) +import Text.Pandoc.Options (ReaderOptions(readerParseRaw, readerTrace) + , Extension (Ext_epub_html_exts, + Ext_native_divs, Ext_native_spans)) +import Text.Pandoc.Parsing hiding ((<|>)) +import Text.Pandoc.Walk +import Data.Maybe ( fromMaybe, isJust) +import Data.List ( intercalate, isInfixOf ) import Data.Char ( isDigit ) -import Control.Monad ( liftM, guard, when, mzero ) -import Control.Applicative ( (<$>), (<$), (<*) ) +import Control.Monad ( liftM, guard, when, mzero, void, unless ) +import Control.Arrow ((***)) +import Control.Applicative ( (<$>), (<$), (<*), (*>), (<|>)) +import Data.Monoid (mconcat, Monoid, mempty, (<>), First (..)) +import Text.Printf (printf) +import Debug.Trace (trace) +import Text.TeXMath (readMathML, writeTeX) +import Data.Default (Default (..), def) +import Control.Monad.Reader (Reader,ask, asks, local, runReader) -isSpace :: Char -> Bool -isSpace ' ' = True -isSpace '\t' = True -isSpace '\n' = True -isSpace _ = False -- | Convert HTML-formatted string to 'Pandoc' document. readHtml :: ReaderOptions -- ^ Reader options -> String -- ^ String to parse (assumes @'\n'@ line endings) -> Pandoc readHtml opts inp = - case runParser parseDoc def{ stateOptions = opts } "source" tags of + case flip runReader def $ runParserT parseDoc (HTMLState def{ stateOptions = opts } []) "source" tags of Left err' -> error $ "\nError at " ++ show err' Right result -> result - where tags = canonicalizeTags $ + where tags = stripPrefixes . canonicalizeTags $ parseTagsOptions parseOptions{ optTagPosition = True } inp parseDoc = do - blocks <- (fixPlains False . concat) <$> manyTill block eof - meta <- stateMeta <$> getState - return $ Pandoc meta blocks + blocks <- (fixPlains False) . mconcat <$> manyTill block eof + meta <- stateMeta . parserState <$> getState + bs' <- replaceNotes (B.toList blocks) + return $ Pandoc meta bs' + +replaceNotes :: [Block] -> TagParser [Block] +replaceNotes = walkM replaceNotes' + +replaceNotes' :: Inline -> TagParser Inline +replaceNotes' (RawInline (Format "noteref") ref) = maybe (Str "") (Note . B.toList) . lookup ref <$> getNotes + where + getNotes = noteTable <$> getState +replaceNotes' x = return x + +data HTMLState = + HTMLState + { parserState :: ParserState, + noteTable :: [(String, Blocks)] + } -type TagParser = Parser [Tag String] ParserState +data HTMLLocal = HTMLLocal { quoteContext :: QuoteContext + , inChapter :: Bool -- ^ Set if in chapter section + , inPlain :: Bool -- ^ Set if in pPlain + } -pBody :: TagParser [Block] +setInChapter :: HTMLParser s a -> HTMLParser s a +setInChapter = local (\s -> s {inChapter = True}) + +setInPlain :: HTMLParser s a -> HTMLParser s a +setInPlain = local (\s -> s {inPlain = True}) + +type HTMLParser s = ParserT s HTMLState (Reader HTMLLocal) + +type TagParser = HTMLParser [Tag String] + +pBody :: TagParser Blocks pBody = pInTags "body" block -pHead :: TagParser [Block] -pHead = pInTags "head" $ pTitle <|> pMetaTag <|> ([] <$ pAnyTag) - where pTitle = pInTags "title" inline >>= setTitle . normalizeSpaces - setTitle t = [] <$ (updateState $ B.setMeta "title" (B.fromList t)) +pHead :: TagParser Blocks +pHead = pInTags "head" $ pTitle <|> pMetaTag <|> (mempty <$ pAnyTag) + where pTitle = pInTags "title" inline >>= setTitle . trimInlines + setTitle t = mempty <$ (updateState $ B.setMeta "title" t) pMetaTag = do mt <- pSatisfy (~== TagOpen "meta" []) let name = fromAttrib "name" mt if null name - then return [] + then return mempty else do let content = fromAttrib "content" mt updateState $ B.setMeta name (B.text content) - return [] + return mempty -block :: TagParser [Block] -block = choice - [ pPara +block :: TagParser Blocks +block = do + tr <- getOption readerTrace + pos <- getPosition + res <- choice + [ eSection + , eSwitch B.para block + , mempty <$ eFootnote + , mempty <$ eTOC + , mempty <$ eTitlePage + , pPara , pHeader , pBlockQuote , pCodeBlock @@ -100,15 +145,76 @@ block = choice , pTable , pHead , pBody - , pPlain , pDiv + , pPlain , pRawHtmlBlock ] + when tr $ trace (printf "line %d: %s" (sourceLine pos) + (take 60 $ show $ B.toList res)) (return ()) + return res + +namespaces :: [(String, TagParser Inlines)] +namespaces = [(mathMLNamespace, pMath True)] + +mathMLNamespace :: String +mathMLNamespace = "http://www.w3.org/1998/Math/MathML" + +eSwitch :: Monoid a => (Inlines -> a) -> TagParser a -> TagParser a +eSwitch constructor parser = try $ do + guardEnabled Ext_epub_html_exts + pSatisfy (~== TagOpen "switch" []) + cases <- getFirst . mconcat <$> + manyTill (First <$> (eCase <* skipMany pBlank) ) + (lookAhead $ try $ pSatisfy (~== TagOpen "default" [])) + skipMany pBlank + fallback <- pInTags "default" (skipMany pBlank *> parser <* skipMany pBlank) + skipMany pBlank + pSatisfy (~== TagClose "switch") + return $ maybe fallback constructor cases -pList :: TagParser [Block] +eCase :: TagParser (Maybe Inlines) +eCase = do + skipMany pBlank + TagOpen _ attr <- lookAhead $ pSatisfy $ (~== TagOpen "case" []) + case (flip lookup namespaces) =<< lookup "required-namespace" attr of + Just p -> Just <$> (pInTags "case" (skipMany pBlank *> p <* skipMany pBlank)) + Nothing -> Nothing <$ manyTill pAnyTag (pSatisfy (~== TagClose "case")) + +eFootnote :: TagParser () +eFootnote = try $ do + let notes = ["footnote", "rearnote"] + guardEnabled Ext_epub_html_exts + (TagOpen tag attr) <- lookAhead $ pAnyTag + guard (maybe False (flip elem notes) (lookup "type" attr)) + let ident = fromMaybe "" (lookup "id" attr) + content <- pInTags tag block + addNote ident content + +addNote :: String -> Blocks -> TagParser () +addNote uid cont = updateState (\s -> s {noteTable = (uid, cont) : (noteTable s)}) + +eNoteref :: TagParser Inlines +eNoteref = try $ do + guardEnabled Ext_epub_html_exts + TagOpen tag attr <- lookAhead $ pAnyTag + guard (maybe False (== "noteref") (lookup "type" attr)) + let ident = maybe "" (dropWhile (== '#')) (lookup "href" attr) + guard (not (null ident)) + pInTags tag block + return $ B.rawInline "noteref" ident + +-- Strip TOC if there is one, better to generate again +eTOC :: TagParser () +eTOC = try $ do + guardEnabled Ext_epub_html_exts + (TagOpen tag attr) <- lookAhead $ pAnyTag + guard (maybe False (== "toc") (lookup "type" attr)) + void (pInTags tag block) + +pList :: TagParser Blocks pList = pBulletList <|> pOrderedList <|> pDefinitionList -pBulletList :: TagParser [Block] +pBulletList :: TagParser Blocks pBulletList = try $ do pSatisfy (~== TagOpen "ul" []) let nonItem = pSatisfy (\t -> @@ -117,10 +223,16 @@ pBulletList = try $ do -- note: if they have an <ol> or <ul> not in scope of a <li>, -- treat it as a list item, though it's not valid xhtml... skipMany nonItem - items <- manyTill (pInTags "li" block >>~ skipMany nonItem) (pCloses "ul") - return [BulletList $ map (fixPlains True) items] + items <- manyTill (pListItem nonItem) (pCloses "ul") + return $ B.bulletList $ map (fixPlains True) items -pOrderedList :: TagParser [Block] +pListItem :: TagParser a -> TagParser Blocks +pListItem nonItem = do + TagOpen _ attr <- lookAhead $ pSatisfy (~== TagOpen "li" []) + let liDiv = maybe mempty (\x -> B.divWith (x, [], []) mempty) (lookup "id" attr) + (liDiv <>) <$> pInTags "li" block <* skipMany nonItem + +pOrderedList :: TagParser Blocks pOrderedList = try $ do TagOpen _ attribs <- pSatisfy (~== TagOpen "ol" []) let (start, style) = (sta', sty') @@ -145,28 +257,28 @@ pOrderedList = try $ do -- note: if they have an <ol> or <ul> not in scope of a <li>, -- treat it as a list item, though it's not valid xhtml... skipMany nonItem - items <- manyTill (pInTags "li" block >>~ skipMany nonItem) (pCloses "ol") - return [OrderedList (start, style, DefaultDelim) $ map (fixPlains True) items] + items <- manyTill (pListItem nonItem) (pCloses "ol") + return $ B.orderedListWith (start, style, DefaultDelim) $ map (fixPlains True) items -pDefinitionList :: TagParser [Block] +pDefinitionList :: TagParser Blocks pDefinitionList = try $ do pSatisfy (~== TagOpen "dl" []) items <- manyTill pDefListItem (pCloses "dl") - return [DefinitionList items] + return $ B.definitionList items -pDefListItem :: TagParser ([Inline],[[Block]]) +pDefListItem :: TagParser (Inlines, [Blocks]) pDefListItem = try $ do let nonItem = pSatisfy (\t -> not (t ~== TagOpen "dt" []) && not (t ~== TagOpen "dd" []) && not (t ~== TagClose "dl")) terms <- many1 (try $ skipMany nonItem >> pInTags "dt" inline) defs <- many1 (try $ skipMany nonItem >> pInTags "dd" block) skipMany nonItem - let term = intercalate [LineBreak] terms + let term = foldl1 (\x y -> x <> B.linebreak <> y) terms return (term, map (fixPlains True) defs) -fixPlains :: Bool -> [Block] -> [Block] -fixPlains inList bs = if any isParaish bs - then map plainToPara bs +fixPlains :: Bool -> Blocks -> Blocks +fixPlains inList bs = if any isParaish bs' + then B.fromList $ map plainToPara bs' else bs where isParaish (Para _) = True isParaish (CodeBlock _ _) = True @@ -178,29 +290,30 @@ fixPlains inList bs = if any isParaish bs isParaish _ = False plainToPara (Plain xs) = Para xs plainToPara x = x + bs' = B.toList bs pRawTag :: TagParser String pRawTag = do tag <- pAnyTag - let ignorable x = x `elem` ["html","head","body"] + let ignorable x = x `elem` ["html","head","body","!DOCTYPE","?xml"] if tagOpen ignorable (const True) tag || tagClose ignorable tag then return [] else return $ renderTags' [tag] -pDiv :: TagParser [Block] +pDiv :: TagParser Blocks pDiv = try $ do - getOption readerParseRaw >>= guard + guardEnabled Ext_native_divs TagOpen _ attr <- lookAhead $ pSatisfy $ tagOpen (=="div") (const True) contents <- pInTags "div" block - return [Div (mkAttr attr) contents] + return $ B.divWith (mkAttr attr) contents -pRawHtmlBlock :: TagParser [Block] +pRawHtmlBlock :: TagParser Blocks pRawHtmlBlock = do raw <- pHtmlBlock "script" <|> pHtmlBlock "style" <|> pRawTag parseRaw <- getOption readerParseRaw if parseRaw && not (null raw) - then return [RawBlock (Format "html") raw] - else return [] + then return $ B.rawBlock "html" raw + else return mempty pHtmlBlock :: String -> TagParser String pHtmlBlock t = try $ do @@ -208,32 +321,57 @@ pHtmlBlock t = try $ do contents <- manyTill pAnyTag (pSatisfy (~== TagClose t)) return $ renderTags' $ [open] ++ contents ++ [TagClose t] -pHeader :: TagParser [Block] +-- Sets chapter context +eSection :: TagParser Blocks +eSection = try $ do + let matchChapter as = maybe False (isInfixOf "chapter") (lookup "type" as) + let sectTag = tagOpen (`elem` sectioningContent) matchChapter + TagOpen tag _ <- lookAhead $ pSatisfy sectTag + setInChapter (pInTags tag block) + +headerLevel :: String -> TagParser Int +headerLevel tagtype = do + let level = read (drop 1 tagtype) + (try $ do + guardEnabled Ext_epub_html_exts + asks inChapter >>= guard + return (level - 1)) + <|> + return level + +eTitlePage :: TagParser () +eTitlePage = try $ do + let isTitlePage as = maybe False (isInfixOf "titlepage") (lookup "type" as) + let groupTag = tagOpen (\x -> x `elem` groupingContent || x == "section") + isTitlePage + TagOpen tag _ <- lookAhead $ pSatisfy groupTag + () <$ pInTags tag block + +pHeader :: TagParser Blocks pHeader = try $ do TagOpen tagtype attr <- pSatisfy $ tagOpen (`elem` ["h1","h2","h3","h4","h5","h6"]) (const True) let bodyTitle = TagOpen tagtype attr ~== TagOpen "h1" [("class","title")] - let level = read (drop 1 tagtype) - contents <- liftM concat $ manyTill inline (pCloses tagtype <|> eof) + level <- headerLevel tagtype + contents <- trimInlines . mconcat <$> manyTill inline (pCloses tagtype <|> eof) let ident = fromMaybe "" $ lookup "id" attr let classes = maybe [] words $ lookup "class" attr let keyvals = [(k,v) | (k,v) <- attr, k /= "class", k /= "id"] return $ if bodyTitle - then [] -- skip a representation of the title in the body - else [Header level (ident, classes, keyvals) $ - normalizeSpaces contents] + then mempty -- skip a representation of the title in the body + else B.headerWith (ident, classes, keyvals) level contents -pHrule :: TagParser [Block] +pHrule :: TagParser Blocks pHrule = do pSelfClosing (=="hr") (const True) - return [HorizontalRule] + return B.horizontalRule -pTable :: TagParser [Block] +pTable :: TagParser Blocks pTable = try $ do TagOpen _ _ <- pSatisfy (~== TagOpen "table" []) skipMany pBlank - caption <- option [] $ pInTags "caption" inline >>~ skipMany pBlank + caption <- option mempty $ pInTags "caption" inline <* skipMany pBlank -- TODO actually read these and take width information from them widths' <- pColgroup <|> many pCol head' <- option [] $ pOptInTag "thead" $ pInTags "tr" (pCell "th") @@ -242,26 +380,25 @@ pTable = try $ do $ many1 $ try $ skipMany pBlank >> pInTags "tr" (pCell "td") skipMany pBlank TagClose _ <- pSatisfy (~== TagClose "table") - let isSinglePlain [] = True - isSinglePlain [Plain _] = True - isSinglePlain _ = False + let isSinglePlain x = case B.toList x of + [Plain _] -> True + _ -> False let isSimple = all isSinglePlain $ concat (head':rows) - let cols = length $ if null head' - then head rows - else head' + let cols = length $ if null head' then head rows else head' -- fail if there are colspans or rowspans guard $ all (\r -> length r == cols) rows - let aligns = replicate cols AlignLeft + let aligns = replicate cols AlignDefault let widths = if null widths' then if isSimple then replicate cols 0 else replicate cols (1.0 / fromIntegral cols) else widths' - return [Table caption aligns widths head' rows] + return $ B.table caption (zip aligns widths) head' rows pCol :: TagParser Double pCol = try $ do TagOpen _ attribs <- pSatisfy (~== TagOpen "col" []) + skipMany pBlank optional $ pSatisfy (~== TagClose "col") skipMany pBlank return $ case lookup "width" attribs of @@ -275,35 +412,35 @@ pColgroup = try $ do skipMany pBlank manyTill pCol (pCloses "colgroup" <|> eof) <* skipMany pBlank -pCell :: String -> TagParser [TableCell] +pCell :: String -> TagParser [Blocks] pCell celltype = try $ do skipMany pBlank res <- pInTags celltype block skipMany pBlank return [res] -pBlockQuote :: TagParser [Block] +pBlockQuote :: TagParser Blocks pBlockQuote = do contents <- pInTags "blockquote" block - return [BlockQuote $ fixPlains False contents] + return $ B.blockQuote $ fixPlains False contents -pPlain :: TagParser [Block] +pPlain :: TagParser Blocks pPlain = do - contents <- liftM (normalizeSpaces . concat) $ many1 inline - if null contents - then return [] - else return [Plain contents] + contents <- setInPlain $ trimInlines . mconcat <$> many1 inline + if B.isNull contents + then return mempty + else return $ B.plain contents -pPara :: TagParser [Block] +pPara :: TagParser Blocks pPara = do - contents <- pInTags "p" inline - return [Para $ normalizeSpaces contents] + contents <- trimInlines <$> pInTags "p" inline + return $ B.para contents -pCodeBlock :: TagParser [Block] +pCodeBlock :: TagParser Blocks pCodeBlock = try $ do TagOpen _ attr <- pSatisfy (~== TagOpen "pre" []) contents <- manyTill pAnyTag (pCloses "pre" <|> eof) - let rawText = concatMap fromTagText $ filter isTagText contents + let rawText = concatMap tagToString contents -- drop leading newline if any let result' = case rawText of '\n':xs -> xs @@ -312,11 +449,18 @@ pCodeBlock = try $ do let result = case reverse result' of '\n':_ -> init result' _ -> result' - return [CodeBlock (mkAttr attr) result] + return $ B.codeBlockWith (mkAttr attr) result -inline :: TagParser [Inline] +tagToString :: Tag String -> String +tagToString (TagText s) = s +tagToString (TagOpen "br" _) = "\n" +tagToString _ = "" + +inline :: TagParser Inlines inline = choice - [ pTagText + [ eNoteref + , eSwitch id inline + , pTagText , pQ , pEmph , pStrong @@ -328,6 +472,7 @@ inline = choice , pImage , pCode , pSpan + , pMath False , pRawHtmlInline ] @@ -354,91 +499,130 @@ pSelfClosing f g = do optional $ pSatisfy (tagClose f) return open -pQ :: TagParser [Inline] +pQ :: TagParser Inlines pQ = do - quoteContext <- stateQuoteContext `fmap` getState - let quoteType = case quoteContext of + context <- asks quoteContext + let quoteType = case context of InDoubleQuote -> SingleQuote _ -> DoubleQuote let innerQuoteContext = if quoteType == SingleQuote then InSingleQuote else InDoubleQuote - withQuoteContext innerQuoteContext $ pInlinesInTags "q" (Quoted quoteType) + let constructor = case quoteType of + SingleQuote -> B.singleQuoted + DoubleQuote -> B.doubleQuoted + withQuoteContext innerQuoteContext $ + pInlinesInTags "q" constructor -pEmph :: TagParser [Inline] -pEmph = pInlinesInTags "em" Emph <|> pInlinesInTags "i" Emph +pEmph :: TagParser Inlines +pEmph = pInlinesInTags "em" B.emph <|> pInlinesInTags "i" B.emph -pStrong :: TagParser [Inline] -pStrong = pInlinesInTags "strong" Strong <|> pInlinesInTags "b" Strong +pStrong :: TagParser Inlines +pStrong = pInlinesInTags "strong" B.strong <|> pInlinesInTags "b" B.strong -pSuperscript :: TagParser [Inline] -pSuperscript = pInlinesInTags "sup" Superscript +pSuperscript :: TagParser Inlines +pSuperscript = pInlinesInTags "sup" B.superscript -pSubscript :: TagParser [Inline] -pSubscript = pInlinesInTags "sub" Subscript +pSubscript :: TagParser Inlines +pSubscript = pInlinesInTags "sub" B.subscript -pStrikeout :: TagParser [Inline] +pStrikeout :: TagParser Inlines pStrikeout = do - pInlinesInTags "s" Strikeout <|> - pInlinesInTags "strike" Strikeout <|> - pInlinesInTags "del" Strikeout <|> + pInlinesInTags "s" B.strikeout <|> + pInlinesInTags "strike" B.strikeout <|> + pInlinesInTags "del" B.strikeout <|> try (do pSatisfy (~== TagOpen "span" [("class","strikeout")]) - contents <- liftM concat $ manyTill inline (pCloses "span") - return [Strikeout contents]) + contents <- mconcat <$> manyTill inline (pCloses "span") + return $ B.strikeout contents) -pLineBreak :: TagParser [Inline] +pLineBreak :: TagParser Inlines pLineBreak = do pSelfClosing (=="br") (const True) - return [LineBreak] + return B.linebreak + +pLink :: TagParser Inlines +pLink = pRelLink <|> pAnchor -pLink :: TagParser [Inline] -pLink = try $ do +pAnchor :: TagParser Inlines +pAnchor = try $ do + tag <- pSatisfy (tagOpenLit "a" (isJust . lookup "id")) + return $ B.spanWith (fromAttrib "id" tag , [], []) mempty + +pRelLink :: TagParser Inlines +pRelLink = try $ do tag <- pSatisfy (tagOpenLit "a" (isJust . lookup "href")) let url = fromAttrib "href" tag let title = fromAttrib "title" tag - lab <- liftM concat $ manyTill inline (pCloses "a") - return [Link (normalizeSpaces lab) (escapeURI url, title)] - -pImage :: TagParser [Inline] + let uid = fromAttrib "id" tag + let spanC = case uid of + [] -> id + s -> B.spanWith (s, [], []) + lab <- trimInlines . mconcat <$> manyTill inline (pCloses "a") + return $ spanC $ B.link (escapeURI url) title lab + +pImage :: TagParser Inlines pImage = do tag <- pSelfClosing (=="img") (isJust . lookup "src") let url = fromAttrib "src" tag let title = fromAttrib "title" tag let alt = fromAttrib "alt" tag - return [Image (B.toList $ B.text alt) (escapeURI url, title)] + return $ B.image (escapeURI url) title (B.text alt) -pCode :: TagParser [Inline] +pCode :: TagParser Inlines pCode = try $ do (TagOpen open attr) <- pSatisfy $ tagOpen (`elem` ["code","tt"]) (const True) result <- manyTill pAnyTag (pCloses open) - return [Code (mkAttr attr) $ intercalate " " $ lines $ innerText result] + return $ B.codeWith (mkAttr attr) $ intercalate " " $ lines $ innerText result -pSpan :: TagParser [Inline] +pSpan :: TagParser Inlines pSpan = try $ do - getOption readerParseRaw >>= guard + guardEnabled Ext_native_spans TagOpen _ attr <- lookAhead $ pSatisfy $ tagOpen (=="span") (const True) contents <- pInTags "span" inline - return [Span (mkAttr attr) contents] - -pRawHtmlInline :: TagParser [Inline] + let attr' = mkAttr attr + return $ case attr' of + ("",[],[("style",s)]) + | filter (`notElem` " \t;") s == "font-variant:small-caps" -> + B.smallcaps contents + _ -> B.spanWith (mkAttr attr) contents + +pRawHtmlInline :: TagParser Inlines pRawHtmlInline = do - result <- pSatisfy (tagComment (const True)) <|> pSatisfy isInlineTag + inplain <- asks inPlain + result <- pSatisfy (tagComment (const True)) + <|> if inplain + then pSatisfy (not . isBlockTag) + else pSatisfy isInlineTag parseRaw <- getOption readerParseRaw if parseRaw - then return [RawInline (Format "html") $ renderTags' [result]] - else return [] - -pInlinesInTags :: String -> ([Inline] -> Inline) - -> TagParser [Inline] -pInlinesInTags tagtype f = do - contents <- pInTags tagtype inline - return [f $ normalizeSpaces contents] - -pInTags :: String -> TagParser [a] - -> TagParser [a] + then return $ B.rawInline "html" $ renderTags' [result] + else return mempty + +mathMLToTeXMath :: String -> Either String String +mathMLToTeXMath s = writeTeX <$> readMathML s + +pMath :: Bool -> TagParser Inlines +pMath inCase = try $ do + open@(TagOpen _ attr) <- pSatisfy $ tagOpen (=="math") (const True) + unless (inCase) (guard (maybe False (== mathMLNamespace) (lookup "xmlns" attr))) + contents <- manyTill pAnyTag (pSatisfy (~== TagClose "math")) + let math = mathMLToTeXMath $ + (renderTags $ [open] ++ contents ++ [TagClose "math"]) + let constructor = + maybe B.math (\x -> if (x == "inline") then B.math else B.displayMath) + (lookup "display" attr) + return $ either (const mempty) + (\x -> if null x then mempty else constructor x) math + +pInlinesInTags :: String -> (Inlines -> Inlines) + -> TagParser Inlines +pInlinesInTags tagtype f = extractSpaces f <$> pInTags tagtype inline + +pInTags :: (Monoid a) => String -> TagParser a + -> TagParser a pInTags tagtype parser = try $ do pSatisfy (~== TagOpen tagtype []) - liftM concat $ manyTill parser (pCloses tagtype <|> eof) + mconcat <$> manyTill parser (pCloses tagtype <|> eof) pOptInTag :: String -> TagParser a -> TagParser a @@ -454,43 +638,47 @@ pCloses :: String -> TagParser () pCloses tagtype = try $ do t <- lookAhead $ pSatisfy $ \tag -> isTagClose tag || isTagOpen tag case t of - (TagClose t') | t' == tagtype -> pAnyTag >> return () + (TagClose t') | t' == tagtype -> pAnyTag >> return () (TagOpen t' _) | t' `closes` tagtype -> return () (TagClose "ul") | tagtype == "li" -> return () (TagClose "ol") | tagtype == "li" -> return () (TagClose "dl") | tagtype == "li" -> return () + (TagClose "table") | tagtype == "td" -> return () + (TagClose "table") | tagtype == "tr" -> return () _ -> mzero -pTagText :: TagParser [Inline] +pTagText :: TagParser Inlines pTagText = try $ do (TagText str) <- pSatisfy isTagText st <- getState - case runParser (many pTagContents) st "text" str of + qu <- ask + case flip runReader qu $ runParserT (many pTagContents) st "text" str of Left _ -> fail $ "Could not parse `" ++ str ++ "'" - Right result -> return result + Right result -> return $ mconcat result pBlank :: TagParser () pBlank = try $ do (TagText str) <- pSatisfy isTagText guard $ all isSpace str -pTagContents :: Parser [Char] ParserState Inline +type InlinesParser = HTMLParser String + +pTagContents :: InlinesParser Inlines pTagContents = - Math DisplayMath `fmap` mathDisplay - <|> Math InlineMath `fmap` mathInline + B.displayMath <$> mathDisplay + <|> B.math <$> mathInline <|> pStr <|> pSpace <|> smartPunctuation pTagContents <|> pSymbol <|> pBad -pStr :: Parser [Char] ParserState Inline +pStr :: InlinesParser Inlines pStr = do result <- many1 $ satisfy $ \c -> not (isSpace c) && not (isSpecial c) && not (isBad c) - pos <- getPosition - updateState $ \s -> s{ stateLastStrPos = Just pos } - return $ Str result + updateLastStrPos + return $ B.str result isSpecial :: Char -> Bool isSpecial '"' = True @@ -504,13 +692,13 @@ isSpecial '\8220' = True isSpecial '\8221' = True isSpecial _ = False -pSymbol :: Parser [Char] ParserState Inline -pSymbol = satisfy isSpecial >>= return . Str . (:[]) +pSymbol :: InlinesParser Inlines +pSymbol = satisfy isSpecial >>= return . B.str . (:[]) isBad :: Char -> Bool isBad c = c >= '\128' && c <= '\159' -- not allowed in HTML -pBad :: Parser [Char] ParserState Inline +pBad :: InlinesParser Inlines pBad = do c <- satisfy isBad let c' = case c of @@ -542,18 +730,20 @@ pBad = do '\158' -> '\382' '\159' -> '\376' _ -> '?' - return $ Str [c'] + return $ B.str [c'] -pSpace :: Parser [Char] ParserState Inline -pSpace = many1 (satisfy isSpace) >> return Space +pSpace :: InlinesParser Inlines +pSpace = many1 (satisfy isSpace) >> return B.space -- -- Constants -- eitherBlockOrInline :: [String] -eitherBlockOrInline = ["applet", "button", "del", "iframe", "ins", - "map", "area", "object"] +eitherBlockOrInline = ["audio", "applet", "button", "iframe", "embed", + "del", "ins", + "progress", "map", "area", "noscript", "script", + "object", "svg", "video", "source"] {- inlineHtmlTags :: [[Char]] @@ -565,15 +755,17 @@ inlineHtmlTags = ["a", "abbr", "acronym", "b", "basefont", "bdo", "big", -} blockHtmlTags :: [String] -blockHtmlTags = ["address", "article", "aside", "blockquote", "body", "button", "canvas", +blockHtmlTags = ["?xml", "!DOCTYPE", "address", "article", "aside", + "blockquote", "body", "button", "canvas", "caption", "center", "col", "colgroup", "dd", "dir", "div", - "dl", "dt", "embed", "fieldset", "figcaption", "figure", "footer", - "form", "h1", "h2", "h3", "h4", - "h5", "h6", "head", "header", "hgroup", "hr", "html", "isindex", "map", "menu", - "noframes", "noscript", "object", "ol", "output", "p", "pre", "progress", - "section", "table", "tbody", "textarea", "thead", "tfoot", "ul", "dd", + "dl", "dt", "fieldset", "figcaption", "figure", + "footer", "form", "h1", "h2", "h3", "h4", + "h5", "h6", "head", "header", "hgroup", "hr", "html", + "isindex", "menu", "noframes", "ol", "output", "p", "pre", + "section", "table", "tbody", "textarea", + "thead", "tfoot", "ul", "dd", "dt", "frameset", "li", "tbody", "td", "tfoot", - "th", "thead", "tr", "script", "style", "svg", "video"] + "th", "thead", "tr", "script", "style"] -- We want to allow raw docbook in markdown documents, so we -- include docbook block tags here too. @@ -591,19 +783,26 @@ blockDocBookTags = ["calloutlist", "bibliolist", "glosslist", "itemizedlist", "classsynopsis", "blockquote", "epigraph", "msgset", "sidebar", "title"] +epubTags :: [String] +epubTags = ["case", "switch", "default"] + blockTags :: [String] -blockTags = blockHtmlTags ++ blockDocBookTags +blockTags = blockHtmlTags ++ blockDocBookTags ++ epubTags isInlineTag :: Tag String -> Bool -isInlineTag t = tagOpen (`notElem` blockTags) (const True) t || - tagClose (`notElem` blockTags) t || +isInlineTag t = tagOpen isInlineTagName (const True) t || + tagClose isInlineTagName t || tagComment (const True) t + where isInlineTagName x = x `notElem` blockTags isBlockTag :: Tag String -> Bool -isBlockTag t = tagOpen (`elem` blocktags) (const True) t || - tagClose (`elem` blocktags) t || +isBlockTag t = tagOpen isBlockTagName (const True) t || + tagClose isBlockTagName t || tagComment (const True) t - where blocktags = blockTags ++ eitherBlockOrInline + where isBlockTagName ('?':_) = True + isBlockTagName ('!':_) = True + isBlockTagName x = x `elem` blockTags + || x `elem` eitherBlockOrInline isTextTag :: Tag String -> Bool isTextTag = tagText (const True) @@ -612,7 +811,7 @@ isCommentTag :: Tag String -> Bool isCommentTag = tagComment (const True) -- taken from HXT and extended - +-- See http://www.w3.org/TR/html5/syntax.html sec 8.1.2.4 optional tags closes :: String -> String -> Bool _ `closes` "body" = False _ `closes` "html" = False @@ -620,11 +819,18 @@ _ `closes` "html" = False "li" `closes` "li" = True "th" `closes` t | t `elem` ["th","td"] = True "tr" `closes` t | t `elem` ["th","td","tr"] = True +"dd" `closes` t | t `elem` ["dt", "dd"] = True "dt" `closes` t | t `elem` ["dt","dd"] = True -"hr" `closes` "p" = True -"p" `closes` "p" = True +"rt" `closes` t | t `elem` ["rb", "rt", "rtc"] = True +"optgroup" `closes` "optgroup" = True +"optgroup" `closes` "option" = True +"option" `closes` "option" = True +-- http://www.w3.org/TR/html-markup/p.html +x `closes` "p" | x `elem` ["address", "article", "aside", "blockquote", + "dir", "div", "dl", "fieldset", "footer", "form", "h1", "h2", "h3", "h4", + "h5", "h6", "header", "hr", "menu", "nav", "ol", "p", "pre", "section", + "table", "ul"] = True "meta" `closes` "meta" = True -"colgroup" `closes` "colgroup" = True "form" `closes` "form" = True "label" `closes` "label" = True "map" `closes` "map" = True @@ -645,19 +851,23 @@ _ `closes` _ = False --- parsers for use in markdown, textile readers -- | Matches a stretch of HTML in balanced tags. -htmlInBalanced :: (Tag String -> Bool) -> Parser [Char] ParserState String +htmlInBalanced :: (Monad m) + => (Tag String -> Bool) + -> ParserT String st m String htmlInBalanced f = try $ do (TagOpen t _, tag) <- htmlTag f guard $ '/' `notElem` tag -- not a self-closing tag let stopper = htmlTag (~== TagClose t) - let anytag = liftM snd $ htmlTag (const True) + let anytag = snd <$> htmlTag (const True) contents <- many $ notFollowedBy' stopper >> (htmlInBalanced f <|> anytag <|> count 1 anyChar) endtag <- liftM snd stopper return $ tag ++ concat contents ++ endtag -- | Matches a tag meeting a certain condition. -htmlTag :: (Tag String -> Bool) -> Parser [Char] st (Tag String, String) +htmlTag :: Monad m + => (Tag String -> Bool) + -> ParserT [Char] st m (Tag String, String) htmlTag f = try $ do lookAhead $ char '<' >> (oneOf "/!?" <|> letter) (next : _) <- getInput >>= return . canonicalizeTags . parseTags @@ -676,6 +886,79 @@ htmlTag f = try $ do mkAttr :: [(String, String)] -> Attr mkAttr attr = (attribsId, attribsClasses, attribsKV) where attribsId = fromMaybe "" $ lookup "id" attr - attribsClasses = words $ fromMaybe "" $ lookup "class" attr + attribsClasses = (words $ fromMaybe "" $ lookup "class" attr) ++ epubTypes attribsKV = filter (\(k,_) -> k /= "class" && k /= "id") attr + epubTypes = words $ fromMaybe "" $ lookup "epub:type" attr + +-- Strip namespace prefixes +stripPrefixes :: [Tag String] -> [Tag String] +stripPrefixes = map stripPrefix + +stripPrefix :: Tag String -> Tag String +stripPrefix (TagOpen s as) = + TagOpen (stripPrefix' s) (map (stripPrefix' *** id) as) +stripPrefix (TagClose s) = TagClose (stripPrefix' s) +stripPrefix x = x + +stripPrefix' :: String -> String +stripPrefix' s = + case span (/= ':') s of + (_, "") -> s + (_, (_:ts)) -> ts + +isSpace :: Char -> Bool +isSpace ' ' = True +isSpace '\t' = True +isSpace '\n' = True +isSpace '\r' = True +isSpace _ = False + +-- Instances + +-- This signature should be more general +-- MonadReader HTMLLocal m => HasQuoteContext st m +instance HasQuoteContext st (Reader HTMLLocal) where + getQuoteContext = asks quoteContext + withQuoteContext q = local (\s -> s{quoteContext = q}) +instance HasReaderOptions HTMLState where + extractReaderOptions = extractReaderOptions . parserState + +instance Default HTMLState where + def = HTMLState def [] + +instance HasMeta HTMLState where + setMeta s b st = st {parserState = setMeta s b $ parserState st} + deleteMeta s st = st {parserState = deleteMeta s $ parserState st} + +instance Default HTMLLocal where + def = HTMLLocal NoQuote False False + +instance HasLastStrPosition HTMLState where + setLastStrPos s st = st {parserState = setLastStrPos s (parserState st)} + getLastStrPos = getLastStrPos . parserState + + +-- EPUB Specific +-- +-- +sectioningContent :: [String] +sectioningContent = ["article", "aside", "nav", "section"] + + +groupingContent :: [String] +groupingContent = ["p", "hr", "pre", "blockquote", "ol" + , "ul", "li", "dl", "dt", "dt", "dd" + , "figure", "figcaption", "div", "main"] + + +{- + +types :: [(String, ([String], Int))] +types = -- Document divisions + map (\s -> (s, (["section", "body"], 0))) + ["volume", "part", "chapter", "division"] + ++ -- Document section and components + [ + ("abstract", ([], 0))] +-} diff --git a/src/Text/Pandoc/Readers/Haddock.hs b/src/Text/Pandoc/Readers/Haddock.hs index 0e74406ef..4b46c869d 100644 --- a/src/Text/Pandoc/Readers/Haddock.hs +++ b/src/Text/Pandoc/Readers/Haddock.hs @@ -3,7 +3,8 @@ Copyright : Copyright (C) 2013 David Lazar License : GNU GPL, version 2 or above - Maintainer : David Lazar <lazar6@illinois.edu> + Maintainer : David Lazar <lazar6@illinois.edu>, + John MacFarlane <jgm@berkeley.edu> Stability : alpha Conversion of Haddock markup to 'Pandoc' document. @@ -12,30 +13,126 @@ module Text.Pandoc.Readers.Haddock ( readHaddock ) where -import Text.Pandoc.Builder +import Text.Pandoc.Builder (Blocks, Inlines) +import qualified Text.Pandoc.Builder as B +import Text.Pandoc.Shared (trim, splitBy) +import Data.Monoid +import Data.List (intersperse, stripPrefix) +import Data.Maybe (fromMaybe) +import Text.Pandoc.Definition import Text.Pandoc.Options -import Text.Pandoc.Readers.Haddock.Lex -import Text.Pandoc.Readers.Haddock.Parse +import Documentation.Haddock.Parser +import Documentation.Haddock.Types +import Debug.Trace (trace) -- | Parse Haddock markup and return a 'Pandoc' document. readHaddock :: ReaderOptions -- ^ Reader options -> String -- ^ String to parse -> Pandoc -readHaddock _ s = Pandoc nullMeta blocks +readHaddock opts = B.doc . docHToBlocks . trace' . parseParas + where trace' x = if readerTrace opts + then trace (show x) x + else x + +docHToBlocks :: DocH String Identifier -> Blocks +docHToBlocks d' = + case d' of + DocEmpty -> mempty + DocAppend (DocParagraph (DocHeader h)) (DocParagraph (DocAName ident)) -> + B.headerWith (ident,[],[]) (headerLevel h) + (docHToInlines False $ headerTitle h) + DocAppend d1 d2 -> mappend (docHToBlocks d1) (docHToBlocks d2) + DocString _ -> inlineFallback + DocParagraph (DocAName h) -> B.plain $ docHToInlines False $ DocAName h + DocParagraph x -> B.para $ docHToInlines False x + DocIdentifier _ -> inlineFallback + DocIdentifierUnchecked _ -> inlineFallback + DocModule s -> B.plain $ docHToInlines False $ DocModule s + DocWarning _ -> mempty -- TODO + DocEmphasis _ -> inlineFallback + DocMonospaced _ -> inlineFallback + DocBold _ -> inlineFallback + DocHeader h -> B.header (headerLevel h) + (docHToInlines False $ headerTitle h) + DocUnorderedList items -> B.bulletList (map docHToBlocks items) + DocOrderedList items -> B.orderedList (map docHToBlocks items) + DocDefList items -> B.definitionList (map (\(d,t) -> + (docHToInlines False d, + [consolidatePlains $ docHToBlocks t])) items) + DocCodeBlock (DocString s) -> B.codeBlockWith ("",[],[]) s + DocCodeBlock d -> B.para $ docHToInlines True d + DocHyperlink _ -> inlineFallback + DocPic _ -> inlineFallback + DocAName _ -> inlineFallback + DocProperty s -> B.codeBlockWith ("",["property","haskell"],[]) (trim s) + DocExamples es -> mconcat $ map (\e -> + makeExample ">>>" (exampleExpression e) (exampleResult e)) es + + where inlineFallback = B.plain $ docHToInlines False d' + consolidatePlains = B.fromList . consolidatePlains' . B.toList + consolidatePlains' zs@(Plain _ : _) = + let (xs, ys) = span isPlain zs in + Para (concatMap extractContents xs) : consolidatePlains' ys + consolidatePlains' (x : xs) = x : consolidatePlains' xs + consolidatePlains' [] = [] + isPlain (Plain _) = True + isPlain _ = False + extractContents (Plain xs) = xs + extractContents _ = [] + +docHToInlines :: Bool -> DocH String Identifier -> Inlines +docHToInlines isCode d' = + case d' of + DocEmpty -> mempty + DocAppend d1 d2 -> mappend (docHToInlines isCode d1) + (docHToInlines isCode d2) + DocString s + | isCode -> mconcat $ intersperse B.linebreak + $ map B.code $ splitBy (=='\n') s + | otherwise -> B.text s + DocParagraph _ -> mempty + DocIdentifier (_,s,_) -> B.codeWith ("",["haskell","identifier"],[]) s + DocIdentifierUnchecked s -> B.codeWith ("",["haskell","identifier"],[]) s + DocModule s -> B.codeWith ("",["haskell","module"],[]) s + DocWarning _ -> mempty -- TODO + DocEmphasis d -> B.emph (docHToInlines isCode d) + DocMonospaced (DocString s) -> B.code s + DocMonospaced d -> docHToInlines True d + DocBold d -> B.strong (docHToInlines isCode d) + DocHeader _ -> mempty + DocUnorderedList _ -> mempty + DocOrderedList _ -> mempty + DocDefList _ -> mempty + DocCodeBlock _ -> mempty + DocHyperlink h -> B.link (hyperlinkUrl h) (hyperlinkUrl h) + (maybe (B.text $ hyperlinkUrl h) B.text $ hyperlinkLabel h) + DocPic p -> B.image (pictureUri p) (fromMaybe (pictureUri p) $ pictureTitle p) + (maybe mempty B.text $ pictureTitle p) + DocAName s -> B.spanWith (s,["anchor"],[]) mempty + DocProperty _ -> mempty + DocExamples _ -> mempty + +-- | Create an 'Example', stripping superfluous characters as appropriate +makeExample :: String -> String -> [String] -> Blocks +makeExample prompt expression result = + B.para $ B.codeWith ("",["prompt"],[]) prompt + <> B.space + <> B.codeWith ([], ["haskell","expr"], []) (trim expression) + <> B.linebreak + <> (mconcat $ intersperse B.linebreak $ map coder result') where - blocks = case parseParas (tokenise s (0,0)) of - Left [] -> error "parse failure" - Left (tok:_) -> error $ "parse failure " ++ pos (tokenPos tok) - where pos (l, c) = "(line " ++ show l ++ ", column " ++ show c ++ ")" - Right x -> mergeLists (toList x) - --- similar to 'docAppend' in Haddock.Doc -mergeLists :: [Block] -> [Block] -mergeLists (BulletList xs : BulletList ys : blocks) - = mergeLists (BulletList (xs ++ ys) : blocks) -mergeLists (OrderedList _ xs : OrderedList a ys : blocks) - = mergeLists (OrderedList a (xs ++ ys) : blocks) -mergeLists (DefinitionList xs : DefinitionList ys : blocks) - = mergeLists (DefinitionList (xs ++ ys) : blocks) -mergeLists (x : blocks) = x : mergeLists blocks -mergeLists [] = [] + -- 1. drop trailing whitespace from the prompt, remember the prefix + prefix = takeWhile (`elem` " \t") prompt + + -- 2. drop, if possible, the exact same sequence of whitespace + -- characters from each result line + -- + -- 3. interpret lines that only contain the string "<BLANKLINE>" as an + -- empty line + result' = map (substituteBlankLine . tryStripPrefix prefix) result + where + tryStripPrefix xs ys = fromMaybe ys $ stripPrefix xs ys + + substituteBlankLine "<BLANKLINE>" = "" + substituteBlankLine line = line + coder = B.codeWith ([], ["result"], []) diff --git a/src/Text/Pandoc/Readers/Haddock/Lex.x b/src/Text/Pandoc/Readers/Haddock/Lex.x deleted file mode 100644 index 120e96ebf..000000000 --- a/src/Text/Pandoc/Readers/Haddock/Lex.x +++ /dev/null @@ -1,171 +0,0 @@ --- --- Haddock - A Haskell Documentation Tool --- --- (c) Simon Marlow 2002 --- --- This file was modified and integrated into GHC by David Waern 2006. --- Then moved back into Haddock by Isaac Dupree in 2009 :-) --- Then copied into Pandoc by David Lazar in 2013 :-D - -{ -{-# LANGUAGE BangPatterns #-} -- Generated by Alex -{-# OPTIONS -Wwarn -w #-} --- The above warning supression flag is a temporary kludge. --- While working on this module you are encouraged to remove it and fix --- any warnings in the module. See --- http://hackage.haskell.org/trac/ghc/wiki/Commentary/CodingStyle#Warnings --- for details - -module Text.Pandoc.Readers.Haddock.Lex ( - Token(..), - LToken, - tokenise, - tokenPos - ) where - -import Data.Char -import Numeric (readHex) -} - -%wrapper "posn" - -$ws = $white # \n -$digit = [0-9] -$hexdigit = [0-9a-fA-F] -$special = [\"\@] -$alphanum = [A-Za-z0-9] -$ident = [$alphanum \'\_\.\!\#\$\%\&\*\+\/\<\=\>\?\@\\\\\^\|\-\~\:] - -:- - --- beginning of a paragraph -<0,para> { - $ws* \n ; - $ws* \> { begin birdtrack } - $ws* prop \> .* \n { strtoken TokProperty `andBegin` property} - $ws* \>\>\> { strtoken TokExamplePrompt `andBegin` exampleexpr } - $ws* [\*\-] { token TokBullet `andBegin` string } - $ws* \[ { token TokDefStart `andBegin` def } - $ws* \( $digit+ \) { token TokNumber `andBegin` string } - $ws* $digit+ \. { token TokNumber `andBegin` string } - $ws* { begin string } -} - --- beginning of a line -<line> { - $ws* \> { begin birdtrack } - $ws* \>\>\> { strtoken TokExamplePrompt `andBegin` exampleexpr } - - $ws* \n { token TokPara `andBegin` para } - -- ^ Here, we really want to be able to say - -- $ws* (\n | <eof>) { token TokPara `andBegin` para} - -- because otherwise a trailing line of whitespace will result in - -- a spurious TokString at the end of a docstring. We don't have <eof>, - -- though (NOW I realise what it was for :-). To get around this, we always - -- append \n to the end of a docstring. - - () { begin string } -} - -<birdtrack> .* \n? { strtokenNL TokBirdTrack `andBegin` line } - -<property> () { token TokPara `andBegin` para } - -<example> { - $ws* \n { token TokPara `andBegin` para } - $ws* \>\>\> { strtoken TokExamplePrompt `andBegin` exampleexpr } - () { begin exampleresult } -} - -<exampleexpr> .* \n { strtokenNL TokExampleExpression `andBegin` example } - -<exampleresult> .* \n { strtokenNL TokExampleResult `andBegin` example } - -<string,def> { - $special { strtoken $ \s -> TokSpecial (head s) } - \<\< [^\>]* \>\> { strtoken $ \s -> TokPic (init $ init $ tail $ tail s) } - \< [^\>]* \> { strtoken $ \s -> TokURL (init (tail s)) } - \# [^\#]* \# { strtoken $ \s -> TokAName (init (tail s)) } - \/ [^\/]* \/ { strtoken $ \s -> TokEmphasis (init (tail s)) } - [\'\`] $ident+ [\'\`] { strtoken $ \s -> TokIdent (init (tail s)) } - \\ . { strtoken (TokString . tail) } - "&#" $digit+ \; { strtoken $ \s -> TokString [chr (read (init (drop 2 s)))] } - "&#" [xX] $hexdigit+ \; - { strtoken $ \s -> case readHex (init (drop 3 s)) of [(n,_)] -> TokString [chr n] } - -- allow special characters through if they don't fit one of the previous - -- patterns. - [\/\'\`\<\#\&\\] { strtoken TokString } - [^ $special \/ \< \# \n \'\` \& \\ \]]* \n { strtokenNL TokString `andBegin` line } - [^ $special \/ \< \# \n \'\` \& \\ \]]+ { strtoken TokString } -} - -<def> { - \] { token TokDefEnd `andBegin` string } -} - --- ']' doesn't have any special meaning outside of the [...] at the beginning --- of a definition paragraph. -<string> { - \] { strtoken TokString } -} - -{ --- | A located token -type LToken = (Token, AlexPosn) - -data Token - = TokPara - | TokNumber - | TokBullet - | TokDefStart - | TokDefEnd - | TokSpecial Char - | TokIdent String - | TokString String - | TokURL String - | TokPic String - | TokEmphasis String - | TokAName String - | TokBirdTrack String - | TokProperty String - | TokExamplePrompt String - | TokExampleExpression String - | TokExampleResult String - deriving Show - -tokenPos :: LToken -> (Int, Int) -tokenPos t = let AlexPn _ line col = snd t in (line, col) - -type StartCode = Int -type Action = AlexPosn -> String -> StartCode -> (StartCode -> [LToken]) -> [LToken] - -tokenise :: String -> (Int, Int) -> [LToken] -tokenise str (line, col) = go (posn,'\n',[],eofHack str) para - where posn = AlexPn 0 line col - go inp@(pos,_,_,str) sc = - case alexScan inp sc of - AlexEOF -> [] - AlexError _ -> [] - AlexSkip inp' len -> go inp' sc - AlexToken inp' len act -> act pos (take len str) sc (\sc -> go inp' sc) - --- NB. we add a final \n to the string, (see comment in the beginning of line --- production above). -eofHack str = str++"\n" - -andBegin :: Action -> StartCode -> Action -andBegin act new_sc = \pos str _ cont -> act pos str new_sc cont - -token :: Token -> Action -token t = \pos _ sc cont -> (t, pos) : cont sc - -strtoken, strtokenNL :: (String -> Token) -> Action -strtoken t = \pos str sc cont -> (t str, pos) : cont sc -strtokenNL t = \pos str sc cont -> (t (filter (/= '\r') str), pos) : cont sc --- ^ We only want LF line endings in our internal doc string format, so we --- filter out all CRs. - -begin :: StartCode -> Action -begin sc = \_ _ _ cont -> cont sc - -} diff --git a/src/Text/Pandoc/Readers/Haddock/Parse.y b/src/Text/Pandoc/Readers/Haddock/Parse.y deleted file mode 100644 index 9c2bbc8a9..000000000 --- a/src/Text/Pandoc/Readers/Haddock/Parse.y +++ /dev/null @@ -1,178 +0,0 @@ --- This code was copied from the 'haddock' package, modified, and integrated --- into Pandoc by David Lazar. -{ -{-# LANGUAGE BangPatterns #-} -- required for versions of Happy before 1.18.6 --- The above warning supression flag is a temporary kludge. --- While working on this module you are encouraged to remove it and fix --- any warnings in the module. See --- http://hackage.haskell.org/trac/ghc/wiki/Commentary/CodingStyle#Warnings --- for details - -module Text.Pandoc.Readers.Haddock.Parse (parseString, parseParas) where - -import Text.Pandoc.Readers.Haddock.Lex -import Text.Pandoc.Builder -import Text.Pandoc.Shared (trim, trimr) -import Data.Generics (everywhere, mkT) -import Data.Char (isSpace) -import Data.Maybe (fromMaybe) -import Data.List (stripPrefix, intersperse) -import Data.Monoid (mempty, mconcat) -} - -%expect 0 - -%tokentype { LToken } - -%token - '/' { (TokSpecial '/',_) } - '@' { (TokSpecial '@',_) } - '[' { (TokDefStart,_) } - ']' { (TokDefEnd,_) } - DQUO { (TokSpecial '\"',_) } - URL { (TokURL $$,_) } - PIC { (TokPic $$,_) } - ANAME { (TokAName $$,_) } - '/../' { (TokEmphasis $$,_) } - '-' { (TokBullet,_) } - '(n)' { (TokNumber,_) } - '>..' { (TokBirdTrack $$,_) } - PROP { (TokProperty $$,_) } - PROMPT { (TokExamplePrompt $$,_) } - RESULT { (TokExampleResult $$,_) } - EXP { (TokExampleExpression $$,_) } - IDENT { (TokIdent $$,_) } - PARA { (TokPara,_) } - STRING { (TokString $$,_) } - -%monad { Either [LToken] } - -%name parseParas doc -%name parseString seq - -%% - -doc :: { Blocks } - : apara PARA doc { $1 <> $3 } - | PARA doc { $2 } - | apara { $1 } - | {- empty -} { mempty } - -apara :: { Blocks } - : ulpara { bulletList [$1] } - | olpara { orderedList [$1] } - | defpara { definitionList [$1] } - | para { $1 } - -ulpara :: { Blocks } - : '-' para { $2 } - -olpara :: { Blocks } - : '(n)' para { $2 } - -defpara :: { (Inlines, [Blocks]) } - : '[' seq ']' seq { (trimInlines $2, [plain $ trimInlines $4]) } - -para :: { Blocks } - : seq { para' $1 } - | codepara { codeBlockWith ([], ["haskell"], []) $1 } - | property { $1 } - | examples { $1 } - -codepara :: { String } - : '>..' codepara { $1 ++ $2 } - | '>..' { $1 } - -property :: { Blocks } - : PROP { makeProperty $1 } - -examples :: { Blocks } - : example examples { $1 <> $2 } - | example { $1 } - -example :: { Blocks } - : PROMPT EXP result { makeExample $1 $2 (lines $3) } - | PROMPT EXP { makeExample $1 $2 [] } - -result :: { String } - : RESULT result { $1 ++ $2 } - | RESULT { $1 } - -seq :: { Inlines } - : elem seq { $1 <> $2 } - | elem { $1 } - -elem :: { Inlines } - : elem1 { $1 } - | '@' seq1 '@' { monospace $2 } - -seq1 :: { Inlines } - : PARA seq1 { linebreak <> $2 } - | elem1 seq1 { $1 <> $2 } - | elem1 { $1 } - -elem1 :: { Inlines } - : STRING { text $1 } - | '/../' { emph (str $1) } - | URL { makeHyperlink $1 } - | PIC { image $1 $1 mempty } - | ANAME { mempty } -- TODO - | IDENT { codeWith ([], ["haskell"], []) $1 } - | DQUO strings DQUO { codeWith ([], ["haskell"], []) $2 } - -strings :: { String } - : STRING { $1 } - | STRING strings { $1 ++ $2 } - -{ -happyError :: [LToken] -> Either [LToken] a -happyError toks = Left toks - -para' :: Inlines -> Blocks -para' = para . trimInlines - -monospace :: Inlines -> Inlines -monospace = everywhere (mkT go) - where - go (Str s) = Code nullAttr s - go x = x - --- | Create a `Hyperlink` from given string. --- --- A hyperlink consists of a URL and an optional label. The label is separated --- from the url by one or more whitespace characters. -makeHyperlink :: String -> Inlines -makeHyperlink input = case break isSpace $ trim input of - (url, "") -> link url url (str url) - (url, lb) -> link url url (trimInlines $ text lb) - -makeProperty :: String -> Blocks -makeProperty s = case trim s of - 'p':'r':'o':'p':'>':xs -> - codeBlockWith ([], ["property"], []) (dropWhile isSpace xs) - xs -> - error $ "makeProperty: invalid input " ++ show xs - --- | Create an 'Example', stripping superfluous characters as appropriate -makeExample :: String -> String -> [String] -> Blocks -makeExample prompt expression result = - para $ codeWith ([], ["haskell","expr"], []) (trim expression) - <> linebreak - <> (mconcat $ intersperse linebreak $ map coder result') - where - -- 1. drop trailing whitespace from the prompt, remember the prefix - prefix = takeWhile isSpace prompt - - -- 2. drop, if possible, the exact same sequence of whitespace - -- characters from each result line - -- - -- 3. interpret lines that only contain the string "<BLANKLINE>" as an - -- empty line - result' = map (substituteBlankLine . tryStripPrefix prefix) result - where - tryStripPrefix xs ys = fromMaybe ys $ stripPrefix xs ys - - substituteBlankLine "<BLANKLINE>" = "" - substituteBlankLine line = line - coder = codeWith ([], ["result"], []) -} diff --git a/src/Text/Pandoc/Readers/LaTeX.hs b/src/Text/Pandoc/Readers/LaTeX.hs index 51271edc5..9420d602f 100644 --- a/src/Text/Pandoc/Readers/LaTeX.hs +++ b/src/Text/Pandoc/Readers/LaTeX.hs @@ -1,6 +1,6 @@ {-# LANGUAGE ScopedTypeVariables, OverloadedStrings #-} {- -Copyright (C) 2006-2012 John MacFarlane <jgm@berkeley.edu> +Copyright (C) 2006-2014 John MacFarlane <jgm@berkeley.edu> This program is free software; you can redistribute it and/or modify it under the terms of the GNU General Public License as published by @@ -19,7 +19,7 @@ Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA {- | Module : Text.Pandoc.Readers.LaTeX - Copyright : Copyright (C) 2006-2012 John MacFarlane + Copyright : Copyright (C) 2006-2014 John MacFarlane License : GNU GPL, version 2 or above Maintainer : John MacFarlane <jgm@berkeley.edu> @@ -31,6 +31,7 @@ Conversion of LaTeX to 'Pandoc' document. module Text.Pandoc.Readers.LaTeX ( readLaTeX, rawLaTeXInline, rawLaTeXBlock, + inlineCommand, handleIncludes ) where @@ -42,6 +43,7 @@ import Text.Pandoc.Parsing hiding ((<|>), many, optional, space, mathDisplay, mathInline) import qualified Text.Pandoc.UTF8 as UTF8 import Data.Char ( chr, ord ) +import Control.Monad.Trans (lift) import Control.Monad import Text.Pandoc.Builder import Data.Char (isLetter, isAlphaNum) @@ -101,7 +103,7 @@ dimenarg = try $ do sp :: LP () sp = skipMany1 $ satisfy (\c -> c == ' ' || c == '\t') - <|> (try $ newline >>~ lookAhead anyChar >>~ notFollowedBy blankline) + <|> (try $ newline <* lookAhead anyChar <* notFollowedBy blankline) isLowerHex :: Char -> Bool isLowerHex x = x >= '0' && x <= '9' || x >= 'a' && x <= 'f' @@ -123,7 +125,7 @@ comment :: LP () comment = do char '%' skipMany (satisfy (/='\n')) - newline + optional newline return () bgroup :: LP () @@ -302,6 +304,13 @@ blockCommands = M.fromList $ , ("item", skipopts *> loose_item) , ("documentclass", skipopts *> braced *> preamble) , ("centerline", (para . trimInlines) <$> (skipopts *> tok)) + , ("caption", skipopts *> tok >>= setCaption) + , ("PandocStartInclude", startInclude) + , ("PandocEndInclude", endInclude) + , ("bibliography", mempty <$ (skipopts *> braced >>= + addMeta "bibliography" . splitBibs)) + , ("addbibresource", mempty <$ (skipopts *> braced >>= + addMeta "bibliography" . splitBibs)) ] ++ map ignoreBlocks -- these commands will be ignored unless --parse-raw is specified, -- in which case they will appear as raw latex blocks @@ -309,7 +318,7 @@ blockCommands = M.fromList $ -- newcommand, etc. should be parsed by macro, but we need this -- here so these aren't parsed as inline commands to ignore , "special", "pdfannot", "pdfstringdef" - , "bibliography", "bibliographystyle" + , "bibliographystyle" , "maketitle", "makeindex", "makeglossary" , "addcontentsline", "addtocontents", "addtocounter" -- \ignore{} is used conventionally in literate haskell for definitions @@ -321,7 +330,19 @@ blockCommands = M.fromList $ ] addMeta :: ToMetaValue a => String -> a -> LP () -addMeta field val = updateState $ setMeta field val +addMeta field val = updateState $ \st -> + st{ stateMeta = addMetaField field val $ stateMeta st } + +splitBibs :: String -> [Inlines] +splitBibs = map (str . flip replaceExtension "bib" . trim) . splitBy (==',') + +setCaption :: Inlines -> LP Blocks +setCaption ils = do + updateState $ \st -> st{ stateCaption = Just ils } + return mempty + +resetCaption :: LP () +resetCaption = updateState $ \st -> st{ stateCaption = Nothing } authors :: LP () authors = try $ do @@ -332,7 +353,7 @@ authors = try $ do -- skip e.g. \vspace{10pt} auths <- sepBy oneAuthor (controlSeq "and") char '}' - addMeta "authors" (map trimInlines auths) + addMeta "author" (map trimInlines auths) section :: Attr -> Int -> LP Blocks section (ident, classes, kvs) lvl = do @@ -375,18 +396,18 @@ isBlockCommand s = maybe False (const True) $ M.lookup s blockCommands inlineCommands :: M.Map String (LP Inlines) inlineCommands = M.fromList $ - [ ("emph", emph <$> tok) - , ("textit", emph <$> tok) - , ("textsl", emph <$> tok) - , ("textsc", smallcaps <$> tok) - , ("sout", strikeout <$> tok) - , ("textsuperscript", superscript <$> tok) - , ("textsubscript", subscript <$> tok) + [ ("emph", extractSpaces emph <$> tok) + , ("textit", extractSpaces emph <$> tok) + , ("textsl", extractSpaces emph <$> tok) + , ("textsc", extractSpaces smallcaps <$> tok) + , ("sout", extractSpaces strikeout <$> tok) + , ("textsuperscript", extractSpaces superscript <$> tok) + , ("textsubscript", extractSpaces subscript <$> tok) , ("textbackslash", lit "\\") , ("backslash", lit "\\") , ("slash", lit "/") - , ("textbf", strong <$> tok) - , ("textnormal", spanWith ("",["nodecor"],[]) <$> tok) + , ("textbf", extractSpaces strong <$> tok) + , ("textnormal", extractSpaces (spanWith ("",["nodecor"],[])) <$> tok) , ("ldots", lit "…") , ("dots", lit "…") , ("mdots", lit "…") @@ -406,15 +427,15 @@ inlineCommands = M.fromList $ , ("{", lit "{") , ("}", lit "}") -- old TeX commands - , ("em", emph <$> inlines) - , ("it", emph <$> inlines) - , ("sl", emph <$> inlines) - , ("bf", strong <$> inlines) + , ("em", extractSpaces emph <$> inlines) + , ("it", extractSpaces emph <$> inlines) + , ("sl", extractSpaces emph <$> inlines) + , ("bf", extractSpaces strong <$> inlines) , ("rm", inlines) - , ("itshape", emph <$> inlines) - , ("slshape", emph <$> inlines) - , ("scshape", smallcaps <$> inlines) - , ("bfseries", strong <$> inlines) + , ("itshape", extractSpaces emph <$> inlines) + , ("slshape", extractSpaces emph <$> inlines) + , ("scshape", extractSpaces smallcaps <$> inlines) + , ("bfseries", extractSpaces strong <$> inlines) , ("/", pure mempty) -- italic correction , ("aa", lit "å") , ("AA", lit "Å") @@ -473,6 +494,7 @@ inlineCommands = M.fromList $ , ("citealp", citation "citealp" NormalCitation False) , ("citealp*", citation "citealp*" NormalCitation False) , ("autocite", citation "autocite" NormalCitation False) + , ("smartcite", citation "smartcite" NormalCitation False) , ("footcite", inNote <$> citation "footcite" NormalCitation False) , ("parencite", citation "parencite" NormalCitation False) , ("supercite", citation "supercite" NormalCitation False) @@ -495,6 +517,7 @@ inlineCommands = M.fromList $ , ("supercites", citation "supercites" NormalCitation True) , ("footcitetexts", inNote <$> citation "footcitetexts" NormalCitation True) , ("Autocite", citation "Autocite" NormalCitation False) + , ("Smartcite", citation "Smartcite" NormalCitation False) , ("Footcite", citation "Footcite" NormalCitation False) , ("Parencite", citation "Parencite" NormalCitation False) , ("Supercite", citation "Supercite" NormalCitation False) @@ -516,25 +539,21 @@ inlineCommands = M.fromList $ , ("citeauthor", (try (tok *> optional sp *> controlSeq "citetext") *> complexNatbibCitation AuthorInText) <|> citation "citeauthor" AuthorInText False) + , ("nocite", mempty <$ (citation "nocite" NormalCitation False >>= + addMeta "nocite")) ] ++ map ignoreInlines -- these commands will be ignored unless --parse-raw is specified, -- in which case they will appear as raw latex blocks: - [ "noindent", "index", "nocite" ] + [ "noindent", "index" ] mkImage :: String -> LP Inlines mkImage src = do - -- try for a caption - (alt, tit) <- option (str "image", "") $ try $ do - spaces - controlSeq "caption" - optional (char '*') - ils <- grouped inline - return (ils, "fig:") + let alt = str "image" case takeExtension src of "" -> do defaultExt <- getOption readerDefaultImageExtension - return $ image (addExtension src defaultExt) tit alt - _ -> return $ image src tit alt + return $ image (addExtension src defaultExt) "" alt + _ -> return $ image src "" alt inNote :: Inlines -> Inlines inNote ils = @@ -788,31 +807,107 @@ rawEnv name = do (withRaw (env name blocks) >>= applyMacros' . snd) else env name blocks +---- + +type IncludeParser = ParserT [Char] [String] IO String + -- | Replace "include" commands with file contents. handleIncludes :: String -> IO String -handleIncludes = handleIncludes' [] - --- parents parameter prevents infinite include loops -handleIncludes' :: [FilePath] -> String -> IO String -handleIncludes' _ [] = return [] -handleIncludes' parents ('\\':'%':xs) = - ("\\%"++) `fmap` handleIncludes' parents xs -handleIncludes' parents ('%':xs) = handleIncludes' parents - $ drop 1 $ dropWhile (/='\n') xs -handleIncludes' parents ('\\':xs) = - case runParser include defaultParserState "input" ('\\':xs) of - Right (fs, rest) -> do yss <- mapM (\f -> if f `elem` parents - then "" <$ warn ("Include file loop in '" - ++ f ++ "'.") - else readTeXFile f >>= - handleIncludes' (f:parents)) fs - rest' <- handleIncludes' parents rest - return $ intercalate "\n" yss ++ rest' - _ -> case runParser (verbCmd <|> verbatimEnv) defaultParserState - "input" ('\\':xs) of - Right (r, rest) -> (r ++) `fmap` handleIncludes' parents rest - _ -> ('\\':) `fmap` handleIncludes' parents xs -handleIncludes' parents (x:xs) = (x:) `fmap` handleIncludes' parents xs +handleIncludes s = do + res <- runParserT includeParser' [] "input" s + case res of + Right s' -> return s' + Left e -> error $ show e + +includeParser' :: IncludeParser +includeParser' = + concat <$> many (comment' <|> escaped' <|> blob' <|> include' + <|> startMarker' <|> endMarker' + <|> verbCmd' <|> verbatimEnv' <|> backslash') + +comment' :: IncludeParser +comment' = do + char '%' + xs <- manyTill anyChar newline + return ('%':xs ++ "\n") + +escaped' :: IncludeParser +escaped' = try $ string "\\%" <|> string "\\\\" + +verbCmd' :: IncludeParser +verbCmd' = fmap snd <$> + withRaw $ try $ do + string "\\verb" + c <- anyChar + manyTill anyChar (char c) + +verbatimEnv' :: IncludeParser +verbatimEnv' = fmap snd <$> + withRaw $ try $ do + string "\\begin" + name <- braced' + guard $ name `elem` ["verbatim", "Verbatim", "lstlisting", + "minted", "alltt"] + manyTill anyChar (try $ string $ "\\end{" ++ name ++ "}") + +blob' :: IncludeParser +blob' = try $ many1 (noneOf "\\%") + +backslash' :: IncludeParser +backslash' = string "\\" + +braced' :: IncludeParser +braced' = try $ char '{' *> manyTill (satisfy (/='}')) (char '}') + +include' :: IncludeParser +include' = do + fs' <- try $ do + char '\\' + name <- try (string "include") + <|> try (string "input") + <|> string "usepackage" + -- skip options + skipMany $ try $ char '[' *> (manyTill anyChar (char ']')) + fs <- (map trim . splitBy (==',')) <$> braced' + return $ if name == "usepackage" + then map (flip replaceExtension ".sty") fs + else map (flip replaceExtension ".tex") fs + pos <- getPosition + containers <- getState + let fn = case containers of + (f':_) -> f' + [] -> "input" + -- now process each include file in order... + rest <- getInput + results' <- forM fs' (\f -> do + when (f `elem` containers) $ + fail "Include file loop!" + contents <- lift $ readTeXFile f + return $ "\\PandocStartInclude{" ++ f ++ "}" ++ + contents ++ "\\PandocEndInclude{" ++ + fn ++ "}{" ++ show (sourceLine pos) ++ "}{" + ++ show (sourceColumn pos) ++ "}") + setInput $ concat results' ++ rest + return "" + +startMarker' :: IncludeParser +startMarker' = try $ do + string "\\PandocStartInclude" + fn <- braced' + updateState (fn:) + setPosition $ newPos fn 1 1 + return $ "\\PandocStartInclude{" ++ fn ++ "}" + +endMarker' :: IncludeParser +endMarker' = try $ do + string "\\PandocEndInclude" + fn <- braced' + ln <- braced' + co <- braced' + updateState tail + setPosition $ newPos fn (fromMaybe 1 $ safeRead ln) (fromMaybe 1 $ safeRead co) + return $ "\\PandocEndInclude{" ++ fn ++ "}{" ++ ln ++ "}{" ++ + co ++ "}" readTeXFile :: FilePath -> IO String readTeXFile f = do @@ -827,27 +922,7 @@ readFileFromDirs (d:ds) f = E.catch (UTF8.readFile $ d </> f) $ \(_ :: E.SomeException) -> readFileFromDirs ds f -include :: LP ([FilePath], String) -include = do - name <- controlSeq "include" - <|> controlSeq "input" - <|> controlSeq "usepackage" - skipopts - fs <- (splitBy (==',')) <$> braced - rest <- getInput - let fs' = if name == "usepackage" - then map (flip replaceExtension ".sty") fs - else map (flip replaceExtension ".tex") fs - return (fs', rest) - -verbCmd :: LP (String, String) -verbCmd = do - (_,r) <- withRaw $ do - controlSeq "verb" - c <- anyChar - manyTill anyChar (char c) - rest <- getInput - return (r, rest) +---- keyval :: LP (String, String) keyval = try $ do @@ -869,17 +944,6 @@ alltt t = walk strToCode <$> parseFromString blocks where strToCode (Str s) = Code nullAttr s strToCode x = x -verbatimEnv :: LP (String, String) -verbatimEnv = do - (_,r) <- withRaw $ do - controlSeq "begin" - name <- braced - guard $ name `elem` ["verbatim", "Verbatim", "lstlisting", - "minted", "alltt"] - verbEnv name - rest <- getInput - return (r,rest) - rawLaTeXBlock :: Parser [Char] ParserState String rawLaTeXBlock = snd <$> try (withRaw (environment <|> blockCommand)) @@ -888,12 +952,33 @@ rawLaTeXInline = do raw <- (snd <$> withRaw inlineCommand) <|> (snd <$> withRaw blockCommand) RawInline "latex" <$> applyMacros' raw +addImageCaption :: Blocks -> LP Blocks +addImageCaption = walkM go + where go (Image alt (src,tit)) = do + mbcapt <- stateCaption <$> getState + case mbcapt of + Just ils -> return (Image (toList ils) (src, "fig:")) + Nothing -> return (Image alt (src,tit)) + go x = return x + +addTableCaption :: Blocks -> LP Blocks +addTableCaption = walkM go + where go (Table c als ws hs rs) = do + mbcapt <- stateCaption <$> getState + case mbcapt of + Just ils -> return (Table (toList ils) als ws hs rs) + Nothing -> return (Table c als ws hs rs) + go x = return x + environments :: M.Map String (LP Blocks) environments = M.fromList [ ("document", env "document" blocks <* skipMany anyChar) , ("letter", env "letter" letter_contents) - , ("figure", env "figure" $ skipopts *> blocks) + , ("figure", env "figure" $ + resetCaption *> skipopts *> blocks >>= addImageCaption) , ("center", env "center" blocks) + , ("table", env "table" $ + resetCaption *> skipopts *> blocks >>= addTableCaption) , ("tabular", env "tabular" simpTable) , ("quote", blockQuote <$> env "quote" blocks) , ("quotation", blockQuote <$> env "quotation" blocks) @@ -1050,7 +1135,7 @@ paragraph = do preamble :: LP Blocks preamble = mempty <$> manyTill preambleBlock beginDoc - where beginDoc = lookAhead $ controlSeq "begin" *> string "{document}" + where beginDoc = lookAhead $ try $ controlSeq "begin" *> string "{document}" preambleBlock = (void comment) <|> (void sp) <|> (void blanklines) @@ -1144,12 +1229,13 @@ complexNatbibCitation mode = try $ do parseAligns :: LP [Alignment] parseAligns = try $ do char '{' - let maybeBar = try $ spaces >> optional (char '|') + let maybeBar = skipMany $ sp <|> () <$ char '|' <|> () <$ try (string "@{}") maybeBar let cAlign = AlignCenter <$ char 'c' let lAlign = AlignLeft <$ char 'l' let rAlign = AlignRight <$ char 'r' - let alignChar = optional sp *> (cAlign <|> lAlign <|> rAlign) + let parAlign = AlignLeft <$ (char 'p' >> braced) + let alignChar = cAlign <|> lAlign <|> rAlign <|> parAlign aligns' <- sepEndBy alignChar maybeBar spaces char '}' @@ -1170,10 +1256,14 @@ parseTableRow :: Int -- ^ number of columns parseTableRow cols = try $ do let tableCellInline = notFollowedBy (amp <|> lbreak) >> inline let tableCell = (plain . trimInlines . mconcat) <$> many tableCellInline - cells' <- sepBy tableCell amp - guard $ length cells' == cols + cells' <- sepBy1 tableCell amp + let numcells = length cells' + guard $ numcells <= cols && numcells >= 1 + guard $ cells' /= [mempty] + -- note: a & b in a three-column table leaves an empty 3rd cell: + let cells'' = cells' ++ replicate (cols - numcells) mempty spaces - return cells' + return cells'' simpTable :: LP Blocks simpTable = try $ do @@ -1184,9 +1274,23 @@ simpTable = try $ do header' <- option [] $ try (parseTableRow cols <* lbreak <* hline) rows <- sepEndBy (parseTableRow cols) (lbreak <* optional hline) spaces + skipMany (comment *> spaces) let header'' = if null header' then replicate cols mempty else header' lookAhead $ controlSeq "end" -- make sure we're at end return $ table mempty (zip aligns (repeat 0)) header'' rows +startInclude :: LP Blocks +startInclude = do + fn <- braced + setPosition $ newPos fn 1 1 + return mempty + +endInclude :: LP Blocks +endInclude = do + fn <- braced + ln <- braced + co <- braced + setPosition $ newPos fn (fromMaybe 1 $ safeRead ln) (fromMaybe 1 $ safeRead co) + return mempty diff --git a/src/Text/Pandoc/Readers/Markdown.hs b/src/Text/Pandoc/Readers/Markdown.hs index 8a41cef49..2ca3b0eb6 100644 --- a/src/Text/Pandoc/Readers/Markdown.hs +++ b/src/Text/Pandoc/Readers/Markdown.hs @@ -1,6 +1,6 @@ {-# LANGUAGE RelaxedPolyRec #-} -- needed for inlinesBetween on GHC < 7 {- -Copyright (C) 2006-2010 John MacFarlane <jgm@berkeley.edu> +Copyright (C) 2006-2014 John MacFarlane <jgm@berkeley.edu> This program is free software; you can redistribute it and/or modify it under the terms of the GNU General Public License as published by @@ -19,7 +19,7 @@ Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA {- | Module : Text.Pandoc.Readers.Markdown - Copyright : Copyright (C) 2006-2013 John MacFarlane + Copyright : Copyright (C) 2006-2014 John MacFarlane License : GNU GPL, version 2 or above Maintainer : John MacFarlane <jgm@berkeley.edu> @@ -33,6 +33,7 @@ module Text.Pandoc.Readers.Markdown ( readMarkdown, import Data.List ( transpose, sortBy, findIndex, intersperse, intercalate ) import qualified Data.Map as M +import Data.Scientific (coefficient, base10Exponent) import Data.Ord ( comparing ) import Data.Char ( isAlphaNum, toLower ) import Data.Maybe @@ -60,6 +61,8 @@ import System.FilePath (takeExtension, addExtension) import Text.HTML.TagSoup import Text.HTML.TagSoup.Match (tagOpen) import qualified Data.Set as Set +import Text.Printf (printf) +import Debug.Trace (trace) type MarkdownParser = Parser [Char] ParserState @@ -76,11 +79,7 @@ readMarkdownWithWarnings :: ReaderOptions -- ^ Reader options -> String -- ^ String to parse (assuming @'\n'@ line endings) -> (Pandoc, [String]) readMarkdownWithWarnings opts s = - (readWith parseMarkdownWithWarnings) def{ stateOptions = opts } (s ++ "\n\n") - where parseMarkdownWithWarnings = do - doc <- parseMarkdown - warnings <- stateWarnings <$> getState - return (doc, warnings) + (readWithWarnings parseMarkdown) def{ stateOptions = opts } (s ++ "\n\n") trimInlinesF :: F Inlines -> F Inlines trimInlinesF = liftM trimInlines @@ -114,6 +113,12 @@ isBlank _ = False -- auxiliary functions -- +-- | Succeeds when we're in list context. +inList :: MarkdownParser () +inList = do + ctx <- stateParserContext <$> getState + guard (ctx == ListItemState) + isNull :: F Inlines -> Bool isNull ils = B.isNull $ runF ils def @@ -138,14 +143,16 @@ nonindentSpaces = do then return sps else unexpected "indented line" -skipNonindentSpaces :: MarkdownParser () +-- returns number of spaces parsed +skipNonindentSpaces :: MarkdownParser Int skipNonindentSpaces = do tabStop <- getOption readerTabStop - atMostSpaces (tabStop - 1) + atMostSpaces (tabStop - 1) <* notFollowedBy (char ' ') -atMostSpaces :: Int -> MarkdownParser () -atMostSpaces 0 = notFollowedBy (char ' ') -atMostSpaces n = (char ' ' >> atMostSpaces (n-1)) <|> return () +atMostSpaces :: Int -> MarkdownParser Int +atMostSpaces n + | n > 0 = (char ' ' >> (+1) <$> atMostSpaces (n-1)) <|> return 0 + | otherwise = return 0 litChar :: MarkdownParser Char litChar = escapedChar' @@ -283,7 +290,11 @@ toMetaValue opts x = yamlToMeta :: ReaderOptions -> Yaml.Value -> MetaValue yamlToMeta opts (Yaml.String t) = toMetaValue opts t -yamlToMeta _ (Yaml.Number n) = MetaString $ show n +yamlToMeta _ (Yaml.Number n) + -- avoid decimal points for numbers that don't need them: + | base10Exponent n >= 0 = MetaString $ show + $ coefficient n * (10 ^ base10Exponent n) + | otherwise = MetaString $ show n yamlToMeta _ (Yaml.Bool b) = MetaBool b yamlToMeta opts (Yaml.Array xs) = B.toMetaValue $ map (yamlToMeta opts) $ V.toList xs @@ -328,12 +339,6 @@ parseMarkdown = do let Pandoc _ bs = B.doc $ runF blocks st return $ Pandoc meta bs -addWarning :: Maybe SourcePos -> String -> MarkdownParser () -addWarning mbpos msg = - updateState $ \st -> st{ - stateWarnings = (msg ++ maybe "" (\pos -> " " ++ show pos) mbpos) : - stateWarnings st } - referenceKey :: MarkdownParser (F Blocks) referenceKey = try $ do pos <- getPosition @@ -342,19 +347,16 @@ referenceKey = try $ do char ':' skipSpaces >> optional newline >> skipSpaces >> notFollowedBy (char '[') let sourceURL = liftM unwords $ many $ try $ do - notFollowedBy' referenceTitle - skipMany spaceChar - optional $ newline >> notFollowedBy blankline skipMany spaceChar + notFollowedBy' referenceTitle notFollowedBy' (() <$ reference) many1 $ notFollowedBy space >> litChar - let betweenAngles = try $ char '<' >> - manyTill (escapedChar' <|> litChar) (char '>') + let betweenAngles = try $ char '<' >> manyTill litChar (char '>') src <- try betweenAngles <|> sourceURL tit <- option "" referenceTitle -- currently we just ignore MMD-style link/image attributes _kvs <- option [] $ guardEnabled Ext_link_attributes - >> many (spnl >> keyValAttr) + >> many (try $ spnl >> keyValAttr) blanklines let target = (escapeURI $ trimr src, tit) st <- getState @@ -440,7 +442,10 @@ parseBlocks :: MarkdownParser (F Blocks) parseBlocks = mconcat <$> manyTill block eof block :: MarkdownParser (F Blocks) -block = choice [ mempty <$ blanklines +block = do + tr <- getOption readerTrace + pos <- getPosition + res <- choice [ mempty <$ blanklines , codeBlockFenced , yamlMetaBlock , guardEnabled Ext_latex_macros *> (macro >>= return . return) @@ -465,6 +470,11 @@ block = choice [ mempty <$ blanklines , para , plain ] <?> "block" + when tr $ do + st <- getState + trace (printf "line %d: %s" (sourceLine pos) + (take 60 $ show $ B.toList $ runF res st)) (return ()) + return res -- -- header blocks @@ -558,7 +568,7 @@ attributes :: MarkdownParser Attr attributes = try $ do char '{' spnl - attrs <- many (attribute >>~ spnl) + attrs <- many (attribute <* spnl) char '}' return $ foldl (\x f -> f x) nullAttr attrs @@ -605,12 +615,19 @@ codeBlockFenced = try $ do skipMany spaceChar attr <- option ([],[],[]) $ try (guardEnabled Ext_fenced_code_attributes >> attributes) - <|> ((\x -> ("",[x],[])) <$> identifier) + <|> ((\x -> ("",[toLanguageId x],[])) <$> many1 nonspaceChar) blankline contents <- manyTill anyLine (blockDelimiter (== c) (Just size)) blanklines return $ return $ B.codeBlockWith attr $ intercalate "\n" contents +-- correctly handle github language identifiers +toLanguageId :: String -> String +toLanguageId = map toLower . go + where go "c++" = "cpp" + go "objective-c" = "objectivec" + go x = x + codeBlockIndented :: MarkdownParser (F Blocks) codeBlockIndented = do contents <- many1 (indentedLine <|> @@ -668,7 +685,7 @@ birdTrackLine c = try $ do -- emailBlockQuoteStart :: MarkdownParser Char -emailBlockQuoteStart = try $ skipNonindentSpaces >> char '>' >>~ optional (char ' ') +emailBlockQuoteStart = try $ skipNonindentSpaces >> char '>' <* optional (char ' ') emailBlockQuote :: MarkdownParser [String] emailBlockQuote = try $ do @@ -698,54 +715,64 @@ blockQuote = do bulletListStart :: MarkdownParser () bulletListStart = try $ do optional newline -- if preceded by a Plain block in a list context + startpos <- sourceColumn <$> getPosition skipNonindentSpaces notFollowedBy' (() <$ hrule) -- because hrules start out just like lists satisfy isBulletListMarker - spaceChar <|> lookAhead newline - skipSpaces + endpos <- sourceColumn <$> getPosition + tabStop <- getOption readerTabStop + lookAhead (newline <|> spaceChar) + () <$ atMostSpaces (tabStop - (endpos - startpos)) anyOrderedListStart :: MarkdownParser (Int, ListNumberStyle, ListNumberDelim) anyOrderedListStart = try $ do optional newline -- if preceded by a Plain block in a list context + startpos <- sourceColumn <$> getPosition skipNonindentSpaces notFollowedBy $ string "p." >> spaceChar >> digit -- page number - (guardDisabled Ext_fancy_lists >> - do many1 digit - char '.' - spaceChar - return (1, DefaultStyle, DefaultDelim)) - <|> do (num, style, delim) <- anyOrderedListMarker - -- if it could be an abbreviated first name, insist on more than one space - if delim == Period && (style == UpperAlpha || (style == UpperRoman && - num `elem` [1, 5, 10, 50, 100, 500, 1000])) - then char '\t' <|> (try $ char ' ' >> spaceChar) - else spaceChar - skipSpaces - return (num, style, delim) + res <- do guardDisabled Ext_fancy_lists + start <- many1 digit >>= safeRead + char '.' + return (start, DefaultStyle, DefaultDelim) + <|> do (num, style, delim) <- anyOrderedListMarker + -- if it could be an abbreviated first name, + -- insist on more than one space + when (delim == Period && (style == UpperAlpha || + (style == UpperRoman && + num `elem` [1, 5, 10, 50, 100, 500, 1000]))) $ + () <$ spaceChar + return (num, style, delim) + endpos <- sourceColumn <$> getPosition + tabStop <- getOption readerTabStop + lookAhead (newline <|> spaceChar) + atMostSpaces (tabStop - (endpos - startpos)) + return res listStart :: MarkdownParser () listStart = bulletListStart <|> (anyOrderedListStart >> return ()) --- parse a line of a list item (start = parser for beginning of list item) listLine :: MarkdownParser String listLine = try $ do notFollowedBy' (do indentSpaces many spaceChar listStart) - notFollowedBy' $ htmlTag (~== TagClose "div") - chunks <- manyTill + notFollowedByHtmlCloser + optional (() <$ indentSpaces) + listLineCommon + +listLineCommon :: MarkdownParser String +listLineCommon = concat <$> manyTill ( many1 (satisfy $ \c -> c /= '\n' && c /= '<') <|> liftM snd (htmlTag isCommentTag) <|> count 1 anyChar ) newline - return $ concat chunks -- parse raw text for one list item, excluding start marker and continuations rawListItem :: MarkdownParser a -> MarkdownParser String rawListItem start = try $ do start - first <- listLine + first <- listLineCommon rest <- many (notFollowedBy listStart >> notFollowedBy blankline >> listLine) blanks <- many blankline return $ unlines (first:rest) ++ blanks @@ -760,11 +787,18 @@ listContinuation = try $ do blanks <- many blankline return $ concat result ++ blanks +notFollowedByHtmlCloser :: MarkdownParser () +notFollowedByHtmlCloser = do + inHtmlBlock <- stateInHtmlBlock <$> getState + case inHtmlBlock of + Just t -> notFollowedBy' $ htmlTag (~== TagClose t) + Nothing -> return () + listContinuationLine :: MarkdownParser String listContinuationLine = try $ do notFollowedBy blankline notFollowedBy' listStart - notFollowedBy' $ htmlTag (~== TagClose "div") + notFollowedByHtmlCloser optional indentSpaces result <- anyLine return $ result ++ "\n" @@ -796,8 +830,14 @@ orderedList = try $ do items <- fmap sequence $ many1 $ listItem ( try $ do optional newline -- if preceded by Plain block in a list + startpos <- sourceColumn <$> getPosition skipNonindentSpaces - orderedListMarker style delim ) + res <- orderedListMarker style delim + endpos <- sourceColumn <$> getPosition + tabStop <- getOption readerTabStop + lookAhead (newline <|> spaceChar) + atMostSpaces (tabStop - (endpos - startpos)) + return res ) start' <- option 1 $ guardEnabled Ext_startnum >> return start return $ B.orderedListWith (start', style, delim) <$> fmap compactify' items @@ -819,53 +859,52 @@ defListMarker = do else mzero return () -definitionListItem :: MarkdownParser (F (Inlines, [Blocks])) -definitionListItem = try $ do - -- first, see if this has any chance of being a definition list: - lookAhead (anyLine >> optional blankline >> defListMarker) - term <- trimInlinesF . mconcat <$> manyTill inline newline - optional blankline - raw <- many1 defRawBlock - state <- getState - let oldContext = stateParserContext state - -- parse the extracted block, which may contain various block elements: +definitionListItem :: Bool -> MarkdownParser (F (Inlines, [Blocks])) +definitionListItem compact = try $ do + rawLine' <- anyLine + raw <- many1 $ defRawBlock compact + term <- parseFromString (trimInlinesF . mconcat <$> many inline) rawLine' contents <- mapM (parseFromString parseBlocks) raw - updateState (\st -> st {stateParserContext = oldContext}) + optional blanklines return $ liftM2 (,) term (sequence contents) -defRawBlock :: MarkdownParser String -defRawBlock = try $ do +defRawBlock :: Bool -> MarkdownParser String +defRawBlock compact = try $ do + hasBlank <- option False $ blankline >> return True defListMarker firstline <- anyLine - rawlines <- many (notFollowedBy blankline >> indentSpaces >> anyLine) - trailing <- option "" blanklines - cont <- liftM concat $ many $ do - lns <- many1 $ notFollowedBy blankline >> indentSpaces >> anyLine - trl <- option "" blanklines - return $ unlines lns ++ trl - return $ firstline ++ "\n" ++ unlines rawlines ++ trailing ++ cont + let dline = try + ( do notFollowedBy blankline + if compact -- laziness not compatible with compact + then () <$ indentSpaces + else (() <$ indentSpaces) + <|> notFollowedBy defListMarker + anyLine ) + rawlines <- many dline + cont <- liftM concat $ many $ try $ do + trailing <- option "" blanklines + ln <- indentSpaces >> notFollowedBy blankline >> anyLine + lns <- many dline + return $ trailing ++ unlines (ln:lns) + return $ trimr (firstline ++ "\n" ++ unlines rawlines ++ cont) ++ + if hasBlank || not (null cont) then "\n\n" else "" definitionList :: MarkdownParser (F Blocks) -definitionList = do - guardEnabled Ext_definition_lists - items <- fmap sequence $ many1 definitionListItem +definitionList = try $ do + lookAhead (anyLine >> optional blankline >> defListMarker) + compactDefinitionList <|> normalDefinitionList + +compactDefinitionList :: MarkdownParser (F Blocks) +compactDefinitionList = do + guardEnabled Ext_compact_definition_lists + items <- fmap sequence $ many1 $ definitionListItem True return $ B.definitionList <$> fmap compactify'DL items -compactify'DL :: [(Inlines, [Blocks])] -> [(Inlines, [Blocks])] -compactify'DL items = - let defs = concatMap snd items - defBlocks = reverse $ concatMap B.toList defs - isPara (Para _) = True - isPara _ = False - in case defBlocks of - (Para x:_) -> if not $ any isPara (drop 1 defBlocks) - then let (t,ds) = last items - lastDef = B.toList $ last ds - ds' = init ds ++ - [B.fromList $ init lastDef ++ [Plain x]] - in init items ++ [(t, ds')] - else items - _ -> items +normalDefinitionList :: MarkdownParser (F Blocks) +normalDefinitionList = do + guardEnabled Ext_definition_lists + items <- fmap sequence $ many1 $ definitionListItem False + return $ B.definitionList <$> items -- -- paragraph block @@ -883,7 +922,15 @@ para = try $ do <|> (guardEnabled Ext_backtick_code_blocks >> () <$ lookAhead codeBlockFenced) <|> (guardDisabled Ext_blank_before_header >> () <$ lookAhead header) <|> (guardEnabled Ext_lists_without_preceding_blankline >> + -- Avoid creating a paragraph in a nested list. + notFollowedBy' inList >> () <$ lookAhead listStart) + <|> do guardEnabled Ext_native_divs + inHtmlBlock <- stateInHtmlBlock <$> getState + case inHtmlBlock of + Just "div" -> () <$ + lookAhead (htmlTag (~== TagClose "div")) + _ -> mzero return $ do result' <- result case B.toList result' of @@ -909,16 +956,34 @@ htmlElement = rawVerbatimBlock htmlBlock :: MarkdownParser (F Blocks) htmlBlock = do guardEnabled Ext_raw_html - res <- (guardEnabled Ext_markdown_in_html_blocks >> rawHtmlBlocks) - <|> htmlBlock' - return $ return $ B.rawBlock "html" res - -htmlBlock' :: MarkdownParser String + try (do + (TagOpen t attrs) <- lookAhead $ fst <$> htmlTag isBlockTag + (guard (t `elem` ["pre","style","script"]) >> + (return . B.rawBlock "html") <$> rawVerbatimBlock) + <|> (do guardEnabled Ext_markdown_attribute + oldMarkdownAttribute <- stateMarkdownAttribute <$> getState + markdownAttribute <- + case lookup "markdown" attrs of + Just "0" -> False <$ updateState (\st -> st{ + stateMarkdownAttribute = False }) + Just _ -> True <$ updateState (\st -> st{ + stateMarkdownAttribute = True }) + Nothing -> return oldMarkdownAttribute + res <- if markdownAttribute + then rawHtmlBlocks + else htmlBlock' + updateState $ \st -> st{ stateMarkdownAttribute = + oldMarkdownAttribute } + return res) + <|> (guardEnabled Ext_markdown_in_html_blocks >> rawHtmlBlocks)) + <|> htmlBlock' + +htmlBlock' :: MarkdownParser (F Blocks) htmlBlock' = try $ do first <- htmlElement - finalSpace <- many spaceChar - finalNewlines <- many newline - return $ first ++ finalSpace ++ finalNewlines + skipMany spaceChar + optional blanklines + return $ return $ B.rawBlock "html" first strictHtmlBlock :: MarkdownParser String strictHtmlBlock = htmlInBalanced (not . isInlineTag) @@ -929,46 +994,36 @@ rawVerbatimBlock = try $ do ["pre", "style", "script"]) (const True)) contents <- manyTill anyChar (htmlTag (~== TagClose tag)) - return $ open ++ contents ++ renderTags [TagClose tag] + return $ open ++ contents ++ renderTags' [TagClose tag] rawTeXBlock :: MarkdownParser (F Blocks) rawTeXBlock = do guardEnabled Ext_raw_tex - result <- (B.rawBlock "latex" <$> rawLaTeXBlock) - <|> (B.rawBlock "context" <$> rawConTeXtEnvironment) + result <- (B.rawBlock "latex" . concat <$> + rawLaTeXBlock `sepEndBy1` blankline) + <|> (B.rawBlock "context" . concat <$> + rawConTeXtEnvironment `sepEndBy1` blankline) spaces return $ return result -rawHtmlBlocks :: MarkdownParser String +rawHtmlBlocks :: MarkdownParser (F Blocks) rawHtmlBlocks = do - htmlBlocks <- many1 $ try $ do - s <- rawVerbatimBlock <|> try ( - do (t,raw) <- htmlTag isBlockTag - exts <- getOption readerExtensions - -- if open tag, need markdown="1" if - -- markdown_attributes extension is set - case t of - TagOpen _ as - | Ext_markdown_attribute `Set.member` - exts -> - if "markdown" `notElem` - map fst as - then mzero - else return $ - stripMarkdownAttribute raw - | otherwise -> return raw - _ -> return raw ) - sps <- do sp1 <- many spaceChar - sp2 <- option "" (blankline >> return "\n") - sp3 <- many spaceChar - sp4 <- option "" blanklines - return $ sp1 ++ sp2 ++ sp3 ++ sp4 - -- note: we want raw html to be able to - -- precede a code block, when separated - -- by a blank line - return $ s ++ sps - let combined = concat htmlBlocks - return $ if last combined == '\n' then init combined else combined + (TagOpen tagtype _, raw) <- htmlTag isBlockTag + -- try to find closing tag + -- we set stateInHtmlBlock so that closing tags that can be either block or + -- inline will not be parsed as inline tags + oldInHtmlBlock <- stateInHtmlBlock <$> getState + updateState $ \st -> st{ stateInHtmlBlock = Just tagtype } + let closer = htmlTag (\x -> x ~== TagClose tagtype) + contents <- mconcat <$> many (notFollowedBy' closer >> block) + result <- + (closer >>= \(_, rawcloser) -> return ( + return (B.rawBlock "html" $ stripMarkdownAttribute raw) <> + contents <> + return (B.rawBlock "html" rawcloser))) + <|> return (return (B.rawBlock "html" raw) <> contents) + updateState $ \st -> st{ stateInHtmlBlock = oldInHtmlBlock } + return result -- remove markdown="1" attribute stripMarkdownAttribute :: String -> String @@ -1110,13 +1165,11 @@ multilineTable headless = multilineTableHeader :: Bool -- ^ Headerless table -> MarkdownParser (F [Blocks], [Alignment], [Int]) multilineTableHeader headless = try $ do - if headless - then return '\n' - else tableSep >>~ notFollowedBy blankline + unless headless $ + tableSep >> notFollowedBy blankline rawContent <- if headless then return $ repeat "" - else many1 - (notFollowedBy tableSep >> many1Till anyChar newline) + else many1 $ notFollowedBy tableSep >> anyLine initSp <- nonindentSpaces dashes <- many1 (dashedLine '-') newline @@ -1158,7 +1211,7 @@ gridPart ch = do return (length dashes, length dashes + 1) gridDashedLines :: Char -> Parser [Char] st [(Int,Int)] -gridDashedLines ch = try $ char '+' >> many1 (gridPart ch) >>~ blankline +gridDashedLines ch = try $ char '+' >> many1 (gridPart ch) <* blankline removeFinalBar :: String -> String removeFinalBar = @@ -1220,11 +1273,20 @@ removeOneLeadingSpace xs = gridTableFooter :: MarkdownParser [Char] gridTableFooter = blanklines +pipeBreak :: MarkdownParser [Alignment] +pipeBreak = try $ do + nonindentSpaces + openPipe <- (True <$ char '|') <|> return False + first <- pipeTableHeaderPart + rest <- many $ sepPipe *> pipeTableHeaderPart + -- surrounding pipes needed for a one-column table: + guard $ not (null rest && not openPipe) + optional (char '|') + blankline + return (first:rest) + pipeTable :: MarkdownParser ([Alignment], [Double], F [Blocks], F [[Blocks]]) pipeTable = try $ do - let pipeBreak = nonindentSpaces *> optional (char '|') *> - pipeTableHeaderPart `sepBy1` sepPipe <* - optional (char '|') <* blankline (heads,aligns) <- try ( pipeBreak >>= \als -> return (return $ replicate (length als) mempty, als)) <|> ( pipeTableRow >>= \row -> pipeBreak >>= \als -> @@ -1243,12 +1305,13 @@ sepPipe = try $ do pipeTableRow :: MarkdownParser (F [Blocks]) pipeTableRow = do nonindentSpaces - optional (char '|') + openPipe <- (True <$ char '|') <|> return False let cell = mconcat <$> many (notFollowedBy (blankline <|> char '|') >> inline) first <- cell - sepPipe - rest <- cell `sepBy1` sepPipe + rest <- many $ sepPipe *> cell + -- surrounding pipes needed for a one-column table: + guard $ not (null rest && not openPipe) optional (char '|') blankline let cells = sequence (first:rest) @@ -1373,8 +1436,7 @@ escapedChar = do ltSign :: MarkdownParser (F Inlines) ltSign = do guardDisabled Ext_raw_html - <|> guardDisabled Ext_markdown_in_html_blocks - <|> (notFollowedBy' rawHtmlBlocks >> return ()) + <|> (notFollowedByHtmlCloser >> notFollowedBy' (htmlTag isBlockTag)) char '<' return $ return $ B.str "<" @@ -1419,54 +1481,60 @@ math = (return . B.displayMath <$> (mathDisplay >>= applyMacros')) enclosure :: Char -> MarkdownParser (F Inlines) enclosure c = do + -- we can't start an enclosure with _ if after a string and + -- the intraword_underscores extension is enabled: + guardDisabled Ext_intraword_underscores + <|> guard (c == '*') + <|> (guard =<< notAfterString) cs <- many1 (char c) (return (B.str cs) <>) <$> whitespace - <|> case length cs of + <|> do + case length cs of 3 -> three c 2 -> two c mempty 1 -> one c mempty _ -> return (return $ B.str cs) +ender :: Char -> Int -> MarkdownParser () +ender c n = try $ do + count n (char c) + guard (c == '*') + <|> guardDisabled Ext_intraword_underscores + <|> notFollowedBy alphaNum + -- Parse inlines til you hit one c or a sequence of two cs. -- If one c, emit emph and then parse two. -- If two cs, emit strong and then parse one. -- Otherwise, emit ccc then the results. three :: Char -> MarkdownParser (F Inlines) three c = do - contents <- mconcat <$> many (notFollowedBy (char c) >> inline) - (try (string [c,c,c]) >> return ((B.strong . B.emph) <$> contents)) - <|> (try (string [c,c]) >> one c (B.strong <$> contents)) - <|> (char c >> two c (B.emph <$> contents)) + contents <- mconcat <$> many (notFollowedBy (ender c 1) >> inline) + (ender c 3 >> return ((B.strong . B.emph) <$> contents)) + <|> (ender c 2 >> one c (B.strong <$> contents)) + <|> (ender c 1 >> two c (B.emph <$> contents)) <|> return (return (B.str [c,c,c]) <> contents) -- Parse inlines til you hit two c's, and emit strong. -- If you never do hit two cs, emit ** plus inlines parsed. two :: Char -> F Inlines -> MarkdownParser (F Inlines) two c prefix' = do - let ender = try $ string [c,c] - contents <- mconcat <$> many (try $ notFollowedBy ender >> inline) - (ender >> return (B.strong <$> (prefix' <> contents))) + contents <- mconcat <$> many (try $ notFollowedBy (ender c 2) >> inline) + (ender c 2 >> return (B.strong <$> (prefix' <> contents))) <|> return (return (B.str [c,c]) <> (prefix' <> contents)) -- Parse inlines til you hit a c, and emit emph. -- If you never hit a c, emit * plus inlines parsed. one :: Char -> F Inlines -> MarkdownParser (F Inlines) one c prefix' = do - contents <- mconcat <$> many ( (notFollowedBy (char c) >> inline) + contents <- mconcat <$> many ( (notFollowedBy (ender c 1) >> inline) <|> try (string [c,c] >> - notFollowedBy (char c) >> + notFollowedBy (ender c 1) >> two c mempty) ) - (char c >> return (B.emph <$> (prefix' <> contents))) + (ender c 1 >> return (B.emph <$> (prefix' <> contents))) <|> return (return (B.str [c]) <> (prefix' <> contents)) strongOrEmph :: MarkdownParser (F Inlines) -strongOrEmph = enclosure '*' <|> (checkIntraword >> enclosure '_') - where checkIntraword = do - exts <- getOption readerExtensions - when (Ext_intraword_underscores `Set.member` exts) $ do - pos <- getPosition - lastStrPos <- stateLastStrPos <$> getState - guard $ lastStrPos /= Just pos +strongOrEmph = enclosure '*' <|> enclosure '_' -- | Parses a list of inlines between start and end delimiters. inlinesBetween :: (Show b) @@ -1476,7 +1544,7 @@ inlinesBetween :: (Show b) inlinesBetween start end = (trimInlinesF . mconcat) <$> try (start >> many1Till inner end) where inner = innerSpace <|> (notFollowedBy' (() <$ whitespace) >> inline) - innerSpace = try $ whitespace >>~ notFollowedBy' end + innerSpace = try $ whitespace <* notFollowedBy' end strikeout :: MarkdownParser (F Inlines) strikeout = fmap B.strikeout <$> @@ -1508,8 +1576,7 @@ nonEndline = satisfy (/='\n') str :: MarkdownParser (F Inlines) str = do result <- many1 alphaNum - pos <- getPosition - updateState $ \s -> s{ stateLastStrPos = Just pos } + updateLastStrPos let spacesToNbr = map (\c -> if c == ' ' then '\160' else c) isSmart <- getOption readerSmart if isSmart @@ -1541,14 +1608,15 @@ endline = try $ do newline notFollowedBy blankline -- parse potential list-starts differently if in a list: - st <- getState - when (stateParserContext st == ListItemState) $ notFollowedBy listStart + notFollowedBy (inList >> listStart) guardDisabled Ext_lists_without_preceding_blankline <|> notFollowedBy listStart guardEnabled Ext_blank_before_blockquote <|> notFollowedBy emailBlockQuoteStart guardEnabled Ext_blank_before_header <|> notFollowedBy (char '#') -- atx header - guardEnabled Ext_backtick_code_blocks >> + guardDisabled Ext_backtick_code_blocks <|> notFollowedBy (() <$ (lookAhead (char '`') >> codeBlockFenced)) - (guardEnabled Ext_hard_line_breaks >> return (return B.linebreak)) + notFollowedByHtmlCloser + (eof >> return mempty) + <|> (guardEnabled Ext_hard_line_breaks >> return (return B.linebreak)) <|> (guardEnabled Ext_ignore_line_breaks >> return mempty) <|> (return $ return B.space) @@ -1571,8 +1639,10 @@ source :: MarkdownParser (String, String) source = do char '(' skipSpaces - let urlChunk = try $ notFollowedBy (oneOf "\"')") >> - (parenthesizedChars <|> count 1 litChar) + let urlChunk = + try parenthesizedChars + <|> (notFollowedBy (oneOf " )") >> (count 1 litChar)) + <|> try (many1 spaceChar <* notFollowedBy (oneOf "\"')")) let sourceURL = (unwords . words . concat) <$> many urlChunk let betweenAngles = try $ char '<' >> manyTill litChar (char '>') @@ -1717,31 +1787,55 @@ inBrackets parser = do spanHtml :: MarkdownParser (F Inlines) spanHtml = try $ do - guardEnabled Ext_markdown_in_html_blocks + guardEnabled Ext_native_spans (TagOpen _ attrs, _) <- htmlTag (~== TagOpen "span" []) contents <- mconcat <$> manyTill inline (htmlTag (~== TagClose "span")) let ident = fromMaybe "" $ lookup "id" attrs let classes = maybe [] words $ lookup "class" attrs let keyvals = [(k,v) | (k,v) <- attrs, k /= "id" && k /= "class"] - return $ B.spanWith (ident, classes, keyvals) <$> contents + case lookup "style" keyvals of + Just s | null ident && null classes && + map toLower (filter (`notElem` " \t;") s) == + "font-variant:small-caps" + -> return $ B.smallcaps <$> contents + _ -> return $ B.spanWith (ident, classes, keyvals) <$> contents divHtml :: MarkdownParser (F Blocks) divHtml = try $ do - guardEnabled Ext_markdown_in_html_blocks - (TagOpen _ attrs, _) <- htmlTag (~== TagOpen "div" []) - contents <- mconcat <$> manyTill block (htmlTag (~== TagClose "div")) - let ident = fromMaybe "" $ lookup "id" attrs - let classes = maybe [] words $ lookup "class" attrs - let keyvals = [(k,v) | (k,v) <- attrs, k /= "id" && k /= "class"] - return $ B.divWith (ident, classes, keyvals) <$> contents + guardEnabled Ext_native_divs + (TagOpen _ attrs, rawtag) <- htmlTag (~== TagOpen "div" []) + -- we set stateInHtmlBlock so that closing tags that can be either block or + -- inline will not be parsed as inline tags + oldInHtmlBlock <- stateInHtmlBlock <$> getState + updateState $ \st -> st{ stateInHtmlBlock = Just "div" } + bls <- option "" (blankline >> option "" blanklines) + contents <- mconcat <$> + many (notFollowedBy' (htmlTag (~== TagClose "div")) >> block) + closed <- option False (True <$ htmlTag (~== TagClose "div")) + if closed + then do + updateState $ \st -> st{ stateInHtmlBlock = oldInHtmlBlock } + let ident = fromMaybe "" $ lookup "id" attrs + let classes = maybe [] words $ lookup "class" attrs + let keyvals = [(k,v) | (k,v) <- attrs, k /= "id" && k /= "class"] + return $ B.divWith (ident, classes, keyvals) <$> contents + else -- avoid backtracing + return $ return (B.rawBlock "html" (rawtag <> bls)) <> contents rawHtmlInline :: MarkdownParser (F Inlines) rawHtmlInline = do guardEnabled Ext_raw_html + inHtmlBlock <- stateInHtmlBlock <$> getState + let isCloseBlockTag t = case inHtmlBlock of + Just t' -> t ~== TagClose t' + Nothing -> False mdInHtml <- option False $ - guardEnabled Ext_markdown_in_html_blocks >> return True + ( guardEnabled Ext_markdown_in_html_blocks + <|> guardEnabled Ext_markdown_attribute + ) >> return True (_,result) <- htmlTag $ if mdInHtml - then isInlineTag + then (\x -> isInlineTag x && + not (isCloseBlockTag x)) else not . isTextTag return $ return $ B.rawInline "html" result @@ -1800,22 +1894,6 @@ normalCite = try $ do char ']' return citations -citeKey :: MarkdownParser (Bool, String) -citeKey = try $ do - -- make sure we're not right after an alphanumeric, - -- since foo@bar.baz is probably an email address - lastStrPos <- stateLastStrPos <$> getState - pos <- getPosition - guard $ lastStrPos /= Just pos - suppress_author <- option False (char '-' >> return True) - char '@' - first <- letter <|> char '_' - let regchar = satisfy (\c -> isAlphaNum c || c == '_') - let internal p = try $ p >>~ lookAhead regchar - rest <- many $ regchar <|> internal (oneOf ":.#$%&-+?<>~/") - let key = first:rest - return (suppress_author, key) - suffix :: MarkdownParser (F Inlines) suffix = try $ do hasSpace <- option False (notFollowedBy nonspaceChar >> return True) @@ -1854,7 +1932,7 @@ smart :: MarkdownParser (F Inlines) smart = do getOption readerSmart >>= guard doubleQuoted <|> singleQuoted <|> - choice (map (return . B.singleton <$>) [apostrophe, dash, ellipses]) + choice (map (return <$>) [apostrophe, dash, ellipses]) singleQuoted :: MarkdownParser (F Inlines) singleQuoted = try $ do @@ -1873,4 +1951,3 @@ doubleQuoted = try $ do (withQuoteContext InDoubleQuote $ doubleQuoteEnd >> return (fmap B.doubleQuoted . trimInlinesF $ contents)) <|> (return $ return (B.str "\8220") <> contents) - diff --git a/src/Text/Pandoc/Readers/MediaWiki.hs b/src/Text/Pandoc/Readers/MediaWiki.hs index 794890eb6..e43b8a86c 100644 --- a/src/Text/Pandoc/Readers/MediaWiki.hs +++ b/src/Text/Pandoc/Readers/MediaWiki.hs @@ -1,7 +1,7 @@ {-# LANGUAGE RelaxedPolyRec, FlexibleInstances, TypeSynonymInstances #-} -- RelaxedPolyRec needed for inlinesBetween on GHC < 7 {- - Copyright (C) 2012 John MacFarlane <jgm@berkeley.edu> + Copyright (C) 2012-2014 John MacFarlane <jgm@berkeley.edu> This program is free software; you can redistribute it and/or modify it under the terms of the GNU General Public License as published by @@ -20,7 +20,7 @@ Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA {- | Module : Text.Pandoc.Readers.MediaWiki - Copyright : Copyright (C) 2012 John MacFarlane + Copyright : Copyright (C) 2012-2014 John MacFarlane License : GNU GPL, version 2 or above Maintainer : John MacFarlane <jgm@berkeley.edu> @@ -55,6 +55,8 @@ import qualified Data.Foldable as F import qualified Data.Map as M import Data.Char (isDigit, isSpace) import Data.Maybe (fromMaybe) +import Text.Printf (printf) +import Debug.Trace (trace) -- | Read mediawiki from an input string and return a Pandoc document. readMediaWiki :: ReaderOptions -- ^ Reader options @@ -82,16 +84,16 @@ data MWState = MWState { mwOptions :: ReaderOptions type MWParser = Parser [Char] MWState -instance HasReaderOptions MWParser where - askReaderOption f = (f . mwOptions) `fmap` getState +instance HasReaderOptions MWState where + extractReaderOptions = mwOptions -instance HasHeaderMap MWParser where - getHeaderMap = fmap mwHeaderMap getState - putHeaderMap hm = updateState $ \st -> st{ mwHeaderMap = hm } +instance HasHeaderMap MWState where + extractHeaderMap = mwHeaderMap + updateHeaderMap f st = st{ mwHeaderMap = f $ mwHeaderMap st } -instance HasIdentifierList MWParser where - getIdentifierList = fmap mwIdentifierList getState - putIdentifierList l = updateState $ \st -> st{ mwIdentifierList = l } +instance HasIdentifierList MWState where + extractIdentifierList = mwIdentifierList + updateIdentifierList f st = st{ mwIdentifierList = f $ mwIdentifierList st } -- -- auxiliary functions @@ -187,7 +189,10 @@ parseMediaWiki = do -- block :: MWParser Blocks -block = mempty <$ skipMany1 blankline +block = do + tr <- getOption readerTrace + pos <- getPosition + res <- mempty <$ skipMany1 blankline <|> table <|> header <|> hrule @@ -199,6 +204,10 @@ block = mempty <$ skipMany1 blankline <|> blockTag <|> (B.rawBlock "mediawiki" <$> template) <|> para + when tr $ + trace (printf "line %d: %s" (sourceLine pos) + (take 60 $ show $ B.toList res)) (return ()) + return res para :: MWParser Blocks para = do @@ -227,6 +236,7 @@ table = do let widths' = map (\w -> if w == 0 then defaultwidth else w) widths let cellspecs = zip (map fst cellspecs') widths' rows' <- many $ try $ rowsep *> (map snd <$> tableRow) + optional blanklines tableEnd let cols = length hdr let (headers,rows) = if hasheader @@ -275,7 +285,7 @@ tableCaption = try $ do (trimInlines . mconcat) <$> many (notFollowedBy (cellsep <|> rowsep) *> inline) tableRow :: MWParser [((Alignment, Double), Blocks)] -tableRow = try $ many tableCell +tableRow = try $ skipMany htmlComment *> many tableCell tableCell :: MWParser ((Alignment, Double), Blocks) tableCell = try $ do @@ -307,6 +317,7 @@ template :: MWParser String template = try $ do string "{{" notFollowedBy (char '{') + lookAhead $ letter <|> digit <|> char ':' let chunk = template <|> variable <|> many1 (noneOf "{}") <|> count 1 anyChar contents <- manyTill chunk (try $ string "}}") return $ "{{" ++ concat contents ++ "}}" @@ -438,7 +449,8 @@ listItem c = try $ do skipMany spaceChar first <- concat <$> manyTill listChunk newline rest <- many - (try $ string extras *> (concat <$> manyTill listChunk newline)) + (try $ string extras *> lookAhead listStartChar *> + (concat <$> manyTill listChunk newline)) contents <- parseFromString (many1 $ listItem' c) (unlines (first : rest)) case c of @@ -555,10 +567,15 @@ endline = () <$ try (newline <* notFollowedBy' header <* notFollowedBy anyListStart) +imageIdentifiers :: [MWParser ()] +imageIdentifiers = [sym (identifier ++ ":") | identifier <- identifiers] + where identifiers = ["File", "Image", "Archivo", "Datei", "Fichier", + "Bild"] + image :: MWParser Inlines image = try $ do sym "[[" - sym "File:" <|> sym "Image:" + choice imageIdentifiers fname <- many1 (noneOf "|]") _ <- many (try $ char '|' *> imageOption) caption <- (B.str fname <$ sym "]]") @@ -618,7 +635,7 @@ inlinesBetween :: (Show b) => MWParser a -> MWParser b -> MWParser Inlines inlinesBetween start end = (trimInlines . mconcat) <$> try (start >> many1Till inner end) where inner = innerSpace <|> (notFollowedBy' (() <$ whitespace) >> inline) - innerSpace = try $ whitespace >>~ notFollowedBy' end + innerSpace = try $ whitespace <* notFollowedBy' end emph :: MWParser Inlines emph = B.emph <$> nested (inlinesBetween start end) diff --git a/src/Text/Pandoc/Readers/Native.hs b/src/Text/Pandoc/Readers/Native.hs index c5d4cb98a..f4dfa62c1 100644 --- a/src/Text/Pandoc/Readers/Native.hs +++ b/src/Text/Pandoc/Readers/Native.hs @@ -1,5 +1,5 @@ {- -Copyright (C) 2011 John MacFarlane <jgm@berkeley.edu> +Copyright (C) 2011-2014 John MacFarlane <jgm@berkeley.edu> This program is free software; you can redistribute it and/or modify it under the terms of the GNU General Public License as published by @@ -18,7 +18,7 @@ Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA {- | Module : Text.Pandoc.Readers.Native - Copyright : Copyright (C) 2011 John MacFarlane + Copyright : Copyright (C) 2011-2014 John MacFarlane License : GNU GPL, version 2 or above Maintainer : John MacFarlane <jgm@berkeley.edu> diff --git a/src/Text/Pandoc/Readers/Org.hs b/src/Text/Pandoc/Readers/Org.hs new file mode 100644 index 000000000..440b6d144 --- /dev/null +++ b/src/Text/Pandoc/Readers/Org.hs @@ -0,0 +1,1487 @@ +{-# LANGUAGE OverloadedStrings #-} +{-# LANGUAGE GeneralizedNewtypeDeriving #-} +{- +Copyright (C) 2014 Albert Krewinkel <tarleb@moltkeplatz.de> + +This program is free software; you can redistribute it and/or modify +it under the terms of the GNU General Public License as published by +the Free Software Foundation; either version 2 of the License, or +(at your option) any later version. + +This program is distributed in the hope that it will be useful, +but WITHOUT ANY WARRANTY; without even the implied warranty of +MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the +GNU General Public License for more details. + +You should have received a copy of the GNU General Public License +along with this program; if not, write to the Free Software +Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA +-} + +{- | + Module : Text.Pandoc.Readers.Org + Copyright : Copyright (C) 2014 Albert Krewinkel + License : GNU GPL, version 2 or above + + Maintainer : Albert Krewinkel <tarleb@moltkeplatz.de> + +Conversion of org-mode formatted plain text to 'Pandoc' document. +-} +module Text.Pandoc.Readers.Org ( readOrg ) where + +import qualified Text.Pandoc.Builder as B +import Text.Pandoc.Builder ( Inlines, Blocks, HasMeta(..), (<>) + , trimInlines ) +import Text.Pandoc.Definition +import Text.Pandoc.Options +import qualified Text.Pandoc.Parsing as P +import Text.Pandoc.Parsing hiding ( F, unF, askF, asksF, runF + , newline, orderedListMarker + , parseFromString, blanklines + ) +import Text.Pandoc.Readers.LaTeX (inlineCommand, rawLaTeXInline) +import Text.Pandoc.Shared (compactify', compactify'DL) +import Text.TeXMath (readTeX, writePandoc, DisplayType(..)) +import qualified Text.TeXMath.Readers.MathML.EntityMap as MathMLEntityMap + +import Control.Applicative ( Applicative, pure + , (<$>), (<$), (<*>), (<*), (*>) ) +import Control.Arrow (first) +import Control.Monad (foldM, guard, liftM, liftM2, mplus, mzero, when) +import Control.Monad.Reader (Reader, runReader, ask, asks) +import Data.Char (isAlphaNum, toLower) +import Data.Default +import Data.List (intersperse, isPrefixOf, isSuffixOf) +import qualified Data.Map as M +import Data.Maybe (fromMaybe, isJust) +import Data.Monoid (Monoid, mconcat, mempty, mappend) +import Network.HTTP (urlEncode) + +-- | Parse org-mode string and return a Pandoc document. +readOrg :: ReaderOptions -- ^ Reader options + -> String -- ^ String to parse (assuming @'\n'@ line endings) + -> Pandoc +readOrg opts s = readWith parseOrg def{ orgStateOptions = opts } (s ++ "\n\n") + +type OrgParser = Parser [Char] OrgParserState + +parseOrg :: OrgParser Pandoc +parseOrg = do + blocks' <- parseBlocks + st <- getState + let meta = runF (orgStateMeta' st) st + let removeUnwantedBlocks = dropCommentTrees . filter (/= Null) + return $ Pandoc meta $ removeUnwantedBlocks (B.toList $ runF blocks' st) + +-- | Drop COMMENT headers and the document tree below those headers. +dropCommentTrees :: [Block] -> [Block] +dropCommentTrees [] = [] +dropCommentTrees blks@(b:bs) = + maybe blks (flip dropUntilHeaderAboveLevel bs) $ commentHeaderLevel b + +-- | Return the level of a header starting a comment tree and Nothing +-- otherwise. +commentHeaderLevel :: Block -> Maybe Int +commentHeaderLevel blk = + case blk of + (Header level _ ((Str "COMMENT"):_)) -> Just level + _ -> Nothing + +-- | Drop blocks until a header on or above the given level is seen +dropUntilHeaderAboveLevel :: Int -> [Block] -> [Block] +dropUntilHeaderAboveLevel n = dropWhile (not . isHeaderLevelLowerEq n) + +isHeaderLevelLowerEq :: Int -> Block -> Bool +isHeaderLevelLowerEq n blk = + case blk of + (Header level _ _) -> n >= level + _ -> False + +-- +-- Parser State for Org +-- + +type OrgNoteRecord = (String, F Blocks) +type OrgNoteTable = [OrgNoteRecord] + +type OrgBlockAttributes = M.Map String String + +type OrgLinkFormatters = M.Map String (String -> String) + +-- | Org-mode parser state +data OrgParserState = OrgParserState + { orgStateOptions :: ReaderOptions + , orgStateAnchorIds :: [String] + , orgStateBlockAttributes :: OrgBlockAttributes + , orgStateEmphasisCharStack :: [Char] + , orgStateEmphasisNewlines :: Maybe Int + , orgStateLastForbiddenCharPos :: Maybe SourcePos + , orgStateLastPreCharPos :: Maybe SourcePos + , orgStateLastStrPos :: Maybe SourcePos + , orgStateLinkFormatters :: OrgLinkFormatters + , orgStateMeta :: Meta + , orgStateMeta' :: F Meta + , orgStateNotes' :: OrgNoteTable + } + +instance HasReaderOptions OrgParserState where + extractReaderOptions = orgStateOptions + +instance HasMeta OrgParserState where + setMeta field val st = + st{ orgStateMeta = setMeta field val $ orgStateMeta st } + deleteMeta field st = + st{ orgStateMeta = deleteMeta field $ orgStateMeta st } + +instance HasLastStrPosition OrgParserState where + getLastStrPos = orgStateLastStrPos + setLastStrPos pos st = st{ orgStateLastStrPos = Just pos } + +instance Default OrgParserState where + def = defaultOrgParserState + +defaultOrgParserState :: OrgParserState +defaultOrgParserState = OrgParserState + { orgStateOptions = def + , orgStateAnchorIds = [] + , orgStateBlockAttributes = M.empty + , orgStateEmphasisCharStack = [] + , orgStateEmphasisNewlines = Nothing + , orgStateLastForbiddenCharPos = Nothing + , orgStateLastPreCharPos = Nothing + , orgStateLastStrPos = Nothing + , orgStateLinkFormatters = M.empty + , orgStateMeta = nullMeta + , orgStateMeta' = return nullMeta + , orgStateNotes' = [] + } + +recordAnchorId :: String -> OrgParser () +recordAnchorId i = updateState $ \s -> + s{ orgStateAnchorIds = i : (orgStateAnchorIds s) } + +addBlockAttribute :: String -> String -> OrgParser () +addBlockAttribute key val = updateState $ \s -> + let attrs = orgStateBlockAttributes s + in s{ orgStateBlockAttributes = M.insert key val attrs } + +lookupBlockAttribute :: String -> OrgParser (Maybe String) +lookupBlockAttribute key = + M.lookup key . orgStateBlockAttributes <$> getState + +resetBlockAttributes :: OrgParser () +resetBlockAttributes = updateState $ \s -> + s{ orgStateBlockAttributes = orgStateBlockAttributes def } + +updateLastForbiddenCharPos :: OrgParser () +updateLastForbiddenCharPos = getPosition >>= \p -> + updateState $ \s -> s{ orgStateLastForbiddenCharPos = Just p} + +updateLastPreCharPos :: OrgParser () +updateLastPreCharPos = getPosition >>= \p -> + updateState $ \s -> s{ orgStateLastPreCharPos = Just p} + +pushToInlineCharStack :: Char -> OrgParser () +pushToInlineCharStack c = updateState $ \s -> + s{ orgStateEmphasisCharStack = c:orgStateEmphasisCharStack s } + +popInlineCharStack :: OrgParser () +popInlineCharStack = updateState $ \s -> + s{ orgStateEmphasisCharStack = drop 1 . orgStateEmphasisCharStack $ s } + +surroundingEmphasisChar :: OrgParser [Char] +surroundingEmphasisChar = + take 1 . drop 1 . orgStateEmphasisCharStack <$> getState + +startEmphasisNewlinesCounting :: Int -> OrgParser () +startEmphasisNewlinesCounting maxNewlines = updateState $ \s -> + s{ orgStateEmphasisNewlines = Just maxNewlines } + +decEmphasisNewlinesCount :: OrgParser () +decEmphasisNewlinesCount = updateState $ \s -> + s{ orgStateEmphasisNewlines = (\n -> n - 1) <$> orgStateEmphasisNewlines s } + +newlinesCountWithinLimits :: OrgParser Bool +newlinesCountWithinLimits = do + st <- getState + return $ ((< 0) <$> orgStateEmphasisNewlines st) /= Just True + +resetEmphasisNewlines :: OrgParser () +resetEmphasisNewlines = updateState $ \s -> + s{ orgStateEmphasisNewlines = Nothing } + +addLinkFormat :: String + -> (String -> String) + -> OrgParser () +addLinkFormat key formatter = updateState $ \s -> + let fs = orgStateLinkFormatters s + in s{ orgStateLinkFormatters = M.insert key formatter fs } + +addToNotesTable :: OrgNoteRecord -> OrgParser () +addToNotesTable note = do + oldnotes <- orgStateNotes' <$> getState + updateState $ \s -> s{ orgStateNotes' = note:oldnotes } + +-- The version Text.Pandoc.Parsing cannot be used, as we need additional parts +-- of the state saved and restored. +parseFromString :: OrgParser a -> String -> OrgParser a +parseFromString parser str' = do + oldLastPreCharPos <- orgStateLastPreCharPos <$> getState + updateState $ \s -> s{ orgStateLastPreCharPos = Nothing } + result <- P.parseFromString parser str' + updateState $ \s -> s{ orgStateLastPreCharPos = oldLastPreCharPos } + return result + + +-- +-- Adaptions and specializations of parsing utilities +-- + +newtype F a = F { unF :: Reader OrgParserState a + } deriving (Monad, Applicative, Functor) + +runF :: F a -> OrgParserState -> a +runF = runReader . unF + +askF :: F OrgParserState +askF = F ask + +asksF :: (OrgParserState -> a) -> F a +asksF f = F $ asks f + +instance Monoid a => Monoid (F a) where + mempty = return mempty + mappend = liftM2 mappend + mconcat = fmap mconcat . sequence + +trimInlinesF :: F Inlines -> F Inlines +trimInlinesF = liftM trimInlines + +returnF :: a -> OrgParser (F a) +returnF = return . return + + +-- | Like @Text.Parsec.Char.newline@, but causes additional state changes. +newline :: OrgParser Char +newline = + P.newline + <* updateLastPreCharPos + <* updateLastForbiddenCharPos + +-- | Like @Text.Parsec.Char.blanklines@, but causes additional state changes. +blanklines :: OrgParser [Char] +blanklines = + P.blanklines + <* updateLastPreCharPos + <* updateLastForbiddenCharPos + +-- +-- parsing blocks +-- + +parseBlocks :: OrgParser (F Blocks) +parseBlocks = mconcat <$> manyTill block eof + +block :: OrgParser (F Blocks) +block = choice [ mempty <$ blanklines + , optionalAttributes $ choice + [ orgBlock + , figure + , table + ] + , example + , drawer + , specialLine + , header + , return <$> hline + , list + , latexFragment + , noteBlock + , paraOrPlain + ] <?> "block" + +optionalAttributes :: OrgParser (F Blocks) -> OrgParser (F Blocks) +optionalAttributes parser = try $ + resetBlockAttributes *> parseBlockAttributes *> parser + +parseBlockAttributes :: OrgParser () +parseBlockAttributes = do + attrs <- many attribute + mapM_ (uncurry parseAndAddAttribute) attrs + where + attribute :: OrgParser (String, String) + attribute = try $ do + key <- metaLineStart *> many1Till nonspaceChar (char ':') + val <- skipSpaces *> anyLine + return (map toLower key, val) + +parseAndAddAttribute :: String -> String -> OrgParser () +parseAndAddAttribute key value = do + let key' = map toLower key + () <$ addBlockAttribute key' value + +lookupInlinesAttr :: String -> OrgParser (Maybe (F Inlines)) +lookupInlinesAttr attr = try $ do + val <- lookupBlockAttribute attr + maybe (return Nothing) + (fmap Just . parseFromString parseInlines) + val + + +-- +-- Org Blocks (#+BEGIN_... / #+END_...) +-- + +type BlockProperties = (Int, String) -- (Indentation, Block-Type) + +orgBlock :: OrgParser (F Blocks) +orgBlock = try $ do + blockProp@(_, blkType) <- blockHeaderStart + ($ blockProp) $ + case blkType of + "comment" -> withRaw' (const mempty) + "html" -> withRaw' (return . (B.rawBlock blkType)) + "latex" -> withRaw' (return . (B.rawBlock blkType)) + "ascii" -> withRaw' (return . (B.rawBlock blkType)) + "example" -> withRaw' (return . exampleCode) + "quote" -> withParsed (fmap B.blockQuote) + "verse" -> verseBlock + "src" -> codeBlock + _ -> withParsed (fmap $ divWithClass blkType) + +blockHeaderStart :: OrgParser (Int, String) +blockHeaderStart = try $ (,) <$> indent <*> blockType + where + indent = length <$> many spaceChar + blockType = map toLower <$> (stringAnyCase "#+begin_" *> orgArgWord) + +withRaw' :: (String -> F Blocks) -> BlockProperties -> OrgParser (F Blocks) +withRaw' f blockProp = (ignHeaders *> (f <$> rawBlockContent blockProp)) + +withParsed :: (F Blocks -> F Blocks) -> BlockProperties -> OrgParser (F Blocks) +withParsed f blockProp = (ignHeaders *> (f <$> parsedBlockContent blockProp)) + +ignHeaders :: OrgParser () +ignHeaders = (() <$ newline) <|> (() <$ anyLine) + +divWithClass :: String -> Blocks -> Blocks +divWithClass cls = B.divWith ("", [cls], []) + +verseBlock :: BlockProperties -> OrgParser (F Blocks) +verseBlock blkProp = try $ do + ignHeaders + content <- rawBlockContent blkProp + fmap B.para . mconcat . intersperse (pure B.linebreak) + <$> mapM (parseFromString parseInlines) (lines content) + +exportsCode :: [(String, String)] -> Bool +exportsCode attrs = not (("rundoc-exports", "none") `elem` attrs + || ("rundoc-exports", "results") `elem` attrs) + +exportsResults :: [(String, String)] -> Bool +exportsResults attrs = ("rundoc-exports", "results") `elem` attrs + || ("rundoc-exports", "both") `elem` attrs + +followingResultsBlock :: OrgParser (Maybe String) +followingResultsBlock = + optionMaybe (try $ blanklines *> stringAnyCase "#+RESULTS:" + *> blankline + *> (unlines <$> many1 exampleLine)) + +codeBlock :: BlockProperties -> OrgParser (F Blocks) +codeBlock blkProp = do + skipSpaces + (classes, kv) <- codeHeaderArgs <|> (mempty <$ ignHeaders) + id' <- fromMaybe "" <$> lookupBlockAttribute "name" + content <- rawBlockContent blkProp + resultsContent <- followingResultsBlock + let includeCode = exportsCode kv + let includeResults = exportsResults kv + let codeBlck = B.codeBlockWith ( id', classes, kv ) content + labelledBlck <- maybe (pure codeBlck) + (labelDiv codeBlck) + <$> lookupInlinesAttr "caption" + let resultBlck = pure $ maybe mempty (exampleCode) resultsContent + return $ (if includeCode then labelledBlck else mempty) + <> (if includeResults then resultBlck else mempty) + where + labelDiv blk value = + B.divWith nullAttr <$> (mappend <$> labelledBlock value + <*> pure blk) + labelledBlock = fmap (B.plain . B.spanWith ("", ["label"], [])) + +rawBlockContent :: BlockProperties -> OrgParser String +rawBlockContent (indent, blockType) = try $ + unlines . map commaEscaped <$> manyTill indentedLine blockEnder + where + indentedLine = try $ ("" <$ blankline) <|> (indentWith indent *> anyLine) + blockEnder = try $ indentWith indent *> stringAnyCase ("#+end_" <> blockType) + +parsedBlockContent :: BlockProperties -> OrgParser (F Blocks) +parsedBlockContent blkProps = try $ do + raw <- rawBlockContent blkProps + parseFromString parseBlocks (raw ++ "\n") + +-- indent by specified number of spaces (or equiv. tabs) +indentWith :: Int -> OrgParser String +indentWith num = do + tabStop <- getOption readerTabStop + if num < tabStop + then count num (char ' ') + else choice [ try (count num (char ' ')) + , try (char '\t' >> count (num - tabStop) (char ' ')) ] + +type SwitchOption = (Char, Maybe String) + +orgArgWord :: OrgParser String +orgArgWord = many1 orgArgWordChar + +-- | Parse code block arguments +-- TODO: We currently don't handle switches. +codeHeaderArgs :: OrgParser ([String], [(String, String)]) +codeHeaderArgs = try $ do + language <- skipSpaces *> orgArgWord + _ <- skipSpaces *> (try $ switch `sepBy` (many1 spaceChar)) + parameters <- manyTill blockOption newline + let pandocLang = translateLang language + return $ + if hasRundocParameters parameters + then ( [ pandocLang, rundocBlockClass ] + , map toRundocAttrib (("language", language) : parameters) + ) + else ([ pandocLang ], parameters) + where hasRundocParameters = not . null + +switch :: OrgParser SwitchOption +switch = try $ simpleSwitch <|> lineNumbersSwitch + where + simpleSwitch = (\c -> (c, Nothing)) <$> (oneOf "-+" *> letter) + lineNumbersSwitch = (\ls -> ('l', Just ls)) <$> + (string "-l \"" *> many1Till nonspaceChar (char '"')) + +translateLang :: String -> String +translateLang "C" = "c" +translateLang "C++" = "cpp" +translateLang "emacs-lisp" = "commonlisp" -- emacs lisp is not supported +translateLang "js" = "javascript" +translateLang "lisp" = "commonlisp" +translateLang "R" = "r" +translateLang "sh" = "bash" +translateLang "sqlite" = "sql" +translateLang cs = cs + +-- | Prefix used for Rundoc classes and arguments. +rundocPrefix :: String +rundocPrefix = "rundoc-" + +-- | The class-name used to mark rundoc blocks. +rundocBlockClass :: String +rundocBlockClass = rundocPrefix ++ "block" + +blockOption :: OrgParser (String, String) +blockOption = try $ (,) <$> orgArgKey <*> orgParamValue + +inlineBlockOption :: OrgParser (String, String) +inlineBlockOption = try $ (,) <$> orgArgKey <*> orgInlineParamValue + +orgArgKey :: OrgParser String +orgArgKey = try $ + skipSpaces *> char ':' + *> many1 orgArgWordChar + +orgParamValue :: OrgParser String +orgParamValue = try $ + skipSpaces *> many1 (noneOf "\t\n\r ") <* skipSpaces + +orgInlineParamValue :: OrgParser String +orgInlineParamValue = try $ + skipSpaces *> many1 (noneOf "\t\n\r ]") <* skipSpaces + +orgArgWordChar :: OrgParser Char +orgArgWordChar = alphaNum <|> oneOf "-_" + +toRundocAttrib :: (String, String) -> (String, String) +toRundocAttrib = first ("rundoc-" ++) + +commaEscaped :: String -> String +commaEscaped (',':cs@('*':_)) = cs +commaEscaped (',':cs@('#':'+':_)) = cs +commaEscaped cs = cs + +example :: OrgParser (F Blocks) +example = try $ do + return . return . exampleCode =<< unlines <$> many1 exampleLine + +exampleCode :: String -> Blocks +exampleCode = B.codeBlockWith ("", ["example"], []) + +exampleLine :: OrgParser String +exampleLine = try $ skipSpaces *> string ": " *> anyLine + +-- Drawers for properties or a logbook +drawer :: OrgParser (F Blocks) +drawer = try $ do + drawerStart + manyTill drawerLine (try drawerEnd) + return mempty + +drawerStart :: OrgParser String +drawerStart = try $ + skipSpaces *> drawerName <* skipSpaces <* P.newline + where drawerName = try $ char ':' *> validDrawerName <* char ':' + validDrawerName = stringAnyCase "PROPERTIES" + <|> stringAnyCase "LOGBOOK" + +drawerLine :: OrgParser String +drawerLine = try anyLine + +drawerEnd :: OrgParser String +drawerEnd = try $ + skipSpaces *> stringAnyCase ":END:" <* skipSpaces <* P.newline + + +-- +-- Figures +-- + +-- Figures (Image on a line by itself, preceded by name and/or caption) +figure :: OrgParser (F Blocks) +figure = try $ do + (cap, nam) <- nameAndCaption + src <- skipSpaces *> selfTarget <* skipSpaces <* P.newline + guard (isImageFilename src) + return $ do + cap' <- cap + return $ B.para $ B.image src nam cap' + where + nameAndCaption = + do + maybeCap <- lookupInlinesAttr "caption" + maybeNam <- lookupBlockAttribute "name" + guard $ isJust maybeCap || isJust maybeNam + return ( fromMaybe mempty maybeCap + , maybe mempty withFigPrefix maybeNam ) + withFigPrefix cs = + if "fig:" `isPrefixOf` cs + then cs + else "fig:" ++ cs + +-- +-- Comments, Options and Metadata +specialLine :: OrgParser (F Blocks) +specialLine = fmap return . try $ metaLine <|> commentLine + +metaLine :: OrgParser Blocks +metaLine = try $ mempty + <$ (metaLineStart *> (optionLine <|> declarationLine)) + +commentLine :: OrgParser Blocks +commentLine = try $ commentLineStart *> anyLine *> pure mempty + +-- The order, in which blocks are tried, makes sure that we're not looking at +-- the beginning of a block, so we don't need to check for it +metaLineStart :: OrgParser String +metaLineStart = try $ mappend <$> many spaceChar <*> string "#+" + +commentLineStart :: OrgParser String +commentLineStart = try $ mappend <$> many spaceChar <*> string "# " + +declarationLine :: OrgParser () +declarationLine = try $ do + key <- metaKey + inlinesF <- metaInlines + updateState $ \st -> + let meta' = B.setMeta <$> pure key <*> inlinesF <*> pure nullMeta + in st { orgStateMeta' = orgStateMeta' st <> meta' } + return () + +metaInlines :: OrgParser (F MetaValue) +metaInlines = fmap (MetaInlines . B.toList) <$> inlinesTillNewline + +metaKey :: OrgParser String +metaKey = map toLower <$> many1 (noneOf ": \n\r") + <* char ':' + <* skipSpaces + +optionLine :: OrgParser () +optionLine = try $ do + key <- metaKey + case key of + "link" -> parseLinkFormat >>= uncurry addLinkFormat + _ -> mzero + +parseLinkFormat :: OrgParser ((String, String -> String)) +parseLinkFormat = try $ do + linkType <- (:) <$> letter <*> many (alphaNum <|> oneOf "-_") <* skipSpaces + linkSubst <- parseFormat + return (linkType, linkSubst) + +-- | An ad-hoc, single-argument-only implementation of a printf-style format +-- parser. +parseFormat :: OrgParser (String -> String) +parseFormat = try $ do + replacePlain <|> replaceUrl <|> justAppend + where + -- inefficient, but who cares + replacePlain = try $ (\x -> concat . flip intersperse x) + <$> sequence [tillSpecifier 's', rest] + replaceUrl = try $ (\x -> concat . flip intersperse x . urlEncode) + <$> sequence [tillSpecifier 'h', rest] + justAppend = try $ (++) <$> rest + + rest = manyTill anyChar (eof <|> () <$ oneOf "\n\r") + tillSpecifier c = manyTill (noneOf "\n\r") (try $ string ('%':c:"")) + +-- +-- Headers +-- + +-- | Headers +header :: OrgParser (F Blocks) +header = try $ do + level <- headerStart + title <- inlinesTillNewline + return $ B.header level <$> title + +headerStart :: OrgParser Int +headerStart = try $ + (length <$> many1 (char '*')) <* many1 (char ' ') + + +-- Don't use (or need) the reader wrapper here, we want hline to be +-- @show@able. Otherwise we can't use it with @notFollowedBy'@. + +-- | Horizontal Line (five -- dashes or more) +hline :: OrgParser Blocks +hline = try $ do + skipSpaces + string "-----" + many (char '-') + skipSpaces + newline + return B.horizontalRule + +-- +-- Tables +-- + +data OrgTableRow = OrgContentRow (F [Blocks]) + | OrgAlignRow [Alignment] + | OrgHlineRow + +data OrgTable = OrgTable + { orgTableColumns :: Int + , orgTableAlignments :: [Alignment] + , orgTableHeader :: [Blocks] + , orgTableRows :: [[Blocks]] + } + +table :: OrgParser (F Blocks) +table = try $ do + lookAhead tableStart + do + rows <- tableRows + cptn <- fromMaybe (pure "") <$> lookupInlinesAttr "caption" + return $ (<$> cptn) . orgToPandocTable . normalizeTable =<< rowsToTable rows + +orgToPandocTable :: OrgTable + -> Inlines + -> Blocks +orgToPandocTable (OrgTable _ aligns heads lns) caption = + B.table caption (zip aligns $ repeat 0) heads lns + +tableStart :: OrgParser Char +tableStart = try $ skipSpaces *> char '|' + +tableRows :: OrgParser [OrgTableRow] +tableRows = try $ many (tableAlignRow <|> tableHline <|> tableContentRow) + +tableContentRow :: OrgParser OrgTableRow +tableContentRow = try $ + OrgContentRow . sequence <$> (tableStart *> manyTill tableContentCell newline) + +tableContentCell :: OrgParser (F Blocks) +tableContentCell = try $ + fmap B.plain . trimInlinesF . mconcat <$> many1Till inline endOfCell + +endOfCell :: OrgParser Char +endOfCell = try $ char '|' <|> lookAhead newline + +tableAlignRow :: OrgParser OrgTableRow +tableAlignRow = try $ + OrgAlignRow <$> (tableStart *> manyTill tableAlignCell newline) + +tableAlignCell :: OrgParser Alignment +tableAlignCell = + choice [ try $ emptyCell *> return AlignDefault + , try $ skipSpaces + *> char '<' + *> tableAlignFromChar + <* many digit + <* char '>' + <* emptyCell + ] <?> "alignment info" + where emptyCell = try $ skipSpaces *> endOfCell + +tableAlignFromChar :: OrgParser Alignment +tableAlignFromChar = try $ choice [ char 'l' *> return AlignLeft + , char 'c' *> return AlignCenter + , char 'r' *> return AlignRight + ] + +tableHline :: OrgParser OrgTableRow +tableHline = try $ + OrgHlineRow <$ (tableStart *> char '-' *> anyLine) + +rowsToTable :: [OrgTableRow] + -> F OrgTable +rowsToTable = foldM (flip rowToContent) zeroTable + where zeroTable = OrgTable 0 mempty mempty mempty + +normalizeTable :: OrgTable + -> OrgTable +normalizeTable (OrgTable cols aligns heads lns) = + let aligns' = fillColumns aligns AlignDefault + heads' = if heads == mempty + then mempty + else fillColumns heads (B.plain mempty) + lns' = map (`fillColumns` B.plain mempty) lns + fillColumns base padding = take cols $ base ++ repeat padding + in OrgTable cols aligns' heads' lns' + + +-- One or more horizontal rules after the first content line mark the previous +-- line as a header. All other horizontal lines are discarded. +rowToContent :: OrgTableRow + -> OrgTable + -> F OrgTable +rowToContent OrgHlineRow t = maybeBodyToHeader t +rowToContent (OrgAlignRow as) t = setLongestRow as =<< setAligns as t +rowToContent (OrgContentRow rf) t = do + rs <- rf + setLongestRow rs =<< appendToBody rs t + +setLongestRow :: [a] + -> OrgTable + -> F OrgTable +setLongestRow rs t = + return t{ orgTableColumns = max (length rs) (orgTableColumns t) } + +maybeBodyToHeader :: OrgTable + -> F OrgTable +maybeBodyToHeader t = case t of + OrgTable{ orgTableHeader = [], orgTableRows = b:[] } -> + return t{ orgTableHeader = b , orgTableRows = [] } + _ -> return t + +appendToBody :: [Blocks] + -> OrgTable + -> F OrgTable +appendToBody r t = return t{ orgTableRows = orgTableRows t ++ [r] } + +setAligns :: [Alignment] + -> OrgTable + -> F OrgTable +setAligns aligns t = return $ t{ orgTableAlignments = aligns } + + +-- +-- LaTeX fragments +-- +latexFragment :: OrgParser (F Blocks) +latexFragment = try $ do + envName <- latexEnvStart + content <- mconcat <$> manyTill anyLineNewline (latexEnd envName) + return . return $ B.rawBlock "latex" (content `inLatexEnv` envName) + where + c `inLatexEnv` e = mconcat [ "\\begin{", e, "}\n" + , c + , "\\end{", e, "}\n" + ] + +latexEnvStart :: OrgParser String +latexEnvStart = try $ do + skipSpaces *> string "\\begin{" + *> latexEnvName + <* string "}" + <* blankline + +latexEnd :: String -> OrgParser () +latexEnd envName = try $ + () <$ skipSpaces + <* string ("\\end{" ++ envName ++ "}") + <* blankline + +-- | Parses a LaTeX environment name. +latexEnvName :: OrgParser String +latexEnvName = try $ do + mappend <$> many1 alphaNum + <*> option "" (string "*") + + +-- +-- Footnote defintions +-- +noteBlock :: OrgParser (F Blocks) +noteBlock = try $ do + ref <- noteMarker <* skipSpaces + content <- mconcat <$> blocksTillHeaderOrNote + addToNotesTable (ref, content) + return mempty + where + blocksTillHeaderOrNote = + many1Till block (eof <|> () <$ lookAhead noteMarker + <|> () <$ lookAhead headerStart) + +-- Paragraphs or Plain text +paraOrPlain :: OrgParser (F Blocks) +paraOrPlain = try $ do + ils <- parseInlines + nl <- option False (newline >> return True) + try (guard nl >> notFollowedBy (orderedListStart <|> bulletListStart) >> + return (B.para <$> ils)) + <|> (return (B.plain <$> ils)) + +inlinesTillNewline :: OrgParser (F Inlines) +inlinesTillNewline = trimInlinesF . mconcat <$> manyTill inline newline + + +-- +-- list blocks +-- + +list :: OrgParser (F Blocks) +list = choice [ definitionList, bulletList, orderedList ] <?> "list" + +definitionList :: OrgParser (F Blocks) +definitionList = try $ do n <- lookAhead (bulletListStart' Nothing) + fmap B.definitionList . fmap compactify'DL . sequence + <$> many1 (definitionListItem $ bulletListStart' (Just n)) + +bulletList :: OrgParser (F Blocks) +bulletList = try $ do n <- lookAhead (bulletListStart' Nothing) + fmap B.bulletList . fmap compactify' . sequence + <$> many1 (listItem (bulletListStart' $ Just n)) + +orderedList :: OrgParser (F Blocks) +orderedList = fmap B.orderedList . fmap compactify' . sequence + <$> many1 (listItem orderedListStart) + +genericListStart :: OrgParser String + -> OrgParser Int +genericListStart listMarker = try $ + (+) <$> (length <$> many spaceChar) + <*> (length <$> listMarker <* many1 spaceChar) + +-- parses bullet list marker. maybe we know the indent level +bulletListStart :: OrgParser Int +bulletListStart = bulletListStart' Nothing + +bulletListStart' :: Maybe Int -> OrgParser Int +-- returns length of bulletList prefix, inclusive of marker +bulletListStart' Nothing = do ind <- length <$> many spaceChar + when (ind == 0) $ notFollowedBy (char '*') + oneOf bullets + many1 spaceChar + return (ind + 1) + -- Unindented lists are legal, but they can't use '*' bullets + -- We return n to maintain compatibility with the generic listItem +bulletListStart' (Just n) = do count (n-1) spaceChar + when (n == 1) $ notFollowedBy (char '*') + oneOf bullets + many1 spaceChar + return n + +bullets :: String +bullets = "*+-" + +orderedListStart :: OrgParser Int +orderedListStart = genericListStart orderedListMarker + -- Ordered list markers allowed in org-mode + where orderedListMarker = mappend <$> many1 digit <*> (pure <$> oneOf ".)") + +definitionListItem :: OrgParser Int + -> OrgParser (F (Inlines, [Blocks])) +definitionListItem parseMarkerGetLength = try $ do + markerLength <- parseMarkerGetLength + term <- manyTill (noneOf "\n\r") (try $ string "::") + line1 <- anyLineNewline + blank <- option "" ("\n" <$ blankline) + cont <- concat <$> many (listContinuation markerLength) + term' <- parseFromString parseInlines term + contents' <- parseFromString parseBlocks $ line1 ++ blank ++ cont + return $ (,) <$> term' <*> fmap (:[]) contents' + + +-- parse raw text for one list item, excluding start marker and continuations +listItem :: OrgParser Int + -> OrgParser (F Blocks) +listItem start = try $ do + markerLength <- try start + firstLine <- anyLineNewline + blank <- option "" ("\n" <$ blankline) + rest <- concat <$> many (listContinuation markerLength) + parseFromString parseBlocks $ firstLine ++ blank ++ rest + +-- continuation of a list item - indented and separated by blankline or endline. +-- Note: nested lists are parsed as continuations. +listContinuation :: Int + -> OrgParser String +listContinuation markerLength = try $ + notFollowedBy' blankline + *> (mappend <$> (concat <$> many1 listLine) + <*> many blankline) + where listLine = try $ indentWith markerLength *> anyLineNewline + +anyLineNewline :: OrgParser String +anyLineNewline = (++ "\n") <$> anyLine + + +-- +-- inline +-- + +inline :: OrgParser (F Inlines) +inline = + choice [ whitespace + , linebreak + , cite + , footnote + , linkOrImage + , anchor + , inlineCodeBlock + , str + , endline + , emph + , strong + , strikeout + , underline + , code + , math + , displayMath + , verbatim + , subscript + , superscript + , inlineLaTeX + , symbol + ] <* (guard =<< newlinesCountWithinLimits) + <?> "inline" + +parseInlines :: OrgParser (F Inlines) +parseInlines = trimInlinesF . mconcat <$> many1 inline + +-- treat these as potentially non-text when parsing inline: +specialChars :: [Char] +specialChars = "\"$'()*+-,./:<=>[\\]^_{|}~" + + +whitespace :: OrgParser (F Inlines) +whitespace = pure B.space <$ skipMany1 spaceChar + <* updateLastPreCharPos + <* updateLastForbiddenCharPos + <?> "whitespace" + +linebreak :: OrgParser (F Inlines) +linebreak = try $ pure B.linebreak <$ string "\\\\" <* skipSpaces <* newline + +str :: OrgParser (F Inlines) +str = return . B.str <$> many1 (noneOf $ specialChars ++ "\n\r ") + <* updateLastStrPos + +-- | An endline character that can be treated as a space, not a structural +-- break. This should reflect the values of the Emacs variable +-- @org-element-pagaraph-separate@. +endline :: OrgParser (F Inlines) +endline = try $ do + newline + notFollowedBy blankline + notFollowedBy' exampleLine + notFollowedBy' hline + notFollowedBy' noteMarker + notFollowedBy' tableStart + notFollowedBy' drawerStart + notFollowedBy' headerStart + notFollowedBy' metaLineStart + notFollowedBy' latexEnvStart + notFollowedBy' commentLineStart + notFollowedBy' bulletListStart + notFollowedBy' orderedListStart + decEmphasisNewlinesCount + guard =<< newlinesCountWithinLimits + updateLastPreCharPos + return . return $ B.space + +cite :: OrgParser (F Inlines) +cite = try $ do + guardEnabled Ext_citations + (cs, raw) <- withRaw normalCite + return $ (flip B.cite (B.text raw)) <$> cs + +normalCite :: OrgParser (F [Citation]) +normalCite = try $ char '[' + *> skipSpaces + *> citeList + <* skipSpaces + <* char ']' + +citeList :: OrgParser (F [Citation]) +citeList = sequence <$> sepBy1 citation (try $ char ';' *> skipSpaces) + +citation :: OrgParser (F Citation) +citation = try $ do + pref <- prefix + (suppress_author, key) <- citeKey + suff <- suffix + return $ do + x <- pref + y <- suff + return $ Citation{ citationId = key + , citationPrefix = B.toList x + , citationSuffix = B.toList y + , citationMode = if suppress_author + then SuppressAuthor + else NormalCitation + , citationNoteNum = 0 + , citationHash = 0 + } + where + prefix = trimInlinesF . mconcat <$> + manyTill inline (char ']' <|> (']' <$ lookAhead citeKey)) + suffix = try $ do + hasSpace <- option False (notFollowedBy nonspaceChar >> return True) + skipSpaces + rest <- trimInlinesF . mconcat <$> + many (notFollowedBy (oneOf ";]") *> inline) + return $ if hasSpace + then (B.space <>) <$> rest + else rest + +footnote :: OrgParser (F Inlines) +footnote = try $ inlineNote <|> referencedNote + +inlineNote :: OrgParser (F Inlines) +inlineNote = try $ do + string "[fn:" + ref <- many alphaNum + char ':' + note <- fmap B.para . trimInlinesF . mconcat <$> many1Till inline (char ']') + when (not $ null ref) $ + addToNotesTable ("fn:" ++ ref, note) + return $ B.note <$> note + +referencedNote :: OrgParser (F Inlines) +referencedNote = try $ do + ref <- noteMarker + return $ do + notes <- asksF orgStateNotes' + case lookup ref notes of + Nothing -> return $ B.str $ "[" ++ ref ++ "]" + Just contents -> do + st <- askF + let contents' = runF contents st{ orgStateNotes' = [] } + return $ B.note contents' + +noteMarker :: OrgParser String +noteMarker = try $ do + char '[' + choice [ many1Till digit (char ']') + , (++) <$> string "fn:" + <*> many1Till (noneOf "\n\r\t ") (char ']') + ] + +linkOrImage :: OrgParser (F Inlines) +linkOrImage = explicitOrImageLink + <|> selflinkOrImage + <|> angleLink + <|> plainLink + <?> "link or image" + +explicitOrImageLink :: OrgParser (F Inlines) +explicitOrImageLink = try $ do + char '[' + srcF <- applyCustomLinkFormat =<< possiblyEmptyLinkTarget + title <- enclosedRaw (char '[') (char ']') + title' <- parseFromString (mconcat <$> many inline) title + char ']' + return $ do + src <- srcF + if isImageFilename src && isImageFilename title + then pure $ B.link src "" $ B.image title mempty mempty + else linkToInlinesF src =<< title' + +selflinkOrImage :: OrgParser (F Inlines) +selflinkOrImage = try $ do + src <- char '[' *> linkTarget <* char ']' + return $ linkToInlinesF src (B.str src) + +plainLink :: OrgParser (F Inlines) +plainLink = try $ do + (orig, src) <- uri + returnF $ B.link src "" (B.str orig) + +angleLink :: OrgParser (F Inlines) +angleLink = try $ do + char '<' + link <- plainLink + char '>' + return link + +selfTarget :: OrgParser String +selfTarget = try $ char '[' *> linkTarget <* char ']' + +linkTarget :: OrgParser String +linkTarget = enclosedByPair '[' ']' (noneOf "\n\r[]") + +possiblyEmptyLinkTarget :: OrgParser String +possiblyEmptyLinkTarget = try linkTarget <|> ("" <$ string "[]") + +applyCustomLinkFormat :: String -> OrgParser (F String) +applyCustomLinkFormat link = do + let (linkType, rest) = break (== ':') link + return $ do + formatter <- M.lookup linkType <$> asksF orgStateLinkFormatters + return $ maybe link ($ drop 1 rest) formatter + +-- TODO: might be a lot smarter/cleaner to use parsec and ADTs for this kind +-- of parsing. +linkToInlinesF :: String -> Inlines -> F Inlines +linkToInlinesF s = + case s of + "" -> pure . B.link "" "" + ('#':_) -> pure . B.link s "" + _ | isImageFilename s -> const . pure $ B.image s "" "" + _ | isFileLink s -> pure . B.link (dropLinkType s) "" + _ | isUri s -> pure . B.link s "" + _ | isAbsoluteFilePath s -> pure . B.link ("file://" ++ s) "" + _ | isRelativeFilePath s -> pure . B.link s "" + _ -> internalLink s + +isFileLink :: String -> Bool +isFileLink s = ("file:" `isPrefixOf` s) && not ("file://" `isPrefixOf` s) + +dropLinkType :: String -> String +dropLinkType = tail . snd . break (== ':') + +isRelativeFilePath :: String -> Bool +isRelativeFilePath s = (("./" `isPrefixOf` s) || ("../" `isPrefixOf` s)) && + (':' `notElem` s) + +isUri :: String -> Bool +isUri s = let (scheme, path) = break (== ':') s + in all (\c -> isAlphaNum c || c `elem` ".-") scheme + && not (null path) + +isAbsoluteFilePath :: String -> Bool +isAbsoluteFilePath = ('/' ==) . head + +isImageFilename :: String -> Bool +isImageFilename filename = + any (\x -> ('.':x) `isSuffixOf` filename) imageExtensions && + (any (\x -> (x++":") `isPrefixOf` filename) protocols || + ':' `notElem` filename) + where + imageExtensions = [ "jpeg" , "jpg" , "png" , "gif" , "svg" ] + protocols = [ "file", "http", "https" ] + +internalLink :: String -> Inlines -> F Inlines +internalLink link title = do + anchorB <- (link `elem`) <$> asksF orgStateAnchorIds + if anchorB + then return $ B.link ('#':link) "" title + else return $ B.emph title + +-- | Parse an anchor like @<<anchor-id>>@ and return an empty span with +-- @anchor-id@ set as id. Legal anchors in org-mode are defined through +-- @org-target-regexp@, which is fairly liberal. Since no link is created if +-- @anchor-id@ contains spaces, we are more restrictive in what is accepted as +-- an anchor. + +anchor :: OrgParser (F Inlines) +anchor = try $ do + anchorId <- parseAnchor + recordAnchorId anchorId + returnF $ B.spanWith (solidify anchorId, [], []) mempty + where + parseAnchor = string "<<" + *> many1 (noneOf "\t\n\r<>\"' ") + <* string ">>" + <* skipSpaces + +-- | Replace every char but [a-zA-Z0-9_.-:] with a hypen '-'. This mirrors +-- the org function @org-export-solidify-link-text@. + +solidify :: String -> String +solidify = map replaceSpecialChar + where replaceSpecialChar c + | isAlphaNum c = c + | c `elem` "_.-:" = c + | otherwise = '-' + +-- | Parses an inline code block and marks it as an babel block. +inlineCodeBlock :: OrgParser (F Inlines) +inlineCodeBlock = try $ do + string "src_" + lang <- many1 orgArgWordChar + opts <- option [] $ enclosedByPair '[' ']' inlineBlockOption + inlineCode <- enclosedByPair '{' '}' (noneOf "\n\r") + let attrClasses = [translateLang lang, rundocBlockClass] + let attrKeyVal = map toRundocAttrib (("language", lang) : opts) + returnF $ B.codeWith ("", attrClasses, attrKeyVal) inlineCode + +enclosedByPair :: Char -- ^ opening char + -> Char -- ^ closing char + -> OrgParser a -- ^ parser + -> OrgParser [a] +enclosedByPair s e p = char s *> many1Till p (char e) + +emph :: OrgParser (F Inlines) +emph = fmap B.emph <$> emphasisBetween '/' + +strong :: OrgParser (F Inlines) +strong = fmap B.strong <$> emphasisBetween '*' + +strikeout :: OrgParser (F Inlines) +strikeout = fmap B.strikeout <$> emphasisBetween '+' + +-- There is no underline, so we use strong instead. +underline :: OrgParser (F Inlines) +underline = fmap B.strong <$> emphasisBetween '_' + +verbatim :: OrgParser (F Inlines) +verbatim = return . B.code <$> verbatimBetween '=' + +code :: OrgParser (F Inlines) +code = return . B.code <$> verbatimBetween '~' + +subscript :: OrgParser (F Inlines) +subscript = fmap B.subscript <$> try (char '_' *> subOrSuperExpr) + +superscript :: OrgParser (F Inlines) +superscript = fmap B.superscript <$> try (char '^' *> subOrSuperExpr) + +math :: OrgParser (F Inlines) +math = return . B.math <$> choice [ math1CharBetween '$' + , mathStringBetween '$' + , rawMathBetween "\\(" "\\)" + ] + +displayMath :: OrgParser (F Inlines) +displayMath = return . B.displayMath <$> choice [ rawMathBetween "\\[" "\\]" + , rawMathBetween "$$" "$$" + ] +symbol :: OrgParser (F Inlines) +symbol = return . B.str . (: "") <$> (oneOf specialChars >>= updatePositions) + where updatePositions c = do + when (c `elem` emphasisPreChars) updateLastPreCharPos + when (c `elem` emphasisForbiddenBorderChars) updateLastForbiddenCharPos + return c + +emphasisBetween :: Char + -> OrgParser (F Inlines) +emphasisBetween c = try $ do + startEmphasisNewlinesCounting emphasisAllowedNewlines + res <- enclosedInlines (emphasisStart c) (emphasisEnd c) + isTopLevelEmphasis <- null . orgStateEmphasisCharStack <$> getState + when isTopLevelEmphasis + resetEmphasisNewlines + return res + +verbatimBetween :: Char + -> OrgParser String +verbatimBetween c = try $ + emphasisStart c *> + many1TillNOrLessNewlines 1 (noneOf "\n\r") (emphasisEnd c) + +-- | Parses a raw string delimited by @c@ using Org's math rules +mathStringBetween :: Char + -> OrgParser String +mathStringBetween c = try $ do + mathStart c + body <- many1TillNOrLessNewlines mathAllowedNewlines + (noneOf (c:"\n\r")) + (lookAhead $ mathEnd c) + final <- mathEnd c + return $ body ++ [final] + +-- | Parse a single character between @c@ using math rules +math1CharBetween :: Char + -> OrgParser String +math1CharBetween c = try $ do + char c + res <- noneOf $ c:mathForbiddenBorderChars + char c + eof <|> () <$ lookAhead (oneOf mathPostChars) + return [res] + +rawMathBetween :: String + -> String + -> OrgParser String +rawMathBetween s e = try $ string s *> manyTill anyChar (try $ string e) + +-- | Parses the start (opening character) of emphasis +emphasisStart :: Char -> OrgParser Char +emphasisStart c = try $ do + guard =<< afterEmphasisPreChar + guard =<< notAfterString + char c + lookAhead (noneOf emphasisForbiddenBorderChars) + pushToInlineCharStack c + return c + +-- | Parses the closing character of emphasis +emphasisEnd :: Char -> OrgParser Char +emphasisEnd c = try $ do + guard =<< notAfterForbiddenBorderChar + char c + eof <|> () <$ lookAhead acceptablePostChars + updateLastStrPos + popInlineCharStack + return c + where acceptablePostChars = + surroundingEmphasisChar >>= \x -> oneOf (x ++ emphasisPostChars) + +mathStart :: Char -> OrgParser Char +mathStart c = try $ + char c <* notFollowedBy' (oneOf (c:mathForbiddenBorderChars)) + +mathEnd :: Char -> OrgParser Char +mathEnd c = try $ do + res <- noneOf (c:mathForbiddenBorderChars) + char c + eof <|> () <$ lookAhead (oneOf mathPostChars) + return res + + +enclosedInlines :: OrgParser a + -> OrgParser b + -> OrgParser (F Inlines) +enclosedInlines start end = try $ + trimInlinesF . mconcat <$> enclosed start end inline + +enclosedRaw :: OrgParser a + -> OrgParser b + -> OrgParser String +enclosedRaw start end = try $ + start *> (onSingleLine <|> spanningTwoLines) + where onSingleLine = try $ many1Till (noneOf "\n\r") end + spanningTwoLines = try $ + anyLine >>= \f -> mappend (f <> " ") <$> onSingleLine + +-- | Like many1Till, but parses at most @n+1@ lines. @p@ must not consume +-- newlines. +many1TillNOrLessNewlines :: Int + -> OrgParser Char + -> OrgParser a + -> OrgParser String +many1TillNOrLessNewlines n p end = try $ + nMoreLines (Just n) mempty >>= oneOrMore + where + nMoreLines Nothing cs = return cs + nMoreLines (Just 0) cs = try $ (cs ++) <$> finalLine + nMoreLines k cs = try $ (final k cs <|> rest k cs) + >>= uncurry nMoreLines + final _ cs = (\x -> (Nothing, cs ++ x)) <$> try finalLine + rest m cs = (\x -> (minus1 <$> m, cs ++ x ++ "\n")) <$> try (manyTill p P.newline) + finalLine = try $ manyTill p end + minus1 k = k - 1 + oneOrMore cs = guard (not $ null cs) *> return cs + +-- Org allows customization of the way it reads emphasis. We use the defaults +-- here (see, e.g., the Emacs Lisp variable `org-emphasis-regexp-components` +-- for details). + +-- | Chars allowed to occur before emphasis (spaces and newlines are ok, too) +emphasisPreChars :: [Char] +emphasisPreChars = "\t \"'({" + +-- | Chars allowed at after emphasis +emphasisPostChars :: [Char] +emphasisPostChars = "\t\n !\"'),-.:;?\\}" + +-- | Chars not allowed at the (inner) border of emphasis +emphasisForbiddenBorderChars :: [Char] +emphasisForbiddenBorderChars = "\t\n\r \"'," + +-- | The maximum number of newlines within +emphasisAllowedNewlines :: Int +emphasisAllowedNewlines = 1 + +-- LaTeX-style math: see `org-latex-regexps` for details + +-- | Chars allowed after an inline ($...$) math statement +mathPostChars :: [Char] +mathPostChars = "\t\n \"'),-.:;?" + +-- | Chars not allowed at the (inner) border of math +mathForbiddenBorderChars :: [Char] +mathForbiddenBorderChars = "\t\n\r ,;.$" + +-- | Maximum number of newlines in an inline math statement +mathAllowedNewlines :: Int +mathAllowedNewlines = 2 + +-- | Whether we are right behind a char allowed before emphasis +afterEmphasisPreChar :: OrgParser Bool +afterEmphasisPreChar = do + pos <- getPosition + lastPrePos <- orgStateLastPreCharPos <$> getState + return . fromMaybe True $ (== pos) <$> lastPrePos + +-- | Whether the parser is right after a forbidden border char +notAfterForbiddenBorderChar :: OrgParser Bool +notAfterForbiddenBorderChar = do + pos <- getPosition + lastFBCPos <- orgStateLastForbiddenCharPos <$> getState + return $ lastFBCPos /= Just pos + +-- | Read a sub- or superscript expression +subOrSuperExpr :: OrgParser (F Inlines) +subOrSuperExpr = try $ + choice [ id <$> charsInBalanced '{' '}' (noneOf "\n\r") + , enclosing ('(', ')') <$> charsInBalanced '(' ')' (noneOf "\n\r") + , simpleSubOrSuperString + ] >>= parseFromString (mconcat <$> many inline) + where enclosing (left, right) s = left : s ++ [right] + +simpleSubOrSuperString :: OrgParser String +simpleSubOrSuperString = try $ + choice [ string "*" + , mappend <$> option [] ((:[]) <$> oneOf "+-") + <*> many1 alphaNum + ] + +inlineLaTeX :: OrgParser (F Inlines) +inlineLaTeX = try $ do + cmd <- inlineLaTeXCommand + maybe mzero returnF $ + parseAsMath cmd `mplus` parseAsMathMLSym cmd `mplus` parseAsInlineLaTeX cmd + where + parseAsMath :: String -> Maybe Inlines + parseAsMath cs = B.fromList <$> texMathToPandoc cs + + parseAsInlineLaTeX :: String -> Maybe Inlines + parseAsInlineLaTeX cs = maybeRight $ runParser inlineCommand state "" cs + + parseAsMathMLSym :: String -> Maybe Inlines + parseAsMathMLSym cs = B.str <$> MathMLEntityMap.getUnicode (clean cs) + -- dropWhileEnd would be nice here, but it's not available before base 4.5 + where clean = reverse . dropWhile (`elem` "{}") . reverse . drop 1 + + state :: ParserState + state = def{ stateOptions = def{ readerParseRaw = True }} + + texMathToPandoc inp = (maybeRight $ readTeX inp) >>= + writePandoc DisplayInline + +maybeRight :: Either a b -> Maybe b +maybeRight = either (const Nothing) Just + +inlineLaTeXCommand :: OrgParser String +inlineLaTeXCommand = try $ do + rest <- getInput + case runParser rawLaTeXInline def "source" rest of + Right (RawInline _ cs) -> do + let len = length cs + count len anyChar + return cs + _ -> mzero diff --git a/src/Text/Pandoc/Readers/RST.hs b/src/Text/Pandoc/Readers/RST.hs index c12a1493a..8bfc6f606 100644 --- a/src/Text/Pandoc/Readers/RST.hs +++ b/src/Text/Pandoc/Readers/RST.hs @@ -1,6 +1,6 @@ {-# LANGUAGE OverloadedStrings #-} {- -Copyright (C) 2006-2010 John MacFarlane <jgm@berkeley.edu> +Copyright (C) 2006-2014 John MacFarlane <jgm@berkeley.edu> This program is free software; you can redistribute it and/or modify it under the terms of the GNU General Public License as published by @@ -19,7 +19,7 @@ Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA {- | Module : Text.Pandoc.Readers.RST - Copyright : Copyright (C) 2006-2010 John MacFarlane + Copyright : Copyright (C) 2006-2014 John MacFarlane License : GNU GPL, version 2 or above Maintainer : John MacFarlane <jgm@berkeley.edu> @@ -29,7 +29,8 @@ Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA Conversion from reStructuredText to 'Pandoc' document. -} module Text.Pandoc.Readers.RST ( - readRST + readRST, + readRSTWithWarnings ) where import Text.Pandoc.Definition import Text.Pandoc.Builder (setMeta, fromList) @@ -38,15 +39,16 @@ import Text.Pandoc.Parsing import Text.Pandoc.Options import Control.Monad ( when, liftM, guard, mzero ) import Data.List ( findIndex, intersperse, intercalate, - transpose, sort, deleteFirstsBy, isSuffixOf ) + transpose, sort, deleteFirstsBy, isSuffixOf , nub, union) +import Data.Maybe (fromMaybe) import qualified Data.Map as M import Text.Printf ( printf ) -import Control.Applicative ((<$>), (<$), (<*), (*>)) +import Control.Applicative ((<$>), (<$), (<*), (*>), (<*>), pure) import Text.Pandoc.Builder (Inlines, Blocks, trimInlines, (<>)) import qualified Text.Pandoc.Builder as B import Data.Monoid (mconcat, mempty) import Data.Sequence (viewr, ViewR(..)) -import Data.Char (toLower) +import Data.Char (toLower, isHexDigit, isSpace) -- | Parse reStructuredText string and return Pandoc document. readRST :: ReaderOptions -- ^ Reader options @@ -54,6 +56,9 @@ readRST :: ReaderOptions -- ^ Reader options -> Pandoc readRST opts s = (readWith parseRST) def{ stateOptions = opts } (s ++ "\n\n") +readRSTWithWarnings :: ReaderOptions -> String -> (Pandoc, [String]) +readRSTWithWarnings opts s = (readWithWarnings parseRST) def{ stateOptions = opts } (s ++ "\n\n") + type RSTParser = Parser [Char] ParserState -- @@ -112,15 +117,16 @@ titleTransform (bs, meta) = metaFromDefList :: [([Inline], [[Block]])] -> Meta -> Meta metaFromDefList ds meta = adjustAuthors $ foldr f meta ds where f (k,v) = setMeta (map toLower $ stringify k) (mconcat $ map fromList v) - adjustAuthors (Meta metamap) = Meta $ M.adjust toPlain "author" + adjustAuthors (Meta metamap) = Meta $ M.adjust splitAuthors "author" $ M.adjust toPlain "date" $ M.adjust toPlain "title" - $ M.adjust splitAuthors "authors" + $ M.mapKeys (\k -> if k == "authors" then "author" else k) $ metamap toPlain (MetaBlocks [Para xs]) = MetaInlines xs toPlain x = x - splitAuthors (MetaBlocks [Para xs]) = MetaList $ map MetaInlines - $ splitAuthors' xs + splitAuthors (MetaBlocks [Para xs]) + = MetaList $ map MetaInlines + $ splitAuthors' xs splitAuthors x = x splitAuthors' = map normalizeSpaces . splitOnSemi . concatMap factorSemi @@ -184,22 +190,22 @@ block = choice [ codeBlock -- field list -- -rawFieldListItem :: String -> RSTParser (String, String) -rawFieldListItem indent = try $ do - string indent +rawFieldListItem :: Int -> RSTParser (String, String) +rawFieldListItem minIndent = try $ do + indent <- length <$> many (char ' ') + guard $ indent >= minIndent char ':' name <- many1Till (noneOf "\n") (char ':') (() <$ lookAhead newline) <|> skipMany1 spaceChar first <- anyLine - rest <- option "" $ try $ do lookAhead (string indent >> spaceChar) + rest <- option "" $ try $ do lookAhead (count indent (char ' ') >> spaceChar) indentedBlock let raw = (if null first then "" else (first ++ "\n")) ++ rest ++ "\n" return (name, raw) -fieldListItem :: String - -> RSTParser (Inlines, [Blocks]) -fieldListItem indent = try $ do - (name, raw) <- rawFieldListItem indent +fieldListItem :: Int -> RSTParser (Inlines, [Blocks]) +fieldListItem minIndent = try $ do + (name, raw) <- rawFieldListItem minIndent let term = B.str name contents <- parseFromString parseBlocks raw optional blanklines @@ -207,7 +213,7 @@ fieldListItem indent = try $ do fieldList :: RSTParser Blocks fieldList = try $ do - indent <- lookAhead $ many spaceChar + indent <- length <$> lookAhead (many spaceChar) items <- many1 $ fieldListItem indent case items of [] -> return mempty @@ -333,6 +339,13 @@ indentedBlock = try $ do optional blanklines return $ unlines lns +quotedBlock :: Parser [Char] st [Char] +quotedBlock = try $ do + quote <- lookAhead $ oneOf "!\"#$%&'()*+,-./:;<=>?@[\\]^_`{|}~" + lns <- many1 $ lookAhead (char quote) >> anyLine + optional blanklines + return $ unlines lns + codeBlockStart :: Parser [Char] st Char codeBlockStart = string "::" >> blankline >> blankline @@ -340,7 +353,8 @@ codeBlock :: Parser [Char] st Blocks codeBlock = try $ codeBlockStart >> codeBlockBody codeBlockBody :: Parser [Char] st Blocks -codeBlockBody = try $ B.codeBlock . stripTrailingNewlines <$> indentedBlock +codeBlockBody = try $ B.codeBlock . stripTrailingNewlines <$> + (indentedBlock <|> quotedBlock) lhsCodeBlock :: RSTParser Blocks lhsCodeBlock = try $ do @@ -458,7 +472,7 @@ listItem :: RSTParser Int listItem start = try $ do (markerLength, first) <- rawListItem start rest <- many (listContinuation markerLength) - blanks <- choice [ try (many blankline >>~ lookAhead start), + blanks <- choice [ try (many blankline <* lookAhead start), many1 blankline ] -- whole list must end with blank. -- parsing with ListItemState forces markers at beginning of lines to -- count as list item markers, even if not separated by blank space. @@ -478,7 +492,7 @@ listItem start = try $ do orderedList :: RSTParser Blocks orderedList = try $ do - (start, style, delim) <- lookAhead (anyOrderedListMarker >>~ spaceChar) + (start, style, delim) <- lookAhead (anyOrderedListMarker <* spaceChar) items <- many1 (listItem (orderedListStart style delim)) let items' = compactify' items return $ B.orderedListWith (start, style, delim) items' @@ -511,7 +525,6 @@ directive = try $ do -- TODO: line-block, parsed-literal, table, csv-table, list-table -- date -- include --- class -- title directive' :: RSTParser Blocks directive' = do @@ -520,17 +533,17 @@ directive' = do skipMany spaceChar top <- many $ satisfy (/='\n') <|> try (char '\n' <* - notFollowedBy' (rawFieldListItem " ") <* + notFollowedBy' (rawFieldListItem 3) <* count 3 (char ' ') <* notFollowedBy blankline) newline - fields <- many $ rawFieldListItem " " + fields <- many $ rawFieldListItem 3 body <- option "" $ try $ blanklines >> indentedBlock optional blanklines let body' = body ++ "\n\n" case label of "raw" -> return $ B.rawBlock (trim top) (stripTrailingNewlines body) - "role" -> return mempty + "role" -> addNewRole top $ map (\(k,v) -> (k, trim v)) fields "container" -> parseFromString parseBlocks body' "replace" -> B.para <$> -- consumed by substKey parseFromString (trimInlines . mconcat <$> many inline) @@ -575,12 +588,15 @@ directive' = do role -> role }) "code" -> codeblock (lookup "number-lines" fields) (trim top) body "code-block" -> codeblock (lookup "number-lines" fields) (trim top) body + "aafig" -> do + let attribs = ("", ["aafig"], map (\(k,v) -> (k, trimr v)) fields) + return $ B.codeBlockWith attribs $ stripTrailingNewlines body "math" -> return $ B.para $ mconcat $ map B.displayMath $ toChunks $ top ++ "\n\n" ++ body "figure" -> do (caption, legend) <- parseFromString extractCaption body' let src = escapeURI $ trim top - return $ B.para (B.image src "" caption) <> legend + return $ B.para (B.image src "fig:" caption) <> legend "image" -> do let src = escapeURI $ trim top let alt = B.str $ maybe "image" trim $ lookup "alt" fields @@ -589,9 +605,71 @@ directive' = do Just t -> B.link (escapeURI $ trim t) "" $ B.image src "" alt Nothing -> B.image src "" alt - _ -> return mempty - --- Can contain haracter codes as decimal numbers or + "class" -> do + let attrs = ("", (splitBy isSpace $ trim top), map (\(k,v) -> (k, trimr v)) fields) + -- directive content or the first immediately following element + children <- case body of + "" -> block + _ -> parseFromString parseBlocks body' + return $ B.divWith attrs children + other -> do + pos <- getPosition + addWarning (Just pos) $ "ignoring unknown directive: " ++ other + return mempty + +-- TODO: +-- - Silently ignores illegal fields +-- - Only supports :format: fields with a single format for :raw: roles, +-- change Text.Pandoc.Definition.Format to fix +addNewRole :: String -> [(String, String)] -> RSTParser Blocks +addNewRole roleString fields = do + (role, parentRole) <- parseFromString inheritedRole roleString + customRoles <- stateRstCustomRoles <$> getState + let (baseRole, baseFmt, baseAttr) = + maybe (parentRole, Nothing, nullAttr) id $ + M.lookup parentRole customRoles + fmt = if parentRole == "raw" then lookup "format" fields else baseFmt + annotate :: [String] -> [String] + annotate = maybe id (:) $ + if parentRole == "code" + then lookup "language" fields + else Nothing + attr = let (ident, classes, keyValues) = baseAttr + -- nub in case role name & language class are the same + in (ident, nub . (role :) . annotate $ classes, keyValues) + + -- warn about syntax we ignore + flip mapM_ fields $ \(key, _) -> case key of + "language" -> when (parentRole /= "code") $ addWarning Nothing $ + "ignoring :language: field because the parent of role :" ++ + role ++ ": is :" ++ parentRole ++ ": not :code:" + "format" -> when (parentRole /= "raw") $ addWarning Nothing $ + "ignoring :format: field because the parent of role :" ++ + role ++ ": is :" ++ parentRole ++ ": not :raw:" + _ -> addWarning Nothing $ "ignoring unknown field :" ++ key ++ + ": in definition of role :" ++ role ++ ": in" + when (parentRole == "raw" && countKeys "format" > 1) $ + addWarning Nothing $ + "ignoring :format: fields after the first in the definition of role :" + ++ role ++": in" + when (parentRole == "code" && countKeys "language" > 1) $ + addWarning Nothing $ + "ignoring :language: fields after the first in the definition of role :" + ++ role ++": in" + + updateState $ \s -> s { + stateRstCustomRoles = + M.insert role (baseRole, fmt, attr) customRoles + } + + return $ B.singleton Null + where + countKeys k = length . filter (== k) . map fst $ fields + inheritedRole = + (,) <$> roleName <*> ((char '(' *> roleName <* char ')') <|> pure "span") + + +-- Can contain character codes as decimal numbers or -- hexadecimal numbers, prefixed by 0x, x, \x, U+, u, or \u -- or as XML-style hexadecimal character entities, e.g. ᨫ -- or text, which is used as-is. Comments start with .. @@ -620,9 +698,6 @@ extractUnicodeChar s = maybe Nothing (\c -> Just (c,rest)) mbc where (ds,rest) = span isHexDigit s mbc = safeRead ('\'':'\\':'x':ds ++ "'") -isHexDigit :: Char -> Bool -isHexDigit c = c `elem` "0123456789ABCDEFabcdef" - extractCaption :: RSTParser (Inlines, Blocks) extractCaption = do capt <- trimInlines . mconcat <$> many inline @@ -711,7 +786,7 @@ simpleReferenceName = do referenceName :: RSTParser Inlines referenceName = quotedReferenceName <|> - (try $ simpleReferenceName >>~ lookAhead (char ':')) <|> + (try $ simpleReferenceName <* lookAhead (char ':')) <|> unquotedReferenceName referenceKey :: RSTParser [Char] @@ -930,17 +1005,61 @@ strong = B.strong . trimInlines . mconcat <$> -- Note, this doesn't precisely implement the complex rule in -- http://docutils.sourceforge.net/docs/ref/rst/restructuredtext.html#inline-markup-recognition-rules -- but it should be good enough for most purposes +-- +-- TODO: +-- - Classes are silently discarded in addNewRole +-- - Lacks sensible implementation for title-reference (which is the default) +-- - Allows direct use of the :raw: role, rST only allows inherited use. interpretedRole :: RSTParser Inlines interpretedRole = try $ do (role, contents) <- roleBefore <|> roleAfter - case role of - "sup" -> return $ B.superscript $ B.str contents - "sub" -> return $ B.subscript $ B.str contents - "math" -> return $ B.math contents - _ -> return $ B.str contents --unknown + renderRole contents Nothing role nullAttr + +renderRole :: String -> Maybe String -> String -> Attr -> RSTParser Inlines +renderRole contents fmt role attr = case role of + "sup" -> return $ B.superscript $ B.str contents + "superscript" -> return $ B.superscript $ B.str contents + "sub" -> return $ B.subscript $ B.str contents + "subscript" -> return $ B.subscript $ B.str contents + "emphasis" -> return $ B.emph $ B.str contents + "strong" -> return $ B.strong $ B.str contents + "rfc-reference" -> return $ rfcLink contents + "RFC" -> return $ rfcLink contents + "pep-reference" -> return $ pepLink contents + "PEP" -> return $ pepLink contents + "literal" -> return $ B.codeWith attr contents + "math" -> return $ B.math contents + "title-reference" -> titleRef contents + "title" -> titleRef contents + "t" -> titleRef contents + "code" -> return $ B.codeWith (addClass "sourceCode" attr) contents + "span" -> return $ B.spanWith attr $ B.str contents + "raw" -> return $ B.rawInline (fromMaybe "" fmt) contents + custom -> do + customRoles <- stateRstCustomRoles <$> getState + case M.lookup custom customRoles of + Just (newRole, newFmt, newAttr) -> + renderRole contents newFmt newRole newAttr + Nothing -> do + pos <- getPosition + addWarning (Just pos) $ "ignoring unknown role :" ++ custom ++ ": in" + return $ B.str contents -- Undefined role + where + titleRef ref = return $ B.str ref -- FIXME: Not a sensible behaviour + rfcLink rfcNo = B.link rfcUrl ("RFC " ++ rfcNo) $ B.str ("RFC " ++ rfcNo) + where rfcUrl = "http://www.faqs.org/rfcs/rfc" ++ rfcNo ++ ".html" + pepLink pepNo = B.link pepUrl ("PEP " ++ pepNo) $ B.str ("PEP " ++ pepNo) + where padNo = replicate (4 - length pepNo) '0' ++ pepNo + pepUrl = "http://www.python.org/dev/peps/pep-" ++ padNo ++ "/" + +addClass :: String -> Attr -> Attr +addClass c (ident, classes, keyValues) = (ident, union classes [c], keyValues) + +roleName :: RSTParser String +roleName = many1 (letter <|> char '-') roleMarker :: RSTParser String -roleMarker = char ':' *> many1Till (letter <|> char '-') (char ':') +roleMarker = char ':' *> roleName <* char ':' roleBefore :: RSTParser (String,String) roleBefore = try $ do @@ -1001,7 +1120,7 @@ explicitLink = try $ do referenceLink :: RSTParser Inlines referenceLink = try $ do - (label',ref) <- withRaw (quotedReferenceName <|> simpleReferenceName) >>~ + (label',ref) <- withRaw (quotedReferenceName <|> simpleReferenceName) <* char '_' state <- getState let keyTable = stateKeys state @@ -1069,7 +1188,7 @@ smart :: RSTParser Inlines smart = do getOption readerSmart >>= guard doubleQuoted <|> singleQuoted <|> - choice (map (B.singleton <$>) [apostrophe, dash, ellipses]) + choice [apostrophe, dash, ellipses] singleQuoted :: RSTParser Inlines singleQuoted = try $ do diff --git a/src/Text/Pandoc/Readers/TWiki.hs b/src/Text/Pandoc/Readers/TWiki.hs new file mode 100644 index 000000000..c2325c0ea --- /dev/null +++ b/src/Text/Pandoc/Readers/TWiki.hs @@ -0,0 +1,526 @@ +{-# LANGUAGE RelaxedPolyRec, FlexibleInstances, TypeSynonymInstances #-} +-- RelaxedPolyRec needed for inlinesBetween on GHC < 7 +{- + Copyright (C) 2014 Alexander Sulfrian <alexander.sulfrian@fu-berlin.de> + +This program is free software; you can redistribute it and/or modify +it under the terms of the GNU General Public License as published by +the Free Software Foundation; either version 2 of the License, or +(at your option) any later version. + +This program is distributed in the hope that it will be useful, +but WITHOUT ANY WARRANTY; without even the implied warranty of +MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the +GNU General Public License for more details. + +You should have received a copy of the GNU General Public License +along with this program; if not, write to the Free Software +Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA +-} + +{- | + Module : Text.Pandoc.Readers.TWiki + Copyright : Copyright (C) 2014 Alexander Sulfrian + License : GNU GPL, version 2 or above + + Maintainer : Alexander Sulfrian <alexander.sulfrian@fu-berlin.de> + Stability : alpha + Portability : portable + +Conversion of twiki text to 'Pandoc' document. +-} +module Text.Pandoc.Readers.TWiki ( readTWiki + , readTWikiWithWarnings + ) where + +import Text.Pandoc.Definition +import qualified Text.Pandoc.Builder as B +import Text.Pandoc.Options +import Text.Pandoc.Parsing hiding (enclosed, macro, nested) +import Text.Pandoc.Readers.HTML (htmlTag, isCommentTag) +import Data.Monoid (Monoid, mconcat, mempty) +import Control.Applicative ((<$>), (<*), (*>), (<$)) +import Control.Monad +import Text.Printf (printf) +import Debug.Trace (trace) +import Text.Pandoc.XML (fromEntities) +import Data.Maybe (fromMaybe) +import Text.HTML.TagSoup +import Data.Char (isAlphaNum) +import qualified Data.Foldable as F + +-- | Read twiki from an input string and return a Pandoc document. +readTWiki :: ReaderOptions -- ^ Reader options + -> String -- ^ String to parse (assuming @'\n'@ line endings) + -> Pandoc +readTWiki opts s = + (readWith parseTWiki) def{ stateOptions = opts } (s ++ "\n\n") + +readTWikiWithWarnings :: ReaderOptions -- ^ Reader options + -> String -- ^ String to parse (assuming @'\n'@ line endings) + -> (Pandoc, [String]) +readTWikiWithWarnings opts s = + (readWith parseTWikiWithWarnings) def{ stateOptions = opts } (s ++ "\n\n") + where parseTWikiWithWarnings = do + doc <- parseTWiki + warnings <- stateWarnings <$> getState + return (doc, warnings) + +type TWParser = Parser [Char] ParserState + +-- +-- utility functions +-- + +tryMsg :: String -> TWParser a -> TWParser a +tryMsg msg p = try p <?> msg + +skip :: TWParser a -> TWParser () +skip parser = parser >> return () + +nested :: TWParser a -> TWParser a +nested p = do + nestlevel <- stateMaxNestingLevel <$> getState + guard $ nestlevel > 0 + updateState $ \st -> st{ stateMaxNestingLevel = stateMaxNestingLevel st - 1 } + res <- p + updateState $ \st -> st{ stateMaxNestingLevel = nestlevel } + return res + +htmlElement :: String -> TWParser (Attr, String) +htmlElement tag = tryMsg tag $ do + (TagOpen _ attr, _) <- htmlTag (~== TagOpen tag []) + content <- manyTill anyChar (endtag <|> endofinput) + return (htmlAttrToPandoc attr, trim content) + where + endtag = skip $ htmlTag (~== TagClose tag) + endofinput = lookAhead $ try $ skipMany blankline >> skipSpaces >> eof + trim = dropWhile (=='\n') . reverse . dropWhile (=='\n') . reverse + +htmlAttrToPandoc :: [Attribute String] -> Attr +htmlAttrToPandoc attrs = (ident, classes, keyvals) + where + ident = fromMaybe "" $ lookup "id" attrs + classes = maybe [] words $ lookup "class" attrs + keyvals = [(k,v) | (k,v) <- attrs, k /= "id" && k /= "class"] + +parseHtmlContentWithAttrs :: String -> TWParser a -> TWParser (Attr, [a]) +parseHtmlContentWithAttrs tag parser = do + (attr, content) <- htmlElement tag + parsedContent <- try $ parseContent content + return (attr, parsedContent) + where + parseContent = parseFromString $ nested $ manyTill parser endOfContent + endOfContent = try $ skipMany blankline >> skipSpaces >> eof + +parseHtmlContent :: String -> TWParser a -> TWParser [a] +parseHtmlContent tag p = parseHtmlContentWithAttrs tag p >>= return . snd + +-- +-- main parser +-- + +parseTWiki :: TWParser Pandoc +parseTWiki = do + bs <- mconcat <$> many block + spaces + eof + return $ B.doc bs + + +-- +-- block parsers +-- + +block :: TWParser B.Blocks +block = do + tr <- getOption readerTrace + pos <- getPosition + res <- mempty <$ skipMany1 blankline + <|> blockElements + <|> para + skipMany blankline + when tr $ + trace (printf "line %d: %s" (sourceLine pos) + (take 60 $ show $ B.toList res)) (return ()) + return res + +blockElements :: TWParser B.Blocks +blockElements = choice [ separator + , header + , verbatim + , literal + , list "" + , table + , blockQuote + , noautolink + ] + +separator :: TWParser B.Blocks +separator = tryMsg "separator" $ string "---" >> newline >> return B.horizontalRule + +header :: TWParser B.Blocks +header = tryMsg "header" $ do + string "---" + level <- many1 (char '+') >>= return . length + guard $ level <= 6 + classes <- option [] $ string "!!" >> return ["unnumbered"] + skipSpaces + content <- B.trimInlines . mconcat <$> manyTill inline newline + attr <- registerHeader ("", classes, []) content + return $ B.headerWith attr level $ content + +verbatim :: TWParser B.Blocks +verbatim = (htmlElement "verbatim" <|> htmlElement "pre") + >>= return . (uncurry B.codeBlockWith) + +literal :: TWParser B.Blocks +literal = htmlElement "literal" >>= return . rawBlock + where + format (_, _, kvs) = fromMaybe "html" $ lookup "format" kvs + rawBlock (attrs, content) = B.rawBlock (format attrs) content + +list :: String -> TWParser B.Blocks +list prefix = choice [ bulletList prefix + , orderedList prefix + , definitionList prefix] + +definitionList :: String -> TWParser B.Blocks +definitionList prefix = tryMsg "definitionList" $ do + indent <- lookAhead $ string prefix *> (many1 $ string " ") <* string "$ " + elements <- many $ parseDefinitionListItem (prefix ++ concat indent) + return $ B.definitionList elements + where + parseDefinitionListItem :: String -> TWParser (B.Inlines, [B.Blocks]) + parseDefinitionListItem indent = do + string (indent ++ "$ ") >> skipSpaces + term <- many1Till inline $ string ": " + line <- listItemLine indent $ string "$ " + return $ (mconcat term, [line]) + +bulletList :: String -> TWParser B.Blocks +bulletList prefix = tryMsg "bulletList" $ + parseList prefix (char '*') (char ' ') + +orderedList :: String -> TWParser B.Blocks +orderedList prefix = tryMsg "orderedList" $ + parseList prefix (oneOf "1iIaA") (string ". ") + +parseList :: Show a => String -> TWParser Char -> TWParser a -> TWParser B.Blocks +parseList prefix marker delim = do + (indent, style) <- lookAhead $ string prefix *> listStyle <* delim + blocks <- many $ parseListItem (prefix ++ indent) (char style <* delim) + return $ case style of + '1' -> B.orderedListWith (1, DefaultStyle, DefaultDelim) blocks + 'i' -> B.orderedListWith (1, LowerRoman, DefaultDelim) blocks + 'I' -> B.orderedListWith (1, UpperRoman, DefaultDelim) blocks + 'a' -> B.orderedListWith (1, LowerAlpha, DefaultDelim) blocks + 'A' -> B.orderedListWith (1, UpperAlpha, DefaultDelim) blocks + _ -> B.bulletList blocks + where + listStyle = do + indent <- many1 $ string " " + style <- marker + return (concat indent, style) + +parseListItem :: Show a => String -> TWParser a -> TWParser B.Blocks +parseListItem prefix marker = string prefix >> marker >> listItemLine prefix marker + +listItemLine :: Show a => String -> TWParser a -> TWParser B.Blocks +listItemLine prefix marker = lineContent >>= parseContent >>= return . mconcat + where + lineContent = do + content <- anyLine + continuation <- optionMaybe listContinuation + return $ filterSpaces content ++ "\n" ++ (maybe "" (" " ++) continuation) + filterSpaces = reverse . dropWhile (== ' ') . reverse + listContinuation = notFollowedBy (string prefix >> marker) >> + string " " >> lineContent + parseContent = parseFromString $ many1 $ nestedList <|> parseInline + parseInline = many1Till inline (lastNewline <|> newlineBeforeNestedList) >>= + return . B.plain . mconcat + nestedList = list prefix + lastNewline = try $ char '\n' <* eof + newlineBeforeNestedList = try $ char '\n' <* lookAhead nestedList + +table :: TWParser B.Blocks +table = try $ do + tableHead <- optionMaybe $ many1Till tableParseHeader newline >>= return . unzip + rows <- many1 tableParseRow + return $ buildTable mempty rows $ fromMaybe (align rows, columns rows) tableHead + where + buildTable caption rows (aligns, heads) + = B.table caption aligns heads rows + align rows = replicate (columCount rows) (AlignDefault, 0) + columns rows = replicate (columCount rows) mempty + columCount rows = length $ head rows + +tableParseHeader :: TWParser ((Alignment, Double), B.Blocks) +tableParseHeader = try $ do + char '|' + leftSpaces <- many spaceChar >>= return . length + char '*' + content <- tableColumnContent (char '*' >> skipSpaces >> char '|') + char '*' + rightSpaces <- many spaceChar >>= return . length + optional tableEndOfRow + return (tableAlign leftSpaces rightSpaces, content) + where + tableAlign left right + | left >= 2 && left == right = (AlignCenter, 0) + | left > right = (AlignRight, 0) + | otherwise = (AlignLeft, 0) + +tableParseRow :: TWParser [B.Blocks] +tableParseRow = many1Till tableParseColumn newline + +tableParseColumn :: TWParser B.Blocks +tableParseColumn = char '|' *> skipSpaces *> + tableColumnContent (skipSpaces >> char '|') + <* skipSpaces <* optional tableEndOfRow + +tableEndOfRow :: TWParser Char +tableEndOfRow = lookAhead (try $ char '|' >> char '\n') >> char '|' + +tableColumnContent :: Show a => TWParser a -> TWParser B.Blocks +tableColumnContent end = manyTill content (lookAhead $ try end) >>= return . B.plain . mconcat + where + content = continuation <|> inline + continuation = try $ char '\\' >> newline >> return mempty + +blockQuote :: TWParser B.Blocks +blockQuote = parseHtmlContent "blockquote" block >>= return . B.blockQuote . mconcat + +noautolink :: TWParser B.Blocks +noautolink = do + (_, content) <- htmlElement "noautolink" + st <- getState + setState $ st{ stateAllowLinks = False } + blocks <- try $ parseContent content + setState $ st{ stateAllowLinks = True } + return $ mconcat blocks + where + parseContent = parseFromString $ many $ block + +para :: TWParser B.Blocks +para = many1Till inline endOfParaElement >>= return . result . mconcat + where + endOfParaElement = lookAhead $ endOfInput <|> endOfPara <|> newBlockElement + endOfInput = try $ skipMany blankline >> skipSpaces >> eof + endOfPara = try $ blankline >> skipMany1 blankline + newBlockElement = try $ blankline >> skip blockElements + result content = if F.all (==Space) content + then mempty + else B.para $ B.trimInlines content + + +-- +-- inline parsers +-- + +inline :: TWParser B.Inlines +inline = choice [ whitespace + , br + , macro + , strong + , strongHtml + , strongAndEmph + , emph + , emphHtml + , boldCode + , smart + , link + , htmlComment + , code + , codeHtml + , nop + , autoLink + , str + , symbol + ] <?> "inline" + +whitespace :: TWParser B.Inlines +whitespace = (lb <|> regsp) >>= return + where lb = try $ skipMany spaceChar >> linebreak >> return B.space + regsp = try $ skipMany1 spaceChar >> return B.space + +br :: TWParser B.Inlines +br = try $ string "%BR%" >> return B.linebreak + +linebreak :: TWParser B.Inlines +linebreak = newline >> notFollowedBy newline >> (lastNewline <|> innerNewline) + where lastNewline = eof >> return mempty + innerNewline = return B.space + +between :: (Show b, Monoid c) => TWParser a -> TWParser b -> (TWParser b -> TWParser c) -> TWParser c +between start end p = + mconcat <$> try (start >> notFollowedBy whitespace >> many1Till (p end) end) + +enclosed :: (Show a, Monoid b) => TWParser a -> (TWParser a -> TWParser b) -> TWParser b +enclosed sep p = between sep (try $ sep <* endMarker) p + where + endMarker = lookAhead $ skip endSpace <|> skip (oneOf ".,!?:)|") <|> eof + endSpace = (spaceChar <|> newline) >> return B.space + +macro :: TWParser B.Inlines +macro = macroWithParameters <|> withoutParameters + where + withoutParameters = enclosed (char '%') (\_ -> macroName) >>= return . emptySpan + emptySpan name = buildSpan name [] mempty + +macroWithParameters :: TWParser B.Inlines +macroWithParameters = try $ do + char '%' + name <- macroName + (content, kvs) <- attributes + char '%' + return $ buildSpan name kvs $ B.str content + +buildSpan :: String -> [(String, String)] -> B.Inlines -> B.Inlines +buildSpan className kvs = B.spanWith attrs + where + attrs = ("", ["twiki-macro", className] ++ additionalClasses, kvsWithoutClasses) + additionalClasses = maybe [] words $ lookup "class" kvs + kvsWithoutClasses = [(k,v) | (k,v) <- kvs, k /= "class"] + +macroName :: TWParser String +macroName = do + first <- letter + rest <- many $ alphaNum <|> char '_' + return (first:rest) + +attributes :: TWParser (String, [(String, String)]) +attributes = char '{' *> spnl *> many (attribute <* spnl) <* char '}' >>= + return . foldr (either mkContent mkKvs) ([], []) + where + spnl = skipMany (spaceChar <|> newline) + mkContent c ([], kvs) = (c, kvs) + mkContent c (rest, kvs) = (c ++ " " ++ rest, kvs) + mkKvs kv (cont, rest) = (cont, (kv : rest)) + +attribute :: TWParser (Either String (String, String)) +attribute = withKey <|> withoutKey + where + withKey = try $ do + key <- macroName + char '=' + parseValue False >>= return . (curry Right key) + withoutKey = try $ parseValue True >>= return . Left + parseValue allowSpaces = (withQuotes <|> withoutQuotes allowSpaces) >>= return . fromEntities + withQuotes = between (char '"') (char '"') (\_ -> count 1 $ noneOf ['"']) + withoutQuotes allowSpaces + | allowSpaces == True = many1 $ noneOf "}" + | otherwise = many1 $ noneOf " }" + +nestedInlines :: Show a => TWParser a -> TWParser B.Inlines +nestedInlines end = innerSpace <|> nestedInline + where + innerSpace = try $ whitespace <* (notFollowedBy end) + nestedInline = notFollowedBy whitespace >> nested inline + +strong :: TWParser B.Inlines +strong = try $ enclosed (char '*') nestedInlines >>= return . B.strong + +strongHtml :: TWParser B.Inlines +strongHtml = (parseHtmlContent "strong" inline <|> parseHtmlContent "b" inline) + >>= return . B.strong . mconcat + +strongAndEmph :: TWParser B.Inlines +strongAndEmph = try $ enclosed (string "__") nestedInlines >>= return . B.emph . B.strong + +emph :: TWParser B.Inlines +emph = try $ enclosed (char '_') nestedInlines >>= return . B.emph + +emphHtml :: TWParser B.Inlines +emphHtml = (parseHtmlContent "em" inline <|> parseHtmlContent "i" inline) + >>= return . B.emph . mconcat + +nestedString :: Show a => TWParser a -> TWParser String +nestedString end = innerSpace <|> (count 1 nonspaceChar) + where + innerSpace = try $ many1 spaceChar <* notFollowedBy end + +boldCode :: TWParser B.Inlines +boldCode = try $ enclosed (string "==") nestedString >>= return . B.strong . B.code . fromEntities + +htmlComment :: TWParser B.Inlines +htmlComment = htmlTag isCommentTag >> return mempty + +code :: TWParser B.Inlines +code = try $ enclosed (char '=') nestedString >>= return . B.code . fromEntities + +codeHtml :: TWParser B.Inlines +codeHtml = do + (attrs, content) <- parseHtmlContentWithAttrs "code" anyChar + return $ B.codeWith attrs $ fromEntities content + +autoLink :: TWParser B.Inlines +autoLink = try $ do + state <- getState + guard $ stateAllowLinks state + (text, url) <- parseLink + guard $ checkLink (head $ reverse url) + return $ makeLink (text, url) + where + parseLink = notFollowedBy nop >> (uri <|> emailAddress) + makeLink (text, url) = B.link url "" $ B.str text + checkLink c + | c == '/' = True + | otherwise = isAlphaNum c + +str :: TWParser B.Inlines +str = (many1 alphaNum <|> count 1 characterReference) >>= return . B.str + +nop :: TWParser B.Inlines +nop = try $ (skip exclamation <|> skip nopTag) >> followContent + where + exclamation = char '!' + nopTag = stringAnyCase "<nop>" + followContent = many1 nonspaceChar >>= return . B.str . fromEntities + +symbol :: TWParser B.Inlines +symbol = count 1 nonspaceChar >>= return . B.str + +smart :: TWParser B.Inlines +smart = do + getOption readerSmart >>= guard + doubleQuoted <|> singleQuoted <|> + choice [ apostrophe + , dash + , ellipses + ] + +singleQuoted :: TWParser B.Inlines +singleQuoted = try $ do + singleQuoteStart + withQuoteContext InSingleQuote $ + many1Till inline singleQuoteEnd >>= + (return . B.singleQuoted . B.trimInlines . mconcat) + +doubleQuoted :: TWParser B.Inlines +doubleQuoted = try $ do + doubleQuoteStart + contents <- mconcat <$> many (try $ notFollowedBy doubleQuoteEnd >> inline) + (withQuoteContext InDoubleQuote $ doubleQuoteEnd >> + return (B.doubleQuoted $ B.trimInlines contents)) + <|> (return $ (B.str "\8220") B.<> contents) + +link :: TWParser B.Inlines +link = try $ do + st <- getState + guard $ stateAllowLinks st + setState $ st{ stateAllowLinks = False } + (url, title, content) <- linkText + setState $ st{ stateAllowLinks = True } + return $ B.link url title content + +linkText :: TWParser (String, String, B.Inlines) +linkText = do + string "[[" + url <- many1Till anyChar (char ']') + content <- option [B.str url] linkContent + char ']' + return (url, "", mconcat content) + where + linkContent = (char '[') >> many1Till anyChar (char ']') >>= parseLinkContent + parseLinkContent = parseFromString $ many1 inline diff --git a/src/Text/Pandoc/Readers/TeXMath.hs b/src/Text/Pandoc/Readers/TeXMath.hs index 6bd617f7e..3fee3051e 100644 --- a/src/Text/Pandoc/Readers/TeXMath.hs +++ b/src/Text/Pandoc/Readers/TeXMath.hs @@ -1,5 +1,5 @@ {- -Copyright (C) 2007-2010 John MacFarlane <jgm@berkeley.edu> +Copyright (C) 2007-2014 John MacFarlane <jgm@berkeley.edu> This program is free software; you can redistribute it and/or modify it under the terms of the GNU General Public License as published by @@ -18,7 +18,7 @@ Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA {- | Module : Text.Pandoc.Readers.TeXMath - Copyright : Copyright (C) 2007-2010 John MacFarlane + Copyright : Copyright (C) 2007-2014 John MacFarlane License : GNU GPL, version 2 or above Maintainer : John MacFarlane <jgm@berkeley.edu> @@ -27,7 +27,7 @@ Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA Conversion of TeX math to a list of 'Pandoc' inline elements. -} -module Text.Pandoc.Readers.TeXMath ( readTeXMath, readTeXMath' ) where +module Text.Pandoc.Readers.TeXMath ( texMathToInlines ) where import Text.Pandoc.Definition import Text.TeXMath @@ -35,22 +35,14 @@ import Text.TeXMath -- | Converts a raw TeX math formula to a list of 'Pandoc' inlines. -- Defaults to raw formula between @$@ or @$$@ characters if entire formula -- can't be converted. -readTeXMath' :: MathType +texMathToInlines :: MathType -> String -- ^ String to parse (assumes @'\n'@ line endings) -> [Inline] -readTeXMath' mt inp = case texMathToPandoc dt inp of - Left _ -> [Str (delim ++ inp ++ delim)] - Right res -> res +texMathToInlines mt inp = + case writePandoc dt `fmap` readTeX inp of + Right (Just ils) -> ils + _ -> [Str (delim ++ inp ++ delim)] where (dt, delim) = case mt of DisplayMath -> (DisplayBlock, "$$") InlineMath -> (DisplayInline, "$") -{-# DEPRECATED readTeXMath "Use readTeXMath' from Text.Pandoc.JSON instead" #-} --- | Converts a raw TeX math formula to a list of 'Pandoc' inlines. --- Defaults to raw formula between @$@ characters if entire formula --- can't be converted. (This is provided for backwards compatibility; --- it is better to use @readTeXMath'@, which properly distinguishes --- between display and inline math.) -readTeXMath :: String -- ^ String to parse (assumes @'\n'@ line endings) - -> [Inline] -readTeXMath = readTeXMath' InlineMath diff --git a/src/Text/Pandoc/Readers/Textile.hs b/src/Text/Pandoc/Readers/Textile.hs index 93658cdea..ee64e8f2a 100644 --- a/src/Text/Pandoc/Readers/Textile.hs +++ b/src/Text/Pandoc/Readers/Textile.hs @@ -1,5 +1,6 @@ {- -Copyright (C) 2010 Paul Rivier <paul*rivier#demotera*com> | tr '*#' '.@' +Copyright (C) 2010-2014 Paul Rivier <paul*rivier#demotera*com> | tr '*#' '.@' + and John MacFarlane This program is free software; you can redistribute it and/or modify it under the terms of the GNU General Public License as published by @@ -18,7 +19,7 @@ Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA {- | Module : Text.Pandoc.Readers.Textile - Copyright : Copyright (C) 2010-2012 Paul Rivier and John MacFarlane + Copyright : Copyright (C) 2010-2014 Paul Rivier and John MacFarlane License : GNU GPL, version 2 or above Maintainer : Paul Rivier <paul*rivier#demotera*com> @@ -50,20 +51,22 @@ TODO : refactor common patterns across readers : module Text.Pandoc.Readers.Textile ( readTextile) where - import Text.Pandoc.Definition +import Text.Pandoc.Builder (Inlines, Blocks, trimInlines) import qualified Text.Pandoc.Builder as B -import Text.Pandoc.Shared import Text.Pandoc.Options import Text.Pandoc.Parsing -import Text.Pandoc.Readers.HTML ( htmlTag, isInlineTag, isBlockTag ) +import Text.Pandoc.Readers.HTML ( htmlTag, isBlockTag ) import Text.Pandoc.Readers.LaTeX ( rawLaTeXInline, rawLaTeXBlock ) import Text.HTML.TagSoup (parseTags, innerText, fromAttrib, Tag(..)) import Text.HTML.TagSoup.Match import Data.List ( intercalate ) -import Data.Char ( digitToInt, isUpper ) -import Control.Monad ( guard, liftM ) -import Control.Applicative ((<$>), (*>), (<*)) +import Data.Char ( digitToInt, isUpper) +import Control.Monad ( guard, liftM, when ) +import Text.Printf +import Control.Applicative ((<$>), (*>), (<*), (<$)) +import Data.Monoid +import Debug.Trace (trace) -- | Parse a Textile text and return a Pandoc document. readTextile :: ReaderOptions -- ^ Reader options @@ -95,7 +98,7 @@ parseTextile = do updateState $ \s -> s { stateNotes = reverse reversedNotes } -- now parse it for real... blocks <- parseBlocks - return $ Pandoc nullMeta blocks -- FIXME + return $ Pandoc nullMeta (B.toList blocks) -- FIXME noteMarker :: Parser [Char] ParserState [Char] noteMarker = skipMany spaceChar >> string "fn" >> manyTill digit (char '.') @@ -115,11 +118,11 @@ noteBlock = try $ do return $ replicate (sourceLine endPos - sourceLine startPos) '\n' -- | Parse document blocks -parseBlocks :: Parser [Char] ParserState [Block] -parseBlocks = manyTill block eof +parseBlocks :: Parser [Char] ParserState Blocks +parseBlocks = mconcat <$> manyTill block eof -- | Block parsers list tried in definition order -blockParsers :: [Parser [Char] ParserState Block] +blockParsers :: [Parser [Char] ParserState Blocks] blockParsers = [ codeBlock , header , blockQuote @@ -130,29 +133,37 @@ blockParsers = [ codeBlock , rawLaTeXBlock' , maybeExplicitBlock "table" table , maybeExplicitBlock "p" para + , mempty <$ blanklines ] -- | Any block in the order of definition of blockParsers -block :: Parser [Char] ParserState Block -block = choice blockParsers <?> "block" - -commentBlock :: Parser [Char] ParserState Block +block :: Parser [Char] ParserState Blocks +block = do + res <- choice blockParsers <?> "block" + pos <- getPosition + tr <- getOption readerTrace + when tr $ + trace (printf "line %d: %s" (sourceLine pos) + (take 60 $ show $ B.toList res)) (return ()) + return res + +commentBlock :: Parser [Char] ParserState Blocks commentBlock = try $ do string "###." manyTill anyLine blanklines - return Null + return mempty -codeBlock :: Parser [Char] ParserState Block +codeBlock :: Parser [Char] ParserState Blocks codeBlock = codeBlockBc <|> codeBlockPre -codeBlockBc :: Parser [Char] ParserState Block +codeBlockBc :: Parser [Char] ParserState Blocks codeBlockBc = try $ do string "bc. " contents <- manyTill anyLine blanklines - return $ CodeBlock ("",[],[]) $ unlines contents + return $ B.codeBlock (unlines contents) -- | Code Blocks in Textile are between <pre> and </pre> -codeBlockPre :: Parser [Char] ParserState Block +codeBlockPre :: Parser [Char] ParserState Blocks codeBlockPre = try $ do (t@(TagOpen _ attrs),_) <- htmlTag (tagOpen (=="pre") (const True)) result' <- (innerText . parseTags) `fmap` -- remove internal tags @@ -169,29 +180,29 @@ codeBlockPre = try $ do let classes = words $ fromAttrib "class" t let ident = fromAttrib "id" t let kvs = [(k,v) | (k,v) <- attrs, k /= "id" && k /= "class"] - return $ CodeBlock (ident,classes,kvs) result''' + return $ B.codeBlockWith (ident,classes,kvs) result''' -- | Header of the form "hN. content" with N in 1..6 -header :: Parser [Char] ParserState Block +header :: Parser [Char] ParserState Blocks header = try $ do char 'h' level <- digitToInt <$> oneOf "123456" attr <- attributes char '.' - whitespace - name <- normalizeSpaces <$> manyTill inline blockBreak - attr' <- registerHeader attr (B.fromList name) - return $ Header level attr' name + lookAhead whitespace + name <- trimInlines . mconcat <$> many inline + attr' <- registerHeader attr name + return $ B.headerWith attr' level name -- | Blockquote of the form "bq. content" -blockQuote :: Parser [Char] ParserState Block +blockQuote :: Parser [Char] ParserState Blocks blockQuote = try $ do string "bq" >> attributes >> char '.' >> whitespace - BlockQuote . singleton <$> para + B.blockQuote <$> para -- Horizontal rule -hrule :: Parser [Char] st Block +hrule :: Parser [Char] st Blocks hrule = try $ do skipSpaces start <- oneOf "-*" @@ -199,62 +210,74 @@ hrule = try $ do skipMany (spaceChar <|> char start) newline optional blanklines - return HorizontalRule + return B.horizontalRule -- Lists handling -- | Can be a bullet list or an ordered list. This implementation is -- strict in the nesting, sublist must start at exactly "parent depth -- plus one" -anyList :: Parser [Char] ParserState Block +anyList :: Parser [Char] ParserState Blocks anyList = try $ anyListAtDepth 1 <* blanklines -- | This allow one type of list to be nested into an other type, -- provided correct nesting -anyListAtDepth :: Int -> Parser [Char] ParserState Block +anyListAtDepth :: Int -> Parser [Char] ParserState Blocks anyListAtDepth depth = choice [ bulletListAtDepth depth, orderedListAtDepth depth, definitionList ] -- | Bullet List of given depth, depth being the number of leading '*' -bulletListAtDepth :: Int -> Parser [Char] ParserState Block -bulletListAtDepth depth = try $ BulletList <$> many1 (bulletListItemAtDepth depth) +bulletListAtDepth :: Int -> Parser [Char] ParserState Blocks +bulletListAtDepth depth = try $ B.bulletList <$> many1 (bulletListItemAtDepth depth) -- | Bullet List Item of given depth, depth being the number of -- leading '*' -bulletListItemAtDepth :: Int -> Parser [Char] ParserState [Block] +bulletListItemAtDepth :: Int -> Parser [Char] ParserState Blocks bulletListItemAtDepth = genericListItemAtDepth '*' -- | Ordered List of given depth, depth being the number of -- leading '#' -orderedListAtDepth :: Int -> Parser [Char] ParserState Block +orderedListAtDepth :: Int -> Parser [Char] ParserState Blocks orderedListAtDepth depth = try $ do items <- many1 (orderedListItemAtDepth depth) - return (OrderedList (1, DefaultStyle, DefaultDelim) items) + return $ B.orderedList items -- | Ordered List Item of given depth, depth being the number of -- leading '#' -orderedListItemAtDepth :: Int -> Parser [Char] ParserState [Block] +orderedListItemAtDepth :: Int -> Parser [Char] ParserState Blocks orderedListItemAtDepth = genericListItemAtDepth '#' -- | Common implementation of list items -genericListItemAtDepth :: Char -> Int -> Parser [Char] ParserState [Block] +genericListItemAtDepth :: Char -> Int -> Parser [Char] ParserState Blocks genericListItemAtDepth c depth = try $ do count depth (char c) >> attributes >> whitespace - p <- many listInline + p <- mconcat <$> many listInline newline - sublist <- option [] (singleton <$> anyListAtDepth (depth + 1)) - return (Plain p : sublist) + sublist <- option mempty (anyListAtDepth (depth + 1)) + return $ (B.plain p) <> sublist -- | A definition list is a set of consecutive definition items -definitionList :: Parser [Char] ParserState Block -definitionList = try $ DefinitionList <$> many1 definitionListItem +definitionList :: Parser [Char] ParserState Blocks +definitionList = try $ B.definitionList <$> many1 definitionListItem -- | List start character. -listStart :: Parser [Char] st Char -listStart = oneOf "*#-" +listStart :: Parser [Char] ParserState () +listStart = genericListStart '*' + <|> () <$ genericListStart '#' + <|> () <$ definitionListStart + +genericListStart :: Char -> Parser [Char] st () +genericListStart c = () <$ try (many1 (char c) >> whitespace) + +definitionListStart :: Parser [Char] ParserState Inlines +definitionListStart = try $ do + char '-' + whitespace + trimInlines . mconcat <$> + many1Till inline (try (string ":=")) <* optional whitespace -listInline :: Parser [Char] ParserState Inline +listInline :: Parser [Char] ParserState Inlines listInline = try (notFollowedBy newline >> inline) <|> try (endline <* notFollowedBy listStart) @@ -262,16 +285,15 @@ listInline = try (notFollowedBy newline >> inline) -- the term defined, then spaces and ":=". The definition follows, on -- the same single line, or spaned on multiple line, after a line -- break. -definitionListItem :: Parser [Char] ParserState ([Inline], [[Block]]) +definitionListItem :: Parser [Char] ParserState (Inlines, [Blocks]) definitionListItem = try $ do - string "- " - term <- many1Till inline (try (whitespace >> string ":=")) + term <- definitionListStart def' <- multilineDef <|> inlineDef return (term, def') - where inlineDef :: Parser [Char] ParserState [[Block]] - inlineDef = liftM (\d -> [[Plain d]]) - $ optional whitespace >> many listInline <* newline - multilineDef :: Parser [Char] ParserState [[Block]] + where inlineDef :: Parser [Char] ParserState [Blocks] + inlineDef = liftM (\d -> [B.plain d]) + $ optional whitespace >> (trimInlines . mconcat <$> many listInline) <* newline + multilineDef :: Parser [Char] ParserState [Blocks] multilineDef = try $ do optional whitespace >> newline s <- many1Till anyChar (try (string "=:" >> newline)) @@ -279,68 +301,61 @@ definitionListItem = try $ do ds <- parseFromString parseBlocks (s ++ "\n\n") return [ds] --- | This terminates a block such as a paragraph. Because of raw html --- blocks support, we have to lookAhead for a rawHtmlBlock. -blockBreak :: Parser [Char] ParserState () -blockBreak = try (newline >> blanklines >> return ()) <|> - try (optional spaces >> lookAhead rawHtmlBlock >> return ()) - -- raw content -- | A raw Html Block, optionally followed by blanklines -rawHtmlBlock :: Parser [Char] ParserState Block +rawHtmlBlock :: Parser [Char] ParserState Blocks rawHtmlBlock = try $ do + skipMany spaceChar (_,b) <- htmlTag isBlockTag optional blanklines - return $ RawBlock (Format "html") b + return $ B.rawBlock "html" b -- | Raw block of LaTeX content -rawLaTeXBlock' :: Parser [Char] ParserState Block +rawLaTeXBlock' :: Parser [Char] ParserState Blocks rawLaTeXBlock' = do guardEnabled Ext_raw_tex - RawBlock (Format "latex") <$> (rawLaTeXBlock <* spaces) + B.rawBlock "latex" <$> (rawLaTeXBlock <* spaces) -- | In textile, paragraphs are separated by blank lines. -para :: Parser [Char] ParserState Block -para = try $ Para . normalizeSpaces <$> manyTill inline blockBreak - +para :: Parser [Char] ParserState Blocks +para = B.para . trimInlines . mconcat <$> many1 inline -- Tables -- | A table cell spans until a pipe | -tableCell :: Parser [Char] ParserState TableCell +tableCell :: Parser [Char] ParserState Blocks tableCell = do c <- many1 (noneOf "|\n") - content <- parseFromString (many1 inline) c - return $ [ Plain $ normalizeSpaces content ] + content <- trimInlines . mconcat <$> parseFromString (many1 inline) c + return $ B.plain content -- | A table row is made of many table cells -tableRow :: Parser [Char] ParserState [TableCell] +tableRow :: Parser [Char] ParserState [Blocks] tableRow = try $ ( char '|' *> (endBy1 tableCell (optional blankline *> char '|')) <* newline) -- | Many table rows -tableRows :: Parser [Char] ParserState [[TableCell]] +tableRows :: Parser [Char] ParserState [[Blocks]] tableRows = many1 tableRow -- | Table headers are made of cells separated by a tag "|_." -tableHeaders :: Parser [Char] ParserState [TableCell] +tableHeaders :: Parser [Char] ParserState [Blocks] tableHeaders = let separator = (try $ string "|_.") in try $ ( separator *> (sepBy1 tableCell separator) <* char '|' <* newline ) -- | A table with an optional header. Current implementation can -- handle tables with and without header, but will parse cells -- alignment attributes as content. -table :: Parser [Char] ParserState Block +table :: Parser [Char] ParserState Blocks table = try $ do - headers <- option [] tableHeaders + headers <- option mempty tableHeaders rows <- tableRows blanklines let nbOfCols = max (length headers) (length $ head rows) - return $ Table [] - (replicate nbOfCols AlignDefault) - (replicate nbOfCols 0.0) + return $ B.table mempty + (zip (replicate nbOfCols AlignDefault) (replicate nbOfCols 0.0)) headers rows @@ -348,8 +363,8 @@ table = try $ do -- | Blocks like 'p' and 'table' do not need explicit block tag. -- However, they can be used to set HTML/CSS attributes when needed. maybeExplicitBlock :: String -- ^ block tag name - -> Parser [Char] ParserState Block -- ^ implicit block - -> Parser [Char] ParserState Block + -> Parser [Char] ParserState Blocks -- ^ implicit block + -> Parser [Char] ParserState Blocks maybeExplicitBlock name blk = try $ do optional $ try $ string name >> attributes >> char '.' >> optional whitespace >> optional endline @@ -363,73 +378,74 @@ maybeExplicitBlock name blk = try $ do -- | Any inline element -inline :: Parser [Char] ParserState Inline -inline = choice inlineParsers <?> "inline" +inline :: Parser [Char] ParserState Inlines +inline = do + choice inlineParsers <?> "inline" -- | Inline parsers tried in order -inlineParsers :: [Parser [Char] ParserState Inline] +inlineParsers :: [Parser [Char] ParserState Inlines] inlineParsers = [ str , whitespace , endline , code , escapedInline - , htmlSpan + , inlineMarkup + , groupedInlineMarkup , rawHtmlInline , rawLaTeXInline' , note - , try $ (char '[' *> inlineMarkup <* char ']') - , inlineMarkup , link , image , mark - , (Str . (:[])) <$> characterReference + , (B.str . (:[])) <$> characterReference , smartPunctuation inline , symbol ] -- | Inline markups -inlineMarkup :: Parser [Char] ParserState Inline -inlineMarkup = choice [ simpleInline (string "??") (Cite []) - , simpleInline (string "**") Strong - , simpleInline (string "__") Emph - , simpleInline (char '*') Strong - , simpleInline (char '_') Emph - , simpleInline (char '+') Emph -- approximates underline - , simpleInline (char '-' <* notFollowedBy (char '-')) Strikeout - , simpleInline (char '^') Superscript - , simpleInline (char '~') Subscript +inlineMarkup :: Parser [Char] ParserState Inlines +inlineMarkup = choice [ simpleInline (string "??") (B.cite []) + , simpleInline (string "**") B.strong + , simpleInline (string "__") B.emph + , simpleInline (char '*') B.strong + , simpleInline (char '_') B.emph + , simpleInline (char '+') B.emph -- approximates underline + , simpleInline (char '-' <* notFollowedBy (char '-')) B.strikeout + , simpleInline (char '^') B.superscript + , simpleInline (char '~') B.subscript + , simpleInline (char '%') id ] -- | Trademark, registered, copyright -mark :: Parser [Char] st Inline +mark :: Parser [Char] st Inlines mark = try $ char '(' >> (try tm <|> try reg <|> copy) -reg :: Parser [Char] st Inline +reg :: Parser [Char] st Inlines reg = do oneOf "Rr" char ')' - return $ Str "\174" + return $ B.str "\174" -tm :: Parser [Char] st Inline +tm :: Parser [Char] st Inlines tm = do oneOf "Tt" oneOf "Mm" char ')' - return $ Str "\8482" + return $ B.str "\8482" -copy :: Parser [Char] st Inline +copy :: Parser [Char] st Inlines copy = do oneOf "Cc" char ')' - return $ Str "\169" + return $ B.str "\169" -note :: Parser [Char] ParserState Inline +note :: Parser [Char] ParserState Inlines note = try $ do ref <- (char '[' *> many1 digit <* char ']') notes <- stateNotes <$> getState case lookup ref notes of Nothing -> fail "note not found" - Just raw -> liftM Note $ parseFromString parseBlocks raw + Just raw -> B.note <$> parseFromString parseBlocks raw -- | Special chars markupChars :: [Char] @@ -450,7 +466,7 @@ wordBoundaries = markupChars ++ stringBreakers hyphenedWords :: Parser [Char] ParserState String hyphenedWords = do x <- wordChunk - xs <- many (try $ char '-' >> wordChunk) + xs <- many (try $ char '-' >> wordChunk) return $ intercalate "-" (x:xs) wordChunk :: Parser [Char] ParserState String @@ -462,99 +478,104 @@ wordChunk = try $ do return $ hd:tl -- | Any string -str :: Parser [Char] ParserState Inline +str :: Parser [Char] ParserState Inlines str = do baseStr <- hyphenedWords -- RedCloth compliance : if parsed word is uppercase and immediatly -- followed by parens, parens content is unconditionally word acronym fullStr <- option baseStr $ try $ do guard $ all isUpper baseStr - acro <- enclosed (char '(') (char ')') anyChar + acro <- enclosed (char '(') (char ')') anyChar' return $ concat [baseStr, " (", acro, ")"] updateLastStrPos - return $ Str fullStr - --- | Textile allows HTML span infos, we discard them -htmlSpan :: Parser [Char] ParserState Inline -htmlSpan = try $ Str <$> ( char '%' *> attributes *> manyTill anyChar (char '%') ) + return $ B.str fullStr -- | Some number of space chars -whitespace :: Parser [Char] ParserState Inline -whitespace = many1 spaceChar >> return Space <?> "whitespace" +whitespace :: Parser [Char] st Inlines +whitespace = many1 spaceChar >> return B.space <?> "whitespace" -- | In Textile, an isolated endline character is a line break -endline :: Parser [Char] ParserState Inline +endline :: Parser [Char] ParserState Inlines endline = try $ do - newline >> notFollowedBy blankline - return LineBreak + newline + notFollowedBy blankline + notFollowedBy listStart + notFollowedBy rawHtmlBlock + return B.linebreak -rawHtmlInline :: Parser [Char] ParserState Inline -rawHtmlInline = RawInline (Format "html") . snd <$> htmlTag isInlineTag +rawHtmlInline :: Parser [Char] ParserState Inlines +rawHtmlInline = B.rawInline "html" . snd <$> htmlTag (const True) -- | Raw LaTeX Inline -rawLaTeXInline' :: Parser [Char] ParserState Inline +rawLaTeXInline' :: Parser [Char] ParserState Inlines rawLaTeXInline' = try $ do guardEnabled Ext_raw_tex - rawLaTeXInline + B.singleton <$> rawLaTeXInline -- | Textile standard link syntax is "label":target. But we -- can also have ["label":target]. -link :: Parser [Char] ParserState Inline -link = linkB <|> linkNoB - -linkNoB :: Parser [Char] ParserState Inline -linkNoB = try $ do - name <- surrounded (char '"') inline - char ':' - let stopChars = "!.,;:" - url <- manyTill nonspaceChar (lookAhead $ space <|> try (oneOf stopChars >> (space <|> newline))) - let name' = if name == [Str "$"] then [Str url] else name - return $ Link name' (url, "") - -linkB :: Parser [Char] ParserState Inline -linkB = try $ do - char '[' - name <- surrounded (char '"') inline +link :: Parser [Char] ParserState Inlines +link = try $ do + bracketed <- (True <$ char '[') <|> return False + char '"' *> notFollowedBy (oneOf " \t\n\r") + attr <- attributes + name <- trimInlines . mconcat <$> + withQuoteContext InDoubleQuote (many1Till inline (char '"')) char ':' - url <- manyTill nonspaceChar (char ']') - let name' = if name == [Str "$"] then [Str url] else name - return $ Link name' (url, "") + let stop = if bracketed + then char ']' + else lookAhead $ space <|> + try (oneOf "!.,;:" *> (space <|> newline)) + url <- manyTill nonspaceChar stop + let name' = if B.toList name == [Str "$"] then B.str url else name + return $ if attr == nullAttr + then B.link url "" name' + else B.spanWith attr $ B.link url "" name' -- | image embedding -image :: Parser [Char] ParserState Inline +image :: Parser [Char] ParserState Inlines image = try $ do char '!' >> notFollowedBy space - src <- manyTill anyChar (lookAhead $ oneOf "!(") - alt <- option "" (try $ (char '(' >> manyTill anyChar (char ')'))) + src <- manyTill anyChar' (lookAhead $ oneOf "!(") + alt <- option "" (try $ (char '(' >> manyTill anyChar' (char ')'))) char '!' - return $ Image [Str alt] (src, alt) + return $ B.image src alt (B.str alt) -escapedInline :: Parser [Char] ParserState Inline +escapedInline :: Parser [Char] ParserState Inlines escapedInline = escapedEqs <|> escapedTag -escapedEqs :: Parser [Char] ParserState Inline -escapedEqs = Str <$> (try $ string "==" *> manyTill anyChar (try $ string "==")) +escapedEqs :: Parser [Char] ParserState Inlines +escapedEqs = B.str <$> + (try $ string "==" *> manyTill anyChar' (try $ string "==")) -- | literal text escaped btw <notextile> tags -escapedTag :: Parser [Char] ParserState Inline -escapedTag = Str <$> - (try $ string "<notextile>" *> manyTill anyChar (try $ string "</notextile>")) +escapedTag :: Parser [Char] ParserState Inlines +escapedTag = B.str <$> + (try $ string "<notextile>" *> + manyTill anyChar' (try $ string "</notextile>")) -- | Any special symbol defined in wordBoundaries -symbol :: Parser [Char] ParserState Inline -symbol = Str . singleton <$> (oneOf wordBoundaries <|> oneOf markupChars) +symbol :: Parser [Char] ParserState Inlines +symbol = B.str . singleton <$> (notFollowedBy newline *> + notFollowedBy rawHtmlBlock *> + oneOf wordBoundaries) -- | Inline code -code :: Parser [Char] ParserState Inline +code :: Parser [Char] ParserState Inlines code = code1 <|> code2 -code1 :: Parser [Char] ParserState Inline -code1 = Code nullAttr <$> surrounded (char '@') anyChar +-- any character except a newline before a blank line +anyChar' :: Parser [Char] ParserState Char +anyChar' = + satisfy (/='\n') <|> (try $ char '\n' <* notFollowedBy blankline) -code2 :: Parser [Char] ParserState Inline +code1 :: Parser [Char] ParserState Inlines +code1 = B.code <$> surrounded (char '@') anyChar' + +code2 :: Parser [Char] ParserState Inlines code2 = do htmlTag (tagOpen (=="tt") null) - Code nullAttr <$> manyTill anyChar (try $ htmlTag $ tagClose (=="tt")) + B.code <$> manyTill anyChar' (try $ htmlTag $ tagClose (=="tt")) -- | Html / CSS attributes attributes :: Parser [Char] ParserState Attr @@ -566,7 +587,7 @@ attribute = classIdAttr <|> styleAttr <|> langAttr classIdAttr :: Parser [Char] ParserState (Attr -> Attr) classIdAttr = try $ do -- (class class #id) char '(' - ws <- words `fmap` manyTill anyChar (char ')') + ws <- words `fmap` manyTill anyChar' (char ')') case reverse ws of [] -> return $ \(_,_,keyvals) -> ("",[],keyvals) (('#':ident'):classes') -> return $ \(_,_,keyvals) -> @@ -576,28 +597,50 @@ classIdAttr = try $ do -- (class class #id) styleAttr :: Parser [Char] ParserState (Attr -> Attr) styleAttr = do - style <- try $ enclosed (char '{') (char '}') anyChar + style <- try $ enclosed (char '{') (char '}') anyChar' return $ \(id',classes,keyvals) -> (id',classes,("style",style):keyvals) langAttr :: Parser [Char] ParserState (Attr -> Attr) langAttr = do - lang <- try $ enclosed (char '[') (char ']') anyChar + lang <- try $ enclosed (char '[') (char ']') alphaNum return $ \(id',classes,keyvals) -> (id',classes,("lang",lang):keyvals) -- | Parses material surrounded by a parser. surrounded :: Parser [Char] st t -- ^ surrounding parser -> Parser [Char] st a -- ^ content parser (to be used repeatedly) -> Parser [Char] st [a] -surrounded border = enclosed (border *> notFollowedBy (oneOf " \t\n\r")) (try border) +surrounded border = + enclosed (border *> notFollowedBy (oneOf " \t\n\r")) (try border) --- | Inlines are most of the time of the same form simpleInline :: Parser [Char] ParserState t -- ^ surrounding parser - -> ([Inline] -> Inline) -- ^ Inline constructor - -> Parser [Char] ParserState Inline -- ^ content parser (to be used repeatedly) -simpleInline border construct = surrounded border inlineWithAttribute >>= - return . construct . normalizeSpaces - where inlineWithAttribute = (try $ optional attributes) >> inline + -> (Inlines -> Inlines) -- ^ Inline constructor + -> Parser [Char] ParserState Inlines -- ^ content parser (to be used repeatedly) +simpleInline border construct = try $ do + st <- getState + pos <- getPosition + let afterString = stateLastStrPos st == Just pos + guard $ not afterString + border *> notFollowedBy (oneOf " \t\n\r") + attr <- attributes + body <- trimInlines . mconcat <$> + withQuoteContext InSingleQuote + (manyTill (notFollowedBy newline >> inline) + (try border <* notFollowedBy alphaNum)) + return $ construct $ + if attr == nullAttr + then body + else B.spanWith attr body + +groupedInlineMarkup :: Parser [Char] ParserState Inlines +groupedInlineMarkup = try $ do + char '[' + sp1 <- option mempty $ B.space <$ whitespace + result <- withQuoteContext InSingleQuote inlineMarkup + sp2 <- option mempty $ B.space <$ whitespace + char ']' + return $ sp1 <> result <> sp2 -- | Create a singleton list singleton :: a -> [a] singleton x = [x] + diff --git a/src/Text/Pandoc/Readers/Txt2Tags.hs b/src/Text/Pandoc/Readers/Txt2Tags.hs new file mode 100644 index 000000000..6f8c19ac7 --- /dev/null +++ b/src/Text/Pandoc/Readers/Txt2Tags.hs @@ -0,0 +1,579 @@ +{-# LANGUAGE ViewPatterns #-} +{- +Copyright (C) 2014 Matthew Pickering <matthewtpickering@gmail.com> + +This program is free software; you can redistribute it and/or modify +it under the terms of the GNU General Public License as published by +the Free Software Foundation; either version 2 of the License, or +(at your option) any later version. + +This program is distributed in the hope that it will be useful, +but WITHOUT ANY WARRANTY; without even the implied warranty of +MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the +GNU General Public License for more details. + +You should have received a copy of the GNU General Public License +along with this program; if not, write to the Free Software +Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA +-} + +{- | + Module : Text.Pandoc.Readers.Txt2Tags + Copyright : Copyright (C) 2014 Matthew Pickering + License : GNU GPL, version 2 or above + + Maintainer : Matthew Pickering <matthewtpickering@gmail.com> + +Conversion of txt2tags formatted plain text to 'Pandoc' document. +-} +module Text.Pandoc.Readers.Txt2Tags ( readTxt2Tags + , getT2TMeta + , T2TMeta (..) + , readTxt2TagsNoMacros) + where + +import qualified Text.Pandoc.Builder as B +import Text.Pandoc.Builder ( Inlines, Blocks, (<>) + , trimInlines ) +import Text.Pandoc.Definition +import Text.Pandoc.Options +import Text.Pandoc.Shared (escapeURI,compactify', compactify'DL) +import Text.Pandoc.Parsing hiding (space, spaces, uri, macro) +import Control.Applicative ((<$>), (<$), (<*>), (<*), (*>)) +import Data.Char (toLower) +import Data.List (transpose, intersperse, intercalate) +import Data.Maybe (fromMaybe) +import Data.Monoid (Monoid, mconcat, mempty, mappend) +--import Network.URI (isURI) -- Not sure whether to use this function +import Control.Monad (void, guard, when) +import Data.Default +import Control.Monad.Reader (Reader, runReader, asks) + +import Data.Time.LocalTime (getZonedTime) +import Text.Pandoc.Compat.Directory(getModificationTime) +import Data.Time.Format (formatTime) +import System.Locale (defaultTimeLocale) +import System.IO.Error (catchIOError) + +type T2T = ParserT String ParserState (Reader T2TMeta) + +-- | An object for the T2T macros meta information +-- the contents of each field is simply substituted verbatim into the file +data T2TMeta = T2TMeta { + date :: String -- ^ Current date + , mtime :: String -- ^ Last modification time of infile + , infile :: FilePath -- ^ Input file + , outfile :: FilePath -- ^ Output file + } deriving Show + +instance Default T2TMeta where + def = T2TMeta "" "" "" "" + +-- | Get the meta information required by Txt2Tags macros +getT2TMeta :: [FilePath] -> FilePath -> IO T2TMeta +getT2TMeta inps out = do + curDate <- formatTime defaultTimeLocale "%F" <$> getZonedTime + let getModTime = fmap (formatTime defaultTimeLocale "%T") . + getModificationTime + curMtime <- case inps of + [] -> formatTime defaultTimeLocale "%T" <$> getZonedTime + _ -> catchIOError + (maximum <$> mapM getModTime inps) + (const (return "")) + return $ T2TMeta curDate curMtime (intercalate ", " inps) out + +-- | Read Txt2Tags from an input string returning a Pandoc document +readTxt2Tags :: T2TMeta -> ReaderOptions -> String -> Pandoc +readTxt2Tags t opts s = flip runReader t $ readWithM parseT2T (def {stateOptions = opts}) (s ++ "\n\n") + +-- | Read Txt2Tags (ignoring all macros) from an input string returning +-- a Pandoc document +readTxt2TagsNoMacros :: ReaderOptions -> String -> Pandoc +readTxt2TagsNoMacros = readTxt2Tags def + +parseT2T :: T2T Pandoc +parseT2T = do + -- Parse header if standalone flag is set + standalone <- getOption readerStandalone + when standalone parseHeader + body <- mconcat <$> manyTill block eof + meta' <- stateMeta <$> getState + return $ Pandoc meta' (B.toList body) + +parseHeader :: T2T () +parseHeader = do + () <$ try blankline <|> header + meta <- stateMeta <$> getState + optional blanklines + config <- manyTill setting (notFollowedBy setting) + -- TODO: Handle settings better + let settings = foldr (\(k,v) -> B.setMeta k (MetaString v)) meta config + updateState (\s -> s {stateMeta = settings}) <* optional blanklines + +header :: T2T () +header = titleline >> authorline >> dateline + +headerline :: B.ToMetaValue a => String -> T2T a -> T2T () +headerline field p = (() <$ try blankline) + <|> (p >>= updateState . B.setMeta field) + +titleline :: T2T () +titleline = + headerline "title" (trimInlines . mconcat <$> manyTill inline newline) + +authorline :: T2T () +authorline = + headerline "author" (sepBy author (char ';') <* newline) + where + author = trimInlines . mconcat <$> many (notFollowedBy (char ';' <|> newline) >> inline) + +dateline :: T2T () +dateline = headerline "date" (trimInlines . mconcat <$> manyTill inline newline) + +type Keyword = String +type Value = String + +setting :: T2T (Keyword, Value) +setting = do + string "%!" + keyword <- ignoreSpacesCap (many1 alphaNum) + char ':' + value <- ignoreSpacesCap (manyTill anyChar (newline)) + return (keyword, value) + +-- Blocks + +parseBlocks :: T2T Blocks +parseBlocks = mconcat <$> manyTill block eof + +block :: T2T Blocks +block = do + choice + [ mempty <$ blanklines + , quote + , hrule -- hrule must go above title + , title + , commentBlock + , verbatim + , rawBlock + , taggedBlock + , list + , table + , para + ] + +title :: T2T Blocks +title = try $ balancedTitle '+' <|> balancedTitle '=' + +balancedTitle :: Char -> T2T Blocks +balancedTitle c = try $ do + spaces + level <- length <$> many1 (char c) + guard (level <= 5) -- Max header level 5 + heading <- manyTill (noneOf "\n\r") (count level (char c)) + label <- optionMaybe (enclosed (char '[') (char ']') (alphaNum <|> oneOf "_-")) + many spaceChar *> newline + let attr = maybe nullAttr (\x -> (x, [], [])) label + return $ B.headerWith attr level (trimInlines $ B.text heading) + +para :: T2T Blocks +para = try $ do + ils <- parseInlines + nl <- option False (True <$ newline) + option (B.plain ils) (guard nl >> notFollowedBy listStart >> return (B.para ils)) + where + listStart = try bulletListStart <|> orderedListStart + +commentBlock :: T2T Blocks +commentBlock = try (blockMarkupArea (anyLine) (const mempty) "%%%") <|> comment + +-- Seperator and Strong line treated the same +hrule :: T2T Blocks +hrule = try $ do + spaces + line <- many1 (oneOf "=-_") + guard (length line >= 20) + B.horizontalRule <$ blankline + +quote :: T2T Blocks +quote = try $ do + lookAhead tab + rawQuote <- many1 (tab *> optional spaces *> anyLine) + contents <- parseFromString parseBlocks (intercalate "\n" rawQuote ++ "\n\n") + return $ B.blockQuote contents + +commentLine :: T2T Inlines +commentLine = comment + +-- List Parsing code from Org Reader + +list :: T2T Blocks +list = choice [bulletList, orderedList, definitionList] + +bulletList :: T2T Blocks +bulletList = B.bulletList . compactify' + <$> many1 (listItem bulletListStart parseBlocks) + +orderedList :: T2T Blocks +orderedList = B.orderedList . compactify' + <$> many1 (listItem orderedListStart parseBlocks) + +definitionList :: T2T Blocks +definitionList = try $ do + B.definitionList . compactify'DL <$> + many1 (listItem definitionListStart definitionListEnd) + +definitionListEnd :: T2T (Inlines, [Blocks]) +definitionListEnd = (,) <$> (mconcat <$> manyTill inline newline) <*> ((:[]) <$> parseBlocks) + +genericListStart :: T2T Char + -> T2T Int +genericListStart listMarker = try $ + (2+) <$> (length <$> many spaceChar + <* listMarker <* space <* notFollowedBy space) + +-- parses bullet list \start and returns its length (excl. following whitespace) +bulletListStart :: T2T Int +bulletListStart = genericListStart (char '-') + +orderedListStart :: T2T Int +orderedListStart = genericListStart (char '+' ) + +definitionListStart :: T2T Int +definitionListStart = genericListStart (char ':') + +-- parse raw text for one list item, excluding start marker and continuations +listItem :: T2T Int + -> T2T a + -> T2T a +listItem start end = try $ do + markerLength <- try start + firstLine <- anyLineNewline + blank <- option "" ("\n" <$ blankline) + rest <- concat <$> many (listContinuation markerLength) + parseFromString end $ firstLine ++ blank ++ rest + +-- continuation of a list item - indented and separated by blankline or endline. +-- Note: nested lists are parsed as continuations. +listContinuation :: Int + -> T2T String +listContinuation markerLength = try $ + notFollowedBy' (blankline >> blankline) + *> (mappend <$> (concat <$> many1 listLine) + <*> many blankline) + where listLine = try $ indentWith markerLength *> anyLineNewline + +anyLineNewline :: T2T String +anyLineNewline = (++ "\n") <$> anyLine + +indentWith :: Int -> T2T String +indentWith n = count n space + +-- Table + +table :: T2T Blocks +table = try $ do + tableHeader <- fmap snd <$> option mempty (try headerRow) + rows <- many1 (many commentLine *> tableRow) + let columns = transpose rows + let ncolumns = length columns + let aligns = map (foldr1 findAlign) (map (map fst) columns) + let rows' = map (map snd) rows + let size = maximum (map length rows') + let rowsPadded = map (pad size) rows' + let headerPadded = if (not (null tableHeader)) then pad size tableHeader else mempty + return $ B.table mempty + (zip aligns (replicate ncolumns 0.0)) + headerPadded rowsPadded + +pad :: (Show a, Monoid a) => Int -> [a] -> [a] +pad n xs = xs ++ (replicate (n - length xs) mempty) + + +findAlign :: Alignment -> Alignment -> Alignment +findAlign x y + | x == y = x + | otherwise = AlignDefault + +headerRow :: T2T [(Alignment, Blocks)] +headerRow = genericRow (string "||") + +tableRow :: T2T [(Alignment, Blocks)] +tableRow = genericRow (char '|') + +genericRow :: T2T a -> T2T [(Alignment, Blocks)] +genericRow start = try $ do + spaces *> start + manyTill tableCell newline <?> "genericRow" + + +tableCell :: T2T (Alignment, Blocks) +tableCell = try $ do + leftSpaces <- length <$> lookAhead (many1 space) -- Case of empty cell means we must lookAhead + content <- (manyTill inline (try $ lookAhead (cellEnd))) + rightSpaces <- length <$> many space + let align = + case compare leftSpaces rightSpaces of + LT -> AlignLeft + EQ -> AlignCenter + GT -> AlignRight + endOfCell + return $ (align, B.plain (B.trimInlines $ mconcat content)) + where + cellEnd = (void newline <|> (many1 space *> endOfCell)) + +endOfCell :: T2T () +endOfCell = try (skipMany1 $ char '|') <|> ( () <$ lookAhead newline) + +-- Raw area + +verbatim :: T2T Blocks +verbatim = genericBlock anyLineNewline B.codeBlock "```" + +rawBlock :: T2T Blocks +rawBlock = genericBlock anyLineNewline (B.para . B.str) "\"\"\"" + +taggedBlock :: T2T Blocks +taggedBlock = do + target <- getTarget + genericBlock anyLineNewline (B.rawBlock target) "'''" + +-- Generic + +genericBlock :: Monoid a => T2T a -> (a -> Blocks) -> String -> T2T Blocks +genericBlock p f s = blockMarkupArea p f s <|> blockMarkupLine p f s + +blockMarkupArea :: Monoid a => (T2T a) -> (a -> Blocks) -> String -> T2T Blocks +blockMarkupArea p f s = try $ (do + string s *> blankline + f . mconcat <$> (manyTill p (eof <|> void (string s *> blankline)))) + +blockMarkupLine :: T2T a -> (a -> Blocks) -> String -> T2T Blocks +blockMarkupLine p f s = try (f <$> (string s *> space *> p)) + +-- Can be in either block or inline position +comment :: Monoid a => T2T a +comment = try $ do + atStart + notFollowedBy macro + mempty <$ (char '%' *> anyLine) + +-- Inline + +parseInlines :: T2T Inlines +parseInlines = trimInlines . mconcat <$> many1 inline + +inline :: T2T Inlines +inline = do + choice + [ endline + , macro + , commentLine + , whitespace + , url + , link + , image + , bold + , underline + , code + , raw + , tagged + , strike + , italic + , code + , str + , symbol + ] + +bold :: T2T Inlines +bold = inlineMarkup inline B.strong '*' (B.str) + +underline :: T2T Inlines +underline = inlineMarkup inline B.emph '_' (B.str) + +strike :: T2T Inlines +strike = inlineMarkup inline B.strikeout '-' (B.str) + +italic :: T2T Inlines +italic = inlineMarkup inline B.emph '/' (B.str) + +code :: T2T Inlines +code = inlineMarkup ((:[]) <$> anyChar) B.code '`' id + +raw :: T2T Inlines +raw = inlineMarkup ((:[]) <$> anyChar) B.text '"' id + +tagged :: T2T Inlines +tagged = do + target <- getTarget + inlineMarkup ((:[]) <$> anyChar) (B.rawInline target) '\'' id + +-- Parser for markup indicated by a double character. +-- Inline markup is greedy and glued +-- Greedy meaning ***a*** = Bold [Str "*a*"] +-- Glued meaning that markup must be tight to content +-- Markup can't pass newlines +inlineMarkup :: Monoid a + => (T2T a) -- Content parser + -> (a -> Inlines) -- Constructor + -> Char -- Fence + -> (String -> a) -- Special Case to handle ****** + -> T2T Inlines +inlineMarkup p f c special = try $ do + start <- many1 (char c) + let l = length start + guard (l >= 2) + when (l == 2) (void $ notFollowedBy space) + -- We must make sure that there is no space before the start of the + -- closing tags + body <- optionMaybe (try $ manyTill (noneOf "\n\r") $ + (try $ lookAhead (noneOf " " >> string [c,c] ))) + case body of + Just middle -> do + lastChar <- anyChar + end <- many1 (char c) + let parser inp = parseFromString (mconcat <$> many p) inp + let start' = special (drop 2 start) + body' <- parser (middle ++ [lastChar]) + let end' = special (drop 2 end) + return $ f (start' <> body' <> end') + Nothing -> do -- Either bad or case such as ***** + guard (l >= 5) + let body' = (replicate (l - 4) c) + return $ f (special body') + +link :: T2T Inlines +link = try imageLink <|> titleLink + +-- Link with title +titleLink :: T2T Inlines +titleLink = try $ do + char '[' + notFollowedBy space + tokens <- sepBy1 (many $ noneOf " ]") space + guard (length tokens >= 2) + char ']' + let link' = last tokens + guard (length link' > 0) + let tit = concat (intersperse " " (init tokens)) + return $ B.link link' "" (B.text tit) + +-- Link with image +imageLink :: T2T Inlines +imageLink = try $ do + char '[' + body <- image + many1 space + l <- manyTill (noneOf "\n\r ") (char ']') + return (B.link l "" body) + +macro :: T2T Inlines +macro = try $ do + name <- string "%%" *> oneOfStringsCI (map fst commands) + optional (try $ enclosed (char '(') (char ')') anyChar) + lookAhead (spaceChar <|> oneOf specialChars <|> newline) + maybe (return mempty) (\f -> B.str <$> asks f) (lookup name commands) + where + commands = [ ("date", date), ("mtime", mtime) + , ("infile", infile), ("outfile", outfile)] + +-- raw URLs in text are automatically linked +url :: T2T Inlines +url = try $ do + (rawUrl, escapedUrl) <- (try uri <|> emailAddress) + return $ B.link rawUrl "" (B.str escapedUrl) + +uri :: T2T (String, String) +uri = try $ do + address <- t2tURI + return (address, escapeURI address) + +-- The definition of a URI in the T2T source differs from the +-- actual definition. This is a transcription of the definition in +-- the source of v2.6 +--isT2TURI :: String -> Bool +--isT2TURI (parse t2tURI "" -> Right _) = True +--isT2TURI _ = False + +t2tURI :: T2T String +t2tURI = do + start <- try ((++) <$> proto <*> urlLogin) <|> guess + domain <- many1 chars + sep <- many (char '/') + form' <- option mempty ((:) <$> char '?' <*> many1 form) + anchor' <- option mempty ((:) <$> char '#' <*> many anchor) + return (start ++ domain ++ sep ++ form' ++ anchor') + where + protos = ["http", "https", "ftp", "telnet", "gopher", "wais"] + proto = (++) <$> oneOfStrings protos <*> string "://" + guess = (++) <$> (((++) <$> stringAnyCase "www" <*> option mempty ((:[]) <$> oneOf "23")) + <|> stringAnyCase "ftp") <*> ((:[]) <$> char '.') + login = alphaNum <|> oneOf "_.-" + pass = many (noneOf " @") + chars = alphaNum <|> oneOf "%._/~:,=$@&+-" + anchor = alphaNum <|> oneOf "%._0" + form = chars <|> oneOf ";*" + urlLogin = option mempty $ try ((\x y z -> x ++ y ++ [z]) <$> many1 login <*> option mempty ((:) <$> char ':' <*> pass) <*> char '@') + + +image :: T2T Inlines +image = try $ do + -- List taken from txt2tags source + let extensions = [".jpg", ".jpeg", ".gif", ".png", ".eps", ".bmp"] + char '[' + path <- manyTill (noneOf "\n\t\r ") (try $ lookAhead (oneOfStrings extensions)) + ext <- oneOfStrings extensions + char ']' + return $ B.image (path ++ ext) "" mempty + +-- Characters used in markup +specialChars :: String +specialChars = "%*-_/|:+;" + +tab :: T2T Char +tab = char '\t' + +space :: T2T Char +space = char ' ' + +spaces :: T2T String +spaces = many space + +endline :: T2T Inlines +endline = try $ do + newline + notFollowedBy blankline + notFollowedBy hrule + notFollowedBy title + notFollowedBy verbatim + notFollowedBy rawBlock + notFollowedBy taggedBlock + notFollowedBy quote + notFollowedBy list + notFollowedBy table + return $ B.space + +str :: T2T Inlines +str = try $ do + B.str <$> many1 (noneOf $ specialChars ++ "\n\r ") + +whitespace :: T2T Inlines +whitespace = try $ B.space <$ spaceChar + +symbol :: T2T Inlines +symbol = B.str . (:[]) <$> oneOf specialChars + +-- Utility + +getTarget :: T2T String +getTarget = do + mv <- lookupMeta "target" . stateMeta <$> getState + let MetaString target = fromMaybe (MetaString "html") mv + return target + +atStart :: T2T () +atStart = (sourceColumn <$> getPosition) >>= guard . (== 1) + +ignoreSpacesCap :: T2T String -> T2T String +ignoreSpacesCap p = map toLower <$> (spaces *> p <* spaces) + diff --git a/src/Text/Pandoc/SelfContained.hs b/src/Text/Pandoc/SelfContained.hs index 6112e764f..5b8f7a75a 100644 --- a/src/Text/Pandoc/SelfContained.hs +++ b/src/Text/Pandoc/SelfContained.hs @@ -1,6 +1,6 @@ {-# LANGUAGE OverloadedStrings #-} {- -Copyright (C) 2011 John MacFarlane <jgm@berkeley.edu> +Copyright (C) 2011-2014 John MacFarlane <jgm@berkeley.edu> This program is free software; you can redistribute it and/or modify it under the terms of the GNU General Public License as published by @@ -19,7 +19,7 @@ Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA {- | Module : Text.Pandoc.SelfContained - Copyright : Copyright (C) 2011 John MacFarlane + Copyright : Copyright (C) 2011-2014 John MacFarlane License : GNU GPL, version 2 or above Maintainer : John MacFarlane <jgm@berkeley.edu> @@ -32,51 +32,56 @@ the HTML using data URIs. -} module Text.Pandoc.SelfContained ( makeSelfContained ) where import Text.HTML.TagSoup -import Network.URI (isURI, escapeURIString) +import Network.URI (isURI, escapeURIString, URI(..), parseURI) import Data.ByteString.Base64 import qualified Data.ByteString.Char8 as B import Data.ByteString (ByteString) -import System.FilePath (takeExtension, dropExtension, takeDirectory, (</>)) +import System.FilePath (takeExtension, takeDirectory, (</>)) import Data.Char (toLower, isAscii, isAlphaNum) import Codec.Compression.GZip as Gzip import qualified Data.ByteString.Lazy as L -import Text.Pandoc.Shared (renderTags', openURL, readDataFile, err) +import Text.Pandoc.Shared (renderTags', err, fetchItem') +import Text.Pandoc.MediaBag (MediaBag) +import Text.Pandoc.MIME (MimeType) import Text.Pandoc.UTF8 (toString, fromString) -import Text.Pandoc.MIME (getMimeType) -import System.Directory (doesFileExist) +import Text.Pandoc.Options (WriterOptions(..)) isOk :: Char -> Bool isOk c = isAscii c && isAlphaNum c -convertTag :: Maybe FilePath -> Tag String -> IO (Tag String) -convertTag userdata t@(TagOpen tagname as) - | tagname `elem` ["img", "embed", "video", "input", "audio", "source"] = - case fromAttrib "src" t of - [] -> return t - src -> do - (raw, mime) <- getRaw userdata (fromAttrib "type" t) src - let enc = "data:" ++ mime ++ ";base64," ++ toString (encode raw) - return $ TagOpen tagname - (("src",enc) : [(x,y) | (x,y) <- as, x /= "src"]) -convertTag userdata t@(TagOpen "script" as) = +convertTag :: MediaBag -> Maybe String -> Tag String -> IO (Tag String) +convertTag media sourceURL t@(TagOpen tagname as) + | tagname `elem` + ["img", "embed", "video", "input", "audio", "source", "track"] = do + as' <- mapM processAttribute as + return $ TagOpen tagname as' + where processAttribute (x,y) = + if x == "src" || x == "href" || x == "poster" + then do + (raw, mime) <- getRaw media sourceURL (fromAttrib "type" t) y + let enc = "data:" ++ mime ++ ";base64," ++ toString (encode raw) + return (x, enc) + else return (x,y) +convertTag media sourceURL t@(TagOpen "script" as) = case fromAttrib "src" t of [] -> return t src -> do - (raw, mime) <- getRaw userdata (fromAttrib "type" t) src + (raw, mime) <- getRaw media sourceURL (fromAttrib "type" t) src let enc = "data:" ++ mime ++ "," ++ escapeURIString isOk (toString raw) return $ TagOpen "script" (("src",enc) : [(x,y) | (x,y) <- as, x /= "src"]) -convertTag userdata t@(TagOpen "link" as) = +convertTag media sourceURL t@(TagOpen "link" as) = case fromAttrib "href" t of [] -> return t src -> do - (raw, mime) <- getRaw userdata (fromAttrib "type" t) src + (raw, mime) <- getRaw media sourceURL (fromAttrib "type" t) src let enc = "data:" ++ mime ++ "," ++ escapeURIString isOk (toString raw) return $ TagOpen "link" (("href",enc) : [(x,y) | (x,y) <- as, x /= "href"]) -convertTag _ t = return t +convertTag _ _ t = return t -- NOTE: This is really crude, it doesn't respect CSS comments. -cssURLs :: Maybe FilePath -> FilePath -> ByteString -> IO ByteString -cssURLs userdata d orig = +cssURLs :: MediaBag -> Maybe String -> FilePath -> ByteString + -> IO ByteString +cssURLs media sourceURL d orig = case B.breakSubstring "url(" orig of (x,y) | B.null y -> return orig | otherwise -> do @@ -89,33 +94,21 @@ cssURLs userdata d orig = let url' = if isURI url then url else d </> url - (raw, mime) <- getRaw userdata "" url' - rest <- cssURLs userdata d v + (raw, mime) <- getRaw media sourceURL "" url' + rest <- cssURLs media sourceURL d v let enc = "data:" `B.append` fromString mime `B.append` ";base64," `B.append` (encode raw) return $ x `B.append` "url(" `B.append` enc `B.append` rest -getItem :: Maybe FilePath -> String -> IO (ByteString, Maybe String) -getItem userdata f = - if isURI f - then openURL f >>= either handleErr return - else do - -- strip off trailing query or fragment part, if relative URL. - -- this is needed for things like cmunrm.eot?#iefix, - -- which is used to get old versions of IE to work with web fonts. - let f' = takeWhile (\c -> c /= '?' && c /= '#') f - let mime = case takeExtension f' of - ".gz" -> getMimeType $ dropExtension f' - x -> getMimeType x - exists <- doesFileExist f' - cont <- if exists then B.readFile f' else readDataFile userdata f' - return (cont, mime) - where handleErr e = err 61 $ "Failed to retrieve " ++ f ++ "\n" ++ show e - -getRaw :: Maybe FilePath -> String -> String -> IO (ByteString, String) -getRaw userdata mimetype src = do +getRaw :: MediaBag -> Maybe String -> MimeType -> String + -> IO (ByteString, MimeType) +getRaw media sourceURL mimetype src = do let ext = map toLower $ takeExtension src - (raw, respMime) <- getItem userdata src + fetchResult <- fetchItem' media sourceURL src + (raw, respMime) <- case fetchResult of + Left msg -> err 67 $ "Could not fetch " ++ src ++ + "\n" ++ show msg + Right x -> return x let raw' = if ext == ".gz" then B.concat $ L.toChunks $ Gzip.decompress $ L.fromChunks $ [raw] @@ -125,21 +118,22 @@ getRaw userdata mimetype src = do $ "Could not determine mime type for `" ++ src ++ "'" (x, Nothing) -> x (_, Just x ) -> x + let cssSourceURL = case parseURI src of + Just u + | uriScheme u `elem` ["http:","https:"] -> + Just $ show u{ uriPath = "", + uriQuery = "", + uriFragment = "" } + _ -> Nothing result <- if mime == "text/css" - then cssURLs userdata (takeDirectory src) raw' + then cssURLs media cssSourceURL (takeDirectory src) raw' else return raw' return (result, mime) -- | Convert HTML into self-contained HTML, incorporating images, --- scripts, and CSS using data: URIs. Items specified using absolute --- URLs will be downloaded; those specified using relative URLs will --- be sought first relative to the working directory, then relative --- to the user data directory (if the first parameter is 'Just' --- a directory), and finally relative to pandoc's default data --- directory. -makeSelfContained :: Maybe FilePath -> String -> IO String -makeSelfContained userdata inp = do +-- scripts, and CSS using data: URIs. +makeSelfContained :: WriterOptions -> String -> IO String +makeSelfContained opts inp = do let tags = parseTags inp - out' <- mapM (convertTag userdata) tags + out' <- mapM (convertTag (writerMediaBag opts) (writerSourceURL opts)) tags return $ renderTags' out' - diff --git a/src/Text/Pandoc/Shared.hs b/src/Text/Pandoc/Shared.hs index 714402e42..9aa70e6f2 100644 --- a/src/Text/Pandoc/Shared.hs +++ b/src/Text/Pandoc/Shared.hs @@ -1,7 +1,8 @@ {-# LANGUAGE DeriveDataTypeable, CPP, MultiParamTypeClasses, - FlexibleContexts #-} + FlexibleContexts, ScopedTypeVariables, PatternGuards, + ViewPatterns #-} {- -Copyright (C) 2006-2013 John MacFarlane <jgm@berkeley.edu> +Copyright (C) 2006-2014 John MacFarlane <jgm@berkeley.edu> This program is free software; you can redistribute it and/or modify it under the terms of the GNU General Public License as published by @@ -20,7 +21,7 @@ Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA {- | Module : Text.Pandoc.Shared - Copyright : Copyright (C) 2006-2013 John MacFarlane + Copyright : Copyright (C) 2006-2014 John MacFarlane License : GNU GPL, version 2 or above Maintainer : John MacFarlane <jgm@berkeley.edu> @@ -35,6 +36,7 @@ module Text.Pandoc.Shared ( splitByIndices, splitStringByIndices, substitute, + ordNub, -- * Text processing backslashEscapes, escapeStringUsing, @@ -52,10 +54,16 @@ module Text.Pandoc.Shared ( -- * Pandoc block and inline list processing orderedListMarkers, normalizeSpaces, + extractSpaces, normalize, + normalizeInlines, + normalizeBlocks, + removeFormatting, stringify, + capitalize, compactify, compactify', + compactify'DL, Element (..), hierarchicalize, uniqueIdent, @@ -71,31 +79,37 @@ module Text.Pandoc.Shared ( readDataFile, readDataFileUTF8, fetchItem, + fetchItem', openURL, + collapseFilePath, -- * Error handling err, warn, -- * Safe read - safeRead + safeRead, + -- * Temp directory + withTempDir ) where import Text.Pandoc.Definition import Text.Pandoc.Walk -import Text.Pandoc.Generic -import Text.Pandoc.Builder (Blocks, ToMetaValue(..)) +import Text.Pandoc.MediaBag (MediaBag, lookupMedia) +import Text.Pandoc.Builder (Inlines, Blocks, ToMetaValue(..)) import qualified Text.Pandoc.Builder as B import qualified Text.Pandoc.UTF8 as UTF8 import System.Environment (getProgName) import System.Exit (exitWith, ExitCode(..)) import Data.Char ( toLower, isLower, isUpper, isAlpha, isLetter, isDigit, isSpace ) -import Data.List ( find, isPrefixOf, intercalate ) +import Data.List ( find, stripPrefix, intercalate ) import qualified Data.Map as M import Network.URI ( escapeURIString, isURI, nonStrictRelativeTo, - unEscapeString, parseURIReference ) + unEscapeString, parseURIReference, isAllowedInURI ) +import qualified Data.Set as Set import System.Directory -import Text.Pandoc.MIME (getMimeType) -import System.FilePath ( (</>), takeExtension, dropExtension ) +import System.FilePath (joinPath, splitDirectories, pathSeparator, isPathSeparator) +import Text.Pandoc.MIME (MimeType, getMimeType) +import System.FilePath ( (</>), takeExtension, dropExtension) import Data.Generics (Typeable, Data) import qualified Control.Monad.State as S import qualified Control.Exception as E @@ -104,23 +118,29 @@ import Text.Pandoc.Pretty (charWidth) import System.Locale (defaultTimeLocale) import Data.Time import System.IO (stderr) +import System.IO.Temp import Text.HTML.TagSoup (renderTagsOptions, RenderOptions(..), Tag(..), renderOptions) import qualified Data.ByteString as BS import qualified Data.ByteString.Char8 as B8 import Text.Pandoc.Compat.Monoid import Data.ByteString.Base64 (decodeLenient) +import Data.Sequence (ViewR(..), ViewL(..), viewl, viewr) +import qualified Data.Text as T (toUpper, pack, unpack) +import Data.ByteString.Lazy (toChunks) #ifdef EMBED_DATA_FILES import Text.Pandoc.Data (dataFiles) -import System.FilePath ( joinPath, splitDirectories ) #else import Paths_pandoc (getDataFileName) #endif -#ifdef HTTP_CONDUIT -import Data.ByteString.Lazy (toChunks) -import Network.HTTP.Conduit (httpLbs, parseUrl, withManager, - responseBody, responseHeaders) +#ifdef HTTP_CLIENT +import Network.HTTP.Client (httpLbs, parseUrl, withManager, + responseBody, responseHeaders, + Request(port,host)) +import Network.HTTP.Client.Internal (addProxy) +import Network.HTTP.Client.TLS (tlsManagerSettings) +import System.Environment (getEnv) import Network.HTTP.Types.Header ( hContentType) import Network (withSocketsDo) #else @@ -165,9 +185,16 @@ substitute :: (Eq a) => [a] -> [a] -> [a] -> [a] substitute _ _ [] = [] substitute [] _ xs = xs substitute target replacement lst@(x:xs) = - if target `isPrefixOf` lst - then replacement ++ substitute target replacement (drop (length target) lst) - else x : substitute target replacement xs + case stripPrefix target lst of + Just lst' -> replacement ++ substitute target replacement lst' + Nothing -> x : substitute target replacement xs + +ordNub :: (Ord a) => [a] -> [a] +ordNub l = go Set.empty l + where + go _ [] = [] + go s (x:xs) = if x `Set.member` s then go s xs + else x : go (Set.insert x s) xs -- -- Text processing @@ -232,9 +259,9 @@ toRomanNumeral x = _ | x >= 50 -> "L" ++ toRomanNumeral (x - 50) _ | x >= 40 -> "XL" ++ toRomanNumeral (x - 40) _ | x >= 10 -> "X" ++ toRomanNumeral (x - 10) - _ | x >= 9 -> "IX" ++ toRomanNumeral (x - 5) + _ | x == 9 -> "IX" _ | x >= 5 -> "V" ++ toRomanNumeral (x - 5) - _ | x >= 4 -> "IV" ++ toRomanNumeral (x - 4) + _ | x == 4 -> "IV" _ | x >= 1 -> "I" ++ toRomanNumeral (x - 1) _ -> "" @@ -317,75 +344,177 @@ isSpaceOrEmpty Space = True isSpaceOrEmpty (Str "") = True isSpaceOrEmpty _ = False +-- | Extract the leading and trailing spaces from inside an inline element +-- and place them outside the element. + +extractSpaces :: (Inlines -> Inlines) -> Inlines -> Inlines +extractSpaces f is = + let contents = B.unMany is + left = case viewl contents of + (Space :< _) -> B.space + _ -> mempty + right = case viewr contents of + (_ :> Space) -> B.space + _ -> mempty in + (left <> f (B.trimInlines . B.Many $ contents) <> right) + -- | Normalize @Pandoc@ document, consolidating doubled 'Space's, -- combining adjacent 'Str's and 'Emph's, remove 'Null's and -- empty elements, etc. -normalize :: (Eq a, Data a) => a -> a -normalize = topDown removeEmptyBlocks . - topDown consolidateInlines . - bottomUp (removeEmptyInlines . removeTrailingInlineSpaces) - -removeEmptyBlocks :: [Block] -> [Block] -removeEmptyBlocks (Null : xs) = removeEmptyBlocks xs -removeEmptyBlocks (BulletList [] : xs) = removeEmptyBlocks xs -removeEmptyBlocks (OrderedList _ [] : xs) = removeEmptyBlocks xs -removeEmptyBlocks (DefinitionList [] : xs) = removeEmptyBlocks xs -removeEmptyBlocks (RawBlock _ [] : xs) = removeEmptyBlocks xs -removeEmptyBlocks (x:xs) = x : removeEmptyBlocks xs -removeEmptyBlocks [] = [] - -removeEmptyInlines :: [Inline] -> [Inline] -removeEmptyInlines (Emph [] : zs) = removeEmptyInlines zs -removeEmptyInlines (Strong [] : zs) = removeEmptyInlines zs -removeEmptyInlines (Subscript [] : zs) = removeEmptyInlines zs -removeEmptyInlines (Superscript [] : zs) = removeEmptyInlines zs -removeEmptyInlines (SmallCaps [] : zs) = removeEmptyInlines zs -removeEmptyInlines (Strikeout [] : zs) = removeEmptyInlines zs -removeEmptyInlines (RawInline _ [] : zs) = removeEmptyInlines zs -removeEmptyInlines (Code _ [] : zs) = removeEmptyInlines zs -removeEmptyInlines (Str "" : zs) = removeEmptyInlines zs -removeEmptyInlines (x : xs) = x : removeEmptyInlines xs -removeEmptyInlines [] = [] - -removeTrailingInlineSpaces :: [Inline] -> [Inline] -removeTrailingInlineSpaces = reverse . removeLeadingInlineSpaces . reverse - -removeLeadingInlineSpaces :: [Inline] -> [Inline] -removeLeadingInlineSpaces = dropWhile isSpaceOrEmpty - -consolidateInlines :: [Inline] -> [Inline] -consolidateInlines (Str x : ys) = +normalize :: Pandoc -> Pandoc +normalize (Pandoc (Meta meta) blocks) = + Pandoc (Meta $ M.map go meta) (normalizeBlocks blocks) + where go (MetaInlines xs) = MetaInlines $ normalizeInlines xs + go (MetaBlocks xs) = MetaBlocks $ normalizeBlocks xs + go (MetaList ms) = MetaList $ map go ms + go (MetaMap m) = MetaMap $ M.map go m + go x = x + +normalizeBlocks :: [Block] -> [Block] +normalizeBlocks (Null : xs) = normalizeBlocks xs +normalizeBlocks (Div attr bs : xs) = + Div attr (normalizeBlocks bs) : normalizeBlocks xs +normalizeBlocks (BlockQuote bs : xs) = + case normalizeBlocks bs of + [] -> normalizeBlocks xs + bs' -> BlockQuote bs' : normalizeBlocks xs +normalizeBlocks (BulletList [] : xs) = normalizeBlocks xs +normalizeBlocks (BulletList items : xs) = + BulletList (map normalizeBlocks items) : normalizeBlocks xs +normalizeBlocks (OrderedList _ [] : xs) = normalizeBlocks xs +normalizeBlocks (OrderedList attr items : xs) = + OrderedList attr (map normalizeBlocks items) : normalizeBlocks xs +normalizeBlocks (DefinitionList [] : xs) = normalizeBlocks xs +normalizeBlocks (DefinitionList items : xs) = + DefinitionList (map go items) : normalizeBlocks xs + where go (ils, bs) = (normalizeInlines ils, map normalizeBlocks bs) +normalizeBlocks (RawBlock _ "" : xs) = normalizeBlocks xs +normalizeBlocks (RawBlock f x : xs) = + case normalizeBlocks xs of + (RawBlock f' x' : rest) | f' == f -> + RawBlock f (x ++ ('\n':x')) : rest + rest -> RawBlock f x : rest +normalizeBlocks (Para ils : xs) = + case normalizeInlines ils of + [] -> normalizeBlocks xs + ils' -> Para ils' : normalizeBlocks xs +normalizeBlocks (Plain ils : xs) = + case normalizeInlines ils of + [] -> normalizeBlocks xs + ils' -> Plain ils' : normalizeBlocks xs +normalizeBlocks (Header lev attr ils : xs) = + Header lev attr (normalizeInlines ils) : normalizeBlocks xs +normalizeBlocks (Table capt aligns widths hdrs rows : xs) = + Table (normalizeInlines capt) aligns widths + (map normalizeBlocks hdrs) (map (map normalizeBlocks) rows) + : normalizeBlocks xs +normalizeBlocks (x:xs) = x : normalizeBlocks xs +normalizeBlocks [] = [] + +normalizeInlines :: [Inline] -> [Inline] +normalizeInlines (Str x : ys) = case concat (x : map fromStr strs) of - "" -> consolidateInlines rest - n -> Str n : consolidateInlines rest + "" -> rest + n -> Str n : rest where - (strs, rest) = span isStr ys + (strs, rest) = span isStr $ normalizeInlines ys isStr (Str _) = True isStr _ = False fromStr (Str z) = z - fromStr _ = error "consolidateInlines - fromStr - not a Str" -consolidateInlines (Space : ys) = Space : rest + fromStr _ = error "normalizeInlines - fromStr - not a Str" +normalizeInlines (Space : ys) = + if null rest + then [] + else Space : rest where isSp Space = True isSp _ = False - rest = consolidateInlines $ dropWhile isSp ys -consolidateInlines (Emph xs : Emph ys : zs) = consolidateInlines $ - Emph (xs ++ ys) : zs -consolidateInlines (Strong xs : Strong ys : zs) = consolidateInlines $ - Strong (xs ++ ys) : zs -consolidateInlines (Subscript xs : Subscript ys : zs) = consolidateInlines $ - Subscript (xs ++ ys) : zs -consolidateInlines (Superscript xs : Superscript ys : zs) = consolidateInlines $ - Superscript (xs ++ ys) : zs -consolidateInlines (SmallCaps xs : SmallCaps ys : zs) = consolidateInlines $ - SmallCaps (xs ++ ys) : zs -consolidateInlines (Strikeout xs : Strikeout ys : zs) = consolidateInlines $ - Strikeout (xs ++ ys) : zs -consolidateInlines (RawInline f x : RawInline f' y : zs) | f == f' = - consolidateInlines $ RawInline f (x ++ y) : zs -consolidateInlines (Code a1 x : Code a2 y : zs) | a1 == a2 = - consolidateInlines $ Code a1 (x ++ y) : zs -consolidateInlines (x : xs) = x : consolidateInlines xs -consolidateInlines [] = [] + rest = dropWhile isSp $ normalizeInlines ys +normalizeInlines (Emph xs : zs) = + case normalizeInlines zs of + (Emph ys : rest) -> normalizeInlines $ + Emph (normalizeInlines $ xs ++ ys) : rest + rest -> case normalizeInlines xs of + [] -> rest + xs' -> Emph xs' : rest +normalizeInlines (Strong xs : zs) = + case normalizeInlines zs of + (Strong ys : rest) -> normalizeInlines $ + Strong (normalizeInlines $ xs ++ ys) : rest + rest -> case normalizeInlines xs of + [] -> rest + xs' -> Strong xs' : rest +normalizeInlines (Subscript xs : zs) = + case normalizeInlines zs of + (Subscript ys : rest) -> normalizeInlines $ + Subscript (normalizeInlines $ xs ++ ys) : rest + rest -> case normalizeInlines xs of + [] -> rest + xs' -> Subscript xs' : rest +normalizeInlines (Superscript xs : zs) = + case normalizeInlines zs of + (Superscript ys : rest) -> normalizeInlines $ + Superscript (normalizeInlines $ xs ++ ys) : rest + rest -> case normalizeInlines xs of + [] -> rest + xs' -> Superscript xs' : rest +normalizeInlines (SmallCaps xs : zs) = + case normalizeInlines zs of + (SmallCaps ys : rest) -> normalizeInlines $ + SmallCaps (normalizeInlines $ xs ++ ys) : rest + rest -> case normalizeInlines xs of + [] -> rest + xs' -> SmallCaps xs' : rest +normalizeInlines (Strikeout xs : zs) = + case normalizeInlines zs of + (Strikeout ys : rest) -> normalizeInlines $ + Strikeout (normalizeInlines $ xs ++ ys) : rest + rest -> case normalizeInlines xs of + [] -> rest + xs' -> Strikeout xs' : rest +normalizeInlines (RawInline _ [] : ys) = normalizeInlines ys +normalizeInlines (RawInline f xs : zs) = + case normalizeInlines zs of + (RawInline f' ys : rest) | f == f' -> normalizeInlines $ + RawInline f (xs ++ ys) : rest + rest -> RawInline f xs : rest +normalizeInlines (Code _ "" : ys) = normalizeInlines ys +normalizeInlines (Code attr xs : zs) = + case normalizeInlines zs of + (Code attr' ys : rest) | attr == attr' -> normalizeInlines $ + Code attr (xs ++ ys) : rest + rest -> Code attr xs : rest +-- allow empty spans, they may carry identifiers etc. +-- normalizeInlines (Span _ [] : ys) = normalizeInlines ys +normalizeInlines (Span attr xs : zs) = + case normalizeInlines zs of + (Span attr' ys : rest) | attr == attr' -> normalizeInlines $ + Span attr (normalizeInlines $ xs ++ ys) : rest + rest -> Span attr (normalizeInlines xs) : rest +normalizeInlines (Note bs : ys) = Note (normalizeBlocks bs) : + normalizeInlines ys +normalizeInlines (Quoted qt ils : ys) = + Quoted qt (normalizeInlines ils) : normalizeInlines ys +normalizeInlines (Link ils t : ys) = + Link (normalizeInlines ils) t : normalizeInlines ys +normalizeInlines (Image ils t : ys) = + Image (normalizeInlines ils) t : normalizeInlines ys +normalizeInlines (Cite cs ils : ys) = + Cite cs (normalizeInlines ils) : normalizeInlines ys +normalizeInlines (x : xs) = x : normalizeInlines xs +normalizeInlines [] = [] + +-- | Extract inlines, removing formatting. +removeFormatting :: Walkable Inline a => a -> [Inline] +removeFormatting = query go . walk deNote + where go :: Inline -> [Inline] + go (Str xs) = [Str xs] + go Space = [Space] + go (Code _ x) = [Str x] + go (Math _ x) = [Str x] + go LineBreak = [Space] + go _ = [] + deNote (Note _) = Str "" + deNote x = x -- | Convert pandoc structure to a string with formatting removed. -- Footnotes are skipped (since we don't want their contents in link @@ -402,6 +531,17 @@ stringify = query go . walk deNote deNote (Note _) = Str "" deNote x = x +-- | Bring all regular text in a pandoc structure to uppercase. +-- +-- This function correctly handles cases where a lowercase character doesn't +-- match to a single uppercase character – e.g. “Straße” would be converted +-- to “STRASSE”, not “STRAßE”. +capitalize :: Walkable Inline a => a -> a +capitalize = walk go + where go :: Inline -> Inline + go (Str s) = Str (T.unpack $ T.toUpper $ T.pack s) + go x = x + -- | Change final list item from @Para@ to @Plain@ if the list contains -- no other @Para@ blocks. compactify :: [[Block]] -- ^ List of list items (each a list of blocks) @@ -433,6 +573,23 @@ compactify' items = _ -> items _ -> items +-- | Like @compactify'@, but acts on items of definition lists. +compactify'DL :: [(Inlines, [Blocks])] -> [(Inlines, [Blocks])] +compactify'DL items = + let defs = concatMap snd items + in case reverse (concatMap B.toList defs) of + (Para x:xs) + | not (any isPara xs) -> + let (t,ds) = last items + lastDef = B.toList $ last ds + ds' = init ds ++ + if null lastDef + then [B.fromList lastDef] + else [B.fromList $ init lastDef ++ [Plain x]] + in init items ++ [(t, ds')] + | otherwise -> items + _ -> items + isPara :: Block -> Bool isPara (Para _) = True isPara _ = False @@ -546,8 +703,10 @@ addMetaField :: ToMetaValue a -> Meta addMetaField key val (Meta meta) = Meta $ M.insertWith combine key (toMetaValue val) meta - where combine newval (MetaList xs) = MetaList (xs ++ [newval]) + where combine newval (MetaList xs) = MetaList (xs ++ tolist newval) combine newval x = MetaList [x, newval] + tolist (MetaList ys) = ys + tolist y = [y] -- | Create 'Meta' from old-style title, authors, date. This is -- provided to ease the transition from the old API. @@ -576,12 +735,10 @@ renderTags' = renderTagsOptions -- | Perform an IO action in a directory, returning to starting directory. inDirectory :: FilePath -> IO a -> IO a -inDirectory path action = do - oldDir <- getCurrentDirectory - setCurrentDirectory path - result <- action - setCurrentDirectory oldDir - return result +inDirectory path action = E.bracket + getCurrentDirectory + setCurrentDirectory + (const $ setCurrentDirectory path >> action) readDefaultDataFile :: FilePath -> IO BS.ByteString readDefaultDataFile fname = @@ -621,34 +778,51 @@ readDataFileUTF8 userDir fname = -- | Fetch an image or other item from the local filesystem or the net. -- Returns raw content and maybe mime type. fetchItem :: Maybe String -> String - -> IO (Either E.SomeException (BS.ByteString, Maybe String)) -fetchItem sourceURL s - | isURI s = openURL s - | otherwise = - case sourceURL >>= parseURIReference of - Just u -> case parseURIReference s of - Just s' -> openURL $ show $ - s' `nonStrictRelativeTo` u - Nothing -> openURL $ show u ++ "/" ++ s - Nothing -> E.try readLocalFile + -> IO (Either E.SomeException (BS.ByteString, Maybe MimeType)) +fetchItem sourceURL s = + case (sourceURL >>= parseURIReference . ensureEscaped, ensureEscaped s) of + (_, s') | isURI s' -> openURL s' + (Just u, s') -> -- try fetching from relative path at source + case parseURIReference s' of + Just u' -> openURL $ show $ u' `nonStrictRelativeTo` u + Nothing -> openURL s' -- will throw error + (Nothing, _) -> E.try readLocalFile -- get from local file system where readLocalFile = do - let mime = case takeExtension s of - ".gz" -> getMimeType $ dropExtension s - x -> getMimeType x - cont <- BS.readFile s + cont <- BS.readFile fp return (cont, mime) + dropFragmentAndQuery = takeWhile (\c -> c /= '?' && c /= '#') + fp = unEscapeString $ dropFragmentAndQuery s + mime = case takeExtension fp of + ".gz" -> getMimeType $ dropExtension fp + x -> getMimeType x + ensureEscaped x@(_:':':'\\':_) = x -- likely windows path + ensureEscaped x = escapeURIString isAllowedInURI x + +-- | Like 'fetchItem', but also looks for items in a 'MediaBag'. +fetchItem' :: MediaBag -> Maybe String -> String + -> IO (Either E.SomeException (BS.ByteString, Maybe MimeType)) +fetchItem' media sourceURL s = do + case lookupMedia s media of + Nothing -> fetchItem sourceURL s + Just (mime, bs) -> return $ Right (BS.concat $ toChunks bs, Just mime) -- | Read from a URL and return raw data and maybe mime type. -openURL :: String -> IO (Either E.SomeException (BS.ByteString, Maybe String)) +openURL :: String -> IO (Either E.SomeException (BS.ByteString, Maybe MimeType)) openURL u - | "data:" `isPrefixOf` u = - let mime = takeWhile (/=',') $ drop 5 u - contents = B8.pack $ unEscapeString $ drop 1 $ dropWhile (/=',') u + | Just u' <- stripPrefix "data:" u = + let mime = takeWhile (/=',') u' + contents = B8.pack $ unEscapeString $ drop 1 $ dropWhile (/=',') u' in return $ Right (decodeLenient contents, Just mime) -#ifdef HTTP_CONDUIT +#ifdef HTTP_CLIENT | otherwise = withSocketsDo $ E.try $ do req <- parseUrl u - resp <- withManager $ httpLbs req + (proxy :: Either E.SomeException String) <- E.try $ getEnv "http_proxy" + let req' = case proxy of + Left _ -> req + Right pr -> case parseUrl pr of + Just r -> addProxy (host r) (port r) req + Nothing -> req + resp <- withManager tlsManagerSettings $ httpLbs req' return (BS.concat $ toChunks $ responseBody resp, UTF8.toString `fmap` lookup hContentType (responseHeaders resp)) #else @@ -681,6 +855,30 @@ warn msg = do name <- getProgName UTF8.hPutStrLn stderr $ name ++ ": " ++ msg +-- | Remove intermediate "." and ".." directories from a path. +-- +-- > collapseFilePath "./foo" == "foo" +-- > collapseFilePath "/bar/../baz" == "/baz" +-- > collapseFilePath "/../baz" == "/../baz" +-- > collapseFilePath "parent/foo/baz/../bar" == "parent/foo/bar" +-- > collapseFilePath "parent/foo/baz/../../bar" == "parent/bar" +-- > collapseFilePath "parent/foo/.." == "parent" +-- > collapseFilePath "/parent/foo/../../bar" == "/bar" +collapseFilePath :: FilePath -> FilePath +collapseFilePath = joinPath . reverse . foldl go [] . splitDirectories + where + go rs "." = rs + go r@(p:rs) ".." = case p of + ".." -> ("..":r) + (checkPathSeperator -> Just True) -> ("..":r) + _ -> rs + go _ (checkPathSeperator -> Just True) = [[pathSeparator]] + go rs x = x:rs + isSingleton [] = Nothing + isSingleton [x] = Just x + isSingleton _ = Nothing + checkPathSeperator = fmap isPathSeparator . isSingleton + -- -- Safe read -- @@ -691,4 +889,14 @@ safeRead s = case reads s of | all isSpace x -> return d _ -> fail $ "Could not read `" ++ s ++ "'" +-- +-- Temp directory +-- +withTempDir :: String -> (FilePath -> IO a) -> IO a +withTempDir = +#ifdef _WINDOWS + withTempDirectory "." +#else + withSystemTempDirectory +#endif diff --git a/src/Text/Pandoc/Slides.hs b/src/Text/Pandoc/Slides.hs index 50c46d17f..2b863c780 100644 --- a/src/Text/Pandoc/Slides.hs +++ b/src/Text/Pandoc/Slides.hs @@ -1,5 +1,5 @@ {- -Copyright (C) 2012 John MacFarlane <jgm@berkeley.edu> +Copyright (C) 2012-2014 John MacFarlane <jgm@berkeley.edu> This program is free software; you can redistribute it and/or modify it under the terms of the GNU General Public License as published by @@ -18,7 +18,7 @@ Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA {- | Module : Text.Pandoc.Slides - Copyright : Copyright (C) 2012 John MacFarlane + Copyright : Copyright (C) 2012-2014 John MacFarlane License : GNU GPL, version 2 or above Maintainer : John MacFarlane <jgm@berkeley.edu> diff --git a/src/Text/Pandoc/Templates.hs b/src/Text/Pandoc/Templates.hs index ad8838f72..4ae6a6d8a 100644 --- a/src/Text/Pandoc/Templates.hs +++ b/src/Text/Pandoc/Templates.hs @@ -1,7 +1,7 @@ {-# LANGUAGE TypeSynonymInstances, FlexibleInstances, CPP, OverloadedStrings, GeneralizedNewtypeDeriving #-} {- -Copyright (C) 2009-2013 John MacFarlane <jgm@berkeley.edu> +Copyright (C) 2009-2014 John MacFarlane <jgm@berkeley.edu> This program is free software; you can redistribute it and/or modify it under the terms of the GNU General Public License as published by @@ -20,7 +20,7 @@ Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA {- | Module : Text.Pandoc.Templates - Copyright : Copyright (C) 2009-2013 John MacFarlane + Copyright : Copyright (C) 2009-2014 John MacFarlane License : GNU GPL, version 2 or above Maintainer : John MacFarlane <jgm@berkeley.edu> @@ -96,14 +96,14 @@ module Text.Pandoc.Templates ( renderTemplate import Data.Char (isAlphaNum) import Control.Monad (guard, when) import Data.Aeson (ToJSON(..), Value(..)) -import qualified Data.Attoparsec.Text as A -import Data.Attoparsec.Text (Parser) +import qualified Text.Parsec as P +import Text.Parsec.Text (Parser) import Control.Applicative import qualified Data.Text as T import Data.Text (Text) import Data.Text.Encoding (encodeUtf8) import Text.Pandoc.Compat.Monoid ((<>), Monoid(..)) -import Data.List (intersperse, nub) +import Data.List (intersperse) import System.FilePath ((</>), (<.>)) import qualified Data.Map as M import qualified Data.HashMap.Strict as H @@ -116,7 +116,7 @@ import Text.Blaze.Internal (preEscapedText) import Text.Blaze (preEscapedText, Html) #endif import Data.ByteString.Lazy (ByteString, fromChunks) -import Text.Pandoc.Shared (readDataFileUTF8) +import Text.Pandoc.Shared (readDataFileUTF8, ordNub) import Data.Vector ((!?)) -- | Get default template for the specified writer. @@ -163,7 +163,7 @@ varListToJSON assoc = toJSON $ M.fromList assoc' where assoc' = [(T.pack k, toVal [T.pack z | (y,z) <- assoc, not (null z), y == k]) - | k <- nub $ map fst assoc ] + | k <- ordNub $ map fst assoc ] toVal [x] = toJSON x toVal [] = Null toVal xs = toJSON xs @@ -172,7 +172,10 @@ renderTemplate :: (ToJSON a, TemplateTarget b) => Template -> a -> b renderTemplate (Template f) context = toTarget $ f $ toJSON context compileTemplate :: Text -> Either String Template -compileTemplate template = A.parseOnly pTemplate template +compileTemplate template = + case P.parse (pTemplate <* P.eof) "template" template of + Left e -> Left (show e) + Right x -> Right x -- | Like 'renderTemplate', but compiles the template first, -- raising an error if compilation fails. @@ -190,6 +193,7 @@ resolveVar var' val = Just (String t) -> T.stripEnd t Just (Number n) -> T.pack $ show n Just (Bool True) -> "true" + Just (Object _) -> "true" Just _ -> mempty Nothing -> mempty @@ -229,7 +233,7 @@ replaceVar _ _ old = old pTemplate :: Parser Template pTemplate = do - sp <- A.option mempty pInitialSpace + sp <- P.option mempty pInitialSpace rest <- mconcat <$> many (pConditional <|> pFor <|> pNewline <|> @@ -238,40 +242,43 @@ pTemplate = do pEscapedDollar) return $ sp <> rest +takeWhile1 :: (Char -> Bool) -> Parser Text +takeWhile1 f = T.pack <$> P.many1 (P.satisfy f) + pLit :: Parser Template -pLit = lit <$> A.takeWhile1 (\x -> x /='$' && x /= '\n') +pLit = lit <$> takeWhile1 (\x -> x /='$' && x /= '\n') pNewline :: Parser Template pNewline = do - A.char '\n' - sp <- A.option mempty pInitialSpace + P.char '\n' + sp <- P.option mempty pInitialSpace return $ lit "\n" <> sp pInitialSpace :: Parser Template pInitialSpace = do - sps <- A.takeWhile1 (==' ') + sps <- takeWhile1 (==' ') let indentVar = if T.null sps then id else indent (T.length sps) - v <- A.option mempty $ indentVar <$> pVar + v <- P.option mempty $ indentVar <$> pVar return $ lit sps <> v pEscapedDollar :: Parser Template -pEscapedDollar = lit "$" <$ A.string "$$" +pEscapedDollar = lit "$" <$ P.try (P.string "$$") pVar :: Parser Template -pVar = var <$> (A.char '$' *> pIdent <* A.char '$') +pVar = var <$> (P.try $ P.char '$' *> pIdent <* P.char '$') pIdent :: Parser [Text] pIdent = do first <- pIdentPart - rest <- many (A.char '.' *> pIdentPart) + rest <- many (P.char '.' *> pIdentPart) return (first:rest) pIdentPart :: Parser Text -pIdentPart = do - first <- A.letter - rest <- A.takeWhile (\c -> isAlphaNum c || c == '_' || c == '-') +pIdentPart = P.try $ do + first <- P.letter + rest <- T.pack <$> P.many (P.satisfy (\c -> isAlphaNum c || c == '_' || c == '-')) let id' = T.singleton first <> rest guard $ id' `notElem` reservedWords return id' @@ -280,38 +287,38 @@ reservedWords :: [Text] reservedWords = ["else","endif","for","endfor","sep"] skipEndline :: Parser () -skipEndline = A.skipWhile (`elem` " \t") >> A.char '\n' >> return () +skipEndline = P.try $ P.skipMany (P.satisfy (`elem` " \t")) >> P.char '\n' >> return () pConditional :: Parser Template pConditional = do - A.string "$if(" + P.try $ P.string "$if(" id' <- pIdent - A.string ")$" + P.string ")$" -- if newline after the "if", then a newline after "endif" will be swallowed - multiline <- A.option False (True <$ skipEndline) + multiline <- P.option False (True <$ skipEndline) ifContents <- pTemplate - elseContents <- A.option mempty $ - do A.string "$else$" - when multiline $ A.option () skipEndline + elseContents <- P.option mempty $ P.try $ + do P.string "$else$" + when multiline $ P.option () skipEndline pTemplate - A.string "$endif$" - when multiline $ A.option () skipEndline + P.string "$endif$" + when multiline $ P.option () skipEndline return $ cond id' ifContents elseContents pFor :: Parser Template pFor = do - A.string "$for(" + P.try $ P.string "$for(" id' <- pIdent - A.string ")$" + P.string ")$" -- if newline after the "for", then a newline after "endfor" will be swallowed - multiline <- A.option False $ skipEndline >> return True + multiline <- P.option False $ skipEndline >> return True contents <- pTemplate - sep <- A.option mempty $ - do A.string "$sep$" - when multiline $ A.option () skipEndline + sep <- P.option mempty $ + do P.try $ P.string "$sep$" + when multiline $ P.option () skipEndline pTemplate - A.string "$endfor$" - when multiline $ A.option () skipEndline + P.string "$endfor$" + when multiline $ P.option () skipEndline return $ iter id' contents sep indent :: Int -> Template -> Template diff --git a/src/Text/Pandoc/UTF8.hs b/src/Text/Pandoc/UTF8.hs index 229442543..543f39ab0 100644 --- a/src/Text/Pandoc/UTF8.hs +++ b/src/Text/Pandoc/UTF8.hs @@ -1,6 +1,6 @@ {-# LANGUAGE CPP #-} {- -Copyright (C) 2010 John MacFarlane <jgm@berkeley.edu> +Copyright (C) 2010-2014 John MacFarlane <jgm@berkeley.edu> This program is free software; you can redistribute it and/or modify it under the terms of the GNU General Public License as published by @@ -19,7 +19,7 @@ Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA {- | Module : Text.Pandoc.UTF8 - Copyright : Copyright (C) 2010 John MacFarlane + Copyright : Copyright (C) 2010-2014 John MacFarlane License : GNU GPL, version 2 or above Maintainer : John MacFarlane <jgm@berkeley.edu> @@ -48,12 +48,7 @@ where import System.IO hiding (readFile, writeFile, getContents, putStr, putStrLn, hPutStr, hPutStrLn, hGetContents) -#if MIN_VERSION_base(4,6,0) import Prelude hiding (readFile, writeFile, getContents, putStr, putStrLn) -#else -import Prelude hiding (readFile, writeFile, getContents, putStr, putStrLn, - catch) -#endif import qualified System.IO as IO import qualified Data.ByteString.Char8 as B import qualified Data.ByteString.Lazy as BL diff --git a/src/Text/Pandoc/UUID.hs b/src/Text/Pandoc/UUID.hs index 082644eea..eebfe09d2 100644 --- a/src/Text/Pandoc/UUID.hs +++ b/src/Text/Pandoc/UUID.hs @@ -1,5 +1,5 @@ {- -Copyright (C) 2010 John MacFarlane <jgm@berkeley.edu> +Copyright (C) 2010-2014 John MacFarlane <jgm@berkeley.edu> This program is free software; you can redistribute it and/or modify it under the terms of the GNU General Public License as published by @@ -18,7 +18,7 @@ Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA {- | Module : Text.Pandoc.UUID - Copyright : Copyright (C) 2010 John MacFarlane + Copyright : Copyright (C) 2010-2014 John MacFarlane License : GNU GPL, version 2 or above Maintainer : John MacFarlane <jgm@berkeley.edu> diff --git a/src/Text/Pandoc/Writers/AsciiDoc.hs b/src/Text/Pandoc/Writers/AsciiDoc.hs index 68b525742..e5b8c5167 100644 --- a/src/Text/Pandoc/Writers/AsciiDoc.hs +++ b/src/Text/Pandoc/Writers/AsciiDoc.hs @@ -1,6 +1,6 @@ {-# LANGUAGE OverloadedStrings #-} {- -Copyright (C) 2006-2010 John MacFarlane <jgm@berkeley.edu> +Copyright (C) 2006-2014 John MacFarlane <jgm@berkeley.edu> This program is free software; you can redistribute it and/or modify it under the terms of the GNU General Public License as published by @@ -19,7 +19,7 @@ Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA {- | Module : Text.Pandoc.Writers.AsciiDoc - Copyright : Copyright (C) 2006-2010 John MacFarlane + Copyright : Copyright (C) 2006-2014 John MacFarlane License : GNU GPL, version 2 or above Maintainer : John MacFarlane <jgm@berkeley.edu> @@ -43,16 +43,19 @@ import Text.Pandoc.Shared import Text.Pandoc.Writers.Shared import Text.Pandoc.Options import Text.Pandoc.Parsing hiding (blankline, space) -import Data.List ( isPrefixOf, intersperse, intercalate ) +import Data.Maybe (fromMaybe) +import Data.List ( stripPrefix, intersperse, intercalate ) import Text.Pandoc.Pretty import Control.Monad.State import qualified Data.Map as M import Data.Aeson (Value(String), fromJSON, toJSON, Result(..)) import qualified Data.Text as T +import Control.Applicative ((<*), (*>)) data WriterState = WriterState { defListMarker :: String , orderedListLevel :: Int , bulletListLevel :: Int + , intraword :: Bool } -- | Convert Pandoc to AsciiDoc. @@ -62,6 +65,7 @@ writeAsciiDoc opts document = defListMarker = "::" , orderedListLevel = 1 , bulletListLevel = 1 + , intraword = False } -- | Return asciidoc representation of document. @@ -123,7 +127,7 @@ blockToAsciiDoc _ Null = return empty blockToAsciiDoc opts (Plain inlines) = do contents <- inlineListToAsciiDoc opts inlines return $ contents <> cr -blockToAsciiDoc opts (Para [Image alt (src,'f':'i':'g':':':tit)]) = +blockToAsciiDoc opts (Para [Image alt (src,'f':'i':'g':':':tit)]) = do blockToAsciiDoc opts (Para [Image alt (src,tit)]) blockToAsciiDoc opts (Para inlines) = do contents <- inlineListToAsciiDoc opts inlines @@ -142,10 +146,10 @@ blockToAsciiDoc opts (Header level (ident,_,_) inlines) = do let len = offset contents -- ident seem to be empty most of the time and asciidoc will generate them automatically -- so lets make them not show up when null - let identifier = if (null ident) then empty else ("[[" <> text ident <> "]]") + let identifier = if (null ident) then empty else ("[[" <> text ident <> "]]") let setext = writerSetextHeaders opts - return $ - (if setext + return $ + (if setext then identifier $$ contents $$ (case level of @@ -155,7 +159,7 @@ blockToAsciiDoc opts (Header level (ident,_,_) inlines) = do 4 -> text $ replicate len '+' _ -> empty) <> blankline else - identifier $$ text (replicate level '=') <> space <> contents <> blankline) + identifier $$ text (replicate level '=') <> space <> contents <> blankline) blockToAsciiDoc _ (CodeBlock (_,classes,_) str) = return $ flush (attrs <> dashes <> space <> attrs <> cr <> text str <> cr <> dashes) <> blankline @@ -217,7 +221,9 @@ blockToAsciiDoc opts (Table caption aligns widths headers rows) = do let makeCell [Plain x] = do d <- blockListToAsciiDoc opts [Plain x] return $ text "|" <> chomp d makeCell [Para x] = makeCell [Plain x] - makeCell _ = return $ text "|" <> "[multiblock cell omitted]" + makeCell [] = return $ text "|" + makeCell bs = do d <- blockListToAsciiDoc opts bs + return $ text "a|" $$ d let makeRow cells = hsep `fmap` mapM makeCell cells rows' <- mapM makeRow rows head' <- makeRow headers @@ -227,7 +233,7 @@ blockToAsciiDoc opts (Table caption aligns widths headers rows) = do else 100000 let maxwidth = maximum $ map offset (head':rows') let body = if maxwidth > colwidth then vsep rows' else vcat rows' - let border = text $ "|" ++ replicate ((min maxwidth colwidth) - 1) '=' + let border = text $ "|" ++ replicate (max 5 (min maxwidth colwidth) - 1) '=' return $ caption'' $$ tablespec $$ border $$ head'' $$ body $$ border $$ blankline blockToAsciiDoc opts (BulletList items) = do @@ -315,17 +321,51 @@ blockListToAsciiDoc opts blocks = cat `fmap` mapM (blockToAsciiDoc opts) blocks -- | Convert list of Pandoc inline elements to asciidoc. inlineListToAsciiDoc :: WriterOptions -> [Inline] -> State WriterState Doc -inlineListToAsciiDoc opts lst = - mapM (inlineToAsciiDoc opts) lst >>= return . cat +inlineListToAsciiDoc opts lst = do + oldIntraword <- gets intraword + setIntraword False + result <- go lst + setIntraword oldIntraword + return result + where go [] = return empty + go (y:x:xs) + | not (isSpacy y) = do + y' <- if isSpacy x + then inlineToAsciiDoc opts y + else withIntraword $ inlineToAsciiDoc opts y + x' <- withIntraword $ inlineToAsciiDoc opts x + xs' <- go xs + return (y' <> x' <> xs') + | x /= Space && x /= LineBreak = do + y' <- withIntraword $ inlineToAsciiDoc opts y + xs' <- go (x:xs) + return (y' <> xs') + go (x:xs) = do + x' <- inlineToAsciiDoc opts x + xs' <- go xs + return (x' <> xs') + isSpacy Space = True + isSpacy LineBreak = True + isSpacy _ = False + +setIntraword :: Bool -> State WriterState () +setIntraword b = modify $ \st -> st{ intraword = b } + +withIntraword :: State WriterState a -> State WriterState a +withIntraword p = setIntraword True *> p <* setIntraword False -- | Convert Pandoc inline element to asciidoc. inlineToAsciiDoc :: WriterOptions -> Inline -> State WriterState Doc inlineToAsciiDoc opts (Emph lst) = do contents <- inlineListToAsciiDoc opts lst - return $ "_" <> contents <> "_" + isIntraword <- gets intraword + let marker = if isIntraword then "__" else "_" + return $ marker <> contents <> marker inlineToAsciiDoc opts (Strong lst) = do contents <- inlineListToAsciiDoc opts lst - return $ "*" <> contents <> "*" + isIntraword <- gets intraword + let marker = if isIntraword then "**" else "*" + return $ marker <> contents <> marker inlineToAsciiDoc opts (Strikeout lst) = do contents <- inlineListToAsciiDoc opts lst return $ "[line-through]*" <> contents <> "*" @@ -336,12 +376,10 @@ inlineToAsciiDoc opts (Subscript lst) = do contents <- inlineListToAsciiDoc opts lst return $ "~" <> contents <> "~" inlineToAsciiDoc opts (SmallCaps lst) = inlineListToAsciiDoc opts lst -inlineToAsciiDoc opts (Quoted SingleQuote lst) = do - contents <- inlineListToAsciiDoc opts lst - return $ "`" <> contents <> "'" -inlineToAsciiDoc opts (Quoted DoubleQuote lst) = do - contents <- inlineListToAsciiDoc opts lst - return $ "``" <> contents <> "''" +inlineToAsciiDoc opts (Quoted SingleQuote lst) = + inlineListToAsciiDoc opts (Str "`" : lst ++ [Str "'"]) +inlineToAsciiDoc opts (Quoted DoubleQuote lst) = + inlineListToAsciiDoc opts (Str "``" : lst ++ [Str "''"]) inlineToAsciiDoc _ (Code _ str) = return $ text "`" <> text (escapeStringUsing (backslashEscapes "`") str) <> "`" inlineToAsciiDoc _ (Str str) = return $ text $ escapeString str @@ -364,7 +402,7 @@ inlineToAsciiDoc opts (Link txt (src, _tit)) = do let prefix = if isRelative then text "link:" else empty - let srcSuffix = if isPrefixOf "mailto:" src then drop 7 src else src + let srcSuffix = fromMaybe src (stripPrefix "mailto:" src) let useAuto = case txt of [Str s] | escapeURI s == srcSuffix -> True _ -> False diff --git a/src/Text/Pandoc/Writers/ConTeXt.hs b/src/Text/Pandoc/Writers/ConTeXt.hs index 3095cf508..ebdc4a3d3 100644 --- a/src/Text/Pandoc/Writers/ConTeXt.hs +++ b/src/Text/Pandoc/Writers/ConTeXt.hs @@ -1,6 +1,6 @@ {-# LANGUAGE OverloadedStrings #-} {- -Copyright (C) 2007-2010 John MacFarlane <jgm@berkeley.edu> +Copyright (C) 2007-2014 John MacFarlane <jgm@berkeley.edu> This program is free software; you can redistribute it and/or modify it under the terms of the GNU General Public License as published by @@ -19,7 +19,7 @@ Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA {- | Module : Text.Pandoc.Writers.ConTeXt - Copyright : Copyright (C) 2007-2010 John MacFarlane + Copyright : Copyright (C) 2007-2014 John MacFarlane License : GNU GPL, version 2 or above Maintainer : John MacFarlane <jgm@berkeley.edu> @@ -35,7 +35,8 @@ import Text.Pandoc.Writers.Shared import Text.Pandoc.Options import Text.Pandoc.Walk (query) import Text.Printf ( printf ) -import Data.List ( intercalate, isPrefixOf ) +import Data.List ( intercalate ) +import Data.Char ( ord ) import Control.Monad.State import Text.Pandoc.Pretty import Text.Pandoc.Templates ( renderTemplate' ) @@ -114,6 +115,13 @@ escapeCharForConTeXt opts ch = stringToConTeXt :: WriterOptions -> String -> String stringToConTeXt opts = concatMap (escapeCharForConTeXt opts) +-- | Sanitize labels +toLabel :: String -> String +toLabel z = concatMap go z + where go x + | elem x "\\#[]\",{}%()|=" = "ux" ++ printf "%x" (ord x) + | otherwise = [x] + -- | Convert Elements to ConTeXt elementToConTeXt :: WriterOptions -> Element -> State WriterState Doc elementToConTeXt _ (Blk block) = blockToConTeXt block @@ -283,38 +291,33 @@ inlineToConTeXt (RawInline "tex" str) = return $ text str inlineToConTeXt (RawInline _ _) = return empty inlineToConTeXt (LineBreak) = return $ text "\\crlf" <> cr inlineToConTeXt Space = return space --- autolink -inlineToConTeXt (Link [Str str] (src, tit)) - | if "mailto:" `isPrefixOf` src - then src == escapeURI ("mailto:" ++ str) - else src == escapeURI str = - inlineToConTeXt (Link - [RawInline "context" "\\hyphenatedurl{", Str str, RawInline "context" "}"] - (src, tit)) -- Handle HTML-like internal document references to sections inlineToConTeXt (Link txt (('#' : ref), _)) = do opts <- gets stOptions - label <- inlineListToConTeXt txt + contents <- inlineListToConTeXt txt + let ref' = toLabel $ stringToConTeXt opts ref return $ text "\\in" <> braces (if writerNumberSections opts - then label <+> text "(\\S" - else label) -- prefix + then contents <+> text "(\\S" + else contents) -- prefix <> braces (if writerNumberSections opts then text ")" else empty) -- suffix - <> brackets (text ref) + <> brackets (text ref') inlineToConTeXt (Link txt (src, _)) = do + let isAutolink = txt == [Str (unEscapeString src)] st <- get let next = stNextRef st put $ st {stNextRef = next + 1} let ref = "url" ++ show next - label <- inlineListToConTeXt txt + contents <- inlineListToConTeXt txt return $ "\\useURL" <> brackets (text ref) <> brackets (text $ escapeStringUsing [('#',"\\#"),('%',"\\%")] src) - <> brackets empty - <> brackets label + <> (if isAutolink + then empty + else brackets empty <> brackets contents) <> "\\from" <> brackets (text ref) inlineToConTeXt (Image _ (src, _)) = do @@ -343,6 +346,7 @@ sectionHeader (ident,classes,_) hdrLevel lst = do st <- get let opts = stOptions st let level' = if writerChapters opts then hdrLevel - 1 else hdrLevel + let ident' = toLabel ident let (section, chapter) = if "unnumbered" `elem` classes then (text "subject", text "title") else (text "section", text "chapter") @@ -350,7 +354,7 @@ sectionHeader (ident,classes,_) hdrLevel lst = do then char '\\' <> text (concat (replicate (level' - 1) "sub")) <> section - <> (if (not . null) ident then brackets (text ident) else empty) + <> (if (not . null) ident' then brackets (text ident') else empty) <> braces contents <> blankline else if level' == 0 diff --git a/src/Text/Pandoc/Writers/Custom.hs b/src/Text/Pandoc/Writers/Custom.hs index 0234e1e35..914d61850 100644 --- a/src/Text/Pandoc/Writers/Custom.hs +++ b/src/Text/Pandoc/Writers/Custom.hs @@ -1,6 +1,7 @@ -{-# LANGUAGE OverlappingInstances, FlexibleInstances, OverloadedStrings #-} +{-# LANGUAGE OverlappingInstances, FlexibleInstances, OverloadedStrings, + ScopedTypeVariables #-} {-# OPTIONS_GHC -fno-warn-orphans #-} -{- Copyright (C) 2012 John MacFarlane <jgm@berkeley.edu> +{- Copyright (C) 2012-2014 John MacFarlane <jgm@berkeley.edu> This program is free software; you can redistribute it and/or modify it under the terms of the GNU General Public License as published by @@ -19,7 +20,7 @@ Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA {- | Module : Text.Pandoc.Writers.Custom - Copyright : Copyright (C) 2012 John MacFarlane + Copyright : Copyright (C) 2012-2014 John MacFarlane License : GNU GPL, version 2 or above Maintainer : John MacFarlane <jgm@berkeley.edu> @@ -35,12 +36,14 @@ import Text.Pandoc.Options import Data.List ( intersperse ) import Data.Char ( toLower ) import Scripting.Lua (LuaState, StackValue, callfunc) +import Text.Pandoc.Writers.Shared import qualified Scripting.Lua as Lua import Text.Pandoc.UTF8 (fromString, toString) import Data.ByteString (ByteString) import qualified Data.ByteString.Char8 as C8 import Data.Monoid import qualified Data.Map as M +import Text.Pandoc.Templates attrToMap :: Attr -> M.Map ByteString ByteString attrToMap (id',classes,keyvals) = M.fromList @@ -128,18 +131,41 @@ instance StackValue MetaValue where valuetype (MetaInlines _) = Lua.TSTRING valuetype (MetaBlocks _) = Lua.TSTRING +instance StackValue Citation where + push lua cit = do + Lua.createtable lua 6 0 + let addValue ((k :: String), v) = Lua.push lua k >> Lua.push lua v >> + Lua.rawset lua (-3) + addValue ("citationId", citationId cit) + addValue ("citationPrefix", citationPrefix cit) + addValue ("citationSuffix", citationSuffix cit) + addValue ("citationMode", show (citationMode cit)) + addValue ("citationNoteNum", citationNoteNum cit) + addValue ("citationHash", citationHash cit) + peek = undefined + valuetype _ = Lua.TTABLE + -- | Convert Pandoc to custom markup. writeCustom :: FilePath -> WriterOptions -> Pandoc -> IO String -writeCustom luaFile opts doc = do - luaScript <- readFile luaFile +writeCustom luaFile opts doc@(Pandoc meta _) = do + luaScript <- C8.unpack `fmap` C8.readFile luaFile lua <- Lua.newstate Lua.openlibs lua Lua.loadstring lua luaScript "custom" Lua.call lua 0 0 -- TODO - call hierarchicalize, so we have that info rendered <- docToCustom lua opts doc + context <- metaToJSON opts + (fmap toString . blockListToCustom lua) + (fmap toString . inlineListToCustom lua) + meta Lua.close lua - return $ toString rendered + let body = toString rendered + if writerStandalone opts + then do + let context' = setField "body" body context + return $ renderTemplate' (writerTemplate opts) context' + else return body docToCustom :: LuaState -> WriterOptions -> Pandoc -> IO ByteString docToCustom lua opts (Pandoc (Meta metamap) blocks) = do @@ -225,7 +251,7 @@ inlineToCustom lua (Quoted SingleQuote lst) = callfunc lua "SingleQuoted" lst inlineToCustom lua (Quoted DoubleQuote lst) = callfunc lua "DoubleQuoted" lst -inlineToCustom lua (Cite _ lst) = callfunc lua "Cite" lst +inlineToCustom lua (Cite cs lst) = callfunc lua "Cite" lst cs inlineToCustom lua (Code attr str) = callfunc lua "Code" (fromString str) (attrToMap attr) diff --git a/src/Text/Pandoc/Writers/Docbook.hs b/src/Text/Pandoc/Writers/Docbook.hs index 02d875be3..b10317506 100644 --- a/src/Text/Pandoc/Writers/Docbook.hs +++ b/src/Text/Pandoc/Writers/Docbook.hs @@ -1,6 +1,6 @@ -{-# LANGUAGE OverloadedStrings #-} +{-# LANGUAGE OverloadedStrings, PatternGuards #-} {- -Copyright (C) 2006-2010 John MacFarlane <jgm@berkeley.edu> +Copyright (C) 2006-2014 John MacFarlane <jgm@berkeley.edu> This program is free software; you can redistribute it and/or modify it under the terms of the GNU General Public License as published by @@ -19,7 +19,7 @@ Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA {- | Module : Text.Pandoc.Writers.Docbook - Copyright : Copyright (C) 2006-2010 John MacFarlane + Copyright : Copyright (C) 2006-2014 John MacFarlane License : GNU GPL, version 2 or above Maintainer : John MacFarlane <jgm@berkeley.edu> @@ -32,12 +32,15 @@ module Text.Pandoc.Writers.Docbook ( writeDocbook) where import Text.Pandoc.Definition import Text.Pandoc.XML import Text.Pandoc.Shared +import Text.Pandoc.Walk import Text.Pandoc.Writers.Shared import Text.Pandoc.Options import Text.Pandoc.Templates (renderTemplate') import Text.Pandoc.Readers.TeXMath -import Data.List ( isPrefixOf, intercalate, isSuffixOf ) +import Data.List ( stripPrefix, isPrefixOf, intercalate, isSuffixOf ) import Data.Char ( toLower ) +import Control.Applicative ((<$>)) +import Data.Monoid ( Any(..) ) import Text.Pandoc.Highlighting ( languages, languagesByExtension ) import Text.Pandoc.Pretty import qualified Text.Pandoc.Builder as B @@ -165,8 +168,9 @@ blockToDocbook opts (Para [Image txt (src,'f':'i':'g':':':_)]) = (inTagsIndented "imageobject" (selfClosingTag "imagedata" [("fileref",src)])) $$ inTagsSimple "textobject" (inTagsSimple "phrase" alt)) -blockToDocbook opts (Para lst) = - inTagsIndented "para" $ inlinesToDocbook opts lst +blockToDocbook opts (Para lst) + | hasLineBreaks lst = flush $ nowrap $ inTagsSimple "literallayout" $ inlinesToDocbook opts lst + | otherwise = inTagsIndented "para" $ inlinesToDocbook opts lst blockToDocbook opts (BlockQuote blocks) = inTagsIndented "blockquote" $ blocksToDocbook opts blocks blockToDocbook _ (CodeBlock (_,classes,_) str) = @@ -182,10 +186,11 @@ blockToDocbook _ (CodeBlock (_,classes,_) str) = else languagesByExtension . map toLower $ s langs = concatMap langsFrom classes blockToDocbook opts (BulletList lst) = - inTagsIndented "itemizedlist" $ listItemsToDocbook opts lst + let attribs = [("spacing", "compact") | isTightList lst] + in inTags True "itemizedlist" attribs $ listItemsToDocbook opts lst blockToDocbook _ (OrderedList _ []) = empty blockToDocbook opts (OrderedList (start, numstyle, _) (first:rest)) = - let attribs = case numstyle of + let numeration = case numstyle of DefaultStyle -> [] Decimal -> [("numeration", "arabic")] Example -> [("numeration", "arabic")] @@ -193,14 +198,17 @@ blockToDocbook opts (OrderedList (start, numstyle, _) (first:rest)) = LowerAlpha -> [("numeration", "loweralpha")] UpperRoman -> [("numeration", "upperroman")] LowerRoman -> [("numeration", "lowerroman")] - items = if start == 1 - then listItemsToDocbook opts (first:rest) - else (inTags True "listitem" [("override",show start)] - (blocksToDocbook opts $ map plainToPara first)) $$ - listItemsToDocbook opts rest + spacing = [("spacing", "compact") | isTightList (first:rest)] + attribs = numeration ++ spacing + items = if start == 1 + then listItemsToDocbook opts (first:rest) + else (inTags True "listitem" [("override",show start)] + (blocksToDocbook opts $ map plainToPara first)) $$ + listItemsToDocbook opts rest in inTags True "orderedlist" attribs items blockToDocbook opts (DefinitionList lst) = - inTagsIndented "variablelist" $ deflistItemsToDocbook opts lst + let attribs = [("spacing", "compact") | isTightList $ concatMap snd lst] + in inTags True "variablelist" attribs $ deflistItemsToDocbook opts lst blockToDocbook _ (RawBlock f str) | f == "docbook" = text str -- raw XML block | f == "html" = text str -- allow html for backwards compatibility @@ -226,6 +234,16 @@ blockToDocbook opts (Table caption aligns widths headers rows) = (inTags True "tgroup" [("cols", show (length headers))] $ coltags $$ head' $$ body') +hasLineBreaks :: [Inline] -> Bool +hasLineBreaks = getAny . query isLineBreak . walk removeNote + where + removeNote :: Inline -> Inline + removeNote (Note _) = Str "" + removeNote x = x + isLineBreak :: Inline -> Any + isLineBreak LineBreak = Any True + isLineBreak _ = Any False + alignmentToString :: Alignment -> [Char] alignmentToString alignment = case alignment of AlignLeft -> "left" @@ -276,14 +294,14 @@ inlineToDocbook _ (Code _ str) = inTagsSimple "literal" $ text (escapeStringForXML str) inlineToDocbook opts (Math t str) | isMathML (writerHTMLMathMethod opts) = - case texMathToMathML dt str of - Right r -> inTagsSimple tagtype - $ text $ Xml.ppcElement conf - $ fixNS - $ removeAttr r - Left _ -> inlinesToDocbook opts - $ readTeXMath' t str - | otherwise = inlinesToDocbook opts $ readTeXMath' t str + case writeMathML dt <$> readTeX str of + Right r -> inTagsSimple tagtype + $ text $ Xml.ppcElement conf + $ fixNS + $ removeAttr r + Left _ -> inlinesToDocbook opts + $ texMathToInlines t str + | otherwise = inlinesToDocbook opts $ texMathToInlines t str where (dt, tagtype) = case t of InlineMath -> (DisplayInline,"inlineequation") DisplayMath -> (DisplayBlock,"informalequation") @@ -293,21 +311,21 @@ inlineToDocbook opts (Math t str) fixNS = everywhere (mkT fixNS') inlineToDocbook _ (RawInline f x) | f == "html" || f == "docbook" = text x | otherwise = empty -inlineToDocbook _ LineBreak = flush $ inTagsSimple "literallayout" (text "\n") +inlineToDocbook _ LineBreak = text "\n" inlineToDocbook _ Space = space -inlineToDocbook opts (Link txt (src, _)) = - if isPrefixOf "mailto:" src - then let src' = drop 7 src - emailLink = inTagsSimple "email" $ text $ - escapeStringForXML $ src' - in case txt of - [Str s] | escapeURI s == src' -> emailLink - _ -> inlinesToDocbook opts txt <+> - char '(' <> emailLink <> char ')' - else (if isPrefixOf "#" src - then inTags False "link" [("linkend", drop 1 src)] - else inTags False "ulink" [("url", src)]) $ - inlinesToDocbook opts txt +inlineToDocbook opts (Link txt (src, _)) + | Just email <- stripPrefix "mailto:" src = + let emailLink = inTagsSimple "email" $ text $ + escapeStringForXML $ email + in case txt of + [Str s] | escapeURI s == email -> emailLink + _ -> inlinesToDocbook opts txt <+> + char '(' <> emailLink <> char ')' + | otherwise = + (if isPrefixOf "#" src + then inTags False "link" [("linkend", drop 1 src)] + else inTags False "ulink" [("url", src)]) $ + inlinesToDocbook opts txt inlineToDocbook _ (Image _ (src, tit)) = let titleDoc = if null tit then empty diff --git a/src/Text/Pandoc/Writers/Docx.hs b/src/Text/Pandoc/Writers/Docx.hs index 2a834c2da..5b9cc62ab 100644 --- a/src/Text/Pandoc/Writers/Docx.hs +++ b/src/Text/Pandoc/Writers/Docx.hs @@ -1,6 +1,6 @@ -{-# LANGUAGE ScopedTypeVariables #-} +{-# LANGUAGE ScopedTypeVariables, PatternGuards #-} {- -Copyright (C) 2012 John MacFarlane <jgm@berkeley.edu> +Copyright (C) 2012-2014 John MacFarlane <jgm@berkeley.edu> This program is free software; you can redistribute it and/or modify it under the terms of the GNU General Public License as published by @@ -19,7 +19,7 @@ Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA {- | Module : Text.Pandoc.Writers.Docx - Copyright : Copyright (C) 2012 John MacFarlane + Copyright : Copyright (C) 2012-2014 John MacFarlane License : GNU GPL, version 2 or above Maintainer : John MacFarlane <jgm@berkeley.edu> @@ -29,8 +29,7 @@ Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA Conversion of 'Pandoc' documents to docx. -} module Text.Pandoc.Writers.Docx ( writeDocx ) where -import Data.Maybe (fromMaybe) -import Data.List ( intercalate, isPrefixOf, isSuffixOf ) +import Data.List ( intercalate, isPrefixOf, isSuffixOf, stripPrefix ) import qualified Data.ByteString as B import qualified Data.ByteString.Lazy as BL import qualified Data.ByteString.Lazy.Char8 as BL8 @@ -39,6 +38,10 @@ import qualified Text.Pandoc.UTF8 as UTF8 import Text.Pandoc.Compat.Monoid ((<>)) import Codec.Archive.Zip import Data.Time.Clock.POSIX +import Data.Time.Clock +import Data.Time.Format +import System.Environment +import System.Locale import Text.Pandoc.Definition import Text.Pandoc.Generic import Text.Pandoc.ImageSize @@ -49,7 +52,7 @@ import Text.Pandoc.Readers.TeXMath import Text.Pandoc.Highlighting ( highlight ) import Text.Pandoc.Walk import Text.Highlighting.Kate.Types () -import Text.XML.Light +import Text.XML.Light as XML import Text.TeXMath import Control.Monad.State import Text.Highlighting.Kate @@ -57,8 +60,35 @@ import Data.Unique (hashUnique, newUnique) import System.Random (randomRIO) import Text.Printf (printf) import qualified Control.Exception as E -import Text.Pandoc.MIME (getMimeType, extensionFromMimeType) -import Control.Applicative ((<|>)) +import Text.Pandoc.MIME (MimeType, getMimeType, getMimeTypeDef, + extensionFromMimeType) +import Control.Applicative ((<$>), (<|>), (<*>)) +import Data.Maybe (fromMaybe, mapMaybe) +import Data.Char (isDigit) + +data ListMarker = NoMarker + | BulletMarker + | NumberMarker ListNumberStyle ListNumberDelim Int + deriving (Show, Read, Eq, Ord) + +listMarkerToId :: ListMarker -> String +listMarkerToId NoMarker = "990" +listMarkerToId BulletMarker = "991" +listMarkerToId (NumberMarker sty delim n) = + '9' : '9' : styNum : delimNum : show n + where styNum = case sty of + DefaultStyle -> '2' + Example -> '3' + Decimal -> '4' + LowerRoman -> '5' + UpperRoman -> '6' + LowerAlpha -> '7' + UpperAlpha -> '8' + delimNum = case delim of + DefaultDelim -> '0' + Period -> '1' + OneParen -> '2' + TwoParens -> '3' data WriterState = WriterState{ stTextProperties :: [Element] @@ -66,18 +96,19 @@ data WriterState = WriterState{ , stFootnotes :: [Element] , stSectionIds :: [String] , stExternalLinks :: M.Map String String - , stImages :: M.Map FilePath (String, String, Maybe String, Element, B.ByteString) + , stImages :: M.Map FilePath (String, String, Maybe MimeType, Element, B.ByteString) , stListLevel :: Int , stListNumId :: Int - , stNumStyles :: M.Map ListMarker Int , stLists :: [ListMarker] + , stInsId :: Int + , stDelId :: Int + , stInDel :: Bool + , stChangesAuthor :: String + , stChangesDate :: String + , stPrintWidth :: Integer + , stHeadingStyles :: [(Int,String)] } -data ListMarker = NoMarker - | BulletMarker - | NumberMarker ListNumberStyle ListNumberDelim Int - deriving (Show, Read, Eq, Ord) - defaultWriterState :: WriterState defaultWriterState = WriterState{ stTextProperties = [] @@ -88,15 +119,27 @@ defaultWriterState = WriterState{ , stImages = M.empty , stListLevel = -1 , stListNumId = 1 - , stNumStyles = M.fromList [(NoMarker, 0)] , stLists = [NoMarker] + , stInsId = 1 + , stDelId = 1 + , stInDel = False + , stChangesAuthor = "unknown" + , stChangesDate = "1969-12-31T19:00:00Z" + , stPrintWidth = 1 + , stHeadingStyles = [] } type WS a = StateT WriterState IO a mknode :: Node t => String -> [(String,String)] -> t -> Element mknode s attrs = - add_attrs (map (\(k,v) -> Attr (unqual k) v) attrs) . node (unqual s) + add_attrs (map (\(k,v) -> Attr (nodename k) v) attrs) . node (nodename s) + +nodename :: String -> QName +nodename s = QName{ qName = name, qURI = Nothing, qPrefix = prefix } + where (name, prefix) = case break (==':') s of + (xs,[]) -> (xs, Nothing) + (ys, _:zs) -> (zs, Just ys) toLazy :: B.ByteString -> BL.ByteString toLazy = BL.fromChunks . (:[]) @@ -105,6 +148,31 @@ renderXml :: Element -> BL.ByteString renderXml elt = BL8.pack "<?xml version=\"1.0\" encoding=\"UTF-8\"?>\n" <> UTF8.fromStringLazy (showElement elt) +renumIdMap :: Int -> [Element] -> M.Map String String +renumIdMap _ [] = M.empty +renumIdMap n (e:es) + | Just oldId <- findAttr (QName "Id" Nothing Nothing) e = + M.insert oldId ("rId" ++ (show n)) (renumIdMap (n+1) es) + | otherwise = renumIdMap n es + +replaceAttr :: (QName -> Bool) -> String -> [XML.Attr] -> [XML.Attr] +replaceAttr _ _ [] = [] +replaceAttr f val (a:as) | f (attrKey a) = + (XML.Attr (attrKey a) val) : (replaceAttr f val as) + | otherwise = a : (replaceAttr f val as) + +renumId :: (QName -> Bool) -> (M.Map String String) -> Element -> Element +renumId f renumMap e + | Just oldId <- findAttrBy f e + , Just newId <- M.lookup oldId renumMap = + let attrs' = replaceAttr f newId (elAttribs e) + in + e { elAttribs = attrs' } + | otherwise = e + +renumIds :: (QName -> Bool) -> (M.Map String String) -> [Element] -> [Element] +renumIds f renumMap = map (renumId f renumMap) + -- | Produce an Docx file from a Pandoc document. writeDocx :: WriterOptions -- ^ Writer options -> Pandoc -- ^ Document to convert @@ -112,16 +180,92 @@ writeDocx :: WriterOptions -- ^ Writer options writeDocx opts doc@(Pandoc meta _) = do let datadir = writerUserDataDir opts let doc' = walk fixDisplayMath doc + username <- lookup "USERNAME" <$> getEnvironment + utctime <- getCurrentTime refArchive <- liftM (toArchive . toLazy) $ case writerReferenceDocx opts of Just f -> B.readFile f Nothing -> readDataFile datadir "reference.docx" + distArchive <- liftM (toArchive . toLazy) $ readDataFile datadir "reference.docx" + + parsedDoc <- parseXml refArchive distArchive "word/document.xml" + let wname f qn = qPrefix qn == Just "w" && f (qName qn) + let mbsectpr = filterElementName (wname (=="sectPr")) parsedDoc + + -- Gets the template size + let mbpgsz = mbsectpr >>= (filterElementName (wname (=="pgSz"))) + let mbAttrSzWidth = (elAttribs <$> mbpgsz) >>= (lookupAttrBy ((=="w") . qName)) + + let mbpgmar = mbsectpr >>= (filterElementName (wname (=="pgMar"))) + let mbAttrMarLeft = (elAttribs <$> mbpgmar) >>= (lookupAttrBy ((=="left") . qName)) + let mbAttrMarRight = (elAttribs <$> mbpgmar) >>= (lookupAttrBy ((=="right") . qName)) + + -- Get the avaible area (converting the size and the margins to int and + -- doing the difference + let pgContentWidth = (-) <$> (read <$> mbAttrSzWidth ::Maybe Integer) + <*> ( + (+) <$> (read <$> mbAttrMarRight ::Maybe Integer) + <*> (read <$> mbAttrMarLeft ::Maybe Integer) + ) + + -- styles + let stylepath = "word/styles.xml" + styledoc <- parseXml refArchive distArchive stylepath + + -- parse styledoc for heading styles + let styleNamespaces = map ((,) <$> qName . attrKey <*> attrVal) . + filter ((==Just "xmlns") . qPrefix . attrKey) . + elAttribs $ styledoc + let headingStyles = + let + mywURI = lookup "w" styleNamespaces + myName name = QName name mywURI (Just "w") + getAttrStyleId = findAttr (myName "styleId") + getNameVal = findChild (myName "name") >=> findAttr (myName "val") + getNum s | not $ null s, all isDigit s = Just (read s :: Int) + | otherwise = Nothing + getEngHeader = getAttrStyleId >=> stripPrefix "Heading" >=> getNum + getIntHeader = getNameVal >=> stripPrefix "heading " >=> getNum + toTuple getF = liftM2 (,) <$> getF <*> getAttrStyleId + toMap getF = mapMaybe (toTuple getF) $ + findChildren (myName "style") styledoc + select a b | not $ null a = a + | otherwise = b + in + select (toMap getEngHeader) (toMap getIntHeader) ((contents, footnotes), st) <- runStateT (writeOpenXML opts{writerWrapText = False} doc') - defaultWriterState - epochtime <- floor `fmap` getPOSIXTime + defaultWriterState{ stChangesAuthor = fromMaybe "unknown" username + , stChangesDate = formatTime defaultTimeLocale "%FT%XZ" utctime + , stPrintWidth = (maybe 420 (\x -> quot x 20) pgContentWidth) + , stHeadingStyles = headingStyles} + let epochtime = floor $ utcTimeToPOSIXSeconds utctime let imgs = M.elems $ stImages st + -- create entries for images in word/media/... + let toImageEntry (_,path,_,_,img) = toEntry ("word/" ++ path) epochtime $ toLazy img + let imageEntries = map toImageEntry imgs + + let stdAttributes = + [("xmlns:w","http://schemas.openxmlformats.org/wordprocessingml/2006/main") + ,("xmlns:m","http://schemas.openxmlformats.org/officeDocument/2006/math") + ,("xmlns:r","http://schemas.openxmlformats.org/officeDocument/2006/relationships") + ,("xmlns:o","urn:schemas-microsoft-com:office:office") + ,("xmlns:v","urn:schemas-microsoft-com:vml") + ,("xmlns:w10","urn:schemas-microsoft-com:office:word") + ,("xmlns:a","http://schemas.openxmlformats.org/drawingml/2006/main") + ,("xmlns:pic","http://schemas.openxmlformats.org/drawingml/2006/picture") + ,("xmlns:wp","http://schemas.openxmlformats.org/drawingml/2006/wordprocessingDrawing")] + + + parsedRels <- parseXml refArchive distArchive "word/_rels/document.xml.rels" + let isHeaderNode e = findAttr (QName "Type" Nothing Nothing) e == Just "http://schemas.openxmlformats.org/officeDocument/2006/relationships/header" + let isFooterNode e = findAttr (QName "Type" Nothing Nothing) e == Just "http://schemas.openxmlformats.org/officeDocument/2006/relationships/footer" + let headers = filterElements isHeaderNode parsedRels + let footers = filterElements isFooterNode parsedRels + + let extractTarget = findAttr (QName "Target" Nothing Nothing) + -- we create [Content_Types].xml and word/_rels/document.xml.rels -- from scratch rather than reading from reference.docx, -- because Word sometimes changes these files when a reference.docx is modified, @@ -132,9 +276,11 @@ writeDocx opts doc@(Pandoc meta _) = do let mkOverrideNode (part', contentType') = mknode "Override" [("PartName",part'),("ContentType",contentType')] () let mkImageOverride (_, imgpath, mbMimeType, _, _) = - mkOverrideNode ("/word/" ++ imgpath, - fromMaybe "application/octet-stream" mbMimeType) - let overrides = map mkOverrideNode + mkOverrideNode ("/word/" ++ imgpath, + fromMaybe "application/octet-stream" mbMimeType) + let mkMediaOverride imgpath = + mkOverrideNode ('/':imgpath, getMimeTypeDef imgpath) + let overrides = map mkOverrideNode ( [("/word/webSettings.xml", "application/vnd.openxmlformats-officedocument.wordprocessingml.webSettings+xml") ,("/word/numbering.xml", @@ -155,7 +301,15 @@ writeDocx opts doc@(Pandoc meta _) = do "application/vnd.openxmlformats-officedocument.wordprocessingml.document.main+xml") ,("/word/footnotes.xml", "application/vnd.openxmlformats-officedocument.wordprocessingml.footnotes+xml") - ] ++ map mkImageOverride imgs + ] ++ + map (\x -> (maybe "" ("/word/" ++) $ extractTarget x, + "application/vnd.openxmlformats-officedocument.wordprocessingml.header+xml")) headers ++ + map (\x -> (maybe "" ("/word/" ++) $ extractTarget x, + "application/vnd.openxmlformats-officedocument.wordprocessingml.footer+xml")) footers) ++ + map mkImageOverride imgs ++ + map mkMediaOverride [ eRelativePath e | e <- zEntries refArchive + , "word/media/" `isPrefixOf` eRelativePath e ] + let defaultnodes = [mknode "Default" [("Extension","xml"),("ContentType","application/xml")] (), mknode "Default" @@ -169,7 +323,7 @@ writeDocx opts doc@(Pandoc meta _) = do [("Type",url') ,("Id",id') ,("Target",target')] () - let baserels = map toBaseRel + let baserels' = map toBaseRel [("http://schemas.openxmlformats.org/officeDocument/2006/relationships/numbering", "rId1", "numbering.xml") @@ -190,7 +344,13 @@ writeDocx opts doc@(Pandoc meta _) = do "theme/theme1.xml") ,("http://schemas.openxmlformats.org/officeDocument/2006/relationships/footnotes", "rId7", - "footnotes.xml")] + "footnotes.xml") + ] + + let idMap = renumIdMap (length baserels' + 1) (headers ++ footers) + let renumHeaders = renumIds (\q -> qName q == "Id") idMap headers + let renumFooters = renumIds (\q -> qName q == "Id") idMap footers + let baserels = baserels' ++ renumHeaders ++ renumFooters let toImgRel (ident,path,_,_,_) = mknode "Relationship" [("Type","http://schemas.openxmlformats.org/officeDocument/2006/relationships/image"),("Id",ident),("Target",path)] () let imgrels = map toImgRel imgs let toLinkRel (src,ident) = mknode "Relationship" [("Type","http://schemas.openxmlformats.org/officeDocument/2006/relationships/hyperlink"),("Id",ident),("Target",src),("TargetMode","External") ] () @@ -199,33 +359,55 @@ writeDocx opts doc@(Pandoc meta _) = do let relEntry = toEntry "word/_rels/document.xml.rels" epochtime $ renderXml reldoc - -- create entries for images in word/media/... - let toImageEntry (_,path,_,_,img) = toEntry ("word/" ++ path) epochtime $ toLazy img - let imageEntries = map toImageEntry imgs + + -- adjust contents to add sectPr from reference.docx + let sectpr = case mbsectpr of + Just sectpr' -> let cs = renumIds + (\q -> qName q == "id" && qPrefix q == Just "r") + idMap + (elChildren sectpr') + in + add_attrs (elAttribs sectpr') $ mknode "w:sectPr" [] cs + Nothing -> (mknode "w:sectPr" [] ()) + + -- let sectpr = fromMaybe (mknode "w:sectPr" [] ()) mbsectpr' + let contents' = contents ++ [sectpr] + let docContents = mknode "w:document" stdAttributes + $ mknode "w:body" [] contents' + + -- word/document.xml - let contentEntry = toEntry "word/document.xml" epochtime $ renderXml contents + let contentEntry = toEntry "word/document.xml" epochtime + $ renderXml docContents -- footnotes - let footnotesEntry = toEntry "word/footnotes.xml" epochtime $ renderXml footnotes + let notes = mknode "w:footnotes" stdAttributes footnotes + let footnotesEntry = toEntry "word/footnotes.xml" epochtime $ renderXml notes -- footnote rels let footnoteRelEntry = toEntry "word/_rels/footnotes.xml.rels" epochtime $ renderXml $ mknode "Relationships" [("xmlns","http://schemas.openxmlformats.org/package/2006/relationships")] - $ linkrels + linkrels -- styles let newstyles = styleToOpenXml $ writerHighlightStyle opts - let stylepath = "word/styles.xml" - styledoc <- parseXml refArchive stylepath let styledoc' = styledoc{ elContent = elContent styledoc ++ [Elem x | x <- newstyles, writerHighlight opts] } let styleEntry = toEntry stylepath epochtime $ renderXml styledoc' -- construct word/numbering.xml let numpath = "word/numbering.xml" - numEntry <- (toEntry numpath epochtime . renderXml) - `fmap` mkNumbering (stNumStyles st) (stLists st) + numbering <- parseXml refArchive distArchive numpath + newNumElts <- mkNumbering (stLists st) + let allElts = onlyElems (elContent numbering) ++ newNumElts + let numEntry = toEntry numpath epochtime $ renderXml numbering{ elContent = + -- we want all the abstractNums first, then the nums, + -- otherwise things break: + [Elem e | e <- allElts + , qName (elName e) == "abstractNum" ] ++ + [Elem e | e <- allElts + , qName (elName e) == "num" ] } let docPropsPath = "docProps/core.xml" let docProps = mknode "cp:coreProperties" [("xmlns:cp","http://schemas.openxmlformats.org/package/2006/metadata/core-properties") @@ -236,8 +418,8 @@ writeDocx opts doc@(Pandoc meta _) = do $ mknode "dc:title" [] (stringify $ docTitle meta) : mknode "dc:creator" [] (intercalate "; " (map stringify $ docAuthors meta)) : maybe [] - (\x -> [ mknode "dcterms:created" [("xsi:type","dcterms:W3CDTF")] $ x - , mknode "dcterms:modified" [("xsi:type","dcterms:W3CDTF")] $ x + (\x -> [ mknode "dcterms:created" [("xsi:type","dcterms:W3CDTF")] x + , mknode "dcterms:modified" [("xsi:type","dcterms:W3CDTF")] x ]) (normalizeDate $ stringify $ docDate meta) let docPropsEntry = toEntry docPropsPath epochtime $ renderXml docProps @@ -256,19 +438,27 @@ writeDocx opts doc@(Pandoc meta _) = do ] let relsEntry = toEntry relsPath epochtime $ renderXml rels - let entryFromArchive path = (toEntry path epochtime . renderXml) `fmap` - parseXml refArchive path - docPropsAppEntry <- entryFromArchive "docProps/app.xml" - themeEntry <- entryFromArchive "word/theme/theme1.xml" - fontTableEntry <- entryFromArchive "word/fontTable.xml" - settingsEntry <- entryFromArchive "word/settings.xml" - webSettingsEntry <- entryFromArchive "word/webSettings.xml" - let miscRels = [ f | f <- filesInArchive refArchive - , "word/_rels/" `isPrefixOf` f - , ".xml.rels" `isSuffixOf` f - , f /= "word/_rels/document.xml.rels" - , f /= "word/_rels/footnotes.xml.rels" ] - miscRelEntries <- mapM entryFromArchive miscRels + let entryFromArchive arch path = + maybe (fail $ path ++ " corrupt or missing in reference docx") + return + (findEntryByPath path arch `mplus` findEntryByPath path distArchive) + docPropsAppEntry <- entryFromArchive refArchive "docProps/app.xml" + themeEntry <- entryFromArchive refArchive "word/theme/theme1.xml" + fontTableEntry <- entryFromArchive refArchive "word/fontTable.xml" + -- we use dist archive for settings.xml, because Word sometimes + -- adds references to footnotes or endnotes we don't have... + settingsEntry <- entryFromArchive distArchive "word/settings.xml" + webSettingsEntry <- entryFromArchive refArchive "word/webSettings.xml" + headerFooterEntries <- mapM (entryFromArchive refArchive) $ + mapMaybe (fmap ("word/" ++) . extractTarget) + (headers ++ footers) + let miscRelEntries = [ e | e <- zEntries refArchive + , "word/_rels/" `isPrefixOf` (eRelativePath e) + , ".xml.rels" `isSuffixOf` (eRelativePath e) + , eRelativePath e /= "word/_rels/document.xml.rels" + , eRelativePath e /= "word/_rels/footnotes.xml.rels" ] + let otherMediaEntries = [ e | e <- zEntries refArchive + , "word/media/" `isPrefixOf` eRelativePath e ] -- Create archive let archive = foldr addEntryToArchive emptyArchive $ @@ -276,7 +466,8 @@ writeDocx opts doc@(Pandoc meta _) = do footnoteRelEntry : numEntry : styleEntry : footnotesEntry : docPropsEntry : docPropsAppEntry : themeEntry : fontTableEntry : settingsEntry : webSettingsEntry : - imageEntries ++ miscRelEntries + imageEntries ++ headerFooterEntries ++ + miscRelEntries ++ otherMediaEntries return $ fromArchive archive styleToOpenXml :: Style -> [Element] @@ -314,29 +505,30 @@ styleToOpenXml style = parStyle : map toStyle alltoktypes $ backgroundColor style ) ] -mkNumbering :: M.Map ListMarker Int -> [ListMarker] -> IO Element -mkNumbering markers lists = do - elts <- mapM mkAbstractNum (M.toList markers) - return $ mknode "w:numbering" - [("xmlns:w","http://schemas.openxmlformats.org/wordprocessingml/2006/main")] - $ elts ++ zipWith (mkNum markers) lists [1..(length lists)] +-- this is the lowest number used for a list numId +baseListId :: Int +baseListId = 1000 + +mkNumbering :: [ListMarker] -> IO [Element] +mkNumbering lists = do + elts <- mapM mkAbstractNum (ordNub lists) + return $ elts ++ zipWith mkNum lists [baseListId..(baseListId + length lists - 1)] -mkNum :: M.Map ListMarker Int -> ListMarker -> Int -> Element -mkNum markers marker numid = +mkNum :: ListMarker -> Int -> Element +mkNum marker numid = mknode "w:num" [("w:numId",show numid)] - $ mknode "w:abstractNumId" [("w:val",show absnumid)] () + $ mknode "w:abstractNumId" [("w:val",listMarkerToId marker)] () : case marker of NoMarker -> [] BulletMarker -> [] NumberMarker _ _ start -> map (\lvl -> mknode "w:lvlOverride" [("w:ilvl",show (lvl :: Int))] $ mknode "w:startOverride" [("w:val",show start)] ()) [0..6] - where absnumid = fromMaybe 0 $ M.lookup marker markers -mkAbstractNum :: (ListMarker,Int) -> IO Element -mkAbstractNum (marker,numid) = do +mkAbstractNum :: ListMarker -> IO Element +mkAbstractNum marker = do nsid <- randomRIO (0x10000000 :: Integer, 0xFFFFFFFF :: Integer) - return $ mknode "w:abstractNum" [("w:abstractNumId",show numid)] + return $ mknode "w:abstractNum" [("w:abstractNumId",listMarkerToId marker)] $ mknode "w:nsid" [("w:val", printf "%8x" nsid)] () : mknode "w:multiLevelType" [("w:val","multilevel")] () : map (mkLvl marker) [0..6] @@ -388,40 +580,42 @@ mkLvl marker lvl = patternFor _ s = s ++ "." getNumId :: WS Int -getNumId = length `fmap` gets stLists +getNumId = (((baseListId - 1) +) . length) `fmap` gets stLists --- | Convert Pandoc document to two OpenXML elements (the main document and footnotes). -writeOpenXML :: WriterOptions -> Pandoc -> WS (Element, Element) +-- | Convert Pandoc document to two lists of +-- OpenXML elements (the main document and footnotes). +writeOpenXML :: WriterOptions -> Pandoc -> WS ([Element], [Element]) writeOpenXML opts (Pandoc meta blocks) = do let tit = docTitle meta ++ case lookupMeta "subtitle" meta of Just (MetaBlocks [Plain xs]) -> LineBreak : xs _ -> [] let auths = docAuthors meta let dat = docDate meta + let abstract' = case lookupMeta "abstract" meta of + Just (MetaBlocks bs) -> bs + Just (MetaInlines ils) -> [Plain ils] + _ -> [] + let subtitle' = case lookupMeta "subtitle" meta of + Just (MetaBlocks [Plain xs]) -> xs + Just (MetaBlocks [Para xs]) -> xs + Just (MetaInlines xs) -> xs + _ -> [] title <- withParaProp (pStyle "Title") $ blocksToOpenXML opts [Para tit | not (null tit)] - authors <- withParaProp (pStyle "Authors") $ blocksToOpenXML opts - [Para (intercalate [LineBreak] auths) | not (null auths)] + subtitle <- withParaProp (pStyle "Subtitle") $ blocksToOpenXML opts [Para subtitle' | not (null subtitle')] + authors <- withParaProp (pStyle "Author") $ blocksToOpenXML opts $ + map Para auths date <- withParaProp (pStyle "Date") $ blocksToOpenXML opts [Para dat | not (null dat)] + abstract <- if null abstract' + then return [] + else withParaProp (pStyle "Abstract") $ blocksToOpenXML opts abstract' let convertSpace (Str x : Space : Str y : xs) = Str (x ++ " " ++ y) : xs convertSpace (Str x : Str y : xs) = Str (x ++ y) : xs convertSpace xs = xs - let blocks' = bottomUp convertSpace $ blocks + let blocks' = bottomUp convertSpace blocks doc' <- blocksToOpenXML opts blocks' notes' <- reverse `fmap` gets stFootnotes - let meta' = title ++ authors ++ date - let stdAttributes = - [("xmlns:w","http://schemas.openxmlformats.org/wordprocessingml/2006/main") - ,("xmlns:m","http://schemas.openxmlformats.org/officeDocument/2006/math") - ,("xmlns:r","http://schemas.openxmlformats.org/officeDocument/2006/relationships") - ,("xmlns:o","urn:schemas-microsoft-com:office:office") - ,("xmlns:v","urn:schemas-microsoft-com:vml") - ,("xmlns:w10","urn:schemas-microsoft-com:office:word") - ,("xmlns:a","http://schemas.openxmlformats.org/drawingml/2006/main") - ,("xmlns:pic","http://schemas.openxmlformats.org/drawingml/2006/picture") - ,("xmlns:wp","http://schemas.openxmlformats.org/drawingml/2006/wordprocessingDrawing")] - let doc = mknode "w:document" stdAttributes $ mknode "w:body" [] (meta' ++ doc') - let notes = mknode "w:footnotes" stdAttributes notes' - return (doc, notes) + let meta' = title ++ subtitle ++ authors ++ date ++ abstract + return (meta' ++ doc', notes') -- | Convert a list of Pandoc blocks to OpenXML. blocksToOpenXML :: WriterOptions -> [Block] -> WS [Element] @@ -441,10 +635,18 @@ getUniqueId = liftIO $ (show . (+ 20) . hashUnique) `fmap` newUnique -- | Convert a Pandoc block element to OpenXML. blockToOpenXML :: WriterOptions -> Block -> WS [Element] blockToOpenXML _ Null = return [] +blockToOpenXML opts (Div (_,["references"],_) bs) = do + let (hs, bs') = span isHeaderBlock bs + header <- blocksToOpenXML opts hs + -- We put the Bibliography style on paragraphs after the header + rest <- withParaProp (pStyle "Bibliography") $ blocksToOpenXML opts bs' + return (header ++ rest) blockToOpenXML opts (Div _ bs) = blocksToOpenXML opts bs blockToOpenXML opts (Header lev (ident,_,_) lst) = do - contents <- withParaProp (pStyle $ "Heading" ++ show lev) $ - blockToOpenXML opts (Para lst) + headingStyles <- gets stHeadingStyles + paraProps <- maybe id (withParaProp . pStyle) (lookup lev headingStyles) $ + getParaProps False + contents <- inlinesToOpenXML opts lst usedIdents <- gets stSectionIds let bookmarkName = if null ident then uniqueIdent lst usedIdents @@ -454,7 +656,7 @@ blockToOpenXML opts (Header lev (ident,_,_) lst) = do let bookmarkStart = mknode "w:bookmarkStart" [("w:id", id') ,("w:name",bookmarkName)] () let bookmarkEnd = mknode "w:bookmarkEnd" [("w:id", id')] () - return $ [bookmarkStart] ++ contents ++ [bookmarkEnd] + return [mknode "w:p" [] (paraProps ++ [bookmarkStart, bookmarkEnd] ++ contents)] blockToOpenXML opts (Plain lst) = withParaProp (pStyle "Compact") $ blockToOpenXML opts (Para lst) -- title beginning with fig: indicates that the image is a figure @@ -494,25 +696,30 @@ blockToOpenXML opts (Table caption aligns widths headers rows) = do let cellToOpenXML (al, cell) = withParaProp (alignmentFor al) $ blocksToOpenXML opts cell headers' <- mapM cellToOpenXML $ zip aligns headers - rows' <- mapM (\cells -> mapM cellToOpenXML $ zip aligns cells) - $ rows + rows' <- mapM (mapM cellToOpenXML . zip aligns) rows let borderProps = mknode "w:tcPr" [] [ mknode "w:tcBorders" [] $ mknode "w:bottom" [("w:val","single")] () , mknode "w:vAlign" [("w:val","bottom")] () ] + let emptyCell = [mknode "w:p" [] [mknode "w:pPr" [] + [mknode "w:pStyle" [("w:val","Compact")] ()]]] let mkcell border contents = mknode "w:tc" [] $ [ borderProps | border ] ++ if null contents - then [mknode "w:p" [] ()] + then emptyCell else contents let mkrow border cells = mknode "w:tr" [] $ map (mkcell border) cells let textwidth = 7920 -- 5.5 in in twips, 1/20 pt + let fullrow = 5000 -- 100% specified in pct + let rowwidth = fullrow * sum widths let mkgridcol w = mknode "w:gridCol" - [("w:w", show $ (floor (textwidth * w) :: Integer))] () + [("w:w", show (floor (textwidth * w) :: Integer))] () return $ - [ mknode "w:tbl" [] + caption' ++ + [mknode "w:tbl" [] ( mknode "w:tblPr" [] - ( [ mknode "w:tblStyle" [("w:val","TableNormal")] () ] ++ + ( mknode "w:tblStyle" [("w:val","TableNormal")] () : + mknode "w:tblW" [("w:type", "pct"), ("w:w", show rowwidth)] () : [ mknode "w:tblCaption" [("w:val", captionStr)] () | not (null caption) ] ) : mknode "w:tblGrid" [] @@ -521,8 +728,7 @@ blockToOpenXML opts (Table caption aligns widths headers rows) = do else map mkgridcol widths) : [ mkrow True headers' | not (all null headers) ] ++ map (mkrow False) rows' - ) - ] ++ caption' + )] blockToOpenXML opts (BulletList lst) = do let marker = BulletMarker addList marker @@ -548,17 +754,13 @@ addList :: ListMarker -> WS () addList marker = do lists <- gets stLists modify $ \st -> st{ stLists = lists ++ [marker] } - numStyles <- gets stNumStyles - case M.lookup marker numStyles of - Just _ -> return () - Nothing -> modify $ \st -> - st{ stNumStyles = M.insert marker (M.size numStyles + 1) numStyles } listItemToOpenXML :: WriterOptions -> Int -> [Block] -> WS [Element] listItemToOpenXML _ _ [] = return [] listItemToOpenXML opts numid (first:rest) = do first' <- withNumId numid $ blockToOpenXML opts first - rest' <- withNumId 1 $ blocksToOpenXML opts rest + -- baseListId is the code for no list marker: + rest' <- withNumId baseListId $ blocksToOpenXML opts rest return $ first' ++ rest' alignmentToString :: Alignment -> [Char] @@ -593,7 +795,7 @@ getTextProps = do props <- gets stTextProperties return $ if null props then [] - else [mknode "w:rPr" [] $ props] + else [mknode "w:rPr" [] props] pushTextProp :: Element -> WS () pushTextProp d = modify $ \s -> s{ stTextProperties = d : stTextProperties s } @@ -639,20 +841,49 @@ withParaProp d p = do formattedString :: String -> WS [Element] formattedString str = do props <- getTextProps + inDel <- gets stInDel return [ mknode "w:r" [] $ props ++ - [ mknode "w:t" [("xml:space","preserve")] str ] ] + [ mknode (if inDel then "w:delText" else "w:t") + [("xml:space","preserve")] str ] ] -- | Convert an inline element to OpenXML. inlineToOpenXML :: WriterOptions -> Inline -> WS [Element] inlineToOpenXML _ (Str str) = formattedString str inlineToOpenXML opts Space = inlineToOpenXML opts (Str " ") -inlineToOpenXML opts (Span (_,classes,_) ils) = do - let off x = withTextProp (mknode x [("w:val","0")] ()) - ((if "csl-no-emph" `elem` classes then off "w:i" else id) . - (if "csl-no-strong" `elem` classes then off "w:b" else id) . - (if "csl-no-smallcaps" `elem` classes then off "w:smallCaps" else id)) - $ inlinesToOpenXML opts ils +inlineToOpenXML opts (Span (_,classes,kvs) ils) + | "insertion" `elem` classes = do + defaultAuthor <- gets stChangesAuthor + defaultDate <- gets stChangesDate + let author = fromMaybe defaultAuthor (lookup "author" kvs) + date = fromMaybe defaultDate (lookup "date" kvs) + insId <- gets stInsId + modify $ \s -> s{stInsId = (insId + 1)} + x <- inlinesToOpenXML opts ils + return [ mknode "w:ins" [("w:id", (show insId)), + ("w:author", author), + ("w:date", date)] + x ] + | "deletion" `elem` classes = do + defaultAuthor <- gets stChangesAuthor + defaultDate <- gets stChangesDate + let author = fromMaybe defaultAuthor (lookup "author" kvs) + date = fromMaybe defaultDate (lookup "date" kvs) + delId <- gets stDelId + modify $ \s -> s{stDelId = (delId + 1)} + modify $ \s -> s{stInDel = True} + x <- inlinesToOpenXML opts ils + modify $ \s -> s{stInDel = False} + return [ mknode "w:del" [("w:id", (show delId)), + ("w:author", author), + ("w:date", date)] + x ] + | otherwise = do + let off x = withTextProp (mknode x [("w:val","0")] ()) + ((if "csl-no-emph" `elem` classes then off "w:i" else id) . + (if "csl-no-strong" `elem` classes then off "w:b" else id) . + (if "csl-no-smallcaps" `elem` classes then off "w:smallCaps" else id)) + $ inlinesToOpenXML opts ils inlineToOpenXML opts (Strong lst) = withTextProp (mknode "w:b" [] ()) $ inlinesToOpenXML opts lst inlineToOpenXML opts (Emph lst) = @@ -682,9 +913,9 @@ inlineToOpenXML opts (Math mathType str) = do let displayType = if mathType == DisplayMath then DisplayBlock else DisplayInline - case texMathToOMML displayType str of + case writeOMML displayType <$> readTeX str of Right r -> return [r] - Left _ -> inlinesToOpenXML opts (readTeXMath' mathType str) + Left _ -> inlinesToOpenXML opts (texMathToInlines mathType str) inlineToOpenXML opts (Cite _ lst) = inlinesToOpenXML opts lst inlineToOpenXML opts (Code attrs str) = withTextProp (rStyle "VerbatimChar") @@ -741,11 +972,13 @@ inlineToOpenXML opts (Link txt (src,_)) = do return [ mknode "w:hyperlink" [("r:id",id')] contents ] inlineToOpenXML opts (Image alt (src, tit)) = do -- first, check to see if we've already done this image + pageWidth <- gets stPrintWidth imgs <- gets stImages case M.lookup src imgs of Just (_,_,_,elt,_) -> return [elt] Nothing -> do - res <- liftIO $ fetchItem (writerSourceURL opts) src + res <- liftIO $ + fetchItem' (writerMediaBag opts) (writerSourceURL opts) src case res of Left (_ :: E.SomeException) -> do liftIO $ warn $ "Could not find image `" ++ src ++ "', skipping..." @@ -756,7 +989,7 @@ inlineToOpenXML opts (Image alt (src, tit)) = do let size = imageSize img let (xpt,ypt) = maybe (120,120) sizeInPoints size -- 12700 emu = 1 pt - let (xemu,yemu) = (xpt * 12700, ypt * 12700) + let (xemu,yemu) = fitToPage (xpt * 12700, ypt * 12700) (pageWidth * 12700) let cNvPicPr = mknode "pic:cNvPicPr" [] $ mknode "a:picLocks" [("noChangeArrowheads","1"),("noChangeAspect","1")] () let nvPicPr = mknode "pic:nvPicPr" [] @@ -814,10 +1047,20 @@ inlineToOpenXML opts (Image alt (src, tit)) = do br :: Element br = mknode "w:r" [] [mknode "w:br" [("w:type","textWrapping")] () ] -parseXml :: Archive -> String -> IO Element -parseXml refArchive relpath = - case findEntryByPath relpath refArchive of - Just e -> case parseXMLDoc $ UTF8.toStringLazy $ fromEntry e of - Just d -> return d - Nothing -> fail $ relpath ++ " corrupt in reference docx" - Nothing -> fail $ relpath ++ " missing in reference docx" +parseXml :: Archive -> Archive -> String -> IO Element +parseXml refArchive distArchive relpath = + case ((findEntryByPath relpath refArchive `mplus` + findEntryByPath relpath distArchive) + >>= parseXMLDoc . UTF8.toStringLazy . fromEntry) of + Just d -> return d + Nothing -> fail $ relpath ++ " corrupt or missing in reference docx" + +-- | Scales the image to fit the page +-- sizes are passed in emu +fitToPage :: (Integer, Integer) -> Integer -> (Integer, Integer) +fitToPage (x, y) pageWidth + -- Fixes width to the page width and scales the height + | x > pageWidth = + (pageWidth, round $ + ((fromIntegral pageWidth) / ((fromIntegral :: Integer -> Double) x)) * (fromIntegral y)) + | otherwise = (x, y) diff --git a/src/Text/Pandoc/Writers/DokuWiki.hs b/src/Text/Pandoc/Writers/DokuWiki.hs new file mode 100644 index 000000000..eed45a965 --- /dev/null +++ b/src/Text/Pandoc/Writers/DokuWiki.hs @@ -0,0 +1,491 @@ +{- +Copyright (C) 2008-2014 John MacFarlane <jgm@berkeley.edu> + +This program is free software; you can redistribute it and/or modify +it under the terms of the GNU General Public License as published by +the Free Software Foundation; either version 2 of the License, or +(at your option) any later version. + +This program is distributed in the hope that it will be useful, +but WITHOUT ANY WARRANTY; without even the implied warranty of +MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the +GNU General Public License for more details. + +You should have received a copy of the GNU General Public License +along with this program; if not, write to the Free Software +Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA +-} + +{- | + Module : Text.Pandoc.Writers.DokuWiki + Copyright : Copyright (C) 2008-2014 John MacFarlane + License : GNU GPL, version 2 or above + + Maintainer : Clare Macrae <clare.macrae@googlemail.com> + Stability : alpha + Portability : portable + +Conversion of 'Pandoc' documents to DokuWiki markup. + +DokuWiki: <https://www.dokuwiki.org/dokuwiki> +-} + +{- + [ ] Implement nested blockquotes (currently only ever does one level) + [x] Implement alignment of text in tables + [ ] Implement comments + [ ] Work through the Dokuwiki spec, and check I've not missed anything out + [ ] Remove dud/duplicate code +-} + +module Text.Pandoc.Writers.DokuWiki ( writeDokuWiki ) where +import Text.Pandoc.Definition +import Text.Pandoc.Options ( WriterOptions( + writerTableOfContents + , writerStandalone + , writerTemplate) ) +import Text.Pandoc.Shared ( escapeURI, removeFormatting, camelCaseToHyphenated + , trimr, normalize, substitute ) +import Text.Pandoc.Writers.Shared ( defField, metaToJSON ) +import Text.Pandoc.Templates ( renderTemplate' ) +import Data.List ( intersect, intercalate, isPrefixOf, transpose ) +import Data.Default (Default(..)) +import Network.URI ( isURI ) +import Control.Monad ( zipWithM ) +import Control.Monad.State ( modify, State, get, evalState ) +import Control.Monad.Reader ( ReaderT, runReaderT, ask, local ) +import Control.Applicative ( (<$>) ) + +data WriterState = WriterState { + stNotes :: Bool -- True if there are notes + } + +data WriterEnvironment = WriterEnvironment { + stIndent :: String -- Indent after the marker at the beginning of list items + , stUseTags :: Bool -- True if we should use HTML tags because we're in a complex list + , stBackSlashLB :: Bool -- True if we should produce formatted strings with newlines (as in a table cell) + } + +instance Default WriterState where + def = WriterState { stNotes = False } + +instance Default WriterEnvironment where + def = WriterEnvironment { stIndent = "" + , stUseTags = False + , stBackSlashLB = False } + +type DokuWiki = ReaderT WriterEnvironment (State WriterState) + +-- | Convert Pandoc to DokuWiki. +writeDokuWiki :: WriterOptions -> Pandoc -> String +writeDokuWiki opts document = + runDokuWiki (pandocToDokuWiki opts $ normalize document) + +runDokuWiki :: DokuWiki a -> a +runDokuWiki = flip evalState def . flip runReaderT def + +-- | Return DokuWiki representation of document. +pandocToDokuWiki :: WriterOptions -> Pandoc -> DokuWiki String +pandocToDokuWiki opts (Pandoc meta blocks) = do + metadata <- metaToJSON opts + (fmap trimr . blockListToDokuWiki opts) + (inlineListToDokuWiki opts) + meta + body <- blockListToDokuWiki opts blocks + notesExist <- stNotes <$> get + let notes = if notesExist + then "" -- TODO Was "\n<references />" Check whether I can really remove this: + -- if it is definitely to do with footnotes, can remove this whole bit + else "" + let main = body ++ notes + let context = defField "body" main + $ defField "toc" (writerTableOfContents opts) + $ metadata + if writerStandalone opts + then return $ renderTemplate' (writerTemplate opts) context + else return main + +-- | Escape special characters for DokuWiki. +escapeString :: String -> String +escapeString = substitute "__" "%%__%%" . + substitute "**" "%%**%%" . + substitute "//" "%%//%%" + +-- | Convert Pandoc block element to DokuWiki. +blockToDokuWiki :: WriterOptions -- ^ Options + -> Block -- ^ Block element + -> DokuWiki String + +blockToDokuWiki _ Null = return "" + +blockToDokuWiki opts (Div _attrs bs) = do + contents <- blockListToDokuWiki opts bs + return $ contents ++ "\n" + +blockToDokuWiki opts (Plain inlines) = + inlineListToDokuWiki opts inlines + +-- title beginning with fig: indicates that the image is a figure +-- dokuwiki doesn't support captions - so combine together alt and caption into alt +blockToDokuWiki opts (Para [Image txt (src,'f':'i':'g':':':tit)]) = do + capt <- if null txt + then return "" + else (" " ++) `fmap` inlineListToDokuWiki opts txt + let opt = if null txt + then "" + else "|" ++ if null tit then capt else tit ++ capt + -- Relative links fail isURI and receive a colon + prefix = if isURI src then "" else ":" + return $ "{{" ++ prefix ++ src ++ opt ++ "}}\n" + +blockToDokuWiki opts (Para inlines) = do + indent <- stIndent <$> ask + useTags <- stUseTags <$> ask + contents <- inlineListToDokuWiki opts inlines + return $ if useTags + then "<HTML><p></HTML>" ++ contents ++ "<HTML></p></HTML>" + else contents ++ if null indent then "\n" else "" + +blockToDokuWiki _ (RawBlock f str) + | f == Format "dokuwiki" = return str + -- See https://www.dokuwiki.org/wiki:syntax + -- use uppercase HTML tag for block-level content: + | f == Format "html" = return $ "<HTML>\n" ++ str ++ "\n</HTML>" + | otherwise = return "" + +blockToDokuWiki _ HorizontalRule = return "\n----\n" + +blockToDokuWiki opts (Header level _ inlines) = do + -- emphasis, links etc. not allowed in headers, apparently, + -- so we remove formatting: + contents <- inlineListToDokuWiki opts $ removeFormatting inlines + let eqs = replicate ( 7 - level ) '=' + return $ eqs ++ " " ++ contents ++ " " ++ eqs ++ "\n" + +blockToDokuWiki _ (CodeBlock (_,classes,_) str) = do + let at = classes `intersect` ["actionscript", "ada", "apache", "applescript", "asm", "asp", + "autoit", "bash", "blitzbasic", "bnf", "c", "c_mac", "caddcl", "cadlisp", "cfdg", "cfm", + "cpp", "cpp-qt", "csharp", "css", "d", "delphi", "diff", "div", "dos", "eiffel", "fortran", + "freebasic", "gml", "groovy", "html4strict", "idl", "ini", "inno", "io", "java", "java5", + "javascript", "latex", "lisp", "lua", "matlab", "mirc", "mpasm", "mysql", "nsis", "objc", + "ocaml", "ocaml-brief", "oobas", "oracle8", "pascal", "perl", "php", "php-brief", "plsql", + "python", "qbasic", "rails", "reg", "robots", "ruby", "sas", "scheme", "sdlbasic", + "smalltalk", "smarty", "sql", "tcl", "", "thinbasic", "tsql", "vb", "vbnet", "vhdl", + "visualfoxpro", "winbatch", "xml", "xpp", "z80"] + let (beg, end) = if null at + then ("<code" ++ if null classes then ">" else " class=\"" ++ unwords classes ++ "\">", "</code>") + else ("<source lang=\"" ++ head at ++ "\">", "</source>") + return $ beg ++ str ++ end + +blockToDokuWiki opts (BlockQuote blocks) = do + contents <- blockListToDokuWiki opts blocks + if isSimpleBlockQuote blocks + then return $ unlines $ map ("> " ++) $ lines contents + else return $ "<HTML><blockquote>\n" ++ contents ++ "</blockquote></HTML>" + +blockToDokuWiki opts (Table capt aligns _ headers rows) = do + captionDoc <- if null capt + then return "" + else do + c <- inlineListToDokuWiki opts capt + return $ "" ++ c ++ "\n" + headers' <- if all null headers + then return [] + else zipWithM (tableItemToDokuWiki opts) aligns headers + rows' <- mapM (zipWithM (tableItemToDokuWiki opts) aligns) rows + let widths = map (maximum . map length) $ transpose (headers':rows') + let padTo (width, al) s = + case (width - length s) of + x | x > 0 -> + if al == AlignLeft || al == AlignDefault + then s ++ replicate x ' ' + else if al == AlignRight + then replicate x ' ' ++ s + else replicate (x `div` 2) ' ' ++ + s ++ replicate (x - x `div` 2) ' ' + | otherwise -> s + let renderRow sep cells = sep ++ + intercalate sep (zipWith padTo (zip widths aligns) cells) ++ sep + return $ captionDoc ++ + (if null headers' then "" else renderRow "^" headers' ++ "\n") ++ + unlines (map (renderRow "|") rows') + +blockToDokuWiki opts x@(BulletList items) = do + oldUseTags <- stUseTags <$> ask + indent <- stIndent <$> ask + backSlash <- stBackSlashLB <$> ask + let useTags = oldUseTags || not (isSimpleList x) + if useTags + then do + contents <- local (\s -> s { stUseTags = True }) + (mapM (listItemToDokuWiki opts) items) + return $ "<HTML><ul></HTML>\n" ++ vcat contents ++ "<HTML></ul></HTML>\n" + else do + contents <- local (\s -> s { stIndent = stIndent s ++ " " + , stBackSlashLB = backSlash}) + (mapM (listItemToDokuWiki opts) items) + return $ vcat contents ++ if null indent then "\n" else "" + +blockToDokuWiki opts x@(OrderedList attribs items) = do + oldUseTags <- stUseTags <$> ask + indent <- stIndent <$> ask + backSlash <- stBackSlashLB <$> ask + let useTags = oldUseTags || not (isSimpleList x) + if useTags + then do + contents <- local (\s -> s { stUseTags = True }) + (mapM (orderedListItemToDokuWiki opts) items) + return $ "<HTML><ol" ++ listAttribsToString attribs ++ "></HTML>\n" ++ vcat contents ++ "<HTML></ol></HTML>\n" + else do + contents <- local (\s -> s { stIndent = stIndent s ++ " " + , stBackSlashLB = backSlash}) + (mapM (orderedListItemToDokuWiki opts) items) + return $ vcat contents ++ if null indent then "\n" else "" + +-- TODO Need to decide how to make definition lists work on dokuwiki - I don't think there +-- is a specific representation of them. +-- TODO This creates double '; ; ' if there is a bullet or ordered list inside a definition list +blockToDokuWiki opts x@(DefinitionList items) = do + oldUseTags <- stUseTags <$> ask + indent <- stIndent <$> ask + backSlash <- stBackSlashLB <$> ask + let useTags = oldUseTags || not (isSimpleList x) + if useTags + then do + contents <- local (\s -> s { stUseTags = True }) + (mapM (definitionListItemToDokuWiki opts) items) + return $ "<HTML><dl></HTML>\n" ++ vcat contents ++ "<HTML></dl></HTML>\n" + else do + contents <- local (\s -> s { stIndent = stIndent s ++ " " + , stBackSlashLB = backSlash}) + (mapM (definitionListItemToDokuWiki opts) items) + return $ vcat contents ++ if null indent then "\n" else "" + +-- Auxiliary functions for lists: + +-- | Convert ordered list attributes to HTML attribute string +listAttribsToString :: ListAttributes -> String +listAttribsToString (startnum, numstyle, _) = + let numstyle' = camelCaseToHyphenated $ show numstyle + in (if startnum /= 1 + then " start=\"" ++ show startnum ++ "\"" + else "") ++ + (if numstyle /= DefaultStyle + then " style=\"list-style-type: " ++ numstyle' ++ ";\"" + else "") + +-- | Convert bullet list item (list of blocks) to DokuWiki. +listItemToDokuWiki :: WriterOptions -> [Block] -> DokuWiki String +listItemToDokuWiki opts items = do + contents <- blockListToDokuWiki opts items + useTags <- stUseTags <$> ask + if useTags + then return $ "<HTML><li></HTML>" ++ contents ++ "<HTML></li></HTML>" + else do + indent <- stIndent <$> ask + backSlash <- stBackSlashLB <$> ask + let indent' = if backSlash then (drop 2 indent) else indent + return $ indent' ++ "* " ++ contents + +-- | Convert ordered list item (list of blocks) to DokuWiki. +-- | TODO Emiminate dreadful duplication of text from listItemToDokuWiki +orderedListItemToDokuWiki :: WriterOptions -> [Block] -> DokuWiki String +orderedListItemToDokuWiki opts items = do + contents <- blockListToDokuWiki opts items + useTags <- stUseTags <$> ask + if useTags + then return $ "<HTML><li></HTML>" ++ contents ++ "<HTML></li></HTML>" + else do + indent <- stIndent <$> ask + backSlash <- stBackSlashLB <$> ask + let indent' = if backSlash then (drop 2 indent) else indent + return $ indent' ++ "- " ++ contents + +-- | Convert definition list item (label, list of blocks) to DokuWiki. +definitionListItemToDokuWiki :: WriterOptions + -> ([Inline],[[Block]]) + -> DokuWiki String +definitionListItemToDokuWiki opts (label, items) = do + labelText <- inlineListToDokuWiki opts label + contents <- mapM (blockListToDokuWiki opts) items + useTags <- stUseTags <$> ask + if useTags + then return $ "<HTML><dt></HTML>" ++ labelText ++ "<HTML></dt></HTML>\n" ++ + (intercalate "\n" $ map (\d -> "<HTML><dd></HTML>" ++ d ++ "<HTML></dd></HTML>") contents) + else do + indent <- stIndent <$> ask + backSlash <- stBackSlashLB <$> ask + let indent' = if backSlash then (drop 2 indent) else indent + return $ indent' ++ "* **" ++ labelText ++ "** " ++ concat contents + +-- | True if the list can be handled by simple wiki markup, False if HTML tags will be needed. +isSimpleList :: Block -> Bool +isSimpleList x = + case x of + BulletList items -> all isSimpleListItem items + OrderedList (num, sty, _) items -> all isSimpleListItem items && + num == 1 && sty `elem` [DefaultStyle, Decimal] + DefinitionList items -> all isSimpleListItem $ concatMap snd items + _ -> False + +-- | True if list item can be handled with the simple wiki syntax. False if +-- HTML tags will be needed. +isSimpleListItem :: [Block] -> Bool +isSimpleListItem [] = True +isSimpleListItem [x] = + case x of + Plain _ -> True + Para _ -> True + BulletList _ -> isSimpleList x + OrderedList _ _ -> isSimpleList x + DefinitionList _ -> isSimpleList x + _ -> False +isSimpleListItem [x, y] | isPlainOrPara x = + case y of + BulletList _ -> isSimpleList y + OrderedList _ _ -> isSimpleList y + DefinitionList _ -> isSimpleList y + _ -> False +isSimpleListItem _ = False + +isPlainOrPara :: Block -> Bool +isPlainOrPara (Plain _) = True +isPlainOrPara (Para _) = True +isPlainOrPara _ = False + +isSimpleBlockQuote :: [Block] -> Bool +isSimpleBlockQuote bs = all isPlainOrPara bs + +-- | Concatenates strings with line breaks between them. +vcat :: [String] -> String +vcat = intercalate "\n" + +backSlashLineBreaks :: String -> String +backSlashLineBreaks cs = reverse $ g $ reverse $ concatMap f cs + where f '\n' = "\\\\ " + f c = [c] + g (' ' : '\\':'\\': xs) = xs + g s = s + +-- Auxiliary functions for tables: + +tableItemToDokuWiki :: WriterOptions + -> Alignment + -> [Block] + -> DokuWiki String +tableItemToDokuWiki opts align' item = do + let mkcell x = (if align' == AlignRight || align' == AlignCenter + then " " + else "") ++ x ++ + (if align' == AlignLeft || align' == AlignCenter + then " " + else "") + contents <- local (\s -> s { stBackSlashLB = True }) $ + blockListToDokuWiki opts item + return $ mkcell contents + +-- | Convert list of Pandoc block elements to DokuWiki. +blockListToDokuWiki :: WriterOptions -- ^ Options + -> [Block] -- ^ List of block elements + -> DokuWiki String +blockListToDokuWiki opts blocks = do + backSlash <- stBackSlashLB <$> ask + if backSlash + then (backSlashLineBreaks . vcat) <$> mapM (blockToDokuWiki opts) blocks + else vcat <$> mapM (blockToDokuWiki opts) blocks + +-- | Convert list of Pandoc inline elements to DokuWiki. +inlineListToDokuWiki :: WriterOptions -> [Inline] -> DokuWiki String +inlineListToDokuWiki opts lst = + concat <$> (mapM (inlineToDokuWiki opts) lst) + +-- | Convert Pandoc inline element to DokuWiki. +inlineToDokuWiki :: WriterOptions -> Inline -> DokuWiki String + +inlineToDokuWiki opts (Span _attrs ils) = + inlineListToDokuWiki opts ils + +inlineToDokuWiki opts (Emph lst) = do + contents <- inlineListToDokuWiki opts lst + return $ "//" ++ contents ++ "//" + +inlineToDokuWiki opts (Strong lst) = do + contents <- inlineListToDokuWiki opts lst + return $ "**" ++ contents ++ "**" + +inlineToDokuWiki opts (Strikeout lst) = do + contents <- inlineListToDokuWiki opts lst + return $ "<del>" ++ contents ++ "</del>" + +inlineToDokuWiki opts (Superscript lst) = do + contents <- inlineListToDokuWiki opts lst + return $ "<sup>" ++ contents ++ "</sup>" + +inlineToDokuWiki opts (Subscript lst) = do + contents <- inlineListToDokuWiki opts lst + return $ "<sub>" ++ contents ++ "</sub>" + +inlineToDokuWiki opts (SmallCaps lst) = inlineListToDokuWiki opts lst + +inlineToDokuWiki opts (Quoted SingleQuote lst) = do + contents <- inlineListToDokuWiki opts lst + return $ "\8216" ++ contents ++ "\8217" + +inlineToDokuWiki opts (Quoted DoubleQuote lst) = do + contents <- inlineListToDokuWiki opts lst + return $ "\8220" ++ contents ++ "\8221" + +inlineToDokuWiki opts (Cite _ lst) = inlineListToDokuWiki opts lst + +inlineToDokuWiki _ (Code _ str) = + -- In dokuwiki, text surrounded by '' is really just a font statement, i.e. <tt>, + -- and so other formatting can be present inside. + -- However, in pandoc, and markdown, inlined code doesn't contain formatting. + -- So I have opted for using %% to disable all formatting inside inline code blocks. + -- This gives the best results when converting from other formats to dokuwiki, even if + -- the resultand code is a little ugly, for short strings that don't contain formatting + -- characters. + -- It does mean that if pandoc could ever read dokuwiki, and so round-trip the format, + -- any formatting inside inlined code blocks would be lost, or presented incorrectly. + return $ "''%%" ++ str ++ "%%''" + +inlineToDokuWiki _ (Str str) = return $ escapeString str + +inlineToDokuWiki _ (Math _ str) = return $ "<math>" ++ str ++ "</math>" + -- note: str should NOT be escaped + +inlineToDokuWiki _ (RawInline f str) + | f == Format "dokuwiki" = return str + | f == Format "html" = return $ "<html>" ++ str ++ "</html>" + | otherwise = return "" + +inlineToDokuWiki _ (LineBreak) = return "\\\\ " + +inlineToDokuWiki _ Space = return " " + +inlineToDokuWiki opts (Link txt (src, _)) = do + label <- inlineListToDokuWiki opts txt + case txt of + [Str s] | "mailto:" `isPrefixOf` src -> return $ "<" ++ s ++ ">" + | escapeURI s == src -> return src + _ -> if isURI src + then return $ "[[" ++ src ++ "|" ++ label ++ "]]" + else return $ "[[" ++ src' ++ "|" ++ label ++ "]]" + where src' = case src of + '/':xs -> xs -- with leading / it's a + _ -> src -- link to a help page +inlineToDokuWiki opts (Image alt (source, tit)) = do + alt' <- inlineListToDokuWiki opts alt + let txt = case (tit, alt) of + ("", []) -> "" + ("", _ ) -> "|" ++ alt' + (_ , _ ) -> "|" ++ tit + -- Relative links fail isURI and receive a colon + prefix = if isURI source then "" else ":" + return $ "{{" ++ prefix ++ source ++ txt ++ "}}" + +inlineToDokuWiki opts (Note contents) = do + contents' <- blockListToDokuWiki opts contents + modify (\s -> s { stNotes = True }) + return $ "((" ++ contents' ++ "))" + -- note - may not work for notes with multiple blocks diff --git a/src/Text/Pandoc/Writers/EPUB.hs b/src/Text/Pandoc/Writers/EPUB.hs index a48300939..2291c7184 100644 --- a/src/Text/Pandoc/Writers/EPUB.hs +++ b/src/Text/Pandoc/Writers/EPUB.hs @@ -1,6 +1,6 @@ -{-# LANGUAGE PatternGuards, CPP, ScopedTypeVariables #-} +{-# LANGUAGE PatternGuards, CPP, ScopedTypeVariables, ViewPatterns #-} {- -Copyright (C) 2010 John MacFarlane <jgm@berkeley.edu> +Copyright (C) 2010-2014 John MacFarlane <jgm@berkeley.edu> This program is free software; you can redistribute it and/or modify it under the terms of the GNU General Public License as published by @@ -19,7 +19,7 @@ Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA {- | Module : Text.Pandoc.Writers.EPUB - Copyright : Copyright (C) 2010 John MacFarlane + Copyright : Copyright (C) 2010-2014 John MacFarlane License : GNU GPL, version 2 or above Maintainer : John MacFarlane <jgm@berkeley.edu> @@ -29,42 +29,45 @@ Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA Conversion of 'Pandoc' documents to EPUB. -} module Text.Pandoc.Writers.EPUB ( writeEPUB ) where -import Data.IORef +import Data.IORef ( IORef, newIORef, readIORef, modifyIORef ) import qualified Data.Map as M import Data.Maybe ( fromMaybe ) -import Data.List ( isInfixOf, intercalate ) +import Data.List ( isPrefixOf, isInfixOf, intercalate ) import System.Environment ( getEnv ) import Text.Printf (printf) -import System.FilePath ( (</>), takeBaseName, takeExtension, takeFileName ) +import System.FilePath ( takeExtension, takeFileName ) import qualified Data.ByteString.Lazy as B import qualified Data.ByteString.Lazy.Char8 as B8 import qualified Text.Pandoc.UTF8 as UTF8 import Text.Pandoc.SelfContained ( makeSelfContained ) -import Codec.Archive.Zip +import Codec.Archive.Zip ( emptyArchive, addEntryToArchive, eRelativePath, fromEntry , Entry, toEntry, fromArchive) import Control.Applicative ((<$>)) -import Data.Time.Clock.POSIX -import Data.Time -import System.Locale -import Text.Pandoc.Shared hiding ( Element ) -import qualified Text.Pandoc.Shared as Shared +import Data.Time.Clock.POSIX ( getPOSIXTime ) +import Data.Time (getCurrentTime,UTCTime, formatTime) +import System.Locale ( defaultTimeLocale ) +import Text.Pandoc.Shared ( trimr, renderTags', safeRead, uniqueIdent, trim + , normalizeDate, readDataFile, stringify, warn + , hierarchicalize, fetchItem' ) +import qualified Text.Pandoc.Shared as S (Element(..)) import Text.Pandoc.Builder (fromList, setMeta) -import Text.Pandoc.Options +import Text.Pandoc.Options ( WriterOptions(..) + , HTMLMathMethod(..) + , EPUBVersion(..) + , ObfuscationMethod(NoObfuscation) ) import Text.Pandoc.Definition -import Text.Pandoc.Walk -import Control.Monad.State -import Text.XML.Light hiding (ppTopElement) -import Text.Pandoc.UUID -import Text.Pandoc.Writers.HTML -import Text.Pandoc.Writers.Markdown ( writePlain ) -import Data.Char ( toLower, isDigit ) -import Network.URI ( unEscapeString ) -import Text.Pandoc.MIME (getMimeType) -#if MIN_VERSION_base(4,6,0) -#else -import Prelude hiding (catch) -#endif -import Control.Exception (catch, SomeException) +import Text.Pandoc.Walk (walk, walkM) +import Control.Monad.State (modify, get, execState, State, put, evalState) +import Control.Monad (foldM, when, mplus, liftM) +import Text.XML.Light ( unode, Element(..), unqual, Attr(..), add_attrs + , strContent, lookupAttr, Node(..), QName(..), parseXML + , onlyElems, node, ppElement) +import Text.Pandoc.UUID (getRandomUUID) +import Text.Pandoc.Writers.HTML (writeHtmlString, writeHtml) +import Data.Char ( toLower, isDigit, isAlphaNum ) +import Text.Pandoc.MIME (MimeType, getMimeType) +import qualified Control.Exception as E import Text.Blaze.Html.Renderer.Utf8 (renderHtml) +import Text.HTML.TagSoup (Tag(TagOpen), fromAttrib, parseTags) -- A Chapter includes a list of blocks and maybe a section -- number offset. Note, some chapters are unnumbered. The section @@ -75,7 +78,7 @@ data Chapter = Chapter (Maybe [Int]) [Block] data EPUBMetadata = EPUBMetadata{ epubIdentifier :: [Identifier] , epubTitle :: [Title] - , epubDate :: String + , epubDate :: [Date] , epubLanguage :: String , epubCreator :: [Creator] , epubContributor :: [Creator] @@ -90,12 +93,18 @@ data EPUBMetadata = EPUBMetadata{ , epubRights :: Maybe String , epubCoverImage :: Maybe String , epubStylesheet :: Maybe Stylesheet + , epubPageDirection :: Maybe ProgressionDirection } deriving Show data Stylesheet = StylesheetPath FilePath | StylesheetContents String deriving Show +data Date = Date{ + dateText :: String + , dateEvent :: Maybe String + } deriving Show + data Creator = Creator{ creatorText :: String , creatorRole :: Maybe String @@ -113,6 +122,8 @@ data Title = Title{ , titleType :: Maybe String } deriving Show +data ProgressionDirection = LTR | RTL deriving Show + dcName :: String -> QName dcName n = QName n Nothing (Just "dc") @@ -122,10 +133,10 @@ dcNode = node . dcName opfName :: String -> QName opfName n = QName n Nothing (Just "opf") -plainify :: [Inline] -> String -plainify t = - trimr $ writePlain def{ writerStandalone = False } - $ Pandoc nullMeta [Plain $ walk removeNote t] +toId :: FilePath -> String +toId = map (\x -> if isAlphaNum x || x == '-' || x == '_' + then x + else '_') . takeFileName removeNote :: Inline -> Inline removeNote (Note _) = Str "" @@ -147,23 +158,25 @@ getEPUBMetadata opts meta = do then case lookup "lang" (writerVariables opts) of Just x -> return m{ epubLanguage = x } Nothing -> do - localeLang <- catch (liftM + localeLang <- E.catch (liftM (map (\c -> if c == '_' then '-' else c) . takeWhile (/='.')) $ getEnv "LANG") - (\e -> let _ = (e :: SomeException) in return "en-US") + (\e -> let _ = (e :: E.SomeException) in return "en-US") return m{ epubLanguage = localeLang } else return m let fixDate m = if null (epubDate m) then do currentTime <- getCurrentTime - return $ m{ epubDate = showDateTimeISO8601 currentTime } + return $ m{ epubDate = [ Date{ + dateText = showDateTimeISO8601 currentTime + , dateEvent = Nothing } ] } else return m let addAuthor m = if any (\c -> creatorRole c == Just "aut") $ epubCreator m then return m else do - let authors' = map plainify $ docAuthors meta + let authors' = map stringify $ docAuthors meta let toAuthor name = Creator{ creatorText = name , creatorRole = Just "aut" , creatorFileAs = Nothing } @@ -181,8 +194,10 @@ addMetadataFromXML e@(Element (QName name _ (Just "dc")) attrs _ _) md , titleFileAs = getAttr "file-as" , titleType = getAttr "type" } : epubTitle md } - | name == "date" = md{ epubDate = fromMaybe "" $ normalizeDate' - $ strContent e } + | name == "date" = md{ epubDate = + Date{ dateText = fromMaybe "" $ normalizeDate' $ strContent e + , dateEvent = getAttr "event" + } : epubDate md } | name == "language" = md{ epubLanguage = strContent e } | name == "creator" = md{ epubCreator = Creator{ creatorText = strContent e @@ -210,8 +225,8 @@ addMetadataFromXML _ md = md metaValueToString :: MetaValue -> String metaValueToString (MetaString s) = s -metaValueToString (MetaInlines ils) = plainify ils -metaValueToString (MetaBlocks bs) = plainify $ query (:[]) bs +metaValueToString (MetaInlines ils) = stringify ils +metaValueToString (MetaBlocks bs) = stringify bs metaValueToString (MetaBool b) = show b metaValueToString _ = "" @@ -247,6 +262,16 @@ getCreator s meta = getList s meta handleMetaValue , creatorRole = metaValueToString <$> M.lookup "role" m } handleMetaValue mv = Creator (metaValueToString mv) Nothing Nothing +getDate :: String -> Meta -> [Date] +getDate s meta = getList s meta handleMetaValue + where handleMetaValue (MetaMap m) = + Date{ dateText = maybe "" id $ + M.lookup "text" m >>= normalizeDate' . metaValueToString + , dateEvent = metaValueToString <$> M.lookup "event" m } + handleMetaValue mv = Date { dateText = maybe "" + id $ normalizeDate' $ metaValueToString mv + , dateEvent = Nothing } + simpleList :: String -> Meta -> [String] simpleList s meta = case lookupMeta s meta of @@ -273,11 +298,11 @@ metadataFromMeta opts meta = EPUBMetadata{ , epubRights = rights , epubCoverImage = coverImage , epubStylesheet = stylesheet + , epubPageDirection = pageDirection } where identifiers = getIdentifier meta titles = getTitle meta - date = fromMaybe "" $ - (metaValueToString <$> lookupMeta "date" meta) >>= normalizeDate' + date = getDate "date" meta language = maybe "" metaValueToString $ lookupMeta "language" meta `mplus` lookupMeta "lang" meta creators = getCreator "creator" meta @@ -296,6 +321,11 @@ metadataFromMeta opts meta = EPUBMetadata{ stylesheet = (StylesheetContents <$> writerEpubStylesheet opts) `mplus` ((StylesheetPath . metaValueToString) <$> lookupMeta "stylesheet" meta) + pageDirection = case map toLower . metaValueToString <$> + lookupMeta "page-progression-direction" meta of + Just "ltr" -> Just LTR + Just "rtl" -> Just RTL + _ -> Nothing -- | Produce an EPUB file from a Pandoc document. writeEPUB :: WriterOptions -- ^ Writer options @@ -319,7 +349,7 @@ writeEPUB opts doc@(Pandoc meta _) = do if epub3 then MathML Nothing else writerHTMLMathMethod opts - , writerWrapText = False } + , writerWrapText = True } metadata <- getEPUBMetadata opts' meta -- cover page @@ -327,9 +357,10 @@ writeEPUB opts doc@(Pandoc meta _) = do case epubCoverImage metadata of Nothing -> return ([],[]) Just img -> do - let coverImage = "cover-image" ++ takeExtension img - let cpContent = renderHtml $ writeHtml opts' - (Pandoc meta [RawBlock (Format "html") $ "<div id=\"cover-image\">\n<img src=\"" ++ coverImage ++ "\" alt=\"cover image\" />\n</div>"]) + let coverImage = "media/" ++ takeFileName img + let cpContent = renderHtml $ writeHtml + opts'{ writerVariables = ("coverpage","true"):vars } + (Pandoc meta [RawBlock (Format "html") $ "<div id=\"cover-image\">\n<img src=\"" ++ coverImage ++ "\" alt=\"cover image\" />\n</div>"]) imgContent <- B.readFile img return ( [mkEntry "cover.xhtml" cpContent] , [mkEntry coverImage imgContent] ) @@ -341,15 +372,16 @@ writeEPUB opts doc@(Pandoc meta _) = do let tpEntry = mkEntry "title_page.xhtml" tpContent -- handle pictures - picsRef <- newIORef [] - Pandoc _ blocks <- walkM - (transformInline opts' picsRef) doc - pics <- readIORef picsRef + mediaRef <- newIORef [] + Pandoc _ blocks <- walkM (transformInline opts' mediaRef) doc >>= + walkM (transformBlock opts' mediaRef) + pics <- readIORef mediaRef let readPicEntry entries (oldsrc, newsrc) = do - res <- fetchItem (writerSourceURL opts') oldsrc + res <- fetchItem' (writerMediaBag opts') + (writerSourceURL opts') oldsrc case res of Left _ -> do - warn $ "Could not find image `" ++ oldsrc ++ "', skipping..." + warn $ "Could not find media `" ++ oldsrc ++ "', skipping..." return entries Right (img,_) -> return $ (toEntry newsrc epochtime $ B.fromChunks . (:[]) $ img) : entries @@ -359,6 +391,14 @@ writeEPUB opts doc@(Pandoc meta _) = do let mkFontEntry f = mkEntry (takeFileName f) `fmap` B.readFile f fontEntries <- mapM mkFontEntry $ writerEpubFonts opts' + -- set page progression direction attribution + let progressionDirection = case epubPageDirection metadata of + Just LTR | epub3 -> + [("page-progression-direction", "ltr")] + Just RTL | epub3 -> + [("page-progression-direction", "rtl")] + _ -> [] + -- body pages -- add level 1 header to beginning if none there @@ -366,7 +406,7 @@ writeEPUB opts doc@(Pandoc meta _) = do $ case blocks of (Header 1 _ _ : _) -> blocks _ -> Header 1 ("",["unnumbered"],[]) - (docTitle meta) : blocks + (docTitle' meta) : blocks let chapterHeaderLevel = writerEpubChapterLevel opts -- internal reference IDs change when we chunk the file, @@ -426,7 +466,7 @@ writeEPUB opts doc@(Pandoc meta _) = do -- contents.opf let chapterNode ent = unode "item" ! - ([("id", takeBaseName $ eRelativePath ent), + ([("id", toId $ eRelativePath ent), ("href", eRelativePath ent), ("media-type", "application/xhtml+xml")] ++ case props ent of @@ -434,21 +474,21 @@ writeEPUB opts doc@(Pandoc meta _) = do xs -> [("properties", unwords xs)]) $ () let chapterRefNode ent = unode "itemref" ! - [("idref", takeBaseName $ eRelativePath ent)] $ () + [("idref", toId $ eRelativePath ent)] $ () let pictureNode ent = unode "item" ! - [("id", takeBaseName $ eRelativePath ent), + [("id", toId $ eRelativePath ent), ("href", eRelativePath ent), ("media-type", fromMaybe "application/octet-stream" - $ imageTypeOf $ eRelativePath ent)] $ () + $ mediaTypeOf $ eRelativePath ent)] $ () let fontNode ent = unode "item" ! - [("id", takeBaseName $ eRelativePath ent), + [("id", toId $ eRelativePath ent), ("href", eRelativePath ent), ("media-type", fromMaybe "" $ getMimeType $ eRelativePath ent)] $ () - let plainTitle = case docTitle meta of + let plainTitle = case docTitle' meta of [] -> case epubTitle metadata of [] -> "UNTITLED" (x:_) -> titleText x - x -> plainify x + x -> stringify x let uuid = case epubIdentifier metadata of (x:_) -> identifierText x -- use first identifier as UUID [] -> error "epubIdentifier is null" -- shouldn't happen @@ -478,19 +518,18 @@ writeEPUB opts doc@(Pandoc meta _) = do (pictureNode x)]) ++ map pictureNode picEntries ++ map fontNode fontEntries - , unode "spine" ! [("toc","ncx")] $ + , unode "spine" ! ([("toc","ncx")] ++ progressionDirection) $ case epubCoverImage metadata of Nothing -> [] Just _ -> [ unode "itemref" ! - [("idref", "cover"),("linear","no")] $ () ] - ++ ((unode "itemref" ! [("idref", "title_page") - ,("linear", if null (docTitle meta) - then "no" - else "yes")] $ ()) : - (unode "itemref" ! [("idref", "nav") - ,("linear", if writerTableOfContents opts - then "yes" - else "no")] $ ()) : + [("idref", "cover_xhtml"),("linear","no")] $ () ] + ++ ((unode "itemref" ! [("idref", "title_page_xhtml") + ,("linear", + case lookupMeta "title" meta of + Just _ -> "yes" + Nothing -> "no")] $ ()) : + [unode "itemref" ! [("idref", "nav")] $ () + | writerTableOfContents opts ] ++ map chapterRefNode chapterEntries) , unode "guide" $ [ unode "reference" ! @@ -509,25 +548,25 @@ writeEPUB opts doc@(Pandoc meta _) = do let tocLevel = writerTOCDepth opts let navPointNode :: (Int -> String -> String -> [Element] -> Element) - -> Shared.Element -> State Int Element - navPointNode formatter (Sec _ nums (ident,_,_) ils children) = do + -> S.Element -> State Int Element + navPointNode formatter (S.Sec _ nums (ident,_,_) ils children) = do n <- get modify (+1) let showNums :: [Int] -> String showNums = intercalate "." . map show - let tit' = plainify ils + let tit' = stringify ils let tit = if writerNumberSections opts && not (null nums) then showNums nums ++ " " ++ tit' else tit' let src = case lookup ident reftable of Just x -> x Nothing -> error (ident ++ " not found in reftable") - let isSec (Sec lev _ _ _ _) = lev <= tocLevel + let isSec (S.Sec lev _ _ _ _) = lev <= tocLevel isSec _ = False let subsecs = filter isSec children subs <- mapM (navPointNode formatter) subsecs return $ formatter n tit src subs - navPointNode _ (Blk _) = error "navPointNode encountered Blk" + navPointNode _ (S.Blk _) = error "navPointNode encountered Blk" let navMapFormatter :: Int -> String -> String -> [Element] -> Element navMapFormatter n tit src subs = unode "navPoint" ! @@ -538,7 +577,7 @@ writeEPUB opts doc@(Pandoc meta _) = do ] ++ subs let tpNode = unode "navPoint" ! [("id", "navPoint-0")] $ - [ unode "navLabel" $ unode "text" (plainify $ docTitle meta) + [ unode "navLabel" $ unode "text" (stringify $ docTitle' meta) , unode "content" ! [("src","title_page.xhtml")] $ () ] let tocData = UTF8.fromStringLazy $ ppTopElement $ @@ -555,8 +594,8 @@ writeEPUB opts doc@(Pandoc meta _) = do ,("content", "0")] $ () ] ++ case epubCoverImage metadata of Nothing -> [] - Just _ -> [unode "meta" ! [("name","cover"), - ("content","cover-image")] $ ()] + Just img -> [unode "meta" ! [("name","cover"), + ("content", toId img)] $ ()] , unode "docTitle" $ unode "text" $ plainTitle , unode "navMap" $ tpNode : evalState (mapM (navPointNode navMapFormatter) secs) 1 @@ -567,23 +606,20 @@ writeEPUB opts doc@(Pandoc meta _) = do navXhtmlFormatter n tit src subs = unode "li" ! [("id", "toc-li-" ++ show n)] $ (unode "a" ! [("href",src)] - $ (unode "span" tit)) + $ tit) : case subs of [] -> [] (_:_) -> [unode "ol" ! [("class","toc")] $ subs] let navtag = if epub3 then "nav" else "div" - let navData = UTF8.fromStringLazy $ ppTopElement $ - unode "html" ! [("xmlns","http://www.w3.org/1999/xhtml") - ,("xmlns:epub","http://www.idpf.org/2007/ops")] $ - [ unode "head" $ - [ unode "title" plainTitle - , unode "link" ! [("rel","stylesheet"),("type","text/css"),("href","stylesheet.css")] $ () ] - , unode "body" $ - unode navtag ! [("epub:type","toc") | epub3] $ - [ unode "h1" ! [("id","toc-title")] $ plainTitle - , unode "ol" ! [("class","toc")] $ evalState (mapM (navPointNode navXhtmlFormatter) secs) 1] - ] + let navBlocks = [RawBlock (Format "html") $ ppElement $ + unode navtag ! [("epub:type","toc") | epub3] $ + [ unode "h1" ! [("id","toc-title")] $ plainTitle + , unode "ol" ! [("class","toc")] $ evalState (mapM (navPointNode navXhtmlFormatter) secs) 1]] + let navData = renderHtml $ writeHtml opts' + (Pandoc (setMeta "title" + (walk removeNote $ fromList $ docTitle' meta) nullMeta) + navBlocks) let navEntry = mkEntry "nav.xhtml" navData -- mimetype @@ -635,7 +671,14 @@ metadataElement version md currentTime = identifierNodes = withIds "epub-id" toIdentifierNode $ epubIdentifier md titleNodes = withIds "epub-title" toTitleNode $ epubTitle md - dateNodes = dcTag' "date" $ epubDate md + dateNodes = if version == EPUB2 + then withIds "epub-date" toDateNode $ epubDate md + else -- epub3 allows only one dc:date + -- http://www.idpf.org/epub/30/spec/epub30-publications.html#sec-opf-dcdate + case epubDate md of + [] -> [] + (x:_) -> [dcNode "date" ! [("id","epub-date")] + $ dateText x] languageNodes = [dcTag "language" $ epubLanguage md] creatorNodes = withIds "epub-creator" (toCreatorNode "creator") $ epubCreator md @@ -651,8 +694,8 @@ metadataElement version md currentTime = coverageNodes = maybe [] (dcTag' "coverage") $ epubCoverage md rightsNodes = maybe [] (dcTag' "rights") $ epubRights md coverImageNodes = maybe [] - (const $ [unode "meta" ! [("name","cover"), - ("content","cover-image")] $ ()]) + (\img -> [unode "meta" ! [("name","cover"), + ("content",toId img)] $ ()]) $ epubCoverImage md modifiedNodes = [ unode "meta" ! [("property", "dcterms:modified")] $ (showDateTimeISO8601 currentTime) | version == EPUB3 ] @@ -669,7 +712,7 @@ metadataElement version md currentTime = (schemeToOnix `fmap` scheme) toCreatorNode s id' creator | version == EPUB2 = [dcNode s ! - ([("id",id')] ++ + (("id",id') : maybe [] (\x -> [("opf:file-as",x)]) (creatorFileAs creator) ++ maybe [] (\x -> [("opf:role",x)]) (creatorRole creator >>= toRelator)) $ creatorText creator] @@ -683,9 +726,9 @@ metadataElement version md currentTime = (creatorRole creator >>= toRelator) toTitleNode id' title | version == EPUB2 = [dcNode "title" ! - ([("id",id')] ++ - maybe [] (\x -> [("opf:file-as",x)]) (titleFileAs title) ++ - maybe [] (\x -> [("opf:title-type",x)]) (titleType title)) $ + (("id",id') : + -- note: EPUB2 doesn't accept opf:title-type + maybe [] (\x -> [("opf:file-as",x)]) (titleFileAs title)) $ titleText title] | otherwise = [dcNode "title" ! [("id",id')] $ titleText title] ++ @@ -695,6 +738,10 @@ metadataElement version md currentTime = maybe [] (\x -> [unode "meta" ! [("refines",'#':id'),("property","title-type")] $ x]) (titleType title) + toDateNode id' date = [dcNode "date" ! + (("id",id') : + maybe [] (\x -> [("opf:event",x)]) (dateEvent date)) $ + dateText date] schemeToOnix "ISBN-10" = "02" schemeToOnix "GTIN-13" = "03" schemeToOnix "UPC" = "04" @@ -715,26 +762,60 @@ metadataElement version md currentTime = showDateTimeISO8601 :: UTCTime -> String showDateTimeISO8601 = formatTime defaultTimeLocale "%FT%TZ" +transformTag :: IORef [(FilePath, FilePath)] -- ^ (oldpath, newpath) media + -> Tag String + -> IO (Tag String) +transformTag mediaRef tag@(TagOpen name attr) + | name `elem` ["video", "source", "img", "audio"] = do + let src = fromAttrib "src" tag + let poster = fromAttrib "poster" tag + newsrc <- modifyMediaRef mediaRef src + newposter <- modifyMediaRef mediaRef poster + let attr' = filter (\(x,_) -> x /= "src" && x /= "poster") attr ++ + [("src", newsrc) | not (null newsrc)] ++ + [("poster", newposter) | not (null newposter)] + return $ TagOpen name attr' +transformTag _ tag = return tag + +modifyMediaRef :: IORef [(FilePath, FilePath)] -> FilePath -> IO FilePath +modifyMediaRef _ "" = return "" +modifyMediaRef mediaRef oldsrc = do + media <- readIORef mediaRef + case lookup oldsrc media of + Just n -> return n + Nothing -> do + let new = "media/file" ++ show (length media) ++ + takeExtension (takeWhile (/='?') oldsrc) -- remove query + modifyIORef mediaRef ( (oldsrc, new): ) + return new + +transformBlock :: WriterOptions + -> IORef [(FilePath, FilePath)] -- ^ (oldpath, newpath) media + -> Block + -> IO Block +transformBlock _ mediaRef (RawBlock fmt raw) + | fmt == Format "html" = do + let tags = parseTags raw + tags' <- mapM (transformTag mediaRef) tags + return $ RawBlock fmt (renderTags' tags') +transformBlock _ _ b = return b + transformInline :: WriterOptions - -> IORef [(FilePath, FilePath)] -- ^ (oldpath, newpath) images + -> IORef [(FilePath, FilePath)] -- ^ (oldpath, newpath) media -> Inline -> IO Inline -transformInline opts picsRef (Image lab (src,tit)) = do - let src' = unEscapeString src - pics <- readIORef picsRef - let oldsrc = maybe src' (</> src) $ writerSourceURL opts - let ext = takeExtension src' - newsrc <- case lookup oldsrc pics of - Just n -> return n - Nothing -> do - let new = "images/img" ++ show (length pics) ++ ext - modifyIORef picsRef ( (oldsrc, new): ) - return new +transformInline _ mediaRef (Image lab (src,tit)) = do + newsrc <- modifyMediaRef mediaRef src return $ Image lab (newsrc, tit) transformInline opts _ (x@(Math _ _)) | WebTeX _ <- writerHTMLMathMethod opts = do - raw <- makeSelfContained Nothing $ writeHtmlInline opts x + raw <- makeSelfContained opts $ writeHtmlInline opts x return $ RawInline (Format "html") raw +transformInline _ mediaRef (RawInline fmt raw) + | fmt == Format "html" = do + let tags = parseTags raw + tags' <- mapM (transformTag mediaRef) tags + return $ RawInline fmt (renderTags' tags') transformInline _ _ x = return x writeHtmlInline :: WriterOptions -> Inline -> String @@ -759,10 +840,12 @@ ppTopElement = ("<?xml version=\"1.0\" encoding=\"UTF-8\"?>\n" ++) . unEntity . Nothing -> '&':'#':unEntity xs unEntity (x:xs) = x : unEntity xs -imageTypeOf :: FilePath -> Maybe String -imageTypeOf x = case getMimeType x of - Just y@('i':'m':'a':'g':'e':_) -> Just y - _ -> Nothing +mediaTypeOf :: FilePath -> Maybe MimeType +mediaTypeOf x = + let mediaPrefixes = ["image", "video", "audio"] in + case getMimeType x of + Just y | any (`isPrefixOf` y) mediaPrefixes -> Just y + _ -> Nothing data IdentState = IdentState{ chapterNumber :: Int, @@ -1100,3 +1183,17 @@ relatorMap = ,("writer of added text", "wat") ] +docTitle' :: Meta -> [Inline] +docTitle' meta = fromMaybe [] $ go <$> lookupMeta "title" meta + where go (MetaString s) = [Str s] + go (MetaInlines xs) = xs + go (MetaBlocks [Para xs]) = xs + go (MetaBlocks [Plain xs]) = xs + go (MetaMap m) = + case M.lookup "type" m of + Just x | stringify x == "main" -> + maybe [] go $ M.lookup "text" m + _ -> [] + go (MetaList xs) = concatMap go xs + go _ = [] + diff --git a/src/Text/Pandoc/Writers/FB2.hs b/src/Text/Pandoc/Writers/FB2.hs index 803617f95..233b8b32b 100644 --- a/src/Text/Pandoc/Writers/FB2.hs +++ b/src/Text/Pandoc/Writers/FB2.hs @@ -1,3 +1,5 @@ +{-# LANGUAGE PatternGuards #-} + {- Copyright (c) 2011-2012, Sergey Astanin All rights reserved. @@ -28,8 +30,8 @@ module Text.Pandoc.Writers.FB2 (writeFB2) where import Control.Monad.State (StateT, evalStateT, get, modify) import Control.Monad.State (liftM, liftM2, liftIO) import Data.ByteString.Base64 (encode) -import Data.Char (toUpper, toLower, isSpace, isAscii, isControl) -import Data.List (intersperse, intercalate, isPrefixOf) +import Data.Char (toLower, isSpace, isAscii, isControl) +import Data.List (intersperse, intercalate, isPrefixOf, stripPrefix) import Data.Either (lefts, rights) import Network.Browser (browse, request, setAllowRedirects, setOutHandler) import Network.HTTP (catchIO_, getRequest, getHeaders, getResponseBody) @@ -44,8 +46,7 @@ import qualified Text.XML.Light.Cursor as XC import Text.Pandoc.Definition import Text.Pandoc.Options (WriterOptions(..), HTMLMathMethod(..), def) -import Text.Pandoc.Shared (orderedListMarkers, isHeaderBlock) -import Text.Pandoc.Walk +import Text.Pandoc.Shared (orderedListMarkers, isHeaderBlock, capitalize) -- | Data to be written at the end of the document: -- (foot)notes, URLs, references, images. @@ -253,22 +254,21 @@ readDataURI :: String -- ^ URI -> Maybe (String,String,Bool,String) -- ^ Maybe (mime,charset,isBase64,data) readDataURI uri = - let prefix = "data:" - in if not (prefix `isPrefixOf` uri) - then Nothing - else - let rest = drop (length prefix) uri - meta = takeWhile (/= ',') rest -- without trailing ',' - uridata = drop (length meta + 1) rest - parts = split (== ';') meta - (mime,cs,enc)=foldr upd ("text/plain","US-ASCII",False) parts - in Just (mime,cs,enc,uridata) + case stripPrefix "data:" uri of + Nothing -> Nothing + Just rest -> + let meta = takeWhile (/= ',') rest -- without trailing ',' + uridata = drop (length meta + 1) rest + parts = split (== ';') meta + (mime,cs,enc)=foldr upd ("text/plain","US-ASCII",False) parts + in Just (mime,cs,enc,uridata) + where upd str m@(mime,cs,enc) - | isMimeType str = (str,cs,enc) - | "charset=" `isPrefixOf` str = (mime,drop (length "charset=") str,enc) - | str == "base64" = (mime,cs,True) - | otherwise = m + | isMimeType str = (str,cs,enc) + | Just str' <- stripPrefix "charset=" str = (mime,str',enc) + | str == "base64" = (mime,cs,True) + | otherwise = m -- Without parameters like ;charset=...; see RFC 2045, 5.1 isMimeType :: String -> Bool @@ -296,7 +296,6 @@ fetchURL url = do let content_type = lookupHeader HdrContentType (getHeaders r) content <- liftM (Just . toStr . encode . toBS) . getResponseBody $ Right r return $ liftM2 (,) content_type content - where toBS :: String -> B.ByteString toBS = B.pack . map (toEnum . fromEnum) @@ -421,10 +420,6 @@ indent = indentBlock indentLines ins = let lns = split isLineBreak ins :: [[Inline]] in intercalate [LineBreak] $ map ((Str spacer):) lns -capitalize :: Inline -> Inline -capitalize (Str xs) = Str $ map toUpper xs -capitalize x = x - -- | Convert a Pandoc's Inline element to FictionBook XML representation. toXml :: Inline -> FBM [Content] toXml (Str s) = return [txt s] @@ -434,7 +429,7 @@ toXml (Strong ss) = list `liftM` wrap "strong" ss toXml (Strikeout ss) = list `liftM` wrap "strikethrough" ss toXml (Superscript ss) = list `liftM` wrap "sup" ss toXml (Subscript ss) = list `liftM` wrap "sub" ss -toXml (SmallCaps ss) = cMapM toXml $ walk capitalize ss +toXml (SmallCaps ss) = cMapM toXml $ capitalize ss toXml (Quoted SingleQuote ss) = do -- FIXME: should be language-specific inner <- cMapM toXml ss return $ [txt "‘"] ++ inner ++ [txt "’"] diff --git a/src/Text/Pandoc/Writers/HTML.hs b/src/Text/Pandoc/Writers/HTML.hs index 805bb57f1..e261cfca8 100644 --- a/src/Text/Pandoc/Writers/HTML.hs +++ b/src/Text/Pandoc/Writers/HTML.hs @@ -1,7 +1,7 @@ -{-# LANGUAGE OverloadedStrings, CPP #-} +{-# LANGUAGE OverloadedStrings, CPP, ViewPatterns #-} {-# OPTIONS_GHC -fno-warn-deprecations #-} {- -Copyright (C) 2006-2010 John MacFarlane <jgm@berkeley.edu> +Copyright (C) 2006-2014 John MacFarlane <jgm@berkeley.edu> This program is free software; you can redistribute it and/or modify it under the terms of the GNU General Public License as published by @@ -20,7 +20,7 @@ Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA {- | Module : Text.Pandoc.Writers.HTML - Copyright : Copyright (C) 2006-2010 John MacFarlane + Copyright : Copyright (C) 2006-2014 John MacFarlane License : GNU GPL, version 2 or above Maintainer : John MacFarlane <jgm@berkeley.edu> @@ -40,6 +40,7 @@ import Text.Pandoc.Slides import Text.Pandoc.Highlighting ( highlight, styleToCss, formatHtmlInline, formatHtmlBlock ) import Text.Pandoc.XML (fromEntities, escapeStringForXML) +import Network.URI ( parseURIReference, URI(..), unEscapeString ) import Network.HTTP ( urlEncode ) import Numeric ( showHex ) import Data.Char ( ord, toLower ) @@ -59,9 +60,12 @@ import qualified Text.Blaze.XHtml1.Transitional.Attributes as A import Text.Blaze.Renderer.String (renderHtml) import Text.TeXMath import Text.XML.Light.Output +import Text.XML.Light (unode, elChildren, add_attr, unqual) +import qualified Text.XML.Light as XML import System.FilePath (takeExtension) import Data.Monoid import Data.Aeson (Value) +import Control.Applicative ((<$>)) data WriterState = WriterState { stNotes :: [Html] -- ^ List of notes @@ -69,11 +73,13 @@ data WriterState = WriterState , stQuotes :: Bool -- ^ <q> tag is used , stHighlighting :: Bool -- ^ Syntax highlighting is used , stSecNum :: [Int] -- ^ Number of current section + , stElement :: Bool -- ^ Processing an Element } defaultWriterState :: WriterState defaultWriterState = WriterState {stNotes= [], stMath = False, stQuotes = False, - stHighlighting = False, stSecNum = []} + stHighlighting = False, stSecNum = [], + stElement = False} -- Helpers to render HTML with the appropriate function. @@ -153,6 +159,10 @@ pandocToHtml opts (Pandoc meta blocks) = do H.script ! A.src (toValue url) ! A.type_ "text/javascript" $ mempty + KaTeX js css -> + (H.script ! A.src (toValue js) $ mempty) <> + (H.link ! A.rel "stylesheet" ! A.href (toValue css)) <> + (H.script ! A.type_ "text/javascript" $ toHtml renderKaTeX) _ -> case lookup "mathml-script" (writerVariables opts) of Just s | not (writerHtml5 opts) -> H.script ! A.type_ "text/javascript" @@ -234,6 +244,9 @@ showSecNum = concat . intersperse "." . map show -- | Converts an Element to a list item for a table of contents, -- retrieving the appropriate identifier from state. elementToListItem :: WriterOptions -> Element -> State WriterState (Maybe Html) +-- Don't include the empty headers created in slide shows +-- shows when an hrule is used to separate slides without a new title: +elementToListItem _ (Sec _ _ _ [Str "\0"] _) = return Nothing elementToListItem opts (Sec lev num (id',classes,_) headerText subsecs) | lev <= writerTOCDepth opts = do let num' = zipWith (+) num (writerNumberOffset opts ++ repeat 0) @@ -269,7 +282,13 @@ elementToHtml slideLevel opts (Sec level num (id',classes,keyvals) title' elemen let titleSlide = slide && level < slideLevel header' <- if title' == [Str "\0"] -- marker for hrule then return mempty - else blockToHtml opts (Header level' (id',classes,keyvals) title') + else do + modify (\st -> st{ stElement = True}) + res <- blockToHtml opts + (Header level' (id',classes,keyvals) title') + modify (\st -> st{ stElement = False}) + return res + let isSec (Sec _ _ _ _ _) = True isSec (Blk _) = False let isPause (Blk x) = x == Para [Str ".",Space,Str ".",Space,Str "."] @@ -337,10 +356,10 @@ parseMailto s = do _ -> fail "not a mailto: URL" -- | Obfuscate a "mailto:" link. -obfuscateLink :: WriterOptions -> String -> String -> Html +obfuscateLink :: WriterOptions -> Html -> String -> Html obfuscateLink opts txt s | writerEmailObfuscation opts == NoObfuscation = - H.a ! A.href (toValue s) $ toHtml txt -obfuscateLink opts txt s = + H.a ! A.href (toValue s) $ txt +obfuscateLink opts (renderHtml -> txt) s = let meth = writerEmailObfuscation opts s' = map toLower (take 7 s) ++ drop 7 s in case parseMailto s' of @@ -356,13 +375,13 @@ obfuscateLink opts txt s = ReferenceObfuscation -> -- need to use preEscapedString or &'s are escaped to & in URL preEscapedString $ "<a href=\"" ++ (obfuscateString s') - ++ "\">" ++ (obfuscateString txt) ++ "</a>" + ++ "\" class=\"email\">" ++ (obfuscateString txt) ++ "</a>" JavascriptObfuscation -> (H.script ! A.type_ "text/javascript" $ preEscapedString ("\n<!--\nh='" ++ obfuscateString domain ++ "';a='" ++ at' ++ "';n='" ++ obfuscateString name' ++ "';e=n+a+h;\n" ++ - "document.write('<a h'+'ref'+'=\"ma'+'ilto'+':'+e+'\">'+" ++ + "document.write('<a h'+'ref'+'=\"ma'+'ilto'+':'+e+'\" clas'+'s=\"em' + 'ail\">'+" ++ linkText ++ "+'<\\/'+'a'+'>');\n// -->\n")) >> H.noscript (preEscapedString $ obfuscateString altText) _ -> error $ "Unknown obfuscation method: " ++ show meth @@ -396,7 +415,10 @@ imageExts = [ "art", "bmp", "cdr", "cdt", "cpt", "cr2", "crw", "djvu", "erf", treatAsImage :: FilePath -> Bool treatAsImage fp = - let ext = map toLower $ drop 1 $ takeExtension fp + let path = case uriPath `fmap` parseURIReference fp of + Nothing -> fp + Just up -> up + ext = map toLower $ drop 1 $ takeExtension path in null ext || ext `elem` imageExts -- | Convert Pandoc block element to HTML. @@ -425,9 +447,11 @@ blockToHtml opts (Div attr@(_,classes,_) bs) = do let contents' = nl opts >> contents >> nl opts return $ if "notes" `elem` classes - then case writerSlideVariant opts of - RevealJsSlides -> addAttrs opts attr $ H5.aside $ contents' - NoSlides -> addAttrs opts attr $ H.div $ contents' + then let opts' = opts{ writerIncremental = False } in + -- we don't want incremental output inside speaker notes + case writerSlideVariant opts of + RevealJsSlides -> addAttrs opts' attr $ H5.aside $ contents' + NoSlides -> addAttrs opts' attr $ H.div $ contents' _ -> mempty else addAttrs opts attr $ H.div $ contents' blockToHtml _ (RawBlock f str) @@ -475,14 +499,17 @@ blockToHtml opts (BlockQuote blocks) = else do contents <- blockListToHtml opts blocks return $ H.blockquote $ nl opts >> contents >> nl opts -blockToHtml opts (Header level (_,_,_) lst) = do +blockToHtml opts (Header level attr@(_,classes,_) lst) = do contents <- inlineListToHtml opts lst secnum <- liftM stSecNum get let contents' = if writerNumberSections opts && not (null secnum) + && "unnumbered" `notElem` classes then (H.span ! A.class_ "header-section-number" $ toHtml $ showSecNum secnum) >> strToHtml " " >> contents else contents - return $ case level of + inElement <- gets stElement + return $ (if inElement then id else addAttrs opts attr) + $ case level of 1 -> H.h1 contents' 2 -> H.h2 contents' 3 -> H.h3 contents' @@ -532,11 +559,16 @@ blockToHtml opts (Table capt aligns widths headers rows') = do let percent w = show (truncate (100*w) :: Integer) ++ "%" let coltags = if all (== 0.0) widths then mempty - else mconcat $ map (\w -> - if writerHtml5 opts - then H.col ! A.style (toValue $ "width: " ++ percent w) - else H.col ! A.width (toValue $ percent w) >> nl opts) - widths + else do + H.colgroup $ do + nl opts + mapM_ (\w -> do + if writerHtml5 opts + then H.col ! A.style (toValue $ "width: " ++ + percent w) + else H.col ! A.width (toValue $ percent w) + nl opts) widths + nl opts head' <- if all null headers then return mempty else do @@ -599,6 +631,18 @@ inlineListToHtml :: WriterOptions -> [Inline] -> State WriterState Html inlineListToHtml opts lst = mapM (inlineToHtml opts) lst >>= return . mconcat +-- | Annotates a MathML expression with the tex source +annotateMML :: XML.Element -> String -> XML.Element +annotateMML e tex = math (unode "semantics" [cs, unode "annotation" (annotAttrs, tex)]) + where + cs = case elChildren e of + [] -> unode "mrow" () + [x] -> x + xs -> unode "mrow" xs + math = add_attr (XML.Attr (unqual "xmlns") "http://www.w3.org/1998/Math/MathML") . unode "math" + annotAttrs = [XML.Attr (unqual "encoding") "application/x-tex"] + + -- | Convert Pandoc inline element to HTML. inlineToHtml :: WriterOptions -> Inline -> State WriterState Html inlineToHtml opts inline = @@ -688,18 +732,22 @@ inlineToHtml opts inline = else DisplayBlock let conf = useShortEmptyTags (const False) defaultConfigPP - case texMathToMathML dt str of - Right r -> return $ preEscapedString $ - ppcElement conf r - Left _ -> inlineListToHtml opts - (readTeXMath' t str) >>= return . - (H.span ! A.class_ "math") + case writeMathML dt <$> readTeX str of + Right r -> return $ preEscapedString $ + ppcElement conf (annotateMML r str) + Left _ -> inlineListToHtml opts + (texMathToInlines t str) >>= + return . (H.span ! A.class_ "math") MathJax _ -> return $ H.span ! A.class_ "math" $ toHtml $ case t of InlineMath -> "\\(" ++ str ++ "\\)" DisplayMath -> "\\[" ++ str ++ "\\]" + KaTeX _ _ -> return $ H.span ! A.class_ "math" $ + toHtml (case t of + InlineMath -> str + DisplayMath -> "\\displaystyle " ++ str) PlainMath -> do - x <- inlineListToHtml opts (readTeXMath' t str) + x <- inlineListToHtml opts (texMathToInlines t str) let m = H.span ! A.class_ "math" $ x let brtag = if writerHtml5 opts then H5.br else H.br return $ case t of @@ -713,13 +761,9 @@ inlineToHtml opts inline = _ -> return mempty | f == Format "html" -> return $ preEscapedString str | otherwise -> return mempty - (Link [Str str] (s,_)) | "mailto:" `isPrefixOf` s && - s == escapeURI ("mailto" ++ str) -> - -- autolink - return $ obfuscateLink opts str s (Link txt (s,_)) | "mailto:" `isPrefixOf` s -> do linkText <- inlineListToHtml opts txt - return $ obfuscateLink opts (renderHtml linkText) s + return $ obfuscateLink opts linkText s (Link txt (s,tit)) -> do linkText <- inlineListToHtml opts txt let s' = case s of @@ -727,9 +771,12 @@ inlineToHtml opts inline = RevealJsSlides -> '#':'/':xs _ -> s let link = H.a ! A.href (toValue s') $ linkText + let link' = if txt == [Str (unEscapeString s)] + then link ! A.class_ "uri" + else link return $ if null tit - then link - else link ! A.title (toValue tit) + then link' + else link' ! A.title (toValue tit) (Image txt (s,tit)) | treatAsImage s -> do let alternate' = stringify txt let attributes = [A.src $ toValue s] ++ @@ -800,3 +847,14 @@ blockListToNote opts ref blocks = Just EPUB3 -> noteItem ! customAttribute "epub:type" "footnote" _ -> noteItem return $ nl opts >> noteItem' + +-- Javascript snippet to render all KaTeX elements +renderKaTeX :: String +renderKaTeX = unlines [ + "window.onload = function(){var mathElements = document.getElementsByClassName(\"math\");" + , "for (var i=0; i < mathElements.length; i++)" + , "{" + , " var texText = mathElements[i].firstChild" + , " katex.render(texText.data, mathElements[i])" + , "}}" + ] diff --git a/src/Text/Pandoc/Writers/Haddock.hs b/src/Text/Pandoc/Writers/Haddock.hs new file mode 100644 index 000000000..14f398da9 --- /dev/null +++ b/src/Text/Pandoc/Writers/Haddock.hs @@ -0,0 +1,346 @@ +{-# LANGUAGE OverloadedStrings, TupleSections, ScopedTypeVariables #-} +{- +Copyright (C) 2014 John MacFarlane <jgm@berkeley.edu> + +This program is free software; you can redistribute it and/or modify +it under the terms of the GNU General Public License as published by +the Free Software Foundation; either version 2 of the License, or +(at your option) any later version. + +This program is distributed in the hope that it will be useful, +but WITHOUT ANY WARRANTY; without even the implied warranty of +MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the +GNU General Public License for more details. + +You should have received a copy of the GNU General Public License +along with this program; if not, write to the Free Software +Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA +-} + +{- | + Module : Text.Pandoc.Writers.Haddock + Copyright : Copyright (C) 2014 John MacFarlane + License : GNU GPL, version 2 or above + + Maintainer : John MacFarlane <jgm@berkeley.edu> + Stability : alpha + Portability : portable + +Conversion of 'Pandoc' documents to haddock markup. + +Haddock: <http://www.haskell.org/haddock/doc/html/> +-} +module Text.Pandoc.Writers.Haddock (writeHaddock) where +import Text.Pandoc.Definition +import Text.Pandoc.Templates (renderTemplate') +import Text.Pandoc.Shared +import Text.Pandoc.Writers.Shared +import Text.Pandoc.Options +import Data.List ( intersperse, transpose ) +import Text.Pandoc.Pretty +import Control.Monad.State +import Text.Pandoc.Readers.TeXMath (texMathToInlines) +import Network.URI (isURI) +import Data.Default + +type Notes = [[Block]] +data WriterState = WriterState { stNotes :: Notes } +instance Default WriterState + where def = WriterState{ stNotes = [] } + +-- | Convert Pandoc to Haddock. +writeHaddock :: WriterOptions -> Pandoc -> String +writeHaddock opts document = + evalState (pandocToHaddock opts{ + writerWrapText = writerWrapText opts } document) def + +-- | Return haddock representation of document. +pandocToHaddock :: WriterOptions -> Pandoc -> State WriterState String +pandocToHaddock opts (Pandoc meta blocks) = do + let colwidth = if writerWrapText opts + then Just $ writerColumns opts + else Nothing + body <- blockListToHaddock opts blocks + st <- get + notes' <- notesToHaddock opts (reverse $ stNotes st) + let render' :: Doc -> String + render' = render colwidth + let main = render' $ body <> + (if isEmpty notes' then empty else blankline <> notes') + metadata <- metaToJSON opts + (fmap (render colwidth) . blockListToHaddock opts) + (fmap (render colwidth) . inlineListToHaddock opts) + meta + let context = defField "body" main + $ metadata + if writerStandalone opts + then return $ renderTemplate' (writerTemplate opts) context + else return main + +-- | Return haddock representation of notes. +notesToHaddock :: WriterOptions -> [[Block]] -> State WriterState Doc +notesToHaddock opts notes = + if null notes + then return empty + else do + contents <- blockToHaddock opts $ OrderedList (1,DefaultStyle,DefaultDelim) notes + return $ text "#notes#" <> blankline <> contents + +-- | Escape special characters for Haddock. +escapeString :: String -> String +escapeString = escapeStringUsing haddockEscapes + where haddockEscapes = backslashEscapes "\\/'`\"@<" + +-- | Convert Pandoc block element to haddock. +blockToHaddock :: WriterOptions -- ^ Options + -> Block -- ^ Block element + -> State WriterState Doc +blockToHaddock _ Null = return empty +blockToHaddock opts (Div _ ils) = do + contents <- blockListToHaddock opts ils + return $ contents <> blankline +blockToHaddock opts (Plain inlines) = do + contents <- inlineListToHaddock opts inlines + return $ contents <> cr +-- title beginning with fig: indicates figure +blockToHaddock opts (Para [Image alt (src,'f':'i':'g':':':tit)]) = + blockToHaddock opts (Para [Image alt (src,tit)]) +blockToHaddock opts (Para inlines) = + -- TODO: if it contains linebreaks, we need to use a @...@ block + (<> blankline) `fmap` blockToHaddock opts (Plain inlines) +blockToHaddock _ (RawBlock f str) + | f == "haddock" = do + return $ text str <> text "\n" + | otherwise = return empty +blockToHaddock opts HorizontalRule = + return $ blankline <> text (replicate (writerColumns opts) '_') <> blankline +blockToHaddock opts (Header level (ident,_,_) inlines) = do + contents <- inlineListToHaddock opts inlines + let attr' = if null ident + then empty + else cr <> text "#" <> text ident <> text "#" + return $ nowrap (text (replicate level '=') <> space <> contents) + <> attr' <> blankline +blockToHaddock _ (CodeBlock (_,_,_) str) = + return $ prefixed "> " (text str) <> blankline +-- Nothing in haddock corresponds to block quotes: +blockToHaddock opts (BlockQuote blocks) = + blockListToHaddock opts blocks +-- Haddock doesn't have tables. Use haddock tables in code. +blockToHaddock opts (Table caption aligns widths headers rows) = do + caption' <- inlineListToHaddock opts caption + let caption'' = if null caption + then empty + else blankline <> caption' <> blankline + rawHeaders <- mapM (blockListToHaddock opts) headers + rawRows <- mapM (mapM (blockListToHaddock opts)) rows + let isSimple = all (==0) widths + let isPlainBlock (Plain _) = True + isPlainBlock _ = False + let hasBlocks = not (all isPlainBlock $ concat . concat $ headers:rows) + (nst,tbl) <- case True of + _ | isSimple -> fmap (nest 2,) $ + pandocTable opts (all null headers) aligns widths + rawHeaders rawRows + | not hasBlocks -> fmap (nest 2,) $ + pandocTable opts (all null headers) aligns widths + rawHeaders rawRows + | otherwise -> fmap (id,) $ + gridTable opts (all null headers) aligns widths + rawHeaders rawRows + return $ (prefixed "> " $ nst $ tbl $$ blankline $$ caption'') $$ blankline +blockToHaddock opts (BulletList items) = do + contents <- mapM (bulletListItemToHaddock opts) items + return $ cat contents <> blankline +blockToHaddock opts (OrderedList (start,_,delim) items) = do + let attribs = (start, Decimal, delim) + let markers = orderedListMarkers attribs + let markers' = map (\m -> if length m < 3 + then m ++ replicate (3 - length m) ' ' + else m) markers + contents <- mapM (\(item, num) -> orderedListItemToHaddock opts item num) $ + zip markers' items + return $ cat contents <> blankline +blockToHaddock opts (DefinitionList items) = do + contents <- mapM (definitionListItemToHaddock opts) items + return $ cat contents <> blankline + +pandocTable :: WriterOptions -> Bool -> [Alignment] -> [Double] + -> [Doc] -> [[Doc]] -> State WriterState Doc +pandocTable opts headless aligns widths rawHeaders rawRows = do + let isSimple = all (==0) widths + let alignHeader alignment = case alignment of + AlignLeft -> lblock + AlignCenter -> cblock + AlignRight -> rblock + AlignDefault -> lblock + let numChars = maximum . map offset + let widthsInChars = if isSimple + then map ((+2) . numChars) + $ transpose (rawHeaders : rawRows) + else map + (floor . (fromIntegral (writerColumns opts) *)) + widths + let makeRow = hcat . intersperse (lblock 1 (text " ")) . + (zipWith3 alignHeader aligns widthsInChars) + let rows' = map makeRow rawRows + let head' = makeRow rawHeaders + let maxRowHeight = maximum $ map height (head':rows') + let underline = cat $ intersperse (text " ") $ + map (\width -> text (replicate width '-')) widthsInChars + let border = if maxRowHeight > 1 + then text (replicate (sum widthsInChars + + length widthsInChars - 1) '-') + else if headless + then underline + else empty + let head'' = if headless + then empty + else border <> cr <> head' + let body = if maxRowHeight > 1 + then vsep rows' + else vcat rows' + let bottom = if headless + then underline + else border + return $ head'' $$ underline $$ body $$ bottom + +gridTable :: WriterOptions -> Bool -> [Alignment] -> [Double] + -> [Doc] -> [[Doc]] -> State WriterState Doc +gridTable opts headless _aligns widths headers' rawRows = do + let numcols = length headers' + let widths' = if all (==0) widths + then replicate numcols (1.0 / fromIntegral numcols) + else widths + let widthsInChars = map (floor . (fromIntegral (writerColumns opts) *)) widths' + let hpipeBlocks blocks = hcat [beg, middle, end] + where h = maximum (map height blocks) + sep' = lblock 3 $ vcat (map text $ replicate h " | ") + beg = lblock 2 $ vcat (map text $ replicate h "| ") + end = lblock 2 $ vcat (map text $ replicate h " |") + middle = chomp $ hcat $ intersperse sep' blocks + let makeRow = hpipeBlocks . zipWith lblock widthsInChars + let head' = makeRow headers' + let rows' = map (makeRow . map chomp) rawRows + let border ch = char '+' <> char ch <> + (hcat $ intersperse (char ch <> char '+' <> char ch) $ + map (\l -> text $ replicate l ch) widthsInChars) <> + char ch <> char '+' + let body = vcat $ intersperse (border '-') rows' + let head'' = if headless + then empty + else head' $$ border '=' + return $ border '-' $$ head'' $$ body $$ border '-' + +-- | Convert bullet list item (list of blocks) to haddock +bulletListItemToHaddock :: WriterOptions -> [Block] -> State WriterState Doc +bulletListItemToHaddock opts items = do + contents <- blockListToHaddock opts items + let sps = replicate (writerTabStop opts - 2) ' ' + let start = text ('-' : ' ' : sps) + -- remove trailing blank line if it is a tight list + let contents' = case reverse items of + (BulletList xs:_) | isTightList xs -> + chomp contents <> cr + (OrderedList _ xs:_) | isTightList xs -> + chomp contents <> cr + _ -> contents + return $ hang (writerTabStop opts) start $ contents' <> cr + +-- | Convert ordered list item (a list of blocks) to haddock +orderedListItemToHaddock :: WriterOptions -- ^ options + -> String -- ^ list item marker + -> [Block] -- ^ list item (list of blocks) + -> State WriterState Doc +orderedListItemToHaddock opts marker items = do + contents <- blockListToHaddock opts items + let sps = case length marker - writerTabStop opts of + n | n > 0 -> text $ replicate n ' ' + _ -> text " " + let start = text marker <> sps + return $ hang (writerTabStop opts) start $ contents <> cr + +-- | Convert definition list item (label, list of blocks) to haddock +definitionListItemToHaddock :: WriterOptions + -> ([Inline],[[Block]]) + -> State WriterState Doc +definitionListItemToHaddock opts (label, defs) = do + labelText <- inlineListToHaddock opts label + defs' <- mapM (mapM (blockToHaddock opts)) defs + let contents = vcat $ map (\d -> hang 4 empty $ vcat d <> cr) defs' + return $ nowrap (brackets labelText) <> cr <> contents <> cr + +-- | Convert list of Pandoc block elements to haddock +blockListToHaddock :: WriterOptions -- ^ Options + -> [Block] -- ^ List of block elements + -> State WriterState Doc +blockListToHaddock opts blocks = + mapM (blockToHaddock opts) blocks >>= return . cat + +-- | Convert list of Pandoc inline elements to haddock. +inlineListToHaddock :: WriterOptions -> [Inline] -> State WriterState Doc +inlineListToHaddock opts lst = + mapM (inlineToHaddock opts) lst >>= return . cat + +-- | Convert Pandoc inline element to haddock. +inlineToHaddock :: WriterOptions -> Inline -> State WriterState Doc +inlineToHaddock opts (Span (ident,_,_) ils) = do + contents <- inlineListToHaddock opts ils + if not (null ident) && null ils + then return $ "#" <> text ident <> "#" + else return contents +inlineToHaddock opts (Emph lst) = do + contents <- inlineListToHaddock opts lst + return $ "/" <> contents <> "/" +inlineToHaddock opts (Strong lst) = do + contents <- inlineListToHaddock opts lst + return $ "__" <> contents <> "__" +inlineToHaddock opts (Strikeout lst) = do + contents <- inlineListToHaddock opts lst + -- not supported in haddock, but we fake it: + return $ "~~" <> contents <> "~~" +-- not supported in haddock: +inlineToHaddock opts (Superscript lst) = inlineListToHaddock opts lst +-- not supported in haddock: +inlineToHaddock opts (Subscript lst) = inlineListToHaddock opts lst +-- not supported in haddock: +inlineToHaddock opts (SmallCaps lst) = inlineListToHaddock opts lst +inlineToHaddock opts (Quoted SingleQuote lst) = do + contents <- inlineListToHaddock opts lst + return $ "‘" <> contents <> "’" +inlineToHaddock opts (Quoted DoubleQuote lst) = do + contents <- inlineListToHaddock opts lst + return $ "“" <> contents <> "”" +inlineToHaddock _ (Code _ str) = + return $ "@" <> text (escapeString str) <> "@" +inlineToHaddock _ (Str str) = do + return $ text $ escapeString str +inlineToHaddock opts (Math mt str) = do + let adjust x = case mt of + DisplayMath -> cr <> x <> cr + InlineMath -> x + adjust `fmap` (inlineListToHaddock opts $ texMathToInlines mt str) +inlineToHaddock _ (RawInline f str) + | f == "haddock" = return $ text str + | otherwise = return empty +-- no line break in haddock (see above on CodeBlock) +inlineToHaddock _ (LineBreak) = return cr +inlineToHaddock _ Space = return space +inlineToHaddock opts (Cite _ lst) = inlineListToHaddock opts lst +inlineToHaddock opts (Link txt (src, _)) = do + linktext <- inlineListToHaddock opts txt + let useAuto = isURI src && + case txt of + [Str s] | escapeURI s == src -> True + _ -> False + return $ nowrap $ "<" <> text src <> + (if useAuto then empty else space <> linktext) <> ">" +inlineToHaddock opts (Image alternate (source, tit)) = do + linkhaddock <- inlineToHaddock opts (Link alternate (source, tit)) + return $ "<" <> linkhaddock <> ">" +-- haddock doesn't have notes, but we can fake it: +inlineToHaddock opts (Note contents) = do + modify (\st -> st{ stNotes = contents : stNotes st }) + st <- get + let ref = text $ writerIdentifierPrefix opts ++ show (length $ stNotes st) + return $ "<#notes [" <> ref <> "]>" diff --git a/src/Text/Pandoc/Writers/ICML.hs b/src/Text/Pandoc/Writers/ICML.hs new file mode 100644 index 000000000..181c63df7 --- /dev/null +++ b/src/Text/Pandoc/Writers/ICML.hs @@ -0,0 +1,525 @@ +{-# LANGUAGE OverloadedStrings #-} + +{- | + Module : Text.Pandoc.Writers.ICML + Copyright : Copyright (C) 2013 github.com/mb21 + License : GNU GPL, version 2 or above + + Stability : alpha + +Conversion of 'Pandoc' documents to Adobe InCopy ICML, a stand-alone XML format +which is a subset of the zipped IDML format for which the documentation is +available here: http://wwwimages.adobe.com/www.adobe.com/content/dam/Adobe/en/devnet/indesign/sdk/cs6/idml/idml-specification.pdf +InCopy is the companion word-processor to Adobe InDesign and ICML documents can be integrated +into InDesign with File -> Place. +-} +module Text.Pandoc.Writers.ICML (writeICML) where +import Text.Pandoc.Definition +import Text.Pandoc.XML +import Text.Pandoc.Writers.Shared +import Text.Pandoc.Shared (splitBy) +import Text.Pandoc.Options +import Text.Pandoc.Templates (renderTemplate') +import Text.Pandoc.Pretty +import Data.List (isPrefixOf, isInfixOf, stripPrefix) +import Data.Text as Text (breakOnAll, pack) +import Data.Monoid (mappend) +import Control.Monad.State +import qualified Data.Set as Set + +type Style = [String] +type Hyperlink = [(Int, String)] + +data WriterState = WriterState{ + blockStyles :: Set.Set String + , inlineStyles :: Set.Set String + , links :: Hyperlink + , listDepth :: Int + , maxListDepth :: Int + } + +type WS a = State WriterState a + +defaultWriterState :: WriterState +defaultWriterState = WriterState{ + blockStyles = Set.empty + , inlineStyles = Set.empty + , links = [] + , listDepth = 1 + , maxListDepth = 0 + } + +-- inline names (appear in InDesign's character styles pane) +emphName :: String +strongName :: String +strikeoutName :: String +superscriptName :: String +subscriptName :: String +smallCapsName :: String +codeName :: String +linkName :: String +emphName = "Italic" +strongName = "Bold" +strikeoutName = "Strikeout" +superscriptName = "Superscript" +subscriptName = "Subscript" +smallCapsName = "SmallCaps" +codeName = "Code" +linkName = "Link" + +-- block element names (appear in InDesign's paragraph styles pane) +paragraphName :: String +codeBlockName :: String +rawBlockName :: String +blockQuoteName :: String +orderedListName :: String +bulletListName :: String +defListTermName :: String +defListDefName :: String +headerName :: String +tableName :: String +tableHeaderName :: String +tableCaptionName :: String +alignLeftName :: String +alignRightName :: String +alignCenterName :: String +firstListItemName :: String +beginsWithName :: String +lowerRomanName :: String +upperRomanName :: String +lowerAlphaName :: String +upperAlphaName :: String +subListParName :: String +footnoteName :: String +paragraphName = "Paragraph" +codeBlockName = "CodeBlock" +rawBlockName = "Rawblock" +blockQuoteName = "Blockquote" +orderedListName = "NumList" +bulletListName = "BulList" +defListTermName = "DefListTerm" +defListDefName = "DefListDef" +headerName = "Header" +tableName = "TablePar" +tableHeaderName = "TableHeader" +tableCaptionName = "TableCaption" +alignLeftName = "LeftAlign" +alignRightName = "RightAlign" +alignCenterName = "CenterAlign" +firstListItemName = "first" +beginsWithName = "beginsWith-" +lowerRomanName = "lowerRoman" +upperRomanName = "upperRoman" +lowerAlphaName = "lowerAlpha" +upperAlphaName = "upperAlpha" +subListParName = "subParagraph" +footnoteName = "Footnote" + + +-- | Convert Pandoc document to string in ICML format. +writeICML :: WriterOptions -> Pandoc -> String +writeICML opts (Pandoc meta blocks) = + let colwidth = if writerWrapText opts + then Just $ writerColumns opts + else Nothing + render' = render colwidth + renderMeta f s = Just $ render' $ fst $ runState (f opts [] s) defaultWriterState + Just metadata = metaToJSON opts + (renderMeta blocksToICML) + (renderMeta inlinesToICML) + meta + (doc, st) = runState (blocksToICML opts [] blocks) defaultWriterState + main = render' doc + context = defField "body" main + $ defField "charStyles" (render' $ charStylesToDoc st) + $ defField "parStyles" (render' $ parStylesToDoc st) + $ defField "hyperlinks" (render' $ hyperlinksToDoc $ links st) + $ metadata + in if writerStandalone opts + then renderTemplate' (writerTemplate opts) context + else main + +-- | Auxilary functions for parStylesToDoc and charStylesToDoc. +contains :: String -> (String, (String, String)) -> [(String, String)] +contains s rule = + if isInfixOf (fst rule) s + then [snd rule] + else [] + +-- | The monospaced font to use as default. +monospacedFont :: Doc +monospacedFont = inTags False "AppliedFont" [("type", "string")] $ text "Courier New" + +-- | How much to indent blockquotes etc. +defaultIndent :: Int +defaultIndent = 20 + +-- | How much to indent numbered lists before the number. +defaultListIndent :: Int +defaultListIndent = 10 + +-- other constants +lineSeparator :: String +lineSeparator = "
" + +-- | Convert a WriterState with its block styles to the ICML listing of Paragraph Styles. +parStylesToDoc :: WriterState -> Doc +parStylesToDoc st = vcat $ map makeStyle $ Set.toAscList $ blockStyles st + where + makeStyle s = + let countSubStrs sub str = length $ Text.breakOnAll (Text.pack sub) (Text.pack str) + attrs = concat $ map (contains s) $ [ + (defListTermName, ("BulletsAndNumberingListType", "BulletList")) + , (defListTermName, ("FontStyle", "Bold")) + , (tableHeaderName, ("FontStyle", "Bold")) + , (alignLeftName, ("Justification", "LeftAlign")) + , (alignRightName, ("Justification", "RightAlign")) + , (alignCenterName, ("Justification", "CenterAlign")) + , (headerName++"1", ("PointSize", "36")) + , (headerName++"2", ("PointSize", "30")) + , (headerName++"3", ("PointSize", "24")) + , (headerName++"4", ("PointSize", "18")) + , (headerName++"5", ("PointSize", "14")) + ] + -- what is the most nested list type, if any? + (isBulletList, isOrderedList) = findList $ reverse $ splitBy (==' ') s + where + findList [] = (False, False) + findList (x:xs) | x == bulletListName = (True, False) + | x == orderedListName = (False, True) + | otherwise = findList xs + nBuls = countSubStrs bulletListName s + nOrds = countSubStrs orderedListName s + attrs' = numbering ++ listType ++ indent ++ attrs + where + numbering | isOrderedList = [("NumberingExpression", "^#.^t"), ("NumberingLevel", show nOrds)] + | otherwise = [] + listType | isOrderedList && (not $ isInfixOf subListParName s) + = [("BulletsAndNumberingListType", "NumberedList")] + | isBulletList && (not $ isInfixOf subListParName s) + = [("BulletsAndNumberingListType", "BulletList")] + | otherwise = [] + indent = [("LeftIndent", show indt)] + where + nBlockQuotes = countSubStrs blockQuoteName s + nDefLists = countSubStrs defListDefName s + indt = max 0 $ defaultListIndent*(nBuls + nOrds - 1) + defaultIndent*(nBlockQuotes + nDefLists) + props = inTags True "Properties" [] $ (basedOn $$ tabList $$ numbForm) + where + font = if isInfixOf codeBlockName s + then monospacedFont + else empty + basedOn = inTags False "BasedOn" [("type", "object")] (text "$ID/NormalParagraphStyle") $$ font + tabList = if isBulletList + then inTags True "TabList" [("type","list")] $ inTags True "ListItem" [("type","record")] + $ vcat [ + inTags False "Alignment" [("type","enumeration")] $ text "LeftAlign" + , inTags False "AlignmentCharacter" [("type","string")] $ text "." + , selfClosingTag "Leader" [("type","string")] + , inTags False "Position" [("type","unit")] $ text + $ show $ defaultListIndent * (nBuls + nOrds) + ] + else empty + makeNumb name = inTags False "NumberingFormat" [("type", "string")] (text name) + numbForm | isInfixOf lowerRomanName s = makeNumb "i, ii, iii, iv..." + | isInfixOf upperRomanName s = makeNumb "I, II, III, IV..." + | isInfixOf lowerAlphaName s = makeNumb "a, b, c, d..." + | isInfixOf upperAlphaName s = makeNumb "A, B, C, D..." + | otherwise = empty + in inTags True "ParagraphStyle" ([("Self", "ParagraphStyle/"++s), ("Name", s)] ++ attrs') props + +-- | Convert a WriterState with its inline styles to the ICML listing of Character Styles. +charStylesToDoc :: WriterState -> Doc +charStylesToDoc st = vcat $ map makeStyle $ Set.toAscList $ inlineStyles st + where + makeStyle s = + let attrs = concat $ map (contains s) [ + (strikeoutName, ("StrikeThru", "true")) + , (superscriptName, ("Position", "Superscript")) + , (subscriptName, ("Position", "Subscript")) + , (smallCapsName, ("Capitalization", "SmallCaps")) + ] + attrs' | isInfixOf emphName s && isInfixOf strongName s = ("FontStyle", "Bold Italic") : attrs + | isInfixOf strongName s = ("FontStyle", "Bold") : attrs + | isInfixOf emphName s = ("FontStyle", "Italic") : attrs + | otherwise = attrs + props = inTags True "Properties" [] $ + inTags False "BasedOn" [("type", "object")] (text "$ID/NormalCharacterStyle") $$ font + where + font = + if isInfixOf codeName s + then monospacedFont + else empty + in inTags True "CharacterStyle" ([("Self", "CharacterStyle/"++s), ("Name", s)] ++ attrs') props + +-- | Convert a list of (identifier, url) pairs to the ICML listing of hyperlinks. +hyperlinksToDoc :: Hyperlink -> Doc +hyperlinksToDoc [] = empty +hyperlinksToDoc (x:xs) = hyp x $$ hyperlinksToDoc xs + where + hyp (ident, url) = hdest $$ hlink + where + hdest = selfClosingTag "HyperlinkURLDestination" + [("Self", "HyperlinkURLDestination/"++url), ("Name","link"), ("DestinationURL",url), ("DestinationUniqueKey","1")] + hlink = inTags True "Hyperlink" [("Self","uf-"++show ident), ("Name",url), + ("Source","htss-"++show ident), ("Visible","true"), ("DestinationUniqueKey","1")] + $ inTags True "Properties" [] + $ inTags False "BorderColor" [("type","enumeration")] (text "Black") + $$ (inTags False "Destination" [("type","object")] + $ text $ "HyperlinkURLDestination/"++(escapeStringForXML url)) + + +-- | Convert a list of Pandoc blocks to ICML. +blocksToICML :: WriterOptions -> Style -> [Block] -> WS Doc +blocksToICML opts style lst = vcat `fmap` mapM (blockToICML opts style) lst + +-- | Convert a Pandoc block element to ICML. +blockToICML :: WriterOptions -> Style -> Block -> WS Doc +blockToICML opts style (Plain lst) = parStyle opts style lst +blockToICML opts style (Para lst) = parStyle opts (paragraphName:style) lst +blockToICML opts style (CodeBlock _ str) = parStyle opts (codeBlockName:style) $ [Str str] +blockToICML opts style (RawBlock _ str) = parStyle opts (rawBlockName:style) $ [Str str] +blockToICML opts style (BlockQuote blocks) = blocksToICML opts (blockQuoteName:style) blocks +blockToICML opts style (OrderedList attribs lst) = listItemsToICML opts orderedListName style (Just attribs) lst +blockToICML opts style (BulletList lst) = listItemsToICML opts bulletListName style Nothing lst +blockToICML opts style (DefinitionList lst) = vcat `fmap` mapM (definitionListItemToICML opts style) lst +blockToICML opts style (Header lvl _ lst) = + let stl = (headerName ++ show lvl):style + in parStyle opts stl lst +blockToICML _ _ HorizontalRule = return empty -- we could insert a page break instead +blockToICML opts style (Table caption aligns widths headers rows) = + let style' = tableName : style + noHeader = all null headers + nrHeaders = if noHeader + then "0" + else "1" + nrRows = length rows + nrCols = if null rows + then 0 + else length $ head rows + rowsToICML [] _ = return empty + rowsToICML (col:rest) rowNr = + liftM2 ($$) (colsToICML col rowNr (0::Int)) $ rowsToICML rest (rowNr+1) + colsToICML [] _ _ = return empty + colsToICML (cell:rest) rowNr colNr = do + let stl = if rowNr == 0 && not noHeader + then tableHeaderName:style' + else style' + alig = aligns !! colNr + stl' | alig == AlignLeft = alignLeftName : stl + | alig == AlignRight = alignRightName : stl + | alig == AlignCenter = alignCenterName : stl + | otherwise = stl + c <- blocksToICML opts stl' cell + let cl = return $ inTags True "Cell" + [("Name", show colNr ++":"++ show rowNr), ("AppliedCellStyle","CellStyle/Cell")] c + liftM2 ($$) cl $ colsToICML rest rowNr (colNr+1) + in do + let tabl = if noHeader + then rows + else headers:rows + cells <- rowsToICML tabl (0::Int) + let colWidths w = if w > 0 + then [("SingleColumnWidth",show $ 500 * w)] + else [] + let tupToDoc tup = selfClosingTag "Column" $ [("Name",show $ fst tup)] ++ (colWidths $ snd tup) + let colDescs = vcat $ map tupToDoc $ zip [0..nrCols-1] widths + let tableDoc = return $ inTags True "Table" [ + ("AppliedTableStyle","TableStyle/Table") + , ("HeaderRowCount", nrHeaders) + , ("BodyRowCount", show nrRows) + , ("ColumnCount", show nrCols) + ] (colDescs $$ cells) + liftM2 ($$) tableDoc $ parStyle opts (tableCaptionName:style) caption +blockToICML opts style (Div _ lst) = blocksToICML opts style lst +blockToICML _ _ Null = return empty + +-- | Convert a list of lists of blocks to ICML list items. +listItemsToICML :: WriterOptions -> String -> Style -> Maybe ListAttributes -> [[Block]] -> WS Doc +listItemsToICML _ _ _ _ [] = return empty +listItemsToICML opts listType style attribs (first:rest) = do + st <- get + put st{ listDepth = 1 + listDepth st} + let stl = listType:style + let f = listItemToICML opts stl True attribs first + let r = map (listItemToICML opts stl False attribs) rest + docs <- sequence $ f:r + s <- get + let maxD = max (maxListDepth s) (listDepth s) + put s{ listDepth = 1, maxListDepth = maxD } + return $ vcat docs + +-- | Convert a list of blocks to ICML list items. +listItemToICML :: WriterOptions -> Style -> Bool-> Maybe ListAttributes -> [Block] -> WS Doc +listItemToICML opts style isFirst attribs item = + let makeNumbStart (Just (beginsWith, numbStl, _)) = + let doN DefaultStyle = [] + doN LowerRoman = [lowerRomanName] + doN UpperRoman = [upperRomanName] + doN LowerAlpha = [lowerAlphaName] + doN UpperAlpha = [upperAlphaName] + doN _ = [] + bw = if beginsWith > 1 + then [beginsWithName ++ show beginsWith] + else [] + in doN numbStl ++ bw + makeNumbStart Nothing = [] + stl = if isFirst + then firstListItemName:style + else style + stl' = makeNumbStart attribs ++ stl + in if length item > 1 + then do + let insertTab (Para lst) = blockToICML opts (subListParName:style) $ Para $ (Str "\t"):lst + insertTab block = blockToICML opts style block + f <- blockToICML opts stl' $ head item + r <- fmap vcat $ mapM insertTab $ tail item + return $ f $$ r + else blocksToICML opts stl' item + +definitionListItemToICML :: WriterOptions -> Style -> ([Inline],[[Block]]) -> WS Doc +definitionListItemToICML opts style (term,defs) = do + term' <- parStyle opts (defListTermName:style) term + defs' <- vcat `fmap` mapM (blocksToICML opts (defListDefName:style)) defs + return $ term' $$ defs' + + +-- | Convert a list of inline elements to ICML. +inlinesToICML :: WriterOptions -> Style -> [Inline] -> WS Doc +inlinesToICML opts style lst = vcat `fmap` mapM (inlineToICML opts style) (mergeSpaces lst) + +-- | Convert an inline element to ICML. +inlineToICML :: WriterOptions -> Style -> Inline -> WS Doc +inlineToICML _ style (Str str) = charStyle style $ text $ escapeStringForXML str +inlineToICML opts style (Emph lst) = inlinesToICML opts (emphName:style) lst +inlineToICML opts style (Strong lst) = inlinesToICML opts (strongName:style) lst +inlineToICML opts style (Strikeout lst) = inlinesToICML opts (strikeoutName:style) lst +inlineToICML opts style (Superscript lst) = inlinesToICML opts (superscriptName:style) lst +inlineToICML opts style (Subscript lst) = inlinesToICML opts (subscriptName:style) lst +inlineToICML opts style (SmallCaps lst) = inlinesToICML opts (smallCapsName:style) lst +inlineToICML opts style (Quoted SingleQuote lst) = inlinesToICML opts style $ [Str "‘"] ++ lst ++ [Str "’"] +inlineToICML opts style (Quoted DoubleQuote lst) = inlinesToICML opts style $ [Str "“"] ++ lst ++ [Str "”"] +inlineToICML opts style (Cite _ lst) = inlinesToICML opts style lst +inlineToICML _ style (Code _ str) = charStyle (codeName:style) $ text $ escapeStringForXML str +inlineToICML _ style Space = charStyle style space +inlineToICML _ style LineBreak = charStyle style $ text lineSeparator +inlineToICML _ style (Math _ str) = charStyle style $ text $ escapeStringForXML str --InDesign doesn't really do math +inlineToICML _ style (RawInline _ str) = charStyle style $ text $ escapeStringForXML str +inlineToICML opts style (Link lst (url, title)) = do + content <- inlinesToICML opts (linkName:style) lst + state $ \st -> + let ident = if null $ links st + then 1::Int + else 1 + (fst $ head $ links st) + newst = st{ links = (ident, url):(links st) } + cont = inTags True "HyperlinkTextSource" + [("Self","htss-"++show ident), ("Name",title), ("Hidden","false")] content + in (cont, newst) +inlineToICML opts style (Image alt target) = imageICML opts style alt target +inlineToICML opts style (Note lst) = footnoteToICML opts style lst +inlineToICML opts style (Span _ lst) = inlinesToICML opts style lst + +-- | Convert a list of block elements to an ICML footnote. +footnoteToICML :: WriterOptions -> Style -> [Block] -> WS Doc +footnoteToICML opts style lst = + let insertTab (Para ls) = blockToICML opts (footnoteName:style) $ Para $ (Str "\t"):ls + insertTab block = blockToICML opts (footnoteName:style) block + in do + contents <- mapM insertTab lst + let number = inTags True "ParagraphStyleRange" [] $ + inTags True "CharacterStyleRange" [] $ inTagsSimple "Content" "<?ACE 4?>" + return $ inTags True "CharacterStyleRange" + [("AppliedCharacterStyle","$ID/NormalCharacterStyle"), ("Position","Superscript")] + $ inTags True "Footnote" [] $ number $$ vcat contents + +-- | Auxiliary function to merge Space elements into the adjacent Strs. +mergeSpaces :: [Inline] -> [Inline] +mergeSpaces ((Str s):(Space:((Str s'):xs))) = mergeSpaces $ Str(s++" "++s') : xs +mergeSpaces (Space:((Str s):xs)) = mergeSpaces $ Str (" "++s) : xs +mergeSpaces ((Str s):(Space:xs)) = mergeSpaces $ Str (s++" ") : xs +mergeSpaces (x:xs) = x : (mergeSpaces xs) +mergeSpaces [] = [] + +-- | Wrap a list of inline elements in an ICML Paragraph Style +parStyle :: WriterOptions -> Style -> [Inline] -> WS Doc +parStyle opts style lst = + let slipIn x y = if null y + then x + else x ++ " > " ++ y + stlStr = foldr slipIn [] $ reverse style + stl = if null stlStr + then "" + else "ParagraphStyle/" ++ stlStr + attrs = ("AppliedParagraphStyle", stl) + attrs' = if firstListItemName `elem` style + then let ats = attrs : [("NumberingContinue", "false")] + begins = filter (isPrefixOf beginsWithName) style + in if null begins + then ats + else let i = maybe "" id $ stripPrefix beginsWithName $ head begins + in ("NumberingStartAt", i) : ats + else [attrs] + in do + content <- inlinesToICML opts [] lst + let cont = inTags True "ParagraphStyleRange" attrs' + $ mappend content $ selfClosingTag "Br" [] + state $ \st -> (cont, st{ blockStyles = Set.insert stlStr $ blockStyles st }) + +-- | Wrap a Doc in an ICML Character Style. +charStyle :: Style -> Doc -> WS Doc +charStyle style content = + let (stlStr, attrs) = styleToStrAttr style + doc = inTags True "CharacterStyleRange" attrs $ inTagsSimple "Content" $ flush content + in do + state $ \st -> + let styles = if null stlStr + then st + else st{ inlineStyles = Set.insert stlStr $ inlineStyles st } + in (doc, styles) + +-- | Transform a Style to a tuple of String (eliminating duplicates and ordered) and corresponding attribute. +styleToStrAttr :: Style -> (String, [(String, String)]) +styleToStrAttr style = + let stlStr = unwords $ Set.toAscList $ Set.fromList style + stl = if null style + then "$ID/NormalCharacterStyle" + else "CharacterStyle/" ++ stlStr + attrs = [("AppliedCharacterStyle", stl)] + in (stlStr, attrs) + +-- | Assemble an ICML Image. +imageICML :: WriterOptions -> Style -> [Inline] -> Target -> WS Doc +imageICML _ style _ (linkURI, _) = + let imgWidth = 300::Int --TODO: set width, height dynamically as in Docx.hs + imgHeight = 200::Int + scaleFact = show (1::Double) --TODO: set scaling factor so image is scaled exactly to imgWidth x imgHeight + hw = show $ imgWidth `div` 2 + hh = show $ imgHeight `div` 2 + qw = show $ imgWidth `div` 4 + qh = show $ imgHeight `div` 4 + (stlStr, attrs) = styleToStrAttr style + props = inTags True "Properties" [] $ inTags True "PathGeometry" [] + $ inTags True "GeometryPathType" [("PathOpen","false")] + $ inTags True "PathPointArray" [] + $ vcat [ + selfClosingTag "PathPointType" [("Anchor", "-"++qw++" -"++qh), + ("LeftDirection", "-"++qw++" -"++qh), ("RightDirection", "-"++qw++" -"++qh)] + , selfClosingTag "PathPointType" [("Anchor", "-"++qw++" "++qh), + ("LeftDirection", "-"++qw++" "++qh), ("RightDirection", "-"++qw++" "++qh)] + , selfClosingTag "PathPointType" [("Anchor", qw++" "++qh), + ("LeftDirection", qw++" "++qh), ("RightDirection", qw++" "++qh)] + , selfClosingTag "PathPointType" [("Anchor", qw++" -"++qh), + ("LeftDirection", qw++" -"++qh), ("RightDirection", qw++" -"++qh)] + ] + image = inTags True "Image" + [("Self","ue6"), ("ItemTransform", scaleFact++" 0 0 "++scaleFact++" -"++qw++" -"++qh)] + $ vcat [ + inTags True "Properties" [] $ inTags True "Profile" [("type","string")] $ text "$ID/Embedded" + $$ selfClosingTag "GraphicBounds" [("Left","0"), ("Top","0"), ("Right", hw), ("Bottom", hh)] + , selfClosingTag "Link" [("Self", "ueb"), ("LinkResourceURI", linkURI)] + ] + doc = inTags True "CharacterStyleRange" attrs + $ inTags True "Rectangle" [("Self","uec"), ("ItemTransform", "1 0 0 1 "++qw++" -"++qh)] + $ (props $$ image) + in do + state $ \st -> (doc, st{ inlineStyles = Set.insert stlStr $ inlineStyles st } ) diff --git a/src/Text/Pandoc/Writers/LaTeX.hs b/src/Text/Pandoc/Writers/LaTeX.hs index 63e8acb7d..ee9f7f620 100644 --- a/src/Text/Pandoc/Writers/LaTeX.hs +++ b/src/Text/Pandoc/Writers/LaTeX.hs @@ -1,6 +1,7 @@ -{-# LANGUAGE OverloadedStrings, ScopedTypeVariables #-} +{-# LANGUAGE OverloadedStrings, ScopedTypeVariables, + PatternGuards #-} {- -Copyright (C) 2006-2010 John MacFarlane <jgm@berkeley.edu> +Copyright (C) 2006-2014 John MacFarlane <jgm@berkeley.edu> This program is free software; you can redistribute it and/or modify it under the terms of the GNU General Public License as published by @@ -19,7 +20,7 @@ Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA {- | Module : Text.Pandoc.Writers.LaTeX - Copyright : Copyright (C) 2006-2010 John MacFarlane + Copyright : Copyright (C) 2006-2014 John MacFarlane License : GNU GPL, version 2 or above Maintainer : John MacFarlane <jgm@berkeley.edu> @@ -37,7 +38,7 @@ import Text.Pandoc.Options import Text.Pandoc.Templates import Text.Printf ( printf ) import Network.URI ( isURI, unEscapeString ) -import Data.List ( (\\), isSuffixOf, isInfixOf, +import Data.List ( (\\), isSuffixOf, isInfixOf, stripPrefix, isPrefixOf, intercalate, intersperse ) import Data.Char ( toLower, isPunctuation, isAscii, isLetter, isDigit, ord ) import Data.Maybe ( fromMaybe ) @@ -51,7 +52,9 @@ import Text.Pandoc.Highlighting (highlight, styleToLaTeX, data WriterState = WriterState { stInNote :: Bool -- true if we're in a note + , stInQuote :: Bool -- true if in a blockquote , stInMinipage :: Bool -- true if in minipage + , stInHeading :: Bool -- true if in a section heading , stNotes :: [Doc] -- notes in a minipage , stOLLevel :: Int -- level of ordered list nesting , stOptions :: WriterOptions -- writer options, so they don't have to be parameter @@ -73,9 +76,10 @@ data WriterState = writeLaTeX :: WriterOptions -> Pandoc -> String writeLaTeX options document = evalState (pandocToLaTeX options document) $ - WriterState { stInNote = False, stInMinipage = False, stNotes = [], - stOLLevel = 1, stOptions = options, - stVerbInNote = False, + WriterState { stInNote = False, stInQuote = False, + stInMinipage = False, stInHeading = False, + stNotes = [], stOLLevel = 1, + stOptions = options, stVerbInNote = False, stTable = False, stStrikeout = False, stUrl = False, stGraphics = False, stLHS = False, stBook = writerChapters options, @@ -133,7 +137,7 @@ pandocToLaTeX options (Pandoc meta blocks) = do authorsMeta <- mapM (stringToLaTeX TextString . stringify) $ docAuthors meta let context = defField "toc" (writerTableOfContents options) $ defField "toc-depth" (show (writerTOCDepth options - - if writerChapters options + if stBook st then 1 else 0)) $ defField "body" main $ @@ -141,7 +145,7 @@ pandocToLaTeX options (Pandoc meta blocks) = do defField "author-meta" (intercalate "; " authorsMeta) $ defField "documentclass" (if writerBeamer options then ("beamer" :: String) - else if writerChapters options + else if stBook st then "book" else "article") $ defField "verbatim-in-note" (stVerbInNote st) $ @@ -176,7 +180,9 @@ pandocToLaTeX options (Pandoc meta blocks) = do elementToLaTeX :: WriterOptions -> Element -> State WriterState Doc elementToLaTeX _ (Blk block) = blockToLaTeX block elementToLaTeX opts (Sec level _ (id',classes,_) title' elements) = do + modify $ \s -> s{stInHeading = True} header' <- sectionHeader ("unnumbered" `elem` classes) id' level title' + modify $ \s -> s{stInHeading = False} innerContents <- mapM (elementToLaTeX opts) elements return $ vsep (header' : innerContents) @@ -191,7 +197,7 @@ stringToLaTeX _ [] = return "" stringToLaTeX ctx (x:xs) = do opts <- gets stOptions rest <- stringToLaTeX ctx xs - let ligatures = writerTeXLigatures opts && (ctx /= CodeString) + let ligatures = writerTeXLigatures opts && ctx == TextString let isUrl = ctx == URLString when (x == '€') $ modify $ \st -> st{ stUsesEuro = True } @@ -205,8 +211,9 @@ stringToLaTeX ctx (x:xs) = do '&' -> "\\&" ++ rest '_' | not isUrl -> "\\_" ++ rest '#' -> "\\#" ++ rest - '-' -> case xs of -- prevent adjacent hyphens from forming ligatures - ('-':_) -> "-{}" ++ rest + '-' | not isUrl -> case xs of + -- prevent adjacent hyphens from forming ligatures + ('-':_) -> "-\\/" ++ rest _ -> '-' : rest '~' | not isUrl -> "\\textasciitilde{}" ++ rest '^' -> "\\^{}" ++ rest @@ -217,6 +224,7 @@ stringToLaTeX ctx (x:xs) = do '>' -> "\\textgreater{}" ++ rest '[' -> "{[}" ++ rest -- to avoid interpretation as ']' -> "{]}" ++ rest -- optional arguments + '\'' | ctx == CodeString -> "\\textquotesingle{}" ++ rest '\160' -> "~" ++ rest '\x2026' -> "\\ldots{}" ++ rest '\x2018' | ligatures -> "`" ++ rest @@ -227,12 +235,13 @@ stringToLaTeX ctx (x:xs) = do '\x2013' | ligatures -> "--" ++ rest _ -> x : rest -toLabel :: String -> String -toLabel [] = "" -toLabel (x:xs) - | (isLetter x || isDigit x) && isAscii x = x:toLabel xs - | elem x "-+=:;." = x:toLabel xs - | otherwise = "ux" ++ printf "%x" (ord x) ++ toLabel xs +toLabel :: String -> State WriterState String +toLabel z = go `fmap` stringToLaTeX URLString z + where go [] = "" + go (x:xs) + | (isLetter x || isDigit x) && isAscii x = x:go xs + | elem x "-+=:;." = x:go xs + | otherwise = "ux" ++ printf "%x" (ord x) ++ go xs -- | Puts contents into LaTeX command. inCmd :: String -> Doc -> Doc @@ -297,22 +306,28 @@ isLineBreakOrSpace _ = False blockToLaTeX :: Block -- ^ Block to convert -> State WriterState Doc blockToLaTeX Null = return empty -blockToLaTeX (Div (_,classes,_) bs) = do +blockToLaTeX (Div (identifier,classes,_) bs) = do beamer <- writerBeamer `fmap` gets stOptions + ref <- toLabel identifier + let linkAnchor = if null identifier + then empty + else "\\hyperdef{}" <> braces (text ref) <> "{}" contents <- blockListToLaTeX bs if beamer && "notes" `elem` classes -- speaker notes then return $ "\\note" <> braces contents - else return contents + else return (linkAnchor $$ contents) blockToLaTeX (Plain lst) = inlineListToLaTeX $ dropWhile isLineBreakOrSpace lst -- title beginning with fig: indicates that the image is a figure blockToLaTeX (Para [Image txt (src,'f':'i':'g':':':tit)]) = do - capt <- if null txt - then return empty - else (\c -> "\\caption" <> braces c) `fmap` inlineListToLaTeX txt + inNote <- gets stInNote + capt <- inlineListToLaTeX txt img <- inlineToLaTeX (Image txt (src,tit)) - return $ "\\begin{figure}[htbp]" $$ "\\centering" $$ img $$ - capt $$ "\\end{figure}" + return $ if inNote + -- can't have figures in notes + then "\\begin{center}" $$ img $+$ capt $$ "\\end{center}" + else "\\begin{figure}[htbp]" $$ "\\centering" $$ img $$ + ("\\caption" <> braces capt) $$ "\\end{figure}" -- . . . indicates pause in beamer slides blockToLaTeX (Para [Str ".",Space,Str ".",Space,Str "."]) = do beamer <- writerBeamer `fmap` gets stOptions @@ -331,61 +346,64 @@ blockToLaTeX (BlockQuote lst) = do modify $ \s -> s{ stIncremental = oldIncremental } return result _ -> do + oldInQuote <- gets stInQuote + modify (\s -> s{stInQuote = True}) contents <- blockListToLaTeX lst + modify (\s -> s{stInQuote = oldInQuote}) return $ "\\begin{quote}" $$ contents $$ "\\end{quote}" blockToLaTeX (CodeBlock (identifier,classes,keyvalAttr) str) = do opts <- gets stOptions + ref <- toLabel identifier + let linkAnchor = if null identifier + then empty + else "\\hyperdef{}" <> braces (text ref) <> + braces ("\\label" <> braces (text ref)) + let lhsCodeBlock = do + modify $ \s -> s{ stLHS = True } + return $ flush (linkAnchor $$ "\\begin{code}" $$ text str $$ + "\\end{code}") $$ cr + let rawCodeBlock = do + st <- get + env <- if stInNote st + then modify (\s -> s{ stVerbInNote = True }) >> + return "Verbatim" + else return "verbatim" + return $ flush (linkAnchor $$ text ("\\begin{" ++ env ++ "}") $$ + text str $$ text ("\\end{" ++ env ++ "}")) <> cr + let listingsCodeBlock = do + st <- get + let params = if writerListings (stOptions st) + then (case getListingsLanguage classes of + Just l -> [ "language=" ++ l ] + Nothing -> []) ++ + [ "numbers=left" | "numberLines" `elem` classes + || "number" `elem` classes + || "number-lines" `elem` classes ] ++ + [ (if key == "startFrom" + then "firstnumber" + else key) ++ "=" ++ attr | + (key,attr) <- keyvalAttr ] ++ + (if identifier == "" + then [] + else [ "label=" ++ ref ]) + + else [] + printParams + | null params = empty + | otherwise = brackets $ hcat (intersperse ", " (map text params)) + return $ flush ("\\begin{lstlisting}" <> printParams $$ text str $$ + "\\end{lstlisting}") $$ cr + let highlightedCodeBlock = + case highlight formatLaTeXBlock ("",classes,keyvalAttr) str of + Nothing -> rawCodeBlock + Just h -> modify (\st -> st{ stHighlighting = True }) >> + return (flush $ linkAnchor $$ text h) case () of _ | isEnabled Ext_literate_haskell opts && "haskell" `elem` classes && "literate" `elem` classes -> lhsCodeBlock | writerListings opts -> listingsCodeBlock | writerHighlight opts && not (null classes) -> highlightedCodeBlock | otherwise -> rawCodeBlock - where ref = text $ toLabel identifier - linkAnchor = if null identifier - then empty - else "\\hyperdef{}" <> braces ref <> - braces ("\\label" <> braces ref) - lhsCodeBlock = do - modify $ \s -> s{ stLHS = True } - return $ flush (linkAnchor $$ "\\begin{code}" $$ text str $$ - "\\end{code}") $$ cr - rawCodeBlock = do - st <- get - env <- if stInNote st - then modify (\s -> s{ stVerbInNote = True }) >> - return "Verbatim" - else return "verbatim" - return $ flush (linkAnchor $$ text ("\\begin{" ++ env ++ "}") $$ - text str $$ text ("\\end{" ++ env ++ "}")) <> cr - listingsCodeBlock = do - st <- get - let params = if writerListings (stOptions st) - then (case getListingsLanguage classes of - Just l -> [ "language=" ++ l ] - Nothing -> []) ++ - [ "numbers=left" | "numberLines" `elem` classes - || "number" `elem` classes - || "number-lines" `elem` classes ] ++ - [ (if key == "startFrom" - then "firstnumber" - else key) ++ "=" ++ attr | - (key,attr) <- keyvalAttr ] ++ - (if identifier == "" - then [] - else [ "label=" ++ toLabel identifier ]) - - else [] - printParams - | null params = empty - | otherwise = brackets $ hcat (intersperse ", " (map text params)) - return $ flush ("\\begin{lstlisting}" <> printParams $$ text str $$ - "\\end{lstlisting}") $$ cr - highlightedCodeBlock = - case highlight formatLaTeXBlock ("",classes,keyvalAttr) str of - Nothing -> rawCodeBlock - Just h -> modify (\st -> st{ stHighlighting = True }) >> - return (flush $ linkAnchor $$ text h) blockToLaTeX (RawBlock f x) | f == Format "latex" || f == Format "tex" = return $ text x @@ -450,30 +468,39 @@ blockToLaTeX (DefinitionList lst) = do return $ text ("\\begin{description}" ++ inc) $$ spacing $$ vcat items $$ "\\end{description}" blockToLaTeX HorizontalRule = return $ - "\\begin{center}\\rule{3in}{0.4pt}\\end{center}" -blockToLaTeX (Header level (id',classes,_) lst) = - sectionHeader ("unnumbered" `elem` classes) id' level lst + "\\begin{center}\\rule{0.5\\linewidth}{\\linethickness}\\end{center}" +blockToLaTeX (Header level (id',classes,_) lst) = do + modify $ \s -> s{stInHeading = True} + hdr <- sectionHeader ("unnumbered" `elem` classes) id' level lst + modify $ \s -> s{stInHeading = False} + return hdr blockToLaTeX (Table caption aligns widths heads rows) = do headers <- if all null heads then return empty - else ($$ "\\midrule\\endhead") `fmap` + else ($$ "\\midrule\n") `fmap` (tableRowToLaTeX True aligns widths) heads + let endhead = if all null heads + then empty + else text "\\endhead" captionText <- inlineListToLaTeX caption let capt = if isEmpty captionText then empty - else text "\\addlinespace" - $$ text "\\caption" <> braces captionText + else text "\\caption" <> braces captionText + <> "\\tabularnewline\n\\toprule\n" + <> headers + <> "\\endfirsthead" rows' <- mapM (tableRowToLaTeX False aligns widths) rows let colDescriptors = text $ concat $ map toColDescriptor aligns modify $ \s -> s{ stTable = True } return $ "\\begin{longtable}[c]" <> braces ("@{}" <> colDescriptors <> "@{}") -- the @{} removes extra space at beginning and end - $$ "\\toprule\\addlinespace" + $$ capt + $$ "\\toprule" $$ headers + $$ endhead $$ vcat rows' $$ "\\bottomrule" - $$ capt $$ "\\end{longtable}" toColDescriptor :: Alignment -> String @@ -498,11 +525,30 @@ tableRowToLaTeX header aligns widths cols = do let scaleFactor = 0.97 ** fromIntegral (length aligns) let widths' = map (scaleFactor *) widths cells <- mapM (tableCellToLaTeX header) $ zip3 widths' aligns cols - return $ hsep (intersperse "&" cells) $$ "\\\\\\addlinespace" + return $ hsep (intersperse "&" cells) <> "\\tabularnewline" + +-- For simple latex tables (without minipages or parboxes), +-- we need to go to some lengths to get line breaks working: +-- as LineBreak bs = \vtop{\hbox{\strut as}\hbox{\strut bs}}. +fixLineBreaks :: Block -> Block +fixLineBreaks (Para ils) = Para $ fixLineBreaks' ils +fixLineBreaks (Plain ils) = Plain $ fixLineBreaks' ils +fixLineBreaks x = x + +fixLineBreaks' :: [Inline] -> [Inline] +fixLineBreaks' ils = case splitBy (== LineBreak) ils of + [] -> [] + [xs] -> xs + chunks -> RawInline "tex" "\\vtop{" : + concatMap tohbox chunks ++ + [RawInline "tex" "}"] + where tohbox ys = RawInline "tex" "\\hbox{\\strut " : ys ++ + [RawInline "tex" "}"] tableCellToLaTeX :: Bool -> (Double, Alignment, [Block]) -> State WriterState Doc -tableCellToLaTeX _ (0, _, blocks) = blockListToLaTeX blocks +tableCellToLaTeX _ (0, _, blocks) = + blockListToLaTeX $ walk fixLineBreaks blocks tableCellToLaTeX header (width, align, blocks) = do modify $ \st -> st{ stInMinipage = True, stNotes = [] } cellContents <- blockListToLaTeX blocks @@ -516,7 +562,8 @@ tableCellToLaTeX header (width, align, blocks) = do AlignDefault -> "\\raggedright" return $ ("\\begin{minipage}" <> valign <> braces (text (printf "%.2f\\columnwidth" width)) <> - (halign <> cr <> cellContents <> cr) <> "\\end{minipage}") + (halign <> "\\strut" <> cr <> cellContents <> cr) <> + "\\strut\\end{minipage}") $$ case notes of [] -> empty ns -> (case length ns of @@ -531,7 +578,13 @@ tableCellToLaTeX header (width, align, blocks) = do $ reverse ns) listItemToLaTeX :: [Block] -> State WriterState Doc -listItemToLaTeX lst = blockListToLaTeX lst >>= return . (text "\\item" $$) . +listItemToLaTeX lst + -- we need to put some text before a header if it's the first + -- element in an item. This will look ugly in LaTeX regardless, but + -- this will keep the typesetter from throwing an error. + | ((Header _ _ _) :_) <- lst = + blockListToLaTeX lst >>= return . (text "\\item ~" $$) . (nest 2) + | otherwise = blockListToLaTeX lst >>= return . (text "\\item" $$) . (nest 2) defListItemToLaTeX :: ([Inline], [[Block]]) -> State WriterState Doc @@ -545,7 +598,11 @@ defListItemToLaTeX (term, defs) = do then braces term' else term' def' <- liftM vsep $ mapM blockListToLaTeX defs - return $ "\\item" <> brackets term'' $$ def' + return $ case defs of + (((Header _ _ _) : _) : _) -> + "\\item" <> brackets term'' <> " ~ " $$ def' + _ -> + "\\item" <> brackets term'' $$ def' -- | Craft the section header, inserting the secton reference, if supplied. sectionHeader :: Bool -- True for unnumbered @@ -555,6 +612,7 @@ sectionHeader :: Bool -- True for unnumbered -> State WriterState Doc sectionHeader unnumbered ref level lst = do txt <- inlineListToLaTeX lst + lab <- text `fmap` toLabel ref plain <- stringToLaTeX TextString $ foldl (++) "" $ map stringify lst let noNote (Note _) = Str "" noNote x = x @@ -578,13 +636,13 @@ sectionHeader unnumbered ref level lst = do let refLabel x = (if ref `elem` internalLinks then text "\\hyperdef" <> braces empty - <> braces (text $ toLabel ref) + <> braces lab <> braces x else x) - let headerWith x y r = refLabel $ text x <> y <> - if null r + let headerWith x y = refLabel $ text x <> y <> + if null ref then empty - else text "\\label" <> braces (text $ toLabel r) + else text "\\label" <> braces lab let sectionType = case level' of 0 | writerBeamer opts -> "part" | otherwise -> "chapter" @@ -594,9 +652,16 @@ sectionHeader unnumbered ref level lst = do 4 -> "paragraph" 5 -> "subparagraph" _ -> "" + inQuote <- gets stInQuote + let prefix = if inQuote && level' >= 4 + then text "\\mbox{}%" + -- needed for \paragraph, \subparagraph in quote environment + -- see http://tex.stackexchange.com/questions/169830/ + else empty return $ if level' > 5 then txt - else headerWith ('\\':sectionType) stuffing ref + else prefix $$ + headerWith ('\\':sectionType) stuffing $$ if unnumbered then "\\addcontentsline{toc}" <> braces (text sectionType) <> @@ -627,22 +692,29 @@ isQuoted _ = False -- | Convert inline element to LaTeX inlineToLaTeX :: Inline -- ^ Inline to convert -> State WriterState Doc -inlineToLaTeX (Span (_,classes,_) ils) = do +inlineToLaTeX (Span (id',classes,_) ils) = do let noEmph = "csl-no-emph" `elem` classes let noStrong = "csl-no-strong" `elem` classes let noSmallCaps = "csl-no-smallcaps" `elem` classes - ((if noEmph then inCmd "textup" else id) . - (if noStrong then inCmd "textnormal" else id) . - (if noSmallCaps then inCmd "textnormal" else id) . - (if not (noEmph || noStrong || noSmallCaps) - then braces - else id)) `fmap` inlineListToLaTeX ils + ref <- toLabel id' + let linkAnchor = if null id' + then empty + else "\\hyperdef{}" <> braces (text ref) <> "{}" + fmap (linkAnchor <>) + ((if noEmph then inCmd "textup" else id) . + (if noStrong then inCmd "textnormal" else id) . + (if noSmallCaps then inCmd "textnormal" else id) . + (if not (noEmph || noStrong || noSmallCaps) + then braces + else id)) `fmap` inlineListToLaTeX ils inlineToLaTeX (Emph lst) = inlineListToLaTeX lst >>= return . inCmd "emph" inlineToLaTeX (Strong lst) = inlineListToLaTeX lst >>= return . inCmd "textbf" inlineToLaTeX (Strikeout lst) = do - contents <- inlineListToLaTeX lst + -- we need to protect VERB in an mbox or we get an error + -- see #1294 + contents <- inlineListToLaTeX $ protectCode lst modify $ \s -> s{ stStrikeout = True } return $ inCmd "sout" contents inlineToLaTeX (Superscript lst) = @@ -668,15 +740,19 @@ inlineToLaTeX (Code (_,classes,_) str) = do where listingsCode = do inNote <- gets stInNote when inNote $ modify $ \s -> s{ stVerbInNote = True } - let chr = ((enumFromTo '!' '~') \\ str) !! 0 + let chr = case "!\"&'()*,-./:;?@_" \\ str of + (c:_) -> c + [] -> '!' return $ text $ "\\lstinline" ++ [chr] ++ str ++ [chr] highlightCode = do case highlight formatLaTeXInline ("",classes,[]) str of Nothing -> rawCode Just h -> modify (\st -> st{ stHighlighting = True }) >> return (text h) - rawCode = liftM (text . (\s -> "\\texttt{" ++ s ++ "}")) + rawCode = liftM (text . (\s -> "\\texttt{" ++ escapeSpaces s ++ "}")) $ stringToLaTeX CodeString str + where + escapeSpaces = concatMap (\c -> if c == ' ' then "\\ " else [c]) inlineToLaTeX (Quoted qt lst) = do contents <- inlineListToLaTeX lst csquotes <- liftM stCsquotes get @@ -702,7 +778,7 @@ inlineToLaTeX (Quoted qt lst) = do else char '\x2018' <> inner <> char '\x2019' inlineToLaTeX (Str str) = liftM text $ stringToLaTeX TextString str inlineToLaTeX (Math InlineMath str) = - return $ char '$' <> text str <> char '$' + return $ "\\(" <> text str <> "\\)" inlineToLaTeX (Math DisplayMath str) = return $ "\\[" <> text str <> "\\]" inlineToLaTeX (RawInline f str) @@ -713,15 +789,21 @@ inlineToLaTeX (LineBreak) = return "\\\\" inlineToLaTeX Space = return space inlineToLaTeX (Link txt ('#':ident, _)) = do contents <- inlineListToLaTeX txt - ident' <- stringToLaTeX URLString ident - return $ text "\\hyperref" <> brackets (text $ toLabel ident') <> - braces contents + lab <- toLabel ident + return $ text "\\hyperref" <> brackets (text lab) <> braces contents inlineToLaTeX (Link txt (src, _)) = case txt of - [Str x] | x == src -> -- autolink + [Str x] | escapeURI x == src -> -- autolink do modify $ \s -> s{ stUrl = True } - src' <- stringToLaTeX URLString x + src' <- stringToLaTeX URLString src return $ text $ "\\url{" ++ src' ++ "}" + [Str x] | Just rest <- stripPrefix "mailto:" src, + escapeURI x == rest -> -- email autolink + do modify $ \s -> s{ stUrl = True } + src' <- stringToLaTeX URLString src + contents <- inlineListToLaTeX txt + return $ "\\href" <> braces (text src') <> + braces ("\\nolinkurl" <> braces contents) _ -> do contents <- inlineListToLaTeX txt src' <- stringToLaTeX URLString src return $ text ("\\href{" ++ src' ++ "}{") <> @@ -732,7 +814,10 @@ inlineToLaTeX (Image _ (source, _)) = do then source else unEscapeString source source'' <- stringToLaTeX URLString source' - return $ "\\includegraphics" <> braces (text source'') + inHeading <- gets stInHeading + return $ + (if inHeading then "\\protect\\includegraphics" else "\\includegraphics") + <> braces (text source'') inlineToLaTeX (Note contents) = do inMinipage <- gets stInMinipage modify (\s -> s{stInNote = True}) @@ -742,12 +827,24 @@ inlineToLaTeX (Note contents) = do (CodeBlock _ _ : _) -> cr _ -> empty let noteContents = nest 2 contents' <> optnl + opts <- gets stOptions + -- in beamer slides, display footnote from current overlay forward + let beamerMark = if writerBeamer opts + then text "<.->" + else empty modify $ \st -> st{ stNotes = noteContents : stNotes st } return $ if inMinipage then "\\footnotemark{}" -- note: a \n before } needed when note ends with a Verbatim environment - else "\\footnote" <> braces noteContents + else "\\footnote" <> beamerMark <> braces noteContents + +protectCode :: [Inline] -> [Inline] +protectCode [] = [] +protectCode (x@(Code ("",[],[]) _) : xs) = x : protectCode xs +protectCode (x@(Code _ _) : xs) = ltx "\\mbox{" : x : ltx "}" : xs + where ltx = RawInline (Format "latex") +protectCode (x : xs) = x : protectCode xs citationsToNatbib :: [Citation] -> State WriterState Doc citationsToNatbib (one:[]) diff --git a/src/Text/Pandoc/Writers/Man.hs b/src/Text/Pandoc/Writers/Man.hs index b31cc2b70..6b2c4c200 100644 --- a/src/Text/Pandoc/Writers/Man.hs +++ b/src/Text/Pandoc/Writers/Man.hs @@ -1,5 +1,5 @@ {- -Copyright (C) 2007-2010 John MacFarlane <jgm@berkeley.edu> +Copyright (C) 2007-2014 John MacFarlane <jgm@berkeley.edu> This program is free software; you can redistribute it and/or modify it under the terms of the GNU General Public License as published by @@ -18,7 +18,7 @@ Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA {- | Module : Text.Pandoc.Writers.Man - Copyright : Copyright (C) 2007-2010 John MacFarlane + Copyright : Copyright (C) 2007-2014 John MacFarlane License : GNU GPL, version 2 or above Maintainer : John MacFarlane <jgm@berkeley.edu> @@ -36,7 +36,8 @@ import Text.Pandoc.Writers.Shared import Text.Pandoc.Options import Text.Pandoc.Readers.TeXMath import Text.Printf ( printf ) -import Data.List ( isPrefixOf, intersperse, intercalate ) +import Data.List ( stripPrefix, intersperse, intercalate ) +import Data.Maybe (fromMaybe) import Text.Pandoc.Pretty import Text.Pandoc.Builder (deleteMeta) import Control.Monad.State @@ -283,7 +284,7 @@ definitionListItemToMan opts (label, defs) = do mapM (\item -> blockToMan opts item) rest first' <- blockToMan opts first return $ first' $$ text ".RS" $$ rest' $$ text ".RE" - return $ text ".TP" $$ text ".B " <> labelText $$ contents + return $ text ".TP" $$ nowrap (text ".B " <> labelText) $$ contents -- | Convert list of Pandoc block elements to man. blockListToMan :: WriterOptions -- ^ Options @@ -331,9 +332,9 @@ inlineToMan _ (Code _ str) = return $ text $ "\\f[C]" ++ escapeCode str ++ "\\f[]" inlineToMan _ (Str str) = return $ text $ escapeString str inlineToMan opts (Math InlineMath str) = - inlineListToMan opts $ readTeXMath' InlineMath str + inlineListToMan opts $ texMathToInlines InlineMath str inlineToMan opts (Math DisplayMath str) = do - contents <- inlineListToMan opts $ readTeXMath' DisplayMath str + contents <- inlineListToMan opts $ texMathToInlines DisplayMath str return $ cr <> text ".RS" $$ contents $$ text ".RE" inlineToMan _ (RawInline f str) | f == Format "man" = return $ text str @@ -343,7 +344,7 @@ inlineToMan _ (LineBreak) = return $ inlineToMan _ Space = return space inlineToMan opts (Link txt (src, _)) = do linktext <- inlineListToMan opts txt - let srcSuffix = if isPrefixOf "mailto:" src then drop 7 src else src + let srcSuffix = fromMaybe src (stripPrefix "mailto:" src) return $ case txt of [Str s] | escapeURI s == srcSuffix -> diff --git a/src/Text/Pandoc/Writers/Markdown.hs b/src/Text/Pandoc/Writers/Markdown.hs index 278e5cc9d..f06f1d6cc 100644 --- a/src/Text/Pandoc/Writers/Markdown.hs +++ b/src/Text/Pandoc/Writers/Markdown.hs @@ -1,6 +1,6 @@ {-# LANGUAGE OverloadedStrings, TupleSections, ScopedTypeVariables #-} {- -Copyright (C) 2006-2013 John MacFarlane <jgm@berkeley.edu> +Copyright (C) 2006-2014 John MacFarlane <jgm@berkeley.edu> This program is free software; you can redistribute it and/or modify it under the terms of the GNU General Public License as published by @@ -19,7 +19,7 @@ Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA {- | Module : Text.Pandoc.Writers.Markdown - Copyright : Copyright (C) 2006-2013 John MacFarlane + Copyright : Copyright (C) 2006-2014 John MacFarlane License : GNU GPL, version 2 or above Maintainer : John MacFarlane <jgm@berkeley.edu> @@ -37,16 +37,17 @@ import Text.Pandoc.Templates (renderTemplate') import Text.Pandoc.Shared import Text.Pandoc.Writers.Shared import Text.Pandoc.Options -import Text.Pandoc.Parsing hiding (blankline, char, space) -import Data.List ( group, isPrefixOf, find, intersperse, transpose, sortBy ) +import Text.Pandoc.Parsing hiding (blankline, blanklines, char, space) +import Data.Maybe (fromMaybe) +import Data.List ( group, stripPrefix, find, intersperse, transpose, sortBy ) import Data.Char ( isSpace, isPunctuation ) import Data.Ord ( comparing ) import Text.Pandoc.Pretty import Control.Monad.State import qualified Data.Set as Set import Text.Pandoc.Writers.HTML (writeHtmlString) -import Text.Pandoc.Readers.TeXMath (readTeXMath') -import Text.HTML.TagSoup (renderTags, parseTags, isTagText, Tag(..)) +import Text.Pandoc.Readers.TeXMath (texMathToInlines) +import Text.HTML.TagSoup (parseTags, isTagText, Tag(..)) import Network.URI (isURI) import Data.Default import Data.Yaml (Value(Object,String,Array,Bool,Number)) @@ -77,26 +78,15 @@ writePlain :: WriterOptions -> Pandoc -> String writePlain opts document = evalState (pandocToMarkdown opts{ writerExtensions = Set.delete Ext_escaped_line_breaks $ + Set.delete Ext_pipe_tables $ + Set.delete Ext_raw_html $ + Set.delete Ext_markdown_in_html_blocks $ + Set.delete Ext_raw_tex $ + Set.delete Ext_footnotes $ + Set.delete Ext_tex_math_dollars $ + Set.delete Ext_citations $ writerExtensions opts } - document') def{ stPlain = True } - where document' = plainify document - -plainify :: Pandoc -> Pandoc -plainify = walk go - where go :: Inline -> Inline - go (Emph xs) = SmallCaps xs - go (Strong xs) = SmallCaps xs - go (Strikeout xs) = SmallCaps xs - go (Superscript xs) = SmallCaps xs - go (Subscript xs) = SmallCaps xs - go (SmallCaps xs) = SmallCaps xs - go (Code _ s) = Str s - go (Math _ s) = Str s - go (RawInline _ _) = Str "" - go (Link xs _) = SmallCaps xs - go (Image xs _) = SmallCaps $ [Str "["] ++ xs ++ [Str "]"] - go (Cite _ cits) = SmallCaps cits - go x = x + document) def{ stPlain = True } pandocTitleBlock :: Doc -> [Doc] -> Doc -> Doc pandocTitleBlock tit auths dat = @@ -187,7 +177,7 @@ pandocToMarkdown opts (Pandoc meta blocks) = do then tableOfContents opts headerBlocks else empty -- Strip off final 'references' header if markdown citations enabled - let blocks' = if not isPlain && isEnabled Ext_citations opts + let blocks' = if isEnabled Ext_citations opts then case reverse blocks of (Div (_,["references"],_) _):xs -> reverse xs _ -> blocks @@ -251,9 +241,20 @@ noteToMarkdown opts num blocks = do else marker <> spacer <> contents -- | Escape special characters for Markdown. -escapeString :: String -> String -escapeString = escapeStringUsing markdownEscapes - where markdownEscapes = backslashEscapes "\\`*_$<>#~^" +escapeString :: WriterOptions -> String -> String +escapeString opts = escapeStringUsing markdownEscapes + where markdownEscapes = backslashEscapes specialChars + specialChars = + (if isEnabled Ext_superscript opts + then ('^':) + else id) . + (if isEnabled Ext_subscript opts + then ('~':) + else id) . + (if isEnabled Ext_tex_math_dollars opts + then ('$':) + else id) $ + "\\`*_<>#" -- | Construct table of contents from list of header blocks. tableOfContents :: WriterOptions -> [Block] -> Doc @@ -308,45 +309,51 @@ blockToMarkdown :: WriterOptions -- ^ Options -> State WriterState Doc blockToMarkdown _ Null = return empty blockToMarkdown opts (Div attrs ils) = do - isPlain <- gets stPlain contents <- blockListToMarkdown opts ils - return $ if isPlain || not (isEnabled Ext_markdown_in_html_blocks opts) - then contents <> blankline - else tagWithAttrs "div" attrs <> blankline <> + return $ if isEnabled Ext_raw_html opts && + isEnabled Ext_markdown_in_html_blocks opts + then tagWithAttrs "div" attrs <> blankline <> contents <> blankline <> "</div>" <> blankline + else contents <> blankline blockToMarkdown opts (Plain inlines) = do contents <- inlineListToMarkdown opts inlines - return $ contents <> cr + -- escape if para starts with ordered list marker + st <- get + let colwidth = if writerWrapText opts + then Just $ writerColumns opts + else Nothing + let rendered = render colwidth contents + let escapeDelimiter (x:xs) | x `elem` ".()" = '\\':x:xs + | otherwise = x : escapeDelimiter xs + escapeDelimiter [] = [] + let contents' = if isEnabled Ext_all_symbols_escapable opts && + not (stPlain st) && beginsWithOrderedListMarker rendered + then text $ escapeDelimiter rendered + else contents + return $ contents' <> cr -- title beginning with fig: indicates figure blockToMarkdown opts (Para [Image alt (src,'f':'i':'g':':':tit)]) = blockToMarkdown opts (Para [Image alt (src,tit)]) -blockToMarkdown opts (Para inlines) = do - contents <- inlineListToMarkdown opts inlines - -- escape if para starts with ordered list marker - st <- get - let esc = if isEnabled Ext_all_symbols_escapable opts && - not (stPlain st) && - beginsWithOrderedListMarker (render Nothing contents) - then text "\x200B" -- zero-width space, a hack - else empty - return $ esc <> contents <> blankline +blockToMarkdown opts (Para inlines) = + (<> blankline) `fmap` blockToMarkdown opts (Plain inlines) blockToMarkdown opts (RawBlock f str) | f == "html" = do - st <- get - if stPlain st - then return empty - else return $ if isEnabled Ext_markdown_attribute opts + plain <- gets stPlain + return $ if plain + then empty + else if isEnabled Ext_markdown_attribute opts then text (addMarkdownAttribute str) <> text "\n" else text str <> text "\n" | f `elem` ["latex", "tex", "markdown"] = do - st <- get - if stPlain st - then return empty - else return $ text str <> text "\n" + plain <- gets stPlain + return $ if plain + then empty + else text str <> text "\n" blockToMarkdown _ (RawBlock _ _) = return empty -blockToMarkdown _ HorizontalRule = - return $ blankline <> text "* * * * *" <> blankline +blockToMarkdown opts HorizontalRule = do + return $ blankline <> text (replicate (writerColumns opts) '-') <> blankline blockToMarkdown opts (Header level attr inlines) = do + plain <- gets stPlain -- we calculate the id that would be used by auto_identifiers -- so we know whether to print an explicit identifier ids <- gets stIds @@ -361,19 +368,23 @@ blockToMarkdown opts (Header level attr inlines) = do _ | isEnabled Ext_header_attributes opts -> space <> attrsToMarkdown attr | otherwise -> empty - contents <- inlineListToMarkdown opts inlines - st <- get + contents <- inlineListToMarkdown opts $ + if level == 1 && plain + then capitalize inlines + else inlines let setext = writerSetextHeaders opts return $ nowrap $ case level of - 1 | setext -> + 1 | plain -> blanklines 3 <> contents <> blanklines 2 + | setext -> contents <> attr' <> cr <> text (replicate (offset contents) '=') <> blankline - 2 | setext -> + 2 | plain -> blanklines 2 <> contents <> blankline + | setext -> contents <> attr' <> cr <> text (replicate (offset contents) '-') <> blankline -- ghc interprets '#' characters in column 1 as linenum specifiers. - _ | stPlain st || isEnabled Ext_literate_haskell opts -> + _ | plain || isEnabled Ext_literate_haskell opts -> contents <> blankline _ -> text (replicate level '#') <> space <> contents <> attr' <> blankline blockToMarkdown opts (CodeBlock (_,classes,_) str) @@ -392,21 +403,23 @@ blockToMarkdown opts (CodeBlock attribs str) = return $ xs -> case maximum $ map length xs of n | n < 3 -> "~~~~" | otherwise -> replicate (n+1) '~' - backticks = text "```" + backticks = text $ case [ln | ln <- lines str, all (=='`') ln] of + [] -> "```" + xs -> case maximum $ map length xs of + n | n < 3 -> "```" + | otherwise -> replicate (n+1) '`' attrs = if isEnabled Ext_fenced_code_attributes opts then nowrap $ " " <> attrsToMarkdown attribs else case attribs of - (_,[cls],_) -> " " <> text cls - _ -> empty + (_,(cls:_),_) -> " " <> text cls + _ -> empty blockToMarkdown opts (BlockQuote blocks) = do - st <- get + plain <- gets stPlain -- if we're writing literate haskell, put a space before the bird tracks -- so they won't be interpreted as lhs... let leader = if isEnabled Ext_literate_haskell opts then " > " - else if stPlain st - then " " - else "> " + else if plain then " " else "> " contents <- blockListToMarkdown opts blocks return $ (prefixed leader contents) <> blankline blockToMarkdown opts t@(Table caption aligns widths headers rows) = do @@ -462,23 +475,31 @@ addMarkdownAttribute :: String -> String addMarkdownAttribute s = case span isTagText $ reverse $ parseTags s of (xs,(TagOpen t attrs:rest)) -> - renderTags $ reverse rest ++ (TagOpen t attrs' : reverse xs) + renderTags' $ reverse rest ++ (TagOpen t attrs' : reverse xs) where attrs' = ("markdown","1"):[(x,y) | (x,y) <- attrs, x /= "markdown"] _ -> s pipeTable :: Bool -> [Alignment] -> [Doc] -> [[Doc]] -> State WriterState Doc pipeTable headless aligns rawHeaders rawRows = do + let sp = text " " + let blockFor AlignLeft x y = lblock (x + 2) (sp <> y) <> lblock 0 empty + blockFor AlignCenter x y = cblock (x + 2) (sp <> y) <> lblock 0 empty + blockFor AlignRight x y = rblock (x + 2) (sp <> y) <> lblock 0 empty + blockFor _ x y = lblock (x + 2) (sp <> y) <> lblock 0 empty + let widths = map (max 3 . maximum . map offset) $ transpose (rawHeaders : rawRows) let torow cs = nowrap $ text "|" <> - hcat (intersperse (text "|") $ map chomp cs) <> text "|" - let toborder (a, h) = let wid = max (offset h) 3 - in text $ case a of - AlignLeft -> ':':replicate (wid - 1) '-' - AlignCenter -> ':':replicate (wid - 2) '-' ++ ":" - AlignRight -> replicate (wid - 1) '-' ++ ":" - AlignDefault -> replicate wid '-' + hcat (intersperse (text "|") $ + zipWith3 blockFor aligns widths (map chomp cs)) + <> text "|" + let toborder (a, w) = text $ case a of + AlignLeft -> ':':replicate (w + 1) '-' + AlignCenter -> ':':replicate w '-' ++ ":" + AlignRight -> replicate (w + 1) '-' ++ ":" + AlignDefault -> replicate (w + 2) '-' let header = if headless then empty else torow rawHeaders - let border = torow $ map toborder $ zip aligns rawHeaders + let border = nowrap $ text "|" <> hcat (intersperse (text "|") $ + map toborder $ zip aligns widths) <> text "|" let body = vcat $ map torow rawRows return $ header $$ border $$ body @@ -592,8 +613,19 @@ definitionListItemToMarkdown opts (label, defs) = do let sps = case writerTabStop opts - 3 of n | n > 0 -> text $ replicate n ' ' _ -> text " " - let contents = vcat $ map (\d -> hang tabStop (leader <> sps) $ vcat d <> cr) defs' - return $ nowrap labelText <> cr <> contents <> cr + if isEnabled Ext_compact_definition_lists opts + then do + let contents = vcat $ map (\d -> hang tabStop (leader <> sps) + $ vcat d <> cr) defs' + return $ nowrap labelText <> cr <> contents <> cr + else do + let contents = vcat $ map (\d -> hang tabStop (leader <> sps) + $ vcat d <> cr) defs' + let isTight = case defs of + ((Plain _ : _): _) -> True + _ -> False + return $ blankline <> nowrap labelText <> + (if isTight then cr else blankline) <> contents <> blankline else do return $ nowrap labelText <> text " " <> cr <> vsep (map vsep defs') <> blankline @@ -608,15 +640,21 @@ blockListToMarkdown opts blocks = -- code block will be treated as a list continuation paragraph where fixBlocks (b : CodeBlock attr x : rest) | (not (isEnabled Ext_fenced_code_blocks opts) || attr == nullAttr) - && isListBlock b = - b : RawBlock "html" "<!-- -->\n" : CodeBlock attr x : - fixBlocks rest + && isListBlock b = b : commentSep : CodeBlock attr x : + fixBlocks rest + fixBlocks (b1@(BulletList _) : b2@(BulletList _) : bs) = + b1 : commentSep : fixBlocks (b2:bs) + fixBlocks (b1@(OrderedList _ _) : b2@(OrderedList _ _) : bs) = + b1 : commentSep : fixBlocks (b2:bs) + fixBlocks (b1@(DefinitionList _) : b2@(DefinitionList _) : bs) = + b1 : commentSep : fixBlocks (b2:bs) fixBlocks (x : xs) = x : fixBlocks xs fixBlocks [] = [] isListBlock (BulletList _) = True isListBlock (OrderedList _ _) = True isListBlock (DefinitionList _) = True isListBlock _ = False + commentSep = RawBlock "html" "<!-- -->\n" -- | Get reference for target; if none exists, create unique one and return. -- Prefer label if possible; otherwise, generate a unique key. @@ -640,7 +678,11 @@ getReference label (src, tit) = do -- | Convert list of Pandoc inline elements to markdown. inlineListToMarkdown :: WriterOptions -> [Inline] -> State WriterState Doc inlineListToMarkdown opts lst = - mapM (inlineToMarkdown opts) lst >>= return . cat + mapM (inlineToMarkdown opts) (avoidBadWraps lst) >>= return . cat + where avoidBadWraps [] = [] + avoidBadWraps (Space:Str (c:cs):xs) + | c `elem` "-*+>" = Str (' ':c:cs) : avoidBadWraps xs + avoidBadWraps (x:xs) = x : avoidBadWraps xs escapeSpaces :: Inline -> Inline escapeSpaces (Str s) = Str $ substitute " " "\\ " s @@ -650,57 +692,72 @@ escapeSpaces x = x -- | Convert Pandoc inline element to markdown. inlineToMarkdown :: WriterOptions -> Inline -> State WriterState Doc inlineToMarkdown opts (Span attrs ils) = do - st <- get contents <- inlineListToMarkdown opts ils - return $ if stPlain st - then contents - else tagWithAttrs "span" attrs <> contents <> text "</span>" + return $ if isEnabled Ext_raw_html opts + then tagWithAttrs "span" attrs <> contents <> text "</span>" + else contents inlineToMarkdown opts (Emph lst) = do + plain <- gets stPlain contents <- inlineListToMarkdown opts lst - return $ "*" <> contents <> "*" + return $ if plain + then "_" <> contents <> "_" + else "*" <> contents <> "*" inlineToMarkdown opts (Strong lst) = do - contents <- inlineListToMarkdown opts lst - return $ "**" <> contents <> "**" + plain <- gets stPlain + if plain + then inlineListToMarkdown opts $ capitalize lst + else do + contents <- inlineListToMarkdown opts lst + return $ "**" <> contents <> "**" inlineToMarkdown opts (Strikeout lst) = do contents <- inlineListToMarkdown opts lst return $ if isEnabled Ext_strikeout opts then "~~" <> contents <> "~~" else "<s>" <> contents <> "</s>" inlineToMarkdown opts (Superscript lst) = do - let lst' = walk escapeSpaces lst - contents <- inlineListToMarkdown opts lst' + contents <- inlineListToMarkdown opts $ walk escapeSpaces lst return $ if isEnabled Ext_superscript opts then "^" <> contents <> "^" else "<sup>" <> contents <> "</sup>" inlineToMarkdown opts (Subscript lst) = do - let lst' = walk escapeSpaces lst - contents <- inlineListToMarkdown opts lst' + contents <- inlineListToMarkdown opts $ walk escapeSpaces lst return $ if isEnabled Ext_subscript opts then "~" <> contents <> "~" else "<sub>" <> contents <> "</sub>" -inlineToMarkdown opts (SmallCaps lst) = inlineListToMarkdown opts lst +inlineToMarkdown opts (SmallCaps lst) = do + plain <- gets stPlain + if plain + then inlineListToMarkdown opts $ capitalize lst + else do + contents <- inlineListToMarkdown opts lst + return $ tagWithAttrs "span" + ("",[],[("style","font-variant:small-caps;")]) + <> contents <> text "</span>" inlineToMarkdown opts (Quoted SingleQuote lst) = do contents <- inlineListToMarkdown opts lst return $ "‘" <> contents <> "’" inlineToMarkdown opts (Quoted DoubleQuote lst) = do contents <- inlineListToMarkdown opts lst return $ "“" <> contents <> "”" -inlineToMarkdown opts (Code attr str) = +inlineToMarkdown opts (Code attr str) = do let tickGroups = filter (\s -> '`' `elem` s) $ group str - longest = if null tickGroups + let longest = if null tickGroups then 0 else maximum $ map length tickGroups - marker = replicate (longest + 1) '`' - spacer = if (longest == 0) then "" else " " - attrs = if isEnabled Ext_inline_code_attributes opts && attr /= nullAttr + let marker = replicate (longest + 1) '`' + let spacer = if (longest == 0) then "" else " " + let attrs = if isEnabled Ext_inline_code_attributes opts && attr /= nullAttr then attrsToMarkdown attr else empty - in return $ text (marker ++ spacer ++ str ++ spacer ++ marker) <> attrs -inlineToMarkdown _ (Str str) = do + plain <- gets stPlain + if plain + then return $ text str + else return $ text (marker ++ spacer ++ str ++ spacer ++ marker) <> attrs +inlineToMarkdown opts (Str str) = do st <- get if stPlain st then return $ text str - else return $ text $ escapeString str + else return $ text $ escapeString opts str inlineToMarkdown opts (Math InlineMath str) | isEnabled Ext_tex_math_dollars opts = return $ "$" <> text str <> "$" @@ -708,7 +765,11 @@ inlineToMarkdown opts (Math InlineMath str) return $ "\\(" <> text str <> "\\)" | isEnabled Ext_tex_math_double_backslash opts = return $ "\\\\(" <> text str <> "\\\\)" - | otherwise = inlineListToMarkdown opts $ readTeXMath' InlineMath str + | otherwise = do + plain <- gets stPlain + inlineListToMarkdown opts $ + (if plain then makeMathPlainer else id) $ + texMathToInlines InlineMath str inlineToMarkdown opts (Math DisplayMath str) | isEnabled Ext_tex_math_dollars opts = return $ "$$" <> text str <> "$$" @@ -717,16 +778,23 @@ inlineToMarkdown opts (Math DisplayMath str) | isEnabled Ext_tex_math_double_backslash opts = return $ "\\\\[" <> text str <> "\\\\]" | otherwise = (\x -> cr <> x <> cr) `fmap` - inlineListToMarkdown opts (readTeXMath' DisplayMath str) -inlineToMarkdown opts (RawInline f str) - | f == "html" || f == "markdown" || - (isEnabled Ext_raw_tex opts && (f == "latex" || f == "tex")) = - return $ text str -inlineToMarkdown _ (RawInline _ _) = return empty -inlineToMarkdown opts (LineBreak) - | isEnabled Ext_hard_line_breaks opts = return cr - | isEnabled Ext_escaped_line_breaks opts = return $ "\\" <> cr - | otherwise = return $ " " <> cr + inlineListToMarkdown opts (texMathToInlines DisplayMath str) +inlineToMarkdown opts (RawInline f str) = do + plain <- gets stPlain + if not plain && + ( f == "markdown" || + (isEnabled Ext_raw_tex opts && (f == "latex" || f == "tex")) || + (isEnabled Ext_raw_html opts && f == "html") ) + then return $ text str + else return empty +inlineToMarkdown opts (LineBreak) = do + plain <- gets stPlain + if plain || isEnabled Ext_hard_line_breaks opts + then return cr + else return $ + if isEnabled Ext_escaped_line_breaks opts + then "\\" <> cr + else " " <> cr inlineToMarkdown _ Space = return space inlineToMarkdown opts (Cite [] lst) = inlineListToMarkdown opts lst inlineToMarkdown opts (Cite (c:cs) lst) @@ -759,11 +827,12 @@ inlineToMarkdown opts (Cite (c:cs) lst) modekey SuppressAuthor = "-" modekey _ = "" inlineToMarkdown opts (Link txt (src, tit)) = do + plain <- gets stPlain linktext <- inlineListToMarkdown opts txt let linktitle = if null tit then empty else text $ " \"" ++ tit ++ "\"" - let srcSuffix = if isPrefixOf "mailto:" src then drop 7 src else src + let srcSuffix = fromMaybe src (stripPrefix "mailto:" src) let useAuto = isURI src && case txt of [Str s] | escapeURI s == srcSuffix -> True @@ -772,22 +841,29 @@ inlineToMarkdown opts (Link txt (src, tit)) = do ref <- if useRefLinks then getReference txt (src, tit) else return [] reftext <- inlineListToMarkdown opts ref return $ if useAuto - then "<" <> text srcSuffix <> ">" + then if plain + then text srcSuffix + else "<" <> text srcSuffix <> ">" else if useRefLinks then let first = "[" <> linktext <> "]" second = if txt == ref then "[]" else "[" <> reftext <> "]" in first <> second - else "[" <> linktext <> "](" <> - text src <> linktitle <> ")" + else if plain + then linktext + else "[" <> linktext <> "](" <> + text src <> linktitle <> ")" inlineToMarkdown opts (Image alternate (source, tit)) = do + plain <- gets stPlain let txt = if null alternate || alternate == [Str source] -- to prevent autolinks then [Str ""] else alternate linkPart <- inlineToMarkdown opts (Link txt (source, tit)) - return $ "!" <> linkPart + return $ if plain + then "[" <> linkPart <> "]" + else "!" <> linkPart inlineToMarkdown opts (Note contents) = do modify (\st -> st{ stNotes = contents : stNotes st }) st <- get @@ -795,3 +871,9 @@ inlineToMarkdown opts (Note contents) = do if isEnabled Ext_footnotes opts then return $ "[^" <> ref <> "]" else return $ "[" <> ref <> "]" + +makeMathPlainer :: [Inline] -> [Inline] +makeMathPlainer = walk go + where + go (Emph xs) = Span nullAttr xs + go x = x diff --git a/src/Text/Pandoc/Writers/MediaWiki.hs b/src/Text/Pandoc/Writers/MediaWiki.hs index 83fefaa29..3f392a5d0 100644 --- a/src/Text/Pandoc/Writers/MediaWiki.hs +++ b/src/Text/Pandoc/Writers/MediaWiki.hs @@ -1,5 +1,5 @@ {- -Copyright (C) 2008-2010 John MacFarlane <jgm@berkeley.edu> +Copyright (C) 2008-2014 John MacFarlane <jgm@berkeley.edu> This program is free software; you can redistribute it and/or modify it under the terms of the GNU General Public License as published by @@ -18,7 +18,7 @@ Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA {- | Module : Text.Pandoc.Writers.MediaWiki - Copyright : Copyright (C) 2008-2010 John MacFarlane + Copyright : Copyright (C) 2008-2014 John MacFarlane License : GNU GPL, version 2 or above Maintainer : John MacFarlane <jgm@berkeley.edu> @@ -37,92 +37,99 @@ import Text.Pandoc.Writers.Shared import Text.Pandoc.Pretty (render) import Text.Pandoc.Templates (renderTemplate') import Text.Pandoc.XML ( escapeStringForXML ) -import Data.List ( intersect, intercalate, intersperse ) +import Data.List ( intersect, intercalate ) import Network.URI ( isURI ) +import Control.Monad.Reader import Control.Monad.State data WriterState = WriterState { stNotes :: Bool -- True if there are notes - , stListLevel :: [Char] -- String at beginning of list items, e.g. "**" - , stUseTags :: Bool -- True if we should use HTML tags because we're in a complex list } +data WriterReader = WriterReader { + options :: WriterOptions -- Writer options + , listLevel :: String -- String at beginning of list items, e.g. "**" + , useTags :: Bool -- True if we should use HTML tags because we're in a complex list + } + +type MediaWikiWriter = ReaderT WriterReader (State WriterState) + -- | Convert Pandoc to MediaWiki. writeMediaWiki :: WriterOptions -> Pandoc -> String writeMediaWiki opts document = - evalState (pandocToMediaWiki opts document) - WriterState { stNotes = False, stListLevel = [], stUseTags = False } + let initialState = WriterState { stNotes = False } + env = WriterReader { options = opts, listLevel = [], useTags = False } + in evalState (runReaderT (pandocToMediaWiki document) env) initialState -- | Return MediaWiki representation of document. -pandocToMediaWiki :: WriterOptions -> Pandoc -> State WriterState String -pandocToMediaWiki opts (Pandoc meta blocks) = do +pandocToMediaWiki :: Pandoc -> MediaWikiWriter String +pandocToMediaWiki (Pandoc meta blocks) = do + opts <- asks options metadata <- metaToJSON opts - (fmap trimr . blockListToMediaWiki opts) - (inlineListToMediaWiki opts) + (fmap trimr . blockListToMediaWiki) + inlineListToMediaWiki meta - body <- blockListToMediaWiki opts blocks - notesExist <- get >>= return . stNotes + body <- blockListToMediaWiki blocks + notesExist <- gets stNotes let notes = if notesExist then "\n<references />" else "" let main = body ++ notes let context = defField "body" main - $ defField "toc" (writerTableOfContents opts) - $ metadata - if writerStandalone opts - then return $ renderTemplate' (writerTemplate opts) context - else return main + $ defField "toc" (writerTableOfContents opts) metadata + return $ if writerStandalone opts + then renderTemplate' (writerTemplate opts) context + else main -- | Escape special characters for MediaWiki. escapeString :: String -> String escapeString = escapeStringForXML -- | Convert Pandoc block element to MediaWiki. -blockToMediaWiki :: WriterOptions -- ^ Options - -> Block -- ^ Block element - -> State WriterState String +blockToMediaWiki :: Block -- ^ Block element + -> MediaWikiWriter String -blockToMediaWiki _ Null = return "" +blockToMediaWiki Null = return "" -blockToMediaWiki opts (Div attrs bs) = do - contents <- blockListToMediaWiki opts bs +blockToMediaWiki (Div attrs bs) = do + contents <- blockListToMediaWiki bs return $ render Nothing (tagWithAttrs "div" attrs) ++ "\n\n" ++ contents ++ "\n\n" ++ "</div>" -blockToMediaWiki opts (Plain inlines) = - inlineListToMediaWiki opts inlines +blockToMediaWiki (Plain inlines) = + inlineListToMediaWiki inlines -- title beginning with fig: indicates that the image is a figure -blockToMediaWiki opts (Para [Image txt (src,'f':'i':'g':':':tit)]) = do +blockToMediaWiki (Para [Image txt (src,'f':'i':'g':':':tit)]) = do capt <- if null txt then return "" - else ("|caption " ++) `fmap` inlineListToMediaWiki opts txt + else ("|caption " ++) `fmap` inlineListToMediaWiki txt let opt = if null txt then "" else "|alt=" ++ if null tit then capt else tit ++ capt return $ "[[Image:" ++ src ++ "|frame|none" ++ opt ++ "]]\n" -blockToMediaWiki opts (Para inlines) = do - useTags <- get >>= return . stUseTags - listLevel <- get >>= return . stListLevel - contents <- inlineListToMediaWiki opts inlines - return $ if useTags +blockToMediaWiki (Para inlines) = do + tags <- asks useTags + lev <- asks listLevel + contents <- inlineListToMediaWiki inlines + return $ if tags then "<p>" ++ contents ++ "</p>" - else contents ++ if null listLevel then "\n" else "" + else contents ++ if null lev then "\n" else "" -blockToMediaWiki _ (RawBlock f str) +blockToMediaWiki (RawBlock f str) | f == Format "mediawiki" = return str | f == Format "html" = return str | otherwise = return "" -blockToMediaWiki _ HorizontalRule = return "\n-----\n" +blockToMediaWiki HorizontalRule = return "\n-----\n" -blockToMediaWiki opts (Header level _ inlines) = do - contents <- inlineListToMediaWiki opts inlines +blockToMediaWiki (Header level _ inlines) = do + contents <- inlineListToMediaWiki inlines let eqs = replicate level '=' return $ eqs ++ " " ++ contents ++ " " ++ eqs ++ "\n" -blockToMediaWiki _ (CodeBlock (_,classes,_) str) = do +blockToMediaWiki (CodeBlock (_,classes,_) str) = do let at = classes `intersect` ["actionscript", "ada", "apache", "applescript", "asm", "asp", "autoit", "bash", "blitzbasic", "bnf", "c", "c_mac", "caddcl", "cadlisp", "cfdg", "cfm", "cpp", "cpp-qt", "csharp", "css", "d", "delphi", "diff", "div", "dos", "eiffel", "fortran", @@ -132,75 +139,64 @@ blockToMediaWiki _ (CodeBlock (_,classes,_) str) = do "python", "qbasic", "rails", "reg", "robots", "ruby", "sas", "scheme", "sdlbasic", "smalltalk", "smarty", "sql", "tcl", "", "thinbasic", "tsql", "vb", "vbnet", "vhdl", "visualfoxpro", "winbatch", "xml", "xpp", "z80"] - let (beg, end) = if null at - then ("<pre" ++ if null classes then ">" else " class=\"" ++ unwords classes ++ "\">", "</pre>") - else ("<source lang=\"" ++ head at ++ "\">", "</source>") - return $ beg ++ escapeString str ++ end - -blockToMediaWiki opts (BlockQuote blocks) = do - contents <- blockListToMediaWiki opts blocks + return $ + if null at + then "<pre" ++ (if null classes + then ">" + else " class=\"" ++ unwords classes ++ "\">") ++ + escapeString str ++ "</pre>" + else "<source lang=\"" ++ head at ++ "\">" ++ str ++ "</source>" + -- note: no escape! + +blockToMediaWiki (BlockQuote blocks) = do + contents <- blockListToMediaWiki blocks return $ "<blockquote>" ++ contents ++ "</blockquote>" -blockToMediaWiki opts (Table capt aligns widths headers rows') = do +blockToMediaWiki (Table capt aligns widths headers rows') = do caption <- if null capt then return "" else do - c <- inlineListToMediaWiki opts capt + c <- inlineListToMediaWiki capt return $ "|+ " ++ trimr c ++ "\n" let headless = all null headers let allrows = if headless then rows' else headers:rows' - tableBody <- (concat . intersperse "|-\n") `fmap` - mapM (tableRowToMediaWiki opts headless aligns widths) + tableBody <- intercalate "|-\n" `fmap` + mapM (tableRowToMediaWiki headless aligns widths) (zip [1..] allrows) return $ "{|\n" ++ caption ++ tableBody ++ "|}\n" -blockToMediaWiki opts x@(BulletList items) = do - oldUseTags <- get >>= return . stUseTags - listLevel <- get >>= return . stListLevel - let useTags = oldUseTags || not (isSimpleList x) - if useTags +blockToMediaWiki x@(BulletList items) = do + tags <- fmap (|| not (isSimpleList x)) $ asks useTags + if tags then do - modify $ \s -> s { stUseTags = True } - contents <- mapM (listItemToMediaWiki opts) items - modify $ \s -> s { stUseTags = oldUseTags } + contents <- local (\ s -> s { useTags = True }) $ mapM listItemToMediaWiki items return $ "<ul>\n" ++ vcat contents ++ "</ul>\n" else do - modify $ \s -> s { stListLevel = stListLevel s ++ "*" } - contents <- mapM (listItemToMediaWiki opts) items - modify $ \s -> s { stListLevel = init (stListLevel s) } - return $ vcat contents ++ if null listLevel then "\n" else "" - -blockToMediaWiki opts x@(OrderedList attribs items) = do - oldUseTags <- get >>= return . stUseTags - listLevel <- get >>= return . stListLevel - let useTags = oldUseTags || not (isSimpleList x) - if useTags + lev <- asks listLevel + contents <- local (\s -> s { listLevel = listLevel s ++ "*" }) $ mapM listItemToMediaWiki items + return $ vcat contents ++ if null lev then "\n" else "" + +blockToMediaWiki x@(OrderedList attribs items) = do + tags <- fmap (|| not (isSimpleList x)) $ asks useTags + if tags then do - modify $ \s -> s { stUseTags = True } - contents <- mapM (listItemToMediaWiki opts) items - modify $ \s -> s { stUseTags = oldUseTags } + contents <- local (\s -> s { useTags = True }) $ mapM listItemToMediaWiki items return $ "<ol" ++ listAttribsToString attribs ++ ">\n" ++ vcat contents ++ "</ol>\n" else do - modify $ \s -> s { stListLevel = stListLevel s ++ "#" } - contents <- mapM (listItemToMediaWiki opts) items - modify $ \s -> s { stListLevel = init (stListLevel s) } - return $ vcat contents ++ if null listLevel then "\n" else "" - -blockToMediaWiki opts x@(DefinitionList items) = do - oldUseTags <- get >>= return . stUseTags - listLevel <- get >>= return . stListLevel - let useTags = oldUseTags || not (isSimpleList x) - if useTags + lev <- asks listLevel + contents <- local (\s -> s { listLevel = listLevel s ++ "#" }) $ mapM listItemToMediaWiki items + return $ vcat contents ++ if null lev then "\n" else "" + +blockToMediaWiki x@(DefinitionList items) = do + tags <- fmap (|| not (isSimpleList x)) $ asks useTags + if tags then do - modify $ \s -> s { stUseTags = True } - contents <- mapM (definitionListItemToMediaWiki opts) items - modify $ \s -> s { stUseTags = oldUseTags } + contents <- local (\s -> s { useTags = True }) $ mapM definitionListItemToMediaWiki items return $ "<dl>\n" ++ vcat contents ++ "</dl>\n" else do - modify $ \s -> s { stListLevel = stListLevel s ++ ";" } - contents <- mapM (definitionListItemToMediaWiki opts) items - modify $ \s -> s { stListLevel = init (stListLevel s) } - return $ vcat contents ++ if null listLevel then "\n" else "" + lev <- asks listLevel + contents <- local (\s -> s { listLevel = listLevel s ++ ";" }) $ mapM definitionListItemToMediaWiki items + return $ vcat contents ++ if null lev then "\n" else "" -- Auxiliary functions for lists: @@ -216,31 +212,30 @@ listAttribsToString (startnum, numstyle, _) = else "") -- | Convert bullet or ordered list item (list of blocks) to MediaWiki. -listItemToMediaWiki :: WriterOptions -> [Block] -> State WriterState String -listItemToMediaWiki opts items = do - contents <- blockListToMediaWiki opts items - useTags <- get >>= return . stUseTags - if useTags +listItemToMediaWiki :: [Block] -> MediaWikiWriter String +listItemToMediaWiki items = do + contents <- blockListToMediaWiki items + tags <- asks useTags + if tags then return $ "<li>" ++ contents ++ "</li>" else do - marker <- get >>= return . stListLevel + marker <- asks listLevel return $ marker ++ " " ++ contents -- | Convert definition list item (label, list of blocks) to MediaWiki. -definitionListItemToMediaWiki :: WriterOptions - -> ([Inline],[[Block]]) - -> State WriterState String -definitionListItemToMediaWiki opts (label, items) = do - labelText <- inlineListToMediaWiki opts label - contents <- mapM (blockListToMediaWiki opts) items - useTags <- get >>= return . stUseTags - if useTags +definitionListItemToMediaWiki :: ([Inline],[[Block]]) + -> MediaWikiWriter String +definitionListItemToMediaWiki (label, items) = do + labelText <- inlineListToMediaWiki label + contents <- mapM blockListToMediaWiki items + tags <- asks useTags + if tags then return $ "<dt>" ++ labelText ++ "</dt>\n" ++ - (intercalate "\n" $ map (\d -> "<dd>" ++ d ++ "</dd>") contents) + intercalate "\n" (map (\d -> "<dd>" ++ d ++ "</dd>") contents) else do - marker <- get >>= return . stListLevel + marker <- asks listLevel return $ marker ++ " " ++ labelText ++ "\n" ++ - (intercalate "\n" $ map (\d -> init marker ++ ": " ++ d) contents) + intercalate "\n" (map (\d -> init marker ++ ": " ++ d) contents) -- | True if the list can be handled by simple wiki markup, False if HTML tags will be needed. isSimpleList :: Block -> Bool @@ -283,25 +278,22 @@ vcat = intercalate "\n" -- Auxiliary functions for tables: -tableRowToMediaWiki :: WriterOptions - -> Bool +tableRowToMediaWiki :: Bool -> [Alignment] -> [Double] -> (Int, [[Block]]) - -> State WriterState String -tableRowToMediaWiki opts headless alignments widths (rownum, cells) = do - cells' <- mapM (\cellData -> - tableCellToMediaWiki opts headless rownum cellData) + -> MediaWikiWriter String +tableRowToMediaWiki headless alignments widths (rownum, cells) = do + cells' <- mapM (tableCellToMediaWiki headless rownum) $ zip3 alignments widths cells return $ unlines cells' -tableCellToMediaWiki :: WriterOptions - -> Bool +tableCellToMediaWiki :: Bool -> Int -> (Alignment, Double, [Block]) - -> State WriterState String -tableCellToMediaWiki opts headless rownum (alignment, width, bs) = do - contents <- blockListToMediaWiki opts bs + -> MediaWikiWriter String +tableCellToMediaWiki headless rownum (alignment, width, bs) = do + contents <- blockListToMediaWiki bs let marker = if rownum == 1 && not headless then "!" else "|" let percent w = show (truncate (100*w) :: Integer) ++ "%" let attrs = ["align=" ++ show (alignmentToString alignment) | @@ -313,7 +305,7 @@ tableCellToMediaWiki opts headless rownum (alignment, width, bs) = do else unwords attrs ++ "|" return $ marker ++ attr ++ trimr contents -alignmentToString :: Alignment -> [Char] +alignmentToString :: Alignment -> String alignmentToString alignment = case alignment of AlignLeft -> "left" AlignRight -> "right" @@ -321,94 +313,94 @@ alignmentToString alignment = case alignment of AlignDefault -> "left" -- | Convert list of Pandoc block elements to MediaWiki. -blockListToMediaWiki :: WriterOptions -- ^ Options - -> [Block] -- ^ List of block elements - -> State WriterState String -blockListToMediaWiki opts blocks = - mapM (blockToMediaWiki opts) blocks >>= return . vcat +blockListToMediaWiki :: [Block] -- ^ List of block elements + -> MediaWikiWriter String +blockListToMediaWiki blocks = + fmap vcat $ mapM blockToMediaWiki blocks -- | Convert list of Pandoc inline elements to MediaWiki. -inlineListToMediaWiki :: WriterOptions -> [Inline] -> State WriterState String -inlineListToMediaWiki opts lst = - mapM (inlineToMediaWiki opts) lst >>= return . concat +inlineListToMediaWiki :: [Inline] -> MediaWikiWriter String +inlineListToMediaWiki lst = + fmap concat $ mapM inlineToMediaWiki lst -- | Convert Pandoc inline element to MediaWiki. -inlineToMediaWiki :: WriterOptions -> Inline -> State WriterState String +inlineToMediaWiki :: Inline -> MediaWikiWriter String -inlineToMediaWiki opts (Span attrs ils) = do - contents <- inlineListToMediaWiki opts ils +inlineToMediaWiki (Span attrs ils) = do + contents <- inlineListToMediaWiki ils return $ render Nothing (tagWithAttrs "span" attrs) ++ contents ++ "</span>" -inlineToMediaWiki opts (Emph lst) = do - contents <- inlineListToMediaWiki opts lst +inlineToMediaWiki (Emph lst) = do + contents <- inlineListToMediaWiki lst return $ "''" ++ contents ++ "''" -inlineToMediaWiki opts (Strong lst) = do - contents <- inlineListToMediaWiki opts lst +inlineToMediaWiki (Strong lst) = do + contents <- inlineListToMediaWiki lst return $ "'''" ++ contents ++ "'''" -inlineToMediaWiki opts (Strikeout lst) = do - contents <- inlineListToMediaWiki opts lst +inlineToMediaWiki (Strikeout lst) = do + contents <- inlineListToMediaWiki lst return $ "<s>" ++ contents ++ "</s>" -inlineToMediaWiki opts (Superscript lst) = do - contents <- inlineListToMediaWiki opts lst +inlineToMediaWiki (Superscript lst) = do + contents <- inlineListToMediaWiki lst return $ "<sup>" ++ contents ++ "</sup>" -inlineToMediaWiki opts (Subscript lst) = do - contents <- inlineListToMediaWiki opts lst +inlineToMediaWiki (Subscript lst) = do + contents <- inlineListToMediaWiki lst return $ "<sub>" ++ contents ++ "</sub>" -inlineToMediaWiki opts (SmallCaps lst) = inlineListToMediaWiki opts lst +inlineToMediaWiki (SmallCaps lst) = inlineListToMediaWiki lst -inlineToMediaWiki opts (Quoted SingleQuote lst) = do - contents <- inlineListToMediaWiki opts lst +inlineToMediaWiki (Quoted SingleQuote lst) = do + contents <- inlineListToMediaWiki lst return $ "\8216" ++ contents ++ "\8217" -inlineToMediaWiki opts (Quoted DoubleQuote lst) = do - contents <- inlineListToMediaWiki opts lst +inlineToMediaWiki (Quoted DoubleQuote lst) = do + contents <- inlineListToMediaWiki lst return $ "\8220" ++ contents ++ "\8221" -inlineToMediaWiki opts (Cite _ lst) = inlineListToMediaWiki opts lst +inlineToMediaWiki (Cite _ lst) = inlineListToMediaWiki lst -inlineToMediaWiki _ (Code _ str) = - return $ "<code>" ++ (escapeString str) ++ "</code>" +inlineToMediaWiki (Code _ str) = + return $ "<code>" ++ escapeString str ++ "</code>" -inlineToMediaWiki _ (Str str) = return $ escapeString str +inlineToMediaWiki (Str str) = return $ escapeString str -inlineToMediaWiki _ (Math _ str) = return $ "<math>" ++ str ++ "</math>" - -- note: str should NOT be escaped +inlineToMediaWiki (Math _ str) = return $ "<math>" ++ str ++ "</math>" + -- note: str should NOT be escaped -inlineToMediaWiki _ (RawInline f str) +inlineToMediaWiki (RawInline f str) | f == Format "mediawiki" = return str | f == Format "html" = return str | otherwise = return "" -inlineToMediaWiki _ (LineBreak) = return "<br />" +inlineToMediaWiki (LineBreak) = return "<br />" -inlineToMediaWiki _ Space = return " " +inlineToMediaWiki Space = return " " -inlineToMediaWiki opts (Link txt (src, _)) = do - label <- inlineListToMediaWiki opts txt +inlineToMediaWiki (Link txt (src, _)) = do + label <- inlineListToMediaWiki txt case txt of [Str s] | escapeURI s == src -> return src - _ -> if isURI src - then return $ "[" ++ src ++ " " ++ label ++ "]" - else return $ "[[" ++ src' ++ "|" ++ label ++ "]]" + _ -> return $ if isURI src + then "[" ++ src ++ " " ++ label ++ "]" + else "[[" ++ src' ++ "|" ++ label ++ "]]" where src' = case src of '/':xs -> xs -- with leading / it's a _ -> src -- link to a help page -inlineToMediaWiki opts (Image alt (source, tit)) = do - alt' <- inlineListToMediaWiki opts alt - let txt = if (null tit) + +inlineToMediaWiki (Image alt (source, tit)) = do + alt' <- inlineListToMediaWiki alt + let txt = if null tit then if null alt then "" - else "|" ++ alt' - else "|" ++ tit + else '|' : alt' + else '|' : tit return $ "[[Image:" ++ source ++ txt ++ "]]" -inlineToMediaWiki opts (Note contents) = do - contents' <- blockListToMediaWiki opts contents +inlineToMediaWiki (Note contents) = do + contents' <- blockListToMediaWiki contents modify (\s -> s { stNotes = True }) return $ "<ref>" ++ contents' ++ "</ref>" -- note - may not work for notes with multiple blocks diff --git a/src/Text/Pandoc/Writers/Native.hs b/src/Text/Pandoc/Writers/Native.hs index 090b97433..cb821e40b 100644 --- a/src/Text/Pandoc/Writers/Native.hs +++ b/src/Text/Pandoc/Writers/Native.hs @@ -1,6 +1,6 @@ {-# LANGUAGE OverloadedStrings #-} {- -Copyright (C) 2006-2010 John MacFarlane <jgm@berkeley.edu> +Copyright (C) 2006-2014 John MacFarlane <jgm@berkeley.edu> This program is free software; you can redistribute it and/or modify it under the terms of the GNU General Public License as published by @@ -19,7 +19,7 @@ Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA {- | Module : Text.Pandoc.Writers.Native - Copyright : Copyright (C) 2006-2010 John MacFarlane + Copyright : Copyright (C) 2006-2014 John MacFarlane License : GNU GPL, version 2 or above Maintainer : John MacFarlane <jgm@berkeley.edu> diff --git a/src/Text/Pandoc/Writers/ODT.hs b/src/Text/Pandoc/Writers/ODT.hs index c3652d65d..2a4129512 100644 --- a/src/Text/Pandoc/Writers/ODT.hs +++ b/src/Text/Pandoc/Writers/ODT.hs @@ -1,6 +1,6 @@ {-# LANGUAGE ScopedTypeVariables #-} {- -Copyright (C) 2008-2010 John MacFarlane <jgm@berkeley.edu> +Copyright (C) 2008-2014 John MacFarlane <jgm@berkeley.edu> This program is free software; you can redistribute it and/or modify it under the terms of the GNU General Public License as published by @@ -19,7 +19,7 @@ Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA {- | Module : Text.Pandoc.Writers.ODT - Copyright : Copyright (C) 2008-2010 John MacFarlane + Copyright : Copyright (C) 2008-2014 John MacFarlane License : GNU GPL, version 2 or above Maintainer : John MacFarlane <jgm@berkeley.edu> @@ -30,17 +30,18 @@ Conversion of 'Pandoc' documents to ODT. -} module Text.Pandoc.Writers.ODT ( writeODT ) where import Data.IORef -import Data.List ( isPrefixOf, isSuffixOf ) +import Data.List ( isPrefixOf ) import Data.Maybe ( fromMaybe ) import Text.XML.Light.Output import Text.TeXMath import qualified Data.ByteString.Lazy as B import Text.Pandoc.UTF8 ( fromStringLazy ) import Codec.Archive.Zip +import Control.Applicative ((<$>)) import Text.Pandoc.Options ( WriterOptions(..) ) -import Text.Pandoc.Shared ( stringify, readDataFile, fetchItem, warn ) +import Text.Pandoc.Shared ( stringify, readDataFile, fetchItem', warn ) import Text.Pandoc.ImageSize ( imageSize, sizeInPoints ) -import Text.Pandoc.MIME ( getMimeType ) +import Text.Pandoc.MIME ( getMimeType, extensionFromMimeType ) import Text.Pandoc.Definition import Text.Pandoc.Walk import Text.Pandoc.Writers.Shared ( fixDisplayMath ) @@ -50,7 +51,7 @@ import Text.Pandoc.XML import Text.Pandoc.Pretty import qualified Control.Exception as E import Data.Time.Clock.POSIX ( getPOSIXTime ) -import System.FilePath ( takeExtension, takeDirectory ) +import System.FilePath ( takeExtension, takeDirectory, (<.>)) -- | Produce an ODT file from a Pandoc document. writeODT :: WriterOptions -- ^ Writer options @@ -76,11 +77,7 @@ writeODT opts doc@(Pandoc meta _) = do $ contentEntry : picEntries -- construct META-INF/manifest.xml based on archive let toFileEntry fp = case getMimeType fp of - Nothing -> if "Formula-" `isPrefixOf` fp && "/" `isSuffixOf` fp - then selfClosingTag "manifest:file-entry" - [("manifest:media-type","application/vnd.oasis.opendocument.formula") - ,("manifest:full-path",fp)] - else empty + Nothing -> empty Just m -> selfClosingTag "manifest:file-entry" [("manifest:media-type", m) ,("manifest:full-path", fp) @@ -131,17 +128,19 @@ writeODT opts doc@(Pandoc meta _) = do transformPicMath :: WriterOptions -> IORef [Entry] -> Inline -> IO Inline transformPicMath opts entriesRef (Image lab (src,_)) = do - res <- fetchItem (writerSourceURL opts) src + res <- fetchItem' (writerMediaBag opts) (writerSourceURL opts) src case res of Left (_ :: E.SomeException) -> do warn $ "Could not find image `" ++ src ++ "', skipping..." return $ Emph lab - Right (img, _) -> do + Right (img, mbMimeType) -> do let size = imageSize img let (w,h) = fromMaybe (0,0) $ sizeInPoints `fmap` size let tit' = show w ++ "x" ++ show h entries <- readIORef entriesRef - let newsrc = "Pictures/" ++ show (length entries) ++ takeExtension src + let extension = fromMaybe (takeExtension $ takeWhile (/='?') src) + (mbMimeType >>= extensionFromMimeType) + let newsrc = "Pictures/" ++ show (length entries) <.> extension let toLazy = B.fromChunks . (:[]) epochtime <- floor `fmap` getPOSIXTime let entry = toEntry newsrc epochtime $ toLazy img @@ -150,7 +149,7 @@ transformPicMath opts entriesRef (Image lab (src,_)) = do transformPicMath _ entriesRef (Math t math) = do entries <- readIORef entriesRef let dt = if t == InlineMath then DisplayInline else DisplayBlock - case texMathToMathML dt math of + case writeMathML dt <$> readTeX math of Left _ -> return $ Math t math Right r -> do let conf = useShortEmptyTags (const False) defaultConfigPP diff --git a/src/Text/Pandoc/Writers/OPML.hs b/src/Text/Pandoc/Writers/OPML.hs index f6926c1dc..dd359f3f5 100644 --- a/src/Text/Pandoc/Writers/OPML.hs +++ b/src/Text/Pandoc/Writers/OPML.hs @@ -1,5 +1,5 @@ {- -Copyright (C) 2013 John MacFarlane <jgm@berkeley.edu> +Copyright (C) 2013-2014 John MacFarlane <jgm@berkeley.edu> This program is free software; you can redistribute it and/or modify it under the terms of the GNU General Public License as published by @@ -18,7 +18,7 @@ Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA {- | Module : Text.Pandoc.Writers.OPML - Copyright : Copyright (C) 2013 John MacFarlane + Copyright : Copyright (C) 2013-2014 John MacFarlane License : GNU GPL, version 2 or above Maintainer : John MacFarlane <jgm@berkeley.edu> diff --git a/src/Text/Pandoc/Writers/OpenDocument.hs b/src/Text/Pandoc/Writers/OpenDocument.hs index 0029c3296..773d142f4 100644 --- a/src/Text/Pandoc/Writers/OpenDocument.hs +++ b/src/Text/Pandoc/Writers/OpenDocument.hs @@ -1,7 +1,7 @@ {-# LANGUAGE PatternGuards, OverloadedStrings #-} {- -Copyright (C) 2008-2010 Andrea Rossato <andrea.rossato@ing.unitn.it> -and John MacFarlane. +Copyright (C) 2008-2014 Andrea Rossato <andrea.rossato@ing.unitn.it> + and John MacFarlane. This program is free software; you can redistribute it and/or modify it under the terms of the GNU General Public License as published by @@ -20,7 +20,7 @@ Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA {- | Module : Text.Pandoc.Writers.OpenDocument - Copyright : Copyright (C) 2008-2010 Andrea Rossato and John MacFarlane + Copyright : Copyright (C) 2008-2014 Andrea Rossato and John MacFarlane License : GNU GPL, version 2 or above Maintainer : Andrea Rossato <andrea.rossato@ing.unitn.it> @@ -380,7 +380,7 @@ inlineToOpenDocument o ils | SmallCaps l <- ils = withTextStyle SmallC $ inlinesToOpenDocument o l | Quoted t l <- ils = inQuotes t <$> inlinesToOpenDocument o l | Code _ s <- ils = withTextStyle Pre $ inTextStyle $ preformatted s - | Math t s <- ils = inlinesToOpenDocument o (readTeXMath' t s) + | Math t s <- ils = inlinesToOpenDocument o (texMathToInlines t s) | Cite _ l <- ils = inlinesToOpenDocument o l | RawInline f s <- ils = if f == Format "opendocument" then return $ text s @@ -504,7 +504,7 @@ paraStyle parent attrs = do tight = if t then [ ("fo:margin-top" , "0in" ) , ("fo:margin-bottom" , "0in" )] else [] - indent = if (i /= 0 || b) + indent = if (i /= 0 || b) then [ ("fo:margin-left" , indentVal) , ("fo:margin-right" , "0in" ) , ("fo:text-indent" , "0in" ) @@ -534,7 +534,7 @@ paraTableStyles t s (a:xs) [ ("fo:text-align", x) , ("style:justify-single-word", "false")] -data TextStyle = Italic | Bold | Strike | Sub | Sup | SmallC | Pre +data TextStyle = Italic | Bold | Strike | Sub | Sup | SmallC | Pre deriving ( Eq,Ord ) textStyleAttr :: TextStyle -> [(String,String)] diff --git a/src/Text/Pandoc/Writers/Org.hs b/src/Text/Pandoc/Writers/Org.hs index d318c5f6a..414883b29 100644 --- a/src/Text/Pandoc/Writers/Org.hs +++ b/src/Text/Pandoc/Writers/Org.hs @@ -1,6 +1,7 @@ {-# LANGUAGE OverloadedStrings #-} {- -Copyright (C) 2006-2010 Puneeth Chaganti <punchagan@gmail.com> +Copyright (C) 2010-2014 Puneeth Chaganti <punchagan@gmail.com> + and John MacFarlane <jgm@berkeley.edu> This program is free software; you can redistribute it and/or modify it under the terms of the GNU General Public License as published by @@ -19,7 +20,7 @@ Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA {- | Module : Text.Pandoc.Writers.Org - Copyright : Copyright (C) 2010 Puneeth Chaganti + Copyright : Copyright (C) 2010-2014 Puneeth Chaganti and John MacFarlane License : GNU GPL, version 2 or above Maintainer : Puneeth Chaganti <punchagan@gmail.com> @@ -237,6 +238,8 @@ inlineListToOrg lst = mapM inlineToOrg lst >>= return . hcat -- | Convert Pandoc inline element to Org. inlineToOrg :: Inline -> State WriterState Doc +inlineToOrg (Span (uid, [], []) []) = + return $ "<<" <> text uid <> ">>" inlineToOrg (Span _ lst) = inlineListToOrg lst inlineToOrg (Emph lst) = do @@ -271,7 +274,7 @@ inlineToOrg (Math t str) = do else "$$" <> text str <> "$$" inlineToOrg (RawInline f str) | f == "tex" || f == "latex" = return $ text str inlineToOrg (RawInline _ _) = return empty -inlineToOrg (LineBreak) = return cr -- there's no line break in Org +inlineToOrg (LineBreak) = return (text "\\\\" <> cr) inlineToOrg Space = return space inlineToOrg (Link txt (src, _)) = do case txt of diff --git a/src/Text/Pandoc/Writers/RST.hs b/src/Text/Pandoc/Writers/RST.hs index 37bb66632..5ba4c9983 100644 --- a/src/Text/Pandoc/Writers/RST.hs +++ b/src/Text/Pandoc/Writers/RST.hs @@ -1,6 +1,6 @@ {-# LANGUAGE OverloadedStrings #-} {- -Copyright (C) 2006-2010 John MacFarlane <jgm@berkeley.edu> +Copyright (C) 2006-2014 John MacFarlane <jgm@berkeley.edu> This program is free software; you can redistribute it and/or modify it under the terms of the GNU General Public License as published by @@ -19,7 +19,7 @@ Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA {- | Module : Text.Pandoc.Writers.RST - Copyright : Copyright (C) 2006-2010 John MacFarlane + Copyright : Copyright (C) 2006-2014 John MacFarlane License : GNU GPL, version 2 or above Maintainer : John MacFarlane <jgm@berkeley.edu> @@ -37,7 +37,8 @@ import Text.Pandoc.Shared import Text.Pandoc.Writers.Shared import Text.Pandoc.Templates (renderTemplate') import Text.Pandoc.Builder (deleteMeta) -import Data.List ( isPrefixOf, intersperse, transpose ) +import Data.Maybe (fromMaybe) +import Data.List ( isPrefixOf, stripPrefix, intersperse, transpose ) import Network.URI (isURI) import Text.Pandoc.Pretty import Control.Monad.State @@ -172,11 +173,11 @@ blockToRST (Para [Image txt (src,'f':'i':'g':':':tit)]) = do capt <- inlineListToRST txt let fig = "figure:: " <> text src let alt = ":alt: " <> if null tit then capt else text tit - return $ hang 3 ".. " $ fig $$ alt $+$ capt $$ blankline + return $ hang 3 ".. " (fig $$ alt $+$ capt) $$ blankline blockToRST (Para inlines) - | LineBreak `elem` inlines = do -- use line block if LineBreaks + | LineBreak `elem` inlines = do -- use line block if LineBreaks lns <- mapM inlineListToRST $ splitBy (==LineBreak) inlines - return $ (vcat $ map (text "| " <>) lns) <> blankline + return $ (vcat $ map (hang 2 (text "| ")) lns) <> blankline | otherwise = do contents <- inlineListToRST inlines return $ contents <> blankline @@ -219,11 +220,15 @@ blockToRST (Table caption _ widths headers rows) = do else blankline <> text "Table: " <> caption' headers' <- mapM blockListToRST headers rawRows <- mapM (mapM blockListToRST) rows - let isSimple = all (==0) widths && all (all (\bs -> length bs <= 1)) rows + -- let isSimpleCell [Plain _] = True + -- isSimpleCell [Para _] = True + -- isSimpleCell [] = True + -- isSimpleCell _ = False + -- let isSimple = all (==0) widths && all (all isSimpleCell) rows let numChars = maximum . map offset opts <- get >>= return . stOptions let widthsInChars = - if isSimple + if all (== 0) widths then map ((+2) . numChars) $ transpose (headers' : rawRows) else map (floor . (fromIntegral (writerColumns opts) *)) widths let hpipeBlocks blocks = hcat [beg, middle, end] @@ -234,8 +239,7 @@ blockToRST (Table caption _ widths headers rows) = do middle = hcat $ intersperse sep' blocks let makeRow = hpipeBlocks . zipWith lblock widthsInChars let head' = makeRow headers' - rows' <- mapM (\row -> do cols <- mapM blockListToRST row - return $ makeRow cols) rows + let rows' = map makeRow rawRows let border ch = char '+' <> char ch <> (hcat $ intersperse (char ch <> char '+' <> char ch) $ map (\l -> text $ replicate l ch) widthsInChars) <> @@ -248,7 +252,7 @@ blockToRST (Table caption _ widths headers rows) = do blockToRST (BulletList items) = do contents <- mapM bulletListItemToRST items -- ensure that sublists have preceding blank line - return $ blankline $$ vcat contents $$ blankline + return $ blankline $$ chomp (vcat contents) $$ blankline blockToRST (OrderedList (start, style', delim) items) = do let markers = if start == 1 && style' == DefaultStyle && delim == DefaultDelim then take (length items) $ repeat "#." @@ -260,11 +264,11 @@ blockToRST (OrderedList (start, style', delim) items) = do contents <- mapM (\(item, num) -> orderedListItemToRST item num) $ zip markers' items -- ensure that sublists have preceding blank line - return $ blankline $$ vcat contents $$ blankline + return $ blankline $$ chomp (vcat contents) $$ blankline blockToRST (DefinitionList items) = do contents <- mapM definitionListItemToRST items -- ensure that sublists have preceding blank line - return $ blankline $$ vcat contents $$ blankline + return $ blankline $$ chomp (vcat contents) $$ blankline -- | Convert bullet list item (list of blocks) to RST. bulletListItemToRST :: [Block] -> State WriterState Doc @@ -397,7 +401,7 @@ inlineToRST (Link [Str str] (src, _)) if "mailto:" `isPrefixOf` src then src == escapeURI ("mailto:" ++ str) else src == escapeURI str = do - let srcSuffix = if isPrefixOf "mailto:" src then drop 7 src else src + let srcSuffix = fromMaybe src (stripPrefix "mailto:" src) return $ text srcSuffix inlineToRST (Link [Image alt (imgsrc,imgtit)] (src, _tit)) = do label <- registerImage alt (imgsrc,imgtit) (Just src) @@ -422,7 +426,7 @@ inlineToRST (Image alternate (source, tit)) = do return $ "|" <> label <> "|" inlineToRST (Note contents) = do -- add to notes in state - notes <- get >>= return . stNotes + notes <- gets stNotes modify $ \st -> st { stNotes = contents:notes } let ref = show $ (length notes) + 1 return $ " [" <> text ref <> "]_" diff --git a/src/Text/Pandoc/Writers/RTF.hs b/src/Text/Pandoc/Writers/RTF.hs index fb935fa6a..43405ce3c 100644 --- a/src/Text/Pandoc/Writers/RTF.hs +++ b/src/Text/Pandoc/Writers/RTF.hs @@ -1,5 +1,5 @@ {- -Copyright (C) 2006-2010 John MacFarlane <jgm@berkeley.edu> +Copyright (C) 2006-2014 John MacFarlane <jgm@berkeley.edu> This program is free software; you can redistribute it and/or modify it under the terms of the GNU General Public License as published by @@ -18,7 +18,7 @@ Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA {- | Module : Text.Pandoc.Writers.RTF - Copyright : Copyright (C) 2006-2010 John MacFarlane + Copyright : Copyright (C) 2006-2014 John MacFarlane License : GNU GPL, version 2 or above Maintainer : John MacFarlane <jgm@berkeley.edu> @@ -36,50 +36,64 @@ import Text.Pandoc.Readers.TeXMath import Text.Pandoc.Templates (renderTemplate') import Text.Pandoc.Walk import Data.List ( isSuffixOf, intercalate ) -import Data.Char ( ord, chr, isDigit, toLower ) -import System.FilePath ( takeExtension ) +import Data.Char ( ord, chr, isDigit ) import qualified Data.ByteString as B +import qualified Data.Map as M import Text.Printf ( printf ) -import Network.URI ( isURI, unEscapeString ) -import qualified Control.Exception as E +import Text.Pandoc.ImageSize --- | Convert Image inlines into a raw RTF embedded image, read from a file. +-- | Convert Image inlines into a raw RTF embedded image, read from a file, +-- or a MediaBag, or the internet. -- If file not found or filetype not jpeg or png, leave the inline unchanged. -rtfEmbedImage :: Inline -> IO Inline -rtfEmbedImage x@(Image _ (src,_)) = do - let ext = map toLower (takeExtension src) - if ext `elem` [".jpg",".jpeg",".png"] && not (isURI src) - then do - let src' = unEscapeString src - imgdata <- E.catch (B.readFile src') - (\e -> let _ = (e :: E.SomeException) in return B.empty) - let bytes = map (printf "%02x") $ B.unpack imgdata - let filetype = case ext of - ".jpg" -> "\\jpegblip" - ".jpeg" -> "\\jpegblip" - ".png" -> "\\pngblip" - _ -> error "Unknown file type" - let raw = "{\\pict" ++ filetype ++ " " ++ concat bytes ++ "}" - return $ if B.null imgdata - then x - else RawInline (Format "rtf") raw - else return x -rtfEmbedImage x = return x +rtfEmbedImage :: WriterOptions -> Inline -> IO Inline +rtfEmbedImage opts x@(Image _ (src,_)) = do + result <- fetchItem' (writerMediaBag opts) (writerSourceURL opts) src + case result of + Right (imgdata, Just mime) + | mime == "image/jpeg" || mime == "image/png" -> do + let bytes = map (printf "%02x") $ B.unpack imgdata + let filetype = case mime of + "image/jpeg" -> "\\jpegblip" + "image/png" -> "\\pngblip" + _ -> error "Unknown file type" + let sizeSpec = case imageSize imgdata of + Nothing -> "" + Just sz -> "\\picw" ++ show xpx ++ + "\\pich" ++ show ypx ++ + "\\picwgoal" ++ show (xpt * 20) + ++ "\\pichgoal" ++ show (ypt * 20) + -- twip = 1/1440in = 1/20pt + where (xpx, ypx) = sizeInPixels sz + (xpt, ypt) = sizeInPoints sz + let raw = "{\\pict" ++ filetype ++ sizeSpec ++ " " ++ + concat bytes ++ "}" + return $ if B.null imgdata + then x + else RawInline (Format "rtf") raw + _ -> return x +rtfEmbedImage _ x = return x -- | Convert Pandoc to a string in rich text format, with -- images embedded as encoded binary data. writeRTFWithEmbeddedImages :: WriterOptions -> Pandoc -> IO String writeRTFWithEmbeddedImages options doc = - writeRTF options `fmap` walkM rtfEmbedImage doc + writeRTF options `fmap` walkM (rtfEmbedImage options) doc -- | Convert Pandoc to a string in rich text format. writeRTF :: WriterOptions -> Pandoc -> String -writeRTF options (Pandoc meta blocks) = +writeRTF options (Pandoc meta@(Meta metamap) blocks) = let spacer = not $ all null $ docTitle meta : docDate meta : docAuthors meta + toPlain (MetaBlocks [Para ils]) = MetaInlines ils + toPlain x = x + -- adjust title, author, date so we don't get para inside para + meta' = Meta $ M.adjust toPlain "title" + . M.adjust toPlain "author" + . M.adjust toPlain "date" + $ metamap Just metadata = metaToJSON options (Just . concatMap (blockToRTF 0 AlignDefault)) (Just . inlineListToRTF) - meta + meta' body = concatMap (blockToRTF 0 AlignDefault) blocks isTOCHeader (Header lev _ _) = lev <= writerTOCDepth options isTOCHeader _ = False @@ -259,7 +273,7 @@ tableRowToRTF header indent aligns sizes' cols = tableItemToRTF :: Int -> Alignment -> [Block] -> String tableItemToRTF indent alignment item = let contents = concatMap (blockToRTF indent alignment) item - in "{\\intbl " ++ contents ++ "\\cell}\n" + in "{" ++ substitute "\\pard" "\\pard\\intbl" contents ++ "\\cell}\n" -- | Ensure that there's the same amount of space after compact -- lists as after regular lists. @@ -324,7 +338,7 @@ inlineToRTF (Quoted DoubleQuote lst) = "\\u8220\"" ++ (inlineListToRTF lst) ++ "\\u8221\"" inlineToRTF (Code _ str) = "{\\f1 " ++ (codeStringToRTF str) ++ "}" inlineToRTF (Str str) = stringToRTF str -inlineToRTF (Math t str) = inlineListToRTF $ readTeXMath' t str +inlineToRTF (Math t str) = inlineListToRTF $ texMathToInlines t str inlineToRTF (Cite _ lst) = inlineListToRTF lst inlineToRTF (RawInline f str) | f == Format "rtf" = str diff --git a/src/Text/Pandoc/Writers/Shared.hs b/src/Text/Pandoc/Writers/Shared.hs index 604aac1c9..800e741a4 100644 --- a/src/Text/Pandoc/Writers/Shared.hs +++ b/src/Text/Pandoc/Writers/Shared.hs @@ -1,6 +1,6 @@ {-# LANGUAGE OverloadedStrings #-} {- -Copyright (C) 2013 John MacFarlane <jgm@berkeley.edu> +Copyright (C) 2013-2014 John MacFarlane <jgm@berkeley.edu> This program is free software; you can redistribute it and/or modify it under the terms of the GNU General Public License as published by @@ -19,7 +19,7 @@ Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA {- | Module : Text.Pandoc.Writers.Shared - Copyright : Copyright (C) 2013 John MacFarlane + Copyright : Copyright (C) 2013-2014 John MacFarlane License : GNU GPL, version 2 or above Maintainer : John MacFarlane <jgm@berkeley.edu> diff --git a/src/Text/Pandoc/Writers/Texinfo.hs b/src/Text/Pandoc/Writers/Texinfo.hs index bf3df8035..8ac717bab 100644 --- a/src/Text/Pandoc/Writers/Texinfo.hs +++ b/src/Text/Pandoc/Writers/Texinfo.hs @@ -1,6 +1,6 @@ {-# LANGUAGE OverloadedStrings #-} {- -Copyright (C) 2008-2010 John MacFarlane and Peter Wang +Copyright (C) 2008-2014 John MacFarlane and Peter Wang This program is free software; you can redistribute it and/or modify it under the terms of the GNU General Public License as published by @@ -19,7 +19,7 @@ Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA {- | Module : Text.Pandoc.Writers.Texinfo - Copyright : Copyright (C) 2008-2010 John MacFarlane and Peter Wang + Copyright : Copyright (C) 2008-2014 John MacFarlane and Peter Wang License : GNU GPL, version 2 or above Maintainer : John MacFarlane <jgm@berkeley.edu> diff --git a/src/Text/Pandoc/Writers/Textile.hs b/src/Text/Pandoc/Writers/Textile.hs index 95aedf780..05eb50349 100644 --- a/src/Text/Pandoc/Writers/Textile.hs +++ b/src/Text/Pandoc/Writers/Textile.hs @@ -1,5 +1,5 @@ {- -Copyright (C) 2010 John MacFarlane <jgm@berkeley.edu> +Copyright (C) 2010-2014 John MacFarlane <jgm@berkeley.edu> This program is free software; you can redistribute it and/or modify it under the terms of the GNU General Public License as published by @@ -18,7 +18,7 @@ Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA {- | Module : Text.Pandoc.Writers.Textile - Copyright : Copyright (C) 2010 John MacFarlane + Copyright : Copyright (C) 2010-2014 John MacFarlane License : GNU GPL, version 2 or above Maintainer : John MacFarlane <jgm@berkeley.edu> @@ -39,6 +39,7 @@ import Text.Pandoc.Templates (renderTemplate') import Text.Pandoc.XML ( escapeStringForXML ) import Data.List ( intercalate ) import Control.Monad.State +import Control.Applicative ((<$>)) import Data.Char ( isSpace ) data WriterState = WriterState { @@ -164,14 +165,22 @@ blockToTextile opts (BlockQuote blocks) = do return $ "<blockquote>\n\n" ++ contents ++ "\n</blockquote>\n" blockToTextile opts (Table [] aligns widths headers rows') | - all (==0) widths && all (`elem` [AlignLeft,AlignDefault]) aligns = do + all (==0) widths = do hs <- mapM (liftM (("_. " ++) . stripTrailingNewlines) . blockListToTextile opts) headers let cellsToRow cells = "|" ++ intercalate "|" cells ++ "|" - let header = if all null headers then "" else cellsToRow hs - let rowToCells = mapM (liftM stripTrailingNewlines . blockListToTextile opts) + let header = if all null headers then "" else cellsToRow hs ++ "\n" + let blocksToCell (align, bs) = do + contents <- stripTrailingNewlines <$> blockListToTextile opts bs + let alignMarker = case align of + AlignLeft -> "<. " + AlignRight -> ">. " + AlignCenter -> "=. " + AlignDefault -> "" + return $ alignMarker ++ contents + let rowToCells = mapM blocksToCell . zip aligns bs <- mapM rowToCells rows' let body = unlines $ map cellsToRow bs - return $ header ++ "\n" ++ body ++ "\n" + return $ header ++ body blockToTextile opts (Table capt aligns widths headers rows') = do let alignStrings = map alignmentToString aligns @@ -404,8 +413,10 @@ inlineToTextile _ (Str str) = return $ escapeStringForTextile str inlineToTextile _ (Math _ str) = return $ "<span class=\"math\">" ++ escapeStringForXML str ++ "</math>" -inlineToTextile _ (RawInline f str) +inlineToTextile opts (RawInline f str) | f == Format "html" || f == Format "textile" = return str + | (f == Format "latex" || f == Format "tex") && + isEnabled Ext_raw_tex opts = return str | otherwise = return "" inlineToTextile _ (LineBreak) = return "\n" diff --git a/src/Text/Pandoc/XML.hs b/src/Text/Pandoc/XML.hs index c11af9a19..8000368aa 100644 --- a/src/Text/Pandoc/XML.hs +++ b/src/Text/Pandoc/XML.hs @@ -1,5 +1,5 @@ {- -Copyright (C) 2006-2010 John MacFarlane <jgm@berkeley.edu> +Copyright (C) 2006-2014 John MacFarlane <jgm@berkeley.edu> This program is free software; you can redistribute it and/or modify it under the terms of the GNU General Public License as published by @@ -18,7 +18,7 @@ Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA {- | Module : Text.Pandoc.XML - Copyright : Copyright (C) 2006-2010 John MacFarlane + Copyright : Copyright (C) 2006-2014 John MacFarlane License : GNU GPL, version 2 or above Maintainer : John MacFarlane <jgm@berkeley.edu> diff --git a/tests/Tests/Arbitrary.hs b/tests/Tests/Arbitrary.hs index 31c0cb46a..3675d97bf 100644 --- a/tests/Tests/Arbitrary.hs +++ b/tests/Tests/Arbitrary.hs @@ -49,7 +49,7 @@ arbInline n = frequency $ [ (60, liftM Str realString) , (10, liftM Strikeout $ arbInlines (n-1)) , (10, liftM Superscript $ arbInlines (n-1)) , (10, liftM Subscript $ arbInlines (n-1)) --- , (10, liftM SmallCaps $ arbInlines (n-1)) + , (10, liftM SmallCaps $ arbInlines (n-1)) , (10, do x1 <- arbitrary x2 <- arbInlines (n-1) return $ Quoted x1 x2) @@ -64,6 +64,7 @@ arbInline n = frequency $ [ (60, liftM Str realString) x3 <- realString x2 <- liftM escapeURI realString return $ Image x1 (x2,x3)) + , (2, liftM2 Cite arbitrary (arbInlines 1)) , (2, liftM Note $ resize 3 $ listOf1 $ arbBlock (n-1)) ] @@ -111,7 +112,6 @@ instance Arbitrary Pandoc where arbitrary = resize 8 $ liftM normalize $ liftM2 Pandoc arbitrary arbitrary -{- instance Arbitrary CitationMode where arbitrary = do x <- choose (0 :: Int, 2) @@ -123,14 +123,13 @@ instance Arbitrary CitationMode where instance Arbitrary Citation where arbitrary - = do x1 <- liftM (filter (`notElem` ",;]@ \t\n")) arbitrary - x2 <- arbitrary - x3 <- arbitrary + = do x1 <- listOf $ elements $ ['a'..'z'] ++ ['0'..'9'] ++ ['_'] + x2 <- arbInlines 1 + x3 <- arbInlines 1 x4 <- arbitrary x5 <- arbitrary x6 <- arbitrary return (Citation x1 x2 x3 x4 x5 x6) --} instance Arbitrary MathType where arbitrary diff --git a/tests/Tests/Old.hs b/tests/Tests/Old.hs index a16784889..5bdf325b1 100644 --- a/tests/Tests/Old.hs +++ b/tests/Tests/Old.hs @@ -3,10 +3,10 @@ module Tests.Old (tests) where import Test.Framework (testGroup, Test ) import Test.Framework.Providers.HUnit import Test.HUnit ( assertBool ) -import System.Environment ( getArgs ) +import System.Environment.Executable (getExecutablePath) import System.IO ( openTempFile, stderr ) import System.Process ( runProcess, waitForProcess ) -import System.FilePath ( (</>), (<.>) ) +import System.FilePath ( (</>), (<.>), takeDirectory, splitDirectories, joinPath ) import System.Directory import System.Exit import Data.Algorithm.Diff @@ -111,12 +111,12 @@ tests = [ testGroup "markdown" "testsuite.native" "testsuite.native" ] , testGroup "fb2" - [ fb2WriterTest "basic" [] "fb2.basic.markdown" "fb2.basic.fb2" - , fb2WriterTest "titles" [] "fb2.titles.markdown" "fb2.titles.fb2" - , fb2WriterTest "images" [] "fb2.images.markdown" "fb2.images.fb2" - , fb2WriterTest "images-embedded" [] "fb2.images-embedded.html" "fb2.images-embedded.fb2" + [ fb2WriterTest "basic" [] "fb2/basic.markdown" "fb2/basic.fb2" + , fb2WriterTest "titles" [] "fb2/titles.markdown" "fb2/titles.fb2" + , fb2WriterTest "images" [] "fb2/images.markdown" "fb2/images.fb2" + , fb2WriterTest "images-embedded" [] "fb2/images-embedded.html" "fb2/images-embedded.fb2" + , fb2WriterTest "math" [] "fb2/math.markdown" "fb2/math.fb2" , fb2WriterTest "tables" [] "tables.native" "tables.fb2" - , fb2WriterTest "math" [] "fb2.math.markdown" "fb2.math.fb2" , fb2WriterTest "testsuite" [] "testsuite.native" "writer.fb2" ] , testGroup "mediawiki" @@ -124,6 +124,15 @@ tests = [ testGroup "markdown" , test "reader" ["-r", "mediawiki", "-w", "native", "-s"] "mediawiki-reader.wiki" "mediawiki-reader.native" ] + , testGroup "dokuwiki" + [ testGroup "writer" $ writerTests "dokuwiki" + , test "inline_formatting" ["-r", "native", "-w", "dokuwiki", "-s"] + "dokuwiki_inline_formatting.native" "dokuwiki_inline_formatting.dokuwiki" + , test "multiblock table" ["-r", "native", "-w", "dokuwiki", "-s"] + "dokuwiki_multiblock_table.native" "dokuwiki_multiblock_table.dokuwiki" + , test "external images" ["-r", "native", "-w", "dokuwiki", "-s"] + "dokuwiki_external_images.native" "dokuwiki_external_images.dokuwiki" + ] , testGroup "opml" [ test "basic" ["-r", "native", "-w", "opml", "--columns=78", "-s"] "testsuite.native" "writer.opml" @@ -131,11 +140,26 @@ tests = [ testGroup "markdown" "opml-reader.opml" "opml-reader.native" ] , testGroup "haddock" - [ test "reader" ["-r", "haddock", "-w", "native", "-s"] + [ testGroup "writer" $ writerTests "haddock" + , test "reader" ["-r", "haddock", "-w", "native", "-s"] "haddock-reader.haddock" "haddock-reader.native" ] + , testGroup "txt2tags" + [ test "reader" ["-r", "t2t", "-w", "native", "-s"] + "txt2tags.t2t" "txt2tags.native" ] + , testGroup "epub" [ + test "features" ["-r", "epub", "-w", "native"] + "epub/features.epub" "epub/features.native" + , test "wasteland" ["-r", "epub", "-w", "native"] + "epub/wasteland.epub" "epub/wasteland.native" + , test "formatting" ["-r", "epub", "-w", "native"] + "epub/formatting.epub" "epub/formatting.native" + ] + , testGroup "twiki" + [ test "reader" ["-r", "twiki", "-w", "native", "-s"] + "twiki-reader.twiki" "twiki-reader.native" ] , testGroup "other writers" $ map (\f -> testGroup f $ writerTests f) - [ "opendocument" , "context" , "texinfo" + [ "opendocument" , "context" , "texinfo", "icml" , "man" , "plain" , "rtf", "org", "asciidoc" ] ] @@ -175,7 +199,7 @@ s5WriterTest :: String -> [String] -> String -> Test s5WriterTest modifier opts format = test (format ++ " writer (" ++ modifier ++ ")") (["-r", "native", "-w", format] ++ opts) - "s5.native" ("s5." ++ modifier <.> "html") + "s5.native" ("s5-" ++ modifier <.> "html") fb2WriterTest :: String -> [String] -> String -> String -> Test fb2WriterTest title opts inputfile normfile = @@ -206,11 +230,18 @@ testWithNormalize :: (String -> String) -- ^ Normalize function for output -> FilePath -- ^ Norm (for test results) filepath -> Test testWithNormalize normalizer testname opts inp norm = testCase testname $ do - args <- getArgs - let buildDir = case args of - (x:_) -> ".." </> x - _ -> error "test-pandoc: missing buildDir argument" - let pandocPath = buildDir </> "pandoc" </> "pandoc" + -- find pandoc executable relative to test-pandoc + -- First, try in same directory (e.g. if both in ~/.cabal/bin) + -- Second, try ../pandoc (e.g. if in dist/XXX/build/test-pandoc) + pandocPath <- do + testExePath <- getExecutablePath + let testExeDir = takeDirectory testExePath + found <- doesFileExist (testExeDir </> "pandoc") + return $ if found + then testExeDir </> "pandoc" + else case splitDirectories testExeDir of + [] -> error "test-pandoc: empty testExeDir" + xs -> joinPath (init xs) </> "pandoc" </> "pandoc" (outputPath, hOut) <- openTempFile "" "pandoc-test" let inpPath = inp let normPath = norm diff --git a/tests/Tests/Readers/Docx.hs b/tests/Tests/Readers/Docx.hs new file mode 100644 index 000000000..2963c34da --- /dev/null +++ b/tests/Tests/Readers/Docx.hs @@ -0,0 +1,245 @@ +module Tests.Readers.Docx (tests) where + +import Text.Pandoc.Options +import Text.Pandoc.Readers.Native +import Text.Pandoc.Definition +import Tests.Helpers +import Test.Framework +import Test.HUnit (assertBool) +import Test.Framework.Providers.HUnit +import qualified Data.ByteString.Lazy as B +import Text.Pandoc.Readers.Docx +import Text.Pandoc.Writers.Native (writeNative) +import qualified Data.Map as M +import Text.Pandoc.MediaBag (MediaBag, lookupMedia, mediaDirectory) +import Codec.Archive.Zip + +-- We define a wrapper around pandoc that doesn't normalize in the +-- tests. Since we do our own normalization, we want to make sure +-- we're doing it right. + +data NoNormPandoc = NoNormPandoc {unNoNorm :: Pandoc} + deriving Show + +noNorm :: Pandoc -> NoNormPandoc +noNorm = NoNormPandoc + +instance ToString NoNormPandoc where + toString d = writeNative def{ writerStandalone = s } $ toPandoc d + where s = case d of + NoNormPandoc (Pandoc (Meta m) _) + | M.null m -> False + | otherwise -> True + +instance ToPandoc NoNormPandoc where + toPandoc = unNoNorm + +compareOutput :: ReaderOptions + -> FilePath + -> FilePath + -> IO (NoNormPandoc, NoNormPandoc) +compareOutput opts docxFile nativeFile = do + df <- B.readFile docxFile + nf <- Prelude.readFile nativeFile + let (p, _) = readDocx opts df + return $ (noNorm p, noNorm (readNative nf)) + +testCompareWithOptsIO :: ReaderOptions -> String -> FilePath -> FilePath -> IO Test +testCompareWithOptsIO opts name docxFile nativeFile = do + (dp, np) <- compareOutput opts docxFile nativeFile + return $ test id name (dp, np) + +testCompareWithOpts :: ReaderOptions -> String -> FilePath -> FilePath -> Test +testCompareWithOpts opts name docxFile nativeFile = + buildTest $ testCompareWithOptsIO opts name docxFile nativeFile + +testCompare :: String -> FilePath -> FilePath -> Test +testCompare = testCompareWithOpts def + +getMedia :: FilePath -> FilePath -> IO (Maybe B.ByteString) +getMedia archivePath mediaPath = do + zf <- B.readFile archivePath >>= return . toArchive + return $ findEntryByPath ("word/" ++ mediaPath) zf >>= (Just . fromEntry) + +compareMediaPathIO :: FilePath -> MediaBag -> FilePath -> IO Bool +compareMediaPathIO mediaPath mediaBag docxPath = do + docxMedia <- getMedia docxPath mediaPath + let mbBS = case lookupMedia mediaPath mediaBag of + Just (_, bs) -> bs + Nothing -> error ("couldn't find " ++ + mediaPath ++ + " in media bag") + docxBS = case docxMedia of + Just bs -> bs + Nothing -> error ("couldn't find " ++ + mediaPath ++ + " in media bag") + return $ mbBS == docxBS + +compareMediaBagIO :: FilePath -> IO Bool +compareMediaBagIO docxFile = do + df <- B.readFile docxFile + let (_, mb) = readDocx def df + bools <- mapM + (\(fp, _, _) -> compareMediaPathIO fp mb docxFile) + (mediaDirectory mb) + return $ and bools + +testMediaBagIO :: String -> FilePath -> IO Test +testMediaBagIO name docxFile = do + outcome <- compareMediaBagIO docxFile + return $ testCase name (assertBool + ("Media didn't match media bag in file " ++ docxFile) + outcome) + +testMediaBag :: String -> FilePath -> Test +testMediaBag name docxFile = buildTest $ testMediaBagIO name docxFile + +tests :: [Test] +tests = [ testGroup "inlines" + [ testCompare + "font formatting" + "docx/inline_formatting.docx" + "docx/inline_formatting.native" + , testCompare + "font formatting with character styles" + "docx/char_styles.docx" + "docx/char_styles.native" + , testCompare + "hyperlinks" + "docx/links.docx" + "docx/links.native" + , testCompare + "inline image" + "docx/image.docx" + "docx/image_no_embed.native" + , testCompare + "inline image in links" + "docx/inline_images.docx" + "docx/inline_images.native" + , testCompare + "handling unicode input" + "docx/unicode.docx" + "docx/unicode.native" + , testCompare + "literal tabs" + "docx/tabs.docx" + "docx/tabs.native" + , testCompare + "normalizing inlines" + "docx/normalize.docx" + "docx/normalize.native" + , testCompare + "normalizing inlines deep inside blocks" + "docx/deep_normalize.docx" + "docx/deep_normalize.native" + , testCompare + "move trailing spaces outside of formatting" + "docx/trailing_spaces_in_formatting.docx" + "docx/trailing_spaces_in_formatting.native" + , testCompare + "inline code (with VerbatimChar style)" + "docx/inline_code.docx" + "docx/inline_code.native" + ] + , testGroup "blocks" + [ testCompare + "headers" + "docx/headers.docx" + "docx/headers.native" + , testCompare + "headers already having auto identifiers" + "docx/already_auto_ident.docx" + "docx/already_auto_ident.native" + , testCompare + "numbered headers automatically made into list" + "docx/numbered_header.docx" + "docx/numbered_header.native" + , testCompare + "i18n blocks (headers and blockquotes)" + "docx/i18n_blocks.docx" + "docx/i18n_blocks.native" + , testCompare + "lists" + "docx/lists.docx" + "docx/lists.native" + , testCompare + "definition lists" + "docx/definition_list.docx" + "docx/definition_list.native" + , testCompare + "footnotes and endnotes" + "docx/notes.docx" + "docx/notes.native" + , testCompare + "blockquotes (parsing indent as blockquote)" + "docx/block_quotes.docx" + "docx/block_quotes_parse_indent.native" + , testCompare + "hanging indents" + "docx/hanging_indent.docx" + "docx/hanging_indent.native" + , testCompare + "tables" + "docx/tables.docx" + "docx/tables.native" + , testCompare + "code block" + "docx/codeblock.docx" + "docx/codeblock.native" + , testCompare + "dropcap paragraphs" + "docx/drop_cap.docx" + "docx/drop_cap.native" + ] + , testGroup "track changes" + [ testCompare + "insertion (default)" + "docx/track_changes_insertion.docx" + "docx/track_changes_insertion_accept.native" + , testCompareWithOpts def{readerTrackChanges=AcceptChanges} + "insert insertion (accept)" + "docx/track_changes_insertion.docx" + "docx/track_changes_insertion_accept.native" + , testCompareWithOpts def{readerTrackChanges=RejectChanges} + "remove insertion (reject)" + "docx/track_changes_insertion.docx" + "docx/track_changes_insertion_reject.native" + , testCompare + "deletion (default)" + "docx/track_changes_deletion.docx" + "docx/track_changes_deletion_accept.native" + , testCompareWithOpts def{readerTrackChanges=AcceptChanges} + "remove deletion (accept)" + "docx/track_changes_deletion.docx" + "docx/track_changes_deletion_accept.native" + , testCompareWithOpts def{readerTrackChanges=RejectChanges} + "insert deletion (reject)" + "docx/track_changes_deletion.docx" + "docx/track_changes_deletion_reject.native" + , testCompareWithOpts def{readerTrackChanges=AllChanges} + "keep insertion (all)" + "docx/track_changes_deletion.docx" + "docx/track_changes_deletion_all.native" + , testCompareWithOpts def{readerTrackChanges=AllChanges} + "keep deletion (all)" + "docx/track_changes_deletion.docx" + "docx/track_changes_deletion_all.native" + ] + , testGroup "media" + [ testMediaBag + "image extraction" + "docx/image.docx" + ] + , testGroup "metadata" + [ testCompareWithOpts def{readerStandalone=True} + "metadata fields" + "docx/metadata.docx" + "docx/metadata.native" + , testCompareWithOpts def{readerStandalone=True} + "stop recording metadata with normal text" + "docx/metadata_after_normal.docx" + "docx/metadata_after_normal.native" + ] + + ] diff --git a/tests/Tests/Readers/EPUB.hs b/tests/Tests/Readers/EPUB.hs new file mode 100644 index 000000000..0d19a8400 --- /dev/null +++ b/tests/Tests/Readers/EPUB.hs @@ -0,0 +1,34 @@ +module Tests.Readers.EPUB (tests) where + +import Text.Pandoc.Options +import Test.Framework +import Test.HUnit (assertBool) +import Test.Framework.Providers.HUnit +import qualified Data.ByteString.Lazy as BL +import Text.Pandoc.Readers.EPUB +import Text.Pandoc.MediaBag (MediaBag, mediaDirectory) +import Control.Applicative +import System.FilePath (joinPath) + +getMediaBag :: FilePath -> IO MediaBag +getMediaBag fp = snd . readEPUB def <$> BL.readFile fp + +testMediaBag :: FilePath -> [(String, String, Int)] -> IO () +testMediaBag fp bag = do + actBag <- (mediaDirectory <$> getMediaBag fp) + assertBool (show "MediaBag did not match:\nExpected: " + ++ show bag + ++ "\nActual: " + ++ show actBag) + (actBag == bag) + +featuresBag :: [(String, String, Int)] +featuresBag = [(joinPath ["img","check.gif"],"image/gif",1340),(joinPath ["img","check.jpg"],"image/jpeg",2661),(joinPath ["img","check.png"],"image/png",2815),(joinPath ["img","multiscripts_and_greek_alphabet.png"],"image/png",10060)] + +tests :: [Test] +tests = + [ testGroup "EPUB Mediabag" + [ testCase "features bag" + (testMediaBag "epub/img.epub" featuresBag) + ] + ] diff --git a/tests/Tests/Readers/Markdown.hs b/tests/Tests/Readers/Markdown.hs index 492680a35..fdb1a7417 100644 --- a/tests/Tests/Readers/Markdown.hs +++ b/tests/Tests/Readers/Markdown.hs @@ -16,6 +16,13 @@ markdown = readMarkdown def markdownSmart :: String -> Pandoc markdownSmart = readMarkdown def { readerSmart = True } +markdownCDL :: String -> Pandoc +markdownCDL = readMarkdown def { readerExtensions = Set.insert + Ext_compact_definition_lists $ readerExtensions def } + +markdownGH :: String -> Pandoc +markdownGH = readMarkdown def { readerExtensions = githubMarkdownExtensions } + infix 4 =: (=:) :: ToString c => String -> (String, c) -> Test @@ -140,11 +147,28 @@ tests = [ testGroup "inline code" [ "two strongs in emph" =: "***a**b **c**d*" =?> para (emph (strong (str "a") <> str "b" <> space <> strong (str "c") <> str "d")) + , "emph and strong emph alternating" =: + "*xxx* ***xxx*** xxx\n*xxx* ***xxx*** xxx" + =?> para (emph "xxx" <> space <> strong (emph "xxx") <> + space <> "xxx" <> space <> + emph "xxx" <> space <> strong (emph "xxx") <> + space <> "xxx") + , "emph with spaced strong" =: + "*x **xx** x*" + =?> para (emph ("x" <> space <> strong "xx" <> space <> "x")) + , "intraword underscore with opening underscore (#1121)" =: + "_foot_ball_" =?> para (emph (text "foot_ball")) ] , testGroup "raw LaTeX" [ "in URL" =: "\\begin\n" =?> para (text "\\begin") ] + , testGroup "raw HTML" + [ "nesting (issue #1330)" =: + "<del>test</del>" =?> + rawBlock "html" "<del>" <> plain (str "test") <> + rawBlock "html" "</del>" + ] , "unbalanced brackets" =: "[[[[[[[[[[[[[[[hi" =?> para (text "[[[[[[[[[[[[[[[hi") , testGroup "backslash escapes" @@ -163,6 +187,11 @@ tests = [ testGroup "inline code" ] , testGroup "bare URIs" (map testBareLink bareLinkTests) + , testGroup "autolinks" + [ "with unicode dash following" =: + "<http://foo.bar>\8212" =?> para (autolink "http://foo.bar" <> + str "\8212") + ] , testGroup "Headers" [ "blank line before header" =: "\n# Header\n" @@ -179,17 +208,6 @@ tests = [ testGroup "inline code" ("À l'arrivée de la guerre, le thème de l'«impossibilité du socialisme»" =?> para "À l’arrivée de la guerre, le thème de l’«impossibilité du socialisme»") ] - , testGroup "mixed emphasis and strong" - [ "emph and strong emph alternating" =: - "*xxx* ***xxx*** xxx\n*xxx* ***xxx*** xxx" - =?> para (emph "xxx" <> space <> strong (emph "xxx") <> - space <> "xxx" <> space <> - emph "xxx" <> space <> strong (emph "xxx") <> - space <> "xxx") - , "emph with spaced strong" =: - "*x **xx** x*" - =?> para (emph ("x" <> space <> strong "xx" <> space <> "x")) - ] , testGroup "footnotes" [ "indent followed by newline and flush-left text" =: "[^1]\n\n[^1]: my note\n\n \nnot in note\n" @@ -216,4 +234,59 @@ tests = [ testGroup "inline code" -- , testGroup "round trip" -- [ property "p_markdown_round_trip" p_markdown_round_trip -- ] + , testGroup "definition lists" + [ "no blank space" =: + "foo1\n : bar\n\nfoo2\n : bar2\n : bar3\n" =?> + definitionList [ (text "foo1", [plain (text "bar")]) + , (text "foo2", [plain (text "bar2"), + plain (text "bar3")]) + ] + , "blank space before first def" =: + "foo1\n\n : bar\n\nfoo2\n\n : bar2\n : bar3\n" =?> + definitionList [ (text "foo1", [para (text "bar")]) + , (text "foo2", [para (text "bar2"), + plain (text "bar3")]) + ] + , "blank space before second def" =: + "foo1\n : bar\n\nfoo2\n : bar2\n\n : bar3\n" =?> + definitionList [ (text "foo1", [plain (text "bar")]) + , (text "foo2", [plain (text "bar2"), + para (text "bar3")]) + ] + , "laziness" =: + "foo1\n : bar\nbaz\n : bar2\n" =?> + definitionList [ (text "foo1", [plain (text "bar baz"), + plain (text "bar2")]) + ] + , "no blank space before first of two paragraphs" =: + "foo1\n : bar\n\n baz\n" =?> + definitionList [ (text "foo1", [para (text "bar") <> + para (text "baz")]) + ] + ] + , testGroup "+compact_definition_lists" + [ test markdownCDL "basic compact list" $ + "foo1\n: bar\n baz\nfoo2\n: bar2\n" =?> + definitionList [ (text "foo1", [plain (text "bar baz")]) + , (text "foo2", [plain (text "bar2")]) + ] + ] + , testGroup "lists" + [ "issue #1154" =: + " - <div>\n first div breaks\n </div>\n\n <button>if this button exists</button>\n\n <div>\n with this div too.\n </div>\n" + =?> bulletList [divWith nullAttr (para $ text "first div breaks") <> + rawBlock "html" "<button>" <> + plain (text "if this button exists") <> + rawBlock "html" "</button>" <> + divWith nullAttr (para $ text "with this div too.")] + , test markdownGH "issue #1636" $ + unlines [ "* a" + , "* b" + , "* c" + , " * d" ] + =?> + bulletList [ plain "a" + , plain "b" + , plain "c" <> bulletList [plain "d"] ] + ] ] diff --git a/tests/Tests/Readers/Org.hs b/tests/Tests/Readers/Org.hs new file mode 100644 index 000000000..39c40cd45 --- /dev/null +++ b/tests/Tests/Readers/Org.hs @@ -0,0 +1,1155 @@ +{-# LANGUAGE OverloadedStrings #-} +module Tests.Readers.Org (tests) where + +import Text.Pandoc.Definition +import Test.Framework +import Tests.Helpers +import Text.Pandoc.Builder +import Text.Pandoc +import Data.List (intersperse) +import Data.Monoid (mempty, mappend, mconcat) + +org :: String -> Pandoc +org = readOrg def + +infix 4 =: +(=:) :: ToString c + => String -> (String, c) -> Test +(=:) = test org + +spcSep :: [Inlines] -> Inlines +spcSep = mconcat . intersperse space + +simpleTable' :: Int + -> [Blocks] + -> [[Blocks]] + -> Blocks +simpleTable' n = table "" (take n $ repeat (AlignDefault, 0.0)) + +tests :: [Test] +tests = + [ testGroup "Inlines" $ + [ "Plain String" =: + "Hello, World" =?> + para (spcSep [ "Hello,", "World" ]) + + , "Emphasis" =: + "/Planet Punk/" =?> + para (emph . spcSep $ ["Planet", "Punk"]) + + , "Strong" =: + "*Cider*" =?> + para (strong "Cider") + + , "Strong Emphasis" =: + "/*strength*/" =?> + para (emph . strong $ "strength") + + , "Strikeout" =: + "+Kill Bill+" =?> + para (strikeout . spcSep $ [ "Kill", "Bill" ]) + + , "Verbatim" =: + "=Robot.rock()=" =?> + para (code "Robot.rock()") + + , "Code" =: + "~word for word~" =?> + para (code "word for word") + + , "Math $..$" =: + "$E=mc^2$" =?> + para (math "E=mc^2") + + , "Math $$..$$" =: + "$$E=mc^2$$" =?> + para (displayMath "E=mc^2") + + , "Math \\[..\\]" =: + "\\[E=ℎν\\]" =?> + para (displayMath "E=ℎν") + + , "Math \\(..\\)" =: + "\\(σ_x σ_p ≥ \\frac{ℏ}{2}\\)" =?> + para (math "σ_x σ_p ≥ \\frac{ℏ}{2}") + + , "Symbol" =: + "A * symbol" =?> + para (str "A" <> space <> str "*" <> space <> "symbol") + + , "Superscript simple expression" =: + "2^-λ" =?> + para (str "2" <> superscript "-λ") + + , "Superscript multi char" =: + "2^{n-1}" =?> + para (str "2" <> superscript "n-1") + + , "Subscript simple expression" =: + "a_n" =?> + para (str "a" <> subscript "n") + + , "Subscript multi char" =: + "a_{n+1}" =?> + para (str "a" <> subscript "n+1") + + , "Linebreak" =: + "line \\\\ \nbreak" =?> + para ("line" <> linebreak <> "break") + + , "Inline note" =: + "[fn::Schreib mir eine E-Mail]" =?> + para (note $ para "Schreib mir eine E-Mail") + + , "Markup-chars not occuring on word break are symbols" =: + unlines [ "this+that+ +so+on" + , "seven*eight* nine*" + , "+not+funny+" + ] =?> + para (spcSep [ "this+that+", "+so+on" + , "seven*eight*", "nine*" + , strikeout "not+funny" + ]) + + , "No empty markup" =: + "// ** __ ++ == ~~ $$" =?> + para (spcSep [ "//", "**", "__", "++", "==", "~~", "$$" ]) + + , "Adherence to Org's rules for markup borders" =: + "/t/& a/ / ./r/ (*l*) /e/! /b/." =?> + para (spcSep [ emph $ "t/&" <> space <> "a" + , "/" + , "./r/" + , "(" <> (strong "l") <> ")" + , (emph "e") <> "!" + , (emph "b") <> "." + ]) + + , "Quotes are forbidden border chars" =: + "/'nope/ *nope\"*" =?> + para ("/'nope/" <> space <> "*nope\"*") + + , "Commata are forbidden border chars" =: + "/nada,/" =?> + para "/nada,/" + + , "Markup should work properly after a blank line" =: + unlines ["foo", "", "/bar/"] =?> + (para $ text "foo") <> (para $ emph $ text "bar") + + , "Inline math must stay within three lines" =: + unlines [ "$a", "b", "c$", "$d", "e", "f", "g$" ] =?> + para ((math "a\nb\nc") <> space <> + spcSep [ "$d", "e", "f", "g$" ]) + + , "Single-character math" =: + "$a$ $b$! $c$?" =?> + para (spcSep [ math "a" + , "$b$!" + , (math "c") <> "?" + ]) + + , "Markup may not span more than two lines" =: + unlines [ "/this *is +totally", "nice+ not*", "emph/" ] =?> + para (spcSep [ "/this" + , (strong (spcSep + [ "is" + , (strikeout ("totally" <> space <> "nice")) + , "not" + ])) + , "emph/" ]) + + , "Sub- and superscript expressions" =: + unlines [ "a_(a(b)(c)d)" + , "e^(f(g)h)" + , "i_(jk)l)" + , "m^()n" + , "o_{p{q{}r}}" + , "s^{t{u}v}" + , "w_{xy}z}" + , "1^{}2" + , "3_{{}}" + , "4^(a(*b(c*)d))" + ] =?> + para (spcSep [ "a" <> subscript "(a(b)(c)d)" + , "e" <> superscript "(f(g)h)" + , "i" <> (subscript "(jk)") <> "l)" + , "m" <> (superscript "()") <> "n" + , "o" <> subscript "p{q{}r}" + , "s" <> superscript "t{u}v" + , "w" <> (subscript "xy") <> "z}" + , "1" <> (superscript "") <> "2" + , "3" <> subscript "{}" + , "4" <> superscript ("(a(" <> strong "b(c" <> ")d))") + ]) + + , "Image" =: + "[[./sunset.jpg]]" =?> + (para $ image "./sunset.jpg" "" "") + + , "Explicit link" =: + "[[http://zeitlens.com/][pseudo-random /nonsense/]]" =?> + (para $ link "http://zeitlens.com/" "" + ("pseudo-random" <> space <> emph "nonsense")) + + , "Self-link" =: + "[[http://zeitlens.com/]]" =?> + (para $ link "http://zeitlens.com/" "" "http://zeitlens.com/") + + , "Absolute file link" =: + "[[/url][hi]]" =?> + (para $ link "file:///url" "" "hi") + + , "Link to file in parent directory" =: + "[[../file.txt][moin]]" =?> + (para $ link "../file.txt" "" "moin") + + , "Empty link (for gitit interop)" =: + "[[][New Link]]" =?> + (para $ link "" "" "New Link") + + , "Image link" =: + "[[sunset.png][dusk.svg]]" =?> + (para $ link "sunset.png" "" (image "dusk.svg" "" "")) + + , "Plain link" =: + "Posts on http://zeitlens.com/ can be funny at times." =?> + (para $ spcSep [ "Posts", "on" + , link "http://zeitlens.com/" "" "http://zeitlens.com/" + , "can", "be", "funny", "at", "times." + ]) + + , "Angle link" =: + "Look at <http://moltkeplatz.de> for fnords." =?> + (para $ spcSep [ "Look", "at" + , link "http://moltkeplatz.de" "" "http://moltkeplatz.de" + , "for", "fnords." + ]) + + , "Absolute file link" =: + "[[file:///etc/passwd][passwd]]" =?> + (para $ link "file:///etc/passwd" "" "passwd") + + , "File link" =: + "[[file:target][title]]" =?> + (para $ link "target" "" "title") + + , "Anchor" =: + "<<anchor>> Link here later." =?> + (para $ spanWith ("anchor", [], []) mempty <> + "Link" <> space <> "here" <> space <> "later.") + + , "Inline code block" =: + "src_emacs-lisp{(message \"Hello\")}" =?> + (para $ codeWith ( "" + , [ "commonlisp", "rundoc-block" ] + , [ ("rundoc-language", "emacs-lisp") ]) + "(message \"Hello\")") + + , "Inline code block with arguments" =: + "src_sh[:export both :results output]{echo 'Hello, World'}" =?> + (para $ codeWith ( "" + , [ "bash", "rundoc-block" ] + , [ ("rundoc-language", "sh") + , ("rundoc-export", "both") + , ("rundoc-results", "output") + ] + ) + "echo 'Hello, World'") + + , "Citation" =: + "[@nonexistent]" =?> + let citation = Citation + { citationId = "nonexistent" + , citationPrefix = [] + , citationSuffix = [] + , citationMode = NormalCitation + , citationNoteNum = 0 + , citationHash = 0} + in (para $ cite [citation] "[@nonexistent]") + + , "Citation containing text" =: + "[see @item1 p. 34-35]" =?> + let citation = Citation + { citationId = "item1" + , citationPrefix = [Str "see"] + , citationSuffix = [Space ,Str "p.",Space,Str "34-35"] + , citationMode = NormalCitation + , citationNoteNum = 0 + , citationHash = 0} + in (para $ cite [citation] "[see @item1 p. 34-35]") + + , "Inline LaTeX symbol" =: + "\\dots" =?> + para "…" + + , "Inline LaTeX command" =: + "\\textit{Emphasised}" =?> + para (emph "Emphasised") + + , "Inline LaTeX math symbol" =: + "\\tau" =?> + para (emph "τ") + + , "Unknown inline LaTeX command" =: + "\\notacommand{foo}" =?> + para (rawInline "latex" "\\notacommand{foo}") + + , "MathML symbol in LaTeX-style" =: + "There is a hackerspace in Lübeck, Germany, called nbsp (unicode symbol: '\\nbsp')." =?> + para ("There is a hackerspace in Lübeck, Germany, called nbsp (unicode symbol: ' ').") + + , "MathML symbol in LaTeX-style, including braces" =: + "\\Aacute{}stor" =?> + para "Ástor" + + , "MathML copy sign" =: + "\\copy" =?> + para "©" + + , "LaTeX citation" =: + "\\cite{Coffee}" =?> + let citation = Citation + { citationId = "Coffee" + , citationPrefix = [] + , citationSuffix = [] + , citationMode = AuthorInText + , citationNoteNum = 0 + , citationHash = 0} + in (para . cite [citation] $ rawInline "latex" "\\cite{Coffee}") + ] + + , testGroup "Meta Information" $ + [ "Comment" =: + "# Nothing to see here" =?> + (mempty::Blocks) + + , "Not a comment" =: + "#-tag" =?> + para "#-tag" + + , "Comment surrounded by Text" =: + unlines [ "Before" + , "# Comment" + , "After" + ] =?> + mconcat [ para "Before" + , para "After" + ] + + , "Title" =: + "#+TITLE: Hello, World" =?> + let titleInline = toList $ "Hello," <> space <> "World" + meta = setMeta "title" (MetaInlines titleInline) $ nullMeta + in Pandoc meta mempty + + , "Author" =: + "#+author: Albert /Emacs-Fanboy/ Krewinkel" =?> + let author = toList . spcSep $ [ "Albert", emph "Emacs-Fanboy", "Krewinkel" ] + meta = setMeta "author" (MetaInlines author) $ nullMeta + in Pandoc meta mempty + + , "Date" =: + "#+Date: Feb. *28*, 2014" =?> + let date = toList . spcSep $ [ "Feb.", (strong "28") <> ",", "2014" ] + meta = setMeta "date" (MetaInlines date) $ nullMeta + in Pandoc meta mempty + + , "Description" =: + "#+DESCRIPTION: Explanatory text" =?> + let description = toList . spcSep $ [ "Explanatory", "text" ] + meta = setMeta "description" (MetaInlines description) $ nullMeta + in Pandoc meta mempty + + , "Properties drawer" =: + unlines [ " :PROPERTIES:" + , " :setting: foo" + , " :END:" + ] =?> + (mempty::Blocks) + + , "Logbook drawer" =: + unlines [ " :LogBook:" + , " - State \"DONE\" from \"TODO\" [2014-03-03 Mon 11:00]" + , " :END:" + ] =?> + (mempty::Blocks) + + , "Drawer surrounded by text" =: + unlines [ "Before" + , ":PROPERTIES:" + , ":END:" + , "After" + ] =?> + para "Before" <> para "After" + + , "Drawer start is the only text in first line of a drawer" =: + unlines [ " :LOGBOOK: foo" + , " :END:" + ] =?> + para (spcSep [ ":LOGBOOK:", "foo", ":END:" ]) + + , "Drawers with unknown names are just text" =: + unlines [ ":FOO:" + , ":END:" + ] =?> + para (":FOO:" <> space <> ":END:") + + , "Anchor reference" =: + unlines [ "<<link-here>> Target." + , "" + , "[[link-here][See here!]]" + ] =?> + (para (spanWith ("link-here", [], []) mempty <> "Target.") <> + para (link "#link-here" "" ("See" <> space <> "here!"))) + + , "Search links are read as emph" =: + "[[Wally][Where's Wally?]]" =?> + (para (emph $ "Where's" <> space <> "Wally?")) + + , "Link to nonexistent anchor" =: + unlines [ "<<link-here>> Target." + , "" + , "[[link$here][See here!]]" + ] =?> + (para (spanWith ("link-here", [], []) mempty <> "Target.") <> + para (emph ("See" <> space <> "here!"))) + + , "Link abbreviation" =: + unlines [ "#+LINK: wp https://en.wikipedia.org/wiki/%s" + , "[[wp:Org_mode][Wikipedia on Org-mode]]" + ] =?> + (para (link "https://en.wikipedia.org/wiki/Org_mode" "" + ("Wikipedia" <> space <> "on" <> space <> "Org-mode"))) + + , "Link abbreviation, defined after first use" =: + unlines [ "[[zl:non-sense][Non-sense articles]]" + , "#+LINK: zl http://zeitlens.com/tags/%s.html" + ] =?> + (para (link "http://zeitlens.com/tags/non-sense.html" "" + ("Non-sense" <> space <> "articles"))) + + , "Link abbreviation, URL encoded arguments" =: + unlines [ "#+link: expl http://example.com/%h/foo" + , "[[expl:Hello, World!][Moin!]]" + ] =?> + (para (link "http://example.com/Hello%2C%20World%21/foo" "" "Moin!")) + + , "Link abbreviation, append arguments" =: + unlines [ "#+link: expl http://example.com/" + , "[[expl:foo][bar]]" + ] =?> + (para (link "http://example.com/foo" "" "bar")) + ] + + , testGroup "Basic Blocks" $ + [ "Paragraph" =: + "Paragraph\n" =?> + para "Paragraph" + + , "First Level Header" =: + "* Headline\n" =?> + header 1 "Headline" + + , "Third Level Header" =: + "*** Third Level Headline\n" =?> + header 3 ("Third" <> space <> + "Level" <> space <> + "Headline") + + , "Compact Headers with Paragraph" =: + unlines [ "* First Level" + , "** Second Level" + , " Text" + ] =?> + mconcat [ header 1 ("First" <> space <> "Level") + , header 2 ("Second" <> space <> "Level") + , para "Text" + ] + + , "Separated Headers with Paragraph" =: + unlines [ "* First Level" + , "" + , "** Second Level" + , "" + , " Text" + ] =?> + mconcat [ header 1 ("First" <> space <> "Level") + , header 2 ("Second" <> space <> "Level") + , para "Text" + ] + + , "Headers not preceded by a blank line" =: + unlines [ "** eat dinner" + , "Spaghetti and meatballs tonight." + , "** walk dog" + ] =?> + mconcat [ header 2 ("eat" <> space <> "dinner") + , para $ spcSep [ "Spaghetti", "and", "meatballs", "tonight." ] + , header 2 ("walk" <> space <> "dog") + ] + + , "Comment Trees" =: + unlines [ "* COMMENT A comment tree" + , " Not much going on here" + , "** This will be dropped" + , "* Comment tree above" + ] =?> + header 1 "Comment tree above" + + , "Nothing but a COMMENT header" =: + "* COMMENT Test" =?> + (mempty::Blocks) + + , "Paragraph starting with an asterisk" =: + "*five" =?> + para "*five" + + , "Paragraph containing asterisk at beginning of line" =: + unlines [ "lucky" + , "*star" + ] =?> + para ("lucky" <> space <> "*star") + + , "Example block" =: + unlines [ ": echo hello" + , ": echo dear tester" + ] =?> + codeBlockWith ("", ["example"], []) "echo hello\necho dear tester\n" + + , "Example block surrounded by text" =: + unlines [ "Greetings" + , ": echo hello" + , ": echo dear tester" + , "Bye" + ] =?> + mconcat [ para "Greetings" + , codeBlockWith ("", ["example"], []) + "echo hello\necho dear tester\n" + , para "Bye" + ] + + , "Horizontal Rule" =: + unlines [ "before" + , "-----" + , "after" + ] =?> + mconcat [ para "before" + , horizontalRule + , para "after" + ] + + , "Not a Horizontal Rule" =: + "----- five dashes" =?> + (para $ spcSep [ "-----", "five", "dashes" ]) + + , "Comment Block" =: + unlines [ "#+BEGIN_COMMENT" + , "stuff" + , "bla" + , "#+END_COMMENT"] =?> + (mempty::Blocks) + + , "Figure" =: + unlines [ "#+caption: A very courageous man." + , "#+name: goodguy" + , "[[edward.jpg]]" + ] =?> + para (image "edward.jpg" "fig:goodguy" "A very courageous man.") + + , "Unnamed figure" =: + unlines [ "#+caption: A great whistleblower." + , "[[snowden.png]]" + ] =?> + para (image "snowden.png" "" "A great whistleblower.") + + , "Figure with `fig:` prefix in name" =: + unlines [ "#+caption: Used as a metapher in evolutionary biology." + , "#+name: fig:redqueen" + , "[[the-red-queen.jpg]]" + ] =?> + para (image "the-red-queen.jpg" "fig:redqueen" + "Used as a metapher in evolutionary biology.") + + , "Footnote" =: + unlines [ "A footnote[1]" + , "" + , "[1] First paragraph" + , "" + , "second paragraph" + ] =?> + para (mconcat + [ "A", space, "footnote" + , note $ mconcat [ para ("First" <> space <> "paragraph") + , para ("second" <> space <> "paragraph") + ] + ]) + + , "Two footnotes" =: + unlines [ "Footnotes[fn:1][fn:2]" + , "" + , "[fn:1] First note." + , "" + , "[fn:2] Second note." + ] =?> + para (mconcat + [ "Footnotes" + , note $ para ("First" <> space <> "note.") + , note $ para ("Second" <> space <> "note.") + ]) + + , "Footnote followed by header" =: + unlines [ "Another note[fn:yay]" + , "" + , "[fn:yay] This is great!" + , "" + , "** Headline" + ] =?> + mconcat + [ para (mconcat + [ "Another", space, "note" + , note $ para ("This" <> space <> "is" <> space <> "great!") + ]) + , header 2 "Headline" + ] + ] + + , testGroup "Lists" $ + [ "Simple Bullet Lists" =: + ("- Item1\n" ++ + "- Item2\n") =?> + bulletList [ plain "Item1" + , plain "Item2" + ] + + , "Indented Bullet Lists" =: + (" - Item1\n" ++ + " - Item2\n") =?> + bulletList [ plain "Item1" + , plain "Item2" + ] + + , "Unindented *" =: + ("- Item1\n" ++ + "* Item2\n") =?> + bulletList [ plain "Item1" + ] <> + header 1 "Item2" + + , "Multi-line Bullet Lists" =: + ("- *Fat\n" ++ + " Tony*\n" ++ + "- /Sideshow\n" ++ + " Bob/") =?> + bulletList [ plain $ strong ("Fat" <> space <> "Tony") + , plain $ emph ("Sideshow" <> space <> "Bob") + ] + + , "Nested Bullet Lists" =: + ("- Discovery\n" ++ + " + One More Time\n" ++ + " + Harder, Better, Faster, Stronger\n" ++ + "- Homework\n" ++ + " + Around the World\n"++ + "- Human After All\n" ++ + " + Technologic\n" ++ + " + Robot Rock\n") =?> + bulletList [ mconcat + [ plain "Discovery" + , bulletList [ plain ("One" <> space <> + "More" <> space <> + "Time") + , plain ("Harder," <> space <> + "Better," <> space <> + "Faster," <> space <> + "Stronger") + ] + ] + , mconcat + [ plain "Homework" + , bulletList [ plain ("Around" <> space <> + "the" <> space <> + "World") + ] + ] + , mconcat + [ plain ("Human" <> space <> "After" <> space <> "All") + , bulletList [ plain "Technologic" + , plain ("Robot" <> space <> "Rock") + ] + ] + ] + + , "Bullet List with Decreasing Indent" =: + (" - Discovery\n\ + \ - Human After All\n") =?> + mconcat [ bulletList [ plain "Discovery" ] + , bulletList [ plain ("Human" <> space <> "After" <> space <> "All")] + ] + + , "Header follows Bullet List" =: + (" - Discovery\n\ + \ - Human After All\n\ + \* Homework") =?> + mconcat [ bulletList [ plain "Discovery" + , plain ("Human" <> space <> "After" <> space <> "All") + ] + , header 1 "Homework" + ] + + , "Bullet List Unindented with trailing Header" =: + ("- Discovery\n\ + \- Homework\n\ + \* NotValidListItem") =?> + mconcat [ bulletList [ plain "Discovery" + , plain "Homework" + ] + , header 1 "NotValidListItem" + ] + + , "Simple Ordered List" =: + ("1. Item1\n" ++ + "2. Item2\n") =?> + let listStyle = (1, DefaultStyle, DefaultDelim) + listStructure = [ plain "Item1" + , plain "Item2" + ] + in orderedListWith listStyle listStructure + + , "Simple Ordered List with Parens" =: + ("1) Item1\n" ++ + "2) Item2\n") =?> + let listStyle = (1, DefaultStyle, DefaultDelim) + listStructure = [ plain "Item1" + , plain "Item2" + ] + in orderedListWith listStyle listStructure + + , "Indented Ordered List" =: + (" 1. Item1\n" ++ + " 2. Item2\n") =?> + let listStyle = (1, DefaultStyle, DefaultDelim) + listStructure = [ plain "Item1" + , plain "Item2" + ] + in orderedListWith listStyle listStructure + + , "Nested Ordered Lists" =: + ("1. One\n" ++ + " 1. One-One\n" ++ + " 2. One-Two\n" ++ + "2. Two\n" ++ + " 1. Two-One\n"++ + " 2. Two-Two\n") =?> + let listStyle = (1, DefaultStyle, DefaultDelim) + listStructure = [ mconcat + [ plain "One" + , orderedList [ plain "One-One" + , plain "One-Two" + ] + ] + , mconcat + [ plain "Two" + , orderedList [ plain "Two-One" + , plain "Two-Two" + ] + ] + ] + in orderedListWith listStyle listStructure + + , "Ordered List in Bullet List" =: + ("- Emacs\n" ++ + " 1. Org\n") =?> + bulletList [ (plain "Emacs") <> + (orderedList [ plain "Org"]) + ] + + , "Bullet List in Ordered List" =: + ("1. GNU\n" ++ + " - Freedom\n") =?> + orderedList [ (plain "GNU") <> bulletList [ (plain "Freedom") ] ] + + , "Definition List" =: + unlines [ "- PLL :: phase-locked loop" + , "- TTL ::" + , " transistor-transistor logic" + , "- PSK::phase-shift keying" + , "" + , " a digital modulation scheme" + ] =?> + definitionList [ ("PLL", [ plain $ "phase-locked" <> space <> "loop" ]) + , ("TTL", [ plain $ "transistor-transistor" <> space <> + "logic" ]) + , ("PSK", [ mconcat + [ para $ "phase-shift" <> space <> "keying" + , para $ spcSep [ "a", "digital" + , "modulation", "scheme" ] + ] + ]) + ] + , "Definition list with multi-word term" =: + " - Elijah Wood :: He plays Frodo" =?> + definitionList [ ("Elijah" <> space <> "Wood", [plain $ "He" <> space <> "plays" <> space <> "Frodo"])] + , "Compact definition list" =: + unlines [ "- ATP :: adenosine 5' triphosphate" + , "- DNA :: deoxyribonucleic acid" + , "- PCR :: polymerase chain reaction" + , "" + ] =?> + definitionList + [ ("ATP", [ plain $ spcSep [ "adenosine", "5'", "triphosphate" ] ]) + , ("DNA", [ plain $ spcSep [ "deoxyribonucleic", "acid" ] ]) + , ("PCR", [ plain $ spcSep [ "polymerase", "chain", "reaction" ] ]) + ] + + , "Definition List With Trailing Header" =: + "- definition :: list\n\ + \- cool :: defs\n\ + \* header" =?> + mconcat [ definitionList [ ("definition", [plain "list"]) + , ("cool", [plain "defs"]) + ] + , header 1 "header" + ] + + , "Loose bullet list" =: + unlines [ "- apple" + , "" + , "- orange" + , "" + , "- peach" + ] =?> + bulletList [ para "apple" + , para "orange" + , para "peach" + ] + ] + + , testGroup "Tables" + [ "Single cell table" =: + "|Test|" =?> + simpleTable' 1 mempty [[plain "Test"]] + + , "Multi cell table" =: + "| One | Two |" =?> + simpleTable' 2 mempty [ [ plain "One", plain "Two" ] ] + + , "Multi line table" =: + unlines [ "| One |" + , "| Two |" + , "| Three |" + ] =?> + simpleTable' 1 mempty + [ [ plain "One" ] + , [ plain "Two" ] + , [ plain "Three" ] + ] + + , "Empty table" =: + "||" =?> + simpleTable' 1 mempty mempty + + , "Glider Table" =: + unlines [ "| 1 | 0 | 0 |" + , "| 0 | 1 | 1 |" + , "| 1 | 1 | 0 |" + ] =?> + simpleTable' 3 mempty + [ [ plain "1", plain "0", plain "0" ] + , [ plain "0", plain "1", plain "1" ] + , [ plain "1", plain "1", plain "0" ] + ] + + , "Table between Paragraphs" =: + unlines [ "Before" + , "| One | Two |" + , "After" + ] =?> + mconcat [ para "Before" + , simpleTable' 2 mempty [ [ plain "One", plain "Two" ] ] + , para "After" + ] + + , "Table with Header" =: + unlines [ "| Species | Status |" + , "|--------------+--------------|" + , "| cervisiae | domesticated |" + , "| paradoxus | wild |" + ] =?> + simpleTable [ plain "Species", plain "Status" ] + [ [ plain "cervisiae", plain "domesticated" ] + , [ plain "paradoxus", plain "wild" ] + ] + + , "Table with final hline" =: + unlines [ "| cervisiae | domesticated |" + , "| paradoxus | wild |" + , "|--------------+--------------|" + ] =?> + simpleTable' 2 mempty + [ [ plain "cervisiae", plain "domesticated" ] + , [ plain "paradoxus", plain "wild" ] + ] + + , "Table in a box" =: + unlines [ "|---------|---------|" + , "| static | Haskell |" + , "| dynamic | Lisp |" + , "|---------+---------|" + ] =?> + simpleTable' 2 mempty + [ [ plain "static", plain "Haskell" ] + , [ plain "dynamic", plain "Lisp" ] + ] + + , "Table with alignment row" =: + unlines [ "| Numbers | Text | More |" + , "| <c> | <r> | |" + , "| 1 | One | foo |" + , "| 2 | Two | bar |" + ] =?> + table "" (zip [AlignCenter, AlignRight, AlignDefault] [0, 0, 0]) + [] + [ [ plain "Numbers", plain "Text", plain "More" ] + , [ plain "1" , plain "One" , plain "foo" ] + , [ plain "2" , plain "Two" , plain "bar" ] + ] + + , "Pipe within text doesn't start a table" =: + "Ceci n'est pas une | pipe " =?> + para (spcSep [ "Ceci", "n'est", "pas", "une", "|", "pipe" ]) + + , "Missing pipe at end of row" =: + "|incomplete-but-valid" =?> + simpleTable' 1 mempty [ [ plain "incomplete-but-valid" ] ] + + , "Table with differing row lengths" =: + unlines [ "| Numbers | Text " + , "|-" + , "| <c> | <r> |" + , "| 1 | One | foo |" + , "| 2" + ] =?> + table "" (zip [AlignCenter, AlignRight, AlignDefault] [0, 0, 0]) + [ plain "Numbers", plain "Text" , plain mempty ] + [ [ plain "1" , plain "One" , plain "foo" ] + , [ plain "2" , plain mempty , plain mempty ] + ] + + , "Table with caption" =: + unlines [ "#+CAPTION: Hitchhiker's Multiplication Table" + , "| x | 6 |" + , "| 9 | 42 |" + ] =?> + table "Hitchhiker's Multiplication Table" + [(AlignDefault, 0), (AlignDefault, 0)] + [] + [ [ plain "x", plain "6" ] + , [ plain "9", plain "42" ] + ] + ] + + , testGroup "Blocks and fragments" + [ "Source block" =: + unlines [ " #+BEGIN_SRC haskell" + , " main = putStrLn greeting" + , " where greeting = \"moin\"" + , " #+END_SRC" ] =?> + let attr' = ("", ["haskell"], []) + code' = "main = putStrLn greeting\n" ++ + " where greeting = \"moin\"\n" + in codeBlockWith attr' code' + + , "Source block between paragraphs" =: + unlines [ "Low German greeting" + , " #+BEGIN_SRC haskell" + , " main = putStrLn greeting" + , " where greeting = \"Moin!\"" + , " #+END_SRC" ] =?> + let attr' = ("", ["haskell"], []) + code' = "main = putStrLn greeting\n" ++ + " where greeting = \"Moin!\"\n" + in mconcat [ para $ spcSep [ "Low", "German", "greeting" ] + , codeBlockWith attr' code' + ] + , "Source block with rundoc/babel arguments" =: + unlines [ "#+BEGIN_SRC emacs-lisp :exports both" + , "(progn (message \"Hello, World!\")" + , " (+ 23 42))" + , "#+END_SRC" ] =?> + let classes = [ "commonlisp" -- as kate doesn't know emacs-lisp syntax + , "rundoc-block" + ] + params = [ ("rundoc-language", "emacs-lisp") + , ("rundoc-exports", "both") + ] + code' = unlines [ "(progn (message \"Hello, World!\")" + , " (+ 23 42))" ] + in codeBlockWith ("", classes, params) code' + + , "Source block with results and :exports both" =: + unlines [ "#+BEGIN_SRC emacs-lisp :exports both" + , "(progn (message \"Hello, World!\")" + , " (+ 23 42))" + , "#+END_SRC" + , "" + , "#+RESULTS:" + , ": 65"] =?> + let classes = [ "commonlisp" -- as kate doesn't know emacs-lisp syntax + , "rundoc-block" + ] + params = [ ("rundoc-language", "emacs-lisp") + , ("rundoc-exports", "both") + ] + code' = unlines [ "(progn (message \"Hello, World!\")" + , " (+ 23 42))" ] + results' = "65\n" + in codeBlockWith ("", classes, params) code' + <> + codeBlockWith ("", ["example"], []) results' + + , "Source block with results and :exports code" =: + unlines [ "#+BEGIN_SRC emacs-lisp :exports code" + , "(progn (message \"Hello, World!\")" + , " (+ 23 42))" + , "#+END_SRC" + , "" + , "#+RESULTS:" + , ": 65" ] =?> + let classes = [ "commonlisp" -- as kate doesn't know emacs-lisp syntax + , "rundoc-block" + ] + params = [ ("rundoc-language", "emacs-lisp") + , ("rundoc-exports", "code") + ] + code' = unlines [ "(progn (message \"Hello, World!\")" + , " (+ 23 42))" ] + in codeBlockWith ("", classes, params) code' + + , "Source block with results and :exports results" =: + unlines [ "#+BEGIN_SRC emacs-lisp :exports results" + , "(progn (message \"Hello, World!\")" + , " (+ 23 42))" + , "#+END_SRC" + , "" + , "#+RESULTS:" + , ": 65" ] =?> + let results' = "65\n" + in codeBlockWith ("", ["example"], []) results' + + , "Source block with results and :exports none" =: + unlines [ "#+BEGIN_SRC emacs-lisp :exports none" + , "(progn (message \"Hello, World!\")" + , " (+ 23 42))" + , "#+END_SRC" + , "" + , "#+RESULTS:" + , ": 65" ] =?> + rawBlock "html" "" + + , "Example block" =: + unlines [ "#+begin_example" + , "A chosen representation of" + , "a rule." + , "#+eND_exAMPle" + ] =?> + codeBlockWith ("", ["example"], []) + "A chosen representation of\na rule.\n" + + , "HTML block" =: + unlines [ "#+BEGIN_HTML" + , "<aside>HTML5 is pretty nice.</aside>" + , "#+END_HTML" + ] =?> + rawBlock "html" "<aside>HTML5 is pretty nice.</aside>\n" + + , "Quote block" =: + unlines [ "#+BEGIN_QUOTE" + , "/Niemand/ hat die Absicht, eine Mauer zu errichten!" + , "#+END_QUOTE" + ] =?> + blockQuote (para (spcSep [ emph "Niemand", "hat", "die", "Absicht," + , "eine", "Mauer", "zu", "errichten!" + ])) + + , "Verse block" =: + unlines [ "The first lines of Goethe's /Faust/:" + , "#+begin_verse" + , "Habe nun, ach! Philosophie," + , "Juristerei und Medizin," + , "Und leider auch Theologie!" + , "Durchaus studiert, mit heißem Bemühn." + , "#+end_verse" + ] =?> + mconcat + [ para $ spcSep [ "The", "first", "lines", "of" + , "Goethe's", emph "Faust" <> ":"] + , para $ mconcat + [ spcSep [ "Habe", "nun,", "ach!", "Philosophie," ] + , linebreak + , spcSep [ "Juristerei", "und", "Medizin," ] + , linebreak + , spcSep [ "Und", "leider", "auch", "Theologie!" ] + , linebreak + , spcSep [ "Durchaus", "studiert,", "mit", "heißem", "Bemühn." ] + ] + ] + + , "LaTeX fragment" =: + unlines [ "\\begin{equation}" + , "X_i = \\begin{cases}" + , " G_{\\alpha(i)} & \\text{if }\\alpha(i-1) = \\alpha(i)\\\\" + , " C_{\\alpha(i)} & \\text{otherwise}" + , " \\end{cases}" + , "\\end{equation}" + ] =?> + rawBlock "latex" + (unlines [ "\\begin{equation}" + , "X_i = \\begin{cases}" + , " G_{\\alpha(i)} & \\text{if }\\alpha(i-1) =" ++ + " \\alpha(i)\\\\" + , " C_{\\alpha(i)} & \\text{otherwise}" + , " \\end{cases}" + , "\\end{equation}" + ]) + + , "Code block with caption" =: + unlines [ "#+CAPTION: Functor laws in Haskell" + , "#+NAME: functor-laws" + , "#+BEGIN_SRC haskell" + , "fmap id = id" + , "fmap (p . q) = (fmap p) . (fmap q)" + , "#+END_SRC" + ] =?> + divWith + nullAttr + (mappend + (plain $ spanWith ("", ["label"], []) + (spcSep [ "Functor", "laws", "in", "Haskell" ])) + (codeBlockWith ("functor-laws", ["haskell"], []) + (unlines [ "fmap id = id" + , "fmap (p . q) = (fmap p) . (fmap q)" + ]))) + + , "Convert blank lines in blocks to single newlines" =: + unlines [ "#+begin_html" + , "" + , "<span>boring</span>" + , "" + , "#+end_html" + ] =?> + rawBlock "html" "\n<span>boring</span>\n\n" + + , "Non-letter chars in source block parameters" =: + unlines [ "#+BEGIN_SRC C :tangle xxxx.c :city Zürich" + , "code body" + , "#+END_SRC" + ] =?> + let classes = [ "c", "rundoc-block" ] + params = [ ("rundoc-language", "C") + , ("rundoc-tangle", "xxxx.c") + , ("rundoc-city", "Zürich") + ] + in codeBlockWith ( "", classes, params) "code body\n" + ] + ] diff --git a/tests/Tests/Readers/RST.hs b/tests/Tests/Readers/RST.hs index a80dc32b7..1aaf4897f 100644 --- a/tests/Tests/Readers/RST.hs +++ b/tests/Tests/Readers/RST.hs @@ -67,5 +67,45 @@ tests = [ "line block with blank line" =: link "http://foo.bar.baz" "" "http://foo.bar.baz" <> ". " <> link "http://foo.bar/baz_(bam)" "" "http://foo.bar/baz_(bam)" <> " (" <> link "http://foo.bar" "" "http://foo.bar" <> ")") + , testGroup "literal / line / code blocks" + [ "indented literal block" =: unlines + [ "::" + , "" + , " block quotes" + , "" + , " can go on for many lines" + , "but must stop here"] + =?> (doc $ + codeBlock "block quotes\n\ncan go on for many lines" <> + para "but must stop here") + , "line block with 3 lines" =: "| a\n| b\n| c" + =?> para ("a" <> linebreak <> "b" <> linebreak <> "c") + , "quoted literal block using >" =: "::\n\n> quoted\n> block\n\nOrdinary paragraph" + =?> codeBlock "> quoted\n> block" <> para "Ordinary paragraph" + , "quoted literal block using | (not a line block)" =: "::\n\n| quoted\n| block\n\nOrdinary paragraph" + =?> codeBlock "| quoted\n| block" <> para "Ordinary paragraph" + , "class directive with single paragraph" =: ".. class:: special\n\nThis is a \"special\" paragraph." + =?> divWith ("", ["special"], []) (para "This is a \"special\" paragraph.") + , "class directive with two paragraphs" =: ".. class:: exceptional remarkable\n\n First paragraph.\n\n Second paragraph." + =?> divWith ("", ["exceptional", "remarkable"], []) (para "First paragraph." <> para "Second paragraph.") + , "class directive around literal block" =: ".. class:: classy\n\n::\n\n a\n b" + =?> divWith ("", ["classy"], []) (codeBlock "a\nb")] + , testGroup "interpreted text roles" + [ "literal role prefix" =: ":literal:`a`" =?> para (code "a") + , "literal role postfix" =: "`a`:literal:" =?> para (code "a") + , "literal text" =: "``text``" =?> para (code "text") + , "code role" =: ":code:`a`" =?> para (codeWith ("", ["sourceCode"], []) "a") + , "inherited code role" =: ".. role:: codeLike(code)\n\n:codeLike:`a`" + =?> para (codeWith ("", ["codeLike", "sourceCode"], []) "a") + , "custom code role with language field" + =: ".. role:: lhs(code)\n :language: haskell\n\n:lhs:`a`" + =?> para (codeWith ("", ["lhs", "haskell","sourceCode"], []) "a") + , "custom role with unspecified parent role" + =: ".. role:: classy\n\n:classy:`text`" + =?> para (spanWith ("", ["classy"], []) "text") + , "role with recursive inheritance" + =: ".. role:: haskell(code)\n.. role:: lhs(haskell)\n\n:lhs:`text`" + =?> para (codeWith ("", ["lhs", "haskell", "sourceCode"], []) "text") + , "unknown role" =: ":unknown:`text`" =?> para (str "text") + ] ] - diff --git a/tests/Tests/Readers/Txt2Tags.hs b/tests/Tests/Readers/Txt2Tags.hs new file mode 100644 index 000000000..fd7c767e0 --- /dev/null +++ b/tests/Tests/Readers/Txt2Tags.hs @@ -0,0 +1,430 @@ +{-# LANGUAGE OverloadedStrings #-} +module Tests.Readers.Txt2Tags (tests) where + +import Text.Pandoc.Definition +import Test.Framework +import Tests.Helpers +import Tests.Arbitrary() +import Text.Pandoc.Builder +import Text.Pandoc +import Data.List (intersperse) +import Data.Monoid (mempty, mconcat) +import Text.Pandoc.Readers.Txt2Tags + +t2t :: String -> Pandoc +t2t s = readTxt2Tags (T2TMeta "date" "mtime" "in" "out") def s + +infix 4 =: +(=:) :: ToString c + => String -> (String, c) -> Test +(=:) = test t2t + +spcSep :: [Inlines] -> Inlines +spcSep = mconcat . intersperse space + +simpleTable' :: Int + -> [Blocks] + -> [[Blocks]] + -> Blocks +simpleTable' n = table "" (take n $ repeat (AlignCenter, 0.0)) + +tests :: [Test] +tests = + [ testGroup "Inlines" $ + [ "Plain String" =: + "Hello, World" =?> + para (spcSep [ "Hello,", "World" ]) + + , "Emphasis" =: + "//Planet Punk//" =?> + para (emph . spcSep $ ["Planet", "Punk"]) + + , "Strong" =: + "**Cider**" =?> + para (strong "Cider") + + , "Strong Emphasis" =: + "//**strength**//" =?> + para (emph . strong $ "strength") + + , "Strikeout" =: + "--Kill Bill--" =?> + para (strikeout . spcSep $ [ "Kill", "Bill" ]) + + , "Verbatim" =: + "``Robot.rock()``" =?> + para (code "Robot.rock()") + + , "Symbol" =: + "A * symbol" =?> + para (str "A" <> space <> str "*" <> space <> "symbol") + + , "No empty markup" =: + "//// **** ____ ---- ```` \"\"\"\" ''''" =?> + para (spcSep [ "////", "****", "____", "----", "````", "\"\"\"\"", "''''" ]) + + , "Inline markup is greedy" =: + "***** ///// _____ ----- ````` \"\"\"\"\" '''''" =?> + para (spcSep [strong "*", emph "/", emph "_" + , strikeout "-", code "`", text "\"" + , rawInline "html" "'"]) + , "Markup must be greedy" =: + "********** ////////// __________ ---------- `````````` \"\"\"\"\"\"\"\"\"\" ''''''''''" =?> + para (spcSep [strong "******", emph "//////", emph "______" + , strikeout "------", code "``````", text "\"\"\"\"\"\"" + , rawInline "html" "''''''"]) + , "Inlines must be glued" =: + "** a** **a ** ** a **" =?> + para (text "** a** **a ** ** a **") + + , "Macros: Date" =: + "%%date" =?> + para "date" + , "Macros: Mod Time" =: + "%%mtime" =?> + para "mtime" + , "Macros: Infile" =: + "%%infile" =?> + para "in" + , "Macros: Outfile" =: + "%%outfile" =?> + para "out" + , "Autolink" =: + "http://www.google.com" =?> + para (link "http://www.google.com" "" (str "http://www.google.com")) + , "Image" =: + "[image.jpg]" =?> + para (image "image.jpg" "" mempty) + + , "Link" =: + "[title http://google.com]" =?> + para (link "http://google.com" "" (str "title")) + + , "Image link" =: + "[[image.jpg] abc]" =?> + para (link "abc" "" (image "image.jpg" "" mempty)) + , "Invalid link: No trailing space" =: + "[title invalid ]" =?> + para (text "[title invalid ]") + + + ] + + , testGroup "Basic Blocks" $ + ["Paragraph, lines grouped together" =: + "A paragraph\n A blank line ends the \n current paragraph\n" + =?> para "A paragraph A blank line ends the current paragraph" + , "Paragraph, ignore leading and trailing spaces" =: + " Leading and trailing spaces are ignored. \n" =?> + para "Leading and trailing spaces are ignored." + , "Comment line in paragraph" =: + "A comment line can be placed inside a paragraph.\n% this comment will be ignored \nIt will not affect it.\n" + =?> para "A comment line can be placed inside a paragraph. It will not affect it." + , "Paragraph" =: + "Paragraph\n" =?> + para "Paragraph" + + , "First Level Header" =: + "+ Headline +\n" =?> + header 1 "Headline" + + , "Third Level Header" =: + "=== Third Level Headline ===\n" =?> + header 3 ("Third" <> space <> + "Level" <> space <> + "Headline") + + , "Header with label" =: + "= header =[label]" =?> + headerWith ("label", [], []) 1 ("header") + + , "Invalid header, mismatched delimiters" =: + "== header =" =?> + para (text "== header =") + + , "Invalid header, spaces in label" =: + "== header ==[ haha ]" =?> + para (text "== header ==[ haha ]") + + , "Invalid header, invalid label character" =: + "== header ==[lab/el]" =?> + para (text "== header ==[lab/el]") + , "Headers not preceded by a blank line" =: + unlines [ "++ eat dinner ++" + , "Spaghetti and meatballs tonight." + , "== walk dog ==" + ] =?> + mconcat [ header 2 ("eat" <> space <> "dinner") + , para $ spcSep [ "Spaghetti", "and", "meatballs", "tonight." ] + , header 2 ("walk" <> space <> "dog") + ] + + , "Paragraph starting with an equals" =: + "=five" =?> + para "=five" + + , "Paragraph containing asterisk at beginning of line" =: + unlines [ "lucky" + , "*star" + ] =?> + para ("lucky" <> space <> "*star") + + , "Horizontal Rule" =: + unlines [ "before" + , replicate 20 '-' + , replicate 20 '=' + , replicate 20 '_' + , "after" + ] =?> + mconcat [ para "before" + , horizontalRule + , horizontalRule + , horizontalRule + , para "after" + ] + + , "Comment Block" =: + unlines [ "%%%" + , "stuff" + , "bla" + , "%%%"] =?> + (mempty::Blocks) + + + ] + + , testGroup "Lists" $ + [ "Simple Bullet Lists" =: + ("- Item1\n" ++ + "- Item2\n") =?> + bulletList [ plain "Item1" + , plain "Item2" + ] + + , "Indented Bullet Lists" =: + (" - Item1\n" ++ + " - Item2\n") =?> + bulletList [ plain "Item1" + , plain "Item2" + ] + + + + , "Nested Bullet Lists" =: + ("- Discovery\n" ++ + " + One More Time\n" ++ + " + Harder, Better, Faster, Stronger\n" ++ + "- Homework\n" ++ + " + Around the World\n"++ + "- Human After All\n" ++ + " + Technologic\n" ++ + " + Robot Rock\n") =?> + bulletList [ mconcat + [ plain "Discovery" + , orderedList [ plain ("One" <> space <> + "More" <> space <> + "Time") + , plain ("Harder," <> space <> + "Better," <> space <> + "Faster," <> space <> + "Stronger") + ] + ] + , mconcat + [ plain "Homework" + , orderedList [ plain ("Around" <> space <> + "the" <> space <> + "World") + ] + ] + , mconcat + [ plain ("Human" <> space <> "After" <> space <> "All") + , orderedList [ plain "Technologic" + , plain ("Robot" <> space <> "Rock") + ] + ] + ] + + , "Simple Ordered List" =: + ("+ Item1\n" ++ + "+ Item2\n") =?> + let listStyle = (1, DefaultStyle, DefaultDelim) + listStructure = [ plain "Item1" + , plain "Item2" + ] + in orderedListWith listStyle listStructure + + + , "Indented Ordered List" =: + (" + Item1\n" ++ + " + Item2\n") =?> + let listStyle = (1, DefaultStyle, DefaultDelim) + listStructure = [ plain "Item1" + , plain "Item2" + ] + in orderedListWith listStyle listStructure + + , "Nested Ordered Lists" =: + ("+ One\n" ++ + " + One-One\n" ++ + " + One-Two\n" ++ + "+ Two\n" ++ + " + Two-One\n"++ + " + Two-Two\n") =?> + let listStyle = (1, DefaultStyle, DefaultDelim) + listStructure = [ mconcat + [ plain "One" + , orderedList [ plain "One-One" + , plain "One-Two" + ] + ] + , mconcat + [ plain "Two" + , orderedList [ plain "Two-One" + , plain "Two-Two" + ] + ] + ] + in orderedListWith listStyle listStructure + + , "Ordered List in Bullet List" =: + ("- Emacs\n" ++ + " + Org\n") =?> + bulletList [ (plain "Emacs") <> + (orderedList [ plain "Org"]) + ] + + , "Bullet List in Ordered List" =: + ("+ GNU\n" ++ + " - Freedom\n") =?> + orderedList [ (plain "GNU") <> bulletList [ (plain "Freedom") ] ] + + , "Definition List" =: + unlines [ ": PLL" + , " phase-locked loop" + , ": TTL" + , " transistor-transistor logic" + , ": PSK" + , " a digital" + ] =?> + definitionList [ ("PLL", [ plain $ "phase-locked" <> space <> "loop" ]) + , ("TTL", [ plain $ "transistor-transistor" <> space <> "logic" ]) + , ("PSK", [ plain $ "a" <> space <> "digital" ]) + ] + + + , "Loose bullet list" =: + unlines [ "- apple" + , "" + , "- orange" + , "" + , "- peach" + ] =?> + bulletList [ para "apple" + , para "orange" + , para "peach" + ] + ] + + , testGroup "Tables" + [ "Single cell table" =: + "| Test " =?> + simpleTable' 1 mempty [[plain "Test"]] + + , "Multi cell table" =: + "| One | Two |" =?> + simpleTable' 2 mempty [ [ plain "One", plain "Two" ] ] + + , "Multi line table" =: + unlines [ "| One |" + , "| Two |" + , "| Three |" + ] =?> + simpleTable' 1 mempty + [ [ plain "One" ] + , [ plain "Two" ] + , [ plain "Three" ] + ] + + , "Empty table" =: + "| |" =?> + simpleTable' 1 mempty [[mempty]] + + , "Glider Table" =: + unlines [ "| 1 | 0 | 0 |" + , "| 0 | 1 | 1 |" + , "| 1 | 1 | 0 |" + ] =?> + simpleTable' 3 mempty + [ [ plain "1", plain "0", plain "0" ] + , [ plain "0", plain "1", plain "1" ] + , [ plain "1", plain "1", plain "0" ] + ] + + + , "Table with Header" =: + unlines [ "|| Species | Status |" + , "| cervisiae | domesticated |" + , "| paradoxus | wild |" + ] =?> + simpleTable [ plain "Species", plain "Status" ] + [ [ plain "cervisiae", plain "domesticated" ] + , [ plain "paradoxus", plain "wild" ] + ] + + , "Table alignment determined by spacing" =: + unlines [ "| Numbers | Text | More |" + , "| 1 | One | foo |" + , "| 2 | Two | bar |" + ] =?> + table "" (zip [AlignCenter, AlignRight, AlignDefault] [0, 0, 0]) + [] + [ [ plain "Numbers", plain "Text", plain "More" ] + , [ plain "1" , plain "One" , plain "foo" ] + , [ plain "2" , plain "Two" , plain "bar" ] + ] + + , "Pipe within text doesn't start a table" =: + "Ceci n'est pas une | pipe " =?> + para (spcSep [ "Ceci", "n'est", "pas", "une", "|", "pipe" ]) + + + , "Table with differing row lengths" =: + unlines [ "|| Numbers | Text " + , "| 1 | One | foo |" + , "| 2 " + ] =?> + table "" (zip [AlignCenter, AlignLeft, AlignLeft] [0, 0, 0]) + [ plain "Numbers", plain "Text" , plain mempty ] + [ [ plain "1" , plain "One" , plain "foo" ] + , [ plain "2" , plain mempty , plain mempty ] + ] + + ] + + , testGroup "Blocks and fragments" + [ "Source block" =: + unlines [ "```" + , "main = putStrLn greeting" + , " where greeting = \"moin\"" + , "```" ] =?> + let code' = "main = putStrLn greeting\n" ++ + " where greeting = \"moin\"\n" + in codeBlock code' + + , "tagged block" =: + unlines [ "'''" + , "<aside>HTML5 is pretty nice.</aside>" + , "'''" + ] =?> + rawBlock "html" "<aside>HTML5 is pretty nice.</aside>\n" + + , "Quote block" =: + unlines ["\t//Niemand// hat die Absicht, eine Mauer zu errichten!" + ] =?> + blockQuote (para (spcSep [ emph "Niemand", "hat", "die", "Absicht," + , "eine", "Mauer", "zu", "errichten!" + ])) + + ] + ] diff --git a/tests/Tests/Shared.hs b/tests/Tests/Shared.hs index f4bf13da4..9b55b7b1d 100644 --- a/tests/Tests/Shared.hs +++ b/tests/Tests/Shared.hs @@ -5,6 +5,11 @@ import Text.Pandoc.Shared import Test.Framework import Tests.Helpers import Tests.Arbitrary() +import Test.Framework.Providers.HUnit +import Test.HUnit ( assertBool, (@?=) ) +import Text.Pandoc.Builder +import Data.Monoid +import System.FilePath (joinPath) tests :: [Test] tests = [ testGroup "normalize" @@ -13,14 +18,44 @@ tests = [ testGroup "normalize" , property "p_normalize_no_trailing_spaces" p_normalize_no_trailing_spaces ] + , testGroup "compactify'DL" + [ testCase "compactify'DL with empty def" $ + assertBool "compactify'DL" + (let x = [(str "word", [para (str "def"), mempty])] + in compactify'DL x == x) + ] + , testGroup "collapseFilePath" testCollapse ] p_normalize_blocks_rt :: [Block] -> Bool -p_normalize_blocks_rt bs = normalize bs == normalize (normalize bs) +p_normalize_blocks_rt bs = + normalizeBlocks bs == normalizeBlocks (normalizeBlocks bs) p_normalize_inlines_rt :: [Inline] -> Bool -p_normalize_inlines_rt ils = normalize ils == normalize (normalize ils) +p_normalize_inlines_rt ils = + normalizeInlines ils == normalizeInlines (normalizeInlines ils) p_normalize_no_trailing_spaces :: [Inline] -> Bool p_normalize_no_trailing_spaces ils = null ils' || last ils' /= Space - where ils' = normalize $ ils ++ [Space] + where ils' = normalizeInlines $ ils ++ [Space] + +testCollapse :: [Test] +testCollapse = map (testCase "collapse") + [ (collapseFilePath (joinPath [ ""]) @?= (joinPath [ ""])) + , (collapseFilePath (joinPath [ ".","foo"]) @?= (joinPath [ "foo"])) + , (collapseFilePath (joinPath [ ".",".","..","foo"]) @?= (joinPath [ joinPath ["..", "foo"]])) + , (collapseFilePath (joinPath [ "..","foo"]) @?= (joinPath [ "..","foo"])) + , (collapseFilePath (joinPath [ "","bar","..","baz"]) @?= (joinPath [ "","baz"])) + , (collapseFilePath (joinPath [ "","..","baz"]) @?= (joinPath [ "","..","baz"])) + , (collapseFilePath (joinPath [ ".","foo","..",".","bar","..",".",".","baz"]) @?= (joinPath [ "baz"])) + , (collapseFilePath (joinPath [ ".",""]) @?= (joinPath [ ""])) + , (collapseFilePath (joinPath [ ".",".",""]) @?= (joinPath [ ""])) + , (collapseFilePath (joinPath [ "..",""]) @?= (joinPath [ ".."])) + , (collapseFilePath (joinPath [ "..",".",""]) @?= (joinPath [ ".."])) + , (collapseFilePath (joinPath [ ".","..",""]) @?= (joinPath [ ".."])) + , (collapseFilePath (joinPath [ "..","..",""]) @?= (joinPath [ "..",".."])) + , (collapseFilePath (joinPath [ "parent","foo","baz","..","bar"]) @?= (joinPath [ "parent","foo","bar"])) + , (collapseFilePath (joinPath [ "parent","foo","baz","..","..","bar"]) @?= (joinPath [ "parent","bar"])) + , (collapseFilePath (joinPath [ "parent","foo",".."]) @?= (joinPath [ "parent"])) + , (collapseFilePath (joinPath [ "","parent","foo","..","..","bar"]) @?= (joinPath [ "","bar"])) + , (collapseFilePath (joinPath [ "",".","parent","foo"]) @?= (joinPath [ "","parent","foo"]))] diff --git a/tests/Tests/Writers/AsciiDoc.hs b/tests/Tests/Writers/AsciiDoc.hs new file mode 100644 index 000000000..f9e6bd154 --- /dev/null +++ b/tests/Tests/Writers/AsciiDoc.hs @@ -0,0 +1,56 @@ +module Tests.Writers.AsciiDoc (tests) where + +import Test.Framework +import Text.Pandoc.Builder +import Text.Pandoc +import Tests.Helpers +import Tests.Arbitrary() +import Data.Monoid + +asciidoc :: (ToString a, ToPandoc a) => a -> String +asciidoc = writeAsciiDoc def{ writerWrapText = False } . toPandoc + +tests :: [Test] +tests = [ testGroup "emphasis" + [ test asciidoc "emph word before" $ + para (text "foo" <> emph (text "bar")) =?> + "foo__bar__" + , test asciidoc "emph word after" $ + para (emph (text "foo") <> text "bar") =?> + "__foo__bar" + , test asciidoc "emph quoted" $ + para (doubleQuoted (emph (text "foo"))) =?> + "``__foo__''" + , test asciidoc "strong word before" $ + para (text "foo" <> strong (text "bar")) =?> + "foo**bar**" + , test asciidoc "strong word after" $ + para (strong (text "foo") <> text "bar") =?> + "**foo**bar" + , test asciidoc "strong quoted" $ + para (singleQuoted (strong (text "foo"))) =?> + "`**foo**'" + ] + , testGroup "tables" + [ test asciidoc "empty cells" $ + simpleTable [] [[mempty],[mempty]] =?> unlines + [ "[cols=\"\",]" + , "|====" + , "|" + , "|" + , "|====" + ] + , test asciidoc "multiblock cells" $ + simpleTable [] [[para (text "Para 1") <> para (text "Para 2")]] + =?> unlines + [ "[cols=\"\",]" + , "|=====" + , "a|" + , "Para 1" + , "" + , "Para 2" + , "" + , "|=====" + ] + ] + ] diff --git a/tests/Tests/Writers/Docbook.hs b/tests/Tests/Writers/Docbook.hs new file mode 100644 index 000000000..97126b473 --- /dev/null +++ b/tests/Tests/Writers/Docbook.hs @@ -0,0 +1,229 @@ +{-# LANGUAGE OverloadedStrings #-} +module Tests.Writers.Docbook (tests) where + +import Test.Framework +import Text.Pandoc.Builder +import Text.Pandoc +import Tests.Helpers +import Tests.Arbitrary() + +docbook :: (ToString a, ToPandoc a) => a -> String +docbook = writeDocbook def{ writerWrapText = False } . toPandoc + +{- + "my test" =: X =?> Y + +is shorthand for + + test docbook "my test" $ X =?> Y + +which is in turn shorthand for + + test docbook "my test" (X,Y) +-} + +infix 4 =: +(=:) :: (ToString a, ToPandoc a) + => String -> (a, String) -> Test +(=:) = test docbook + +lineblock :: Blocks +lineblock = para ("some text" <> linebreak <> + "and more lines" <> linebreak <> + "and again") +lineblock_out :: [String] +lineblock_out = [ "<literallayout>some text" + , "and more lines" + , "and again</literallayout>" + ] + +tests :: [Test] +tests = [ testGroup "line blocks" + [ "none" =: para "This is a test" + =?> unlines + [ "<para>" + , " This is a test" + , "</para>" + ] + , "basic" =: lineblock + =?> unlines lineblock_out + , "blockquote" =: blockQuote lineblock + =?> unlines + ( [ "<blockquote>" ] ++ + lineblock_out ++ + [ "</blockquote>" ] + ) + , "footnote" =: para ("This is a test" <> + note lineblock <> + " of footnotes") + =?> unlines + ( [ "<para>" + , " This is a test<footnote>" ] ++ + lineblock_out ++ + [ " </footnote> of footnotes" + , "</para>" ] + ) + ] + , testGroup "compact lists" + [ testGroup "bullet" + [ "compact" =: bulletList [plain "a", plain "b", plain "c"] + =?> unlines + [ "<itemizedlist spacing=\"compact\">" + , " <listitem>" + , " <para>" + , " a" + , " </para>" + , " </listitem>" + , " <listitem>" + , " <para>" + , " b" + , " </para>" + , " </listitem>" + , " <listitem>" + , " <para>" + , " c" + , " </para>" + , " </listitem>" + , "</itemizedlist>" + ] + , "loose" =: bulletList [para "a", para "b", para "c"] + =?> unlines + [ "<itemizedlist>" + , " <listitem>" + , " <para>" + , " a" + , " </para>" + , " </listitem>" + , " <listitem>" + , " <para>" + , " b" + , " </para>" + , " </listitem>" + , " <listitem>" + , " <para>" + , " c" + , " </para>" + , " </listitem>" + , "</itemizedlist>" + ] + ] + , testGroup "ordered" + [ "compact" =: orderedList [plain "a", plain "b", plain "c"] + =?> unlines + [ "<orderedlist spacing=\"compact\">" + , " <listitem>" + , " <para>" + , " a" + , " </para>" + , " </listitem>" + , " <listitem>" + , " <para>" + , " b" + , " </para>" + , " </listitem>" + , " <listitem>" + , " <para>" + , " c" + , " </para>" + , " </listitem>" + , "</orderedlist>" + ] + , "loose" =: orderedList [para "a", para "b", para "c"] + =?> unlines + [ "<orderedlist>" + , " <listitem>" + , " <para>" + , " a" + , " </para>" + , " </listitem>" + , " <listitem>" + , " <para>" + , " b" + , " </para>" + , " </listitem>" + , " <listitem>" + , " <para>" + , " c" + , " </para>" + , " </listitem>" + , "</orderedlist>" + ] + ] + , testGroup "definition" + [ "compact" =: definitionList [ ("an", [plain "apple" ]) + , ("a", [plain "banana"]) + , ("an", [plain "orange"])] + =?> unlines + [ "<variablelist spacing=\"compact\">" + , " <varlistentry>" + , " <term>" + , " an" + , " </term>" + , " <listitem>" + , " <para>" + , " apple" + , " </para>" + , " </listitem>" + , " </varlistentry>" + , " <varlistentry>" + , " <term>" + , " a" + , " </term>" + , " <listitem>" + , " <para>" + , " banana" + , " </para>" + , " </listitem>" + , " </varlistentry>" + , " <varlistentry>" + , " <term>" + , " an" + , " </term>" + , " <listitem>" + , " <para>" + , " orange" + , " </para>" + , " </listitem>" + , " </varlistentry>" + , "</variablelist>" + ] + , "loose" =: definitionList [ ("an", [para "apple" ]) + , ("a", [para "banana"]) + , ("an", [para "orange"])] + =?> unlines + [ "<variablelist>" + , " <varlistentry>" + , " <term>" + , " an" + , " </term>" + , " <listitem>" + , " <para>" + , " apple" + , " </para>" + , " </listitem>" + , " </varlistentry>" + , " <varlistentry>" + , " <term>" + , " a" + , " </term>" + , " <listitem>" + , " <para>" + , " banana" + , " </para>" + , " </listitem>" + , " </varlistentry>" + , " <varlistentry>" + , " <term>" + , " an" + , " </term>" + , " <listitem>" + , " <para>" + , " orange" + , " </para>" + , " </listitem>" + , " </varlistentry>" + , "</variablelist>" + ] + ] + ] + ] diff --git a/tests/Tests/Writers/LaTeX.hs b/tests/Tests/Writers/LaTeX.hs index 8cc957620..6d46a15d2 100644 --- a/tests/Tests/Writers/LaTeX.hs +++ b/tests/Tests/Writers/LaTeX.hs @@ -8,7 +8,7 @@ import Tests.Helpers import Tests.Arbitrary() latex :: (ToString a, ToPandoc a) => a -> String -latex = writeLaTeX def . toPandoc +latex = writeLaTeX def{ writerHighlight = True } . toPandoc latexListing :: (ToString a, ToPandoc a) => a -> String latexListing = writeLaTeX def{ writerListings = True } . toPandoc @@ -46,12 +46,34 @@ tests = [ testGroup "code blocks" ] , testGroup "math" [ "escape |" =: para (math "\\sigma|_{\\{x\\}}") =?> - "$\\sigma|_{\\{x\\}}$" + "\\(\\sigma|_{\\{x\\}}\\)" ] , testGroup "headers" [ "unnumbered header" =: headerWith ("foo",["unnumbered"],[]) 1 (text "Header 1" <> note (plain $ text "note")) =?> "\\section*{\\texorpdfstring{Header 1\\footnote{note}}{Header 1}}\\label{foo}\n\\addcontentsline{toc}{section}{Header 1}\n" + , "in list item" =: + bulletList [header 2 (text "foo")] =?> + "\\begin{itemize}\n\\item ~\n \\subsection{foo}\n\\end{itemize}" + , "in definition list item" =: + definitionList [(text "foo", [header 2 (text "bar"), + para $ text "baz"])] =?> + "\\begin{description}\n\\item[foo] ~ \n\\subsection{bar}\n\nbaz\n\\end{description}" + , "containing image" =: + header 1 (image "imgs/foo.jpg" "" (text "Alt text")) =?> + "\\section{\\protect\\includegraphics{imgs/foo.jpg}}" + ] + , testGroup "inline code" + [ "struck out and highlighted" =: + strikeout (codeWith ("",["haskell"],[]) "foo" <> space + <> str "bar") =?> + "\\sout{\\mbox{\\VERB|\\NormalTok{foo}|} bar}" + , "struck out and not highlighted" =: + strikeout (code "foo" <> space + <> str "bar") =?> + "\\sout{\\texttt{foo} bar}" + , "single quotes" =: + code "dog's" =?> "\\texttt{dog\\textquotesingle{}s}" ] ] diff --git a/tests/Tests/Writers/Plain.hs b/tests/Tests/Writers/Plain.hs new file mode 100644 index 000000000..f8f1d3d90 --- /dev/null +++ b/tests/Tests/Writers/Plain.hs @@ -0,0 +1,21 @@ +{-# LANGUAGE OverloadedStrings #-} +module Tests.Writers.Plain (tests) where + +import Test.Framework +import Text.Pandoc.Builder +import Text.Pandoc +import Tests.Helpers +import Tests.Arbitrary() + + +infix 4 =: +(=:) :: (ToString a, ToPandoc a) + => String -> (a, String) -> Test +(=:) = test (writePlain def . toPandoc) + + +tests :: [Test] +tests = [ "strongly emphasized text to uppercase" + =: strong "Straße" + =?> "STRASSE" + ] diff --git a/tests/docbook-reader.docbook b/tests/docbook-reader.docbook index 6173fa50e..cf5059646 100644 --- a/tests/docbook-reader.docbook +++ b/tests/docbook-reader.docbook @@ -4,14 +4,16 @@ <article> <articleinfo> <title>Pandoc Test Suite</title> - <author> - <firstname>John</firstname> - <surname>MacFarlane</surname> - </author> - <author> - <firstname></firstname> - <surname>Anonymous</surname> - </author> + <authorgroup> + <author> + <firstname>John</firstname> + <surname>MacFarlane</surname> + </author> + <author> + <firstname></firstname> + <surname>Anonymous</surname> + </author> + </authorgroup> <date>July 17, 2006</date> </articleinfo> <para> @@ -87,6 +89,9 @@ sub status { print "working"; } </programlisting> + <screen> +% <command>ls</command> +</screen> <para> A list: </para> @@ -504,6 +509,25 @@ These should not be escaped: \$ \\ \> \[ \{ B. Williams </para> </sect2> + <sect2 id="callout"> + <title>Callout</title> + <para>Simple.</para> + <calloutlist> + <callout arearefs="loop1-letrec-co" id="loop1-letrec"> + <para id="x_QA1">A <code>__letrec</code> is equivalent to a normal + Haskell &let;.</para> + </callout> + <callout arearefs="loop1-def-co" id="loop1-def"> + <para id="x_RA1">&GHC; compiled the body of our list comprehension into + a loop named <function>go_s1YC</function>.</para> + </callout> + <callout arearefs="loop1-pat-empty-co" id="loop1-pat-empty"> + <para id="x_SA1">If our &case; expression matches the empty list, we + return the empty list. This is reassuringly + familiar.</para> + </callout> + </calloutlist> + </sect2> </sect1> <sect1 id="definition-lists"> <title>Definition Lists</title> @@ -686,6 +710,9 @@ These should not be escaped: \$ \\ \> \[ \{ <literal><html></literal>. </para> <para> + More code: <classname>Class</classname> and <type>Type</type> + </para> + <para> <emphasis role="strikethrough">This is <emphasis>strikeout</emphasis>.</emphasis> </para> @@ -726,6 +753,54 @@ These should not be escaped: \$ \\ \> \[ \{ Ellipses…and…and…. </para> </sect1> +<sect1 id="math"> + <para> + <equation> + <mml:math> + <mml:mrow> + <mml:mi>e</mml:mi> + <mml:mo>=</mml:mo> + <mml:mi>m</mml:mi> + <mml:msup> + <mml:mi>c</mml:mi> + <mml:mn>2</mml:mn> + </mml:msup> + </mml:mrow> + </mml:math> + <mml:math> + <mrow> + <mn>1</mn> + </mrow> + </mml:math> + </equation> + <inlineequation> + <mml:math> + <mml:mrow> + <mml:mi>e</mml:mi> + <mml:mo>=</mml:mo> + <mml:mi>m</mml:mi> + <mml:msup> + <mml:mi>c</mml:mi> + <mml:mn>2</mml:mn> + </mml:msup> + </mml:mrow> + </mml:math> + </inlineequation> + <informalequation> + <mml:math> + <mml:mrow> + <mml:mi>e</mml:mi> + <mml:mo>=</mml:mo> + <mml:mi>m</mml:mi> + <mml:msup> + <mml:mi>c</mml:mi> + <mml:mn>2</mml:mn> + </mml:msup> + </mml:mrow> + </mml:math> + </informalequation> + </para> +</sect1> <sect1 id="special-characters"> <title>Special Characters</title> <para> diff --git a/tests/docbook-reader.native b/tests/docbook-reader.native index 2d29bb154..353a352a2 100644 --- a/tests/docbook-reader.native +++ b/tests/docbook-reader.native @@ -1,28 +1,29 @@ Pandoc (Meta {unMeta = fromList [("author",MetaList [MetaInlines [Str "John",Space,Str "MacFarlane"],MetaInlines [Str "Anonymous"]]),("date",MetaInlines [Str "July",Space,Str "17,",Space,Str "2006"]),("title",MetaInlines [Str "Pandoc",Space,Str "Test",Space,Str "Suite"])]}) [Para [Str "This",Space,Str "is",Space,Str "a",Space,Str "set",Space,Str "of",Space,Str "tests",Space,Str "for",Space,Str "pandoc.",Space,Str "Most",Space,Str "of",Space,Str "them",Space,Str "are",Space,Str "adapted",Space,Str "from",Space,Str "John",Space,Str "Gruber\8217s",Space,Str "markdown",Space,Str "test",Space,Str "suite."] -,Header 1 ("",[],[]) [Str "Headers"] -,Header 2 ("",[],[]) [Str "Level",Space,Str "2",Space,Str "with",Space,Str "an",Space,Link [Str "embedded",Space,Str "link"] ("/url","")] -,Header 3 ("",[],[]) [Str "Level",Space,Str "3",Space,Str "with",Space,Emph [Str "emphasis"]] -,Header 4 ("",[],[]) [Str "Level",Space,Str "4"] -,Header 5 ("",[],[]) [Str "Level",Space,Str "5"] +,Header 1 ("headers",[],[]) [Str "Headers"] +,Header 2 ("level-2-with-an-embedded-link",[],[]) [Str "Level",Space,Str "2",Space,Str "with",Space,Str "an",Space,Link [Str "embedded",Space,Str "link"] ("/url","")] +,Header 3 ("level-3-with-emphasis",[],[]) [Str "Level",Space,Str "3",Space,Str "with",Space,Emph [Str "emphasis"]] +,Header 4 ("level-4",[],[]) [Str "Level",Space,Str "4"] +,Header 5 ("level-5",[],[]) [Str "Level",Space,Str "5"] ,Para [Str "Hi."] -,Header 1 ("",[],[]) [Str "Level",Space,Str "1"] -,Header 2 ("",[],[]) [Str "Level",Space,Str "2",Space,Str "with",Space,Emph [Str "emphasis"]] -,Header 3 ("",[],[]) [Str "Level",Space,Str "3"] +,Header 1 ("level-1",[],[]) [Str "Level",Space,Str "1"] +,Header 2 ("level-2-with-emphasis",[],[]) [Str "Level",Space,Str "2",Space,Str "with",Space,Emph [Str "emphasis"]] +,Header 3 ("level-3",[],[]) [Str "Level",Space,Str "3"] ,Para [Str "with",Space,Str "no",Space,Str "blank",Space,Str "line"] -,Header 2 ("",[],[]) [Str "Level",Space,Str "2"] +,Header 2 ("level-2",[],[]) [Str "Level",Space,Str "2"] ,Para [Str "with",Space,Str "no",Space,Str "blank",Space,Str "line"] -,Header 1 ("",[],[]) [Str "Paragraphs"] +,Header 1 ("paragraphs",[],[]) [Str "Paragraphs"] ,Para [Str "Here\8217s",Space,Str "a",Space,Str "regular",Space,Str "paragraph."] ,Para [Str "In",Space,Str "Markdown",Space,Str "1.0.0",Space,Str "and",Space,Str "earlier.",Space,Str "Version",Space,Str "8.",Space,Str "This",Space,Str "line",Space,Str "turns",Space,Str "into",Space,Str "a",Space,Str "list",Space,Str "item.",Space,Str "Because",Space,Str "a",Space,Str "hard-wrapped",Space,Str "line",Space,Str "in",Space,Str "the",Space,Str "middle",Space,Str "of",Space,Str "a",Space,Str "paragraph",Space,Str "looked",Space,Str "like",Space,Str "a",Space,Str "list",Space,Str "item."] ,Para [Str "Here\8217s",Space,Str "one",Space,Str "with",Space,Str "a",Space,Str "bullet.",Space,Str "*",Space,Str "criminey."] -,Header 1 ("",[],[]) [Str "Block",Space,Str "Quotes"] +,Header 1 ("block-quotes",[],[]) [Str "Block",Space,Str "Quotes"] ,Para [Str "E-mail",Space,Str "style:"] ,BlockQuote [Para [Str "This",Space,Str "is",Space,Str "a",Space,Str "block",Space,Str "quote.",Space,Str "It",Space,Str "is",Space,Str "pretty",Space,Str "short."]] ,BlockQuote [Para [Str "Code",Space,Str "in",Space,Str "a",Space,Str "block",Space,Str "quote:"] ,CodeBlock ("",[],[]) "sub status {\n print \"working\";\n}" + ,CodeBlock ("",[],[]) "% ls" ,Para [Str "A",Space,Str "list:"] ,OrderedList (1,Decimal,DefaultDelim) [[Para [Str "item",Space,Str "one"]] @@ -34,13 +35,13 @@ Pandoc (Meta {unMeta = fromList [("author",MetaList [MetaInlines [Str "John",Spa [Para [Str "nested"]]] ,Para [Str "This",Space,Str "should",Space,Str "not",Space,Str "be",Space,Str "a",Space,Str "block",Space,Str "quote:",Space,Str "2",Space,Str ">",Space,Str "1."] ,Para [Str "And",Space,Str "a",Space,Str "following",Space,Str "paragraph."] -,Header 1 ("",[],[]) [Str "Code",Space,Str "Blocks"] +,Header 1 ("code-blocks",[],[]) [Str "Code",Space,Str "Blocks"] ,Para [Str "Code:"] ,CodeBlock ("",[],[]) "---- (should be four hyphens)\n\nsub status {\n print \"working\";\n}\n\nthis code block is indented by one tab" ,Para [Str "And:"] ,CodeBlock ("",[],[]) " this code block is indented by two tabs\n\nThese should not be escaped: \\$ \\\\ \\> \\[ \\{" -,Header 1 ("",[],[]) [Str "Lists"] -,Header 2 ("",[],[]) [Str "Unordered"] +,Header 1 ("lists",[],[]) [Str "Lists"] +,Header 2 ("unordered",[],[]) [Str "Unordered"] ,Para [Str "Asterisks",Space,Str "loose:"] ,BulletList [[Para [Str "asterisk",Space,Str "1"]] @@ -56,7 +57,7 @@ Pandoc (Meta {unMeta = fromList [("author",MetaList [MetaInlines [Str "John",Spa [[Para [Str "Minus",Space,Str "1"]] ,[Para [Str "Minus",Space,Str "2"]] ,[Para [Str "Minus",Space,Str "3"]]] -,Header 2 ("",[],[]) [Str "Ordered"] +,Header 2 ("ordered",[],[]) [Str "Ordered"] ,OrderedList (1,Decimal,DefaultDelim) [[Para [Str "First"]] ,[Para [Str "Second"]] @@ -72,7 +73,7 @@ Pandoc (Meta {unMeta = fromList [("author",MetaList [MetaInlines [Str "John",Spa ,Para [Str "Item",Space,Str "1.",Space,Str "graf",Space,Str "two.",Space,Str "The",Space,Str "quick",Space,Str "brown",Space,Str "fox",Space,Str "jumped",Space,Str "over",Space,Str "the",Space,Str "lazy",Space,Str "dog\8217s",Space,Str "back."]] ,[Para [Str "Item",Space,Str "2."]] ,[Para [Str "Item",Space,Str "3."]]] -,Header 2 ("",[],[]) [Str "Nested"] +,Header 2 ("nested",[],[]) [Str "Nested"] ,BulletList [[Para [Str "Tab"] ,BulletList @@ -97,14 +98,14 @@ Pandoc (Meta {unMeta = fromList [("author",MetaList [MetaInlines [Str "John",Spa ,[Para [Str "Fie"]] ,[Para [Str "Foe"]]]] ,[Para [Str "Third"]]] -,Header 2 ("",[],[]) [Str "Tabs",Space,Str "and",Space,Str "spaces"] +,Header 2 ("tabs-and-spaces",[],[]) [Str "Tabs",Space,Str "and",Space,Str "spaces"] ,BulletList [[Para [Str "this",Space,Str "is",Space,Str "a",Space,Str "list",Space,Str "item",Space,Str "indented",Space,Str "with",Space,Str "tabs"]] ,[Para [Str "this",Space,Str "is",Space,Str "a",Space,Str "list",Space,Str "item",Space,Str "indented",Space,Str "with",Space,Str "spaces"] ,BulletList [[Para [Str "this",Space,Str "is",Space,Str "an",Space,Str "example",Space,Str "list",Space,Str "item",Space,Str "indented",Space,Str "with",Space,Str "tabs"]] ,[Para [Str "this",Space,Str "is",Space,Str "an",Space,Str "example",Space,Str "list",Space,Str "item",Space,Str "indented",Space,Str "with",Space,Str "spaces"]]]]] -,Header 2 ("",[],[]) [Str "Fancy",Space,Str "list",Space,Str "markers"] +,Header 2 ("fancy-list-markers",[],[]) [Str "Fancy",Space,Str "list",Space,Str "markers"] ,OrderedList (2,Decimal,DefaultDelim) [[Para [Str "begins",Space,Str "with",Space,Str "2"]] ,[Para [Str "and",Space,Str "now",Space,Str "3"] @@ -133,7 +134,13 @@ Pandoc (Meta {unMeta = fromList [("author",MetaList [MetaInlines [Str "John",Spa ,Para [Str "Should",Space,Str "not",Space,Str "be",Space,Str "a",Space,Str "list",Space,Str "item:"] ,Para [Str "M.A.\160\&2007"] ,Para [Str "B.",Space,Str "Williams"] -,Header 1 ("",[],[]) [Str "Definition",Space,Str "Lists"] +,Header 2 ("callout",[],[]) [Str "Callout"] +,Para [Str "Simple."] +,BulletList + [[Para [Str "A",Space,Code ("",[],[]) "__letrec",Space,Str "is",Space,Str "equivalent",Space,Str "to",Space,Str "a",Space,Str "normal",Space,Str "Haskell",Space,Str "LET."]] + ,[Para [Str "GHC",Space,Str "compiled",Space,Str "the",Space,Str "body",Space,Str "of",Space,Str "our",Space,Str "list",Space,Str "comprehension",Space,Str "into",Space,Str "a",Space,Str "loop",Space,Str "named",Space,Code ("",[],[]) "go_s1YC",Str "."]] + ,[Para [Str "If",Space,Str "our",Space,Str "CASE",Space,Str "expression",Space,Str "matches",Space,Str "the",Space,Str "empty",Space,Str "list,",Space,Str "we",Space,Str "return",Space,Str "the",Space,Str "empty",Space,Str "list.",Space,Str "This",Space,Str "is",Space,Str "reassuringly",Space,Str "familiar."]]] +,Header 1 ("definition-lists",[],[]) [Str "Definition",Space,Str "Lists"] ,DefinitionList [([Str "apple"], [[Para [Str "red",Space,Str "fruit"]]]) @@ -169,7 +176,7 @@ Pandoc (Meta {unMeta = fromList [("author",MetaList [MetaInlines [Str "John",Spa ,OrderedList (1,Decimal,DefaultDelim) [[Para [Str "sublist"]] ,[Para [Str "sublist"]]]]])] -,Header 1 ("",[],[]) [Str "Inline",Space,Str "Markup"] +,Header 1 ("inline-markup",[],[]) [Str "Inline",Space,Str "Markup"] ,Para [Str "This",Space,Str "is",Space,Emph [Str "emphasized"],Str ",",Space,Str "and",Space,Str "so",Space,Emph [Str "is",Space,Str "this"],Str "."] ,Para [Str "This",Space,Str "is",Space,Strong [Str "strong"],Str ",",Space,Str "and",Space,Str "so",Space,Strong [Str "is",Space,Str "this"],Str "."] ,Para [Str "An",Space,Emph [Link [Str "emphasized",Space,Str "link"] ("/url","")],Str "."] @@ -178,18 +185,21 @@ Pandoc (Meta {unMeta = fromList [("author",MetaList [MetaInlines [Str "John",Spa ,Para [Strong [Emph [Str "This",Space,Str "is",Space,Str "strong",Space,Str "and",Space,Str "em."]]] ,Para [Str "So",Space,Str "is",Space,Strong [Emph [Str "this"]],Space,Str "word."] ,Para [Str "This",Space,Str "is",Space,Str "code:",Space,Code ("",[],[]) ">",Str ",",Space,Code ("",[],[]) "$",Str ",",Space,Code ("",[],[]) "\\",Str ",",Space,Code ("",[],[]) "\\$",Str ",",Space,Code ("",[],[]) "<html>",Str "."] +,Para [Str "More",Space,Str "code:",Space,Code ("",[],[]) "Class",Space,Str "and",Space,Code ("",[],[]) "Type"] ,Para [Strikeout [Str "This",Space,Str "is",Space,Emph [Str "strikeout"],Str "."]] ,Para [Str "Superscripts:",Space,Str "a",Superscript [Str "bc"],Str "d",Space,Str "a",Superscript [Emph [Str "hello"]],Space,Str "a",Superscript [Str "hello\160there"],Str "."] ,Para [Str "Subscripts:",Space,Str "H",Subscript [Str "2"],Str "O,",Space,Str "H",Subscript [Str "23"],Str "O,",Space,Str "H",Subscript [Str "many\160of\160them"],Str "O."] ,Para [Str "These",Space,Str "should",Space,Str "not",Space,Str "be",Space,Str "superscripts",Space,Str "or",Space,Str "subscripts,",Space,Str "because",Space,Str "of",Space,Str "the",Space,Str "unescaped",Space,Str "spaces:",Space,Str "a^b",Space,Str "c^d,",Space,Str "a~b",Space,Str "c~d."] -,Header 1 ("",[],[]) [Str "Smart",Space,Str "quotes,",Space,Str "ellipses,",Space,Str "dashes"] +,Header 1 ("smart-quotes-ellipses-dashes",[],[]) [Str "Smart",Space,Str "quotes,",Space,Str "ellipses,",Space,Str "dashes"] ,Para [Quoted DoubleQuote [Str "Hello,"],Space,Str "said",Space,Str "the",Space,Str "spider.",Space,Quoted DoubleQuote [Quoted SingleQuote [Str "Shelob"],Space,Str "is",Space,Str "my",Space,Str "name."]] ,Para [Quoted DoubleQuote [Str "A"],Str ",",Space,Quoted DoubleQuote [Str "B"],Str ",",Space,Str "and",Space,Quoted DoubleQuote [Str "C"],Space,Str "are",Space,Str "letters."] ,Para [Quoted DoubleQuote [Str "He",Space,Str "said,",Space,Quoted SingleQuote [Str "I",Space,Str "want",Space,Str "to",Space,Str "go."]],Space,Str "Were",Space,Str "you",Space,Str "alive",Space,Str "in",Space,Str "the",Space,Str "70\8217s?"] ,Para [Str "Some",Space,Str "dashes:",Space,Str "one\8212two",Space,Str "\8212",Space,Str "three\8212four",Space,Str "\8212",Space,Str "five."] ,Para [Str "Dashes",Space,Str "between",Space,Str "numbers:",Space,Str "5\8211\&7,",Space,Str "255\8211\&66,",Space,Str "1987\8211\&1999."] ,Para [Str "Ellipses\8230and\8230and\8230."] -,Header 1 ("",[],[]) [Str "Special",Space,Str "Characters"] +,Header 1 ("math",[],[]) [] +,Para [Math DisplayMath "e = mc^{2}",Math DisplayMath "1",Space,Math InlineMath "e = mc^{2}",Space,Math DisplayMath "e = mc^{2}"] +,Header 1 ("special-characters",[],[]) [Str "Special",Space,Str "Characters"] ,Para [Str "Here",Space,Str "is",Space,Str "some",Space,Str "unicode:"] ,BulletList [[Para [Str "I",Space,Str "hat:",Space,Str "\206"]] @@ -218,8 +228,8 @@ Pandoc (Meta {unMeta = fromList [("author",MetaList [MetaInlines [Str "John",Spa ,Para [Str "Bang:",Space,Str "!"] ,Para [Str "Plus:",Space,Str "+"] ,Para [Str "Minus:",Space,Str "-"] -,Header 1 ("",[],[]) [Str "Links"] -,Header 2 ("",[],[]) [Str "Explicit"] +,Header 1 ("links",[],[]) [Str "Links"] +,Header 2 ("explicit",[],[]) [Str "Explicit"] ,Para [Str "Just",Space,Str "a",Space,Link [Str "URL"] ("/url/",""),Str "."] ,Para [Link [Str "URL",Space,Str "and",Space,Str "title"] ("/url/",""),Str "."] ,Para [Link [Str "URL",Space,Str "and",Space,Str "title"] ("/url/",""),Str "."] @@ -229,7 +239,7 @@ Pandoc (Meta {unMeta = fromList [("author",MetaList [MetaInlines [Str "John",Spa ,Para [Link [Str "with_underscore"] ("/url/with_underscore","")] ,Para [Link [Str "nobody@nowhere.net"] ("mailto:nobody@nowhere.net","")] ,Para [Link [Str "Empty"] ("",""),Str "."] -,Header 2 ("",[],[]) [Str "Reference"] +,Header 2 ("reference",[],[]) [Str "Reference"] ,Para [Str "Foo",Space,Link [Str "bar"] ("/url/",""),Str "."] ,Para [Str "Foo",Space,Link [Str "bar"] ("/url/",""),Str "."] ,Para [Str "Foo",Space,Link [Str "bar"] ("/url/",""),Str "."] @@ -242,12 +252,12 @@ Pandoc (Meta {unMeta = fromList [("author",MetaList [MetaInlines [Str "John",Spa ,CodeBlock ("",[],[]) "[not]: /url" ,Para [Str "Foo",Space,Link [Str "bar"] ("/url/",""),Str "."] ,Para [Str "Foo",Space,Link [Str "biz"] ("/url/",""),Str "."] -,Header 2 ("",[],[]) [Str "With",Space,Str "ampersands"] +,Header 2 ("with-ampersands",[],[]) [Str "With",Space,Str "ampersands"] ,Para [Str "Here\8217s",Space,Str "a",Space,Link [Str "link",Space,Str "with",Space,Str "an",Space,Str "ampersand",Space,Str "in",Space,Str "the",Space,Str "URL"] ("http://example.com/?foo=1&bar=2",""),Str "."] ,Para [Str "Here\8217s",Space,Str "a",Space,Str "link",Space,Str "with",Space,Str "an",Space,Str "amersand",Space,Str "in",Space,Str "the",Space,Str "link",Space,Str "text:",Space,Link [Str "AT&T"] ("http://att.com/",""),Str "."] ,Para [Str "Here\8217s",Space,Str "an",Space,Link [Str "inline",Space,Str "link"] ("/script?foo=1&bar=2",""),Str "."] ,Para [Str "Here\8217s",Space,Str "an",Space,Link [Str "inline",Space,Str "link",Space,Str "in",Space,Str "pointy",Space,Str "braces"] ("/script?foo=1&bar=2",""),Str "."] -,Header 2 ("",[],[]) [Str "Autolinks"] +,Header 2 ("autolinks",[],[]) [Str "Autolinks"] ,Para [Str "With",Space,Str "an",Space,Str "ampersand:",Space,Link [Str "http://example.com/?foo=1&bar=2"] ("http://example.com/?foo=1&bar=2","")] ,BulletList [[Para [Str "In",Space,Str "a",Space,Str "list?"]] @@ -258,18 +268,18 @@ Pandoc (Meta {unMeta = fromList [("author",MetaList [MetaInlines [Str "John",Spa [Para [Str "Blockquoted:",Space,Link [Str "http://example.com/"] ("http://example.com/","")]] ,Para [Str "Auto-links",Space,Str "should",Space,Str "not",Space,Str "occur",Space,Str "here:",Space,Code ("",[],[]) "<http://example.com/>"] ,CodeBlock ("",[],[]) "or here: <http://example.com/>" -,Header 1 ("",[],[]) [Str "Images"] +,Header 1 ("images",[],[]) [Str "Images"] ,Para [Str "From",Space,Quoted DoubleQuote [Str "Voyage",Space,Str "dans",Space,Str "la",Space,Str "Lune"],Space,Str "by",Space,Str "Georges",Space,Str "Melies",Space,Str "(1902):"] ,Para [Image [Str "lalune"] ("lalune.jpg","")] ,Para [Str "Here",Space,Str "is",Space,Str "a",Space,Str "movie",Space,Image [] ("movie.jpg",""),Space,Str "icon."] -,Header 1 ("",[],[]) [Str "Footnotes"] +,Header 1 ("footnotes",[],[]) [Str "Footnotes"] ,Para [Str "Here",Space,Str "is",Space,Str "a",Space,Str "footnote",Space,Str "reference,",Note [Para [Str "Here",Space,Str "is",Space,Str "the",Space,Str "footnote.",Space,Str "It",Space,Str "can",Space,Str "go",Space,Str "anywhere",Space,Str "after",Space,Str "the",Space,Str "footnote",Space,Str "reference.",Space,Str "It",Space,Str "need",Space,Str "not",Space,Str "be",Space,Str "placed",Space,Str "at",Space,Str "the",Space,Str "end",Space,Str "of",Space,Str "the",Space,Str "document."]],Space,Str "and",Space,Str "another.",Note [Para [Str "Here\8217s",Space,Str "the",Space,Str "long",Space,Str "note.",Space,Str "This",Space,Str "one",Space,Str "contains",Space,Str "multiple",Space,Str "blocks."],Para [Str "Subsequent",Space,Str "blocks",Space,Str "are",Space,Str "indented",Space,Str "to",Space,Str "show",Space,Str "that",Space,Str "they",Space,Str "belong",Space,Str "to",Space,Str "the",Space,Str "footnote",Space,Str "(as",Space,Str "with",Space,Str "list",Space,Str "items)."],CodeBlock ("",[],[]) " { <code> }",Para [Str "If",Space,Str "you",Space,Str "want,",Space,Str "you",Space,Str "can",Space,Str "indent",Space,Str "every",Space,Str "line,",Space,Str "but",Space,Str "you",Space,Str "can",Space,Str "also",Space,Str "be",Space,Str "lazy",Space,Str "and",Space,Str "just",Space,Str "indent",Space,Str "the",Space,Str "first",Space,Str "line",Space,Str "of",Space,Str "each",Space,Str "block."]],Space,Str "This",Space,Str "should",Space,Emph [Str "not"],Space,Str "be",Space,Str "a",Space,Str "footnote",Space,Str "reference,",Space,Str "because",Space,Str "it",Space,Str "contains",Space,Str "a",Space,Str "space.[^my",Space,Str "note]",Space,Str "Here",Space,Str "is",Space,Str "an",Space,Str "inline",Space,Str "note.",Note [Para [Str "This",Space,Str "is",Space,Emph [Str "easier"],Space,Str "to",Space,Str "type.",Space,Str "Inline",Space,Str "notes",Space,Str "may",Space,Str "contain",Space,Link [Str "links"] ("http://google.com",""),Space,Str "and",Space,Code ("",[],[]) "]",Space,Str "verbatim",Space,Str "characters,",Space,Str "as",Space,Str "well",Space,Str "as",Space,Str "[bracketed",Space,Str "text]."]]] ,BlockQuote [Para [Str "Notes",Space,Str "can",Space,Str "go",Space,Str "in",Space,Str "quotes.",Note [Para [Str "In",Space,Str "quote."]]]] ,OrderedList (1,Decimal,DefaultDelim) [[Para [Str "And",Space,Str "in",Space,Str "list",Space,Str "items.",Note [Para [Str "In",Space,Str "list."]]]]] ,Para [Str "This",Space,Str "paragraph",Space,Str "should",Space,Str "not",Space,Str "be",Space,Str "part",Space,Str "of",Space,Str "the",Space,Str "note,",Space,Str "as",Space,Str "it",Space,Str "is",Space,Str "not",Space,Str "indented."] -,Header 1 ("",[],[]) [Str "Tables"] +,Header 1 ("tables",[],[]) [Str "Tables"] ,Para [Str "Simple",Space,Str "table",Space,Str "with",Space,Str "caption:"] ,Table [Str "Demonstration",Space,Str "of",Space,Str "simple",Space,Str "table",Space,Str "syntax."] [AlignRight,AlignLeft,AlignCenter,AlignLeft] [0.0,0.0,0.0,0.0] [[Plain [Str "Right"]] diff --git a/tests/docx/already_auto_ident.docx b/tests/docx/already_auto_ident.docx Binary files differnew file mode 100644 index 000000000..ec2b348d7 --- /dev/null +++ b/tests/docx/already_auto_ident.docx diff --git a/tests/docx/already_auto_ident.native b/tests/docx/already_auto_ident.native new file mode 100644 index 000000000..054bfe34a --- /dev/null +++ b/tests/docx/already_auto_ident.native @@ -0,0 +1,2 @@ +[Header 1 ("anchor-header",[],[]) [Str "Anchor",Space,Str "Header"] +,Para [Str "A",Space,Link [Str "link"] ("#anchor-header","")]] diff --git a/tests/docx/block_quotes.docx b/tests/docx/block_quotes.docx Binary files differnew file mode 100644 index 000000000..729ae1f43 --- /dev/null +++ b/tests/docx/block_quotes.docx diff --git a/tests/docx/block_quotes_parse_indent.native b/tests/docx/block_quotes_parse_indent.native new file mode 100644 index 000000000..842b3606a --- /dev/null +++ b/tests/docx/block_quotes_parse_indent.native @@ -0,0 +1,8 @@ +[Header 2 ("some-block-quotes-in-different-ways",[],[]) [Str "Some",Space,Str "block",Space,Str "quotes,",Space,Str "in",Space,Str "different",Space,Str "ways"] +,Para [Str "This",Space,Str "is",Space,Str "the",Space,Str "proper",Space,Str "way,",Space,Str "with",Space,Str "a",Space,Str "style"] +,BlockQuote + [Para [Str "I",Space,Str "don\8217t",Space,Str "know",Space,Str "why",Space,Str "this",Space,Str "would",Space,Str "be",Space,Str "in",Space,Str "italics,",Space,Str "but",Space,Str "so",Space,Str "it",Space,Str "appears",Space,Str "to",Space,Str "be",Space,Str "on",Space,Str "my",Space,Str "screen."]] +,Para [Str "And",Space,Str "this",Space,Str "is",Space,Str "the",Space,Str "way",Space,Str "that",Space,Str "most",Space,Str "people",Space,Str "do",Space,Str "it:"] +,BlockQuote + [Para [Str "I",Space,Str "just",Space,Str "indented",Space,Str "this,",Space,Str "so",Space,Str "it",Space,Str "looks",Space,Str "like",Space,Str "a",Space,Str "block",Space,Str "quote.",Space,Str "I",Space,Str "think",Space,Str "this",Space,Str "is",Space,Str "how",Space,Str "most",Space,Str "people",Space,Str "do",Space,Str "block",Space,Str "quotes",Space,Str "in",Space,Str "their",Space,Str "documents."]] +,Para [Str "And",Space,Str "back",Space,Str "to",Space,Str "the",Space,Str "normal",Space,Str "style."]] diff --git a/tests/docx/char_styles.docx b/tests/docx/char_styles.docx Binary files differnew file mode 100644 index 000000000..05979b9a7 --- /dev/null +++ b/tests/docx/char_styles.docx diff --git a/tests/docx/char_styles.native b/tests/docx/char_styles.native new file mode 100644 index 000000000..7dfc208fb --- /dev/null +++ b/tests/docx/char_styles.native @@ -0,0 +1,4 @@ +[Para [Emph [Str "This",Space,Str "is",Space,Str "all",Space,Str "in",Space,Str "an"],Space,Emph [Strong [Str "italic",Space,Str "style"],Str "."]] +,Para [Emph [Str "This",Space,Str "is",Space,Str "an",Space,Str "italic"],Space,Str "style",Space,Emph [Str "with",Space,Str "some"],Space,Str "words",Space,Emph [Str "unitalicized."]] +,Para [Strong [Str "This",Space,Str "is",Space,Str "all",Space,Str "in",Space,Str "a",Space,Emph [Str "strong",Space,Str "style"],Str "."]] +,Para [Strong [Str "This",Space,Str "is",Space,Str "a",Space,Str "strong"],Space,Str "style",Space,Strong [Str "with",Space,Str "some"],Space,Str "words",Space,Strong [Str "ubolded."]]] diff --git a/tests/docx/codeblock.docx b/tests/docx/codeblock.docx Binary files differnew file mode 100644 index 000000000..8ec00953c --- /dev/null +++ b/tests/docx/codeblock.docx diff --git a/tests/docx/codeblock.native b/tests/docx/codeblock.native new file mode 100644 index 000000000..441e33511 --- /dev/null +++ b/tests/docx/codeblock.native @@ -0,0 +1,3 @@ +[Para [Str "This",Space,Str "is",Space,Str "some",Space,Str "code:"] +,CodeBlock ("",[],[]) "readDocx :: ReaderOptions\n -> B.ByteString\n -> Pandoc" +,Para [Str "from",Space,Str "the",Space,Str "beginning",Space,Str "of",Space,Str "the",Space,Str "docx",Space,Str "reader."]] diff --git a/tests/docx/deep_normalize.docx b/tests/docx/deep_normalize.docx Binary files differnew file mode 100644 index 000000000..7626d59ce --- /dev/null +++ b/tests/docx/deep_normalize.docx diff --git a/tests/docx/deep_normalize.native b/tests/docx/deep_normalize.native new file mode 100644 index 000000000..9b2089ec8 --- /dev/null +++ b/tests/docx/deep_normalize.native @@ -0,0 +1,6 @@ +[OrderedList (1,Decimal,OneParen) + [[Para [Str "This",Space,Str "is",Space,Str "at",Space,Str "the",Space,Str "first",Space,Str "level"] + ,OrderedList (1,LowerAlpha,DefaultDelim) + [[Para [Str "This",Space,Str "is",Space,Str "at",Space,Str "the",Space,Str "second",Space,Str "level"] + ,OrderedList (1,LowerRoman,DefaultDelim) + [[Para [Str "This",Space,Str "is",Space,Emph [Str "at",Space,Strong [Str "the",Space,Str "third",Space,Str "level"],Str ",",Space,Str "and",Space,Str "I",Space,Str "want",Space,Str "to"],Space,Str "test",Space,Str "normalization",Space,Str "here."]]]]]]]] diff --git a/tests/docx/definition_list.docx b/tests/docx/definition_list.docx Binary files differnew file mode 100644 index 000000000..a19edda45 --- /dev/null +++ b/tests/docx/definition_list.docx diff --git a/tests/docx/definition_list.native b/tests/docx/definition_list.native new file mode 100644 index 000000000..2e08ff1ac --- /dev/null +++ b/tests/docx/definition_list.native @@ -0,0 +1,7 @@ +[DefinitionList + [([Str "Term",Space,Str "1"], + [[Para [Str "Definition",Space,Str "1"]]]) + ,([Str "Term",Space,Str "2",Space,Str "with",Space,Emph [Str "inline",Space,Str "markup"]], + [[Para [Str "Definition",Space,Str "2"] + ,CodeBlock ("",[],[]) "{ some code, part of Definition 2 }" + ,Para [Str "Third",Space,Str "paragraph",Space,Str "of",Space,Str "definition",Space,Str "2."]]])]] diff --git a/tests/docx/drop_cap.docx b/tests/docx/drop_cap.docx Binary files differnew file mode 100644 index 000000000..19fab4a52 --- /dev/null +++ b/tests/docx/drop_cap.docx diff --git a/tests/docx/drop_cap.native b/tests/docx/drop_cap.native new file mode 100644 index 000000000..d361cfb0b --- /dev/null +++ b/tests/docx/drop_cap.native @@ -0,0 +1,4 @@ +[Para [Str "Drop",Space,Str "cap."] +,Para [Str "Next",Space,Str "paragraph."] +,Para [Str "Drop",Space,Str "cap",Space,Str "in",Space,Str "margin."] +,Para [Str "Drop",Space,Str "cap",Space,Str "(not",Space,Str "really)."]] diff --git a/tests/docx/hanging_indent.docx b/tests/docx/hanging_indent.docx Binary files differnew file mode 100644 index 000000000..6f62dc731 --- /dev/null +++ b/tests/docx/hanging_indent.docx diff --git a/tests/docx/hanging_indent.native b/tests/docx/hanging_indent.native new file mode 100644 index 000000000..138a6967f --- /dev/null +++ b/tests/docx/hanging_indent.native @@ -0,0 +1,3 @@ +[Para [Str "This",Space,Str "is",Space,Str "a",Space,Str "hanging",Space,Str "indent,",Space,Str "with",Space,Str "the",Space,Str "left",Space,Str "side",Space,Str "set",Space,Str "to",Space,Str "the",Space,Str "left",Space,Str "margin,",Space,Str "and",Space,Str "it",Space,Str "wraps",Space,Str "around",Space,Str "the",Space,Str "line."] +,BlockQuote + [Para [Str "Five",Space,Str "years",Space,Str "have",Space,Str "passed,",Space,Str "five",Space,Str "summers",Space,Str "with",Space,Str "the",Space,Str "length"]]] diff --git a/tests/docx/headers.docx b/tests/docx/headers.docx Binary files differnew file mode 100644 index 000000000..630b6bfc5 --- /dev/null +++ b/tests/docx/headers.docx diff --git a/tests/docx/headers.native b/tests/docx/headers.native new file mode 100644 index 000000000..03f967728 --- /dev/null +++ b/tests/docx/headers.native @@ -0,0 +1,5 @@ +[Header 1 ("a-test-of-headers",[],[]) [Str "A",Space,Str "Test",Space,Str "of",Space,Str "Headers"] +,Header 2 ("second-level",[],[]) [Str "Second",Space,Str "Level"] +,Para [Str "Some",Space,Str "plain",Space,Str "text."] +,Header 3 ("third-level",[],[]) [Str "Third",Space,Str "level"] +,Para [Str "Some",Space,Str "more",Space,Str "plain",Space,Str "text."]] diff --git a/tests/docx/i18n_blocks.docx b/tests/docx/i18n_blocks.docx Binary files differnew file mode 100644 index 000000000..36341c363 --- /dev/null +++ b/tests/docx/i18n_blocks.docx diff --git a/tests/docx/i18n_blocks.native b/tests/docx/i18n_blocks.native new file mode 100644 index 000000000..582a7360d --- /dev/null +++ b/tests/docx/i18n_blocks.native @@ -0,0 +1,8 @@ +[Header 1 ("this-is-heading-1",[],[]) [Str "This",Space,Str "is",Space,Str "Heading",Space,Str "1"] +,Header 2 ("this-is-heading-2",[],[]) [Str "This",Space,Str "is",Space,Str "Heading",Space,Str "2"] +,BlockQuote + [Para [Str "This",Space,Str "is",Space,Str "Quote"] + ,Para [Str "This",Space,Str "is",Space,Str "Block",Space,Str "Text"]] +,BulletList + [[Para [Str "This",Space,Str "is",Space,Str "list",Space,Str "item",Space,Str "1"]] + ,[Para [Str "This",Space,Str "is",Space,Str "list",Space,Str "item",Space,Str "2"]]]] diff --git a/tests/docx/image.docx b/tests/docx/image.docx Binary files differnew file mode 100644 index 000000000..06e4efd1a --- /dev/null +++ b/tests/docx/image.docx diff --git a/tests/docx/image_no_embed.native b/tests/docx/image_no_embed.native new file mode 100644 index 000000000..95c73610e --- /dev/null +++ b/tests/docx/image_no_embed.native @@ -0,0 +1,2 @@ +[Para [Str "An",Space,Str "image:"] +,Para [Image [] ("media/image1.jpg","")]] diff --git a/tests/docx/inline_code.docx b/tests/docx/inline_code.docx Binary files differnew file mode 100644 index 000000000..75c5ea3cb --- /dev/null +++ b/tests/docx/inline_code.docx diff --git a/tests/docx/inline_code.native b/tests/docx/inline_code.native new file mode 100644 index 000000000..11cf2777c --- /dev/null +++ b/tests/docx/inline_code.native @@ -0,0 +1 @@ +[Para [Str "This",Space,Str "is",Space,Str "an",Space,Str "example",Space,Str "of",Space,Code ("",[],[]) "inline code",Space,Str "with",Space,Str "three",Space,Str "spaces."]] diff --git a/tests/docx/inline_formatting.docx b/tests/docx/inline_formatting.docx Binary files differnew file mode 100644 index 000000000..eccf26425 --- /dev/null +++ b/tests/docx/inline_formatting.docx diff --git a/tests/docx/inline_formatting.native b/tests/docx/inline_formatting.native new file mode 100644 index 000000000..22d8f79e8 --- /dev/null +++ b/tests/docx/inline_formatting.native @@ -0,0 +1,5 @@ +[Para [Str "Regular",Space,Str "text",Space,Emph [Str "italics"],Space,Strong [Str "bold",Space,Emph [Str "bold",Space,Str "italics"]],Str "."] +,Para [Str "This",Space,Str "is",Space,SmallCaps [Str "Small",Space,Str "Caps"],Str ",",Space,Str "and",Space,Str "this",Space,Str "is",Space,Strikeout [Str "strikethrough"],Str "."] +,Para [Str "Some",Space,Str "people",Space,Str "use",Space,Emph [Str "single",Space,Str "underlines",Space,Str "for",Space,Emph [Str "emphasis"]],Str "."] +,Para [Str "Above",Space,Str "the",Space,Str "line",Space,Str "is",Space,Superscript [Str "superscript"],Space,Str "and",Space,Str "below",Space,Str "the",Space,Str "line",Space,Str "is",Space,Subscript [Str "subscript"],Str "."] +,Para [Str "A",Space,Str "line",LineBreak,Str "break."]] diff --git a/tests/docx/inline_images.docx b/tests/docx/inline_images.docx Binary files differnew file mode 100644 index 000000000..6288f66ff --- /dev/null +++ b/tests/docx/inline_images.docx diff --git a/tests/docx/inline_images.native b/tests/docx/inline_images.native new file mode 100644 index 000000000..f962f5c09 --- /dev/null +++ b/tests/docx/inline_images.native @@ -0,0 +1,2 @@ +[Para [Str "This",Space,Str "picture",Space,Image [] ("media/image1.jpg",""),Space,Str "is",Space,Str "an",Space,Str "identicon."] +,Para [Str "Here",Space,Str "is",Space,Link [Str "one",Space,Image [] ("media/image2.jpg",""),Space,Str "that"] ("http://www.google.com",""),Space,Str "links."]] diff --git a/tests/docx/links.docx b/tests/docx/links.docx Binary files differnew file mode 100644 index 000000000..538b84b08 --- /dev/null +++ b/tests/docx/links.docx diff --git a/tests/docx/links.native b/tests/docx/links.native new file mode 100644 index 000000000..cd7ab6fb6 --- /dev/null +++ b/tests/docx/links.native @@ -0,0 +1,7 @@ +[Header 2 ("an-internal-link-and-an-external-link",[],[]) [Str "An",Space,Str "internal",Space,Str "link",Space,Str "and",Space,Str "an",Space,Str "external",Space,Str "link"] +,Para [Str "An",Space,Link [Str "external",Space,Str "link"] ("http://google.com",""),Space,Str "to",Space,Str "a",Space,Str "popular",Space,Str "website."] +,Para [Str "An",Space,Link [Str "external",Space,Str "link"] ("http://johnmacfarlane.net/pandoc/README.html#synopsis",""),Space,Str "to",Space,Str "a",Space,Str "website",Space,Str "with",Space,Str "an",Space,Str "anchor."] +,Para [Str "An",Space,Link [Str "internal",Space,Str "link"] ("#a-section-for-testing-link-targets",""),Space,Str "to",Space,Str "a",Space,Str "section",Space,Str "header."] +,Para [Str "An",Space,Link [Str "internal",Space,Str "link"] ("#my_bookmark",""),Space,Str "to",Space,Str "a",Space,Str "bookmark."] +,Header 2 ("a-section-for-testing-link-targets",[],[]) [Str "A",Space,Str "section",Space,Str "for",Space,Str "testing",Space,Str "link",Space,Str "targets"] +,Para [Str "A",Space,Str "bookmark",Space,Str "right",Space,Span ("my_bookmark",["anchor"],[]) [],Str "here"]] diff --git a/tests/docx/lists.docx b/tests/docx/lists.docx Binary files differnew file mode 100644 index 000000000..bf7fd8ae4 --- /dev/null +++ b/tests/docx/lists.docx diff --git a/tests/docx/lists.native b/tests/docx/lists.native new file mode 100644 index 000000000..af922b335 --- /dev/null +++ b/tests/docx/lists.native @@ -0,0 +1,18 @@ +[Header 2 ("some-nested-lists",[],[]) [Str "Some",Space,Str "nested",Space,Str "lists"] +,OrderedList (1,Decimal,Period) + [[Para [Str "one"]] + ,[Para [Str "two"] + ,OrderedList (1,LowerAlpha,DefaultDelim) + [[Para [Str "a"]] + ,[Para [Str "b"]]]]] +,BulletList + [[Para [Str "one"]] + ,[Para [Str "two"] + ,BulletList + [[Para [Str "three"] + ,BulletList + [[Para [Str "four"] + ,Para [Str "Sub",Space,Str "paragraph"]]]]]] + ,[Para [Str "Same",Space,Str "list"]]] +,BulletList + [[Para [Str "Different",Space,Str "list",Space,Str "adjacent",Space,Str "to",Space,Str "the",Space,Str "one",Space,Str "above."]]]] diff --git a/tests/docx/metadata.docx b/tests/docx/metadata.docx Binary files differnew file mode 100644 index 000000000..ccf50b475 --- /dev/null +++ b/tests/docx/metadata.docx diff --git a/tests/docx/metadata.native b/tests/docx/metadata.native new file mode 100644 index 000000000..ed7ba63cf --- /dev/null +++ b/tests/docx/metadata.native @@ -0,0 +1,2 @@ +Pandoc (Meta {unMeta = fromList [("abstract",MetaInlines [Str "This",Space,Str "is",Space,Str "a",Space,Str "test",Space,Str "of",Space,Str "how",Space,Str "this",Space,Str "all",Space,Str "works.",Space,Str "I\8217ve",Space,Str "skipped",Space,Str "lines",Space,Str "here,",Space,Str "which",Space,Str "pandoc",Space,Str "doesn\8217t",Space,Str "do,",Space,Str "but",Space,Str "which",Space,Str "shouldn\8217t",Space,Str "make",Space,Str "a",Space,Str "difference."]),("author",MetaList [MetaInlines [Str "Mary",Space,Str "Ann",Space,Str "Evans"],MetaInlines [Str "Aurore",Space,Str "Dupin"]]),("date",MetaInlines [Str "July",Space,Str "28,",Space,Str "2014"]),("title",MetaInlines [Str "This",Space,Str "Is",Space,Str "the",Space,Str "Title"])]}) +[Para [Str "And",Space,Str "now",Space,Str "this",Space,Str "is",Space,Str "normal",Space,Str "text."]] diff --git a/tests/docx/metadata_after_normal.docx b/tests/docx/metadata_after_normal.docx Binary files differnew file mode 100644 index 000000000..b94a016cb --- /dev/null +++ b/tests/docx/metadata_after_normal.docx diff --git a/tests/docx/metadata_after_normal.native b/tests/docx/metadata_after_normal.native new file mode 100644 index 000000000..f0e31f8da --- /dev/null +++ b/tests/docx/metadata_after_normal.native @@ -0,0 +1,7 @@ +Pandoc (Meta {unMeta = fromList [("abstract",MetaInlines [Str "This",Space,Str "is",Space,Str "a",Space,Str "test",Space,Str "of",Space,Str "how",Space,Str "this",Space,Str "all",Space,Str "works.",Space,Str "I\8217ve",Space,Str "skipped",Space,Str "lines",Space,Str "here,",Space,Str "which",Space,Str "pandoc",Space,Str "doesn\8217t",Space,Str "do,",Space,Str "but",Space,Str "which",Space,Str "shouldn\8217t",Space,Str "make",Space,Str "a",Space,Str "difference."]),("author",MetaList [MetaInlines [Str "Mary",Space,Str "Ann",Space,Str "Evans"],MetaInlines [Str "Aurore",Space,Str "Dupin"]]),("date",MetaInlines [Str "July",Space,Str "28,",Space,Str "2014"]),("title",MetaInlines [Str "This",Space,Str "Is",Space,Str "the",Space,Str "Title"])]}) +[Para [Str "And",Space,Str "now",Space,Str "this",Space,Str "is",Space,Str "normal",Space,Str "text."] +,Para [Str "This",Space,Str "Is",Space,Str "the",Space,Str "Title"] +,Para [Str "Mary",Space,Str "Ann",Space,Str "Evans"] +,Para [Str "Aurore",Space,Str "Dupin"] +,Para [Str "July",Space,Str "28,",Space,Str "2014"] +,Para [Str "This",Space,Str "is",Space,Str "a",Space,Str "test",Space,Str "of",Space,Str "how",Space,Str "this",Space,Str "all",Space,Str "works.",Space,Str "I\8217ve",Space,Str "skipped",Space,Str "lines",Space,Str "here,",Space,Str "which",Space,Str "pandoc",Space,Str "doesn\8217t",Space,Str "do,",Space,Str "but",Space,Str "which",Space,Str "shouldn\8217t",Space,Str "make",Space,Str "a",Space,Str "difference."]] diff --git a/tests/docx/normalize.docx b/tests/docx/normalize.docx Binary files differnew file mode 100644 index 000000000..b4fc55818 --- /dev/null +++ b/tests/docx/normalize.docx diff --git a/tests/docx/normalize.native b/tests/docx/normalize.native new file mode 100644 index 000000000..aeba672c4 --- /dev/null +++ b/tests/docx/normalize.native @@ -0,0 +1,2 @@ +[Para [Str "These",Space,Str "are",Space,Str "different",Space,Str "fonts."] +,Para [Strong [Str "These",Space,Emph [Str "are",Space,Strikeout [Str "different"]],Space,Str "fonts."]]] diff --git a/tests/docx/notes.docx b/tests/docx/notes.docx Binary files differnew file mode 100644 index 000000000..eb6fa12d4 --- /dev/null +++ b/tests/docx/notes.docx diff --git a/tests/docx/notes.native b/tests/docx/notes.native new file mode 100644 index 000000000..ec1b414b6 --- /dev/null +++ b/tests/docx/notes.native @@ -0,0 +1,2 @@ +[Header 2 ("a-footnote",[],[]) [Str "A",Space,Str "footnote"] +,Para [Str "Test",Space,Str "footnote.",Note [Para [Str "My",Space,Str "note."]],Space,Str "Test",Space,Str "endnote.",Note [Para [Str "This",Space,Str "is",Space,Str "an",Space,Str "endnote",Space,Str "at",Space,Str "the",Space,Str "end",Space,Str "of",Space,Str "the",Space,Str "document."]]]] diff --git a/tests/docx/numbered_header.docx b/tests/docx/numbered_header.docx Binary files differnew file mode 100644 index 000000000..66ce7648d --- /dev/null +++ b/tests/docx/numbered_header.docx diff --git a/tests/docx/numbered_header.native b/tests/docx/numbered_header.native new file mode 100644 index 000000000..a8dd1e897 --- /dev/null +++ b/tests/docx/numbered_header.native @@ -0,0 +1 @@ +[Header 1 ("a-numbered-header.",[],[]) [Str "A",Space,Str "Numbered",Space,Str "Header."]] diff --git a/tests/docx/tables.docx b/tests/docx/tables.docx Binary files differnew file mode 100644 index 000000000..28087ead5 --- /dev/null +++ b/tests/docx/tables.docx diff --git a/tests/docx/tables.native b/tests/docx/tables.native new file mode 100644 index 000000000..cf23cf404 --- /dev/null +++ b/tests/docx/tables.native @@ -0,0 +1,34 @@ +[Header 2 ("a-table-with-and-without-a-header-row",[],[]) [Str "A",Space,Str "table,",Space,Str "with",Space,Str "and",Space,Str "without",Space,Str "a",Space,Str "header",Space,Str "row"] +,Table [] [AlignDefault,AlignDefault,AlignDefault,AlignDefault] [0.0,0.0,0.0,0.0] + [[Plain [Str "Name"]] + ,[Plain [Str "Game"]] + ,[Plain [Str "Fame"]] + ,[Plain [Str "Blame"]]] + [[[Plain [Str "Lebron",Space,Str "James"]] + ,[Plain [Str "Basketball"]] + ,[Plain [Str "Very",Space,Str "High"]] + ,[Plain [Str "Leaving",Space,Str "Cleveland"]]] + ,[[Plain [Str "Ryan",Space,Str "Braun"]] + ,[Plain [Str "Baseball"]] + ,[Plain [Str "Moderate"]] + ,[Plain [Str "Steroids"]]] + ,[[Plain [Str "Russell",Space,Str "Wilson"]] + ,[Plain [Str "Football"]] + ,[Plain [Str "High"]] + ,[Plain [Str "Tacky",Space,Str "uniform"]]]] +,Table [] [AlignDefault,AlignDefault] [0.0,0.0] + [] + [[[Plain [Str "Sinple"]] + ,[Plain [Str "Table"]]] + ,[[Plain [Str "Without"]] + ,[Plain [Str "Header"]]]] +,Table [] [AlignDefault,AlignDefault] [0.0,0.0] + [] + [[[Para [Str "Simple"] + ,Para [Str "Multiparagraph"]] + ,[Para [Str "Table"] + ,Para [Str "Full"]]] + ,[[Para [Str "Of"] + ,Para [Str "Paragraphs"]] + ,[Para [Str "In",Space,Str "each"] + ,Para [Str "Cell."]]]]] diff --git a/tests/docx/tabs.docx b/tests/docx/tabs.docx Binary files differnew file mode 100644 index 000000000..6ff5f4bb1 --- /dev/null +++ b/tests/docx/tabs.docx diff --git a/tests/docx/tabs.native b/tests/docx/tabs.native new file mode 100644 index 000000000..05461f20b --- /dev/null +++ b/tests/docx/tabs.native @@ -0,0 +1,2 @@ +[Para [Str "Some",Space,Str "text",Space,Str "separated",Space,Str "by",Space,Str "a",Space,Str "tab."] +,Para [Str "Tab-indented",Space,Str "text."]] diff --git a/tests/docx/track_changes_deletion.docx b/tests/docx/track_changes_deletion.docx Binary files differnew file mode 100644 index 000000000..5cfdbeed8 --- /dev/null +++ b/tests/docx/track_changes_deletion.docx diff --git a/tests/docx/track_changes_deletion_accept.native b/tests/docx/track_changes_deletion_accept.native new file mode 100644 index 000000000..205c67810 --- /dev/null +++ b/tests/docx/track_changes_deletion_accept.native @@ -0,0 +1 @@ +[Para [Str "This",Space,Str "is",Space,Str "a",Space,Str "text",Space,Str "with",Space,Str "a",Space,Str "deletion."]] diff --git a/tests/docx/track_changes_deletion_all.native b/tests/docx/track_changes_deletion_all.native new file mode 100644 index 000000000..7f4ed2a90 --- /dev/null +++ b/tests/docx/track_changes_deletion_all.native @@ -0,0 +1 @@ +[Para [Str "This",Space,Str "is",Space,Str "a",Space,Str "text",Space,Str "with",Space,Str "a",Span ("",["deletion"],[("author","eng-dept"),("date","2014-06-25T10:42:00Z")]) [Str "n",Space,Str "excessively",Space,Str "modified"],Space,Str "deletion."]] diff --git a/tests/docx/track_changes_deletion_reject.native b/tests/docx/track_changes_deletion_reject.native new file mode 100644 index 000000000..04283bee5 --- /dev/null +++ b/tests/docx/track_changes_deletion_reject.native @@ -0,0 +1 @@ +[Para [Str "This",Space,Str "is",Space,Str "a",Space,Str "text",Space,Str "with",Space,Str "an",Space,Str "excessively",Space,Str "modified",Space,Str "deletion."]] diff --git a/tests/docx/track_changes_insertion.docx b/tests/docx/track_changes_insertion.docx Binary files differnew file mode 100644 index 000000000..fbdc9003e --- /dev/null +++ b/tests/docx/track_changes_insertion.docx diff --git a/tests/docx/track_changes_insertion_accept.native b/tests/docx/track_changes_insertion_accept.native new file mode 100644 index 000000000..ca2e46df0 --- /dev/null +++ b/tests/docx/track_changes_insertion_accept.native @@ -0,0 +1 @@ +[Para [Str "This",Space,Str "is",Space,Str "a",Space,Str "text",Space,Str "with",Space,Str "two",Space,Str "exciting",Space,Str "insertions."]] diff --git a/tests/docx/track_changes_insertion_all.native b/tests/docx/track_changes_insertion_all.native new file mode 100644 index 000000000..12664e425 --- /dev/null +++ b/tests/docx/track_changes_insertion_all.native @@ -0,0 +1 @@ +[Para [Str "This",Space,Str "is",Space,Str "a",Space,Str "text",Space,Str "with",Space,Span ("",["insertion"],[("author","eng-dept"),("date","2014-06-25T10:40:00Z")]) [Str "two",Space,Str "exciting"],Space,Str "insertions."]] diff --git a/tests/docx/track_changes_insertion_reject.native b/tests/docx/track_changes_insertion_reject.native new file mode 100644 index 000000000..def000abd --- /dev/null +++ b/tests/docx/track_changes_insertion_reject.native @@ -0,0 +1 @@ +[Para [Str "This",Space,Str "is",Space,Str "a",Space,Str "text",Space,Str "with",Space,Str "insertions."]] diff --git a/tests/docx/trailing_spaces_in_formatting.docx b/tests/docx/trailing_spaces_in_formatting.docx Binary files differnew file mode 100644 index 000000000..ebe7404a9 --- /dev/null +++ b/tests/docx/trailing_spaces_in_formatting.docx diff --git a/tests/docx/trailing_spaces_in_formatting.native b/tests/docx/trailing_spaces_in_formatting.native new file mode 100644 index 000000000..46ea9bca8 --- /dev/null +++ b/tests/docx/trailing_spaces_in_formatting.native @@ -0,0 +1 @@ +[Para [Str "Turn",Space,Str "my",Space,Emph [Str "formatting"],Space,Str "off",Space,Str "after",Space,Str "the",Space,Str "spaces."]] diff --git a/tests/docx/unicode.docx b/tests/docx/unicode.docx Binary files differnew file mode 100644 index 000000000..cf902c6c6 --- /dev/null +++ b/tests/docx/unicode.docx diff --git a/tests/docx/unicode.native b/tests/docx/unicode.native new file mode 100644 index 000000000..aee7ef74b --- /dev/null +++ b/tests/docx/unicode.native @@ -0,0 +1 @@ +[Para [Str "Hello,",Space,Str "\19990\30028.",Space,Str "This",Space,Str "costs",Space,Str "\8364\&10.\8744\8744("]] diff --git a/tests/dokuwiki_external_images.dokuwiki b/tests/dokuwiki_external_images.dokuwiki new file mode 100644 index 000000000..cc7eddcda --- /dev/null +++ b/tests/dokuwiki_external_images.dokuwiki @@ -0,0 +1 @@ +{{https://cooluri.com/image.png|HTTPS image}} {{http://cooluri.com/image.png|HTTP image}} {{ftp://ftp.cooluri.com/image.png|FTP image}} {{file:///tmp/coolimage.png|Filesystem image}} {{:/image.jpg|Relative image 1}} {{:image.jpg|Relative image 2}} diff --git a/tests/dokuwiki_external_images.native b/tests/dokuwiki_external_images.native new file mode 100644 index 000000000..c2b8876d3 --- /dev/null +++ b/tests/dokuwiki_external_images.native @@ -0,0 +1 @@ +[Para [Image [Str "HTTPS",Space,Str "image"] ("https://cooluri.com/image.png",""),Space,Image [Str "HTTP",Space,Str "image"] ("http://cooluri.com/image.png",""),Space,Image [Str "FTP",Space,Str "image"] ("ftp://ftp.cooluri.com/image.png",""),Space,Image [Str "Filesystem",Space,Str "image"] ("file:///tmp/coolimage.png",""),Space,Image [Str "Relative",Space,Str "image",Space,Str "1"] ("/image.jpg",""),Space,Image [Str "Relative",Space,Str "image",Space,Str "2"] ("image.jpg","")]] diff --git a/tests/dokuwiki_inline_formatting.dokuwiki b/tests/dokuwiki_inline_formatting.dokuwiki new file mode 100644 index 000000000..dd5cb52b4 --- /dev/null +++ b/tests/dokuwiki_inline_formatting.dokuwiki @@ -0,0 +1,13 @@ +Regular text //italics// **bold //bold italics//**. + +This is Small Caps, and this is <del>strikethrough</del>. + +Some people use single underlines for //emphasis//. + +Above the line is <sup>superscript</sup> and below the line is <sub>subscript</sub>. + +A line\\ break. + +hello %%//%% world %%**%% from %%__%% me + +''%%hello // world ** from __ me%%'' diff --git a/tests/dokuwiki_inline_formatting.native b/tests/dokuwiki_inline_formatting.native new file mode 100644 index 000000000..63e85889f --- /dev/null +++ b/tests/dokuwiki_inline_formatting.native @@ -0,0 +1,7 @@ +[Para [Str "Regular",Space,Str "text",Space,Emph [Str "italics"],Space,Strong [Str "bold",Space,Emph [Str "bold",Space,Str "italics"]],Str "."] +,Para [Str "This",Space,Str "is",Space,SmallCaps [Str "Small",Space,Str "Caps"],Str ",",Space,Str "and",Space,Str "this",Space,Str "is",Space,Strikeout [Str "strikethrough"],Str "."] +,Para [Str "Some",Space,Str "people",Space,Str "use",Space,Span ("",[],[("underline","single")]) [Str "single",Space,Str "underlines",Space,Str "for",Space,Emph [Str "emphasis"]],Str "."] +,Para [Str "Above",Space,Str "the",Space,Str "line",Space,Str "is",Space,Superscript [Str "superscript"],Space,Str "and",Space,Str "below",Space,Str "the",Space,Str "line",Space,Str "is",Space,Subscript [Str "subscript"],Str "."] +,Para [Str "A",Space,Str "line",LineBreak,Str "break."] +,Para [Str "hello",Space,Str "//",Space,Str "world",Space,Str "**",Space,Str "from",Space,Str "__",Space,Str "me"] +,Para [Code ("",[],[]) "hello // world ** from __ me"]] diff --git a/tests/dokuwiki_multiblock_table.dokuwiki b/tests/dokuwiki_multiblock_table.dokuwiki new file mode 100644 index 000000000..8b913f1f2 --- /dev/null +++ b/tests/dokuwiki_multiblock_table.dokuwiki @@ -0,0 +1,4 @@ +Sample grid table. +^Fruit ^Price^Advantages ^ +|Bananas|$1.34|built-in wrapper\\ \\ potassium| +|Oranges|$2.10|* cures scurvy\\ * tasty | diff --git a/tests/dokuwiki_multiblock_table.native b/tests/dokuwiki_multiblock_table.native new file mode 100644 index 000000000..ea6b833db --- /dev/null +++ b/tests/dokuwiki_multiblock_table.native @@ -0,0 +1,13 @@ +[Table [Str "Sample",Space,Str "grid",Space,Str "table."] [AlignDefault,AlignDefault,AlignDefault] [0.2222222222222222,0.2222222222222222,0.2916666666666667] + [[Plain [Str "Fruit"]] + ,[Plain [Str "Price"]] + ,[Plain [Str "Advantages"]]] + [[[Para [Str "Bananas"]] + ,[Para [Str "$1.34"]] + ,[Para [Str "built-in",Space,Str "wrapper"] + ,Para [Str "potassium"]]] + ,[[Para [Str "Oranges"]] + ,[Para [Str "$2.10"]] + ,[BulletList + [[Plain [Str "cures",Space,Str "scurvy"]] + ,[Plain [Str "tasty"]]]]]]]
\ No newline at end of file diff --git a/tests/epub/features.epub b/tests/epub/features.epub Binary files differnew file mode 100644 index 000000000..2690eec8b --- /dev/null +++ b/tests/epub/features.epub diff --git a/tests/epub/features.native b/tests/epub/features.native new file mode 100644 index 000000000..6ccc04f43 --- /dev/null +++ b/tests/epub/features.native @@ -0,0 +1,107 @@ +[Para [Span ("front.xhtml",[],[]) []] +,RawBlock (Format "html") "<section>" +,Header 1 ("",[],[]) [Str "Reflowable",Space,Str "EPUB",Space,Str "3",Space,Str "Conformance",Space,Str "Test",Space,Str "Document:",Space,Str "0100"] +,RawBlock (Format "html") "<section>" +,Header 2 ("",[],[]) [Str "Status",Space,Str "of",Space,Str "this",Space,Str "Document"] +,Para [Str "This",Space,Str "publication",Space,Str "is",Space,Str "currently",Space,Str "considered",Space,Span ("",["status"],[]) [Str "[UNDER",Space,Str "DEVELOPMENT]"],Space,Str "by",Space,Str "the",Space,Str "IDPF."] +,Para [Str "This",Space,Str "publication",Space,Str "is",Space,Str "part",Space,Str "of",Space,Str "version",Space,Span ("",["version"],[]) [Str "X.X"],Space,Str "of",Space,Str "the",Space,Str "EPUB",Space,Str "3.0",Space,Str "Compliance",Space,Str "Test",Space,Str "Suite",Space,Str "released",Space,Str "on",Space,RawInline (Format "html") "<time class=\"release\">",Str "TBD",RawInline (Format "html") "</time>",Str "."] +,Para [Str "Before",Space,Str "using",Space,Str "this",Space,Str "publication",Space,Str "to",Space,Str "evaluate",Space,Str "reading",Space,Str "systems,",Space,Str "testers",Space,Str "are",Space,Str "strongly",Space,Str "encouraged",Space,Str "to",Space,Str "verify",Space,Str "that",Space,Str "they",Space,Str "have",Space,Str "the",Space,Str "latest",Space,Str "release",Space,Str "by",Space,Str "checking",Space,Str "the",Space,Str "current",Space,Str "release",Space,Str "version",Space,Str "and",Space,Str "date",Space,Str "of",Space,Str "the",Space,Str "test",Space,Str "suite",Space,Str "at",Space,Link [Str "TBD"] ("","")] +,Para [Str "This",Space,Str "publication",Space,Str "is",Space,Str "one",Space,Str "of",Space,Str "several",Space,Str "that",Space,Str "currently",Space,Str "comprise",Space,Str "the",Space,Str "EPUB",Space,Str "3",Space,Str "conformance",Space,Str "test",Space,Str "suite",Space,Str "for",Space,Str "reflowable",Space,Str "content.",Space,Str "The",Space,Str "complete",Space,Str "test",Space,Str "suite",Space,Str "includes",Space,Str "all",Space,Str "of",Space,Str "the",Space,Str "following",Space,Str "publications:"] +,OrderedList (1,DefaultStyle,DefaultDelim) + [[Plain [Str "."]]] +,RawBlock (Format "html") "</section>" +,RawBlock (Format "html") "<section>" +,Header 2 ("",[],[]) [Str "About",Space,Str "this",Space,Str "Document"] +,Para [Str "This",Space,Str "document",Space,Str "focuses",Space,Str "on",Space,Str "human-evaluated",Space,Str "binary",Space,Str "(pass/fail)",Space,Str "tests",Space,Str "in",Space,Str "a",Space,Str "reflowable",Space,Str "context.",Space,Str "Tests",Space,Str "for",Space,Str "fixed-layout",Space,Str "content",Space,Str "and",Space,Str "other",Space,Str "individual",Space,Str "tests",Space,Str "that",Space,Str "require",Space,Str "a",Space,Str "dedicated",Space,Str "epub",Space,Str "file",Space,Str "are",Space,Str "available",Space,Str "in",Space,Str "additional",Space,Str "sibling",Space,Str "documents;",Space,Str "refer",Space,Str "to",Space,Str "the",Space,Link [Str "test",Space,Str "suite",Space,Str "wiki"] ("Overview",""),Space,Str "(",Code ("",[],[]) "https://github.com/mgylling/epub-testsuite/wiki/Overview",Str ")",Space,Str "for",Space,Str "additional",Space,Str "information."] +,RawBlock (Format "html") "</section>" +,RawBlock (Format "html") "<section>" +,Header 2 ("",[],[]) [Str "Conventions"] +,Para [Str "The",Space,Str "following",Space,Str "conventions",Space,Str "are",Space,Str "used",Space,Str "throughout",Space,Str "the",Space,Str "document:"] +,DefinitionList + [([Str "1.",Space,Str "Locating",Space,Str "a",Space,Str "test"], + [[Div ("",["ctest"],[]) [Para [Str "Tests",Space,Str "for",Space,Emph [Str "required"],Space,Str "Reading",Space,Str "System",Space,Str "functionality",Space,Str "are",Space,Str "preceded",Space,Str "by",Space,Str "the",Space,Str "label:",Space,Span ("",["nature"],[("style","display: inline; font-size: 100%")]) [Str "[REQUIRED]"]]] + ,Div ("",["otest"],[]) [Para [Str "Tests",Space,Str "for",Space,Emph [Str "optional"],Space,Str "Reading",Space,Str "System",Space,Str "functionality",Space,Str "are",Space,Str "preceded",Space,Str "by",Space,Str "the",Space,Str "label:",Space,Span ("",["nature"],[("style","display: inline; font-size: 100%")]) [Str "[OPTIONAL]"]]]]]) + ,([Str "2.",Space,Str "Performing",Space,Str "the",Space,Str "test"], + [[Plain [Str "Each",Space,Str "test",Space,Str "includes",Space,Str "a",Space,Str "description",Space,Str "of",Space,Str "its",Space,Str "purpose",Space,Str "followed",Space,Str "by",Space,Str "the",Space,Str "actual",Space,Strong [Str "test",Space,Str "statement,",Space,Str "which",Space,Str "can",Space,Str "always",Space,Str "be",Space,Str "evaluated",Space,Str "to",Space,Str "true",Space,Str "or",Space,Str "false"],Str ".",Space,Str "These",Space,Str "statements",Space,Str "typically",Space,Str "have",Space,Str "the",Space,Str "form:",Space,Str "\"If",Space,Str "[some",Space,Str "condition],",Space,Str "the",Space,Str "test",Space,Str "passes\"."]]]) + ,([Str "3.",Space,Str "Scoring",Space,Str "in",Space,Str "the",Space,Str "results",Space,Str "form"], + [[Plain [Str "@@@TODO",Space,Str "provide",Space,Str "info",Space,Str "on",Space,Str "where",Space,Str "to",Space,Str "get",Space,Str "the",Space,Str "results",Space,Str "form"]]])] +,RawBlock (Format "html") "</section>" +,RawBlock (Format "html") "</section>" +,Para [Span ("content-mathml-001.xhtml",[],[]) []] +,RawBlock (Format "html") "<section>" +,Header 2 ("content-mathml-001.xhtml#mathml",[],[]) [Str "MathML"] +,RawBlock (Format "html") "<section id=\"mathml-010\" class=\"ctest\">" +,Header 2 ("",[],[]) [Span ("",["nature"],[]) [Str "[REQUIRED]"],Space,Span ("",["test-id"],[]) [Str "mathml-010"],Space,Str "Rendering"] +,Para [Str "Tests",Space,Str "whether",Space,Str "MathML",Space,Str "equation",Space,Str "rendering",Space,Str "is",Space,Str "supported."] +,Para [Math DisplayMath "\\int_{- \\infty}^{\\infty}e^{- x^{2}}\\, dx = \\sqrt{\\pi}",Space,Math DisplayMath "\\sum\\limits_{n = 1}^{\\infty}\\frac{1}{n^{2}} = \\frac{\\pi^{2}}{6}",Space,Math DisplayMath "x = \\frac{- b \\pm \\sqrt{b^{2} - 4ac}}{2a}"] +,Para [Str "If",Space,Str "the",Space,Str "preceding",Space,Str "equations",Space,Str "are",Space,Str "not",Space,Str "presented",Space,Str "as",Space,Str "linear",Space,Str "text",Space,Str "(e.g.,",Space,Str "x=-b\177b2-4ac2a),",Space,Str "the",Space,Str "test",Space,Str "passes."] +,RawBlock (Format "html") "</section>" +,RawBlock (Format "html") "<section id=\"mathml-020\" class=\"otest\">" +,Header 2 ("",[],[]) [Span ("",["nature"],[]) [Str "[OPTIONAL]"],Space,Span ("",["test-id"],[]) [Str "mathml-020"],Space,Str "CSS",Space,Str "Styling",Space,Str "of",Space,Str "the",Space,Code ("",[],[]) "math",Space,Str "element"] +,Para [Str "Tests",Space,Str "whether",Space,Str "basic",Space,Str "CSS",Space,Str "styling",Space,Str "of",Space,Str "MathML",Space,Str "is",Space,Str "supported",Space,Str "on",Space,Str "the",Space,Code ("",[],[]) "math",Space,Str "element."] +,Para [Math InlineMath "{2x}{+ y - z}"] +,Para [Str "The",Space,Str "test",Space,Str "passes",Space,Str "if",Space,Str "the",Space,Str "equation",Space,Str "has",Space,Str "a",Space,Str "yellow",Space,Str "background",Space,Str "and",Space,Str "a",Space,Str "dashed",Space,Str "border."] +,Para [Str "If",Space,Str "the",Space,Str "reading",Space,Str "system",Space,Str "does",Space,Str "not",Space,Str "have",Space,Str "a",Space,Str "viewport,",Space,Str "or",Space,Str "does",Space,Str "not",Space,Str "support",Space,Str "CSS",Space,Str "styles,",Space,Str "this",Space,Str "test",Space,Str "should",Space,Str "be",Space,Str "marked",Space,Code ("",[],[]) "Not Supported",Str "."] +,RawBlock (Format "html") "</section>" +,RawBlock (Format "html") "<section id=\"mathml-021\" class=\"otest\">" +,Header 2 ("",[],[]) [Span ("",["nature"],[]) [Str "[OPTIONAL]"],Space,Span ("",["test-id"],[]) [Str "mathml-021"],Space,Str "CSS",Space,Str "Styling",Space,Str "of",Space,Str "the",Space,Code ("",[],[]) "mo",Space,Str "element"] +,Para [Str "Tests",Space,Str "whether",Space,Str "basic",Space,Str "CSS",Space,Str "styling",Space,Str "of",Space,Str "MathML",Space,Str "is",Space,Str "supported",Space,Str "on",Space,Str "the",Space,Code ("",[],[]) "mo",Space,Str "element."] +,Para [Math InlineMath "{2x}{+ y - z}"] +,Para [Str "The",Space,Str "test",Space,Str "passes",Space,Str "if",Space,Str "the",Space,Str "operators",Space,Str "are",Space,Str "enlarged",Space,Str "relative",Space,Str "to",Space,Str "the",Space,Str "other",Space,Str "symbols",Space,Str "and",Space,Str "numbers."] +,Para [Str "If",Space,Str "the",Space,Str "reading",Space,Str "system",Space,Str "does",Space,Str "not",Space,Str "have",Space,Str "a",Space,Str "viewport,",Space,Str "or",Space,Str "does",Space,Str "not",Space,Str "support",Space,Str "CSS",Space,Str "styles,",Space,Str "this",Space,Str "test",Space,Str "should",Space,Str "be",Space,Str "marked",Space,Code ("",[],[]) "Not Supported",Str "."] +,RawBlock (Format "html") "</section>" +,RawBlock (Format "html") "<section id=\"mathml-022\" class=\"otest\">" +,Header 2 ("",[],[]) [Span ("",["nature"],[]) [Str "[OPTIONAL]"],Space,Span ("",["test-id"],[]) [Str "mathml-022"],Space,Str "CSS",Space,Str "Styling",Space,Str "of",Space,Str "the",Space,Code ("",[],[]) "mi",Space,Str "element"] +,Para [Str "Tests",Space,Str "whether",Space,Str "basic",Space,Str "CSS",Space,Str "styling",Space,Str "of",Space,Str "MathML",Space,Str "is",Space,Str "supported",Space,Str "on",Space,Str "the",Space,Code ("",[],[]) "mi",Space,Str "element."] +,Para [Math InlineMath "{2x}{+ y - z}"] +,Para [Str "The",Space,Str "test",Space,Str "passes",Space,Str "if",Space,Str "the",Space,Str "identifiers",Space,Str "are",Space,Str "bolded",Space,Str "and",Space,Str "blue."] +,Para [Str "If",Space,Str "the",Space,Str "reading",Space,Str "system",Space,Str "does",Space,Str "not",Space,Str "have",Space,Str "a",Space,Str "viewport,",Space,Str "or",Space,Str "does",Space,Str "not",Space,Str "support",Space,Str "CSS",Space,Str "styles,",Space,Str "this",Space,Str "test",Space,Str "should",Space,Str "be",Space,Str "marked",Space,Code ("",[],[]) "Not Supported",Str "."] +,RawBlock (Format "html") "</section>" +,RawBlock (Format "html") "<section id=\"mathml-023\" class=\"otest\">" +,Header 2 ("",[],[]) [Span ("",["nature"],[]) [Str "[OPTIONAL]"],Space,Span ("",["test-id"],[]) [Str "mathml-023"],Space,Str "CSS",Space,Str "Styling",Space,Str "of",Space,Str "the",Space,Code ("",[],[]) "mn",Space,Str "element"] +,Para [Str "Tests",Space,Str "whether",Space,Str "basic",Space,Str "CSS",Space,Str "styling",Space,Str "of",Space,Str "MathML",Space,Str "is",Space,Str "supported",Space,Str "on",Space,Str "the",Space,Code ("",[],[]) "mn",Space,Str "element."] +,Para [Math InlineMath "{2x}{+ y - z}"] +,Para [Str "The",Space,Str "test",Space,Str "passes",Space,Str "if",Space,Str "the",Space,Str "number",Space,Str "2",Space,Str "is",Space,Str "italicized",Space,Str "and",Space,Str "blue."] +,Para [Str "If",Space,Str "the",Space,Str "reading",Space,Str "system",Space,Str "does",Space,Str "not",Space,Str "have",Space,Str "a",Space,Str "viewport,",Space,Str "or",Space,Str "does",Space,Str "not",Space,Str "support",Space,Str "CSS",Space,Str "styles,",Space,Str "this",Space,Str "test",Space,Str "should",Space,Str "be",Space,Str "marked",Space,Code ("",[],[]) "Not Supported",Str "."] +,RawBlock (Format "html") "</section>" +,RawBlock (Format "html") "<section id=\"mathml-024\" class=\"ctest\">" +,Header 2 ("",[],[]) [Span ("",["nature"],[]) [Str "[REQUIRED]"],Space,Span ("",["test-id"],[]) [Str "mathml-024"],Str "Horizontal",Space,Str "stretch,",Space,Code ("",[],[]) "mover",Str ",",Space,Code ("",[],[]) "munder",Str ",",Space,Str "and",Space,Code ("",[],[]) "mspace",Space,Str "elements"] +,Para [Str "Tests",Space,Str "whether",Space,Str "horizontal",Space,Str "stretch,",Space,Code ("",[],[]) "mover",Str ",",Space,Code ("",[],[]) "munder",Str ",",Space,Code ("",[],[]) "mspace",Space,Str "elements",Space,Str "are",Space,Str "supported."] +,Para [Math DisplayMath "c = \\overset{\\text{complex\\ number}}{\\overbrace{\\underset{\\text{real}}{\\underbrace{\\mspace{20mu} a\\mspace{20mu}}} + \\underset{\\text{imaginary}}{\\underbrace{\\quad b{\\mathbb{i}}\\quad}}}}"] +,Para [Str "The",Space,Str "test",Space,Str "passes",Space,Str "if",Space,Str "the",Space,Str "rendering",Space,Str "looks",Space,Str "like",Space,Str "."] +,RawBlock (Format "html") "</section>" +,RawBlock (Format "html") "<section id=\"mathml-025\" class=\"ctest\">" +,Header 2 ("",[],[]) [Span ("",["nature"],[]) [Str "[REQUIRED]"],Space,Span ("",["test-id"],[]) [Str "mathml-025"],Str "Testing",Space,Code ("",[],[]) "mtable",Space,Str "with",Space,Code ("",[],[]) "colspan",Space,Str "and",Space,Code ("",[],[]) "rowspan",Space,Str "attributes,",Space,Str "Hebrew",Space,Str "and",Space,Str "Script",Space,Str "fonts"] +,Para [Str "Tests",Space,Str "whether",Space,Code ("",[],[]) "mtable",Space,Str "with",Space,Code ("",[],[]) "colspan",Space,Str "and",Space,Code ("",[],[]) "mspace",Space,Str "attributes",Space,Str "(colum",Space,Str "and",Space,Str "row",Space,Str "spanning)",Space,Str "are",Space,Str "supported;",Space,Str "uses",Space,Str "Hebrew",Space,Str "and",Space,Str "Script",Space,Str "alphabets."] +,Para [Math DisplayMath "\\begin{array}{llllllllll}\n & {\\operatorname{cov}\\left( \\mathcal{L} \\right)} & \\longrightarrow & {\\operatorname{non}\\left( \\mathcal{K} \\right)} & \\longrightarrow & {\\operatorname{cof}\\left( \\mathcal{K} \\right)} & \\longrightarrow & {\\operatorname{cof}\\left( \\mathcal{L} \\right)} & \\longrightarrow & 2^{\\aleph_{0}} \\\\\n & \\uparrow & & \\uparrow & & \\uparrow & & \\uparrow & & \\\\\n & {\\mathfrak{b}} & \\longrightarrow & {\\mathfrak{d}} & & & & & & \\\\\n & \\uparrow & & \\uparrow & & & & & & \\\\\n\\aleph_{1} & \\longrightarrow & {\\operatorname{add}\\left( \\mathcal{L} \\right)} & \\longrightarrow & {\\operatorname{add}\\left( \\mathcal{K} \\right)} & \\longrightarrow & {\\operatorname{cov}\\left( \\mathcal{K} \\right)} & \\longrightarrow & {\\operatorname{non}\\left( \\mathcal{L} \\right)} & \\\\\n\\end{array}"] +,Para [Str "The",Space,Str "test",Space,Str "passes",Space,Str "if",Space,Str "the",Space,Str "rendering",Space,Str "looks",Space,Str "like",Space,Link [Str "Cicho\324's",Space,Str "Diagram"] ("Cicho%C5%84's_diagram",""),Str ":",Space,Str "."] +,RawBlock (Format "html") "</section>" +,RawBlock (Format "html") "<section id=\"mathml-026\" class=\"ctest\">" +,Header 2 ("",[],[]) [Span ("",["nature"],[]) [Str "[REQUIRED]"],Space,Span ("",["test-id"],[]) [Str "mathml-026"],Str "BiDi,",Space,Str "RTL",Space,Str "and",Space,Str "Arabic",Space,Str "alphabets"] +,Para [Str "Tests",Space,Str "whether",Space,Str "right-to-left",Space,Str "and",Space,Str "Arabic",Space,Str "alphabets",Space,Str "are",Space,Str "supported."] +,Para [Math DisplayMath "{d\\left( s \\right)} = \\begin{cases}\n{\\sum\\limits_{{\\lbrack?\\rbrack} = 1}^{S}s^{\\lbrack?\\rbrack}} & {\\text{\1573\1584\1575\1603\1575\1606}s > 0} \\\\\n{\\int_{1}^{S}{s^{\\lbrack?\\rbrack}s}} & {\\text{\1573\1584\1575\1603\1575\1606}s \\in m} \\\\\n{T\\pi} & {\\text{\1594\1610\1585\1584\1604\1603}\\left( \\text{\1605\1593}\\pi \\simeq 3,141 \\right)} \\\\\n\\end{cases}"] +,Para [Str "The",Space,Str "test",Space,Str "passes",Space,Str "if",Space,Str "the",Space,Str "rendering",Space,Str "looks",Space,Str "like",Space,Str "the",Space,Str "following",Space,Str "image:"] +,RawBlock (Format "html") "</section>" +,RawBlock (Format "html") "<section id=\"mathml-027\" class=\"ctest\">" +,Header 2 ("",[],[]) [Span ("",["nature"],[]) [Str "[REQUIRED]"],Space,Span ("",["test-id"],[]) [Str "mathml-027"],Str "Elementary",Space,Str "math:",Space,Str "long",Space,Str "division",Space,Str "notation"] +,Para [Str "Tests",Space,Str "whether",Space,Code ("",[],[]) "mlongdiv",Space,Str "elements",Space,Str "(from",Space,Str "elementary",Space,Str "math)",Space,Str "are",Space,Str "supported."] +,Para [Str "The",Space,Str "test",Space,Str "passes",Space,Str "if",Space,Str "the",Space,Str "rendering",Space,Str "looks",Space,Str "like",Space,Str "the",Space,Str "following",Space,Str "image:",Space,Str "."] +,RawBlock (Format "html") "</section>" +,RawBlock (Format "html") "</section>" +,Para [Span ("content-switch-001.xhtml",[],[]) []] +,RawBlock (Format "html") "<section id=\"epub-switch\">" +,Header 3 ("",[],[]) [Code ("",[],[]) "epub:switch"] +,RawBlock (Format "html") "<section id=\"switch-010\" class=\"ctest\">" +,Header 4 ("",[],[]) [Span ("",["nature"],[]) [Str "[REQUIRED]"],Space,Span ("",["test-id"],[]) [Str "switch-010"],Space,Str "Support"] +,Para [Str "Tests",Space,Str "whether",Space,Str "the",Space,Code ("",[],[]) "epub:switch",Space,Str "element",Space,Str "is",Space,Str "supported."] +,Para [Str "PASS"] +,Para [Str "If",Space,Str "only",Space,Str "the",Space,Str "word",Space,Str "\"PASS\"",Space,Str "is",Space,Str "rendered",Space,Str "before",Space,Str "this",Space,Str "paragraph,",Space,Str "the",Space,Str "test",Space,Str "passes.",Space,Str "If",Space,Str "both",Space,Str "\"PASS\"",Space,Str "and",Space,Str "\"FAIL\"",Space,Str "are",Space,Str "rendered,",Space,Str "or",Space,Str "neither",Space,Str "\"PASS\"",Space,Str "nor",Space,Str "\"FAIL\"",Space,Str "is",Space,Str "rendered,",Space,Str "the",Space,Str "test",Space,Str "fails."] +,RawBlock (Format "html") "</section>" +,RawBlock (Format "html") "<section id=\"switch-020\" class=\"otest\">" +,Header 4 ("",[],[]) [Span ("",["nature"],[]) [Str "[OPTIONAL]"],Space,Span ("",["test-id"],[]) [Str "switch-020"],Space,Str "MathML",Space,Str "Embedding"] +,Para [Str "Tests",Space,Str "whether",Space,Str "the",Space,Str "MathML",Space,Str "namespace",Space,Str "is",Space,Str "recognized",Space,Str "when",Space,Str "used",Space,Str "in",Space,Str "an",Space,Code ("",[],[]) "epub:case",Space,Str "element."] +,Para [Math InlineMath "{2x}{+ y - z}"] +,Para [Str "If",Space,Str "a",Space,Str "MathML",Space,Str "equation",Space,Str "is",Space,Str "rendered",Space,Str "before",Space,Str "this",Space,Str "paragraph,",Space,Str "the",Space,Str "test",Space,Str "passes."] +,Para [Str "If",Space,Str "test",Space,Code ("",[],[]) "switch-010",Space,Str "did",Space,Str "not",Space,Str "pass,",Space,Str "this",Space,Str "test",Space,Str "should",Space,Str "be",Space,Str "marked",Space,Code ("",[],[]) "Not Supported",Str "."] +,RawBlock (Format "html") "</section>" +,RawBlock (Format "html") "</section>"] diff --git a/tests/epub/formatting.epub b/tests/epub/formatting.epub Binary files differnew file mode 100644 index 000000000..f3f9b5b93 --- /dev/null +++ b/tests/epub/formatting.epub diff --git a/tests/epub/formatting.native b/tests/epub/formatting.native new file mode 100644 index 000000000..bdf86fa20 --- /dev/null +++ b/tests/epub/formatting.native @@ -0,0 +1,447 @@ +[Para [Span ("front.xhtml",[],[]) []] +,RawBlock (Format "html") "<section>" +,Header 1 ("",[],[]) [Str "EPUB",Space,Str "3",Space,Str "Styling",Space,Str "Test",Space,Str "Document:",Space,Str "0101"] +,RawBlock (Format "html") "<section>" +,Header 2 ("",[],[]) [Str "Status",Space,Str "of",Space,Str "this",Space,Str "Document"] +,Para [Str "This",Space,Str "publication",Space,Str "is",Space,Str "currently",Space,Str "considered",Space,Span ("",["status"],[]) [Str "[UNDER",Space,Str "DEVELOPMENT]"],Space,Str "by",Space,Str "the",Space,Str "IDPF."] +,Para [Str "This",Space,Str "publication",Space,Str "is",Space,Str "part",Space,Str "of",Space,Str "version",Space,Span ("",["version"],[]) [Str "X.X"],Space,Str "of",Space,Str "the",Space,Str "EPUB",Space,Str "3.0",Space,Str "Compliance",Space,Str "Test",Space,Str "Suite",Space,Str "released",Space,Str "on",Space,RawInline (Format "html") "<time class=\"release\">",Str "TBD",RawInline (Format "html") "</time>",Str "."] +,Para [Str "Before",Space,Str "using",Space,Str "this",Space,Str "publication",Space,Str "to",Space,Str "evaluate",Space,Str "reading",Space,Str "systems,",Space,Str "testers",Space,Str "are",Space,Str "strongly",Space,Str "encouraged",Space,Str "to",Space,Str "verify",Space,Str "that",Space,Str "they",Space,Str "have",Space,Str "the",Space,Str "latest",Space,Str "release",Space,Str "by",Space,Str "checking",Space,Str "the",Space,Str "current",Space,Str "release",Space,Str "version",Space,Str "and",Space,Str "date",Space,Str "of",Space,Str "the",Space,Str "test",Space,Str "suite",Space,Str "at",Space,Link [Str "TBD"] ("","")] +,Para [Str "This",Space,Str "publication",Space,Str "is",Space,Str "one",Space,Str "of",Space,Str "several",Space,Str "that",Space,Str "currently",Space,Str "comprise",Space,Str "the",Space,Str "EPUB",Space,Str "3",Space,Str "conformance",Space,Str "test",Space,Str "suite",Space,Str "for",Space,Str "reflowable",Space,Str "content.",Space,Str "The",Space,Str "complete",Space,Str "test",Space,Str "suite",Space,Str "includes",Space,Str "all",Space,Str "of",Space,Str "the",Space,Str "following",Space,Str "publications:"] +,OrderedList (1,DefaultStyle,DefaultDelim) + [[Plain [Str "."]]] +,RawBlock (Format "html") "</section>" +,RawBlock (Format "html") "<section>" +,Header 2 ("",[],[]) [Str "About",Space,Str "this",Space,Str "Document"] +,Para [Str "This",Space,Str "document",Space,Str "focuses",Space,Str "on",Space,Str "human-evaluated",Space,Str "binary",Space,Str "(pass/fail)",Space,Str "tests",Space,Str "in",Space,Str "a",Space,Str "reflowable",Space,Str "context.",Space,Str "Tests",Space,Str "for",Space,Str "fixed-layout",Space,Str "content",Space,Str "and",Space,Str "other",Space,Str "individual",Space,Str "tests",Space,Str "that",Space,Str "require",Space,Str "a",Space,Str "dedicated",Space,Str "epub",Space,Str "file",Space,Str "are",Space,Str "available",Space,Str "in",Space,Str "additional",Space,Str "sibling",Space,Str "documents;",Space,Str "refer",Space,Str "to",Space,Str "the",Space,Link [Str "test",Space,Str "suite",Space,Str "wiki"] ("Overview",""),Space,Str "(",Code ("",[],[]) "https://github.com/mgylling/epub-testsuite/wiki/Overview",Str ")",Space,Str "for",Space,Str "additional",Space,Str "information."] +,RawBlock (Format "html") "</section>" +,RawBlock (Format "html") "<section>" +,Header 2 ("",[],[]) [Str "Conventions"] +,Para [Str "The",Space,Str "following",Space,Str "conventions",Space,Str "are",Space,Str "used",Space,Str "throughout",Space,Str "the",Space,Str "document:"] +,DefinitionList + [([Str "1.",Space,Str "Locating",Space,Str "a",Space,Str "test"], + [[Div ("",["ctest"],[]) [Para [Str "Tests",Space,Str "for",Space,Emph [Str "required"],Space,Str "Reading",Space,Str "System",Space,Str "functionality",Space,Str "are",Space,Str "preceded",Space,Str "by",Space,Str "the",Space,Str "label:",Space,Span ("",["nature"],[("style","display: inline; font-size: 100%")]) [Str "[REQUIRED]"]]] + ,Div ("",["otest"],[]) [Para [Str "Tests",Space,Str "for",Space,Emph [Str "optional"],Space,Str "Reading",Space,Str "System",Space,Str "functionality",Space,Str "are",Space,Str "preceded",Space,Str "by",Space,Str "the",Space,Str "label:",Space,Span ("",["nature"],[("style","display: inline; font-size: 100%")]) [Str "[OPTIONAL]"]]]]]) + ,([Str "2.",Space,Str "Performing",Space,Str "the",Space,Str "test"], + [[Plain [Str "Each",Space,Str "test",Space,Str "includes",Space,Str "a",Space,Str "description",Space,Str "of",Space,Str "its",Space,Str "purpose",Space,Str "followed",Space,Str "by",Space,Str "the",Space,Str "actual",Space,Strong [Str "test",Space,Str "statement,",Space,Str "which",Space,Str "can",Space,Str "always",Space,Str "be",Space,Str "evaluated",Space,Str "to",Space,Str "true",Space,Str "or",Space,Str "false"],Str ".",Space,Str "These",Space,Str "statements",Space,Str "typically",Space,Str "have",Space,Str "the",Space,Str "form:",Space,Str "\"If",Space,Str "[some",Space,Str "condition],",Space,Str "the",Space,Str "test",Space,Str "passes\"."]]]) + ,([Str "3.",Space,Str "Scoring",Space,Str "in",Space,Str "the",Space,Str "results",Space,Str "form"], + [[Plain [Str "@@@TODO",Space,Str "provide",Space,Str "info",Space,Str "on",Space,Str "where",Space,Str "to",Space,Str "get",Space,Str "the",Space,Str "results",Space,Str "form"]]])] +,RawBlock (Format "html") "</section>" +,RawBlock (Format "html") "</section>" +,Para [Span ("styling-xhtml-001.xhtml",[],[]) []] +,RawBlock (Format "html") "<section id=\"epub-css\">" +,Header 1 ("",[],[]) [Str "EPUB",Space,Str "Style",Space,Str "Sheets"] +,Para [Str "This",Space,Str "section",Space,Str "contains",Space,Str "tests",Space,Str "for",Space,Str "styling",Space,Str "and",Space,Str "layout."] +,RawBlock (Format "html") "</section>" +,Para [Span ("styling-xhtml-003.xhtml",[],[]) []] +,RawBlock (Format "html") "<section id=\"style-110\" class=\"ctest\">" +,Header 2 ("",[],[]) [Span ("",["nature"],[]) [Str "[REQUIRED]"],Space,Span ("",["test-id"],[]) [Str "style-110"],Space,Str "Multi-Column",Space,Str "Layouts"] +,Para [Str "Tests",Space,Str "whether",Space,Str "the",Space,Code ("",[],[]) "CSS Multi-Column Layout",Space,Str "properties",Space,Str "are",Space,Str "supported."] +,Div ("",["multicol"],[]) [Para [Str "Lorem",Space,Str "ipsum",Space,Str "dolor",Space,Str "sit",Space,Str "amet,",Space,Str "consectetur",Space,Str "adipisicing",Space,Str "elit,",Space,Str "sed",Space,Str "do",Space,Str "eiusmod",Space,Str "tempor",Space,Str "incididunt",Space,Str "ut",Space,Str "labore",Space,Str "et",Space,Str "dolore",Space,Str "magna",Space,Str "aliqua.",Space,Str "Ut",Space,Str "enim",Space,Str "ad",Space,Str "minim",Space,Str "veniam,",Space,Str "quis",Space,Str "nostrud",Space,Str "exercitation",Space,Str "ullamco",Space,Str "laboris",Space,Str "nisi",Space,Str "ut",Space,Str "aliquip",Space,Str "ex",Space,Str "ea",Space,Str "commodo",Space,Str "consequat.",Space,Str "Duis",Space,Str "aute",Space,Str "irure",Space,Str "dolor",Space,Str "in",Space,Str "reprehenderit",Space,Str "in",Space,Str "voluptate",Space,Str "velit",Space,Str "esse",Space,Str "cillum",Space,Str "dolore",Space,Str "eu",Space,Str "fugiat",Space,Str "nulla",Space,Str "pariatur.",Space,Str "Excepteur",Space,Str "sint",Space,Str "occaecat",Space,Str "cupidatat",Space,Str "non",Space,Str "proident,",Space,Str "sunt",Space,Str "in",Space,Str "culpa",Space,Str "qui",Space,Str "officia",Space,Str "deserunt",Space,Str "mollit",Space,Str "anim",Space,Str "id",Space,Str "est",Space,Str "laborum."],Para [Str "Lorem",Space,Str "ipsum",Space,Str "dolor",Space,Str "sit",Space,Str "amet,",Space,Str "consectetur",Space,Str "adipisicing",Space,Str "elit,",Space,Str "sed",Space,Str "do",Space,Str "eiusmod",Space,Str "tempor",Space,Str "incididunt",Space,Str "ut",Space,Str "labore",Space,Str "et",Space,Str "dolore",Space,Str "magna",Space,Str "aliqua.",Space,Str "Ut",Space,Str "enim",Space,Str "ad",Space,Str "minim",Space,Str "veniam,",Space,Str "quis",Space,Str "nostrud",Space,Str "exercitation",Space,Str "ullamco",Space,Str "laboris",Space,Str "nisi",Space,Str "ut",Space,Str "aliquip",Space,Str "ex",Space,Str "ea",Space,Str "commodo",Space,Str "consequat.",Space,Str "Duis",Space,Str "aute",Space,Str "irure",Space,Str "dolor",Space,Str "in",Space,Str "reprehenderit",Space,Str "in",Space,Str "voluptate",Space,Str "velit",Space,Str "esse",Space,Str "cillum",Space,Str "dolore",Space,Str "eu",Space,Str "fugiat",Space,Str "nulla",Space,Str "pariatur.",Space,Str "Excepteur",Space,Str "sint",Space,Str "occaecat",Space,Str "cupidatat",Space,Str "non",Space,Str "proident,",Space,Str "sunt",Space,Str "in",Space,Str "culpa",Space,Str "qui",Space,Str "officia",Space,Str "deserunt",Space,Str "mollit",Space,Str "anim",Space,Str "id",Space,Str "est",Space,Str "laborum."],Para [Str "Lorem",Space,Str "ipsum",Space,Str "dolor",Space,Str "sit",Space,Str "amet,",Space,Str "consectetur",Space,Str "adipisicing",Space,Str "elit,",Space,Str "sed",Space,Str "do",Space,Str "eiusmod",Space,Str "tempor",Space,Str "incididunt",Space,Str "ut",Space,Str "labore",Space,Str "et",Space,Str "dolore",Space,Str "magna",Space,Str "aliqua.",Space,Str "Ut",Space,Str "enim",Space,Str "ad",Space,Str "minim",Space,Str "veniam,",Space,Str "quis",Space,Str "nostrud",Space,Str "exercitation",Space,Str "ullamco",Space,Str "laboris",Space,Str "nisi",Space,Str "ut",Space,Str "aliquip",Space,Str "ex",Space,Str "ea",Space,Str "commodo",Space,Str "consequat.",Space,Str "Duis",Space,Str "aute",Space,Str "irure",Space,Str "dolor",Space,Str "in",Space,Str "reprehenderit",Space,Str "in",Space,Str "voluptate",Space,Str "velit",Space,Str "esse",Space,Str "cillum",Space,Str "dolore",Space,Str "eu",Space,Str "fugiat",Space,Str "nulla",Space,Str "pariatur.",Space,Str "Excepteur",Space,Str "sint",Space,Str "occaecat",Space,Str "cupidatat",Space,Str "non",Space,Str "proident,",Space,Str "sunt",Space,Str "in",Space,Str "culpa",Space,Str "qui",Space,Str "officia",Space,Str "deserunt",Space,Str "mollit",Space,Str "anim",Space,Str "id",Space,Str "est",Space,Str "laborum."],Para [Str "Lorem",Space,Str "ipsum",Space,Str "dolor",Space,Str "sit",Space,Str "amet,",Space,Str "consectetur",Space,Str "adipisicing",Space,Str "elit,",Space,Str "sed",Space,Str "do",Space,Str "eiusmod",Space,Str "tempor",Space,Str "incididunt",Space,Str "ut",Space,Str "labore",Space,Str "et",Space,Str "dolore",Space,Str "magna",Space,Str "aliqua.",Space,Str "Ut",Space,Str "enim",Space,Str "ad",Space,Str "minim",Space,Str "veniam,",Space,Str "quis",Space,Str "nostrud",Space,Str "exercitation",Space,Str "ullamco",Space,Str "laboris",Space,Str "nisi",Space,Str "ut",Space,Str "aliquip",Space,Str "ex",Space,Str "ea",Space,Str "commodo",Space,Str "consequat.",Space,Str "Duis",Space,Str "aute",Space,Str "irure",Space,Str "dolor",Space,Str "in",Space,Str "reprehenderit",Space,Str "in",Space,Str "voluptate",Space,Str "velit",Space,Str "esse",Space,Str "cillum",Space,Str "dolore",Space,Str "eu",Space,Str "fugiat",Space,Str "nulla",Space,Str "pariatur.",Space,Str "Excepteur",Space,Str "sint",Space,Str "occaecat",Space,Str "cupidatat",Space,Str "non",Space,Str "proident,",Space,Str "sunt",Space,Str "in",Space,Str "culpa",Space,Str "qui",Space,Str "officia",Space,Str "deserunt",Space,Str "mollit",Space,Str "anim",Space,Str "id",Space,Str "est",Space,Str "laborum."],Para [Str "Lorem",Space,Str "ipsum",Space,Str "dolor",Space,Str "sit",Space,Str "amet,",Space,Str "consectetur",Space,Str "adipisicing",Space,Str "elit,",Space,Str "sed",Space,Str "do",Space,Str "eiusmod",Space,Str "tempor",Space,Str "incididunt",Space,Str "ut",Space,Str "labore",Space,Str "et",Space,Str "dolore",Space,Str "magna",Space,Str "aliqua.",Space,Str "Ut",Space,Str "enim",Space,Str "ad",Space,Str "minim",Space,Str "veniam,",Space,Str "quis",Space,Str "nostrud",Space,Str "exercitation",Space,Str "ullamco",Space,Str "laboris",Space,Str "nisi",Space,Str "ut",Space,Str "aliquip",Space,Str "ex",Space,Str "ea",Space,Str "commodo",Space,Str "consequat.",Space,Str "Duis",Space,Str "aute",Space,Str "irure",Space,Str "dolor",Space,Str "in",Space,Str "reprehenderit",Space,Str "in",Space,Str "voluptate",Space,Str "velit",Space,Str "esse",Space,Str "cillum",Space,Str "dolore",Space,Str "eu",Space,Str "fugiat",Space,Str "nulla",Space,Str "pariatur.",Space,Str "Excepteur",Space,Str "sint",Space,Str "occaecat",Space,Str "cupidatat",Space,Str "non",Space,Str "proident,",Space,Str "sunt",Space,Str "in",Space,Str "culpa",Space,Str "qui",Space,Str "officia",Space,Str "deserunt",Space,Str "mollit",Space,Str "anim",Space,Str "id",Space,Str "est",Space,Str "laborum."],Para [Str "Lorem",Space,Str "ipsum",Space,Str "dolor",Space,Str "sit",Space,Str "amet,",Space,Str "consectetur",Space,Str "adipisicing",Space,Str "elit,",Space,Str "sed",Space,Str "do",Space,Str "eiusmod",Space,Str "tempor",Space,Str "incididunt",Space,Str "ut",Space,Str "labore",Space,Str "et",Space,Str "dolore",Space,Str "magna",Space,Str "aliqua.",Space,Str "Ut",Space,Str "enim",Space,Str "ad",Space,Str "minim",Space,Str "veniam,",Space,Str "quis",Space,Str "nostrud",Space,Str "exercitation",Space,Str "ullamco",Space,Str "laboris",Space,Str "nisi",Space,Str "ut",Space,Str "aliquip",Space,Str "ex",Space,Str "ea",Space,Str "commodo",Space,Str "consequat.",Space,Str "Duis",Space,Str "aute",Space,Str "irure",Space,Str "dolor",Space,Str "in",Space,Str "reprehenderit",Space,Str "in",Space,Str "voluptate",Space,Str "velit",Space,Str "esse",Space,Str "cillum",Space,Str "dolore",Space,Str "eu",Space,Str "fugiat",Space,Str "nulla",Space,Str "pariatur.",Space,Str "Excepteur",Space,Str "sint",Space,Str "occaecat",Space,Str "cupidatat",Space,Str "non",Space,Str "proident,",Space,Str "sunt",Space,Str "in",Space,Str "culpa",Space,Str "qui",Space,Str "officia",Space,Str "deserunt",Space,Str "mollit",Space,Str "anim",Space,Str "id",Space,Str "est",Space,Str "laborum."],Para [Str "Lorem",Space,Str "ipsum",Space,Str "dolor",Space,Str "sit",Space,Str "amet,",Space,Str "consectetur",Space,Str "adipisicing",Space,Str "elit,",Space,Str "sed",Space,Str "do",Space,Str "eiusmod",Space,Str "tempor",Space,Str "incididunt",Space,Str "ut",Space,Str "labore",Space,Str "et",Space,Str "dolore",Space,Str "magna",Space,Str "aliqua.",Space,Str "Ut",Space,Str "enim",Space,Str "ad",Space,Str "minim",Space,Str "veniam,",Space,Str "quis",Space,Str "nostrud",Space,Str "exercitation",Space,Str "ullamco",Space,Str "laboris",Space,Str "nisi",Space,Str "ut",Space,Str "aliquip",Space,Str "ex",Space,Str "ea",Space,Str "commodo",Space,Str "consequat.",Space,Str "Duis",Space,Str "aute",Space,Str "irure",Space,Str "dolor",Space,Str "in",Space,Str "reprehenderit",Space,Str "in",Space,Str "voluptate",Space,Str "velit",Space,Str "esse",Space,Str "cillum",Space,Str "dolore",Space,Str "eu",Space,Str "fugiat",Space,Str "nulla",Space,Str "pariatur.",Space,Str "Excepteur",Space,Str "sint",Space,Str "occaecat",Space,Str "cupidatat",Space,Str "non",Space,Str "proident,",Space,Str "sunt",Space,Str "in",Space,Str "culpa",Space,Str "qui",Space,Str "officia",Space,Str "deserunt",Space,Str "mollit",Space,Str "anim",Space,Str "id",Space,Str "est",Space,Str "laborum."],Para [Str "Lorem",Space,Str "ipsum",Space,Str "dolor",Space,Str "sit",Space,Str "amet,",Space,Str "consectetur",Space,Str "adipisicing",Space,Str "elit,",Space,Str "sed",Space,Str "do",Space,Str "eiusmod",Space,Str "tempor",Space,Str "incididunt",Space,Str "ut",Space,Str "labore",Space,Str "et",Space,Str "dolore",Space,Str "magna",Space,Str "aliqua.",Space,Str "Ut",Space,Str "enim",Space,Str "ad",Space,Str "minim",Space,Str "veniam,",Space,Str "quis",Space,Str "nostrud",Space,Str "exercitation",Space,Str "ullamco",Space,Str "laboris",Space,Str "nisi",Space,Str "ut",Space,Str "aliquip",Space,Str "ex",Space,Str "ea",Space,Str "commodo",Space,Str "consequat.",Space,Str "Duis",Space,Str "aute",Space,Str "irure",Space,Str "dolor",Space,Str "in",Space,Str "reprehenderit",Space,Str "in",Space,Str "voluptate",Space,Str "velit",Space,Str "esse",Space,Str "cillum",Space,Str "dolore",Space,Str "eu",Space,Str "fugiat",Space,Str "nulla",Space,Str "pariatur.",Space,Str "Excepteur",Space,Str "sint",Space,Str "occaecat",Space,Str "cupidatat",Space,Str "non",Space,Str "proident,",Space,Str "sunt",Space,Str "in",Space,Str "culpa",Space,Str "qui",Space,Str "officia",Space,Str "deserunt",Space,Str "mollit",Space,Str "anim",Space,Str "id",Space,Str "est",Space,Str "laborum."],Para [Str "Lorem",Space,Str "ipsum",Space,Str "dolor",Space,Str "sit",Space,Str "amet,",Space,Str "consectetur",Space,Str "adipisicing",Space,Str "elit,",Space,Str "sed",Space,Str "do",Space,Str "eiusmod",Space,Str "tempor",Space,Str "incididunt",Space,Str "ut",Space,Str "labore",Space,Str "et",Space,Str "dolore",Space,Str "magna",Space,Str "aliqua.",Space,Str "Ut",Space,Str "enim",Space,Str "ad",Space,Str "minim",Space,Str "veniam,",Space,Str "quis",Space,Str "nostrud",Space,Str "exercitation",Space,Str "ullamco",Space,Str "laboris",Space,Str "nisi",Space,Str "ut",Space,Str "aliquip",Space,Str "ex",Space,Str "ea",Space,Str "commodo",Space,Str "consequat.",Space,Str "Duis",Space,Str "aute",Space,Str "irure",Space,Str "dolor",Space,Str "in",Space,Str "reprehenderit",Space,Str "in",Space,Str "voluptate",Space,Str "velit",Space,Str "esse",Space,Str "cillum",Space,Str "dolore",Space,Str "eu",Space,Str "fugiat",Space,Str "nulla",Space,Str "pariatur.",Space,Str "Excepteur",Space,Str "sint",Space,Str "occaecat",Space,Str "cupidatat",Space,Str "non",Space,Str "proident,",Space,Str "sunt",Space,Str "in",Space,Str "culpa",Space,Str "qui",Space,Str "officia",Space,Str "deserunt",Space,Str "mollit",Space,Str "anim",Space,Str "id",Space,Str "est",Space,Str "laborum."]] +,Para [Str "If",Space,Str "the",Space,Str "preceding",Space,Str "text",Space,Str "is",Space,Str "rendered",Space,Str "in",Space,Str "three",Space,Str "columns,",Space,Str "the",Space,Str "test",Space,Str "passes."] +,RawBlock (Format "html") "</section>" +,Para [Span ("styling-xhtml-002.xhtml",[],[]) []] +,RawBlock (Format "html") "<section id=\"style-lists\">" +,Header 2 ("",[],[]) [Str "Lists"] +,RawBlock (Format "html") "<section id=\"style-list-style-type\">" +,Header 3 ("",[],[]) [Str "The",Space,Code ("",[],[]) "list-style-type",Space,Str "property"] +,RawBlock (Format "html") "<section id=\"style-009\" class=\"ctest\">" +,Header 4 ("",[],[]) [Span ("",["nature"],[]) [Str "[REQUIRED]"],Space,Span ("",["test-id"],[]) [Str "style-009"],Space,Code ("",[],[]) "decimal"] +,Para [Str "Tests",Space,Str "whether",Space,Str "the",Space,Code ("",[],[]) "list-style-type",Space,Str "property",Space,Str "set",Space,Str "to",Space,Code ("",[],[]) "decimal",Space,Str "is",Space,Str "supported",Space,Str "on",Space,Str "a",Space,Code ("",[],[]) "ol",Space,Str "element."] +,OrderedList (1,DefaultStyle,DefaultDelim) + [[Plain [Str "Lorem"]] + ,[Plain [Str "Ipsum"]] + ,[Plain [Str "Dolor"]] + ,[Plain [Str "Sit"]] + ,[Plain [Str "Amet"]]] +,Para [Str "If",Space,Str "the",Space,Str "preceding",Space,Str "list",Space,Str "has",Space,Str "decimal",Space,Str "markers",Space,Str "in",Space,Str "ascending",Space,Str "order,",Space,Str "the",Space,Str "test",Space,Str "passes."] +,RawBlock (Format "html") "</section>" +,RawBlock (Format "html") "<section id=\"style-010\" class=\"ctest\">" +,Header 4 ("",[],[]) [Span ("",["nature"],[]) [Str "[REQUIRED]"],Space,Span ("",["test-id"],[]) [Str "style-010"],Space,Code ("",[],[]) "circle"] +,Para [Str "Tests",Space,Str "whether",Space,Str "the",Space,Code ("",[],[]) "list-style-type",Space,Str "property",Space,Str "set",Space,Str "to",Space,Code ("",[],[]) "circle",Space,Str "is",Space,Str "supported",Space,Str "on",Space,Str "a",Space,Code ("",[],[]) "ul",Space,Str "element."] +,BulletList + [[Plain [Str "Lorem"]] + ,[Plain [Str "Ipsum"]] + ,[Plain [Str "Dolor"]] + ,[Plain [Str "Sit"]] + ,[Plain [Str "Amet"]]] +,Para [Str "If",Space,Str "the",Space,Str "preceding",Space,Str "list",Space,Str "has",Space,Str "circle",Space,Str "markers,",Space,Str "the",Space,Str "test",Space,Str "passes."] +,RawBlock (Format "html") "</section>" +,RawBlock (Format "html") "<section id=\"style-011\" class=\"ctest\">" +,Header 4 ("",[],[]) [Span ("",["nature"],[]) [Str "[REQUIRED]"],Space,Span ("",["test-id"],[]) [Str "style-011"],Space,Code ("",[],[]) "square"] +,Para [Str "Tests",Space,Str "whether",Space,Str "the",Space,Code ("",[],[]) "list-style-type",Space,Str "property",Space,Str "set",Space,Str "to",Space,Code ("",[],[]) "square",Space,Str "is",Space,Str "supported",Space,Str "on",Space,Str "a",Space,Code ("",[],[]) "ul",Space,Str "element."] +,BulletList + [[Plain [Str "Lorem"]] + ,[Plain [Str "Ipsum"]] + ,[Plain [Str "Dolor"]] + ,[Plain [Str "Sit"]] + ,[Plain [Str "Amet"]]] +,Para [Str "If",Space,Str "the",Space,Str "preceding",Space,Str "list",Space,Str "has",Space,Str "square",Space,Str "markers,",Space,Str "the",Space,Str "test",Space,Str "passes."] +,RawBlock (Format "html") "</section>" +,RawBlock (Format "html") "<section id=\"style-012\" class=\"ctest\">" +,Header 4 ("",[],[]) [Span ("",["nature"],[]) [Str "[REQUIRED]"],Space,Span ("",["test-id"],[]) [Str "style-012"],Space,Code ("",[],[]) "disc"] +,Para [Str "Tests",Space,Str "whether",Space,Str "the",Space,Code ("",[],[]) "list-style-type",Space,Str "property",Space,Str "set",Space,Str "to",Space,Code ("",[],[]) "disc",Space,Str "is",Space,Str "supported",Space,Str "on",Space,Str "a",Space,Code ("",[],[]) "ul",Space,Str "element."] +,BulletList + [[Plain [Str "Lorem"]] + ,[Plain [Str "Ipsum"]] + ,[Plain [Str "Dolor"]] + ,[Plain [Str "Sit"]] + ,[Plain [Str "Amet"]]] +,Para [Str "If",Space,Str "the",Space,Str "preceding",Space,Str "list",Space,Str "has",Space,Str "disc",Space,Str "markers,",Space,Str "the",Space,Str "test",Space,Str "passes."] +,RawBlock (Format "html") "</section>" +,RawBlock (Format "html") "<section id=\"style-013\" class=\"ctest\">" +,Header 4 ("",[],[]) [Span ("",["nature"],[]) [Str "[REQUIRED]"],Space,Span ("",["test-id"],[]) [Str "style-013"],Space,Code ("",[],[]) "lower-latin"] +,Para [Str "Tests",Space,Str "whether",Space,Str "the",Space,Code ("",[],[]) "list-style-type",Space,Str "property",Space,Str "set",Space,Str "to",Space,Code ("",[],[]) "lower-latin",Space,Str "is",Space,Str "supported",Space,Str "on",Space,Str "a",Space,Code ("",[],[]) "ol",Space,Str "element."] +,OrderedList (1,DefaultStyle,DefaultDelim) + [[Plain [Str "Lorem"]] + ,[Plain [Str "Ipsum"]] + ,[Plain [Str "Dolor"]] + ,[Plain [Str "Sit"]] + ,[Plain [Str "Amet"]]] +,Para [Str "If",Space,Str "the",Space,Str "preceding",Space,Str "list",Space,Str "has",Space,Str "lower-latin",Space,Str "markers",Space,Str "in",Space,Str "ascending",Space,Str "order,",Space,Str "the",Space,Str "test",Space,Str "passes."] +,RawBlock (Format "html") "</section>" +,RawBlock (Format "html") "<section id=\"style-014\" class=\"ctest\">" +,Header 4 ("",[],[]) [Span ("",["nature"],[]) [Str "[REQUIRED]"],Space,Span ("",["test-id"],[]) [Str "style-014"],Space,Code ("",[],[]) "lower-roman"] +,Para [Str "Tests",Space,Str "whether",Space,Str "the",Space,Code ("",[],[]) "list-style-type",Space,Str "property",Space,Str "set",Space,Str "to",Space,Code ("",[],[]) "lower-roman",Space,Str "is",Space,Str "supported",Space,Str "on",Space,Str "a",Space,Code ("",[],[]) "ol",Space,Str "element."] +,OrderedList (1,DefaultStyle,DefaultDelim) + [[Plain [Str "Lorem"]] + ,[Plain [Str "Ipsum"]] + ,[Plain [Str "Dolor"]] + ,[Plain [Str "Sit"]] + ,[Plain [Str "Amet"]]] +,Para [Str "If",Space,Str "the",Space,Str "preceding",Space,Str "list",Space,Str "has",Space,Str "lower-roman",Space,Str "markers",Space,Str "in",Space,Str "ascending",Space,Str "order,",Space,Str "the",Space,Str "test",Space,Str "passes."] +,RawBlock (Format "html") "</section>" +,RawBlock (Format "html") "<section id=\"style-015\" class=\"ctest\">" +,Header 4 ("",[],[]) [Span ("",["nature"],[]) [Str "[REQUIRED]"],Space,Span ("",["test-id"],[]) [Str "style-015"],Space,Code ("",[],[]) "upper-alpha"] +,Para [Str "Tests",Space,Str "whether",Space,Str "the",Space,Code ("",[],[]) "list-style-type",Space,Str "property",Space,Str "set",Space,Str "to",Space,Code ("",[],[]) "upper-alpha",Space,Str "is",Space,Str "supported",Space,Str "on",Space,Str "a",Space,Code ("",[],[]) "ol",Space,Str "element."] +,OrderedList (1,DefaultStyle,DefaultDelim) + [[Plain [Str "Lorem"]] + ,[Plain [Str "Ipsum"]] + ,[Plain [Str "Dolor"]] + ,[Plain [Str "Sit"]] + ,[Plain [Str "Amet"]]] +,Para [Str "If",Space,Str "the",Space,Str "preceding",Space,Str "list",Space,Str "has",Space,Str "upper-alpha",Space,Str "markers",Space,Str "in",Space,Str "ascending",Space,Str "order,",Space,Str "the",Space,Str "test",Space,Str "passes."] +,RawBlock (Format "html") "</section>" +,RawBlock (Format "html") "<section id=\"style-016\" class=\"ctest\">" +,Header 4 ("",[],[]) [Span ("",["nature"],[]) [Str "[REQUIRED]"],Space,Span ("",["test-id"],[]) [Str "style-016"],Space,Code ("",[],[]) "hiragana"] +,Para [Str "Tests",Space,Str "whether",Space,Str "the",Space,Code ("",[],[]) "list-style-type",Space,Str "property",Space,Str "set",Space,Str "to",Space,Code ("",[],[]) "hiragana",Space,Str "is",Space,Str "supported",Space,Str "on",Space,Str "a",Space,Code ("",[],[]) "ol",Space,Str "element."] +,OrderedList (1,DefaultStyle,DefaultDelim) + [[Plain [Str "Lorem"]] + ,[Plain [Str "Ipsum"]] + ,[Plain [Str "Dolor"]] + ,[Plain [Str "Sit"]] + ,[Plain [Str "Amet"]]] +,Para [Str "If",Space,Str "the",Space,Str "preceding",Space,Str "list",Space,Str "has",Space,Str "hiragana",Space,Str "markers",Space,Str "in",Space,Str "ascending",Space,Str "order,",Space,Str "the",Space,Str "test",Space,Str "passes."] +,RawBlock (Format "html") "</section>" +,RawBlock (Format "html") "<section id=\"style-017\" class=\"ctest\">" +,Header 4 ("",[],[]) [Span ("",["nature"],[]) [Str "[REQUIRED]"],Space,Span ("",["test-id"],[]) [Str "style-017"],Space,Code ("",[],[]) "hiragana-iroha"] +,Para [Str "Tests",Space,Str "whether",Space,Str "the",Space,Code ("",[],[]) "list-style-type",Space,Str "property",Space,Str "set",Space,Str "to",Space,Code ("",[],[]) "hiragana-iroha",Space,Str "is",Space,Str "supported",Space,Str "on",Space,Str "a",Space,Code ("",[],[]) "ol",Space,Str "element."] +,OrderedList (1,DefaultStyle,DefaultDelim) + [[Plain [Str "Lorem"]] + ,[Plain [Str "Ipsum"]] + ,[Plain [Str "Dolor"]] + ,[Plain [Str "Sit"]] + ,[Plain [Str "Amet"]]] +,Para [Str "If",Space,Str "the",Space,Str "preceding",Space,Str "list",Space,Str "has",Space,Str "hiragana-iroha",Space,Str "markers",Space,Str "in",Space,Str "ascending",Space,Str "order,",Space,Str "the",Space,Str "test",Space,Str "passes."] +,RawBlock (Format "html") "</section>" +,RawBlock (Format "html") "<section id=\"style-018\" class=\"ctest\">" +,Header 4 ("",[],[]) [Span ("",["nature"],[]) [Str "[REQUIRED]"],Space,Span ("",["test-id"],[]) [Str "style-018"],Space,Code ("",[],[]) "katakana"] +,Para [Str "Tests",Space,Str "whether",Space,Str "the",Space,Code ("",[],[]) "list-style-type",Space,Str "property",Space,Str "set",Space,Str "to",Space,Code ("",[],[]) "katakana",Space,Str "is",Space,Str "supported",Space,Str "on",Space,Str "a",Space,Code ("",[],[]) "ol",Space,Str "element."] +,OrderedList (1,DefaultStyle,DefaultDelim) + [[Plain [Str "Lorem"]] + ,[Plain [Str "Ipsum"]] + ,[Plain [Str "Dolor"]] + ,[Plain [Str "Sit"]] + ,[Plain [Str "Amet"]]] +,Para [Str "If",Space,Str "the",Space,Str "preceding",Space,Str "list",Space,Str "has",Space,Str "katakana",Space,Str "markers",Space,Str "in",Space,Str "ascending",Space,Str "order,",Space,Str "the",Space,Str "test",Space,Str "passes."] +,RawBlock (Format "html") "</section>" +,RawBlock (Format "html") "<section id=\"style-019\" class=\"ctest\">" +,Header 4 ("",[],[]) [Span ("",["nature"],[]) [Str "[REQUIRED]"],Space,Span ("",["test-id"],[]) [Str "style-019"],Space,Code ("",[],[]) "katakana-iroha"] +,Para [Str "Tests",Space,Str "whether",Space,Str "the",Space,Code ("",[],[]) "list-style-type",Space,Str "property",Space,Str "set",Space,Str "to",Space,Code ("",[],[]) "katakana-iroha",Space,Str "is",Space,Str "supported",Space,Str "on",Space,Str "a",Space,Code ("",[],[]) "ol",Space,Str "element."] +,OrderedList (1,DefaultStyle,DefaultDelim) + [[Plain [Str "Lorem"]] + ,[Plain [Str "Ipsum"]] + ,[Plain [Str "Dolor"]] + ,[Plain [Str "Sit"]] + ,[Plain [Str "Amet"]]] +,Para [Str "If",Space,Str "the",Space,Str "preceding",Space,Str "list",Space,Str "has",Space,Str "katakana-iroha",Space,Str "markers",Space,Str "in",Space,Str "ascending",Space,Str "order,",Space,Str "the",Space,Str "test",Space,Str "passes."] +,RawBlock (Format "html") "</section>" +,RawBlock (Format "html") "<section id=\"style-020\" class=\"ctest\">" +,Header 4 ("",[],[]) [Span ("",["nature"],[]) [Str "[REQUIRED]"],Space,Span ("",["test-id"],[]) [Str "style-020"],Space,Code ("",[],[]) "upper-roman"] +,Para [Str "Tests",Space,Str "whether",Space,Str "the",Space,Code ("",[],[]) "list-style-type",Space,Str "property",Space,Str "set",Space,Str "to",Space,Code ("",[],[]) "upper-roman",Space,Str "is",Space,Str "supported",Space,Str "on",Space,Str "a",Space,Code ("",[],[]) "ol",Space,Str "element."] +,OrderedList (1,DefaultStyle,DefaultDelim) + [[Plain [Str "Lorem"]] + ,[Plain [Str "Ipsum"]] + ,[Plain [Str "Dolor"]] + ,[Plain [Str "Sit"]] + ,[Plain [Str "Amet"]]] +,Para [Str "If",Space,Str "the",Space,Str "preceding",Space,Str "list",Space,Str "has",Space,Str "upper-roman",Space,Str "markers",Space,Str "in",Space,Str "ascending",Space,Str "order,",Space,Str "the",Space,Str "test",Space,Str "passes."] +,RawBlock (Format "html") "</section>" +,RawBlock (Format "html") "<section id=\"style-021\" class=\"ctest\">" +,Header 4 ("",[],[]) [Span ("",["nature"],[]) [Str "[REQUIRED]"],Space,Span ("",["test-id"],[]) [Str "style-021"],Space,Code ("",[],[]) "upper-latin"] +,Para [Str "Tests",Space,Str "whether",Space,Str "the",Space,Code ("",[],[]) "list-style-type",Space,Str "property",Space,Str "set",Space,Str "to",Space,Code ("",[],[]) "upper-latin",Space,Str "is",Space,Str "supported",Space,Str "on",Space,Str "a",Space,Code ("",[],[]) "ol",Space,Str "element."] +,OrderedList (1,DefaultStyle,DefaultDelim) + [[Plain [Str "Lorem"]] + ,[Plain [Str "Ipsum"]] + ,[Plain [Str "Dolor"]] + ,[Plain [Str "Sit"]] + ,[Plain [Str "Amet"]]] +,Para [Str "If",Space,Str "the",Space,Str "preceding",Space,Str "list",Space,Str "has",Space,Str "upper-latin",Space,Str "markers",Space,Str "in",Space,Str "ascending",Space,Str "order,",Space,Str "the",Space,Str "test",Space,Str "passes."] +,RawBlock (Format "html") "</section>" +,RawBlock (Format "html") "<section id=\"style-022\" class=\"ctest\">" +,Header 4 ("",[],[]) [Span ("",["nature"],[]) [Str "[REQUIRED]"],Space,Span ("",["test-id"],[]) [Str "style-022"],Space,Code ("",[],[]) "lower-alpha"] +,Para [Str "Tests",Space,Str "whether",Space,Str "the",Space,Code ("",[],[]) "list-style-type",Space,Str "property",Space,Str "set",Space,Str "to",Space,Code ("",[],[]) "lower-alpha",Space,Str "is",Space,Str "supported",Space,Str "on",Space,Str "a",Space,Code ("",[],[]) "ol",Space,Str "element."] +,OrderedList (1,DefaultStyle,DefaultDelim) + [[Plain [Str "Lorem"]] + ,[Plain [Str "Ipsum"]] + ,[Plain [Str "Dolor"]] + ,[Plain [Str "Sit"]] + ,[Plain [Str "Amet"]]] +,Para [Str "If",Space,Str "the",Space,Str "preceding",Space,Str "list",Space,Str "has",Space,Str "lower-alpha",Space,Str "markers",Space,Str "in",Space,Str "ascending",Space,Str "order,",Space,Str "the",Space,Str "test",Space,Str "passes."] +,RawBlock (Format "html") "</section>" +,RawBlock (Format "html") "<section id=\"style-023\" class=\"ctest\">" +,Header 4 ("",[],[]) [Span ("",["nature"],[]) [Str "[REQUIRED]"],Space,Span ("",["test-id"],[]) [Str "style-023"],Space,Code ("",[],[]) "lower-greek"] +,Para [Str "Tests",Space,Str "whether",Space,Str "the",Space,Code ("",[],[]) "list-style-type",Space,Str "property",Space,Str "set",Space,Str "to",Space,Code ("",[],[]) "lower-greek",Space,Str "is",Space,Str "supported",Space,Str "on",Space,Str "a",Space,Code ("",[],[]) "ol",Space,Str "element."] +,OrderedList (1,DefaultStyle,DefaultDelim) + [[Plain [Str "Lorem"]] + ,[Plain [Str "Ipsum"]] + ,[Plain [Str "Dolor"]] + ,[Plain [Str "Sit"]] + ,[Plain [Str "Amet"]]] +,Para [Str "If",Space,Str "the",Space,Str "preceding",Space,Str "list",Space,Str "has",Space,Str "lower-greek",Space,Str "markers",Space,Str "in",Space,Str "ascending",Space,Str "order,",Space,Str "the",Space,Str "test",Space,Str "passes."] +,RawBlock (Format "html") "</section>" +,RawBlock (Format "html") "<section id=\"style-024\" class=\"ctest\">" +,Header 4 ("",[],[]) [Span ("",["nature"],[]) [Str "[REQUIRED]"],Space,Span ("",["test-id"],[]) [Str "style-024"],Space,Code ("",[],[]) "armenian"] +,Para [Str "Tests",Space,Str "whether",Space,Str "the",Space,Code ("",[],[]) "list-style-type",Space,Str "property",Space,Str "set",Space,Str "to",Space,Code ("",[],[]) "armenian",Space,Str "is",Space,Str "supported",Space,Str "on",Space,Str "a",Space,Code ("",[],[]) "ol",Space,Str "element."] +,OrderedList (1,DefaultStyle,DefaultDelim) + [[Plain [Str "Lorem"]] + ,[Plain [Str "Ipsum"]] + ,[Plain [Str "Dolor"]] + ,[Plain [Str "Sit"]] + ,[Plain [Str "Amet"]]] +,Para [Str "If",Space,Str "the",Space,Str "preceding",Space,Str "list",Space,Str "has",Space,Str "armenian",Space,Str "markers",Space,Str "in",Space,Str "ascending",Space,Str "order,",Space,Str "the",Space,Str "test",Space,Str "passes."] +,RawBlock (Format "html") "</section>" +,RawBlock (Format "html") "<section id=\"style-025\" class=\"ctest\">" +,Header 4 ("",[],[]) [Span ("",["nature"],[]) [Str "[REQUIRED]"],Space,Span ("",["test-id"],[]) [Str "style-025"],Space,Code ("",[],[]) "cjk-ideographic"] +,Para [Str "Tests",Space,Str "whether",Space,Str "the",Space,Code ("",[],[]) "list-style-type",Space,Str "property",Space,Str "set",Space,Str "to",Space,Code ("",[],[]) "cjk-ideographic",Space,Str "is",Space,Str "supported",Space,Str "on",Space,Str "a",Space,Code ("",[],[]) "ol",Space,Str "element."] +,OrderedList (1,DefaultStyle,DefaultDelim) + [[Plain [Str "Lorem"]] + ,[Plain [Str "Ipsum"]] + ,[Plain [Str "Dolor"]] + ,[Plain [Str "Sit"]] + ,[Plain [Str "Amet"]]] +,Para [Str "If",Space,Str "the",Space,Str "preceding",Space,Str "list",Space,Str "has",Space,Str "cjk-ideographic",Space,Str "markers",Space,Str "in",Space,Str "ascending",Space,Str "order,",Space,Str "the",Space,Str "test",Space,Str "passes."] +,RawBlock (Format "html") "</section>" +,RawBlock (Format "html") "<section id=\"style-026\" class=\"ctest\">" +,Header 4 ("",[],[]) [Span ("",["nature"],[]) [Str "[REQUIRED]"],Space,Span ("",["test-id"],[]) [Str "style-026"],Space,Code ("",[],[]) "decimal-leading-zero"] +,Para [Str "Tests",Space,Str "whether",Space,Str "the",Space,Code ("",[],[]) "list-style-type",Space,Str "property",Space,Str "set",Space,Str "to",Space,Code ("",[],[]) "decimal-leading-zero",Space,Str "is",Space,Str "supported",Space,Str "on",Space,Str "a",Space,Code ("",[],[]) "ol",Space,Str "element."] +,OrderedList (1,DefaultStyle,DefaultDelim) + [[Plain [Str "Lorem"]] + ,[Plain [Str "Ipsum"]] + ,[Plain [Str "Dolor"]] + ,[Plain [Str "Sit"]] + ,[Plain [Str "Amet"]]] +,Para [Str "If",Space,Str "the",Space,Str "preceding",Space,Str "list",Space,Str "has",Space,Str "decimal-leading-zero",Space,Str "markers",Space,Str "in",Space,Str "ascending",Space,Str "order,",Space,Str "the",Space,Str "test",Space,Str "passes."] +,RawBlock (Format "html") "</section>" +,RawBlock (Format "html") "<section id=\"style-027\" class=\"ctest\">" +,Header 4 ("",[],[]) [Span ("",["nature"],[]) [Str "[REQUIRED]"],Space,Span ("",["test-id"],[]) [Str "style-027"],Space,Code ("",[],[]) "georgian"] +,Para [Str "Tests",Space,Str "whether",Space,Str "the",Space,Code ("",[],[]) "list-style-type",Space,Str "property",Space,Str "set",Space,Str "to",Space,Code ("",[],[]) "georgian",Space,Str "is",Space,Str "supported",Space,Str "on",Space,Str "a",Space,Code ("",[],[]) "ol",Space,Str "element."] +,OrderedList (1,DefaultStyle,DefaultDelim) + [[Plain [Str "Lorem"]] + ,[Plain [Str "Ipsum"]] + ,[Plain [Str "Dolor"]] + ,[Plain [Str "Sit"]] + ,[Plain [Str "Amet"]]] +,Para [Str "If",Space,Str "the",Space,Str "preceding",Space,Str "list",Space,Str "has",Space,Str "georgian",Space,Str "markers",Space,Str "in",Space,Str "ascending",Space,Str "order,",Space,Str "the",Space,Str "test",Space,Str "passes."] +,RawBlock (Format "html") "</section>" +,RawBlock (Format "html") "<section id=\"style-028\" class=\"ctest\">" +,Header 4 ("",[],[]) [Span ("",["nature"],[]) [Str "[REQUIRED]"],Space,Span ("",["test-id"],[]) [Str "style-028"],Space,Code ("",[],[]) "hebrew"] +,Para [Str "Tests",Space,Str "whether",Space,Str "the",Space,Code ("",[],[]) "list-style-type",Space,Str "property",Space,Str "set",Space,Str "to",Space,Code ("",[],[]) "hebrew",Space,Str "is",Space,Str "supported",Space,Str "on",Space,Str "a",Space,Code ("",[],[]) "ol",Space,Str "element."] +,OrderedList (1,DefaultStyle,DefaultDelim) + [[Plain [Str "Lorem"]] + ,[Plain [Str "Ipsum"]] + ,[Plain [Str "Dolor"]] + ,[Plain [Str "Sit"]] + ,[Plain [Str "Amet"]]] +,Para [Str "If",Space,Str "the",Space,Str "preceding",Space,Str "list",Space,Str "has",Space,Str "hebrew",Space,Str "markers",Space,Str "in",Space,Str "ascending",Space,Str "order,",Space,Str "the",Space,Str "test",Space,Str "passes."] +,RawBlock (Format "html") "</section>" +,RawBlock (Format "html") "<section id=\"style-029\" class=\"ctest\">" +,Header 4 ("",[],[]) [Span ("",["nature"],[]) [Str "[REQUIRED]"],Space,Span ("",["test-id"],[]) [Str "style-029"],Space,Code ("",[],[]) "none"] +,Para [Str "Tests",Space,Str "whether",Space,Str "the",Space,Code ("",[],[]) "list-style-type",Space,Str "property",Space,Str "set",Space,Str "to",Space,Code ("",[],[]) "none",Space,Str "is",Space,Str "supported",Space,Str "on",Space,Str "a",Space,Code ("",[],[]) "ol",Space,Str "element."] +,OrderedList (1,DefaultStyle,DefaultDelim) + [[Plain [Str "Lorem"]] + ,[Plain [Str "Ipsum"]] + ,[Plain [Str "Dolor"]] + ,[Plain [Str "Sit"]] + ,[Plain [Str "Amet"]]] +,Para [Str "If",Space,Str "the",Space,Str "preceding",Space,Str "list",Space,Str "has",Space,Str "no",Space,Str "markers,",Space,Str "the",Space,Str "test",Space,Str "passes."] +,RawBlock (Format "html") "</section>" +,RawBlock (Format "html") "</section>" +,RawBlock (Format "html") "<section id=\"style-list-style\">" +,Header 3 ("",[],[]) [Str "The",Space,Code ("",[],[]) "list-style",Space,Str "property"] +,RawBlock (Format "html") "<section id=\"style-030\" class=\"ctest\">" +,Header 4 ("",[],[]) [Span ("",["nature"],[]) [Str "[REQUIRED]"],Space,Span ("",["test-id"],[]) [Str "style-030"],Space,Str "images"] +,Para [Str "Tests",Space,Str "whether",Space,Str "the",Space,Code ("",[],[]) "list-style",Space,Str "shorthand",Space,Str "property",Space,Str "is",Space,Str "supported",Space,Str "using",Space,Str "a",Space,Str "gif",Space,Str "on",Space,Str "a",Space,Code ("",[],[]) "ul",Space,Str "element."] +,BulletList + [[Plain [Str "Lorem"]] + ,[Plain [Str "Ipsum"]] + ,[Plain [Str "Dolor"]] + ,[Plain [Str "Sit"]] + ,[Plain [Str "Amet"]]] +,Para [Str "If",Space,Str "the",Space,Str "preceding",Space,Str "list",Space,Str "has",Space,Str "the",Space,Str "purple",Space,Str "and",Space,Str "aqua",Space,Str "square",Space,Str "bullet",Space,Str "the",Space,Str "test",Space,Str "passes."] +,RawBlock (Format "html") "</section>" +,RawBlock (Format "html") "</section>" +,RawBlock (Format "html") "<section id=\"style-list-style-position\">" +,Header 3 ("",[],[]) [Str "The",Space,Code ("",[],[]) "list-style-position",Space,Str "property"] +,RawBlock (Format "html") "<section id=\"style-040\" class=\"ctest\">" +,Header 4 ("",[],[]) [Span ("",["nature"],[]) [Str "[REQUIRED]"],Space,Span ("",["test-id"],[]) [Str "style-040"],Space,Str "The",Space,Code ("",[],[]) "list-style-position",Space,Str "property:",Space,Code ("",[],[]) "inside"] +,Para [Str "Tests",Space,Str "whether",Space,Str "the",Space,Code ("",[],[]) "list-style-position",Space,Str "property",Space,Str "set",Space,Str "to",Space,Code ("",[],[]) "inside",Space,Str "is",Space,Str "supported",Space,Str "on",Space,Str "a",Space,Code ("",[],[]) "ul",Space,Str "element."] +,BulletList + [[Plain [Str "Lorem",Space,Str "ipsum",Space,Str "dolor",Space,Str "sit",Space,Str "amet,",Space,Str "consectetur",Space,Str "adipisicing",Space,Str "elit,",Space,Str "sed",Space,Str "do",Space,Str "eiusmod",Space,Str "tempor",Space,Str "incididunt",Space,Str "ut",Space,Str "labore",Space,Str "et",Space,Str "dolore",Space,Str "magna",Space,Str "aliqua.",Space,Str "Ut",Space,Str "enim",Space,Str "ad",Space,Str "minim",Space,Str "veniam,",Space,Str "quis",Space,Str "nostrud",Space,Str "exercitation",Space,Str "ullamco",Space,Str "laboris",Space,Str "nisi",Space,Str "ut",Space,Str "aliquip",Space,Str "ex",Space,Str "ea",Space,Str "commodo",Space,Str "consequat."]] + ,[Plain [Str "Lorem",Space,Str "ipsum",Space,Str "dolor",Space,Str "sit",Space,Str "amet,",Space,Str "consectetur",Space,Str "adipisicing",Space,Str "elit,",Space,Str "sed",Space,Str "do",Space,Str "eiusmod",Space,Str "tempor",Space,Str "incididunt",Space,Str "ut",Space,Str "labore",Space,Str "et",Space,Str "dolore",Space,Str "magna",Space,Str "aliqua.",Space,Str "Ut",Space,Str "enim",Space,Str "ad",Space,Str "minim",Space,Str "veniam,",Space,Str "quis",Space,Str "nostrud",Space,Str "exercitation",Space,Str "ullamco",Space,Str "laboris",Space,Str "nisi",Space,Str "ut",Space,Str "aliquip",Space,Str "ex",Space,Str "ea",Space,Str "commodo",Space,Str "consequat."]] + ,[Plain [Str "Lorem",Space,Str "ipsum",Space,Str "dolor",Space,Str "sit",Space,Str "amet,",Space,Str "consectetur",Space,Str "adipisicing",Space,Str "elit,",Space,Str "sed",Space,Str "do",Space,Str "eiusmod",Space,Str "tempor",Space,Str "incididunt",Space,Str "ut",Space,Str "labore",Space,Str "et",Space,Str "dolore",Space,Str "magna",Space,Str "aliqua.",Space,Str "Ut",Space,Str "enim",Space,Str "ad",Space,Str "minim",Space,Str "veniam,",Space,Str "quis",Space,Str "nostrud",Space,Str "exercitation",Space,Str "ullamco",Space,Str "laboris",Space,Str "nisi",Space,Str "ut",Space,Str "aliquip",Space,Str "ex",Space,Str "ea",Space,Str "commodo",Space,Str "consequat."]]] +,Para [Str "If",Space,Str "the",Space,Str "preceding",Space,Str "list",Space,Str "has",Space,Str "markers",Space,Str "inside",Space,Str "the",Space,Str "indentation,",Space,Str "the",Space,Str "test",Space,Str "passes."] +,RawBlock (Format "html") "</section>" +,RawBlock (Format "html") "<section id=\"style-041\" class=\"ctest\">" +,Header 4 ("",[],[]) [Span ("",["nature"],[]) [Str "[REQUIRED]"],Space,Span ("",["test-id"],[]) [Str "style-041"],Space,Str "The",Space,Code ("",[],[]) "list-style-position",Space,Str "property:",Space,Code ("",[],[]) "outside"] +,Para [Str "Tests",Space,Str "whether",Space,Str "the",Space,Code ("",[],[]) "list-style-position",Space,Str "property",Space,Str "set",Space,Str "to",Space,Code ("",[],[]) "outside",Space,Str "is",Space,Str "supported",Space,Str "on",Space,Str "a",Space,Code ("",[],[]) "ul",Space,Str "element."] +,BulletList + [[Plain [Str "Lorem",Space,Str "ipsum",Space,Str "dolor",Space,Str "sit",Space,Str "amet,",Space,Str "consectetur",Space,Str "adipisicing",Space,Str "elit,",Space,Str "sed",Space,Str "do",Space,Str "eiusmod",Space,Str "tempor",Space,Str "incididunt",Space,Str "ut",Space,Str "labore",Space,Str "et",Space,Str "dolore",Space,Str "magna",Space,Str "aliqua.",Space,Str "Ut",Space,Str "enim",Space,Str "ad",Space,Str "minim",Space,Str "veniam,",Space,Str "quis",Space,Str "nostrud",Space,Str "exercitation",Space,Str "ullamco",Space,Str "laboris",Space,Str "nisi",Space,Str "ut",Space,Str "aliquip",Space,Str "ex",Space,Str "ea",Space,Str "commodo",Space,Str "consequat."]] + ,[Plain [Str "Lorem",Space,Str "ipsum",Space,Str "dolor",Space,Str "sit",Space,Str "amet,",Space,Str "consectetur",Space,Str "adipisicing",Space,Str "elit,",Space,Str "sed",Space,Str "do",Space,Str "eiusmod",Space,Str "tempor",Space,Str "incididunt",Space,Str "ut",Space,Str "labore",Space,Str "et",Space,Str "dolore",Space,Str "magna",Space,Str "aliqua.",Space,Str "Ut",Space,Str "enim",Space,Str "ad",Space,Str "minim",Space,Str "veniam,",Space,Str "quis",Space,Str "nostrud",Space,Str "exercitation",Space,Str "ullamco",Space,Str "laboris",Space,Str "nisi",Space,Str "ut",Space,Str "aliquip",Space,Str "ex",Space,Str "ea",Space,Str "commodo",Space,Str "consequat."]] + ,[Plain [Str "Lorem",Space,Str "ipsum",Space,Str "dolor",Space,Str "sit",Space,Str "amet,",Space,Str "consectetur",Space,Str "adipisicing",Space,Str "elit,",Space,Str "sed",Space,Str "do",Space,Str "eiusmod",Space,Str "tempor",Space,Str "incididunt",Space,Str "ut",Space,Str "labore",Space,Str "et",Space,Str "dolore",Space,Str "magna",Space,Str "aliqua.",Space,Str "Ut",Space,Str "enim",Space,Str "ad",Space,Str "minim",Space,Str "veniam,",Space,Str "quis",Space,Str "nostrud",Space,Str "exercitation",Space,Str "ullamco",Space,Str "laboris",Space,Str "nisi",Space,Str "ut",Space,Str "aliquip",Space,Str "ex",Space,Str "ea",Space,Str "commodo",Space,Str "consequat."]]] +,Para [Str "If",Space,Str "the",Space,Str "preceding",Space,Str "list",Space,Str "has",Space,Str "the",Space,Str "default",Space,Str "setting",Space,Str "(marker",Space,Str "outside",Space,Str "the",Space,Str "indentation),",Space,Str "the",Space,Str "test",Space,Str "passes."] +,RawBlock (Format "html") "</section>" +,RawBlock (Format "html") "</section>" +,RawBlock (Format "html") "<section id=\"style-list-start\">" +,Header 3 ("",[],[]) [Str "The",Space,Str "HTML",Space,Code ("",[],[]) "start",Space,Str "attribute"] +,RawBlock (Format "html") "<section id=\"style-050\" class=\"ctest\">" +,Header 4 ("",[],[]) [Span ("",["nature"],[]) [Str "[REQUIRED]"],Space,Span ("",["test-id"],[]) [Str "style-050"],Space,Str "Without",Space,Code ("",[],[]) "list-style-type",Space,Str "set"] +,Para [Str "Tests",Space,Str "whether",Space,Str "the",Space,Code ("",[],[]) "start",Space,Str "attribute",Space,Str "is",Space,Str "supported",Space,Str "on",Space,Str "a",Space,Code ("",[],[]) "ol",Space,Str "element",Space,Str "with",Space,Str "no",Space,Code ("",[],[]) "list-style-type",Space,Str "property."] +,OrderedList (25,DefaultStyle,DefaultDelim) + [[Plain [Str "Lorem"]] + ,[Plain [Str "Ipsum"]] + ,[Plain [Str "Dolor"]] + ,[Plain [Str "Sit"]] + ,[Plain [Str "Amet"]]] +,Para [Str "If",Space,Str "the",Space,Str "preceding",Space,Str "list",Space,Str "starts",Space,Str "at",Space,Str "25,",Space,Str "the",Space,Str "test",Space,Str "passes."] +,RawBlock (Format "html") "</section>" +,RawBlock (Format "html") "<section id=\"style-051\" class=\"ctest\">" +,Header 4 ("",[],[]) [Span ("",["nature"],[]) [Str "[REQUIRED]"],Space,Span ("",["test-id"],[]) [Str "style-051"],Space,Str "With",Space,Code ("",[],[]) "list-style-type",Space,Str "set"] +,Para [Str "Tests",Space,Str "whether",Space,Str "the",Space,Code ("",[],[]) "start",Space,Str "attribute",Space,Str "is",Space,Str "supported",Space,Str "on",Space,Str "a",Space,Code ("",[],[]) "ol",Space,Str "element",Space,Str "with",Space,Str "a",Space,Code ("",[],[]) "list-style-type",Space,Str "property."] +,OrderedList (50,DefaultStyle,DefaultDelim) + [[Plain [Str "Lorem"]] + ,[Plain [Str "Ipsum"]] + ,[Plain [Str "Dolor"]] + ,[Plain [Str "Sit"]] + ,[Plain [Str "Amet"]]] +,Para [Str "If",Space,Str "the",Space,Str "preceding",Space,Str "list",Space,Str "starts",Space,Str "at",Space,Str "'L'",Space,Str "(50),",Space,Str "the",Space,Str "test",Space,Str "passes."] +,RawBlock (Format "html") "</section>" +,RawBlock (Format "html") "</section>" +,RawBlock (Format "html") "</section>" +,Para [Span ("styling-xhtml-004.xhtml",[],[]) []] +,RawBlock (Format "html") "<section id=\"style-media-rules\">" +,Header 2 ("",[],[]) [Code ("",[],[]) "@media",Space,Str "Rules"] +,RawBlock (Format "html") "<section id=\"style-210\" class=\"ctest\">" +,Header 3 ("",[],[]) [Span ("",["nature"],[]) [Str "[REQUIRED]"],Space,Span ("",["test-id"],[]) [Str "style-210"],Space,Code ("",[],[]) "all"] +,Para [Str "Tests",Space,Str "whether",Space,Str "the",Space,Code ("",[],[]) "@media",Space,Str "rule",Space,Str "set",Space,Str "to",Space,Code ("",[],[]) "all",Space,Str "is",Space,Str "supported."] +,Para [Str "FAIL"] +,Para [Str "If",Space,Str "the",Space,Str "preceding",Space,Str "paragraph",Space,Str "reads",Space,Str "\"FAIL\",",Space,Str "the",Space,Str "test",Space,Str "fails."] +,RawBlock (Format "html") "</section>" +,RawBlock (Format "html") "<section id=\"style-211\" class=\"ctest\">" +,Header 3 ("",[],[]) [Span ("",["nature"],[]) [Str "[REQUIRED]"],Space,Span ("",["test-id"],[]) [Str "style-211"],Space,Code ("",[],[]) "screen"] +,Para [Str "Tests",Space,Str "whether",Space,Str "the",Space,Code ("",[],[]) "@media",Space,Str "rule",Space,Str "set",Space,Str "to",Space,Code ("",[],[]) "screen",Space,Str "is",Space,Str "supported."] +,Para [Str "FAIL"] +,Para [Str "If",Space,Str "the",Space,Str "preceding",Space,Str "paragraph",Space,Str "reads",Space,Str "\"FAIL\",",Space,Str "the",Space,Str "test",Space,Str "fails."] +,RawBlock (Format "html") "</section>" +,RawBlock (Format "html") "<section id=\"style-212\" class=\"ctest\">" +,Header 3 ("",[],[]) [Span ("",["nature"],[]) [Str "[REQUIRED]"],Space,Span ("",["test-id"],[]) [Str "style-212"],Space,Code ("",[],[]) "handheld"] +,Para [Str "Tests",Space,Str "whether",Space,Str "the",Space,Code ("",[],[]) "@media",Space,Str "rule",Space,Str "set",Space,Str "to",Space,Code ("",[],[]) "handheld",Space,Str "is",Space,Str "supported."] +,Para [Str "FAIL"] +,Para [Str "If",Space,Str "the",Space,Str "preceding",Space,Str "paragraph",Space,Str "reads",Space,Str "\"FAIL\",",Space,Str "the",Space,Str "test",Space,Str "fails."] +,RawBlock (Format "html") "</section>" +,RawBlock (Format "html") "<section id=\"style-213\" class=\"ctest\">" +,Header 3 ("",[],[]) [Span ("",["nature"],[]) [Str "[REQUIRED]"],Space,Span ("",["test-id"],[]) [Str "style-213"],Space,Code ("",[],[]) "tv"] +,Para [Str "Tests",Space,Str "whether",Space,Str "the",Space,Code ("",[],[]) "@media",Space,Str "rule",Space,Str "set",Space,Str "to",Space,Code ("",[],[]) "tv",Space,Str "is",Space,Str "supported."] +,Para [Str "FAIL"] +,Para [Str "If",Space,Str "the",Space,Str "preceding",Space,Str "paragraph",Space,Str "reads",Space,Str "\"FAIL\",",Space,Str "the",Space,Str "test",Space,Str "fails."] +,RawBlock (Format "html") "</section>" +,RawBlock (Format "html") "<section id=\"style-220\" class=\"ctest\">" +,Header 3 ("",[],[]) [Span ("",["nature"],[]) [Str "[REQUIRED]"],Space,Span ("",["test-id"],[]) [Str "style-220"],Space,Code ("",[],[]) "orientation:landscape"] +,Para [Str "Tests",Space,Str "whether",Space,Str "the",Space,Code ("",[],[]) "@media",Space,Str "rule",Space,Str "set",Space,Str "to",Space,Code ("",[],[]) "orientation:landscape",Space,Str "is",Space,Str "supported."] +,Para [Str "FAIL"] +,Para [Str "If",Space,Str "the",Space,Str "preceding",Space,Str "paragraph",Space,Str "reads",Space,Str "\"FAIL\"",Space,Str "when",Space,Str "the",Space,Str "device",Space,Str "is",Space,Str "held",Space,Str "in",Space,Str "landscape",Space,Str "mode,",Space,Str "and",Space,Str "the",Space,Str "device",Space,Str "supports",Space,Str "multiple",Space,Str "orientations,",Space,Str "the",Space,Str "test",Space,Str "fails."] +,RawBlock (Format "html") "</section>" +,RawBlock (Format "html") "<section id=\"style-221\" class=\"ctest\">" +,Header 3 ("",[],[]) [Span ("",["nature"],[]) [Str "[REQUIRED]"],Space,Span ("",["test-id"],[]) [Str "style-221"],Space,Code ("",[],[]) "orientation:portrait"] +,Para [Str "Tests",Space,Str "whether",Space,Str "the",Space,Code ("",[],[]) "@media",Space,Str "rule",Space,Str "set",Space,Str "to",Space,Code ("",[],[]) "orientation:portrait",Space,Str "is",Space,Str "supported."] +,Para [Str "FAIL"] +,Para [Str "If",Space,Str "the",Space,Str "preceding",Space,Str "paragraph",Space,Str "reads",Space,Str "\"FAIL\"",Space,Str "when",Space,Str "the",Space,Str "device",Space,Str "is",Space,Str "held",Space,Str "in",Space,Str "portrait",Space,Str "mode,",Space,Str "and",Space,Str "the",Space,Str "device",Space,Str "supports",Space,Str "multiple",Space,Str "orientations,",Space,Str "the",Space,Str "test",Space,Str "fails."] +,RawBlock (Format "html") "</section>" +,RawBlock (Format "html") "<section id=\"style-230\" class=\"ctest\">" +,Header 3 ("",[],[]) [Span ("",["nature"],[]) [Str "[REQUIRED]"],Space,Span ("",["test-id"],[]) [Str "style-230"],Space,Code ("",[],[]) "min-width"] +,Para [Str "Tests",Space,Str "whether",Space,Str "the",Space,Code ("",[],[]) "@media",Space,Str "rule",Space,Str "set",Space,Str "to",Space,Code ("",[],[]) "min-width:200px",Space,Str "is",Space,Str "supported."] +,Para [Str "FAIL"] +,Para [Str "If",Space,Str "the",Space,Str "preceding",Space,Str "paragraph",Space,Str "reads",Space,Str "\"FAIL\",",Space,Str "the",Space,Str "test",Space,Str "fails."] +,RawBlock (Format "html") "</section>" +,RawBlock (Format "html") "<section id=\"style-231\" class=\"ctest\">" +,Header 3 ("",[],[]) [Span ("",["nature"],[]) [Str "[REQUIRED]"],Space,Span ("",["test-id"],[]) [Str "style-231"],Space,Code ("",[],[]) "max-width"] +,Para [Str "Tests",Space,Str "whether",Space,Str "the",Space,Code ("",[],[]) "@media",Space,Str "rule",Space,Str "set",Space,Str "to",Space,Code ("",[],[]) "max-width:2000px",Space,Str "is",Space,Str "supported."] +,Para [Str "FAIL"] +,Para [Str "If",Space,Str "the",Space,Str "preceding",Space,Str "paragraph",Space,Str "reads",Space,Str "\"FAIL\",",Space,Str "the",Space,Str "test",Space,Str "fails."] +,RawBlock (Format "html") "</section>" +,RawBlock (Format "html") "<section id=\"style-240\" class=\"ctest\">" +,Header 3 ("",[],[]) [Span ("",["nature"],[]) [Str "[REQUIRED]"],Space,Span ("",["test-id"],[]) [Str "style-240"],Space,Code ("",[],[]) "min-device-width"] +,Para [Str "Tests",Space,Str "whether",Space,Str "the",Space,Code ("",[],[]) "@media",Space,Str "rule",Space,Str "set",Space,Str "to",Space,Code ("",[],[]) "min-device-width:200px",Space,Str "is",Space,Str "supported."] +,Para [Str "FAIL"] +,Para [Str "If",Space,Str "the",Space,Str "preceding",Space,Str "paragraph",Space,Str "reads",Space,Str "\"FAIL\",",Space,Str "the",Space,Str "test",Space,Str "fails."] +,RawBlock (Format "html") "</section>" +,RawBlock (Format "html") "<section id=\"style-241\" class=\"ctest\">" +,Header 3 ("",[],[]) [Span ("",["nature"],[]) [Str "[REQUIRED]"],Space,Span ("",["test-id"],[]) [Str "style-241"],Space,Code ("",[],[]) "max-device-width"] +,Para [Str "Tests",Space,Str "whether",Space,Str "the",Space,Code ("",[],[]) "@media",Space,Str "rule",Space,Str "set",Space,Str "to",Space,Code ("",[],[]) "max-device-width:2000px",Space,Str "is",Space,Str "supported."] +,Para [Str "FAIL"] +,Para [Str "If",Space,Str "the",Space,Str "preceding",Space,Str "paragraph",Space,Str "reads",Space,Str "\"FAIL\",",Space,Str "the",Space,Str "test",Space,Str "fails."] +,RawBlock (Format "html") "</section>" +,RawBlock (Format "html") "</section>" +,Para [Span ("styling-xhtml-005.xhtml",[],[]) []] +,RawBlock (Format "html") "<section id=\"style-text-xform\">" +,Header 2 ("",[],[]) [Str "The",Space,Code ("",[],[]) "text-transform",Space,Str "property"] +,RawBlock (Format "html") "<section id=\"style-310\" class=\"ctest\">" +,Header 2 ("",[],[]) [Span ("",["nature"],[]) [Str "[REQUIRED]"],Space,Span ("",["test-id"],[]) [Str "style-310"],Space,Code ("",[],[]) "uppercase"] +,Para [Str "Tests",Space,Str "whether",Space,Str "the",Space,Code ("",[],[]) "text-transform",Space,Str "property",Space,Str "set",Space,Str "to",Space,Str "uppercase",Space,Str "is",Space,Str "supported."] +,Para [Str "Lorem",Space,Str "ipsum",Space,Str "dolor",Space,Str "sit",Space,Str "amet,",Space,Str "consectetur",Space,Str "adipisicing",Space,Str "elit,",Space,Str "sed",Space,Str "do",Space,Str "eiusmod",Space,Str "tempor",Space,Str "incididunt",Space,Str "ut",Space,Str "labore",Space,Str "et",Space,Str "dolore",Space,Str "magna",Space,Str "aliqua.",Space,Str "Ut",Space,Str "enim",Space,Str "ad",Space,Str "minim",Space,Str "veniam,",Space,Str "quis",Space,Str "nostrud",Space,Str "exercitation",Space,Str "ullamco",Space,Str "laboris",Space,Str "nisi",Space,Str "ut",Space,Str "aliquip",Space,Str "ex",Space,Str "ea",Space,Str "commodo",Space,Str "consequat.",Space,Str "Duis",Space,Str "aute",Space,Str "irure",Space,Str "dolor",Space,Str "in",Space,Str "reprehenderit",Space,Str "in",Space,Str "voluptate",Space,Str "velit",Space,Str "esse",Space,Str "cillum",Space,Str "dolore",Space,Str "eu",Space,Str "fugiat",Space,Str "nulla",Space,Str "pariatur.",Space,Str "Excepteur",Space,Str "sint",Space,Str "occaecat",Space,Str "cupidatat",Space,Str "non",Space,Str "proident,",Space,Str "sunt",Space,Str "in",Space,Str "culpa",Space,Str "qui",Space,Str "officia",Space,Str "deserunt",Space,Str "mollit",Space,Str "anim",Space,Str "id",Space,Str "est",Space,Str "laborum."] +,Para [Str "If",Space,Str "the",Space,Str "preceding",Space,Str "paragraph",Space,Str "is",Space,Str "in",Space,Str "upper",Space,Str "case,",Space,Str "the",Space,Str "test",Space,Str "passes."] +,RawBlock (Format "html") "</section>" +,RawBlock (Format "html") "<section id=\"style-311\" class=\"ctest\">" +,Header 2 ("",[],[]) [Span ("",["nature"],[]) [Str "[REQUIRED]"],Space,Span ("",["test-id"],[]) [Str "style-311"],Space,Code ("",[],[]) "capitalize"] +,Para [Str "Tests",Space,Str "whether",Space,Str "the",Space,Code ("",[],[]) "text-transform",Space,Str "property",Space,Str "set",Space,Str "to",Space,Str "capitalize",Space,Str "is",Space,Str "supported."] +,Para [Str "Lorem",Space,Str "ipsum",Space,Str "dolor",Space,Str "sit",Space,Str "amet,",Space,Str "consectetur",Space,Str "adipisicing",Space,Str "elit,",Space,Str "sed",Space,Str "do",Space,Str "eiusmod",Space,Str "tempor",Space,Str "incididunt",Space,Str "ut",Space,Str "labore",Space,Str "et",Space,Str "dolore",Space,Str "magna",Space,Str "aliqua.",Space,Str "Ut",Space,Str "enim",Space,Str "ad",Space,Str "minim",Space,Str "veniam,",Space,Str "quis",Space,Str "nostrud",Space,Str "exercitation",Space,Str "ullamco",Space,Str "laboris",Space,Str "nisi",Space,Str "ut",Space,Str "aliquip",Space,Str "ex",Space,Str "ea",Space,Str "commodo",Space,Str "consequat.",Space,Str "Duis",Space,Str "aute",Space,Str "irure",Space,Str "dolor",Space,Str "in",Space,Str "reprehenderit",Space,Str "in",Space,Str "voluptate",Space,Str "velit",Space,Str "esse",Space,Str "cillum",Space,Str "dolore",Space,Str "eu",Space,Str "fugiat",Space,Str "nulla",Space,Str "pariatur.",Space,Str "Excepteur",Space,Str "sint",Space,Str "occaecat",Space,Str "cupidatat",Space,Str "non",Space,Str "proident,",Space,Str "sunt",Space,Str "in",Space,Str "culpa",Space,Str "qui",Space,Str "officia",Space,Str "deserunt",Space,Str "mollit",Space,Str "anim",Space,Str "id",Space,Str "est",Space,Str "laborum."] +,Para [Str "If",Space,Str "each",Space,Str "first",Space,Str "letter",Space,Str "of",Space,Str "each",Space,Str "word",Space,Str "in",Space,Str "the",Space,Str "preceding",Space,Str "paragraph",Space,Str "is",Space,Str "in",Space,Str "upper",Space,Str "case,",Space,Str "the",Space,Str "test",Space,Str "passes."] +,RawBlock (Format "html") "</section>" +,RawBlock (Format "html") "<section id=\"style-312\" class=\"ctest\">" +,Header 2 ("",[],[]) [Span ("",["nature"],[]) [Str "[REQUIRED]"],Space,Span ("",["test-id"],[]) [Str "style-312"],Space,Code ("",[],[]) "lowercase"] +,Para [Str "Tests",Space,Str "whether",Space,Str "the",Space,Code ("",[],[]) "text-transform",Space,Str "property",Space,Str "set",Space,Str "to",Space,Str "lowercase",Space,Str "is",Space,Str "supported."] +,Para [Str "Lorem",Space,Str "ipsum",Space,Str "dolor",Space,Str "sit",Space,Str "amet,",Space,Str "consectetur",Space,Str "adipisicing",Space,Str "elit,",Space,Str "sed",Space,Str "do",Space,Str "eiusmod",Space,Str "tempor",Space,Str "incididunt",Space,Str "ut",Space,Str "labore",Space,Str "et",Space,Str "dolore",Space,Str "magna",Space,Str "aliqua.",Space,Str "Ut",Space,Str "enim",Space,Str "ad",Space,Str "minim",Space,Str "veniam,",Space,Str "quis",Space,Str "nostrud",Space,Str "exercitation",Space,Str "ullamco",Space,Str "laboris",Space,Str "nisi",Space,Str "ut",Space,Str "aliquip",Space,Str "ex",Space,Str "ea",Space,Str "commodo",Space,Str "consequat.",Space,Str "Duis",Space,Str "aute",Space,Str "irure",Space,Str "dolor",Space,Str "in",Space,Str "reprehenderit",Space,Str "in",Space,Str "voluptate",Space,Str "velit",Space,Str "esse",Space,Str "cillum",Space,Str "dolore",Space,Str "eu",Space,Str "fugiat",Space,Str "nulla",Space,Str "pariatur.",Space,Str "Excepteur",Space,Str "sint",Space,Str "occaecat",Space,Str "cupidatat",Space,Str "non",Space,Str "proident,",Space,Str "sunt",Space,Str "in",Space,Str "culpa",Space,Str "qui",Space,Str "officia",Space,Str "deserunt",Space,Str "mollit",Space,Str "anim",Space,Str "id",Space,Str "est",Space,Str "laborum."] +,Para [Str "If",Space,Str "the",Space,Str "preceding",Space,Str "paragraph",Space,Str "is",Space,Str "in",Space,Str "lower",Space,Str "case,",Space,Str "the",Space,Str "test",Space,Str "passes."] +,RawBlock (Format "html") "</section>" +,RawBlock (Format "html") "</section>" +,Para [Span ("styling-xhtml-006.xhtml",[],[]) []] +,RawBlock (Format "html") "<section id=\"style-ruby\">" +,Header 2 ("",[],[]) [Str "The",Space,Code ("",[],[]) "epub-ruby-position",Space,Str "property"] +,RawBlock (Format "html") "<section id=\"style-410\" class=\"ctest\">" +,Header 2 ("",[],[]) [Span ("",["nature"],[]) [Str "[REQUIRED]"],Space,Span ("",["test-id"],[]) [Str "style-410"],Space,Code ("",[],[]) "over"] +,Para [Str "Tests",Space,Str "whether",Space,Str "the",Space,Code ("",[],[]) "-epub-ruby-position",Space,Str "property",Space,Str "set",Space,Str "to",Space,Str "over",Space,Str "is",Space,Str "supported."] +,Para [RawInline (Format "html") "<ruby class=\"ruby-over\">",Strong [Str "Lorem",Space,Str "Ipsum"],Space,RawInline (Format "html") "<rp>",Str "(",RawInline (Format "html") "</rp>",RawInline (Format "html") "<rt>",Str "Lorem",Space,Str "Ipsum",RawInline (Format "html") "</rt>",RawInline (Format "html") "<rp>",Str ")",RawInline (Format "html") "</rp>",RawInline (Format "html") "</ruby>"] +,Para [Str "If",Space,Str "the",Space,Str "Ruby",Space,Str "text",Space,Str "is",Space,Str "positioned",Space,Str "on",Space,Str "the",Space,Link [Str "over"] ("#over",""),Space,Str "side",Space,Str "of",Space,Str "the",Space,Str "ruby",Space,Str "base,",Space,Str "the",Space,Str "test",Space,Str "passes."] +,RawBlock (Format "html") "</section>" +,RawBlock (Format "html") "<section id=\"style-411\" class=\"ctest\">" +,Header 2 ("",[],[]) [Span ("",["nature"],[]) [Str "[REQUIRED]"],Space,Span ("",["test-id"],[]) [Str "style-411"],Space,Code ("",[],[]) "under"] +,Para [Str "Tests",Space,Str "whether",Space,Str "the",Space,Code ("",[],[]) "-epub-ruby-position",Space,Str "property",Space,Str "set",Space,Str "to",Space,Str "under",Space,Str "is",Space,Str "supported."] +,Para [RawInline (Format "html") "<ruby class=\"ruby-under\">",Strong [Str "Lorem",Space,Str "Ipsum"],Space,RawInline (Format "html") "<rp>",Str "(",RawInline (Format "html") "</rp>",RawInline (Format "html") "<rt>",Str "Lorem",Space,Str "Ipsum",RawInline (Format "html") "</rt>",RawInline (Format "html") "<rp>",Str ")",RawInline (Format "html") "</rp>",RawInline (Format "html") "</ruby>"] +,Para [Str "If",Space,Str "the",Space,Str "Ruby",Space,Str "text",Space,Str "is",Space,Str "positioned",Space,Str "on",Space,Str "the",Space,Link [Str "under"] ("#under",""),Space,Str "side",Space,Str "of",Space,Str "the",Space,Str "ruby",Space,Str "base,",Space,Str "the",Space,Str "test",Space,Str "passes."] +,RawBlock (Format "html") "</section>" +,RawBlock (Format "html") "<section id=\"style-412\" class=\"ctest\">" +,Header 2 ("",[],[]) [Span ("",["nature"],[]) [Str "[REQUIRED]"],Space,Span ("",["test-id"],[]) [Str "style-412"],Space,Code ("",[],[]) "inter-character"] +,Para [Str "Tests",Space,Str "whether",Space,Str "the",Space,Code ("",[],[]) "-epub-ruby-position",Space,Str "property",Space,Str "set",Space,Str "to",Space,Str "inter-caracter",Space,Str "is",Space,Str "supported."] +,Para [RawInline (Format "html") "<ruby class=\"ruby-inter-character\">",Strong [Str "Lorem",Space,Str "Ipsum"],Space,RawInline (Format "html") "<rp>",Str "(",RawInline (Format "html") "</rp>",RawInline (Format "html") "<rt>",Str "Lorem",Space,Str "Ipsum",RawInline (Format "html") "</rt>",RawInline (Format "html") "<rp>",Str ")",RawInline (Format "html") "</rp>",RawInline (Format "html") "</ruby>"] +,Para [Str "If",Space,Str "the",Space,Str "Ruby",Space,Str "text",Space,Str "is",Space,Str "positioned",Space,Str "on",Space,Str "the",Space,Str "right",Space,Str "side",Space,Str "of",Space,Str "the",Space,Str "base",Space,Str "text,",Space,Str "the",Space,Str "test",Space,Str "passes."] +,RawBlock (Format "html") "</section>" +,RawBlock (Format "html") "</section>"] diff --git a/tests/epub/img.epub b/tests/epub/img.epub Binary files differnew file mode 100644 index 000000000..ebe80d935 --- /dev/null +++ b/tests/epub/img.epub diff --git a/tests/epub/wasteland.epub b/tests/epub/wasteland.epub Binary files differnew file mode 100644 index 000000000..e4e52db7f --- /dev/null +++ b/tests/epub/wasteland.epub diff --git a/tests/epub/wasteland.native b/tests/epub/wasteland.native new file mode 100644 index 000000000..96418226e --- /dev/null +++ b/tests/epub/wasteland.native @@ -0,0 +1,9 @@ +[Para [Image [] ("wasteland-cover.jpg","")] +,Para [Span ("wasteland-content.xhtml",[],[]) []] +,RawBlock (Format "html") "<section type=\"frontmatter\" id=\"frontmatter\">" +,RawBlock (Format "html") "</section>" +,RawBlock (Format "html") "<section type=\"bodymatter\" id=\"bodymatter\">" +,RawBlock (Format "html") "<section id=\"ch1\">" +,Header 2 ("",[],[]) [Str "I.",Space,Str "THE",Space,Str "BURIAL",Space,Str "OF",Space,Str "THE",Space,Str "DEAD"] +,Div ("",["linegroup"],[]) [Div ("",[],[]) [Plain [Str "April",Space,Str "is",Space,Str "the",Space,Str "cruellest",Space,Str "month,",Space,Str "breeding"]],Div ("",[],[]) [Plain [Str "Lilacs",Space,Str "out",Space,Str "of",Space,Str "the",Space,Str "dead",Space,Str "land,",Space,Str "mixing"]],Div ("",[],[]) [Plain [Str "Memory",Space,Str "and",Space,Str "desire,",Space,Str "stirring"]],Div ("",[],[]) [Plain [Str "Dull",Space,Str "roots",Space,Str "with",Space,Str "spring",Space,Str "rain."]],Div ("",[],[]) [Plain [Str "Winter",Space,Str "kept",Space,Str "us",Space,Str "warm,",Space,Str "covering"]],Div ("",[],[]) [Plain [Str "Earth",Space,Str "in",Space,Str "forgetful",Space,Str "snow,",Space,Str "feeding"]],Div ("",[],[]) [Plain [Str "A",Space,Str "little",Space,Str "life",Space,Str "with",Space,Str "dried",Space,Str "tubers."]],Div ("",[],[]) [Plain [Str "Summer",Space,Str "surprised",Space,Str "us,",Space,Str "coming",Space,Str "over",Space,Str "the",Space,Str "Starnbergersee"]],Div ("",[],[]) [Plain [Str "With",Space,Str "a",Space,Str "shower",Space,Str "of",Space,Str "rain;",Space,Str "we",Space,Str "stopped",Space,Str "in",Space,Str "the",Space,Str "colonnade,"]],Div ("",[],[]) [Plain [Str "And",Space,Str "went",Space,Str "on",Space,Str "in",Space,Str "sunlight,",Space,Str "into",Space,Str "the",Space,Str "Hofgarten,",Span ("",["lnum"],[]) [Str "10"]]],Div ("",[],[]) [Plain [Str "And",Space,Str "drank",Space,Str "coffee,",Space,Str "and",Space,Str "talked",Space,Str "for",Space,Str "an",Space,Str "hour."]],Div ("",[],[("lang","de")]) [Plain [Str "Bin",Space,Str "gar",Space,Str "keine",Space,Str "Russin,",Space,Str "stamm'",Space,Str "aus",Space,Str "Litauen,",Space,Str "echt",Space,Str "deutsch."]],Div ("",[],[]) [Plain [Str "And",Space,Str "when",Space,Str "we",Space,Str "were",Space,Str "children,",Space,Str "staying",Space,Str "at",Space,Str "the",Space,Str "archduke's,"]],Div ("",[],[]) [Plain [Str "My",Space,Str "cousin's,",Space,Str "he",Space,Str "took",Space,Str "me",Space,Str "out",Space,Str "on",Space,Str "a",Space,Str "sled,"]],Div ("",[],[]) [Plain [Str "And",Space,Str "I",Space,Str "was",Space,Str "frightened.",Space,Str "He",Space,Str "said,",Space,Str "Marie,"]],Div ("",[],[]) [Plain [Str "Marie,",Space,Str "hold",Space,Str "on",Space,Str "tight.",Space,Str "And",Space,Str "down",Space,Str "we",Space,Str "went."]],Div ("",[],[]) [Plain [Str "In",Space,Str "the",Space,Str "mountains,",Space,Str "there",Space,Str "you",Space,Str "feel",Space,Str "free."]],Div ("",[],[]) [Plain [Str "I",Space,Str "read,",Space,Str "much",Space,Str "of",Space,Str "the",Space,Str "night,",Space,Str "and",Space,Str "go",Space,Str "south",Space,Str "in",Space,Str "the",Space,Str "winter."]]] +,Div ("",["linegroup"],[]) [Div ("",[],[]) [Plain [Str "What",Space,Str "are",Space,Str "the",Space,Str "roots",Space,Str "that",Space,Str "clutch,",Space,Str "what",Space,Str "branches",Space,Str "grow"]],Div ("wasteland-content.xhtml#ln20",[],[]) [Plain [Str "Out",Space,Str "of",Space,Str "this",Space,Str "stony",Space,Str "rubbish?",Space,Str "Son",Space,Str "of",Space,Str "man,",Note [Para [Link [Str "Line",Space,Str "20."] ("#wasteland-content.xhtml#ln20",""),Space,Str "Cf.",Space,Str "Ezekiel",Space,Str "2:1."]]],Div ("",[],[]) [Plain [Str "You",Space,Str "cannot",Space,Str "say,",Space,Str "or",Space,Str "guess,",Space,Str "for",Space,Str "you",Space,Str "know",Space,Str "only"]],Div ("",[],[]) [Plain [Str "A",Space,Str "heap",Space,Str "of",Space,Str "broken",Space,Str "images,",Space,Str "where",Space,Str "the",Space,Str "sun",Space,Str "beats,"]],Div ("wasteland-content.xhtml#ln23",[],[]) [Plain [Str "And",Space,Str "the",Space,Str "dead",Space,Str "tree",Space,Str "gives",Space,Str "no",Space,Str "shelter,",Space,Str "the",Space,Str "cricket",Space,Str "no",Space,Str "relief,",Note [Para [Link [Str "23."] ("#wasteland-content.xhtml#ln23",""),Space,Str "Cf.",Space,Str "Ecclesiastes",Space,Str "12:5."]]],Div ("",[],[]) [Plain [Str "And",Space,Str "the",Space,Str "dry",Space,Str "stone",Space,Str "no",Space,Str "sound",Space,Str "of",Space,Str "water.",Space,Str "Only"]],Div ("",[],[]) [Plain [Str "There",Space,Str "is",Space,Str "shadow",Space,Str "under",Space,Str "this",Space,Str "red",Space,Str "rock,"]],Div ("",[],[]) [Plain [Str "(Come",Space,Str "in",Space,Str "under",Space,Str "the",Space,Str "shadow",Space,Str "of",Space,Str "this",Space,Str "red",Space,Str "rock),"]],Div ("",[],[]) [Plain [Str "And",Space,Str "I",Space,Str "will",Space,Str "show",Space,Str "you",Space,Str "something",Space,Str "different",Space,Str "from",Space,Str "either"]],Div ("",[],[]) [Plain [Str "Your",Space,Str "shadow",Space,Str "at",Space,Str "morning",Space,Str "striding",Space,Str "behind",Space,Str "you"]],Div ("",[],[]) [Plain [Str "Or",Space,Str "your",Space,Str "shadow",Space,Str "at",Space,Str "evening",Space,Str "rising",Space,Str "to",Space,Str "meet",Space,Str "you;"]],Div ("",[],[]) [Plain [Str "I",Space,Str "will",Space,Str "show",Space,Str "you",Space,Str "fear",Space,Str "in",Space,Str "a",Space,Str "handful",Space,Str "of",Space,Str "dust.",Span ("",["lnum"],[]) [Str "30"]]],BlockQuote [Div ("",[],[]) [Div ("wasteland-content.xhtml#ln31",[],[]) [Plain [Str "Frisch",Space,Str "weht",Space,Str "der",Space,Str "Wind",Note [Para [Link [Str "31."] ("#wasteland-content.xhtml#ln31",""),Space,Str "V.",Space,Str "Tristan",Space,Str "und",Space,Str "Isolde,",Space,Str "i,",Space,Str "verses",Space,Str "5-8."]]],Div ("",[],[]) [Plain [Str "Der",Space,Str "Heimat",Space,Str "zu"]],Div ("",[],[]) [Plain [Str "Mein",Space,Str "Irisch",Space,Str "Kind,"]],Div ("",[],[]) [Plain [Str "Wo",Space,Str "weilest",Space,Str "du?"]]],RawBlock (Format "html") "</blockquote>",Div ("",[],[]) [Plain [Str "\"You",Space,Str "gave",Space,Str "me",Space,Str "hyacinths",Space,Str "first",Space,Str "a",Space,Str "year",Space,Str "ago;"]],Div ("",[],[]) [Plain [Str "\"They",Space,Str "called",Space,Str "me",Space,Str "the",Space,Str "hyacinth",Space,Str "girl.\""]],Div ("",[],[]) [Plain [Str "\8213Yet",Space,Str "when",Space,Str "we",Space,Str "came",Space,Str "back,",Space,Str "late,",Space,Str "from",Space,Str "the",Space,Str "Hyacinth",Space,Str "garden,"]],Div ("",[],[]) [Plain [Str "Your",Space,Str "arms",Space,Str "full,",Space,Str "and",Space,Str "your",Space,Str "hair",Space,Str "wet,",Space,Str "I",Space,Str "could",Space,Str "not"]],Div ("",[],[]) [Plain [Str "Speak,",Space,Str "and",Space,Str "my",Space,Str "eyes",Space,Str "failed,",Space,Str "I",Space,Str "was",Space,Str "neither"]],Div ("",[],[]) [Plain [Str "Living",Space,Str "nor",Space,Str "dead,",Space,Str "and",Space,Str "I",Space,Str "knew",Space,Str "nothing,",Span ("",["lnum"],[]) [Str "40"]]],Div ("",[],[]) [Plain [Str "Looking",Space,Str "into",Space,Str "the",Space,Str "heart",Space,Str "of",Space,Str "light,",Space,Str "the",Space,Str "silence."]],Div ("wasteland-content.xhtml#ln42",[],[("lang","de")]) [Plain [Emph [Str "Od'",Space,Str "und",Space,Str "leer",Space,Str "das",Space,Str "Meer"],Str ".",Note [Para [Link [Str "42."] ("#wasteland-content.xhtml#ln42",""),Space,Str "Id.",Space,Str "iii,",Space,Str "verse",Space,Str "24."]]],Div ("",["linegroup"],[]) [Div ("",[],[]) [Plain [Str "Madame",Space,Str "Sosostris,",Space,Str "famous",Space,Str "clairvoyante,"]],Div ("",[],[]) [Plain [Str "Had",Space,Str "a",Space,Str "bad",Space,Str "cold,",Space,Str "nevertheless"]],Div ("",[],[]) [Plain [Str "Is",Space,Str "known",Space,Str "to",Space,Str "be",Space,Str "the",Space,Str "wisest",Space,Str "woman",Space,Str "in",Space,Str "Europe,"]],Div ("wasteland-content.xhtml#ln46",[],[]) [Plain [Str "With",Space,Str "a",Space,Str "wicked",Space,Str "pack",Space,Str "of",Space,Str "cards.",Space,Str "Here,",Space,Str "said",Space,Str "she,",Note [Para [Link [Str "46."] ("#wasteland-content.xhtml#ln46",""),Space,Str "I",Space,Str "am",Space,Str "not",Space,Str "familiar",Space,Str "with",Space,Str "the",Space,Str "exact",Space,Str "constitution",Space,Str "of",Space,Str "the",Space,Str "Tarot",Space,Str "pack",Space,Str "of",Space,Str "cards,",Space,Str "from",Space,Str "which",Space,Str "I",Space,Str "have",Space,Str "obviously",Space,Str "departed",Space,Str "to",Space,Str "suit",Space,Str "my",Space,Str "own",Space,Str "convenience.",Space,Str "The",Space,Str "Hanged",Space,Str "Man,",Space,Str "a",Space,Str "member",Space,Str "of",Space,Str "the",Space,Str "traditional",Space,Str "pack,",Space,Str "fits",Space,Str "my",Space,Str "purpose",Space,Str "in",Space,Str "two",Space,Str "ways:",Space,Str "because",Space,Str "he",Space,Str "is",Space,Str "associated",Space,Str "in",Space,Str "my",Space,Str "mind",Space,Str "with",Space,Str "the",Space,Str "Hanged",Space,Str "God",Space,Str "of",Space,Str "Frazer,",Space,Str "and",Space,Str "because",Space,Str "I",Space,Str "associate",Space,Str "him",Space,Str "with",Space,Str "the",Space,Str "hooded",Space,Str "figure",Space,Str "in",Space,Str "the",Space,Str "passage",Space,Str "of",Space,Str "the",Space,Str "disciples",Space,Str "to",Space,Str "Emmaus",Space,Str "in",Space,Str "Part",Space,Str "V.",Space,Str "The",Space,Str "Phoenician",Space,Str "Sailor",Space,Str "and",Space,Str "the",Space,Str "Merchant",Space,Str "appear",Space,Str "later;",Space,Str "also",Space,Str "the",Space,Str "\"crowds",Space,Str "of",Space,Str "people,\"",Space,Str "and",Space,Str "Death",Space,Str "by",Space,Str "Water",Space,Str "is",Space,Str "executed",Space,Str "in",Space,Str "Part",Space,Str "IV.",Space,Str "The",Space,Str "Man",Space,Str "with",Space,Str "Three",Space,Str "Staves",Space,Str "(an",Space,Str "authentic",Space,Str "member",Space,Str "of",Space,Str "the",Space,Str "Tarot",Space,Str "pack)",Space,Str "I",Space,Str "associate,",Space,Str "quite",Space,Str "arbitrarily,",Space,Str "with",Space,Str "the",Space,Str "Fisher",Space,Str "King",Space,Str "himself."]]],Div ("",[],[]) [Plain [Str "Is",Space,Str "your",Space,Str "card,",Space,Str "the",Space,Str "drowned",Space,Str "Phoenician",Space,Str "Sailor,"]],Div ("",[],[]) [Plain [Str "(Those",Space,Str "are",Space,Str "pearls",Space,Str "that",Space,Str "were",Space,Str "his",Space,Str "eyes.",Space,Str "Look!)"]],Div ("",[],[]) [Plain [Str "Here",Space,Str "is",Space,Str "Belladonna,",Space,Str "the",Space,Str "Lady",Space,Str "of",Space,Str "the",Space,Str "Rocks,"]],Div ("",[],[]) [Plain [Str "The",Space,Str "lady",Space,Str "of",Space,Str "situations.",Span ("",["lnum"],[]) [Str "50"]]],Div ("",[],[]) [Plain [Str "Here",Space,Str "is",Space,Str "the",Space,Str "man",Space,Str "with",Space,Str "three",Space,Str "staves,",Space,Str "and",Space,Str "here",Space,Str "the",Space,Str "Wheel,"]],Div ("",[],[]) [Plain [Str "And",Space,Str "here",Space,Str "is",Space,Str "the",Space,Str "one-eyed",Space,Str "merchant,",Space,Str "and",Space,Str "this",Space,Str "card,"]],Div ("",[],[]) [Plain [Str "Which",Space,Str "is",Space,Str "blank,",Space,Str "is",Space,Str "something",Space,Str "he",Space,Str "carries",Space,Str "on",Space,Str "his",Space,Str "back,"]],Div ("",[],[]) [Plain [Str "Which",Space,Str "I",Space,Str "am",Space,Str "forbidden",Space,Str "to",Space,Str "see.",Space,Str "I",Space,Str "do",Space,Str "not",Space,Str "find"]],Div ("",[],[]) [Plain [Str "The",Space,Str "Hanged",Space,Str "Man.",Space,Str "Fear",Space,Str "death",Space,Str "by",Space,Str "water."]],Div ("",[],[]) [Plain [Str "I",Space,Str "see",Space,Str "crowds",Space,Str "of",Space,Str "people,",Space,Str "walking",Space,Str "round",Space,Str "in",Space,Str "a",Space,Str "ring."]],Div ("",[],[]) [Plain [Str "Thank",Space,Str "you.",Space,Str "If",Space,Str "you",Space,Str "see",Space,Str "dear",Space,Str "Mrs.",Space,Str "Equitone,"]],Div ("",[],[]) [Plain [Str "Tell",Space,Str "her",Space,Str "I",Space,Str "bring",Space,Str "the",Space,Str "horoscope",Space,Str "myself:"]],Div ("",[],[]) [Plain [Str "One",Space,Str "must",Space,Str "be",Space,Str "so",Space,Str "careful",Space,Str "these",Space,Str "days."]]],Div ("",["linegroup"],[]) [Div ("wasteland-content.xhtml#ln60",[],[]) [Plain [Str "Unreal",Space,Str "City,",Note [Para [Link [Str "60."] ("#wasteland-content.xhtml#ln60",""),Space,Str "Cf.",Space,Str "Baudelaire:"],BlockQuote [Para [Str "\"Fourmillante",Space,Str "cite;,",Space,Str "cite;",Space,Str "pleine",Space,Str "de",Space,Str "reves,",LineBreak,Str "Ou",Space,Str "le",Space,Str "spectre",Space,Str "en",Space,Str "plein",Space,Str "jour",Space,Str "raccroche",Space,Str "le",Space,Str "passant.\""]]]],Div ("",[],[]) [Plain [Str "Under",Space,Str "the",Space,Str "brown",Space,Str "fog",Space,Str "of",Space,Str "a",Space,Str "winter",Space,Str "dawn,"]],Div ("",[],[]) [Plain [Str "A",Space,Str "crowd",Space,Str "flowed",Space,Str "over",Space,Str "London",Space,Str "Bridge,",Space,Str "so",Space,Str "many,"]],Div ("wasteland-content.xhtml#ln63",[],[]) [Plain [Str "I",Space,Str "had",Space,Str "not",Space,Str "thought",Space,Str "death",Space,Str "had",Space,Str "undone",Space,Str "so",Space,Str "many.",Note [Para [Link [Str "63."] ("#wasteland-content.xhtml#ln63",""),Space,Str "Cf.",Space,Str "Inferno,",Space,Str "iii.",Space,Str "55-7."],BlockQuote [Para [Str "\"si",Space,Str "lunga",Space,Str "tratta",LineBreak,Str "di",Space,Str "gente,",Space,Str "ch'io",Space,Str "non",Space,Str "avrei",Space,Str "mai",Space,Str "creduto",LineBreak,Str "che",Space,Str "morte",Space,Str "tanta",Space,Str "n'avesse",Space,Str "disfatta.\""]]]],Div ("wasteland-content.xhtml#ln64",[],[]) [Plain [Str "Sighs,",Space,Str "short",Space,Str "and",Space,Str "infrequent,",Space,Str "were",Space,Str "exhaled,",Note [Para [Link [Str "64."] ("#wasteland-content.xhtml#ln64",""),Space,Str "Cf.",Space,Str "Inferno,",Space,Str "iv.",Space,Str "25-7:"],BlockQuote [Para [Str "\"Quivi,",Space,Str "secondo",Space,Str "che",Space,Str "per",Space,Str "ascoltahre,",LineBreak,Str "\"non",Space,Str "avea",Space,Str "pianto,",Space,Str "ma'",Space,Str "che",Space,Str "di",Space,Str "sospiri,",LineBreak,Str "\"che",Space,Str "l'aura",Space,Str "eterna",Space,Str "facevan",Space,Str "tremare.\""]]]],Div ("",[],[]) [Plain [Str "And",Space,Str "each",Space,Str "man",Space,Str "fixed",Space,Str "his",Space,Str "eyes",Space,Str "before",Space,Str "his",Space,Str "feet."]],Div ("",[],[]) [Plain [Str "Flowed",Space,Str "up",Space,Str "the",Space,Str "hill",Space,Str "and",Space,Str "down",Space,Str "King",Space,Str "William",Space,Str "Street,"]],Div ("",[],[]) [Plain [Str "To",Space,Str "where",Space,Str "Saint",Space,Str "Mary",Space,Str "Woolnoth",Space,Str "kept",Space,Str "the",Space,Str "hours"]],Div ("wasteland-content.xhtml#ln68",[],[]) [Plain [Str "With",Space,Str "a",Space,Str "dead",Space,Str "sound",Space,Str "on",Space,Str "the",Space,Str "final",Space,Str "stroke",Space,Str "of",Space,Str "nine.",Note [Para [Link [Str "68."] ("#wasteland-content.xhtml#ln68",""),Space,Str "A",Space,Str "phenomenon",Space,Str "which",Space,Str "I",Space,Str "have",Space,Str "often",Space,Str "noticed."]]],Div ("",[],[]) [Plain [Str "There",Space,Str "I",Space,Str "saw",Space,Str "one",Space,Str "I",Space,Str "knew,",Space,Str "and",Space,Str "stopped",Space,Str "him,",Space,Str "crying",Space,Str "\"Stetson!"]],Div ("",[],[]) [Plain [Str "\"You",Space,Str "who",Space,Str "were",Space,Str "with",Space,Str "me",Space,Str "in",Space,Str "the",Space,Str "ships",Space,Str "at",Space,Str "Mylae!",Span ("",["lnum"],[]) [Str "70"]]],Div ("",[],[]) [Plain [Str "\"That",Space,Str "corpse",Space,Str "you",Space,Str "planted",Space,Str "last",Space,Str "year",Space,Str "in",Space,Str "your",Space,Str "garden,"]],Div ("",[],[]) [Plain [Str "\"Has",Space,Str "it",Space,Str "begun",Space,Str "to",Space,Str "sprout?",Space,Str "Will",Space,Str "it",Space,Str "bloom",Space,Str "this",Space,Str "year?"]],Div ("",[],[]) [Plain [Str "\"Or",Space,Str "has",Space,Str "the",Space,Str "sudden",Space,Str "frost",Space,Str "disturbed",Space,Str "its",Space,Str "bed?"]]],Div ("",["linegroup"],[]) [Div ("wasteland-content.xhtml#ln74",[],[]) [Plain [Str "\"Oh",Space,Str "keep",Space,Str "the",Space,Str "Dog",Space,Str "far",Space,Str "hence,",Space,Str "that's",Space,Str "friend",Space,Str "to",Space,Str "men,",Note [Para [Link [Str "74."] ("#wasteland-content.xhtml#ln74",""),Space,Str "Cf.",Space,Str "the",Space,Str "Dirge",Space,Str "in",Space,Str "Webster's",Space,Str "White",Space,Str "Devil",Space,Str "."]]],Div ("",[],[]) [Plain [Str "\"Or",Space,Str "with",Space,Str "his",Space,Str "nails",Space,Str "he'll",Space,Str "dig",Space,Str "it",Space,Str "up",Space,Str "again!"]],Div ("wasteland-content.xhtml#ln76",[],[]) [Plain [Str "\"You!",Space,Span ("",[],[("lang","fr")]) [Str "hypocrite",Space,Str "lecteur!",Space,Str "-",Space,Str "mon",Space,Str "semblable,",Space,Str "-",Space,Str "mon",Space,Str "frere"],Space,Str "!\"",Note [Para [Link [Str "76."] ("#wasteland-content.xhtml#ln76",""),Space,Str "V.",Space,Str "Baudelaire,",Space,Str "Preface",Space,Str "to",Space,Str "Fleurs",Space,Str "du",Space,Str "Mal."]]],RawBlock (Format "html") "<section id=\"ch2\">",Header 2 ("",[],[]) [Str "II.",Space,Str "A",Space,Str "GAME",Space,Str "OF",Space,Str "CHESS"],Div ("",["linegroup"],[]) [Div ("wasteland-content.xhtml#ln77",[],[]) [Plain [Str "The",Space,Str "Chair",Space,Str "she",Space,Str "sat",Space,Str "in,",Space,Str "like",Space,Str "a",Space,Str "burnished",Space,Str "throne,",Note [Para [Link [Str "77."] ("#wasteland-content.xhtml#ln77",""),Space,Str "Cf.",Space,Str "Antony",Space,Str "and",Space,Str "Cleopatra,",Space,Str "II.",Space,Str "ii.,",Space,Str "l.",Space,Str "190."]]],Div ("",[],[]) [Plain [Str "Glowed",Space,Str "on",Space,Str "the",Space,Str "marble,",Space,Str "where",Space,Str "the",Space,Str "glass"]],Div ("",[],[]) [Plain [Str "Held",Space,Str "up",Space,Str "by",Space,Str "standards",Space,Str "wrought",Space,Str "with",Space,Str "fruited",Space,Str "vines"]],Div ("",[],[]) [Plain [Str "From",Space,Str "which",Space,Str "a",Space,Str "golden",Space,Str "Cupidon",Space,Str "peeped",Space,Str "out",Span ("",["lnum"],[]) [Str "80"]]],Div ("",[],[]) [Plain [Str "(Another",Space,Str "hid",Space,Str "his",Space,Str "eyes",Space,Str "behind",Space,Str "his",Space,Str "wing)"]],Div ("",[],[]) [Plain [Str "Doubled",Space,Str "the",Space,Str "flames",Space,Str "of",Space,Str "sevenbranched",Space,Str "candelabra"]],Div ("",[],[]) [Plain [Str "Reflecting",Space,Str "light",Space,Str "upon",Space,Str "the",Space,Str "table",Space,Str "as"]],Div ("",[],[]) [Plain [Str "The",Space,Str "glitter",Space,Str "of",Space,Str "her",Space,Str "jewels",Space,Str "rose",Space,Str "to",Space,Str "meet",Space,Str "it,"]],Div ("",[],[]) [Plain [Str "From",Space,Str "satin",Space,Str "cases",Space,Str "poured",Space,Str "in",Space,Str "rich",Space,Str "profusion;"]],Div ("",[],[]) [Plain [Str "In",Space,Str "vials",Space,Str "of",Space,Str "ivory",Space,Str "and",Space,Str "coloured",Space,Str "glass"]],Div ("",[],[]) [Plain [Str "Unstoppered,",Space,Str "lurked",Space,Str "her",Space,Str "strange",Space,Str "synthetic",Space,Str "perfumes,"]],Div ("",[],[]) [Plain [Str "Unguent,",Space,Str "powdered,",Space,Str "or",Space,Str "liquid",Space,Str "-",Space,Str "troubled,",Space,Str "confused"]],Div ("",[],[]) [Plain [Str "And",Space,Str "drowned",Space,Str "the",Space,Str "sense",Space,Str "in",Space,Str "odours;",Space,Str "stirred",Space,Str "by",Space,Str "the",Space,Str "air"]],Div ("",[],[]) [Plain [Str "That",Space,Str "freshened",Space,Str "from",Space,Str "the",Space,Str "window,",Space,Str "these",Space,Str "ascended",Span ("",["lnum"],[]) [Str "90"]]],Div ("",[],[]) [Plain [Str "In",Space,Str "fattening",Space,Str "the",Space,Str "prolonged",Space,Str "candle-flames,"]],Div ("wasteland-content.xhtml#ln92",[],[]) [Plain [Str "Flung",Space,Str "their",Space,Str "smoke",Space,Str "into",Space,Str "the",Space,Str "laquearia,",Note [Para [Link [Str "92."] ("#wasteland-content.xhtml#ln92",""),Space,Str "Laquearia.",Space,Str "V.",Space,Str "Aeneid,",Space,Str "I.",Space,Str "726:"],BlockQuote [Para [Str "dependent",Space,Str "lychni",Space,Str "laquearibus",Space,Str "aureis",Space,Str "incensi,",Space,Str "et",Space,Str "noctem",Space,Str "flammis",LineBreak,Str "funalia",Space,Str "vincunt."]]]],Div ("",[],[]) [Plain [Str "Stirring",Space,Str "the",Space,Str "pattern",Space,Str "on",Space,Str "the",Space,Str "coffered",Space,Str "ceiling."]],Div ("",[],[]) [Plain [Str "Huge",Space,Str "sea-wood",Space,Str "fed",Space,Str "with",Space,Str "copper"]],Div ("",[],[]) [Plain [Str "Burned",Space,Str "green",Space,Str "and",Space,Str "orange,",Space,Str "framed",Space,Str "by",Space,Str "the",Space,Str "coloured",Space,Str "stone,"]],Div ("",[],[]) [Plain [Str "In",Space,Str "which",Space,Str "sad",Space,Str "light",Space,Str "a",Space,Str "carved",Space,Str "dolphin",Space,Str "swam."]],Div ("",[],[]) [Plain [Str "Above",Space,Str "the",Space,Str "antique",Space,Str "mantel",Space,Str "was",Space,Str "displayed"]],Div ("wasteland-content.xhtml#ln98",[],[]) [Plain [Str "As",Space,Str "though",Space,Str "a",Space,Str "window",Space,Str "gave",Space,Str "upon",Space,Str "the",Space,Str "sylvan",Space,Str "scene",Note [Para [Link [Str "98."] ("#wasteland-content.xhtml#ln98",""),Space,Str "Sylvan",Space,Str "scene.",Space,Str "V.",Space,Str "Milton,",Space,Str "Paradise",Space,Str "Lost,",Space,Str "iv.",Space,Str "140."]]],Div ("wasteland-content.xhtml#ln99",[],[]) [Plain [Str "The",Space,Str "change",Space,Str "of",Space,Str "Philomel,",Space,Str "by",Space,Str "the",Space,Str "barbarous",Space,Str "king",Note [Para [Link [Str "99."] ("#wasteland-content.xhtml#ln99",""),Space,Str "V.",Space,Str "Ovid,",Space,Str "Metamorphoses,",Space,Str "vi,",Space,Str "Philomela."]]],Div ("wasteland-content.xhtml#ln100",[],[]) [Plain [Str "So",Space,Str "rudely",Space,Str "forced;",Space,Str "yet",Space,Str "there",Space,Str "the",Space,Str "nightingale",Note [Para [Link [Str "100."] ("#wasteland-content.xhtml#ln100",""),Space,Str "Cf.",Space,Str "Part",Space,Str "III,",Space,Str "l.",Space,Str "204."]]],Div ("",[],[]) [Plain [Str "Filled",Space,Str "all",Space,Str "the",Space,Str "desert",Space,Str "with",Space,Str "inviolable",Space,Str "voice"]],Div ("",[],[]) [Plain [Str "And",Space,Str "still",Space,Str "she",Space,Str "cried,",Space,Str "and",Space,Str "still",Space,Str "the",Space,Str "world",Space,Str "pursues,"]],Div ("",[],[]) [Plain [Str "\"Jug",Space,Str "Jug\"",Space,Str "to",Space,Str "dirty",Space,Str "ears."]],Div ("",[],[]) [Plain [Str "And",Space,Str "other",Space,Str "withered",Space,Str "stumps",Space,Str "of",Space,Str "time"]],Div ("",[],[]) [Plain [Str "Were",Space,Str "told",Space,Str "upon",Space,Str "the",Space,Str "walls;",Space,Str "staring",Space,Str "forms"]],Div ("",[],[]) [Plain [Str "Leaned",Space,Str "out,",Space,Str "leaning,",Space,Str "hushing",Space,Str "the",Space,Str "room",Space,Str "enclosed."]],Div ("",[],[]) [Plain [Str "Footsteps",Space,Str "shuffled",Space,Str "on",Space,Str "the",Space,Str "stair."]],Div ("",[],[]) [Plain [Str "Under",Space,Str "the",Space,Str "firelight,",Space,Str "under",Space,Str "the",Space,Str "brush,",Space,Str "her",Space,Str "hair"]],Div ("",[],[]) [Plain [Str "Spread",Space,Str "out",Space,Str "in",Space,Str "fiery",Space,Str "points"]],Div ("",[],[]) [Plain [Str "Glowed",Space,Str "into",Space,Str "words,",Space,Str "then",Space,Str "would",Space,Str "be",Space,Str "savagely",Space,Str "still.",Span ("",["lnum"],[]) [Str "110"]]]],Div ("",["linegroup"],[]) [Div ("",["linegroup"],[]) [Div ("",[],[]) [Plain [Str "\"My",Space,Str "nerves",Space,Str "are",Space,Str "bad",Space,Str "to-night.",Space,Str "Yes,",Space,Str "bad.",Space,Str "Stay",Space,Str "with",Space,Str "me."]],Div ("",[],[]) [Plain [Str "\"Speak",Space,Str "to",Space,Str "me.",Space,Str "Why",Space,Str "do",Space,Str "you",Space,Str "never",Space,Str "speak.",Space,Str "Speak."]],Div ("",[],[]) [Plain [Str "\"What",Space,Str "are",Space,Str "you",Space,Str "thinking",Space,Str "of?",Space,Str "What",Space,Str "thinking?",Space,Str "What?"]],Div ("",[],[]) [Plain [Str "\"I",Space,Str "never",Space,Str "know",Space,Str "what",Space,Str "you",Space,Str "are",Space,Str "thinking.",Space,Str "Think.\""]]],Div ("",["linegroup"],[]) [Div ("wasteland-content.xhtml#ln115",[],[]) [Plain [Str "I",Space,Str "think",Space,Str "we",Space,Str "are",Space,Str "in",Space,Str "rats'",Space,Str "alley",Note [Para [Link [Str "115."] ("#wasteland-content.xhtml#ln115",""),Space,Str "Cf.",Space,Str "Part",Space,Str "III,",Space,Str "l.",Space,Str "195."]]],Div ("",[],[]) [Plain [Str "Where",Space,Str "the",Space,Str "dead",Space,Str "men",Space,Str "lost",Space,Str "their",Space,Str "bones."]]]],Div ("",["linegroup"],[]) [Div ("",[],[]) [Plain [Str "\"What",Space,Str "is",Space,Str "that",Space,Str "noise?\""]],Div ("wasteland-content.xhtml#ln118",["indent"],[]) [Plain [Str "The",Space,Str "wind",Space,Str "under",Space,Str "the",Space,Str "door.",Note [Para [Link [Str "118."] ("#wasteland-content.xhtml#ln118",""),Space,Str "Cf.",Space,Str "Webster:"],BlockQuote [Para [Str "\"Is",Space,Str "the",Space,Str "wind",Space,Str "in",Space,Str "that",Space,Str "door",Space,Str "still?\""]]]],Div ("",[],[]) [Plain [Str "\"What",Space,Str "is",Space,Str "that",Space,Str "noise",Space,Str "now?",Space,Str "What",Space,Str "is",Space,Str "the",Space,Str "wind",Space,Str "doing?\""]],Div ("",["indent"],[]) [Plain [Str "Nothing",Space,Str "again",Space,Str "nothing.",Span ("",["lnum"],[]) [Str "120"]]]],Div ("",["linegroup"],[]) [Div ("",[],[]) [Plain [Str "\"Do"]],Div ("",[],[]) [Plain [Str "\"You",Space,Str "know",Space,Str "nothing?",Space,Str "Do",Space,Str "you",Space,Str "see",Space,Str "nothing?",Space,Str "Do",Space,Str "you",Space,Str "remember"]],Div ("",[],[]) [Plain [Str "\"Nothing?\""]]],Div ("",["linegroup"],[]) [Div ("",[],[]) [Plain [Str "I",Space,Str "remember"]],Div ("",[],[]) [Plain [Str "Those",Space,Str "are",Space,Str "pearls",Space,Str "that",Space,Str "were",Space,Str "his",Space,Str "eyes."]],Div ("wasteland-content.xhtml#ln126",[],[]) [Plain [Str "\"Are",Space,Str "you",Space,Str "alive,",Space,Str "or",Space,Str "not?",Space,Str "Is",Space,Str "there",Space,Str "nothing",Space,Str "in",Space,Str "your",Space,Str "head?\"",Note [Para [Link [Str "126."] ("#wasteland-content.xhtml#ln126",""),Space,Str "Cf.",Space,Str "Part",Space,Str "I,",Space,Str "l.",Space,Str "37,",Space,Str "48."]]],Div ("",[],[]) [Plain [Str "But"]],Div ("",[],[]) [Plain [Str "O",Space,Str "O",Space,Str "O",Space,Str "O",Space,Str "that",Space,Str "Shakespeherian",Space,Str "Rag\8213"]],Div ("",[],[]) [Plain [Str "It's",Space,Str "so",Space,Str "elegant"]],Div ("",[],[]) [Plain [Str "So",Space,Str "intelligent",Span ("",["lnum"],[]) [Str "130"]]],Div ("",[],[]) [Plain [Str "\"What",Space,Str "shall",Space,Str "I",Space,Str "do",Space,Str "now?",Space,Str "What",Space,Str "shall",Space,Str "I",Space,Str "do?\""]],Div ("",[],[]) [Plain [Str "I",Space,Str "shall",Space,Str "rush",Space,Str "out",Space,Str "as",Space,Str "I",Space,Str "am,",Space,Str "and",Space,Str "walk",Space,Str "the",Space,Str "street"]],Div ("",[],[]) [Plain [Str "\"With",Space,Str "my",Space,Str "hair",Space,Str "down,",Space,Str "so.",Space,Str "What",Space,Str "shall",Space,Str "we",Space,Str "do",Space,Str "to-morrow?"]],Div ("",[],[]) [Plain [Str "\"What",Space,Str "shall",Space,Str "we",Space,Str "ever",Space,Str "do?\""]],Div ("",[],[]) [Plain [Str "The",Space,Str "hot",Space,Str "water",Space,Str "at",Space,Str "ten."]],Div ("",[],[]) [Plain [Str "And",Space,Str "if",Space,Str "it",Space,Str "rains,",Space,Str "a",Space,Str "closed",Space,Str "car",Space,Str "at",Space,Str "four."]],Div ("",[],[]) [Plain [Str "And",Space,Str "we",Space,Str "shall",Space,Str "play",Space,Str "a",Space,Str "game",Space,Str "of",Space,Str "chess,"]],Div ("wasteland-content.xhtml#ln138",[],[]) [Plain [Str "Pressing",Space,Str "lidless",Space,Str "eyes",Space,Str "and",Space,Str "waiting",Space,Str "for",Space,Str "a",Space,Str "knock",Space,Str "upon",Space,Str "the",Space,Str "door.",Note [Para [Link [Str "138."] ("#wasteland-content.xhtml#ln138",""),Space,Str "Cf.",Space,Str "the",Space,Str "game",Space,Str "of",Space,Str "chess",Space,Str "in",Space,Str "Middleton's",Space,Str "Women",Space,Str "beware",Space,Str "Women."]]],Div ("",["linegroup"],[]) [Div ("",[],[]) [Plain [Str "When",Space,Str "Lil's",Space,Str "husband",Space,Str "got",Space,Str "demobbed,",Space,Str "I",Space,Str "said",Space,Str "-"]],Div ("",[],[]) [Plain [Str "I",Space,Str "didn't",Space,Str "mince",Space,Str "my",Space,Str "words,",Space,Str "I",Space,Str "said",Space,Str "to",Space,Str "her",Space,Str "myself,",Span ("",["lnum"],[]) [Str "140"]]],Div ("",[],[]) [Plain [Str "HURRY",Space,Str "UP",Space,Str "PLEASE",Space,Str "ITS",Space,Str "TIME"]],Div ("",[],[]) [Plain [Str "Now",Space,Str "Albert's",Space,Str "coming",Space,Str "back,",Space,Str "make",Space,Str "yourself",Space,Str "a",Space,Str "bit",Space,Str "smart."]],Div ("",[],[]) [Plain [Str "He'll",Space,Str "want",Space,Str "to",Space,Str "know",Space,Str "what",Space,Str "you",Space,Str "done",Space,Str "with",Space,Str "that",Space,Str "money",Space,Str "he",Space,Str "gave",Space,Str "you"]],Div ("",[],[]) [Plain [Str "To",Space,Str "get",Space,Str "yourself",Space,Str "some",Space,Str "teeth.",Space,Str "He",Space,Str "did,",Space,Str "I",Space,Str "was",Space,Str "there."]],Div ("",[],[]) [Plain [Str "You",Space,Str "have",Space,Str "them",Space,Str "all",Space,Str "out,",Space,Str "Lil,",Space,Str "and",Space,Str "get",Space,Str "a",Space,Str "nice",Space,Str "set,"]],Div ("",[],[]) [Plain [Str "He",Space,Str "said,",Space,Str "I",Space,Str "swear,",Space,Str "I",Space,Str "can't",Space,Str "bear",Space,Str "to",Space,Str "look",Space,Str "at",Space,Str "you."]],Div ("",[],[]) [Plain [Str "And",Space,Str "no",Space,Str "more",Space,Str "can't",Space,Str "I,",Space,Str "I",Space,Str "said,",Space,Str "and",Space,Str "think",Space,Str "of",Space,Str "poor",Space,Str "Albert,"]],Div ("",[],[]) [Plain [Str "He's",Space,Str "been",Space,Str "in",Space,Str "the",Space,Str "army",Space,Str "four",Space,Str "years,",Space,Str "he",Space,Str "wants",Space,Str "a",Space,Str "good",Space,Str "time,"]],Div ("",[],[]) [Plain [Str "And",Space,Str "if",Space,Str "you",Space,Str "don't",Space,Str "give",Space,Str "it",Space,Str "him,",Space,Str "there's",Space,Str "others",Space,Str "will,",Space,Str "I",Space,Str "said."]],Div ("",[],[]) [Plain [Str "Oh",Space,Str "is",Space,Str "there,",Space,Str "she",Space,Str "said.",Space,Str "Something",Space,Str "o'",Space,Str "that,",Space,Str "I",Space,Str "said.",Span ("",["lnum"],[]) [Str "150"]]],Div ("",[],[]) [Plain [Str "Then",Space,Str "I'll",Space,Str "know",Space,Str "who",Space,Str "to",Space,Str "thank,",Space,Str "she",Space,Str "said,",Space,Str "and",Space,Str "give",Space,Str "me",Space,Str "a",Space,Str "straight",Space,Str "look."]],Div ("",[],[]) [Plain [Str "HURRY",Space,Str "UP",Space,Str "PLEASE",Space,Str "ITS",Space,Str "TIME"]],Div ("",[],[]) [Plain [Str "If",Space,Str "you",Space,Str "don't",Space,Str "like",Space,Str "it",Space,Str "you",Space,Str "can",Space,Str "get",Space,Str "on",Space,Str "with",Space,Str "it,",Space,Str "I",Space,Str "said."]],Div ("",[],[]) [Plain [Str "Others",Space,Str "can",Space,Str "pick",Space,Str "and",Space,Str "choose",Space,Str "if",Space,Str "you",Space,Str "can't."]],Div ("",[],[]) [Plain [Str "But",Space,Str "if",Space,Str "Albert",Space,Str "makes",Space,Str "off,",Space,Str "it",Space,Str "won't",Space,Str "be",Space,Str "for",Space,Str "lack",Space,Str "of",Space,Str "telling."]],Div ("",[],[]) [Plain [Str "You",Space,Str "ought",Space,Str "to",Space,Str "be",Space,Str "ashamed,",Space,Str "I",Space,Str "said,",Space,Str "to",Space,Str "look",Space,Str "so",Space,Str "antique."]],Div ("",[],[]) [Plain [Str "(And",Space,Str "her",Space,Str "only",Space,Str "thirty-one.)"]],Div ("",[],[]) [Plain [Str "I",Space,Str "can't",Space,Str "help",Space,Str "it,",Space,Str "she",Space,Str "said,",Space,Str "pulling",Space,Str "a",Space,Str "long",Space,Str "face,"]],Div ("",[],[]) [Plain [Str "It's",Space,Str "them",Space,Str "pills",Space,Str "I",Space,Str "took,",Space,Str "to",Space,Str "bring",Space,Str "it",Space,Str "off,",Space,Str "she",Space,Str "said."]],Div ("",[],[]) [Plain [Str "(She's",Space,Str "had",Space,Str "five",Space,Str "already,",Space,Str "and",Space,Str "nearly",Space,Str "died",Space,Str "of",Space,Str "young",Space,Str "George.)",Span ("",["lnum"],[]) [Str "160"]]],Div ("",[],[]) [Plain [Str "The",Space,Str "chemist",Space,Str "said",Space,Str "it",Space,Str "would",Space,Str "be",Space,Str "all",Space,Str "right,",Space,Str "but",Space,Str "I've",Space,Str "never",Space,Str "been",Space,Str "the",Space,Str "same."]],Div ("",[],[]) [Plain [Str "You",Space,Emph [Str "are"],Space,Str "a",Space,Str "proper",Space,Str "fool,",Space,Str "I",Space,Str "said."]],Div ("",[],[]) [Plain [Str "Well,",Space,Str "if",Space,Str "Albert",Space,Str "won't",Space,Str "leave",Space,Str "you",Space,Str "alone,",Space,Str "there",Space,Str "it",Space,Str "is,",Space,Str "I",Space,Str "said,"]],Div ("",[],[]) [Plain [Str "What",Space,Str "you",Space,Str "get",Space,Str "married",Space,Str "for",Space,Str "if",Space,Str "you",Space,Str "don't",Space,Str "want",Space,Str "children?"]],Div ("",[],[]) [Plain [Str "HURRY",Space,Str "UP",Space,Str "PLEASE",Space,Str "ITS",Space,Str "TIME"]],Div ("",[],[]) [Plain [Str "Well,",Space,Str "that",Space,Str "Sunday",Space,Str "Albert",Space,Str "was",Space,Str "home,",Space,Str "they",Space,Str "had",Space,Str "a",Space,Str "hot",Space,Str "gammon,"]],Div ("",[],[]) [Plain [Str "And",Space,Str "they",Space,Str "asked",Space,Str "me",Space,Str "in",Space,Str "to",Space,Str "dinner,",Space,Str "to",Space,Str "get",Space,Str "the",Space,Str "beauty",Space,Str "of",Space,Str "it",Space,Str "hot\8213"]],Div ("",[],[]) [Plain [Str "HURRY",Space,Str "UP",Space,Str "PLEASE",Space,Str "ITS",Space,Str "TIME"]],Div ("",[],[]) [Plain [Str "HURRY",Space,Str "UP",Space,Str "PLEASE",Space,Str "ITS",Space,Str "TIME"]],Div ("",[],[]) [Plain [Str "Goonight",Space,Str "Bill.",Space,Str "Goonight",Space,Str "Lou.",Space,Str "Goonight",Space,Str "May.",Space,Str "Goonight.",Span ("",["lnum"],[]) [Str "170"]]],Div ("",[],[]) [Plain [Str "Ta",Space,Str "ta.",Space,Str "Goonight.",Space,Str "Goonight."]],Div ("",[],[]) [Plain [Str "Good",Space,Str "night,",Space,Str "ladies,",Space,Str "good",Space,Str "night,",Space,Str "sweet",Space,Str "ladies,",Space,Str "good",Space,Str "night,",Space,Str "good",Space,Str "night."]]],RawBlock (Format "html") "</section>",RawBlock (Format "html") "<section id=\"ch3\">",Header 2 ("",[],[]) [Str "III.",Space,Str "THE",Space,Str "FIRE",Space,Str "SERMON"],Div ("",["linegroup"],[]) [Div ("",[],[]) [Plain [Str "The",Space,Str "river's",Space,Str "tent",Space,Str "is",Space,Str "broken:",Space,Str "the",Space,Str "last",Space,Str "fingers",Space,Str "of",Space,Str "leaf"]],Div ("",[],[]) [Plain [Str "Clutch",Space,Str "and",Space,Str "sink",Space,Str "into",Space,Str "the",Space,Str "wet",Space,Str "bank.",Space,Str "The",Space,Str "wind"]],Div ("",[],[]) [Plain [Str "Crosses",Space,Str "the",Space,Str "brown",Space,Str "land,",Space,Str "unheard.",Space,Str "The",Space,Str "nymphs",Space,Str "are",Space,Str "departed."]],Div ("wasteland-content.xhtml#ln176",[],[]) [Plain [Str "Sweet",Space,Str "Thames,",Space,Str "run",Space,Str "softly,",Space,Str "till",Space,Str "I",Space,Str "end",Space,Str "my",Space,Str "song.",Note [Para [Link [Str "176."] ("#wasteland-content.xhtml#ln176",""),Space,Str "V.",Space,Str "Spenser,",Space,Str "Prothalamion."]]],Div ("",[],[]) [Plain [Str "The",Space,Str "river",Space,Str "bears",Space,Str "no",Space,Str "empty",Space,Str "bottles,",Space,Str "sandwich",Space,Str "papers,"]],Div ("",[],[]) [Plain [Str "Silk",Space,Str "handkerchiefs,",Space,Str "cardboard",Space,Str "boxes,",Space,Str "cigarette",Space,Str "ends"]],Div ("",[],[]) [Plain [Str "Or",Space,Str "other",Space,Str "testimony",Space,Str "of",Space,Str "summer",Space,Str "nights.",Space,Str "The",Space,Str "nymphs",Space,Str "are",Space,Str "departed."]],Div ("",[],[]) [Plain [Str "And",Space,Str "their",Space,Str "friends,",Space,Str "the",Space,Str "loitering",Space,Str "heirs",Space,Str "of",Space,Str "city",Space,Str "directors;",Span ("",["lnum"],[]) [Str "180"]]],Div ("",[],[]) [Plain [Str "Departed,",Space,Str "have",Space,Str "left",Space,Str "no",Space,Str "addresses."]],Div ("",[],[]) [Plain [Str "By",Space,Str "the",Space,Str "waters",Space,Str "of",Space,Str "Leman",Space,Str "I",Space,Str "sat",Space,Str "down",Space,Str "and",Space,Str "wept",Space,Str ".",Space,Str ".",Space,Str "."]],Div ("",[],[]) [Plain [Str "Sweet",Space,Str "Thames,",Space,Str "run",Space,Str "softly",Space,Str "till",Space,Str "I",Space,Str "end",Space,Str "my",Space,Str "song,"]],Div ("",[],[]) [Plain [Str "Sweet",Space,Str "Thames,",Space,Str "run",Space,Str "softly,",Space,Str "for",Space,Str "I",Space,Str "speak",Space,Str "not",Space,Str "loud",Space,Str "or",Space,Str "long."]],Div ("",[],[]) [Plain [Str "But",Space,Str "at",Space,Str "my",Space,Str "back",Space,Str "in",Space,Str "a",Space,Str "cold",Space,Str "blast",Space,Str "I",Space,Str "hear"]],Div ("",[],[]) [Plain [Str "The",Space,Str "rattle",Space,Str "of",Space,Str "the",Space,Str "bones,",Space,Str "and",Space,Str "chuckle",Space,Str "spread",Space,Str "from",Space,Str "ear",Space,Str "to",Space,Str "ear."]]],Div ("",["linegroup"],[]) [Div ("",[],[]) [Plain [Str "A",Space,Str "rat",Space,Str "crept",Space,Str "softly",Space,Str "through",Space,Str "the",Space,Str "vegetation"]],Div ("",[],[]) [Plain [Str "Dragging",Space,Str "its",Space,Str "slimy",Space,Str "belly",Space,Str "on",Space,Str "the",Space,Str "bank"]],Div ("",[],[]) [Plain [Str "While",Space,Str "I",Space,Str "was",Space,Str "fishing",Space,Str "in",Space,Str "the",Space,Str "dull",Space,Str "canal"]],Div ("",[],[]) [Plain [Str "On",Space,Str "a",Space,Str "winter",Space,Str "evening",Space,Str "round",Space,Str "behind",Space,Str "the",Space,Str "gashouse",Span ("",["lnum"],[]) [Str "190"]]],Div ("",[],[]) [Plain [Str "Musing",Space,Str "upon",Space,Str "the",Space,Str "king",Space,Str "my",Space,Str "brother's",Space,Str "wreck"]],Div ("wasteland-content.xhtml#ln192",[],[]) [Plain [Str "And",Space,Str "on",Space,Str "the",Space,Str "king",Space,Str "my",Space,Str "father's",Space,Str "death",Space,Str "before",Space,Str "him.",Note [Para [Link [Str "192."] ("#wasteland-content.xhtml#ln192",""),Space,Str "Cf.",Space,Str "The",Space,Str "Tempest,",Space,Str "I.",Space,Str "ii."]]],Div ("",[],[]) [Plain [Str "White",Space,Str "bodies",Space,Str "naked",Space,Str "on",Space,Str "the",Space,Str "low",Space,Str "damp",Space,Str "ground"]],Div ("",[],[]) [Plain [Str "And",Space,Str "bones",Space,Str "cast",Space,Str "in",Space,Str "a",Space,Str "little",Space,Str "low",Space,Str "dry",Space,Str "garret,"]],Div ("",[],[]) [Plain [Str "Rattled",Space,Str "by",Space,Str "the",Space,Str "rat's",Space,Str "foot",Space,Str "only,",Space,Str "year",Space,Str "to",Space,Str "year."]],Div ("wasteland-content.xhtml#ln196",[],[]) [Plain [Str "But",Space,Str "at",Space,Str "my",Space,Str "back",Space,Str "from",Space,Str "time",Space,Str "to",Space,Str "time",Space,Str "I",Space,Str "hear",Note [Para [Link [Str "196."] ("#wasteland-content.xhtml#ln196",""),Space,Str "Cf.",Space,Str "Marvell,",Space,Str "To",Space,Str "His",Space,Str "Coy",Space,Str "Mistress."]]],Div ("wasteland-content.xhtml#ln197",[],[]) [Plain [Str "The",Space,Str "sound",Space,Str "of",Space,Str "horns",Space,Str "and",Space,Str "motors,",Space,Str "which",Space,Str "shall",Space,Str "bring",Note [Para [Link [Str "197."] ("#wasteland-content.xhtml#ln197",""),Space,Str "Cf.",Space,Str "Day,",Space,Str "Parliament",Space,Str "of",Space,Str "Bees:"],BlockQuote [Div ("",[],[]) [Div ("",[],[]) [Plain [Str "\"When",Space,Str "of",Space,Str "the",Space,Str "sudden,",Space,Str "listening,",Space,Str "you",Space,Str "shall",Space,Str "hear,"]],Div ("",[],[]) [Plain [Str "\"A",Space,Str "noise",Space,Str "of",Space,Str "horns",Space,Str "and",Space,Str "hunting,",Space,Str "which",Space,Str "shall",Space,Str "bring"]],Div ("",[],[]) [Plain [Str "\"Actaeon",Space,Str "to",Space,Str "Diana",Space,Str "in",Space,Str "the",Space,Str "spring,"]],Div ("",[],[]) [Plain [Str "\"Where",Space,Str "all",Space,Str "shall",Space,Str "see",Space,Str "her",Space,Str "naked",Space,Str "skin",Space,Str ".",Space,Str ".",Space,Str ".\""]]]]]],Div ("",[],[]) [Plain [Str "Sweeney",Space,Str "to",Space,Str "Mrs.",Space,Str "Porter",Space,Str "in",Space,Str "the",Space,Str "spring."]],Div ("wasteland-content.xhtml#ln199",[],[]) [Plain [Str "O",Space,Str "the",Space,Str "moon",Space,Str "shone",Space,Str "bright",Space,Str "on",Space,Str "Mrs.",Space,Str "Porter",Note [Para [Link [Str "199."] ("#wasteland-content.xhtml#ln199",""),Space,Str "I",Space,Str "do",Space,Str "not",Space,Str "know",Space,Str "the",Space,Str "origin",Space,Str "of",Space,Str "the",Space,Str "ballad",Space,Str "from",Space,Str "which",Space,Str "these",Space,Str "lines",Space,Str "are",Space,Str "taken:",Space,Str "it",Space,Str "was",Space,Str "reported",Space,Str "to",Space,Str "me",Space,Str "from",Space,Str "Sydney,",Space,Str "Australia."]]],Div ("",[],[]) [Plain [Str "And",Space,Str "on",Space,Str "her",Space,Str "daughter",Span ("",["lnum"],[]) [Str "200"]]],Div ("",[],[]) [Plain [Str "They",Space,Str "wash",Space,Str "their",Space,Str "feet",Space,Str "in",Space,Str "soda",Space,Str "water"]],Div ("wasteland-content.xhtml#ln202",[],[("lang","fr")]) [Plain [Emph [Str "Et",Space,Str "O",Space,Str "ces",Space,Str "voix",Space,Str "d'enfants,",Space,Str "chantant",Space,Str "dans",Space,Str "la",Space,Str "coupole"],Str "!",Note [Para [Link [Str "202."] ("#wasteland-content.xhtml#ln202",""),Space,Str "V.",Space,Str "Verlaine,",Space,Str "Parsifal."]]],Div ("",["linegroup"],[]) [Div ("",[],[]) [Plain [Str "Twit",Space,Str "twit",Space,Str "twit"]],Div ("",[],[]) [Plain [Str "Jug",Space,Str "jug",Space,Str "jug",Space,Str "jug",Space,Str "jug",Space,Str "jug"]],Div ("",[],[]) [Plain [Str "So",Space,Str "rudely",Space,Str "forc'd."]],Div ("",[],[]) [Plain [Str "Tereu"]]],Div ("",["linegroup"],[]) [Div ("",[],[]) [Plain [Str "Unreal",Space,Str "City"]],Div ("",[],[]) [Plain [Str "Under",Space,Str "the",Space,Str "brown",Space,Str "fog",Space,Str "of",Space,Str "a",Space,Str "winter",Space,Str "noon"]],Div ("",[],[]) [Plain [Str "Mr.",Space,Str "Eugenides,",Space,Str "the",Space,Str "Smyrna",Space,Str "merchant"]],Div ("wasteland-content.xhtml#ln210",[],[]) [Plain [Str "Unshaven,",Space,Str "with",Space,Str "a",Space,Str "pocket",Space,Str "full",Space,Str "of",Space,Str "currants",Note [Para [Link [Str "210."] ("#wasteland-content.xhtml#ln210",""),Space,Str "The",Space,Str "currants",Space,Str "were",Space,Str "quoted",Space,Str "at",Space,Str "a",Space,Str "price",Space,Str "\"cost",Space,Str "insurance",Space,Str "and",Space,Str "freight",Space,Str "to",Space,Str "London\";",Space,Str "and",Space,Str "the",Space,Str "Bill",Space,Str "of",Space,Str "Lading",Space,Str "etc.",Space,Str "were",Space,Str "to",Space,Str "be",Space,Str "handed",Space,Str "to",Space,Str "the",Space,Str "buyer",Space,Str "upon",Space,Str "payment",Space,Str "of",Space,Str "the",Space,Str "sight",Space,Str "draft."]]],Div ("",[],[]) [Plain [Str "C.i.f.",Space,Str "London:",Space,Str "documents",Space,Str "at",Space,Str "sight,"]],Div ("",[],[]) [Plain [Str "Asked",Space,Str "me",Space,Str "in",Space,Str "demotic",Space,Str "French"]],Div ("",[],[]) [Plain [Str "To",Space,Str "luncheon",Space,Str "at",Space,Str "the",Space,Str "Cannon",Space,Str "Street",Space,Str "Hotel"]],Div ("",[],[]) [Plain [Str "Followed",Space,Str "by",Space,Str "a",Space,Str "weekend",Space,Str "at",Space,Str "the",Space,Str "Metropole."]]],Div ("",["linegroup"],[]) [Div ("",[],[]) [Plain [Str "At",Space,Str "the",Space,Str "violet",Space,Str "hour,",Space,Str "when",Space,Str "the",Space,Str "eyes",Space,Str "and",Space,Str "back"]],Div ("",[],[]) [Plain [Str "Turn",Space,Str "upward",Space,Str "from",Space,Str "the",Space,Str "desk,",Space,Str "when",Space,Str "the",Space,Str "human",Space,Str "engine",Space,Str "waits"]],Div ("",[],[]) [Plain [Str "Like",Space,Str "a",Space,Str "taxi",Space,Str "throbbing",Space,Str "waiting,"]],Div ("wasteland-content.xhtml#ln218",[],[]) [Plain [Str "I",Space,Str "Tiresias,",Space,Str "though",Space,Str "blind,",Space,Str "throbbing",Space,Str "between",Space,Str "two",Space,Str "lives,",Note [Para [Link [Str "218."] ("#wasteland-content.xhtml#ln218",""),Space,Str "Tiresias,",Space,Str "although",Space,Str "a",Space,Str "mere",Space,Str "spectator",Space,Str "and",Space,Str "not",Space,Str "indeed",Space,Str "a",Space,Str "\"character,\"",Space,Str "is",Space,Str "yet",Space,Str "the",Space,Str "most",Space,Str "important",Space,Str "personage",Space,Str "in",Space,Str "the",Space,Str "poem,",Space,Str "uniting",Space,Str "all",Space,Str "the",Space,Str "rest.",Space,Str "Just",Space,Str "as",Space,Str "the",Space,Str "one-eyed",Space,Str "merchant,",Space,Str "seller",Space,Str "of",Space,Str "currants,",Space,Str "melts",Space,Str "into",Space,Str "the",Space,Str "Phoenician",Space,Str "Sailor,",Space,Str "and",Space,Str "the",Space,Str "latter",Space,Str "is",Space,Str "not",Space,Str "wholly",Space,Str "distinct",Space,Str "from",Space,Str "Ferdinand",Space,Str "Prince",Space,Str "of",Space,Str "Naples,",Space,Str "so",Space,Str "all",Space,Str "the",Space,Str "women",Space,Str "are",Space,Str "one",Space,Str "woman,",Space,Str "and",Space,Str "the",Space,Str "two",Space,Str "sexes",Space,Str "meet",Space,Str "in",Space,Str "Tiresias.",Space,Str "What",Space,Str "Tiresias",Space,Str "sees,",Space,Str "in",Space,Str "fact,",Space,Str "is",Space,Str "the",Space,Str "substance",Space,Str "of",Space,Str "the",Space,Str "poem.",Space,Str "The",Space,Str "whole",Space,Str "passage",Space,Str "from",Space,Str "Ovid",Space,Str "is",Space,Str "of",Space,Str "great",Space,Str "anthropological",Space,Str "interest:"],BlockQuote [Para [Str "'.",Space,Str ".",Space,Str ".",Space,Str "Cum",Space,Str "Iunone",Space,Str "iocos",Space,Str "et",Space,Str "maior",Space,Str "vestra",Space,Str "profecto",Space,Str "est",LineBreak,Space,Str "Quam,",Space,Str "quae",Space,Str "contingit",Space,Str "maribus,'",Space,Str "dixisse,",Space,Str "'voluptas.'",LineBreak,Space,Str "Illa",Space,Str "negat;",Space,Str "placuit",Space,Str "quae",Space,Str "sit",Space,Str "sententia",Space,Str "docti",LineBreak,Space,Str "Quaerere",Space,Str "Tiresiae:",Space,Str "venus",Space,Str "huic",Space,Str "erat",Space,Str "utraque",Space,Str "nota.",LineBreak,Space,Str "Nam",Space,Str "duo",Space,Str "magnorum",Space,Str "viridi",Space,Str "coeuntia",Space,Str "silva",LineBreak,Space,Str "Corpora",Space,Str "serpentum",Space,Str "baculi",Space,Str "violaverat",Space,Str "ictu",LineBreak,Space,Str "Deque",Space,Str "viro",Space,Str "factus,",Space,Str "mirabile,",Space,Str "femina",Space,Str "septem",LineBreak,Space,Str "Egerat",Space,Str "autumnos;",Space,Str "octavo",Space,Str "rursus",Space,Str "eosdem",LineBreak,Space,Str "Vidit",Space,Str "et",Space,Str "'est",Space,Str "vestrae",Space,Str "si",Space,Str "tanta",Space,Str "potentia",Space,Str "plagae,'",LineBreak,Space,Str "Dixit",Space,Str "'ut",Space,Str "auctoris",Space,Str "sortem",Space,Str "in",Space,Str "contraria",Space,Str "mutet,",LineBreak,Space,Str "Nunc",Space,Str "quoque",Space,Str "vos",Space,Str "feriam!'",Space,Str "percussis",Space,Str "anguibus",Space,Str "isdem",LineBreak,Space,Str "Forma",Space,Str "prior",Space,Str "rediit",Space,Str "genetivaque",Space,Str "venit",Space,Str "imago.",LineBreak,Space,Str "Arbiter",Space,Str "hic",Space,Str "igitur",Space,Str "sumptus",Space,Str "de",Space,Str "lite",Space,Str "iocosa",LineBreak,Space,Str "Dicta",Space,Str "Iovis",Space,Str "firmat;",Space,Str "gravius",Space,Str "Saturnia",Space,Str "iusto",LineBreak,Space,Str "Nec",Space,Str "pro",Space,Str "materia",Space,Str "fertur",Space,Str "doluisse",Space,Str "suique",LineBreak,Space,Str "Iudicis",Space,Str "aeterna",Space,Str "damnavit",Space,Str "lumina",Space,Str "nocte,",LineBreak,Space,Str "At",Space,Str "pater",Space,Str "omnipotens",Space,Str "(neque",Space,Str "enim",Space,Str "licet",Space,Str "inrita",Space,Str "cuiquam",LineBreak,Space,Str "Facta",Space,Str "dei",Space,Str "fecisse",Space,Str "deo)",Space,Str "pro",Space,Str "lumine",Space,Str "adempto",LineBreak,Space,Str "Scire",Space,Str "futura",Space,Str "dedit",Space,Str "poenamque",Space,Str "levavit",Space,Str "honore.",LineBreak]]]],Div ("",[],[]) [Plain [Str "Old",Space,Str "man",Space,Str "with",Space,Str "wrinkled",Space,Str "female",Space,Str "breasts,",Space,Str "can",Space,Str "see"]],Div ("",[],[]) [Plain [Str "At",Space,Str "the",Space,Str "violet",Space,Str "hour,",Space,Str "the",Space,Str "evening",Space,Str "hour",Space,Str "that",Space,Str "strives",Span ("",["lnum"],[]) [Str "220"]]],Div ("wasteland-content.xhtml#ln221",[],[]) [Plain [Str "Homeward,",Space,Str "and",Space,Str "brings",Space,Str "the",Space,Str "sailor",Space,Str "home",Space,Str "from",Space,Str "sea,",Note [Para [Link [Str "221."] ("#wasteland-content.xhtml#ln221",""),Space,Str "This",Space,Str "may",Space,Str "not",Space,Str "appear",Space,Str "as",Space,Str "exact",Space,Str "as",Space,Str "Sappho's",Space,Str "lines,",Space,Str "but",Space,Str "I",Space,Str "had",Space,Str "in",Space,Str "mind",Space,Str "the",Space,Str "\"longshore\"",Space,Str "or",Space,Str "\"dory\"",Space,Str "fisherman,",Space,Str "who",Space,Str "returns",Space,Str "at",Space,Str "nightfall."]]],Div ("",[],[]) [Plain [Str "The",Space,Str "typist",Space,Str "home",Space,Str "at",Space,Str "teatime,",Space,Str "clears",Space,Str "her",Space,Str "breakfast,",Space,Str "lights"]],Div ("",[],[]) [Plain [Str "Her",Space,Str "stove,",Space,Str "and",Space,Str "lays",Space,Str "out",Space,Str "food",Space,Str "in",Space,Str "tins."]],Div ("",[],[]) [Plain [Str "Out",Space,Str "of",Space,Str "the",Space,Str "window",Space,Str "perilously",Space,Str "spread"]],Div ("",[],[]) [Plain [Str "Her",Space,Str "drying",Space,Str "combinations",Space,Str "touched",Space,Str "by",Space,Str "the",Space,Str "sun's",Space,Str "last",Space,Str "rays,"]],Div ("",[],[]) [Plain [Str "On",Space,Str "the",Space,Str "divan",Space,Str "are",Space,Str "piled",Space,Str "(at",Space,Str "night",Space,Str "her",Space,Str "bed)"]],Div ("",[],[]) [Plain [Str "Stockings,",Space,Str "slippers,",Space,Str "camisoles,",Space,Str "and",Space,Str "stays."]],Div ("",[],[]) [Plain [Str "I",Space,Str "Tiresias,",Space,Str "old",Space,Str "man",Space,Str "with",Space,Str "wrinkled",Space,Str "dugs"]],Div ("",[],[]) [Plain [Str "Perceived",Space,Str "the",Space,Str "scene,",Space,Str "and",Space,Str "foretold",Space,Str "the",Space,Str "rest",Space,Str "-"]],Div ("",[],[]) [Plain [Str "I",Space,Str "too",Space,Str "awaited",Space,Str "the",Space,Str "expected",Space,Str "guest.",Span ("",["lnum"],[]) [Str "230"]]],Div ("",[],[]) [Plain [Str "He,",Space,Str "the",Space,Str "young",Space,Str "man",Space,Str "carbuncular,",Space,Str "arrives,"]],Div ("",[],[]) [Plain [Str "A",Space,Str "small",Space,Str "house",Space,Str "agent's",Space,Str "clerk,",Space,Str "with",Space,Str "one",Space,Str "bold",Space,Str "stare,"]],Div ("",[],[]) [Plain [Str "One",Space,Str "of",Space,Str "the",Space,Str "low",Space,Str "on",Space,Str "whom",Space,Str "assurance",Space,Str "sits"]],Div ("",[],[]) [Plain [Str "As",Space,Str "a",Space,Str "silk",Space,Str "hat",Space,Str "on",Space,Str "a",Space,Str "Bradford",Space,Str "millionaire."]],Div ("",[],[]) [Plain [Str "The",Space,Str "time",Space,Str "is",Space,Str "now",Space,Str "propitious,",Space,Str "as",Space,Str "he",Space,Str "guesses,"]],Div ("",[],[]) [Plain [Str "The",Space,Str "meal",Space,Str "is",Space,Str "ended,",Space,Str "she",Space,Str "is",Space,Str "bored",Space,Str "and",Space,Str "tired,"]],Div ("",[],[]) [Plain [Str "Endeavours",Space,Str "to",Space,Str "engage",Space,Str "her",Space,Str "in",Space,Str "caresses"]],Div ("",[],[]) [Plain [Str "Which",Space,Str "still",Space,Str "are",Space,Str "unreproved,",Space,Str "if",Space,Str "undesired."]],Div ("",[],[]) [Plain [Str "Flushed",Space,Str "and",Space,Str "decided,",Space,Str "he",Space,Str "assaults",Space,Str "at",Space,Str "once;"]],Div ("",[],[]) [Plain [Str "Exploring",Space,Str "hands",Space,Str "encounter",Space,Str "no",Space,Str "defence;",Span ("",["lnum"],[]) [Str "240"]]],Div ("",[],[]) [Plain [Str "His",Space,Str "vanity",Space,Str "requires",Space,Str "no",Space,Str "response,"]],Div ("",[],[]) [Plain [Str "And",Space,Str "makes",Space,Str "a",Space,Str "welcome",Space,Str "of",Space,Str "indifference."]],Div ("",[],[]) [Plain [Str "(And",Space,Str "I",Space,Str "Tiresias",Space,Str "have",Space,Str "foresuffered",Space,Str "all"]],Div ("",[],[]) [Plain [Str "Enacted",Space,Str "on",Space,Str "this",Space,Str "same",Space,Str "divan",Space,Str "or",Space,Str "bed;"]],Div ("",[],[]) [Plain [Str "I",Space,Str "who",Space,Str "have",Space,Str "sat",Space,Str "by",Space,Str "Thebes",Space,Str "below",Space,Str "the",Space,Str "wall"]],Div ("",[],[]) [Plain [Str "And",Space,Str "walked",Space,Str "among",Space,Str "the",Space,Str "lowest",Space,Str "of",Space,Str "the",Space,Str "dead.)"]],Div ("",[],[]) [Plain [Str "Bestows",Space,Str "one",Space,Str "final",Space,Str "patronising",Space,Str "kiss,"]],Div ("",[],[]) [Plain [Str "And",Space,Str "gropes",Space,Str "his",Space,Str "way,",Space,Str "finding",Space,Str "the",Space,Str "stairs",Space,Str "unlit",Space,Str ".",Space,Str ".",Space,Str "."]]],Div ("",["linegroup"],[]) [Div ("",[],[]) [Plain [Str "She",Space,Str "turns",Space,Str "and",Space,Str "looks",Space,Str "a",Space,Str "moment",Space,Str "in",Space,Str "the",Space,Str "glass,"]],Div ("",[],[]) [Plain [Str "Hardly",Space,Str "aware",Space,Str "of",Space,Str "her",Space,Str "departed",Space,Str "lover;",Span ("",["lnum"],[]) [Str "250"]]],Div ("",[],[]) [Plain [Str "Her",Space,Str "brain",Space,Str "allows",Space,Str "one",Space,Str "half-formed",Space,Str "thought",Space,Str "to",Space,Str "pass:"]],Div ("",[],[]) [Plain [Str "\"Well",Space,Str "now",Space,Str "that's",Space,Str "done:",Space,Str "and",Space,Str "I'm",Space,Str "glad",Space,Str "it's",Space,Str "over.\""]],Div ("wasteland-content.xhtml#ln253",[],[]) [Plain [Str "When",Space,Str "lovely",Space,Str "woman",Space,Str "stoops",Space,Str "to",Space,Str "folly",Space,Str "and",Note [Para [Link [Str "253."] ("#wasteland-content.xhtml#ln253",""),Space,Str "V.",Space,Str "Goldsmith,",Space,Str "the",Space,Str "song",Space,Str "in",Space,Str "The",Space,Str "Vicar",Space,Str "of",Space,Str "Wakefield."]]],Div ("",[],[]) [Plain [Str "Paces",Space,Str "about",Space,Str "her",Space,Str "room",Space,Str "again,",Space,Str "alone,"]],Div ("",[],[]) [Plain [Str "She",Space,Str "smoothes",Space,Str "her",Space,Str "hair",Space,Str "with",Space,Str "automatic",Space,Str "hand,"]],Div ("",[],[]) [Plain [Str "And",Space,Str "puts",Space,Str "a",Space,Str "record",Space,Str "on",Space,Str "the",Space,Str "gramophone."]]],Div ("",["linegroup"],[]) [Div ("wasteland-content.xhtml#ln257",[],[]) [Plain [Str "\"This",Space,Str "music",Space,Str "crept",Space,Str "by",Space,Str "me",Space,Str "upon",Space,Str "the",Space,Str "waters\"",Note [Para [Link [Str "257."] ("#wasteland-content.xhtml#ln257",""),Space,Str "V.",Space,Str "The",Space,Str "Tempest,",Space,Str "as",Space,Str "above."]]],Div ("",[],[]) [Plain [Str "And",Space,Str "along",Space,Str "the",Space,Str "Strand,",Space,Str "up",Space,Str "Queen",Space,Str "Victoria",Space,Str "Street."]],Div ("",[],[]) [Plain [Str "O",Space,Str "City",Space,Str "city,",Space,Str "I",Space,Str "can",Space,Str "sometimes",Space,Str "hear"]],Div ("",[],[]) [Plain [Str "Beside",Space,Str "a",Space,Str "public",Space,Str "bar",Space,Str "in",Space,Str "Lower",Space,Str "Thames",Space,Str "Street,",Span ("",["lnum"],[]) [Str "260"]]],Div ("",[],[]) [Plain [Str "The",Space,Str "pleasant",Space,Str "whining",Space,Str "of",Space,Str "a",Space,Str "mandoline"]],Div ("",[],[]) [Plain [Str "And",Space,Str "a",Space,Str "clatter",Space,Str "and",Space,Str "a",Space,Str "chatter",Space,Str "from",Space,Str "within"]],Div ("",[],[]) [Plain [Str "Where",Space,Str "fishmen",Space,Str "lounge",Space,Str "at",Space,Str "noon:",Space,Str "where",Space,Str "the",Space,Str "walls"]],Div ("wasteland-content.xhtml#ln264",[],[]) [Plain [Str "Of",Space,Str "Magnus",Space,Str "Martyr",Space,Str "hold",Note [Para [Link [Str "264."] ("#wasteland-content.xhtml#ln264",""),Space,Str "The",Space,Str "interior",Space,Str "of",Space,Str "St.",Space,Str "Magnus",Space,Str "Martyr",Space,Str "is",Space,Str "to",Space,Str "my",Space,Str "mind",Space,Str "one",Space,Str "of",Space,Str "the",Space,Str "finest",Space,Str "among",Space,Str "Wren's",Space,Str "interiors.",Space,Str "See",Space,Str "The",Space,Str "Proposed",Space,Str "Demolition",Space,Str "of",Space,Str "Nineteen",Space,Str "City",Space,Str "Churches",Space,Str "(P.",Space,Str "S.",Space,Str "King",Space,Str "&",Space,Str "Son,",Space,Str "Ltd.)."]]],Div ("",[],[]) [Plain [Str "Inexplicable",Space,Str "splendour",Space,Str "of",Space,Str "Ionian",Space,Str "white",Space,Str "and",Space,Str "gold."]]],Div ("",["linegroup","indent"],[]) [Div ("wasteland-content.xhtml#ln266",[],[]) [Plain [Str "The",Space,Str "river",Space,Str "sweats",Note [Para [Link [Str "266."] ("#wasteland-content.xhtml#ln266",""),Space,Str "The",Space,Str "Song",Space,Str "of",Space,Str "the",Space,Str "(three)",Space,Str "Thames-daughters",Space,Str "begins",Space,Str "here.",Space,Str "From",Space,Str "line",Space,Str "292",Space,Str "to",Space,Str "306",Space,Str "inclusive",Space,Str "they",Space,Str "speak",Space,Str "in",Space,Str "turn.",Space,Str "V.",Space,Str "Gutterdsammerung,",Space,Str "III.",Space,Str "i:",Space,Str "the",Space,Str "Rhine-daughters."]]],Div ("",[],[]) [Plain [Str "Oil",Space,Str "and",Space,Str "tar"]],Div ("",[],[]) [Plain [Str "The",Space,Str "barges",Space,Str "drift"]],Div ("",[],[]) [Plain [Str "With",Space,Str "the",Space,Str "turning",Space,Str "tide"]],Div ("",[],[]) [Plain [Str "Red",Space,Str "sails",Span ("",["lnum"],[]) [Str "270"]]],Div ("",[],[]) [Plain [Str "Wide"]],Div ("",[],[]) [Plain [Str "To",Space,Str "leeward,",Space,Str "swing",Space,Str "on",Space,Str "the",Space,Str "heavy",Space,Str "spar."]],Div ("",[],[]) [Plain [Str "The",Space,Str "barges",Space,Str "wash"]],Div ("",[],[]) [Plain [Str "Drifting",Space,Str "logs"]],Div ("",[],[]) [Plain [Str "Down",Space,Str "Greenwich",Space,Str "reach"]],Div ("",[],[]) [Plain [Str "Past",Space,Str "the",Space,Str "Isle",Space,Str "of",Space,Str "Dogs."]],Div ("",["indent"],[]) [Plain [Str "Weialala",Space,Str "leia"]],Div ("",["indent"],[]) [Plain [Str "Wallala",Space,Str "leialala"]]],Div ("",["linegroup","indent"],[]) [Div ("wasteland-content.xhtml#ln279",[],[]) [Plain [Str "Elizabeth",Space,Str "and",Space,Str "Leicester",Note [Para [Link [Str "279."] ("#wasteland-content.xhtml#ln279",""),Space,Str "V.",Space,Str "Froude,",Space,Str "Elizabeth,",Space,Str "Vol.",Space,Str "I,",Space,Str "ch.",Space,Str "iv,",Space,Str "letter",Space,Str "of",Space,Str "De",Space,Str "Quadra",Space,Str "to",Space,Str "Philip",Space,Str "of",Space,Str "Spain:"],BlockQuote [Div ("",[],[]) [Div ("",[],[]) [Plain [Str "\"In",Space,Str "the",Space,Str "afternoon",Space,Str "we",Space,Str "were",Space,Str "in",Space,Str "a",Space,Str "barge,",Space,Str "watching",Space,Str "the",Space,Str "games",Space,Str "on",Space,Str "the",Space,Str "river."]],Div ("",[],[]) [Plain [Str "(The",Space,Str "queen)",Space,Str "was",Space,Str "alone",Space,Str "with",Space,Str "Lord",Space,Str "Robert",Space,Str "and",Space,Str "myself",Space,Str "on",Space,Str "the",Space,Str "poop,"]],Div ("",[],[]) [Plain [Str "when",Space,Str "they",Space,Str "began",Space,Str "to",Space,Str "talk",Space,Str "nonsense,",Space,Str "and",Space,Str "went",Space,Str "so",Space,Str "far",Space,Str "that",Space,Str "Lord",Space,Str "Robert"]],Div ("",[],[]) [Plain [Str "at",Space,Str "last",Space,Str "said,",Space,Str "as",Space,Str "I",Space,Str "was",Space,Str "on",Space,Str "the",Space,Str "spot",Space,Str "there",Space,Str "was",Space,Str "no",Space,Str "reason",Space,Str "why",Space,Str "they"]],Div ("",[],[]) [Plain [Str "should",Space,Str "not",Space,Str "be",Space,Str "married",Space,Str "if",Space,Str "the",Space,Str "queen",Space,Str "pleased.\""]]]]]],Div ("",[],[]) [Plain [Str "Beating",Space,Str "oars",Span ("",["lnum"],[]) [Str "280"]]],Div ("",[],[]) [Plain [Str "The",Space,Str "stern",Space,Str "was",Space,Str "formed"]],Div ("",[],[]) [Plain [Str "A",Space,Str "gilded",Space,Str "shell"]],Div ("",[],[]) [Plain [Str "Red",Space,Str "and",Space,Str "gold"]],Div ("",[],[]) [Plain [Str "The",Space,Str "brisk",Space,Str "swell"]],Div ("",[],[]) [Plain [Str "Rippled",Space,Str "both",Space,Str "shores"]],Div ("",[],[]) [Plain [Str "Southwest",Space,Str "wind"]],Div ("",[],[]) [Plain [Str "Carried",Space,Str "down",Space,Str "stream"]],Div ("",[],[]) [Plain [Str "The",Space,Str "peal",Space,Str "of",Space,Str "bells"]],Div ("",[],[]) [Plain [Str "White",Space,Str "towers"]],Div ("",["indent"],[]) [Plain [Str "Weialala",Space,Str "leia",Span ("",["lnum"],[]) [Str "290"]]],Div ("",["indent"],[]) [Plain [Str "Wallala",Space,Str "leialala"]]],Div ("",["linegroup"],[]) [Div ("",[],[]) [Plain [Str "\"Trams",Space,Str "and",Space,Str "dusty",Space,Str "trees."]],Div ("wasteland-content.xhtml#ln293",[],[]) [Plain [Str "Highbury",Space,Str "bore",Space,Str "me.",Space,Str "Richmond",Space,Str "and",Space,Str "Kew",Note [Para [Link [Str "293."] ("#wasteland-content.xhtml#ln293",""),Space,Str "Cf.",Space,Str "Purgatorio,",Space,Str "v.",Space,Str "133:"],BlockQuote [Para [Str "\"Ricorditi",Space,Str "di",Space,Str "me,",Space,Str "che",Space,Str "son",Space,Str "la",Space,Str "Pia;",LineBreak,Str "Siena",Space,Str "mi",Space,Str "fe',",Space,Str "disfecemi",Space,Str "Maremma.\""]]]],Div ("",[],[]) [Plain [Str "Undid",Space,Str "me.",Space,Str "By",Space,Str "Richmond",Space,Str "I",Space,Str "raised",Space,Str "my",Space,Str "knees"]],Div ("",[],[]) [Plain [Str "Supine",Space,Str "on",Space,Str "the",Space,Str "floor",Space,Str "of",Space,Str "a",Space,Str "narrow",Space,Str "canoe.\""]]],Div ("",["linegroup"],[]) [Div ("",[],[]) [Plain [Str "\"My",Space,Str "feet",Space,Str "are",Space,Str "at",Space,Str "Moorgate,",Space,Str "and",Space,Str "my",Space,Str "heart"]],Div ("",[],[]) [Plain [Str "Under",Space,Str "my",Space,Str "feet.",Space,Str "After",Space,Str "the",Space,Str "event"]],Div ("",[],[]) [Plain [Str "He",Space,Str "wept.",Space,Str "He",Space,Str "promised",Space,Str "'a",Space,Str "new",Space,Str "start'."]],Div ("",[],[]) [Plain [Str "I",Space,Str "made",Space,Str "no",Space,Str "comment.",Space,Str "What",Space,Str "should",Space,Str "I",Space,Str "resent?\""]],Div ("",[],[]) [Plain [Str "\"On",Space,Str "Margate",Space,Str "Sands.",Span ("",["lnum"],[]) [Str "300"]]],Div ("",[],[]) [Plain [Str "I",Space,Str "can",Space,Str "connect"]],Div ("",[],[]) [Plain [Str "Nothing",Space,Str "with",Space,Str "nothing."]],Div ("",[],[]) [Plain [Str "The",Space,Str "broken",Space,Str "fingernails",Space,Str "of",Space,Str "dirty",Space,Str "hands."]],Div ("",[],[]) [Plain [Str "My",Space,Str "people",Space,Str "humble",Space,Str "people",Space,Str "who",Space,Str "expect"]],Div ("",[],[]) [Plain [Str "Nothing.\""]],Div ("",["indent"],[]) [Plain [Str "la",Space,Str "la"]]],Div ("",["linegroup"],[]) [Div ("wasteland-content.xhtml#ln307",[],[]) [Plain [Str "To",Space,Str "Carthage",Space,Str "then",Space,Str "I",Space,Str "came",Note [Para [Link [Str "307."] ("#wasteland-content.xhtml#ln307",""),Space,Str "V.",Space,Str "St.",Space,Str "Augustine's",Space,Str "Confessions:",Space,Str "\"to",Space,Str "Carthage",Space,Str "then",Space,Str "I",Space,Str "came,",Space,Str "where",Space,Str "a",Space,Str "cauldron",Space,Str "of",Space,Str "unholy",Space,Str "loves",Space,Str "sang",Space,Str "all",Space,Str "about",Space,Str "mine",Space,Str "ears.\""]]],Div ("",["linegroup"],[]) [Div ("wasteland-content.xhtml#ln308",[],[]) [Plain [Str "Burning",Space,Str "burning",Space,Str "burning",Space,Str "burning",Note [Para [Link [Str "308."] ("#wasteland-content.xhtml#ln308",""),Space,Str "The",Space,Str "complete",Space,Str "text",Space,Str "of",Space,Str "the",Space,Str "Buddha's",Space,Str "Fire",Space,Str "Sermon",Space,Str "(which",Space,Str "corresponds",Space,Str "in",Space,Str "importance",Space,Str "to",Space,Str "the",Space,Str "Sermon",Space,Str "on",Space,Str "the",Space,Str "Mount)",Space,Str "from",Space,Str "which",Space,Str "these",Space,Str "words",Space,Str "are",Space,Str "taken,",Space,Str "will",Space,Str "be",Space,Str "found",Space,Str "translated",Space,Str "in",Space,Str "the",Space,Str "late",Space,Str "Henry",Space,Str "Clarke",Space,Str "Warren's",Space,Str "Buddhism",Space,Str "in",Space,Str "Translation",Space,Str "(Harvard",Space,Str "Oriental",Space,Str "Series).",Space,Str "Mr.",Space,Str "Warren",Space,Str "was",Space,Str "one",Space,Str "of",Space,Str "the",Space,Str "great",Space,Str "pioneers",Space,Str "of",Space,Str "Buddhist",Space,Str "studies",Space,Str "in",Space,Str "the",Space,Str "Occident."]]],Div ("wasteland-content.xhtml#ln309",[],[]) [Plain [Str "O",Space,Str "Lord",Space,Str "Thou",Space,Str "pluckest",Space,Str "me",Space,Str "out",Note [Para [Link [Str "309."] ("#wasteland-content.xhtml#ln309",""),Space,Str "From",Space,Str "St.",Space,Str "Augustine's",Space,Str "Confessions",Space,Str "again.",Space,Str "The",Space,Str "collocation",Space,Str "of",Space,Str "these",Space,Str "two",Space,Str "representatives",Space,Str "of",Space,Str "eastern",Space,Str "and",Space,Str "western",Space,Str "asceticism,",Space,Str "as",Space,Str "the",Space,Str "culmination",Space,Str "of",Space,Str "this",Space,Str "part",Space,Str "of",Space,Str "the",Space,Str "poem,",Space,Str "is",Space,Str "not",Space,Str "an",Space,Str "accident."]]],Div ("",[],[]) [Plain [Str "O",Space,Str "Lord",Space,Str "Thou",Space,Str "pluckest",Span ("",["lnum"],[]) [Str "310"]]]],Div ("",["linegroup"],[]) [Div ("",[],[]) [Plain [Str "burning"]]],RawBlock (Format "html") "</section>",RawBlock (Format "html") "<section id=\"ch4\">",Header 2 ("",[],[]) [Str "IV.",Space,Str "DEATH",Space,Str "BY",Space,Str "WATER"],Div ("",["linegroup"],[]) [Div ("",[],[]) [Plain [Str "Phlebas",Space,Str "the",Space,Str "Phoenician,",Space,Str "a",Space,Str "fortnight",Space,Str "dead,"]],Div ("",[],[]) [Plain [Str "Forgot",Space,Str "the",Space,Str "cry",Space,Str "of",Space,Str "gulls,",Space,Str "and",Space,Str "the",Space,Str "deep",Space,Str "sea",Space,Str "swell"]],Div ("",[],[]) [Plain [Str "And",Space,Str "the",Space,Str "profit",Space,Str "and",Space,Str "loss."]]],Div ("",["linegroup"],[]) [Div ("",["indent2"],[]) [Plain [Str "A",Space,Str "current",Space,Str "under",Space,Str "sea"]],Div ("",[],[]) [Plain [Str "Picked",Space,Str "his",Space,Str "bones",Space,Str "in",Space,Str "whispers.",Space,Str "As",Space,Str "he",Space,Str "rose",Space,Str "and",Space,Str "fell"]],Div ("",[],[]) [Plain [Str "He",Space,Str "passed",Space,Str "the",Space,Str "stages",Space,Str "of",Space,Str "his",Space,Str "age",Space,Str "and",Space,Str "youth"]],Div ("",[],[]) [Plain [Str "Entering",Space,Str "the",Space,Str "whirlpool."]]],Div ("",["linegroup"],[]) [Div ("",["indent2"],[]) [Plain [Str "Gentile",Space,Str "or",Space,Str "Jew"]],Div ("",[],[]) [Plain [Str "O",Space,Str "you",Space,Str "who",Space,Str "turn",Space,Str "the",Space,Str "wheel",Space,Str "and",Space,Str "look",Space,Str "to",Space,Str "windward,",Span ("",["lnum"],[]) [Str "320"]]],Div ("",[],[]) [Plain [Str "Consider",Space,Str "Phlebas,",Space,Str "who",Space,Str "was",Space,Str "once",Space,Str "handsome",Space,Str "and",Space,Str "tall",Space,Str "as",Space,Str "you."]]],RawBlock (Format "html") "</section>",RawBlock (Format "html") "<section id=\"ch5\">",Header 2 ("",[],[]) [Str "V.",Space,Str "WHAT",Space,Str "THE",Space,Str "THUNDER",Space,Str "SAID"],Div ("",["linegroup"],[]) [Div ("",[],[]) [Plain [Str "After",Space,Str "the",Space,Str "torchlight",Space,Str "red",Space,Str "on",Space,Str "sweaty",Space,Str "faces"]],Div ("",[],[]) [Plain [Str "After",Space,Str "the",Space,Str "frosty",Space,Str "silence",Space,Str "in",Space,Str "the",Space,Str "gardens"]],Div ("",[],[]) [Plain [Str "After",Space,Str "the",Space,Str "agony",Space,Str "in",Space,Str "stony",Space,Str "places"]],Div ("",[],[]) [Plain [Str "The",Space,Str "shouting",Space,Str "and",Space,Str "the",Space,Str "crying"]],Div ("",[],[]) [Plain [Str "Prison",Space,Str "and",Space,Str "palace",Space,Str "and",Space,Str "reverberation"]],Div ("",[],[]) [Plain [Str "Of",Space,Str "thunder",Space,Str "of",Space,Str "spring",Space,Str "over",Space,Str "distant",Space,Str "mountains"]],Div ("",[],[]) [Plain [Str "He",Space,Str "who",Space,Str "was",Space,Str "living",Space,Str "is",Space,Str "now",Space,Str "dead"]],Div ("",[],[]) [Plain [Str "We",Space,Str "who",Space,Str "were",Space,Str "living",Space,Str "are",Space,Str "now",Space,Str "dying"]],Div ("",[],[]) [Plain [Str "With",Space,Str "a",Space,Str "little",Space,Str "patience",Span ("",["lnum"],[]) [Str "330"]]]],Div ("",["linegroup"],[]) [Div ("",[],[]) [Plain [Str "Here",Space,Str "is",Space,Str "no",Space,Str "water",Space,Str "but",Space,Str "only",Space,Str "rock"]],Div ("",[],[]) [Plain [Str "Rock",Space,Str "and",Space,Str "no",Space,Str "water",Space,Str "and",Space,Str "the",Space,Str "sandy",Space,Str "road"]],Div ("",[],[]) [Plain [Str "The",Space,Str "road",Space,Str "winding",Space,Str "above",Space,Str "among",Space,Str "the",Space,Str "mountains"]],Div ("",[],[]) [Plain [Str "Which",Space,Str "are",Space,Str "mountains",Space,Str "of",Space,Str "rock",Space,Str "without",Space,Str "water"]],Div ("",[],[]) [Plain [Str "If",Space,Str "there",Space,Str "were",Space,Str "water",Space,Str "we",Space,Str "should",Space,Str "stop",Space,Str "and",Space,Str "drink"]],Div ("",[],[]) [Plain [Str "Amongst",Space,Str "the",Space,Str "rock",Space,Str "one",Space,Str "cannot",Space,Str "stop",Space,Str "or",Space,Str "think"]],Div ("",[],[]) [Plain [Str "Sweat",Space,Str "is",Space,Str "dry",Space,Str "and",Space,Str "feet",Space,Str "are",Space,Str "in",Space,Str "the",Space,Str "sand"]],Div ("",[],[]) [Plain [Str "If",Space,Str "there",Space,Str "were",Space,Str "only",Space,Str "water",Space,Str "amongst",Space,Str "the",Space,Str "rock"]],Div ("",[],[]) [Plain [Str "Dead",Space,Str "mountain",Space,Str "mouth",Space,Str "of",Space,Str "carious",Space,Str "teeth",Space,Str "that",Space,Str "cannot",Space,Str "spit"]],Div ("",[],[]) [Plain [Str "Here",Space,Str "one",Space,Str "can",Space,Str "neither",Space,Str "stand",Space,Str "nor",Space,Str "lie",Space,Str "nor",Space,Str "sit",Span ("",["lnum"],[]) [Str "340"]]],Div ("",[],[]) [Plain [Str "There",Space,Str "is",Space,Str "not",Space,Str "even",Space,Str "silence",Space,Str "in",Space,Str "the",Space,Str "mountains"]],Div ("",[],[]) [Plain [Str "But",Space,Str "dry",Space,Str "sterile",Space,Str "thunder",Space,Str "without",Space,Str "rain"]],Div ("",[],[]) [Plain [Str "There",Space,Str "is",Space,Str "not",Space,Str "even",Space,Str "solitude",Space,Str "in",Space,Str "the",Space,Str "mountains"]],Div ("",[],[]) [Plain [Str "But",Space,Str "red",Space,Str "sullen",Space,Str "faces",Space,Str "sneer",Space,Str "and",Space,Str "snarl"]],Div ("",[],[]) [Plain [Str "From",Space,Str "doors",Space,Str "of",Space,Str "mudcracked",Space,Str "houses"]],Div ("",["linegroup"],[]) [Div ("",["indent2"],[]) [Plain [Str "If",Space,Str "there",Space,Str "were",Space,Str "water"]],Div ("",[],[]) [Plain [Str "And",Space,Str "no",Space,Str "rock"]],Div ("",[],[]) [Plain [Str "If",Space,Str "there",Space,Str "were",Space,Str "rock"]],Div ("",[],[]) [Plain [Str "And",Space,Str "also",Space,Str "water"]],Div ("",[],[]) [Plain [Str "And",Space,Str "water",Span ("",["lnum"],[]) [Str "350"]]],Div ("",[],[]) [Plain [Str "A",Space,Str "spring"]],Div ("",[],[]) [Plain [Str "A",Space,Str "pool",Space,Str "among",Space,Str "the",Space,Str "rock"]],Div ("",[],[]) [Plain [Str "If",Space,Str "there",Space,Str "were",Space,Str "the",Space,Str "sound",Space,Str "of",Space,Str "water",Space,Str "only"]],Div ("",[],[]) [Plain [Str "Not",Space,Str "the",Space,Str "cicada"]],Div ("",[],[]) [Plain [Str "And",Space,Str "dry",Space,Str "grass",Space,Str "singing"]],Div ("",[],[]) [Plain [Str "But",Space,Str "sound",Space,Str "of",Space,Str "water",Space,Str "over",Space,Str "a",Space,Str "rock"]],Div ("wasteland-content.xhtml#ln357",[],[]) [Plain [Str "Where",Space,Str "the",Space,Str "hermit-thrush",Space,Str "sings",Space,Str "in",Space,Str "the",Space,Str "pine",Space,Str "trees",Note [Para [Link [Str "357."] ("#wasteland-content.xhtml#ln357",""),Space,Str "This",Space,Str "is",Space,Str "Turdus",Space,Str "aonalaschkae",Space,Str "pallasii,",Space,Str "the",Space,Str "hermit-thrush",Space,Str "which",Space,Str "I",Space,Str "have",Space,Str "heard",Space,Str "in",Space,Str "Quebec",Space,Str "County.",Space,Str "Chapman",Space,Str "says",Space,Str "(Handbook",Space,Str "of",Space,Str "Birds",Space,Str "of",Space,Str "Eastern",Space,Str "North",Space,Str "America)",Space,Str "\"it",Space,Str "is",Space,Str "most",Space,Str "at",Space,Str "home",Space,Str "in",Space,Str "secluded",Space,Str "woodland",Space,Str "and",Space,Str "thickety",Space,Str "retreats.",Space,Str ".",Space,Str ".",Space,Str ".",Space,Str "Its",Space,Str "notes",Space,Str "are",Space,Str "not",Space,Str "remarkable",Space,Str "for",Space,Str "variety",Space,Str "or",Space,Str "volume,",Space,Str "but",Space,Str "in",Space,Str "purity",Space,Str "and",Space,Str "sweetness",Space,Str "of",Space,Str "tone",Space,Str "and",Space,Str "exquisite",Space,Str "modulation",Space,Str "they",Space,Str "are",Space,Str "unequalled.\"",Space,Str "Its",Space,Str "\"water-dripping",Space,Str "song\"",Space,Str "is",Space,Str "justly",Space,Str "celebrated."]]],Div ("",[],[]) [Plain [Str "Drip",Space,Str "drop",Space,Str "drip",Space,Str "drop",Space,Str "drop",Space,Str "drop",Space,Str "drop"]],Div ("",[],[]) [Plain [Str "But",Space,Str "there",Space,Str "is",Space,Str "no",Space,Str "water"]]]],Div ("",["linegroup"],[]) [Div ("wasteland-content.xhtml#ln360",[],[]) [Plain [Str "Who",Space,Str "is",Space,Str "the",Space,Str "third",Space,Str "who",Space,Str "walks",Space,Str "always",Space,Str "beside",Space,Str "you?",Note [Para [Link [Str "360."] ("#wasteland-content.xhtml#ln360",""),Space,Str "The",Space,Str "following",Space,Str "lines",Space,Str "were",Space,Str "stimulated",Space,Str "by",Space,Str "the",Space,Str "account",Space,Str "of",Space,Str "one",Space,Str "of",Space,Str "the",Space,Str "Antarctic",Space,Str "expeditions",Space,Str "(I",Space,Str "forget",Space,Str "which,",Space,Str "but",Space,Str "I",Space,Str "think",Space,Str "one",Space,Str "of",Space,Str "Shackleton's):",Space,Str "it",Space,Str "was",Space,Str "related",Space,Str "that",Space,Str "the",Space,Str "party",Space,Str "of",Space,Str "explorers,",Space,Str "at",Space,Str "the",Space,Str "extremity",Space,Str "of",Space,Str "their",Space,Str "strength,",Space,Str "had",Space,Str "the",Space,Str "constant",Space,Str "delusion",Space,Str "that",Space,Str "there",Space,Str "was",Space,Str "one",Space,Str "more",Space,Str "member",Space,Str "than",Space,Str "could",Space,Str "actually",Space,Str "be",Space,Str "counted."]]],Div ("",[],[]) [Plain [Str "When",Space,Str "I",Space,Str "count,",Space,Str "there",Space,Str "are",Space,Str "only",Space,Str "you",Space,Str "and",Space,Str "I",Space,Str "together"]],Div ("",[],[]) [Plain [Str "But",Space,Str "when",Space,Str "I",Space,Str "look",Space,Str "ahead",Space,Str "up",Space,Str "the",Space,Str "white",Space,Str "road"]],Div ("",[],[]) [Plain [Str "There",Space,Str "is",Space,Str "always",Space,Str "another",Space,Str "one",Space,Str "walking",Space,Str "beside",Space,Str "you"]],Div ("",[],[]) [Plain [Str "Gliding",Space,Str "wrapt",Space,Str "in",Space,Str "a",Space,Str "brown",Space,Str "mantle,",Space,Str "hooded"]],Div ("",[],[]) [Plain [Str "I",Space,Str "do",Space,Str "not",Space,Str "know",Space,Str "whether",Space,Str "a",Space,Str "man",Space,Str "or",Space,Str "a",Space,Str "woman"]],Div ("wasteland-content.xhtml#ln367",[],[]) [Plain [Str "\8213But",Space,Str "who",Space,Str "is",Space,Str "that",Space,Str "on",Space,Str "the",Space,Str "other",Space,Str "side",Space,Str "of",Space,Str "you?",Note [Para [Link [Str "367-77."] ("#wasteland-content.xhtml#ln367",""),Space,Str "Cf.",Space,Str "Hermann",Space,Str "Hesse,",Space,Str "Blick",Space,Str "ins",Space,Str "Chaos:"],BlockQuote [Para [Str "\"Schon",Space,Str "ist",Space,Str "halb",Space,Str "Europa,",Space,Str "schon",Space,Str "ist",Space,Str "zumindest",Space,Str "der",Space,Str "halbe",Space,Str "Osten",Space,Str "Europas",Space,Str "auf",Space,Str "dem",LineBreak,Space,Str "Wege",Space,Str "zum",Space,Str "Chaos,",Space,Str "fhrt",Space,Str "betrunken",Space,Str "im",Space,Str "heiligem",Space,Str "Wahn",Space,Str "am",Space,Str "Abgrund",Space,Str "entlang",LineBreak,Space,Str "und",Space,Str "singt",Space,Str "dazu,",Space,Str "singt",Space,Str "betrunken",Space,Str "und",Space,Str "hymnisch",Space,Str "wie",Space,Str "Dmitri",Space,Str "Karamasoff",Space,Str "sang.",LineBreak,Space,Str "Ueber",Space,Str "diese",Space,Str "Lieder",Space,Str "lacht",Space,Str "der",Space,Str "Bsrger",Space,Str "beleidigt,",Space,Str "der",Space,Str "Heilige",LineBreak,Space,Str "und",Space,Str "Seher",Space,Str "hrt",Space,Str "sie",Space,Str "mit",Space,Str "Trvnen.\""]]]],Div ("",["linegroup"],[]) [Div ("",[],[]) [Plain [Str "What",Space,Str "is",Space,Str "that",Space,Str "sound",Space,Str "high",Space,Str "in",Space,Str "the",Space,Str "air"]],Div ("",[],[]) [Plain [Str "Murmur",Space,Str "of",Space,Str "maternal",Space,Str "lamentation"]],Div ("",[],[]) [Plain [Str "Who",Space,Str "are",Space,Str "those",Space,Str "hooded",Space,Str "hordes",Space,Str "swarming"]],Div ("",[],[]) [Plain [Str "Over",Space,Str "endless",Space,Str "plains,",Space,Str "stumbling",Space,Str "in",Space,Str "cracked",Space,Str "earth",Span ("",["lnum"],[]) [Str "370"]]],Div ("",[],[]) [Plain [Str "Ringed",Space,Str "by",Space,Str "the",Space,Str "flat",Space,Str "horizon",Space,Str "only"]],Div ("",[],[]) [Plain [Str "What",Space,Str "is",Space,Str "the",Space,Str "city",Space,Str "over",Space,Str "the",Space,Str "mountains"]],Div ("",[],[]) [Plain [Str "Cracks",Space,Str "and",Space,Str "reforms",Space,Str "and",Space,Str "bursts",Space,Str "in",Space,Str "the",Space,Str "violet",Space,Str "air"]],Div ("",[],[]) [Plain [Str "Falling",Space,Str "towers"]],Div ("",[],[]) [Plain [Str "Jerusalem",Space,Str "Athens",Space,Str "Alexandria"]],Div ("",[],[]) [Plain [Str "Vienna",Space,Str "London"]],Div ("",[],[]) [Plain [Str "Unreal"]]],Div ("",["linegroup"],[]) [Div ("",[],[]) [Plain [Str "A",Space,Str "woman",Space,Str "drew",Space,Str "her",Space,Str "long",Space,Str "black",Space,Str "hair",Space,Str "out",Space,Str "tight"]],Div ("",[],[]) [Plain [Str "And",Space,Str "fiddled",Space,Str "whisper",Space,Str "music",Space,Str "on",Space,Str "those",Space,Str "strings"]],Div ("",[],[]) [Plain [Str "And",Space,Str "bats",Space,Str "with",Space,Str "baby",Space,Str "faces",Space,Str "in",Space,Str "the",Space,Str "violet",Space,Str "light",Span ("",["lnum"],[]) [Str "380"]]],Div ("",[],[]) [Plain [Str "Whistled,",Space,Str "and",Space,Str "beat",Space,Str "their",Space,Str "wings"]],Div ("",[],[]) [Plain [Str "And",Space,Str "crawled",Space,Str "head",Space,Str "downward",Space,Str "down",Space,Str "a",Space,Str "blackened",Space,Str "wall"]],Div ("",[],[]) [Plain [Str "And",Space,Str "upside",Space,Str "down",Space,Str "in",Space,Str "air",Space,Str "were",Space,Str "towers"]],Div ("",[],[]) [Plain [Str "Tolling",Space,Str "reminiscent",Space,Str "bells,",Space,Str "that",Space,Str "kept",Space,Str "the",Space,Str "hours"]],Div ("",[],[]) [Plain [Str "And",Space,Str "voices",Space,Str "singing",Space,Str "out",Space,Str "of",Space,Str "empty",Space,Str "cisterns",Space,Str "and",Space,Str "exhausted",Space,Str "wells."]]],Div ("",["linegroup"],[]) [Div ("",[],[]) [Plain [Str "In",Space,Str "this",Space,Str "decayed",Space,Str "hole",Space,Str "among",Space,Str "the",Space,Str "mountains"]],Div ("",[],[]) [Plain [Str "In",Space,Str "the",Space,Str "faint",Space,Str "moonlight,",Space,Str "the",Space,Str "grass",Space,Str "is",Space,Str "singing"]],Div ("",[],[]) [Plain [Str "Over",Space,Str "the",Space,Str "tumbled",Space,Str "graves,",Space,Str "about",Space,Str "the",Space,Str "chapel"]],Div ("",[],[]) [Plain [Str "There",Space,Str "is",Space,Str "the",Space,Str "empty",Space,Str "chapel,",Space,Str "only",Space,Str "the",Space,Str "wind's",Space,Str "home."]],Div ("",[],[]) [Plain [Str "It",Space,Str "has",Space,Str "no",Space,Str "windows,",Space,Str "and",Space,Str "the",Space,Str "door",Space,Str "swings,",Span ("",["lnum"],[]) [Str "390"]]],Div ("",[],[]) [Plain [Str "Dry",Space,Str "bones",Space,Str "can",Space,Str "harm",Space,Str "no",Space,Str "one."]],Div ("",[],[]) [Plain [Str "Only",Space,Str "a",Space,Str "cock",Space,Str "stood",Space,Str "on",Space,Str "the",Space,Str "rooftree"]],Div ("",[],[]) [Plain [Str "Co",Space,Str "co",Space,Str "rico",Space,Str "co",Space,Str "co",Space,Str "rico"]],Div ("",[],[]) [Plain [Str "In",Space,Str "a",Space,Str "flash",Space,Str "of",Space,Str "lightning.",Space,Str "Then",Space,Str "a",Space,Str "damp",Space,Str "gust"]],Div ("",[],[]) [Plain [Str "Bringing",Space,Str "rain"]]],Div ("",["linegroup"],[]) [Div ("",[],[]) [Plain [Str "Ganga",Space,Str "was",Space,Str "sunken,",Space,Str "and",Space,Str "the",Space,Str "limp",Space,Str "leaves"]],Div ("",[],[]) [Plain [Str "Waited",Space,Str "for",Space,Str "rain,",Space,Str "while",Space,Str "the",Space,Str "black",Space,Str "clouds"]],Div ("",[],[]) [Plain [Str "Gathered",Space,Str "far",Space,Str "distant,",Space,Str "over",Space,Str "Himavant."]],Div ("",[],[]) [Plain [Str "The",Space,Str "jungle",Space,Str "crouched,",Space,Str "humped",Space,Str "in",Space,Str "silence."]],Div ("",[],[]) [Plain [Str "Then",Space,Str "spoke",Space,Str "the",Space,Str "thunder",Span ("",["lnum"],[]) [Str "400"]]],Div ("",[],[]) [Plain [Str "DA"]],Div ("wasteland-content.xhtml#ln402",[],[]) [Plain [Span ("",[],[("lang","sa")]) [Str "Datta"],Str ":",Space,Str "what",Space,Str "have",Space,Str "we",Space,Str "given?",Note [Para [Link [Str "402."] ("#wasteland-content.xhtml#ln402",""),Space,Quoted DoubleQuote [Str "\"Datta,",Space,Str "dayadhvam,",Space,Str "damyata\""],Space,Str "(Give,",Space,Str "sympathize,",Space,Str "control).",Space,Str "The",Space,Str "fable",Space,Str "of",Space,Str "the",Space,Str "meaning",Space,Str "of",Space,Str "the",Space,Str "Thunder",Space,Str "is",Space,Str "found",Space,Str "in",Space,Str "the",Space,Str "Brihadaranyaka-Upanishad,",Space,Str "5,",Space,Str "1.",Space,Str "A",Space,Str "translation",Space,Str "is",Space,Str "found",Space,Str "in",Space,Str "Deussen's",Space,Str "Sechzig",Space,Str "Upanishads",Space,Str "des",Space,Str "Veda,",Space,Str "p.",Space,Str "489."]]],Div ("",[],[]) [Plain [Str "My",Space,Str "friend,",Space,Str "blood",Space,Str "shaking",Space,Str "my",Space,Str "heart"]],Div ("",[],[]) [Plain [Str "The",Space,Str "awful",Space,Str "daring",Space,Str "of",Space,Str "a",Space,Str "moment's",Space,Str "surrender"]],Div ("",[],[]) [Plain [Str "Which",Space,Str "an",Space,Str "age",Space,Str "of",Space,Str "prudence",Space,Str "can",Space,Str "never",Space,Str "retract"]],Div ("",[],[]) [Plain [Str "By",Space,Str "this,",Space,Str "and",Space,Str "this",Space,Str "only,",Space,Str "we",Space,Str "have",Space,Str "existed"]],Div ("",[],[]) [Plain [Str "Which",Space,Str "is",Space,Str "not",Space,Str "to",Space,Str "be",Space,Str "found",Space,Str "in",Space,Str "our",Space,Str "obituaries"]],Div ("wasteland-content.xhtml#ln408",[],[]) [Plain [Str "Or",Space,Str "in",Space,Str "memories",Space,Str "draped",Space,Str "by",Space,Str "the",Space,Str "beneficent",Space,Str "spider",Note [Para [Link [Str "408."] ("#wasteland-content.xhtml#ln408",""),Space,Str "Cf.",Space,Str "Webster,",Space,Str "The",Space,Str "White",Space,Str "Devil,",Space,Str "v.",Space,Str "vi:"],BlockQuote [Para [Str "\".",Space,Str ".",Space,Str ".",Space,Str "they'll",Space,Str "remarry",LineBreak,Space,Str "Ere",Space,Str "the",Space,Str "worm",Space,Str "pierce",Space,Str "your",Space,Str "winding-sheet,",Space,Str "ere",Space,Str "the",Space,Str "spider",LineBreak,Space,Str "Make",Space,Str "a",Space,Str "thin",Space,Str "curtain",Space,Str "for",Space,Str "your",Space,Str "epitaphs.\""]]]],Div ("",[],[]) [Plain [Str "Or",Space,Str "under",Space,Str "seals",Space,Str "broken",Space,Str "by",Space,Str "the",Space,Str "lean",Space,Str "solicitor"]],Div ("",[],[]) [Plain [Str "In",Space,Str "our",Space,Str "empty",Space,Str "rooms",Span ("",["lnum"],[]) [Str "410"]]],Div ("",[],[]) [Plain [Str "DA"]],Div ("wasteland-content.xhtml#ln412",[],[]) [Plain [Span ("",[],[("lang","sa")]) [Str "Dayadhvam"],Str ":",Space,Str "I",Space,Str "have",Space,Str "heard",Space,Str "the",Space,Str "key",Note [Para [Link [Str "412."] ("#wasteland-content.xhtml#ln412",""),Space,Str "Cf.",Space,Str "Inferno,",Space,Str "xxxiii.",Space,Str "46:"],BlockQuote [Para [Str "\"ed",Space,Str "io",Space,Str "sentii",Space,Str "chiavar",Space,Str "l'uscio",Space,Str "di",Space,Str "sotto",LineBreak,Space,Str "all'orribile",Space,Str "torre.\""]],Para [Str "Also",Space,Str "F.",Space,Str "H.",Space,Str "Bradley,",Space,Str "Appearance",Space,Str "and",Space,Str "Reality,",Space,Str "p.",Space,Str "346:"],BlockQuote [Para [Str "\"My",Space,Str "external",Space,Str "sensations",Space,Str "are",Space,Str "no",Space,Str "less",Space,Str "private",Space,Str "to",Space,Str "myself",Space,Str "than",Space,Str "are",Space,Str "my",Space,Str "thoughts",Space,Str "or",Space,Str "my",Space,Str "feelings.",Space,Str "In",Space,Str "either",Space,Str "case",Space,Str "my",Space,Str "experience",Space,Str "falls",Space,Str "within",Space,Str "my",Space,Str "own",Space,Str "circle,",Space,Str "a",Space,Str "circle",Space,Str "closed",Space,Str "on",Space,Str "the",Space,Str "outside;",Space,Str "and,",Space,Str "with",Space,Str "all",Space,Str "its",Space,Str "elements",Space,Str "alike,",Space,Str "every",Space,Str "sphere",Space,Str "is",Space,Str "opaque",Space,Str "to",Space,Str "the",Space,Str "others",Space,Str "which",Space,Str "surround",Space,Str "it.",Space,Str ".",Space,Str ".",Space,Str ".",Space,Str "In",Space,Str "brief,",Space,Str "regarded",Space,Str "as",Space,Str "an",Space,Str "existence",Space,Str "which",Space,Str "appears",Space,Str "in",Space,Str "a",Space,Str "soul,",Space,Str "the",Space,Str "whole",Space,Str "world",Space,Str "for",Space,Str "each",Space,Str "is",Space,Str "peculiar",Space,Str "and",Space,Str "private",Space,Str "to",Space,Str "that",Space,Str "soul.\""]]]],Div ("",[],[]) [Plain [Str "Turn",Space,Str "in",Space,Str "the",Space,Str "door",Space,Str "once",Space,Str "and",Space,Str "turn",Space,Str "once",Space,Str "only"]],Div ("",[],[]) [Plain [Str "We",Space,Str "think",Space,Str "of",Space,Str "the",Space,Str "key,",Space,Str "each",Space,Str "in",Space,Str "his",Space,Str "prison"]],Div ("",[],[]) [Plain [Str "Thinking",Space,Str "of",Space,Str "the",Space,Str "key,",Space,Str "each",Space,Str "confirms",Space,Str "a",Space,Str "prison"]],Div ("",[],[]) [Plain [Str "Only",Space,Str "at",Space,Str "nightfall,",Space,Str "aetherial",Space,Str "rumours"]],Div ("",[],[]) [Plain [Str "Revive",Space,Str "for",Space,Str "a",Space,Str "moment",Space,Str "a",Space,Str "broken",Space,Str "Coriolanus"]],Div ("",[],[]) [Plain [Str "DA"]],Div ("",[],[]) [Plain [Span ("",[],[("lang","sa")]) [Str "Damyata"],Str ":",Space,Str "The",Space,Str "boat",Space,Str "responded"]],Div ("",[],[]) [Plain [Str "Gaily,",Space,Str "to",Space,Str "the",Space,Str "hand",Space,Str "expert",Space,Str "with",Space,Str "sail",Space,Str "and",Space,Str "oar",Span ("",["lnum"],[]) [Str "420"]]],Div ("",[],[]) [Plain [Str "The",Space,Str "sea",Space,Str "was",Space,Str "calm,",Space,Str "your",Space,Str "heart",Space,Str "would",Space,Str "have",Space,Str "responded"]],Div ("",[],[]) [Plain [Str "Gaily,",Space,Str "when",Space,Str "invited,",Space,Str "beating",Space,Str "obedient"]],Div ("",[],[]) [Plain [Str "To",Space,Str "controlling",Space,Str "hands"]]],Div ("",["linegroup"],[]) [Div ("",["indent"],[]) [Plain [Str "I",Space,Str "sat",Space,Str "upon",Space,Str "the",Space,Str "shore"]],Div ("wasteland-content.xhtml#ln425",[],[]) [Plain [Str "Fishing,",Space,Str "with",Space,Str "the",Space,Str "arid",Space,Str "plain",Space,Str "behind",Space,Str "me",Note [Para [Link [Str "425."] ("#wasteland-content.xhtml#ln425",""),Space,Str "V.",Space,Str "Weston,",Space,Str "From",Space,Str "Ritual",Space,Str "to",Space,Str "Romance;",Space,Str "chapter",Space,Str "on",Space,Str "the",Space,Str "Fisher",Space,Str "King."]]],Div ("",[],[]) [Plain [Str "Shall",Space,Str "I",Space,Str "at",Space,Str "least",Space,Str "set",Space,Str "my",Space,Str "lands",Space,Str "in",Space,Str "order?"]],Div ("",[],[]) [Plain [Str "London",Space,Str "Bridge",Space,Str "is",Space,Str "falling",Space,Str "down",Space,Str "falling",Space,Str "down",Space,Str "falling",Space,Str "down"]],Div ("wasteland-content.xhtml#ln428",[],[("lang","it")]) [Plain [Emph [Str "Poi",Space,Str "s'ascose",Space,Str "nel",Space,Str "foco",Space,Str "che",Space,Str "gli",Space,Str "affina"],Space,Note [Para [Link [Str "428."] ("#wasteland-content.xhtml#ln428",""),Space,Str "V.",Space,Str "Purgatorio,",Space,Str "xxvi.",Space,Str "148."],BlockQuote [Para [Str "\"'Ara",Space,Str "vos",Space,Str "prec",Space,Str "per",Space,Str "aquella",Space,Str "valor",LineBreak,Space,Str "'que",Space,Str "vos",Space,Str "guida",Space,Str "al",Space,Str "som",Space,Str "de",Space,Str "l'escalina,",LineBreak,Space,Str "'sovegna",Space,Str "vos",Space,Str "a",Space,Str "temps",Space,Str "de",Space,Str "ma",Space,Str "dolor.'",LineBreak,Space,Str "Poi",Space,Str "s'ascose",Space,Str "nel",Space,Str "foco",Space,Str "che",Space,Str "gli",Space,Str "affina.\""]]]],Div ("wasteland-content.xhtml#ln429",[],[]) [Plain [Span ("",[],[("lang","it")]) [Space,Emph [Str "Quando",Space,Str "fiam",Space,Str "ceu",Space,Str "chelidon"],Space],Space,Str "-",Space,Str "O",Space,Str "swallow",Space,Str "swallow",Note [Para [Link [Str "429."] ("#wasteland-content.xhtml#ln429",""),Space,Str "V.",Space,Str "Pervigilium",Space,Str "Veneris.",Space,Str "Cf.",Space,Str "Philomela",Space,Str "in",Space,Str "Parts",Space,Str "II",Space,Str "and",Space,Str "III."]]],Div ("wasteland-content.xhtml#ln430",[],[("lang","fr")]) [Plain [Emph [Str "Le",Space,Str "Prince",Space,Str "d'Aquitaine",Space,Str "a",Space,Str "la",Space,Str "tour",Space,Str "abolie"],Space,Note [Para [Link [Str "430."] ("#wasteland-content.xhtml#ln430",""),Space,Str "V.",Space,Str "Gerard",Space,Str "de",Space,Str "Nerval,",Space,Str "Sonnet",Space,Str "El",Space,Str "Desdichado."]]],Div ("",[],[]) [Plain [Str "These",Space,Str "fragments",Space,Str "I",Space,Str "have",Space,Str "shored",Space,Str "against",Space,Str "my",Space,Str "ruins"]],Div ("wasteland-content.xhtml#ln432",[],[]) [Plain [Str "Why",Space,Str "then",Space,Str "Ile",Space,Str "fit",Space,Str "you.",Space,Str "Hieronymo's",Space,Str "mad",Space,Str "againe.",Note [Para [Link [Str "432."] ("#wasteland-content.xhtml#ln432",""),Space,Str "V.",Space,Str "Kyd's",Space,Str "Spanish",Space,Str "Tragedy."]]],Div ("",[],[("lang","sa")]) [Plain [Str "Datta.",Space,Str "Dayadhvam.",Space,Str "Damyata."]],Div ("wasteland-content.xhtml#ln434",["linegroup","indent"],[]) [Plain [Span ("",[],[("lang","sa")]) [Str "Shantih",Space,Str "shantih",Space,Str "shantih",Note [Para [Link [Str "434."] ("#wasteland-content.xhtml#ln434",""),Space,Str "Shantih.",Space,Str "Repeated",Space,Str "as",Space,Str "here,",Space,Str "a",Space,Str "formal",Space,Str "ending",Space,Str "to",Space,Str "an",Space,Str "Upanishad.",Space,Str "'The",Space,Str "Peace",Space,Str "which",Space,Str "passeth",Space,Str "understanding'",Space,Str "is",Space,Str "a",Space,Str "feeble",Space,Str "translation",Space,Str "of",Space,Str "the",Space,Str "content",Space,Str "of",Space,Str "this",Space,Str "word."]]]],RawBlock (Format "html") "<section type=\"backmatter\" id=\"backmatter\">",RawBlock (Format "html") "<section type=\"rearnotes\" id=\"rearnotes\">",Header 2 ("",[],[]) [Str "NOTES",Space,Str "ON",Space,Str "\"THE",Space,Str "WASTE",Space,Str "LAND\""],Para [Str "Not",Space,Str "only",Space,Str "the",Space,Str "title,",Space,Str "but",Space,Str "the",Space,Str "plan",Space,Str "and",Space,Str "a",Space,Str "good",Space,Str "deal",Space,Str "of",Space,Str "the",Space,Str "incidental",Space,Str "symbolism",Space,Str "of",Space,Str "the",Space,Str "poem",Space,Str "were",Space,Str "suggested",Space,Str "by",Space,Str "Miss",Space,Str "Jessie",Space,Str "L.",Space,Str "Weston's",Space,Str "book",Space,Str "on",Space,Str "the",Space,Str "Grail",Space,Str "legend:",Space,Str "From",Space,Str "Ritual",Space,Str "to",Space,Str "Romance"],Para [Str "Indeed,",Space,Str "so",Space,Str "deeply",Space,Str "am",Space,Str "I",Space,Str "indebted,",Space,Str "Miss",Space,Str "Weston's",Space,Str "book",Space,Str "will",Space,Str "elucidate",Space,Str "the",Space,Str "difficulties",Space,Str "of",Space,Str "the",Space,Str "poem",Space,Str "much",Space,Str "better",Space,Str "than",Space,Str "my",Space,Str "notes",Space,Str "can",Space,Str "do;",Space,Str "and",Space,Str "I",Space,Str "recommend",Space,Str "it",Space,Str "(apart",Space,Str "from",Space,Str "the",Space,Str "great",Space,Str "interest",Space,Str "of",Space,Str "the",Space,Str "book",Space,Str "itself)",Space,Str "to",Space,Str "any",Space,Str "who",Space,Str "think",Space,Str "such",Space,Str "elucidation",Space,Str "of",Space,Str "the",Space,Str "poem",Space,Str "worth",Space,Str "the",Space,Str "trouble.",Space,Str "To",Space,Str "another",Space,Str "work",Space,Str "of",Space,Str "anthropology",Space,Str "I",Space,Str "am",Space,Str "indebted",Space,Str "in",Space,Str "general,",Space,Str "one",Space,Str "which",Space,Str "has",Space,Str "influenced",Space,Str "our",Space,Str "generation",Space,Str "profoundly;",Space,Str "I",Space,Str "mean",Space,Str "The",Space,Str "Golden",Space,Str "Bough;",Space,Str "I",Space,Str "have",Space,Str "used",Space,Str "especially",Space,Str "the",Space,Str "two",Space,Str "volumes",Space,Str "Adonis,",Space,Str "Attis,",Space,Str "Osiris.",Space,Str "Anyone",Space,Str "who",Space,Str "is",Space,Str "acquainted",Space,Str "with",Space,Str "these",Space,Str "works",Space,Str "will",Space,Str "immediately",Space,Str "recognise",Space,Str "in",Space,Str "the",Space,Str "poem",Space,Str "certain",Space,Str "references",Space,Str "to",Space,Str "vegetation",Space,Str "ceremonies."],RawBlock (Format "html") "<section>",Header 3 ("",[],[]) [Str "I.",Space,Str "THE",Space,Str "BURIAL",Space,Str "OF",Space,Str "THE",Space,Str "DEAD"],RawBlock (Format "html") "</section>",RawBlock (Format "html") "<section>",Header 3 ("",[],[]) [Str "II.",Space,Str "A",Space,Str "GAME",Space,Str "OF",Space,Str "CHESS"],RawBlock (Format "html") "</section>",RawBlock (Format "html") "<section>",Header 3 ("",[],[]) [Str "III.",Space,Str "THE",Space,Str "FIRE",Space,Str "SERMON"],RawBlock (Format "html") "</section>",RawBlock (Format "html") "<section>",Header 3 ("",[],[]) [Str "V.",Space,Str "WHAT",Space,Str "THE",Space,Str "THUNDER",Space,Str "SAID"],Para [Str "In",Space,Str "the",Space,Str "first",Space,Str "part",Space,Str "of",Space,Str "Part",Space,Str "V",Space,Str "three",Space,Str "themes",Space,Str "are",Space,Str "employed:",Space,Str "the",Space,Str "journey",Space,Str "to",Space,Str "Emmaus,",Space,Str "the",Space,Str "approach",Space,Str "to",Space,Str "the",Space,Str "Chapel",Space,Str "Perilous",Space,Str "(see",Space,Str "Miss",Space,Str "Weston's",Space,Str "book)",Space,Str "and",Space,Str "the",Space,Str "present",Space,Str "decay",Space,Str "of",Space,Str "eastern",Space,Str "Europe."],RawBlock (Format "html") "</section>",RawBlock (Format "html") "</section>",RawBlock (Format "html") "</section>"]]]]]]]]]]]]]]]]]]]]]]]]]]]]]]]]]]]]]]]]]]]]]]]]]]]]]]]]]]] diff --git a/tests/fb2.images-embedded.fb2 b/tests/fb2.images-embedded.fb2 deleted file mode 100644 index 1954232da..000000000 --- a/tests/fb2.images-embedded.fb2 +++ /dev/null @@ -1,2 +0,0 @@ -<?xml version="1.0" encoding="UTF-8"?> -<FictionBook xmlns="http://www.gribuser.ru/xml/fictionbook/2.0" xmlns:l="http://www.w3.org/1999/xlink"><description><title-info /><document-info><program-used>pandoc</program-used></document-info></description><body><title><p /></title><annotation><p></p></annotation><section><p><image l:href="#image1" l:type="inlineImageType" alt="This image was embedded using data URI scheme" /></p><p>This image was embedded using data URI scheme</p></section></body><binary id="image1" content-type="image/png">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</binary></FictionBook> diff --git a/tests/fb2.basic.fb2 b/tests/fb2/basic.fb2 index 14b03fbea..14b03fbea 100644 --- a/tests/fb2.basic.fb2 +++ b/tests/fb2/basic.fb2 diff --git a/tests/fb2.basic.markdown b/tests/fb2/basic.markdown index b798b13a4..b798b13a4 100644 --- a/tests/fb2.basic.markdown +++ b/tests/fb2/basic.markdown diff --git a/tests/fb2/images-embedded.fb2 b/tests/fb2/images-embedded.fb2 new file mode 100644 index 000000000..8c22efad3 --- /dev/null +++ b/tests/fb2/images-embedded.fb2 @@ -0,0 +1,2 @@ +<?xml version="1.0" encoding="UTF-8"?> +<FictionBook xmlns="http://www.gribuser.ru/xml/fictionbook/2.0" xmlns:l="http://www.w3.org/1999/xlink"><description><title-info /><document-info><program-used>pandoc</program-used></document-info></description><body><title><p /></title><annotation><p></p></annotation><section><image l:href="#image1" l:type="inlineImageType" alt="This image was embedded using data URI scheme" /><p>This image was embedded using data URI scheme</p></section></body><binary id="image1" content-type="image/png">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</binary></FictionBook> diff --git a/tests/fb2.images-embedded.html b/tests/fb2/images-embedded.html index 19c8f7c7a..19c8f7c7a 100644 --- a/tests/fb2.images-embedded.html +++ b/tests/fb2/images-embedded.html diff --git a/tests/fb2.images.fb2 b/tests/fb2/images.fb2 index 8b783edf5..8b783edf5 100644 --- a/tests/fb2.images.fb2 +++ b/tests/fb2/images.fb2 diff --git a/tests/fb2.images.markdown b/tests/fb2/images.markdown index 419be7c44..e7d3cc1e6 100644 --- a/tests/fb2.images.markdown +++ b/tests/fb2/images.markdown @@ -4,10 +4,10 @@ Small inline image: ![alt text a small PNG image][inline-image]. Paragraph image: - +  A missing image inline: . -[inline-image]: fb2.test-small.png +[inline-image]: fb2/test-small.png diff --git a/tests/fb2.math.fb2 b/tests/fb2/math.fb2 index 5a69556c1..5a69556c1 100644 --- a/tests/fb2.math.fb2 +++ b/tests/fb2/math.fb2 diff --git a/tests/fb2.math.markdown b/tests/fb2/math.markdown index a88fb6cf1..a88fb6cf1 100644 --- a/tests/fb2.math.markdown +++ b/tests/fb2/math.markdown diff --git a/tests/fb2.test-small.png b/tests/fb2/test-small.png Binary files differindex 16e177219..16e177219 100644 --- a/tests/fb2.test-small.png +++ b/tests/fb2/test-small.png diff --git a/tests/fb2.test.jpg b/tests/fb2/test.jpg Binary files differindex 99d57db17..99d57db17 100644 --- a/tests/fb2.test.jpg +++ b/tests/fb2/test.jpg diff --git a/tests/fb2.titles.fb2 b/tests/fb2/titles.fb2 index d8fc1e424..d8fc1e424 100644 --- a/tests/fb2.titles.fb2 +++ b/tests/fb2/titles.fb2 diff --git a/tests/fb2.titles.markdown b/tests/fb2/titles.markdown index cc3d0e0d0..cc3d0e0d0 100644 --- a/tests/fb2.titles.markdown +++ b/tests/fb2/titles.markdown diff --git a/tests/haddock-reader.haddock b/tests/haddock-reader.haddock index c4f6d6c36..c3ef0c9fc 100644 --- a/tests/haddock-reader.haddock +++ b/tests/haddock-reader.haddock @@ -18,10 +18,10 @@ This is a code block: This is another code block: @ - f x = x + x. - The \@...\@ code block /interprets markup normally/. - "Module.Foo" - \"Hello World\" +f x = x + x. +The \@...\@ code block /interprets markup normally/. +"Module.Foo" +\"Hello World\" @ Haddock supports REPL examples: @@ -42,21 +42,21 @@ This is a reference to the "Foo" module. This is a bulleted list: - * first item + * first item - * second item + * second item This is an enumerated list: - (1) first item + (1) first item - 2. second item + 2. second item This is a definition list: - [@foo@] The description of @foo@. + [@foo@] The description of @foo@. - [@bar@] The description of @bar@. + [@bar@] The description of @bar@. Here is a link: <http://haskell.org> diff --git a/tests/haddock-reader.native b/tests/haddock-reader.native index 877719b50..b62189046 100644 --- a/tests/haddock-reader.native +++ b/tests/haddock-reader.native @@ -4,14 +4,14 @@ Pandoc (Meta {unMeta = fromList []}) ,Para [Str "*",Space,Str "This",Space,Str "is",Space,Str "a",Space,Str "paragraph,",Space,Str "not",Space,Str "a",Space,Str "list",Space,Str "item.",Space,Str ">",Space,Str "This",Space,Str "sentence",Space,Str "is",Space,Str "not",Space,Str "code.",Space,Str ">>>",Space,Str "This",Space,Str "is",Space,Str "not",Space,Str "an",Space,Str "example."] ,Para [Str "The",Space,Str "references",Space,Str "\955,",Space,Str "\955",Space,Str "and",Space,Str "\955",Space,Str "all",Space,Str "represent",Space,Str "the",Space,Str "lower-case",Space,Str "letter",Space,Str "lambda."] ,Para [Str "This",Space,Str "is",Space,Str "a",Space,Str "code",Space,Str "block:"] -,CodeBlock ("",["haskell"],[]) " map :: (a -> b) -> [a] -> [b]\n map _ [] = []\n map f (x:xs) = f x : map f xs\n" +,CodeBlock ("",[],[]) "map :: (a -> b) -> [a] -> [b]\nmap _ [] = []\nmap f (x:xs) = f x : map f xs" ,Para [Str "This",Space,Str "is",Space,Str "another",Space,Str "code",Space,Str "block:"] -,Para [Code ("",[],[]) "f",Space,Code ("",[],[]) "x",Space,Code ("",[],[]) "=",Space,Code ("",[],[]) "x",Space,Code ("",[],[]) "+",Space,Code ("",[],[]) "x.",Space,Code ("",[],[]) "The",Space,Code ("",[],[]) "@...@",Space,Code ("",[],[]) "code",Space,Code ("",[],[]) "block",Space,Emph [Code ("",[],[]) "interprets markup normally"],Code ("",[],[]) ".",Space,Code ("",["haskell"],[]) "Module.Foo",Space,Code ("",[],[]) "\"Hello",Space,Code ("",[],[]) "World\""] +,Para [Code ("",[],[]) "f x = x + x.",LineBreak,Code ("",[],[]) "The @...@ code block ",Emph [Code ("",[],[]) "interprets markup normally"],Code ("",[],[]) ".",Code ("",["haskell","module"],[]) "Module.Foo",Code ("",[],[]) "",LineBreak,Code ("",[],[]) "\"Hello World\""] ,Para [Str "Haddock",Space,Str "supports",Space,Str "REPL",Space,Str "examples:"] -,Para [Code ("",["haskell","expr"],[]) "fib 10",LineBreak,Code ("",["result"],[]) "55"] -,Para [Code ("",["haskell","expr"],[]) "putStrLn \"foo\\nbar\"",LineBreak,Code ("",["result"],[]) "foo",LineBreak,Code ("",["result"],[]) "bar"] -,Para [Str "That",Space,Str "was",Space,Emph [Str "really cool"],Str "!",Space,Str "I",Space,Str "had",Space,Str "no",Space,Str "idea",Space,Code ("",[],[]) "fib",Space,Code ("",[],[]) "10",Space,Code ("",[],[]) "=",Space,Code ("",[],[]) "55",Str "."] -,Para [Str "This",Space,Str "module",Space,Str "defines",Space,Str "the",Space,Str "type",Space,Code ("",["haskell"],[]) "T",Str ".",Space,Str "The",Space,Str "identifier",Space,Code ("",["haskell"],[]) "M.T",Space,Str "is",Space,Str "not",Space,Str "in",Space,Str "scope",Space,Str "I",Space,Str "don't",Space,Str "have",Space,Str "to",Space,Str "escape",Space,Str "my",Space,Str "apostrophes;",Space,Str "great,",Space,Str "isn't",Space,Str "it?",Space,Str "This",Space,Str "is",Space,Str "a",Space,Str "reference",Space,Str "to",Space,Str "the",Space,Code ("",["haskell"],[]) "Foo",Space,Str "module."] +,Para [Code ("",["prompt"],[]) ">>>",Space,Code ("",["haskell","expr"],[]) "fib 10",LineBreak,Code ("",["result"],[]) "55"] +,Para [Code ("",["prompt"],[]) ">>>",Space,Code ("",["haskell","expr"],[]) "putStrLn \"foo\\nbar\"",LineBreak,Code ("",["result"],[]) "foo",LineBreak,Code ("",["result"],[]) "bar"] +,Para [Str "That",Space,Str "was",Space,Emph [Str "really",Space,Str "cool"],Str "!",Space,Str "I",Space,Str "had",Space,Str "no",Space,Str "idea",Space,Code ("",[],[]) "fib 10 = 55",Str "."] +,Para [Str "This",Space,Str "module",Space,Str "defines",Space,Str "the",Space,Str "type",Space,Code ("",["haskell","identifier"],[]) "T",Str ".",Space,Str "The",Space,Str "identifier",Space,Code ("",["haskell","identifier"],[]) "M.T",Space,Str "is",Space,Str "not",Space,Str "in",Space,Str "scope",Space,Str "I",Space,Str "don't",Space,Str "have",Space,Str "to",Space,Str "escape",Space,Str "my",Space,Str "apostrophes;",Space,Str "great,",Space,Str "isn't",Space,Str "it?",Space,Str "This",Space,Str "is",Space,Str "a",Space,Str "reference",Space,Str "to",Space,Str "the",Space,Code ("",["haskell","module"],[]) "Foo",Space,Str "module."] ,Para [Str "This",Space,Str "is",Space,Str "a",Space,Str "bulleted",Space,Str "list:"] ,BulletList [[Para [Str "first",Space,Str "item"]] @@ -23,9 +23,9 @@ Pandoc (Meta {unMeta = fromList []}) ,Para [Str "This",Space,Str "is",Space,Str "a",Space,Str "definition",Space,Str "list:"] ,DefinitionList [([Code ("",[],[]) "foo"], - [[Plain [Str "The",Space,Str "description",Space,Str "of",Space,Code ("",[],[]) "foo",Str "."]]]) + [[Para [Str "The",Space,Str "description",Space,Str "of",Space,Code ("",[],[]) "foo",Str "."]]]) ,([Code ("",[],[]) "bar"], - [[Plain [Str "The",Space,Str "description",Space,Str "of",Space,Code ("",[],[]) "bar",Str "."]]])] + [[Para [Str "The",Space,Str "description",Space,Str "of",Space,Code ("",[],[]) "bar",Str "."]]])] ,Para [Str "Here",Space,Str "is",Space,Str "a",Space,Str "link:",Space,Link [Str "http://haskell.org"] ("http://haskell.org","http://haskell.org")] ,Para [Link [Str "Haskell"] ("http://haskell.org","http://haskell.org"),Space,Str "is",Space,Str "a",Space,Str "fun",Space,Str "language!"] ,Para [Link [Str "Click",Space,Str "Here!"] ("http://example.com","http://example.com")]] diff --git a/tests/html-reader.html b/tests/html-reader.html index 69bb9ba8a..e9ba2a68b 100644 --- a/tests/html-reader.html +++ b/tests/html-reader.html @@ -302,12 +302,14 @@ These should not be escaped: \$ \\ \> \[ \{ <h1>Inline Markup</h1> <p>This is <em>emphasized</em>, and so <em>is this</em>.</p> <p>This is <strong>strong</strong>, and so <strong>is this</strong>.</p> +<p>Empty <strong></strong> and <em></em>. <p>An <em><a href="/url">emphasized link</a></em>.</p> <p><strong><em>This is strong and em.</em></strong></p> <p>So is <strong><em>this</em></strong> word.</p> <p><strong><em>This is strong and em.</em></strong></p> <p>So is <strong><em>this</em></strong> word.</p> <p>This is code: <code>></code>, <code>$</code>, <code>\</code>, <code>\$</code>, <code><html></code>.</p> +<p>This is <span style="font-variant: small-caps;">small caps</span>.</p> <hr /> <h1>Smart quotes, ellipses, dashes</h1> <p>"Hello," said the spider. "'Shelob' is my name."</p> @@ -426,5 +428,27 @@ An e-mail address: nobody [at] nowhere.net<blockquote> <pre><code> { <code> } </code></pre> <p>If you want, you can use a caret at the beginning of every line, as with blockquotes, but all that you need is a caret at the beginning of the first line of the block and any preceding blank lines.</p> +<p>text<em> Leading space</em></p> +<p><em>Trailing space </em>text</p> +<p>text<em> Leading spaces</em></p> +<p><em>Trailing spaces </em>text</p> +<h1>Tables</h1> +<table> + <tr> + <th>X</th> + <th>Y</th> + <th>Z</th> + </tr> + <tr> + <td>1</td> + <td>2</td> + <td>3</td> + </tr> + <tr> + <td>4</td> + <td>5</td> + <td>6</td> + </tr> +</table> </body> </html> diff --git a/tests/html-reader.native b/tests/html-reader.native index e80905729..aef6e40fc 100644 --- a/tests/html-reader.native +++ b/tests/html-reader.native @@ -1,5 +1,5 @@ Pandoc (Meta {unMeta = fromList [("generator",MetaInlines [Str "pandoc"]),("title",MetaInlines [Str "Pandoc",Space,Str "Test",Space,Str "Suite"])]}) -[Para [Str "This",Space,Str "is",Space,Str "a",Space,Str "set",Space,Str "of",Space,Str "tests",Space,Str "for",Space,Str "pandoc",Str ".",Space,Str "Most",Space,Str "of",Space,Str "them",Space,Str "are",Space,Str "adapted",Space,Str "from",Space,Str "John",Space,Str "Gruber",Str "'",Str "s",Space,Str "markdown",Space,Str "test",Space,Str "suite",Str "."] +[Para [Str "This",Space,Str "is",Space,Str "a",Space,Str "set",Space,Str "of",Space,Str "tests",Space,Str "for",Space,Str "pandoc.",Space,Str "Most",Space,Str "of",Space,Str "them",Space,Str "are",Space,Str "adapted",Space,Str "from",Space,Str "John",Space,Str "Gruber's",Space,Str "markdown",Space,Str "test",Space,Str "suite."] ,HorizontalRule ,Header 1 ("",[],[]) [Str "Headers"] ,Header 2 ("",[],[]) [Str "Level",Space,Str "2",Space,Str "with",Space,Str "an",Space,Link [Str "embedded",Space,Str "link"] ("/url","")] @@ -14,15 +14,15 @@ Pandoc (Meta {unMeta = fromList [("generator",MetaInlines [Str "pandoc"]),("titl ,Para [Str "with",Space,Str "no",Space,Str "blank",Space,Str "line"] ,HorizontalRule ,Header 1 ("",[],[]) [Str "Paragraphs"] -,Para [Str "Here",Str "'",Str "s",Space,Str "a",Space,Str "regular",Space,Str "paragraph",Str "."] -,Para [Str "In",Space,Str "Markdown",Space,Str "1",Str ".",Str "0",Str ".",Str "0",Space,Str "and",Space,Str "earlier",Str ".",Space,Str "Version",Space,Str "8",Str ".",Space,Str "This",Space,Str "line",Space,Str "turns",Space,Str "into",Space,Str "a",Space,Str "list",Space,Str "item",Str ".",Space,Str "Because",Space,Str "a",Space,Str "hard",Str "-",Str "wrapped",Space,Str "line",Space,Str "in",Space,Str "the",Space,Str "middle",Space,Str "of",Space,Str "a",Space,Str "paragraph",Space,Str "looked",Space,Str "like",Space,Str "a",Space,Str "list",Space,Str "item",Str "."] -,Para [Str "Here",Str "'",Str "s",Space,Str "one",Space,Str "with",Space,Str "a",Space,Str "bullet",Str ".",Space,Str "*",Space,Str "criminey",Str "."] -,Para [Str "There",Space,Str "should",Space,Str "be",Space,Str "a",Space,Str "hard",Space,Str "line",Space,Str "break",LineBreak,Space,Str "here",Str "."] +,Para [Str "Here's",Space,Str "a",Space,Str "regular",Space,Str "paragraph."] +,Para [Str "In",Space,Str "Markdown",Space,Str "1.0.0",Space,Str "and",Space,Str "earlier.",Space,Str "Version",Space,Str "8.",Space,Str "This",Space,Str "line",Space,Str "turns",Space,Str "into",Space,Str "a",Space,Str "list",Space,Str "item.",Space,Str "Because",Space,Str "a",Space,Str "hard-wrapped",Space,Str "line",Space,Str "in",Space,Str "the",Space,Str "middle",Space,Str "of",Space,Str "a",Space,Str "paragraph",Space,Str "looked",Space,Str "like",Space,Str "a",Space,Str "list",Space,Str "item."] +,Para [Str "Here's",Space,Str "one",Space,Str "with",Space,Str "a",Space,Str "bullet.",Space,Str "*",Space,Str "criminey."] +,Para [Str "There",Space,Str "should",Space,Str "be",Space,Str "a",Space,Str "hard",Space,Str "line",Space,Str "break",LineBreak,Space,Str "here."] ,HorizontalRule ,Header 1 ("",[],[]) [Str "Block",Space,Str "Quotes"] -,Para [Str "E",Str "-",Str "mail",Space,Str "style:"] +,Para [Str "E-mail",Space,Str "style:"] ,BlockQuote - [Para [Str "This",Space,Str "is",Space,Str "a",Space,Str "block",Space,Str "quote",Str ".",Space,Str "It",Space,Str "is",Space,Str "pretty",Space,Str "short",Str "."]] + [Para [Str "This",Space,Str "is",Space,Str "a",Space,Str "block",Space,Str "quote.",Space,Str "It",Space,Str "is",Space,Str "pretty",Space,Str "short."]] ,BlockQuote [Para [Str "Code",Space,Str "in",Space,Str "a",Space,Str "block",Space,Str "quote:"] ,CodeBlock ("",[],[]) "sub status {\n print \"working\";\n}" @@ -35,8 +35,8 @@ Pandoc (Meta {unMeta = fromList [("generator",MetaInlines [Str "pandoc"]),("titl [Para [Str "nested"]] ,BlockQuote [Para [Str "nested"]]] -,Para [Str "This",Space,Str "should",Space,Str "not",Space,Str "be",Space,Str "a",Space,Str "block",Space,Str "quote:",Space,Str "2",Space,Str ">",Space,Str "1",Str "."] -,Para [Str "Box",Str "-",Str "style:"] +,Para [Str "This",Space,Str "should",Space,Str "not",Space,Str "be",Space,Str "a",Space,Str "block",Space,Str "quote:",Space,Str "2",Space,Str ">",Space,Str "1."] +,Para [Str "Box-style:"] ,BlockQuote [Para [Str "Example:"] ,CodeBlock ("",[],[]) "sub status {\n print \"working\";\n}"] @@ -44,12 +44,12 @@ Pandoc (Meta {unMeta = fromList [("generator",MetaInlines [Str "pandoc"]),("titl [OrderedList (1,DefaultStyle,DefaultDelim) [[Plain [Str "do",Space,Str "laundry"]] ,[Plain [Str "take",Space,Str "out",Space,Str "the",Space,Str "trash"]]]] -,Para [Str "Here",Str "'",Str "s",Space,Str "a",Space,Str "nested",Space,Str "one:"] +,Para [Str "Here's",Space,Str "a",Space,Str "nested",Space,Str "one:"] ,BlockQuote [Para [Str "Joe",Space,Str "said:"] ,BlockQuote - [Para [Str "Don",Str "'",Str "t",Space,Str "quote",Space,Str "me",Str "."]]] -,Para [Str "And",Space,Str "a",Space,Str "following",Space,Str "paragraph",Str "."] + [Para [Str "Don't",Space,Str "quote",Space,Str "me."]]] +,Para [Str "And",Space,Str "a",Space,Str "following",Space,Str "paragraph."] ,HorizontalRule ,Header 1 ("",[],[]) [Str "Code",Space,Str "Blocks"] ,Para [Str "Code:"] @@ -112,10 +112,10 @@ Pandoc (Meta {unMeta = fromList [("generator",MetaInlines [Str "pandoc"]),("titl ,[Para [Str "Three"]]] ,Para [Str "Multiple",Space,Str "paragraphs:"] ,OrderedList (1,DefaultStyle,DefaultDelim) - [[Para [Str "Item",Space,Str "1,",Space,Str "graf",Space,Str "one",Str "."] - ,Para [Str "Item",Space,Str "1",Str ".",Space,Str "graf",Space,Str "two",Str ".",Space,Str "The",Space,Str "quick",Space,Str "brown",Space,Str "fox",Space,Str "jumped",Space,Str "over",Space,Str "the",Space,Str "lazy",Space,Str "dog",Str "'",Str "s",Space,Str "back",Str "."]] - ,[Para [Str "Item",Space,Str "2",Str "."]] - ,[Para [Str "Item",Space,Str "3",Str "."]]] + [[Para [Str "Item",Space,Str "1,",Space,Str "graf",Space,Str "one."] + ,Para [Str "Item",Space,Str "1.",Space,Str "graf",Space,Str "two.",Space,Str "The",Space,Str "quick",Space,Str "brown",Space,Str "fox",Space,Str "jumped",Space,Str "over",Space,Str "the",Space,Str "lazy",Space,Str "dog's",Space,Str "back."]] + ,[Para [Str "Item",Space,Str "2."]] + ,[Para [Str "Item",Space,Str "3."]]] ,Header 2 ("",[],[]) [Str "Nested"] ,BulletList [[Plain [Str "Tab"] @@ -123,7 +123,7 @@ Pandoc (Meta {unMeta = fromList [("generator",MetaInlines [Str "pandoc"]),("titl [[Plain [Str "Tab"] ,BulletList [[Plain [Str "Tab"]]]]]]] -,Para [Str "Here",Str "'",Str "s",Space,Str "another:"] +,Para [Str "Here's",Space,Str "another:"] ,OrderedList (1,DefaultStyle,DefaultDelim) [[Plain [Str "First"]] ,[Plain [Str "Second:"] @@ -163,63 +163,65 @@ Pandoc (Meta {unMeta = fromList [("generator",MetaInlines [Str "pandoc"]),("titl ,OrderedList (1,UpperAlpha,DefaultDelim) [[Plain [Str "Upper",Space,Str "Alpha"] ,OrderedList (1,UpperRoman,DefaultDelim) - [[Plain [Str "Upper",Space,Str "Roman",Str "."] + [[Plain [Str "Upper",Space,Str "Roman."] ,OrderedList (6,Decimal,DefaultDelim) [[Plain [Str "Decimal",Space,Str "start",Space,Str "with",Space,Str "6"] ,OrderedList (3,LowerAlpha,DefaultDelim) [[Plain [Str "Lower",Space,Str "alpha",Space,Str "with",Space,Str "paren"]]]]]]]]] ,Para [Str "Autonumbering:"] ,OrderedList (1,DefaultStyle,DefaultDelim) - [[Plain [Str "Autonumber",Str "."]] - ,[Plain [Str "More",Str "."] + [[Plain [Str "Autonumber."]] + ,[Plain [Str "More."] ,OrderedList (1,DefaultStyle,DefaultDelim) - [[Plain [Str "Nested",Str "."]]]]] + [[Plain [Str "Nested."]]]]] ,HorizontalRule ,Header 2 ("",[],[]) [Str "Definition"] ,DefinitionList [([Str "Violin"], - [[Plain [Str "Stringed",Space,Str "musical",Space,Str "instrument",Str "."]] - ,[Plain [Str "Torture",Space,Str "device",Str "."]]]) + [[Plain [Str "Stringed",Space,Str "musical",Space,Str "instrument."]] + ,[Plain [Str "Torture",Space,Str "device."]]]) ,([Str "Cello",LineBreak,Str "Violoncello"], - [[Plain [Str "Low",Str "-",Str "voiced",Space,Str "stringed",Space,Str "instrument",Str "."]]])] + [[Plain [Str "Low-voiced",Space,Str "stringed",Space,Str "instrument."]]])] ,HorizontalRule ,Header 1 ("",[],[]) [Str "Inline",Space,Str "Markup"] ,Para [Str "This",Space,Str "is",Space,Emph [Str "emphasized"],Str ",",Space,Str "and",Space,Str "so",Space,Emph [Str "is",Space,Str "this"],Str "."] ,Para [Str "This",Space,Str "is",Space,Strong [Str "strong"],Str ",",Space,Str "and",Space,Str "so",Space,Strong [Str "is",Space,Str "this"],Str "."] +,Para [Str "Empty",Space,Strong [],Space,Str "and",Space,Emph [],Str "."] ,Para [Str "An",Space,Emph [Link [Str "emphasized",Space,Str "link"] ("/url","")],Str "."] -,Para [Strong [Emph [Str "This",Space,Str "is",Space,Str "strong",Space,Str "and",Space,Str "em",Str "."]]] -,Para [Str "So",Space,Str "is",Space,Strong [Emph [Str "this"]],Space,Str "word",Str "."] -,Para [Strong [Emph [Str "This",Space,Str "is",Space,Str "strong",Space,Str "and",Space,Str "em",Str "."]]] -,Para [Str "So",Space,Str "is",Space,Strong [Emph [Str "this"]],Space,Str "word",Str "."] +,Para [Strong [Emph [Str "This",Space,Str "is",Space,Str "strong",Space,Str "and",Space,Str "em."]]] +,Para [Str "So",Space,Str "is",Space,Strong [Emph [Str "this"]],Space,Str "word."] +,Para [Strong [Emph [Str "This",Space,Str "is",Space,Str "strong",Space,Str "and",Space,Str "em."]]] +,Para [Str "So",Space,Str "is",Space,Strong [Emph [Str "this"]],Space,Str "word."] ,Para [Str "This",Space,Str "is",Space,Str "code:",Space,Code ("",[],[]) ">",Str ",",Space,Code ("",[],[]) "$",Str ",",Space,Code ("",[],[]) "\\",Str ",",Space,Code ("",[],[]) "\\$",Str ",",Space,Code ("",[],[]) "<html>",Str "."] +,Para [Str "This",Space,Str "is",Space,SmallCaps [Str "small",Space,Str "caps"],Str "."] ,HorizontalRule ,Header 1 ("",[],[]) [Str "Smart",Space,Str "quotes,",Space,Str "ellipses,",Space,Str "dashes"] -,Para [Str "\"",Str "Hello,",Str "\"",Space,Str "said",Space,Str "the",Space,Str "spider",Str ".",Space,Str "\"",Str "'",Str "Shelob",Str "'",Space,Str "is",Space,Str "my",Space,Str "name",Str ".",Str "\""] -,Para [Str "'",Str "A",Str "'",Str ",",Space,Str "'",Str "B",Str "'",Str ",",Space,Str "and",Space,Str "'",Str "C",Str "'",Space,Str "are",Space,Str "letters",Str "."] -,Para [Str "'",Str "Oak,",Str "'",Space,Str "'",Str "elm,",Str "'",Space,Str "and",Space,Str "'",Str "beech",Str "'",Space,Str "are",Space,Str "names",Space,Str "of",Space,Str "trees",Str ".",Space,Str "So",Space,Str "is",Space,Str "'",Str "pine",Str ".",Str "'"] -,Para [Str "'",Str "He",Space,Str "said,",Space,Str "\"",Str "I",Space,Str "want",Space,Str "to",Space,Str "go",Str ".",Str "\"",Str "'",Space,Str "Were",Space,Str "you",Space,Str "alive",Space,Str "in",Space,Str "the",Space,Str "70",Str "'",Str "s?"] -,Para [Str "Here",Space,Str "is",Space,Str "some",Space,Str "quoted",Space,Str "'",Code ("",[],[]) "code",Str "'",Space,Str "and",Space,Str "a",Space,Str "\"",Link [Str "quoted",Space,Str "link"] ("http://example.com/?foo=1&bar=2",""),Str "\"",Str "."] -,Para [Str "Some",Space,Str "dashes:",Space,Str "one",Str "-",Str "-",Str "-",Str "two",Space,Str "-",Str "-",Str "-",Space,Str "three",Str "-",Str "-",Str "four",Space,Str "-",Str "-",Space,Str "five",Str "."] -,Para [Str "Dashes",Space,Str "between",Space,Str "numbers:",Space,Str "5",Str "-",Str "7,",Space,Str "255",Str "-",Str "66,",Space,Str "1987",Str "-",Str "1999",Str "."] -,Para [Str "Ellipses",Str ".",Str ".",Str ".",Str "and",Str ".",Space,Str ".",Space,Str ".",Str "and",Space,Str ".",Space,Str ".",Space,Str ".",Space,Str "."] +,Para [Str "\"Hello,\"",Space,Str "said",Space,Str "the",Space,Str "spider.",Space,Str "\"'Shelob'",Space,Str "is",Space,Str "my",Space,Str "name.\""] +,Para [Str "'A',",Space,Str "'B',",Space,Str "and",Space,Str "'C'",Space,Str "are",Space,Str "letters."] +,Para [Str "'Oak,'",Space,Str "'elm,'",Space,Str "and",Space,Str "'beech'",Space,Str "are",Space,Str "names",Space,Str "of",Space,Str "trees.",Space,Str "So",Space,Str "is",Space,Str "'pine.'"] +,Para [Str "'He",Space,Str "said,",Space,Str "\"I",Space,Str "want",Space,Str "to",Space,Str "go.\"'",Space,Str "Were",Space,Str "you",Space,Str "alive",Space,Str "in",Space,Str "the",Space,Str "70's?"] +,Para [Str "Here",Space,Str "is",Space,Str "some",Space,Str "quoted",Space,Str "'",Code ("",[],[]) "code",Str "'",Space,Str "and",Space,Str "a",Space,Str "\"",Link [Str "quoted",Space,Str "link"] ("http://example.com/?foo=1&bar=2",""),Str "\"."] +,Para [Str "Some",Space,Str "dashes:",Space,Str "one---two",Space,Str "---",Space,Str "three--four",Space,Str "--",Space,Str "five."] +,Para [Str "Dashes",Space,Str "between",Space,Str "numbers:",Space,Str "5-7,",Space,Str "255-66,",Space,Str "1987-1999."] +,Para [Str "Ellipses...and.",Space,Str ".",Space,Str ".and",Space,Str ".",Space,Str ".",Space,Str ".",Space,Str "."] ,HorizontalRule ,Header 1 ("",[],[]) [Str "LaTeX"] ,BulletList - [[Plain [Str "\\cite[22",Str "-",Str "23]{smith",Str ".",Str "1899}"]] + [[Plain [Str "\\cite[22-23]{smith.1899}"]] ,[Plain [Str "\\doublespacing"]] - ,[Plain [Str "$",Str "2+2=4",Str "$"]] - ,[Plain [Str "$",Str "x",Space,Str "\\in",Space,Str "y",Str "$"]] - ,[Plain [Str "$",Str "\\alpha",Space,Str "\\wedge",Space,Str "\\omega",Str "$"]] - ,[Plain [Str "$",Str "223",Str "$"]] - ,[Plain [Str "$",Str "p",Str "$",Str "-",Str "Tree"]] - ,[Plain [Str "$",Str "\\frac{d}{dx}f(x)=\\lim_{h\\to",Space,Str "0}\\frac{f(x+h)",Str "-",Str "f(x)}{h}",Str "$"]] - ,[Plain [Str "Here",Str "'",Str "s",Space,Str "one",Space,Str "that",Space,Str "has",Space,Str "a",Space,Str "line",Space,Str "break",Space,Str "in",Space,Str "it:",Space,Str "$",Str "\\alpha",Space,Str "+",Space,Str "\\omega",Space,Str "\\times",Space,Str "x^2",Str "$",Str "."]]] -,Para [Str "These",Space,Str "shouldn",Str "'",Str "t",Space,Str "be",Space,Str "math:"] + ,[Plain [Str "$2+2=4$"]] + ,[Plain [Str "$x",Space,Str "\\in",Space,Str "y$"]] + ,[Plain [Str "$\\alpha",Space,Str "\\wedge",Space,Str "\\omega$"]] + ,[Plain [Str "$223$"]] + ,[Plain [Str "$p$-Tree"]] + ,[Plain [Str "$\\frac{d}{dx}f(x)=\\lim_{h\\to",Space,Str "0}\\frac{f(x+h)-f(x)}{h}$"]] + ,[Plain [Str "Here's",Space,Str "one",Space,Str "that",Space,Str "has",Space,Str "a",Space,Str "line",Space,Str "break",Space,Str "in",Space,Str "it:",Space,Str "$\\alpha",Space,Str "+",Space,Str "\\omega",Space,Str "\\times",Space,Str "x^2$."]]] +,Para [Str "These",Space,Str "shouldn't",Space,Str "be",Space,Str "math:"] ,BulletList [[Plain [Str "To",Space,Str "get",Space,Str "the",Space,Str "famous",Space,Str "equation,",Space,Str "write",Space,Code ("",[],[]) "$e = mc^2$",Str "."]] - ,[Plain [Str "$",Str "22,000",Space,Str "is",Space,Str "a",Space,Emph [Str "lot"],Space,Str "of",Space,Str "money",Str ".",Space,Str "So",Space,Str "is",Space,Str "$",Str "34,000",Str ".",Space,Str "(It",Space,Str "worked",Space,Str "if",Space,Str "\"",Str "lot",Str "\"",Space,Str "is",Space,Str "emphasized",Str ".",Str ")"]] - ,[Plain [Str "Escaped",Space,Code ("",[],[]) "$",Str ":",Space,Str "$",Str "73",Space,Emph [Str "this",Space,Str "should",Space,Str "be",Space,Str "emphasized"],Space,Str "23",Str "$",Str "."]]] -,Para [Str "Here",Str "'",Str "s",Space,Str "a",Space,Str "LaTeX",Space,Str "table:"] + ,[Plain [Str "$22,000",Space,Str "is",Space,Str "a",Space,Emph [Str "lot"],Space,Str "of",Space,Str "money.",Space,Str "So",Space,Str "is",Space,Str "$34,000.",Space,Str "(It",Space,Str "worked",Space,Str "if",Space,Str "\"lot\"",Space,Str "is",Space,Str "emphasized.)"]] + ,[Plain [Str "Escaped",Space,Code ("",[],[]) "$",Str ":",Space,Str "$73",Space,Emph [Str "this",Space,Str "should",Space,Str "be",Space,Str "emphasized"],Space,Str "23$."]]] +,Para [Str "Here's",Space,Str "a",Space,Str "LaTeX",Space,Str "table:"] ,Para [Str "\\begin{tabular}{|l|l|}\\hline",Space,Str "Animal",Space,Str "&",Space,Str "Number",Space,Str "\\\\",Space,Str "\\hline",Space,Str "Dog",Space,Str "&",Space,Str "2",Space,Str "\\\\",Space,Str "Cat",Space,Str "&",Space,Str "1",Space,Str "\\\\",Space,Str "\\hline",Space,Str "\\end{tabular}"] ,HorizontalRule ,Header 1 ("",[],[]) [Str "Special",Space,Str "Characters"] @@ -230,11 +232,11 @@ Pandoc (Meta {unMeta = fromList [("generator",MetaInlines [Str "pandoc"]),("titl ,[Plain [Str "section:",Space,Str "\167"]] ,[Plain [Str "set",Space,Str "membership:",Space,Str "\8712"]] ,[Plain [Str "copyright:",Space,Str "\169"]]] -,Para [Str "AT&T",Space,Str "has",Space,Str "an",Space,Str "ampersand",Space,Str "in",Space,Str "their",Space,Str "name",Str "."] -,Para [Str "AT&T",Space,Str "is",Space,Str "another",Space,Str "way",Space,Str "to",Space,Str "write",Space,Str "it",Str "."] -,Para [Str "This",Space,Str "&",Space,Str "that",Str "."] -,Para [Str "4",Space,Str "<",Space,Str "5",Str "."] -,Para [Str "6",Space,Str ">",Space,Str "5",Str "."] +,Para [Str "AT&T",Space,Str "has",Space,Str "an",Space,Str "ampersand",Space,Str "in",Space,Str "their",Space,Str "name."] +,Para [Str "AT&T",Space,Str "is",Space,Str "another",Space,Str "way",Space,Str "to",Space,Str "write",Space,Str "it."] +,Para [Str "This",Space,Str "&",Space,Str "that."] +,Para [Str "4",Space,Str "<",Space,Str "5."] +,Para [Str "6",Space,Str ">",Space,Str "5."] ,Para [Str "Backslash:",Space,Str "\\"] ,Para [Str "Backtick:",Space,Str "`"] ,Para [Str "Asterisk:",Space,Str "*"] @@ -245,7 +247,7 @@ Pandoc (Meta {unMeta = fromList [("generator",MetaInlines [Str "pandoc"]),("titl ,Para [Str "Right",Space,Str "bracket:",Space,Str "]"] ,Para [Str "Left",Space,Str "paren:",Space,Str "("] ,Para [Str "Right",Space,Str "paren:",Space,Str ")"] -,Para [Str "Greater",Str "-",Str "than:",Space,Str ">"] +,Para [Str "Greater-than:",Space,Str ">"] ,Para [Str "Hash:",Space,Str "#"] ,Para [Str "Period:",Space,Str "."] ,Para [Str "Bang:",Space,Str "!"] @@ -260,47 +262,62 @@ Pandoc (Meta {unMeta = fromList [("generator",MetaInlines [Str "pandoc"]),("titl ,Para [Link [Str "URL",Space,Str "and",Space,Str "title"] ("/url/","title preceded by a tab"),Str "."] ,Para [Link [Str "URL",Space,Str "and",Space,Str "title"] ("/url/","title with \"quotes\" in it")] ,Para [Link [Str "URL",Space,Str "and",Space,Str "title"] ("/url/","title with single quotes")] -,Para [Str "Email",Space,Str "link",Space,Str "(nobody",Space,Str "[at]",Space,Str "nowhere",Str ".",Str "net)"] +,Para [Str "Email",Space,Str "link",Space,Str "(nobody",Space,Str "[at]",Space,Str "nowhere.net)"] ,Para [Link [Str "Empty"] ("",""),Str "."] ,Header 2 ("",[],[]) [Str "Reference"] ,Para [Str "Foo",Space,Link [Str "bar"] ("/url/",""),Str "."] ,Para [Str "Foo",Space,Link [Str "bar"] ("/url/",""),Str "."] ,Para [Str "Foo",Space,Link [Str "bar"] ("/url/",""),Str "."] ,Para [Str "With",Space,Link [Str "embedded",Space,Str "[brackets]"] ("/url/",""),Str "."] -,Para [Link [Str "b"] ("/url/",""),Space,Str "by",Space,Str "itself",Space,Str "should",Space,Str "be",Space,Str "a",Space,Str "link",Str "."] +,Para [Link [Str "b"] ("/url/",""),Space,Str "by",Space,Str "itself",Space,Str "should",Space,Str "be",Space,Str "a",Space,Str "link."] ,Para [Str "Indented",Space,Link [Str "once"] ("/url",""),Str "."] ,Para [Str "Indented",Space,Link [Str "twice"] ("/url",""),Str "."] ,Para [Str "Indented",Space,Link [Str "thrice"] ("/url",""),Str "."] -,Para [Str "This",Space,Str "should",Space,Str "[not]",Space,Str "be",Space,Str "a",Space,Str "link",Str "."] +,Para [Str "This",Space,Str "should",Space,Str "[not]",Space,Str "be",Space,Str "a",Space,Str "link."] ,CodeBlock ("",[],[]) "[not]: /url" ,Para [Str "Foo",Space,Link [Str "bar"] ("/url/","Title with \"quotes\" inside"),Str "."] ,Para [Str "Foo",Space,Link [Str "biz"] ("/url/","Title with \"quote\" inside"),Str "."] ,Header 2 ("",[],[]) [Str "With",Space,Str "ampersands"] -,Para [Str "Here",Str "'",Str "s",Space,Str "a",Space,Link [Str "link",Space,Str "with",Space,Str "an",Space,Str "ampersand",Space,Str "in",Space,Str "the",Space,Str "URL"] ("http://example.com/?foo=1&bar=2",""),Str "."] -,Para [Str "Here",Str "'",Str "s",Space,Str "a",Space,Str "link",Space,Str "with",Space,Str "an",Space,Str "amersand",Space,Str "in",Space,Str "the",Space,Str "link",Space,Str "text:",Space,Link [Str "AT&T"] ("http://att.com/","AT&T"),Str "."] -,Para [Str "Here",Str "'",Str "s",Space,Str "an",Space,Link [Str "inline",Space,Str "link"] ("/script?foo=1&bar=2",""),Str "."] -,Para [Str "Here",Str "'",Str "s",Space,Str "an",Space,Link [Str "inline",Space,Str "link",Space,Str "in",Space,Str "pointy",Space,Str "braces"] ("/script?foo=1&bar=2",""),Str "."] +,Para [Str "Here's",Space,Str "a",Space,Link [Str "link",Space,Str "with",Space,Str "an",Space,Str "ampersand",Space,Str "in",Space,Str "the",Space,Str "URL"] ("http://example.com/?foo=1&bar=2",""),Str "."] +,Para [Str "Here's",Space,Str "a",Space,Str "link",Space,Str "with",Space,Str "an",Space,Str "amersand",Space,Str "in",Space,Str "the",Space,Str "link",Space,Str "text:",Space,Link [Str "AT&T"] ("http://att.com/","AT&T"),Str "."] +,Para [Str "Here's",Space,Str "an",Space,Link [Str "inline",Space,Str "link"] ("/script?foo=1&bar=2",""),Str "."] +,Para [Str "Here's",Space,Str "an",Space,Link [Str "inline",Space,Str "link",Space,Str "in",Space,Str "pointy",Space,Str "braces"] ("/script?foo=1&bar=2",""),Str "."] ,Header 2 ("",[],[]) [Str "Autolinks"] -,Para [Str "With",Space,Str "an",Space,Str "ampersand:",Space,Link [Str "http://example",Str ".",Str "com/?foo=1&bar=2"] ("http://example.com/?foo=1&bar=2","")] +,Para [Str "With",Space,Str "an",Space,Str "ampersand:",Space,Link [Str "http://example.com/?foo=1&bar=2"] ("http://example.com/?foo=1&bar=2","")] ,BulletList [[Plain [Str "In",Space,Str "a",Space,Str "list?"]] - ,[Plain [Link [Str "http://example",Str ".",Str "com/"] ("http://example.com/","")]] - ,[Plain [Str "It",Space,Str "should",Str "."]]] -,Para [Str "An",Space,Str "e",Str "-",Str "mail",Space,Str "address:",Space,Str "nobody",Space,Str "[at]",Space,Str "nowhere",Str ".",Str "net"] + ,[Plain [Link [Str "http://example.com/"] ("http://example.com/","")]] + ,[Plain [Str "It",Space,Str "should."]]] +,Para [Str "An",Space,Str "e-mail",Space,Str "address:",Space,Str "nobody",Space,Str "[at]",Space,Str "nowhere.net"] ,BlockQuote - [Para [Str "Blockquoted:",Space,Link [Str "http://example",Str ".",Str "com/"] ("http://example.com/","")]] -,Para [Str "Auto",Str "-",Str "links",Space,Str "should",Space,Str "not",Space,Str "occur",Space,Str "here:",Space,Code ("",[],[]) "<http://example.com/>"] + [Para [Str "Blockquoted:",Space,Link [Str "http://example.com/"] ("http://example.com/","")]] +,Para [Str "Auto-links",Space,Str "should",Space,Str "not",Space,Str "occur",Space,Str "here:",Space,Code ("",[],[]) "<http://example.com/>"] ,CodeBlock ("",[],[]) "or here: <http://example.com/>" ,HorizontalRule ,Header 1 ("",[],[]) [Str "Images"] -,Para [Str "From",Space,Str "\"",Str "Voyage",Space,Str "dans",Space,Str "la",Space,Str "Lune",Str "\"",Space,Str "by",Space,Str "Georges",Space,Str "Melies",Space,Str "(1902):"] +,Para [Str "From",Space,Str "\"Voyage",Space,Str "dans",Space,Str "la",Space,Str "Lune\"",Space,Str "by",Space,Str "Georges",Space,Str "Melies",Space,Str "(1902):"] ,Para [Image [Str "lalune"] ("lalune.jpg","Voyage dans la Lune")] -,Para [Str "Here",Space,Str "is",Space,Str "a",Space,Str "movie",Space,Image [Str "movie"] ("movie.jpg",""),Space,Str "icon",Str "."] +,Para [Str "Here",Space,Str "is",Space,Str "a",Space,Str "movie",Space,Image [Str "movie"] ("movie.jpg",""),Space,Str "icon."] ,HorizontalRule ,Header 1 ("",[],[]) [Str "Footnotes"] -,Para [Str "Here",Space,Str "is",Space,Str "a",Space,Str "footnote",Space,Str "reference",Link [Str "(1)"] ("#note_1",""),Str ",",Space,Str "and",Space,Str "another",Link [Str "(longnote)"] ("#note_longnote",""),Str ".",Space,Str "This",Space,Str "should",Space,Emph [Str "not"],Space,Str "be",Space,Str "a",Space,Str "footnote",Space,Str "reference,",Space,Str "because",Space,Str "it",Space,Str "contains",Space,Str "a",Space,Str "space^(my",Space,Str "note)",Str "."] -,Para [Link [Str "(1)"] ("#ref_1",""),Space,Str "Here",Space,Str "is",Space,Str "the",Space,Str "footnote",Str ".",Space,Str "It",Space,Str "can",Space,Str "go",Space,Str "anywhere",Space,Str "in",Space,Str "the",Space,Str "document,",Space,Str "not",Space,Str "just",Space,Str "at",Space,Str "the",Space,Str "end",Str "."] -,Para [Link [Str "(longnote)"] ("#ref_longnote",""),Space,Str "Here",Str "'",Str "s",Space,Str "the",Space,Str "other",Space,Str "note",Str ".",Space,Str "This",Space,Str "one",Space,Str "contains",Space,Str "multiple",Space,Str "blocks",Str "."] -,Para [Str "Caret",Space,Str "characters",Space,Str "are",Space,Str "used",Space,Str "to",Space,Str "indicate",Space,Str "that",Space,Str "the",Space,Str "blocks",Space,Str "all",Space,Str "belong",Space,Str "to",Space,Str "a",Space,Str "single",Space,Str "footnote",Space,Str "(as",Space,Str "with",Space,Str "block",Space,Str "quotes)",Str "."] +,Para [Str "Here",Space,Str "is",Space,Str "a",Space,Str "footnote",Space,Str "reference",Link [Str "(1)"] ("#note_1",""),Str ",",Space,Str "and",Space,Str "another",Link [Str "(longnote)"] ("#note_longnote",""),Str ".",Space,Str "This",Space,Str "should",Space,Emph [Str "not"],Space,Str "be",Space,Str "a",Space,Str "footnote",Space,Str "reference,",Space,Str "because",Space,Str "it",Space,Str "contains",Space,Str "a",Space,Str "space^(my",Space,Str "note)."] +,Para [Link [Str "(1)"] ("#ref_1",""),Space,Str "Here",Space,Str "is",Space,Str "the",Space,Str "footnote.",Space,Str "It",Space,Str "can",Space,Str "go",Space,Str "anywhere",Space,Str "in",Space,Str "the",Space,Str "document,",Space,Str "not",Space,Str "just",Space,Str "at",Space,Str "the",Space,Str "end."] +,Para [Link [Str "(longnote)"] ("#ref_longnote",""),Space,Str "Here's",Space,Str "the",Space,Str "other",Space,Str "note.",Space,Str "This",Space,Str "one",Space,Str "contains",Space,Str "multiple",Space,Str "blocks."] +,Para [Str "Caret",Space,Str "characters",Space,Str "are",Space,Str "used",Space,Str "to",Space,Str "indicate",Space,Str "that",Space,Str "the",Space,Str "blocks",Space,Str "all",Space,Str "belong",Space,Str "to",Space,Str "a",Space,Str "single",Space,Str "footnote",Space,Str "(as",Space,Str "with",Space,Str "block",Space,Str "quotes)."] ,CodeBlock ("",[],[]) " { <code> }" -,Para [Str "If",Space,Str "you",Space,Str "want,",Space,Str "you",Space,Str "can",Space,Str "use",Space,Str "a",Space,Str "caret",Space,Str "at",Space,Str "the",Space,Str "beginning",Space,Str "of",Space,Str "every",Space,Str "line,",Space,Str "as",Space,Str "with",Space,Str "blockquotes,",Space,Str "but",Space,Str "all",Space,Str "that",Space,Str "you",Space,Str "need",Space,Str "is",Space,Str "a",Space,Str "caret",Space,Str "at",Space,Str "the",Space,Str "beginning",Space,Str "of",Space,Str "the",Space,Str "first",Space,Str "line",Space,Str "of",Space,Str "the",Space,Str "block",Space,Str "and",Space,Str "any",Space,Str "preceding",Space,Str "blank",Space,Str "lines",Str "."]] +,Para [Str "If",Space,Str "you",Space,Str "want,",Space,Str "you",Space,Str "can",Space,Str "use",Space,Str "a",Space,Str "caret",Space,Str "at",Space,Str "the",Space,Str "beginning",Space,Str "of",Space,Str "every",Space,Str "line,",Space,Str "as",Space,Str "with",Space,Str "blockquotes,",Space,Str "but",Space,Str "all",Space,Str "that",Space,Str "you",Space,Str "need",Space,Str "is",Space,Str "a",Space,Str "caret",Space,Str "at",Space,Str "the",Space,Str "beginning",Space,Str "of",Space,Str "the",Space,Str "first",Space,Str "line",Space,Str "of",Space,Str "the",Space,Str "block",Space,Str "and",Space,Str "any",Space,Str "preceding",Space,Str "blank",Space,Str "lines."] +,Para [Str "text",Space,Emph [Str "Leading",Space,Str "space"]] +,Para [Emph [Str "Trailing",Space,Str "space"],Space,Str "text"] +,Para [Str "text",Space,Emph [Str "Leading",Space,Str "spaces"]] +,Para [Emph [Str "Trailing",Space,Str "spaces"],Space,Str "text"] +,Header 1 ("",[],[]) [Str "Tables"] +,Table [] [AlignDefault,AlignDefault,AlignDefault] [0.0,0.0,0.0] + [[Plain [Str "X"]] + ,[Plain [Str "Y"]] + ,[Plain [Str "Z"]]] + [[[Plain [Str "1"]] + ,[Plain [Str "2"]] + ,[Plain [Str "3"]]] + ,[[Plain [Str "4"]] + ,[Plain [Str "5"]] + ,[Plain [Str "6"]]]]] diff --git a/tests/latex-reader.native b/tests/latex-reader.native index fcc3153cf..abc4b05a7 100644 --- a/tests/latex-reader.native +++ b/tests/latex-reader.native @@ -1,4 +1,4 @@ -Pandoc (Meta {unMeta = fromList [("authors",MetaList [MetaInlines [Str "John",Space,Str "MacFarlane"],MetaInlines [Str "Anonymous"]]),("date",MetaInlines [Str "July",Space,Str "17,",Space,Str "2006"]),("title",MetaInlines [Str "Pandoc",Space,Str "Test",Space,Str "Suite"])]}) +Pandoc (Meta {unMeta = fromList [("author",MetaList [MetaInlines [Str "John",Space,Str "MacFarlane"],MetaInlines [Str "Anonymous"]]),("date",MetaInlines [Str "July",Space,Str "17,",Space,Str "2006"]),("title",MetaInlines [Str "Pandoc",Space,Str "Test",Space,Str "Suite"])]}) [RawBlock (Format "latex") "\\maketitle" ,Para [Str "This",Space,Str "is",Space,Str "a",Space,Str "set",Space,Str "of",Space,Str "tests",Space,Str "for",Space,Str "pandoc.",Space,Str "Most",Space,Str "of",Space,Str "them",Space,Str "are",Space,Str "adapted",Space,Str "from",Space,Str "John",Space,Str "Gruber\8217s",Space,Str "markdown",Space,Str "test",Space,Str "suite."] ,HorizontalRule diff --git a/tests/lhs-test.latex b/tests/lhs-test.latex index 6bdce2247..d8f60e545 100644 --- a/tests/lhs-test.latex +++ b/tests/lhs-test.latex @@ -1,12 +1,10 @@ \documentclass[]{article} -\usepackage[T1]{fontenc} \usepackage{lmodern} \usepackage{amssymb,amsmath} \usepackage{ifxetex,ifluatex} \usepackage{fixltx2e} % provides \textsubscript -% use upquote if available, for straight quotes in verbatim environments -\IfFileExists{upquote.sty}{\usepackage{upquote}}{} \ifnum 0\ifxetex 1\fi\ifluatex 1\fi=0 % if pdftex + \usepackage[T1]{fontenc} \usepackage[utf8]{inputenc} \else % if luatex or xelatex \ifxetex @@ -18,8 +16,13 @@ \defaultfontfeatures{Mapping=tex-text,Scale=MatchLowercase} \newcommand{\euro}{€} \fi +% use upquote if available, for straight quotes in verbatim environments +\IfFileExists{upquote.sty}{\usepackage{upquote}}{} % use microtype if available -\IfFileExists{microtype.sty}{\usepackage{microtype}}{} +\IfFileExists{microtype.sty}{% +\usepackage{microtype} +\UseMicrotypeSet[protrusion]{basicmath} % disable protrusion for tt fonts +}{} \usepackage{color} \usepackage{fancyvrb} \newcommand{\VerbBar}{|} @@ -63,7 +66,6 @@ \setlength{\emergencystretch}{3em} % prevent overfull lines \setcounter{secnumdepth}{0} -\author{} \date{} \begin{document} diff --git a/tests/lhs-test.latex+lhs b/tests/lhs-test.latex+lhs index 30a7106ce..8e1ac55b5 100644 --- a/tests/lhs-test.latex+lhs +++ b/tests/lhs-test.latex+lhs @@ -1,12 +1,10 @@ \documentclass[]{article} -\usepackage[T1]{fontenc} \usepackage{lmodern} \usepackage{amssymb,amsmath} \usepackage{ifxetex,ifluatex} \usepackage{fixltx2e} % provides \textsubscript -% use upquote if available, for straight quotes in verbatim environments -\IfFileExists{upquote.sty}{\usepackage{upquote}}{} \ifnum 0\ifxetex 1\fi\ifluatex 1\fi=0 % if pdftex + \usepackage[T1]{fontenc} \usepackage[utf8]{inputenc} \else % if luatex or xelatex \ifxetex @@ -18,8 +16,13 @@ \defaultfontfeatures{Mapping=tex-text,Scale=MatchLowercase} \newcommand{\euro}{€} \fi +% use upquote if available, for straight quotes in verbatim environments +\IfFileExists{upquote.sty}{\usepackage{upquote}}{} % use microtype if available -\IfFileExists{microtype.sty}{\usepackage{microtype}}{} +\IfFileExists{microtype.sty}{% +\usepackage{microtype} +\UseMicrotypeSet[protrusion]{basicmath} % disable protrusion for tt fonts +}{} \usepackage{listings} \lstnewenvironment{code}{\lstset{language=Haskell,basicstyle=\small\ttfamily}}{} \ifxetex @@ -44,7 +47,6 @@ \setlength{\emergencystretch}{3em} % prevent overfull lines \setcounter{secnumdepth}{0} -\author{} \date{} \begin{document} diff --git a/tests/markdown-reader-more.native b/tests/markdown-reader-more.native index 27f09dada..00313a0ac 100644 --- a/tests/markdown-reader-more.native +++ b/tests/markdown-reader-more.native @@ -5,9 +5,10 @@ ,Plain [RawInline (Format "tex") "\\placeformula "] ,RawBlock (Format "context") "\\startformula\n L_{1} = L_{2}\n \\stopformula" ,RawBlock (Format "context") "\\start[a2]\n\\start[a2]\n\\stop[a2]\n\\stop[a2]" -,Header 2 ("urls-with-spaces",[],[]) [Str "URLs",Space,Str "with",Space,Str "spaces"] +,Header 2 ("urls-with-spaces-and-punctuation",[],[]) [Str "URLs",Space,Str "with",Space,Str "spaces",Space,Str "and",Space,Str "punctuation"] ,Para [Link [Str "foo"] ("/bar%20and%20baz",""),Space,Link [Str "foo"] ("/bar%20and%20baz",""),Space,Link [Str "foo"] ("/bar%20and%20baz",""),Space,Link [Str "foo"] ("bar%20baz","title")] ,Para [Link [Str "baz"] ("/foo%20foo",""),Space,Link [Str "bam"] ("/foo%20fee",""),Space,Link [Str "bork"] ("/foo/zee%20zob","title")] +,Para [Link [Str "Ward\8217s",Space,Str "method."] ("http://en.wikipedia.org/wiki/Ward's_method","")] ,Header 2 ("horizontal-rules-with-spaces-at-end",[],[]) [Str "Horizontal",Space,Str "rules",Space,Str "with",Space,Str "spaces",Space,Str "at",Space,Str "end"] ,HorizontalRule ,HorizontalRule @@ -16,10 +17,22 @@ ,Header 3 ("my-header",[],[]) [Str "my",Space,Str "header"] ,Header 2 ("in-math",[],[]) [Str "$",Space,Str "in",Space,Str "math"] ,Para [Math InlineMath "\\$2 + \\$3"] +,Para [Math InlineMath "x = \\text{the $n$th root of $y$}"] +,Para [Str "This",Space,Str "should",Space,Str "not",Space,Str "be",Space,Str "math:"] +,Para [Str "$PATH",Space,Str "90",Space,Str "$PATH"] ,Header 2 ("commented-out-list-item",[],[]) [Str "Commented-out",Space,Str "list",Space,Str "item"] ,BulletList [[Plain [Str "one",Space,RawInline (Format "html") "<!--\n- two\n-->"]] ,[Plain [Str "three"]]] +,Header 2 ("indented-code-at-beginning-of-list",[],[]) [Str "Indented",Space,Str "code",Space,Str "at",Space,Str "beginning",Space,Str "of",Space,Str "list"] +,BulletList + [[CodeBlock ("",[],[]) "code\ncode"]] +,OrderedList (1,Decimal,Period) + [[CodeBlock ("",[],[]) "code\ncode"] + ,[CodeBlock ("",[],[]) "code\ncode"]] +,BulletList + [[CodeBlock ("",[],[]) "code\ncode"] + ,[Plain [Str "no",Space,Str "code"]]] ,Header 2 ("backslash-newline",[],[]) [Str "Backslash",Space,Str "newline"] ,Para [Str "hi",LineBreak,Str "there"] ,Header 2 ("code-spans",[],[]) [Str "Code",Space,Str "spans"] @@ -66,6 +79,8 @@ ,Para [Str "Link",Space,Str "to",Space,Link [Str "Explicit",Space,Str "header",Space,Str "attributes"] ("#foobar",""),Str "."] ,Para [Str "But",Space,Str "this",Space,Str "is",Space,Str "not",Space,Str "a",Space,Str "link",Space,Str "to",Space,Link [Str "My",Space,Str "other",Space,Str "header"] ("/foo",""),Str ",",Space,Str "since",Space,Str "the",Space,Str "reference",Space,Str "is",Space,Str "defined."] ,Header 2 ("foobar",["baz"],[("key","val")]) [Str "Explicit",Space,Str "header",Space,Str "attributes"] +,BlockQuote + [Header 2 ("foobar",["baz"],[("key","val")]) [Str "Header",Space,Str "attributes",Space,Str "inside",Space,Str "block",Space,Str "quote"]] ,Header 2 ("line-blocks",[],[]) [Str "Line",Space,Str "blocks"] ,Para [Str "But",Space,Str "can",Space,Str "a",Space,Str "bee",Space,Str "be",Space,Str "said",Space,Str "to",Space,Str "be",LineBreak,Str "\160\160\160\160or",Space,Str "not",Space,Str "to",Space,Str "be",Space,Str "an",Space,Str "entire",Space,Str "bee,",LineBreak,Str "\160\160\160\160\160\160\160\160when",Space,Str "half",Space,Str "the",Space,Str "bee",Space,Str "is",Space,Str "not",Space,Str "a",Space,Str "bee,",LineBreak,Str "\160\160\160\160\160\160\160\160\160\160\160\160due",Space,Str "to",Space,Str "some",Space,Str "ancient",Space,Str "injury?"] ,Para [Str "Continuation",Space,Str "line",LineBreak,Str "\160\160and",Space,Str "another"] @@ -136,4 +151,7 @@ ,Para [Link [Str "link"] ("/hithere)","")] ,Para [Link [Str "linky"] ("hi_(there_(nested))","")] ,Header 2 ("reference-link-fallbacks",[],[]) [Str "Reference",Space,Str "link",Space,Str "fallbacks"] -,Para [Str "[",Emph [Str "not",Space,Str "a",Space,Str "link"],Str "]",Space,Str "[",Emph [Str "nope"],Str "]\8230"]] +,Para [Str "[",Emph [Str "not",Space,Str "a",Space,Str "link"],Str "]",Space,Str "[",Emph [Str "nope"],Str "]\8230"] +,Header 2 ("empty-reference-links",[],[]) [Str "Empty",Space,Str "reference",Space,Str "links"] +,Para [Str "bar"] +,Para [Link [Str "foo2"] ("","")]] diff --git a/tests/markdown-reader-more.txt b/tests/markdown-reader-more.txt index d133b3dbb..ea4fc9cad 100644 --- a/tests/markdown-reader-more.txt +++ b/tests/markdown-reader-more.txt @@ -28,7 +28,7 @@ \stop[a2] \stop[a2] -## URLs with spaces +## URLs with spaces and punctuation [foo](/bar and baz) [foo](/bar @@ -42,6 +42,8 @@ [bam]: /foo fee [bork]: /foo/zee zob (title) +[Ward's method.](http://en.wikipedia.org/wiki/Ward's_method) + ## Horizontal rules with spaces at end * * * * * @@ -58,6 +60,12 @@ $\$2 + \$3$ +$x = \text{the $n$th root of $y$}$ + +This should not be math: + +$PATH 90 $PATH + ## Commented-out list item - one @@ -66,6 +74,22 @@ $\$2 + \$3$ --> - three +## Indented code at beginning of list + +- code + code + + 1. code + code + + 12345678. code + code + + - code + code + + - no code + ## Backslash newline hi\ @@ -152,6 +176,8 @@ But this is not a link to [My other header], since the reference is defined. ## Explicit header attributes {#foobar .baz key="val"} +> ## Header attributes inside block quote {#foobar .baz key="val"} + ## Line blocks | But can a bee be said to be @@ -235,3 +261,11 @@ Empty cells ## Reference link fallbacks [*not a link*] [*nope*]... + +## Empty reference links + +[foo2]: + +bar + +[foo2] diff --git a/tests/mediawiki-reader.native b/tests/mediawiki-reader.native index 238413445..2e97e9484 100644 --- a/tests/mediawiki-reader.native +++ b/tests/mediawiki-reader.native @@ -88,6 +88,7 @@ Pandoc (Meta {unMeta = fromList []}) ,Para [Image [Str "the",Space,Emph [Str "caption"],Space,Str "with",Space,Link [Str "external",Space,Str "link"] ("http://google.com","")] ("example.jpg","fig:the caption with external link")] ,Para [Image [Str "caption"] ("example.jpg","fig:caption")] ,Para [Image [Str "example.jpg"] ("example.jpg","fig:example.jpg")] +,Para [Image [Str "example_es.jpg"] ("example_es.jpg","fig:example_es.jpg")] ,Header 2 ("lists",[],[]) [Str "lists"] ,BulletList [[Plain [Str "Start",Space,Str "each",Space,Str "line"]] @@ -101,6 +102,10 @@ Pandoc (Meta {unMeta = fromList []}) [[BulletList [[Plain [Str "But",Space,Str "jumping",Space,Str "levels",Space,Str "creates",Space,Str "empty",Space,Str "space."]]]]]]] ,Para [Str "Any",Space,Str "other",Space,Str "start",Space,Str "ends",Space,Str "the",Space,Str "list."] +,BulletList + [[BulletList + [[Plain [Str "two"]]]] + ,[Plain [Str "one"]]] ,OrderedList (1,DefaultStyle,DefaultDelim) [[Plain [Str "Start",Space,Str "each",Space,Str "line"]] ,[Plain [Str "with",Space,Str "a",Space,Str "number",Space,Str "sign",Space,Str "(#)."] diff --git a/tests/mediawiki-reader.wiki b/tests/mediawiki-reader.wiki index c0c22bec6..6a6bc226d 100644 --- a/tests/mediawiki-reader.wiki +++ b/tests/mediawiki-reader.wiki @@ -173,6 +173,8 @@ http://johnmacfarlane.net/pandoc/ [[File:example.jpg]] +[[Archivo:example_es.jpg]] + == lists == * Start each line @@ -183,6 +185,9 @@ http://johnmacfarlane.net/pandoc/ *** But jumping levels creates empty space. Any other start ends the list. +** two +* one + # Start each line # with a number sign (#). ## More number signs gives deeper diff --git a/tests/opml-reader.native b/tests/opml-reader.native index e71857680..14aff2c03 100644 --- a/tests/opml-reader.native +++ b/tests/opml-reader.native @@ -19,7 +19,7 @@ Pandoc (Meta {unMeta = fromList [("author",MetaList [MetaInlines [Str "Dave",Spa ,Header 3 ("",[],[]) [Str "North",Space,Str "Dakota"] ,Header 3 ("",[],[]) [Str "Oklahoma"] ,Header 3 ("",[],[]) [Str "South",Space,Str "Dakota"] -,Header 2 ("",[],[]) [Str "Mid",Str "-",Str "Atlantic"] +,Header 2 ("",[],[]) [Str "Mid-Atlantic"] ,Header 3 ("",[],[]) [Str "Delaware"] ,Header 3 ("",[],[]) [Str "Maryland"] ,Header 3 ("",[],[]) [Str "New",Space,Str "Jersey"] diff --git a/tests/pipe-tables.native b/tests/pipe-tables.native index 5420a7bd3..eafd21d22 100644 --- a/tests/pipe-tables.native +++ b/tests/pipe-tables.native @@ -67,4 +67,12 @@ ,[[Plain [Str "orange"]] ,[Plain [Str "17"]]] ,[[Plain [Str "pear"]] - ,[Plain [Str "302"]]]]] + ,[Plain [Str "302"]]]] +,Para [Str "One-column:"] +,Table [] [AlignDefault] [0.0] + [[Plain [Str "hi"]]] + [[[Plain [Str "lo"]]]] +,Para [Str "Header-less",Space,Str "one-column:"] +,Table [] [AlignCenter] [0.0] + [[]] + [[[Plain [Str "hi"]]]]] diff --git a/tests/pipe-tables.txt b/tests/pipe-tables.txt index 79d79200f..ee8d54d9f 100644 --- a/tests/pipe-tables.txt +++ b/tests/pipe-tables.txt @@ -40,3 +40,13 @@ apple | 5 orange| 17 pear | 302 +One-column: + +|hi| +|--| +|lo| + +Header-less one-column: + +|:-:| +|hi| diff --git a/tests/rst-reader.native b/tests/rst-reader.native index 497810f39..1f402f835 100644 --- a/tests/rst-reader.native +++ b/tests/rst-reader.native @@ -1,4 +1,4 @@ -Pandoc (Meta {unMeta = fromList [("authors",MetaList [MetaInlines [Str "John",Space,Str "MacFarlane"],MetaInlines [Str "Anonymous"]]),("date",MetaInlines [Str "July",Space,Str "17,",Space,Str "2006"]),("revision",MetaBlocks [Para [Str "3"]]),("subtitle",MetaInlines [Str "Subtitle"]),("title",MetaInlines [Str "Pandoc",Space,Str "Test",Space,Str "Suite"])]}) +Pandoc (Meta {unMeta = fromList [("author",MetaList [MetaInlines [Str "John",Space,Str "MacFarlane"],MetaInlines [Str "Anonymous"]]),("date",MetaInlines [Str "July",Space,Str "17,",Space,Str "2006"]),("revision",MetaBlocks [Para [Str "3"]]),("subtitle",MetaInlines [Str "Subtitle"]),("title",MetaInlines [Str "Pandoc",Space,Str "Test",Space,Str "Suite"])]}) [Header 1 ("level-one-header",[],[]) [Str "Level",Space,Str "one",Space,Str "header"] ,Para [Str "This",Space,Str "is",Space,Str "a",Space,Str "set",Space,Str "of",Space,Str "tests",Space,Str "for",Space,Str "pandoc.",Space,Str "Most",Space,Str "of",Space,Str "them",Space,Str "are",Space,Str "adapted",Space,Str "from",Space,Str "John",Space,Str "Gruber\8217s",Space,Str "markdown",Space,Str "test",Space,Str "suite."] ,Header 2 ("level-two-header",[],[]) [Str "Level",Space,Str "two",Space,Str "header"] @@ -319,5 +319,15 @@ Pandoc (Meta {unMeta = fromList [("authors",MetaList [MetaInlines [Str "John",Sp ,Para [Str "Some",Space,Superscript [Str "of"],Space,Str "these",Space,Superscript [Str "words"],Space,Str "are",Space,Str "in",Space,Superscript [Str "superscript"],Str "."] ,Para [Str "Reset",Space,Str "default-role",Space,Str "to",Space,Str "the",Space,Str "default",Space,Str "default."] ,Para [Str "And",Space,Str "now",Space,Str "some-invalid-string-3231231",Space,Str "is",Space,Str "nonsense."] +,Null +,Para [Str "And",Space,Str "now",Space,Str "with",Space,RawInline (Format "html") "<b>inline</b> <span id=\"test\">HTML</span>",Str "."] +,Null +,Para [Str "And",Space,Str "some",Space,Str "inline",Space,Str "haskell",Space,Code ("",["haskell","sourceCode"],[]) "fmap id [1,2..10]",Str "."] +,Null +,Null +,Para [Str "Indirect",Space,Str "python",Space,Str "role",Space,Code ("",["python","indirect","sourceCode"],[]) "[x*x for x in [1,2,3,4,5]]",Str "."] +,Null +,Null +,Para [Str "Different",Space,Str "indirect",Space,Str "C",Space,Code ("",["c","different-indirect","sourceCode"],[]) "int x = 15;",Str "."] ,Header 2 ("literal-symbols",[],[]) [Str "Literal",Space,Str "symbols"] ,Para [Str "2*2",Space,Str "=",Space,Str "4*1"]] diff --git a/tests/rst-reader.rst b/tests/rst-reader.rst index 748bfe0a5..930bf2ed2 100644 --- a/tests/rst-reader.rst +++ b/tests/rst-reader.rst @@ -599,6 +599,30 @@ Reset default-role to the default default. And now `some-invalid-string-3231231` is nonsense. +.. role:: html(raw) + :format: html + +And now with :html:`<b>inline</b> <span id="test">HTML</span>`. + +.. role:: haskell(code) + :language: haskell + +And some inline haskell :haskell:`fmap id [1,2..10]`. + +.. role:: indirect(code) + +.. role:: python(indirect) + :language: python + +Indirect python role :python:`[x*x for x in [1,2,3,4,5]]`. + +.. role:: different-indirect(code) + :language: c + +.. role:: c(different-indirect) + +Different indirect C :c:`int x = 15;`. + Literal symbols --------------- diff --git a/tests/s5.basic.html b/tests/s5-basic.html index ceb896b8e..ceb896b8e 100644 --- a/tests/s5.basic.html +++ b/tests/s5-basic.html diff --git a/tests/s5.fancy.html b/tests/s5-fancy.html index 818cca04a..818cca04a 100644 --- a/tests/s5.fancy.html +++ b/tests/s5-fancy.html diff --git a/tests/s5.fragment.html b/tests/s5-fragment.html index e8a888972..e8a888972 100644 --- a/tests/s5.fragment.html +++ b/tests/s5-fragment.html diff --git a/tests/s5.inserts.html b/tests/s5-inserts.html index 455225f9b..455225f9b 100644 --- a/tests/s5.inserts.html +++ b/tests/s5-inserts.html diff --git a/tests/tables.asciidoc b/tests/tables.asciidoc index 38daca192..2a24544a3 100644 --- a/tests/tables.asciidoc +++ b/tests/tables.asciidoc @@ -52,20 +52,16 @@ Multiline table without caption: Table without column headers: [cols=">,<,^,>",] -|============================================================================= +|================== |12 |12 |12 |12 - |123 |123 |123 |123 - |1 |1 |1 |1 -|============================================================================= +|================== Multiline table without column headers: [width="78%",cols="^21%,<17%,>20%,42%",] -|============================================================================= +|======================================================================= |First |row |12.0 |Example of a row that spans multiple lines. - |Second |row |5.0 |Here's another one. Note the blank line between rows. -|============================================================================= - +|======================================================================= diff --git a/tests/tables.dokuwiki b/tests/tables.dokuwiki new file mode 100644 index 000000000..21e61f656 --- /dev/null +++ b/tests/tables.dokuwiki @@ -0,0 +1,47 @@ +Simple table with caption: + +Demonstration of simple table syntax. +^ Right^Left ^ Center ^Default^ +| 12|12 | 12 |12 | +| 123|123 | 123 |123 | +| 1|1 | 1 |1 | + +Simple table without caption: + +^ Right^Left ^ Center ^Default^ +| 12|12 | 12 |12 | +| 123|123 | 123 |123 | +| 1|1 | 1 |1 | + +Simple table indented two spaces: + +Demonstration of simple table syntax. +^ Right^Left ^ Center ^Default^ +| 12|12 | 12 |12 | +| 123|123 | 123 |123 | +| 1|1 | 1 |1 | + +Multiline table with caption: + +Here's the caption. It may span multiple lines. +^ Centered Header ^Left Aligned ^ Right Aligned^Default aligned ^ +| First |row | 12.0|Example of a row that spans multiple lines. | +| Second |row | 5.0|Here's another one. Note the blank line between rows. | + +Multiline table without caption: + +^ Centered Header ^Left Aligned ^ Right Aligned^Default aligned ^ +| First |row | 12.0|Example of a row that spans multiple lines. | +| Second |row | 5.0|Here's another one. Note the blank line between rows. | + +Table without column headers: + +| 12|12 | 12 | 12| +| 123|123 | 123 | 123| +| 1|1 | 1 | 1| + +Multiline table without column headers: + +| First |row | 12.0|Example of a row that spans multiple lines. | +| Second |row | 5.0|Here's another one. Note the blank line between rows.| + diff --git a/tests/tables.haddock b/tests/tables.haddock new file mode 100644 index 000000000..f9efdc0de --- /dev/null +++ b/tests/tables.haddock @@ -0,0 +1,76 @@ +Simple table with caption: + +> Right Left Center Default +> ------- ------ -------- --------- +> 12 12 12 12 +> 123 123 123 123 +> 1 1 1 1 +> +> Demonstration of simple table syntax. + +Simple table without caption: + +> Right Left Center Default +> ------- ------ -------- --------- +> 12 12 12 12 +> 123 123 123 123 +> 1 1 1 1 + +Simple table indented two spaces: + +> Right Left Center Default +> ------- ------ -------- --------- +> 12 12 12 12 +> 123 123 123 123 +> 1 1 1 1 +> +> Demonstration of simple table syntax. + +Multiline table with caption: + +> -------------------------------------------------------------- +> Centered Left Right Default aligned +> Header Aligned Aligned +> ----------- ---------- ------------ -------------------------- +> First row 12.0 Example of a row that +> spans multiple lines. +> +> Second row 5.0 Here\'s another one. Note +> the blank line between +> rows. +> -------------------------------------------------------------- +> +> Here\'s the caption. It may span multiple lines. + +Multiline table without caption: + +> -------------------------------------------------------------- +> Centered Left Right Default aligned +> Header Aligned Aligned +> ----------- ---------- ------------ -------------------------- +> First row 12.0 Example of a row that +> spans multiple lines. +> +> Second row 5.0 Here\'s another one. Note +> the blank line between +> rows. +> -------------------------------------------------------------- + +Table without column headers: + +> ----- ----- ----- ----- +> 12 12 12 12 +> 123 123 123 123 +> 1 1 1 1 +> ----- ----- ----- ----- + +Multiline table without column headers: + +> ----------- ---------- ------------ -------------------------- +> First row 12.0 Example of a row that +> spans multiple lines. +> +> Second row 5.0 Here\'s another one. Note +> the blank line between +> rows. +> ----------- ---------- ------------ -------------------------- diff --git a/tests/tables.html b/tests/tables.html index b72aa784e..a9b2b247d 100644 --- a/tests/tables.html +++ b/tests/tables.html @@ -96,10 +96,12 @@ <p>Multiline table with caption:</p> <table> <caption>Here's the caption. It may span multiple lines.</caption> +<colgroup> <col width="15%" /> <col width="13%" /> <col width="16%" /> <col width="33%" /> +</colgroup> <thead> <tr class="header"> <th align="center">Centered Header</th> @@ -125,10 +127,12 @@ </table> <p>Multiline table without caption:</p> <table> +<colgroup> <col width="15%" /> <col width="13%" /> <col width="16%" /> <col width="33%" /> +</colgroup> <thead> <tr class="header"> <th align="center">Centered Header</th> @@ -177,10 +181,12 @@ </table> <p>Multiline table without column headers:</p> <table> +<colgroup> <col width="15%" /> <col width="13%" /> <col width="16%" /> <col width="33%" /> +</colgroup> <tbody> <tr class="odd"> <td align="center">First</td> diff --git a/tests/tables.icml b/tests/tables.icml new file mode 100644 index 000000000..eb73af670 --- /dev/null +++ b/tests/tables.icml @@ -0,0 +1,748 @@ +<ParagraphStyleRange AppliedParagraphStyle="ParagraphStyle/Paragraph"> + <CharacterStyleRange AppliedCharacterStyle="$ID/NormalCharacterStyle"> + <Content>Simple table with caption:</Content> + </CharacterStyleRange><Br /> +</ParagraphStyleRange> +<Table AppliedTableStyle="TableStyle/Table" HeaderRowCount="1" BodyRowCount="3" ColumnCount="4"> + <Column Name="0" /> + <Column Name="1" /> + <Column Name="2" /> + <Column Name="3" /> + <Cell Name="0:0" AppliedCellStyle="CellStyle/Cell"> + <ParagraphStyleRange AppliedParagraphStyle="ParagraphStyle/TablePar > TableHeader > RightAlign"> + <CharacterStyleRange AppliedCharacterStyle="$ID/NormalCharacterStyle"> + <Content>Right</Content> + </CharacterStyleRange><Br /> + </ParagraphStyleRange> + </Cell> + <Cell Name="1:0" AppliedCellStyle="CellStyle/Cell"> + <ParagraphStyleRange AppliedParagraphStyle="ParagraphStyle/TablePar > TableHeader > LeftAlign"> + <CharacterStyleRange AppliedCharacterStyle="$ID/NormalCharacterStyle"> + <Content>Left</Content> + </CharacterStyleRange><Br /> + </ParagraphStyleRange> + </Cell> + <Cell Name="2:0" AppliedCellStyle="CellStyle/Cell"> + <ParagraphStyleRange AppliedParagraphStyle="ParagraphStyle/TablePar > TableHeader > CenterAlign"> + <CharacterStyleRange AppliedCharacterStyle="$ID/NormalCharacterStyle"> + <Content>Center</Content> + </CharacterStyleRange><Br /> + </ParagraphStyleRange> + </Cell> + <Cell Name="3:0" AppliedCellStyle="CellStyle/Cell"> + <ParagraphStyleRange AppliedParagraphStyle="ParagraphStyle/TablePar > TableHeader"> + <CharacterStyleRange AppliedCharacterStyle="$ID/NormalCharacterStyle"> + <Content>Default</Content> + </CharacterStyleRange><Br /> + </ParagraphStyleRange> + </Cell> + <Cell Name="0:1" AppliedCellStyle="CellStyle/Cell"> + <ParagraphStyleRange AppliedParagraphStyle="ParagraphStyle/TablePar > RightAlign"> + <CharacterStyleRange AppliedCharacterStyle="$ID/NormalCharacterStyle"> + <Content>12</Content> + </CharacterStyleRange><Br /> + </ParagraphStyleRange> + </Cell> + <Cell Name="1:1" AppliedCellStyle="CellStyle/Cell"> + <ParagraphStyleRange AppliedParagraphStyle="ParagraphStyle/TablePar > LeftAlign"> + <CharacterStyleRange AppliedCharacterStyle="$ID/NormalCharacterStyle"> + <Content>12</Content> + </CharacterStyleRange><Br /> + </ParagraphStyleRange> + </Cell> + <Cell Name="2:1" AppliedCellStyle="CellStyle/Cell"> + <ParagraphStyleRange AppliedParagraphStyle="ParagraphStyle/TablePar > CenterAlign"> + <CharacterStyleRange AppliedCharacterStyle="$ID/NormalCharacterStyle"> + <Content>12</Content> + </CharacterStyleRange><Br /> + </ParagraphStyleRange> + </Cell> + <Cell Name="3:1" AppliedCellStyle="CellStyle/Cell"> + <ParagraphStyleRange AppliedParagraphStyle="ParagraphStyle/TablePar"> + <CharacterStyleRange AppliedCharacterStyle="$ID/NormalCharacterStyle"> + <Content>12</Content> + </CharacterStyleRange><Br /> + </ParagraphStyleRange> + </Cell> + <Cell Name="0:2" AppliedCellStyle="CellStyle/Cell"> + <ParagraphStyleRange AppliedParagraphStyle="ParagraphStyle/TablePar > RightAlign"> + <CharacterStyleRange AppliedCharacterStyle="$ID/NormalCharacterStyle"> + <Content>123</Content> + </CharacterStyleRange><Br /> + </ParagraphStyleRange> + </Cell> + <Cell Name="1:2" AppliedCellStyle="CellStyle/Cell"> + <ParagraphStyleRange AppliedParagraphStyle="ParagraphStyle/TablePar > LeftAlign"> + <CharacterStyleRange AppliedCharacterStyle="$ID/NormalCharacterStyle"> + <Content>123</Content> + </CharacterStyleRange><Br /> + </ParagraphStyleRange> + </Cell> + <Cell Name="2:2" AppliedCellStyle="CellStyle/Cell"> + <ParagraphStyleRange AppliedParagraphStyle="ParagraphStyle/TablePar > CenterAlign"> + <CharacterStyleRange AppliedCharacterStyle="$ID/NormalCharacterStyle"> + <Content>123</Content> + </CharacterStyleRange><Br /> + </ParagraphStyleRange> + </Cell> + <Cell Name="3:2" AppliedCellStyle="CellStyle/Cell"> + <ParagraphStyleRange AppliedParagraphStyle="ParagraphStyle/TablePar"> + <CharacterStyleRange AppliedCharacterStyle="$ID/NormalCharacterStyle"> + <Content>123</Content> + </CharacterStyleRange><Br /> + </ParagraphStyleRange> + </Cell> + <Cell Name="0:3" AppliedCellStyle="CellStyle/Cell"> + <ParagraphStyleRange AppliedParagraphStyle="ParagraphStyle/TablePar > RightAlign"> + <CharacterStyleRange AppliedCharacterStyle="$ID/NormalCharacterStyle"> + <Content>1</Content> + </CharacterStyleRange><Br /> + </ParagraphStyleRange> + </Cell> + <Cell Name="1:3" AppliedCellStyle="CellStyle/Cell"> + <ParagraphStyleRange AppliedParagraphStyle="ParagraphStyle/TablePar > LeftAlign"> + <CharacterStyleRange AppliedCharacterStyle="$ID/NormalCharacterStyle"> + <Content>1</Content> + </CharacterStyleRange><Br /> + </ParagraphStyleRange> + </Cell> + <Cell Name="2:3" AppliedCellStyle="CellStyle/Cell"> + <ParagraphStyleRange AppliedParagraphStyle="ParagraphStyle/TablePar > CenterAlign"> + <CharacterStyleRange AppliedCharacterStyle="$ID/NormalCharacterStyle"> + <Content>1</Content> + </CharacterStyleRange><Br /> + </ParagraphStyleRange> + </Cell> + <Cell Name="3:3" AppliedCellStyle="CellStyle/Cell"> + <ParagraphStyleRange AppliedParagraphStyle="ParagraphStyle/TablePar"> + <CharacterStyleRange AppliedCharacterStyle="$ID/NormalCharacterStyle"> + <Content>1</Content> + </CharacterStyleRange><Br /> + </ParagraphStyleRange> + </Cell> +</Table> +<ParagraphStyleRange AppliedParagraphStyle="ParagraphStyle/TableCaption"> + <CharacterStyleRange AppliedCharacterStyle="$ID/NormalCharacterStyle"> + <Content>Demonstration of simple table syntax.</Content> + </CharacterStyleRange><Br /> +</ParagraphStyleRange> +<ParagraphStyleRange AppliedParagraphStyle="ParagraphStyle/Paragraph"> + <CharacterStyleRange AppliedCharacterStyle="$ID/NormalCharacterStyle"> + <Content>Simple table without caption:</Content> + </CharacterStyleRange><Br /> +</ParagraphStyleRange> +<Table AppliedTableStyle="TableStyle/Table" HeaderRowCount="1" BodyRowCount="3" ColumnCount="4"> + <Column Name="0" /> + <Column Name="1" /> + <Column Name="2" /> + <Column Name="3" /> + <Cell Name="0:0" AppliedCellStyle="CellStyle/Cell"> + <ParagraphStyleRange AppliedParagraphStyle="ParagraphStyle/TablePar > TableHeader > RightAlign"> + <CharacterStyleRange AppliedCharacterStyle="$ID/NormalCharacterStyle"> + <Content>Right</Content> + </CharacterStyleRange><Br /> + </ParagraphStyleRange> + </Cell> + <Cell Name="1:0" AppliedCellStyle="CellStyle/Cell"> + <ParagraphStyleRange AppliedParagraphStyle="ParagraphStyle/TablePar > TableHeader > LeftAlign"> + <CharacterStyleRange AppliedCharacterStyle="$ID/NormalCharacterStyle"> + <Content>Left</Content> + </CharacterStyleRange><Br /> + </ParagraphStyleRange> + </Cell> + <Cell Name="2:0" AppliedCellStyle="CellStyle/Cell"> + <ParagraphStyleRange AppliedParagraphStyle="ParagraphStyle/TablePar > TableHeader > CenterAlign"> + <CharacterStyleRange AppliedCharacterStyle="$ID/NormalCharacterStyle"> + <Content>Center</Content> + </CharacterStyleRange><Br /> + </ParagraphStyleRange> + </Cell> + <Cell Name="3:0" AppliedCellStyle="CellStyle/Cell"> + <ParagraphStyleRange AppliedParagraphStyle="ParagraphStyle/TablePar > TableHeader"> + <CharacterStyleRange AppliedCharacterStyle="$ID/NormalCharacterStyle"> + <Content>Default</Content> + </CharacterStyleRange><Br /> + </ParagraphStyleRange> + </Cell> + <Cell Name="0:1" AppliedCellStyle="CellStyle/Cell"> + <ParagraphStyleRange AppliedParagraphStyle="ParagraphStyle/TablePar > RightAlign"> + <CharacterStyleRange AppliedCharacterStyle="$ID/NormalCharacterStyle"> + <Content>12</Content> + </CharacterStyleRange><Br /> + </ParagraphStyleRange> + </Cell> + <Cell Name="1:1" AppliedCellStyle="CellStyle/Cell"> + <ParagraphStyleRange AppliedParagraphStyle="ParagraphStyle/TablePar > LeftAlign"> + <CharacterStyleRange AppliedCharacterStyle="$ID/NormalCharacterStyle"> + <Content>12</Content> + </CharacterStyleRange><Br /> + </ParagraphStyleRange> + </Cell> + <Cell Name="2:1" AppliedCellStyle="CellStyle/Cell"> + <ParagraphStyleRange AppliedParagraphStyle="ParagraphStyle/TablePar > CenterAlign"> + <CharacterStyleRange AppliedCharacterStyle="$ID/NormalCharacterStyle"> + <Content>12</Content> + </CharacterStyleRange><Br /> + </ParagraphStyleRange> + </Cell> + <Cell Name="3:1" AppliedCellStyle="CellStyle/Cell"> + <ParagraphStyleRange AppliedParagraphStyle="ParagraphStyle/TablePar"> + <CharacterStyleRange AppliedCharacterStyle="$ID/NormalCharacterStyle"> + <Content>12</Content> + </CharacterStyleRange><Br /> + </ParagraphStyleRange> + </Cell> + <Cell Name="0:2" AppliedCellStyle="CellStyle/Cell"> + <ParagraphStyleRange AppliedParagraphStyle="ParagraphStyle/TablePar > RightAlign"> + <CharacterStyleRange AppliedCharacterStyle="$ID/NormalCharacterStyle"> + <Content>123</Content> + </CharacterStyleRange><Br /> + </ParagraphStyleRange> + </Cell> + <Cell Name="1:2" AppliedCellStyle="CellStyle/Cell"> + <ParagraphStyleRange AppliedParagraphStyle="ParagraphStyle/TablePar > LeftAlign"> + <CharacterStyleRange AppliedCharacterStyle="$ID/NormalCharacterStyle"> + <Content>123</Content> + </CharacterStyleRange><Br /> + </ParagraphStyleRange> + </Cell> + <Cell Name="2:2" AppliedCellStyle="CellStyle/Cell"> + <ParagraphStyleRange AppliedParagraphStyle="ParagraphStyle/TablePar > CenterAlign"> + <CharacterStyleRange AppliedCharacterStyle="$ID/NormalCharacterStyle"> + <Content>123</Content> + </CharacterStyleRange><Br /> + </ParagraphStyleRange> + </Cell> + <Cell Name="3:2" AppliedCellStyle="CellStyle/Cell"> + <ParagraphStyleRange AppliedParagraphStyle="ParagraphStyle/TablePar"> + <CharacterStyleRange AppliedCharacterStyle="$ID/NormalCharacterStyle"> + <Content>123</Content> + </CharacterStyleRange><Br /> + </ParagraphStyleRange> + </Cell> + <Cell Name="0:3" AppliedCellStyle="CellStyle/Cell"> + <ParagraphStyleRange AppliedParagraphStyle="ParagraphStyle/TablePar > RightAlign"> + <CharacterStyleRange AppliedCharacterStyle="$ID/NormalCharacterStyle"> + <Content>1</Content> + </CharacterStyleRange><Br /> + </ParagraphStyleRange> + </Cell> + <Cell Name="1:3" AppliedCellStyle="CellStyle/Cell"> + <ParagraphStyleRange AppliedParagraphStyle="ParagraphStyle/TablePar > LeftAlign"> + <CharacterStyleRange AppliedCharacterStyle="$ID/NormalCharacterStyle"> + <Content>1</Content> + </CharacterStyleRange><Br /> + </ParagraphStyleRange> + </Cell> + <Cell Name="2:3" AppliedCellStyle="CellStyle/Cell"> + <ParagraphStyleRange AppliedParagraphStyle="ParagraphStyle/TablePar > CenterAlign"> + <CharacterStyleRange AppliedCharacterStyle="$ID/NormalCharacterStyle"> + <Content>1</Content> + </CharacterStyleRange><Br /> + </ParagraphStyleRange> + </Cell> + <Cell Name="3:3" AppliedCellStyle="CellStyle/Cell"> + <ParagraphStyleRange AppliedParagraphStyle="ParagraphStyle/TablePar"> + <CharacterStyleRange AppliedCharacterStyle="$ID/NormalCharacterStyle"> + <Content>1</Content> + </CharacterStyleRange><Br /> + </ParagraphStyleRange> + </Cell> +</Table> +<ParagraphStyleRange AppliedParagraphStyle="ParagraphStyle/TableCaption"> + <Br /> +</ParagraphStyleRange> +<ParagraphStyleRange AppliedParagraphStyle="ParagraphStyle/Paragraph"> + <CharacterStyleRange AppliedCharacterStyle="$ID/NormalCharacterStyle"> + <Content>Simple table indented two spaces:</Content> + </CharacterStyleRange><Br /> +</ParagraphStyleRange> +<Table AppliedTableStyle="TableStyle/Table" HeaderRowCount="1" BodyRowCount="3" ColumnCount="4"> + <Column Name="0" /> + <Column Name="1" /> + <Column Name="2" /> + <Column Name="3" /> + <Cell Name="0:0" AppliedCellStyle="CellStyle/Cell"> + <ParagraphStyleRange AppliedParagraphStyle="ParagraphStyle/TablePar > TableHeader > RightAlign"> + <CharacterStyleRange AppliedCharacterStyle="$ID/NormalCharacterStyle"> + <Content>Right</Content> + </CharacterStyleRange><Br /> + </ParagraphStyleRange> + </Cell> + <Cell Name="1:0" AppliedCellStyle="CellStyle/Cell"> + <ParagraphStyleRange AppliedParagraphStyle="ParagraphStyle/TablePar > TableHeader > LeftAlign"> + <CharacterStyleRange AppliedCharacterStyle="$ID/NormalCharacterStyle"> + <Content>Left</Content> + </CharacterStyleRange><Br /> + </ParagraphStyleRange> + </Cell> + <Cell Name="2:0" AppliedCellStyle="CellStyle/Cell"> + <ParagraphStyleRange AppliedParagraphStyle="ParagraphStyle/TablePar > TableHeader > CenterAlign"> + <CharacterStyleRange AppliedCharacterStyle="$ID/NormalCharacterStyle"> + <Content>Center</Content> + </CharacterStyleRange><Br /> + </ParagraphStyleRange> + </Cell> + <Cell Name="3:0" AppliedCellStyle="CellStyle/Cell"> + <ParagraphStyleRange AppliedParagraphStyle="ParagraphStyle/TablePar > TableHeader"> + <CharacterStyleRange AppliedCharacterStyle="$ID/NormalCharacterStyle"> + <Content>Default</Content> + </CharacterStyleRange><Br /> + </ParagraphStyleRange> + </Cell> + <Cell Name="0:1" AppliedCellStyle="CellStyle/Cell"> + <ParagraphStyleRange AppliedParagraphStyle="ParagraphStyle/TablePar > RightAlign"> + <CharacterStyleRange AppliedCharacterStyle="$ID/NormalCharacterStyle"> + <Content>12</Content> + </CharacterStyleRange><Br /> + </ParagraphStyleRange> + </Cell> + <Cell Name="1:1" AppliedCellStyle="CellStyle/Cell"> + <ParagraphStyleRange AppliedParagraphStyle="ParagraphStyle/TablePar > LeftAlign"> + <CharacterStyleRange AppliedCharacterStyle="$ID/NormalCharacterStyle"> + <Content>12</Content> + </CharacterStyleRange><Br /> + </ParagraphStyleRange> + </Cell> + <Cell Name="2:1" AppliedCellStyle="CellStyle/Cell"> + <ParagraphStyleRange AppliedParagraphStyle="ParagraphStyle/TablePar > CenterAlign"> + <CharacterStyleRange AppliedCharacterStyle="$ID/NormalCharacterStyle"> + <Content>12</Content> + </CharacterStyleRange><Br /> + </ParagraphStyleRange> + </Cell> + <Cell Name="3:1" AppliedCellStyle="CellStyle/Cell"> + <ParagraphStyleRange AppliedParagraphStyle="ParagraphStyle/TablePar"> + <CharacterStyleRange AppliedCharacterStyle="$ID/NormalCharacterStyle"> + <Content>12</Content> + </CharacterStyleRange><Br /> + </ParagraphStyleRange> + </Cell> + <Cell Name="0:2" AppliedCellStyle="CellStyle/Cell"> + <ParagraphStyleRange AppliedParagraphStyle="ParagraphStyle/TablePar > RightAlign"> + <CharacterStyleRange AppliedCharacterStyle="$ID/NormalCharacterStyle"> + <Content>123</Content> + </CharacterStyleRange><Br /> + </ParagraphStyleRange> + </Cell> + <Cell Name="1:2" AppliedCellStyle="CellStyle/Cell"> + <ParagraphStyleRange AppliedParagraphStyle="ParagraphStyle/TablePar > LeftAlign"> + <CharacterStyleRange AppliedCharacterStyle="$ID/NormalCharacterStyle"> + <Content>123</Content> + </CharacterStyleRange><Br /> + </ParagraphStyleRange> + </Cell> + <Cell Name="2:2" AppliedCellStyle="CellStyle/Cell"> + <ParagraphStyleRange AppliedParagraphStyle="ParagraphStyle/TablePar > CenterAlign"> + <CharacterStyleRange AppliedCharacterStyle="$ID/NormalCharacterStyle"> + <Content>123</Content> + </CharacterStyleRange><Br /> + </ParagraphStyleRange> + </Cell> + <Cell Name="3:2" AppliedCellStyle="CellStyle/Cell"> + <ParagraphStyleRange AppliedParagraphStyle="ParagraphStyle/TablePar"> + <CharacterStyleRange AppliedCharacterStyle="$ID/NormalCharacterStyle"> + <Content>123</Content> + </CharacterStyleRange><Br /> + </ParagraphStyleRange> + </Cell> + <Cell Name="0:3" AppliedCellStyle="CellStyle/Cell"> + <ParagraphStyleRange AppliedParagraphStyle="ParagraphStyle/TablePar > RightAlign"> + <CharacterStyleRange AppliedCharacterStyle="$ID/NormalCharacterStyle"> + <Content>1</Content> + </CharacterStyleRange><Br /> + </ParagraphStyleRange> + </Cell> + <Cell Name="1:3" AppliedCellStyle="CellStyle/Cell"> + <ParagraphStyleRange AppliedParagraphStyle="ParagraphStyle/TablePar > LeftAlign"> + <CharacterStyleRange AppliedCharacterStyle="$ID/NormalCharacterStyle"> + <Content>1</Content> + </CharacterStyleRange><Br /> + </ParagraphStyleRange> + </Cell> + <Cell Name="2:3" AppliedCellStyle="CellStyle/Cell"> + <ParagraphStyleRange AppliedParagraphStyle="ParagraphStyle/TablePar > CenterAlign"> + <CharacterStyleRange AppliedCharacterStyle="$ID/NormalCharacterStyle"> + <Content>1</Content> + </CharacterStyleRange><Br /> + </ParagraphStyleRange> + </Cell> + <Cell Name="3:3" AppliedCellStyle="CellStyle/Cell"> + <ParagraphStyleRange AppliedParagraphStyle="ParagraphStyle/TablePar"> + <CharacterStyleRange AppliedCharacterStyle="$ID/NormalCharacterStyle"> + <Content>1</Content> + </CharacterStyleRange><Br /> + </ParagraphStyleRange> + </Cell> +</Table> +<ParagraphStyleRange AppliedParagraphStyle="ParagraphStyle/TableCaption"> + <CharacterStyleRange AppliedCharacterStyle="$ID/NormalCharacterStyle"> + <Content>Demonstration of simple table syntax.</Content> + </CharacterStyleRange><Br /> +</ParagraphStyleRange> +<ParagraphStyleRange AppliedParagraphStyle="ParagraphStyle/Paragraph"> + <CharacterStyleRange AppliedCharacterStyle="$ID/NormalCharacterStyle"> + <Content>Multiline table with caption:</Content> + </CharacterStyleRange><Br /> +</ParagraphStyleRange> +<Table AppliedTableStyle="TableStyle/Table" HeaderRowCount="1" BodyRowCount="2" ColumnCount="4"> + <Column Name="0" SingleColumnWidth="75.0" /> + <Column Name="1" SingleColumnWidth="68.75" /> + <Column Name="2" SingleColumnWidth="81.25" /> + <Column Name="3" SingleColumnWidth="168.75" /> + <Cell Name="0:0" AppliedCellStyle="CellStyle/Cell"> + <ParagraphStyleRange AppliedParagraphStyle="ParagraphStyle/TablePar > TableHeader > CenterAlign"> + <CharacterStyleRange AppliedCharacterStyle="$ID/NormalCharacterStyle"> + <Content>Centered Header</Content> + </CharacterStyleRange><Br /> + </ParagraphStyleRange> + </Cell> + <Cell Name="1:0" AppliedCellStyle="CellStyle/Cell"> + <ParagraphStyleRange AppliedParagraphStyle="ParagraphStyle/TablePar > TableHeader > LeftAlign"> + <CharacterStyleRange AppliedCharacterStyle="$ID/NormalCharacterStyle"> + <Content>Left Aligned</Content> + </CharacterStyleRange><Br /> + </ParagraphStyleRange> + </Cell> + <Cell Name="2:0" AppliedCellStyle="CellStyle/Cell"> + <ParagraphStyleRange AppliedParagraphStyle="ParagraphStyle/TablePar > TableHeader > RightAlign"> + <CharacterStyleRange AppliedCharacterStyle="$ID/NormalCharacterStyle"> + <Content>Right Aligned</Content> + </CharacterStyleRange><Br /> + </ParagraphStyleRange> + </Cell> + <Cell Name="3:0" AppliedCellStyle="CellStyle/Cell"> + <ParagraphStyleRange AppliedParagraphStyle="ParagraphStyle/TablePar > TableHeader > LeftAlign"> + <CharacterStyleRange AppliedCharacterStyle="$ID/NormalCharacterStyle"> + <Content>Default aligned</Content> + </CharacterStyleRange><Br /> + </ParagraphStyleRange> + </Cell> + <Cell Name="0:1" AppliedCellStyle="CellStyle/Cell"> + <ParagraphStyleRange AppliedParagraphStyle="ParagraphStyle/TablePar > CenterAlign"> + <CharacterStyleRange AppliedCharacterStyle="$ID/NormalCharacterStyle"> + <Content>First</Content> + </CharacterStyleRange><Br /> + </ParagraphStyleRange> + </Cell> + <Cell Name="1:1" AppliedCellStyle="CellStyle/Cell"> + <ParagraphStyleRange AppliedParagraphStyle="ParagraphStyle/TablePar > LeftAlign"> + <CharacterStyleRange AppliedCharacterStyle="$ID/NormalCharacterStyle"> + <Content>row</Content> + </CharacterStyleRange><Br /> + </ParagraphStyleRange> + </Cell> + <Cell Name="2:1" AppliedCellStyle="CellStyle/Cell"> + <ParagraphStyleRange AppliedParagraphStyle="ParagraphStyle/TablePar > RightAlign"> + <CharacterStyleRange AppliedCharacterStyle="$ID/NormalCharacterStyle"> + <Content>12.0</Content> + </CharacterStyleRange><Br /> + </ParagraphStyleRange> + </Cell> + <Cell Name="3:1" AppliedCellStyle="CellStyle/Cell"> + <ParagraphStyleRange AppliedParagraphStyle="ParagraphStyle/TablePar > LeftAlign"> + <CharacterStyleRange AppliedCharacterStyle="$ID/NormalCharacterStyle"> + <Content>Example of a row that spans multiple lines.</Content> + </CharacterStyleRange><Br /> + </ParagraphStyleRange> + </Cell> + <Cell Name="0:2" AppliedCellStyle="CellStyle/Cell"> + <ParagraphStyleRange AppliedParagraphStyle="ParagraphStyle/TablePar > CenterAlign"> + <CharacterStyleRange AppliedCharacterStyle="$ID/NormalCharacterStyle"> + <Content>Second</Content> + </CharacterStyleRange><Br /> + </ParagraphStyleRange> + </Cell> + <Cell Name="1:2" AppliedCellStyle="CellStyle/Cell"> + <ParagraphStyleRange AppliedParagraphStyle="ParagraphStyle/TablePar > LeftAlign"> + <CharacterStyleRange AppliedCharacterStyle="$ID/NormalCharacterStyle"> + <Content>row</Content> + </CharacterStyleRange><Br /> + </ParagraphStyleRange> + </Cell> + <Cell Name="2:2" AppliedCellStyle="CellStyle/Cell"> + <ParagraphStyleRange AppliedParagraphStyle="ParagraphStyle/TablePar > RightAlign"> + <CharacterStyleRange AppliedCharacterStyle="$ID/NormalCharacterStyle"> + <Content>5.0</Content> + </CharacterStyleRange><Br /> + </ParagraphStyleRange> + </Cell> + <Cell Name="3:2" AppliedCellStyle="CellStyle/Cell"> + <ParagraphStyleRange AppliedParagraphStyle="ParagraphStyle/TablePar > LeftAlign"> + <CharacterStyleRange AppliedCharacterStyle="$ID/NormalCharacterStyle"> + <Content>Here's another one. Note the blank line between rows.</Content> + </CharacterStyleRange><Br /> + </ParagraphStyleRange> + </Cell> +</Table> +<ParagraphStyleRange AppliedParagraphStyle="ParagraphStyle/TableCaption"> + <CharacterStyleRange AppliedCharacterStyle="$ID/NormalCharacterStyle"> + <Content>Here's the caption. It may span multiple lines.</Content> + </CharacterStyleRange><Br /> +</ParagraphStyleRange> +<ParagraphStyleRange AppliedParagraphStyle="ParagraphStyle/Paragraph"> + <CharacterStyleRange AppliedCharacterStyle="$ID/NormalCharacterStyle"> + <Content>Multiline table without caption:</Content> + </CharacterStyleRange><Br /> +</ParagraphStyleRange> +<Table AppliedTableStyle="TableStyle/Table" HeaderRowCount="1" BodyRowCount="2" ColumnCount="4"> + <Column Name="0" SingleColumnWidth="75.0" /> + <Column Name="1" SingleColumnWidth="68.75" /> + <Column Name="2" SingleColumnWidth="81.25" /> + <Column Name="3" SingleColumnWidth="168.75" /> + <Cell Name="0:0" AppliedCellStyle="CellStyle/Cell"> + <ParagraphStyleRange AppliedParagraphStyle="ParagraphStyle/TablePar > TableHeader > CenterAlign"> + <CharacterStyleRange AppliedCharacterStyle="$ID/NormalCharacterStyle"> + <Content>Centered Header</Content> + </CharacterStyleRange><Br /> + </ParagraphStyleRange> + </Cell> + <Cell Name="1:0" AppliedCellStyle="CellStyle/Cell"> + <ParagraphStyleRange AppliedParagraphStyle="ParagraphStyle/TablePar > TableHeader > LeftAlign"> + <CharacterStyleRange AppliedCharacterStyle="$ID/NormalCharacterStyle"> + <Content>Left Aligned</Content> + </CharacterStyleRange><Br /> + </ParagraphStyleRange> + </Cell> + <Cell Name="2:0" AppliedCellStyle="CellStyle/Cell"> + <ParagraphStyleRange AppliedParagraphStyle="ParagraphStyle/TablePar > TableHeader > RightAlign"> + <CharacterStyleRange AppliedCharacterStyle="$ID/NormalCharacterStyle"> + <Content>Right Aligned</Content> + </CharacterStyleRange><Br /> + </ParagraphStyleRange> + </Cell> + <Cell Name="3:0" AppliedCellStyle="CellStyle/Cell"> + <ParagraphStyleRange AppliedParagraphStyle="ParagraphStyle/TablePar > TableHeader > LeftAlign"> + <CharacterStyleRange AppliedCharacterStyle="$ID/NormalCharacterStyle"> + <Content>Default aligned</Content> + </CharacterStyleRange><Br /> + </ParagraphStyleRange> + </Cell> + <Cell Name="0:1" AppliedCellStyle="CellStyle/Cell"> + <ParagraphStyleRange AppliedParagraphStyle="ParagraphStyle/TablePar > CenterAlign"> + <CharacterStyleRange AppliedCharacterStyle="$ID/NormalCharacterStyle"> + <Content>First</Content> + </CharacterStyleRange><Br /> + </ParagraphStyleRange> + </Cell> + <Cell Name="1:1" AppliedCellStyle="CellStyle/Cell"> + <ParagraphStyleRange AppliedParagraphStyle="ParagraphStyle/TablePar > LeftAlign"> + <CharacterStyleRange AppliedCharacterStyle="$ID/NormalCharacterStyle"> + <Content>row</Content> + </CharacterStyleRange><Br /> + </ParagraphStyleRange> + </Cell> + <Cell Name="2:1" AppliedCellStyle="CellStyle/Cell"> + <ParagraphStyleRange AppliedParagraphStyle="ParagraphStyle/TablePar > RightAlign"> + <CharacterStyleRange AppliedCharacterStyle="$ID/NormalCharacterStyle"> + <Content>12.0</Content> + </CharacterStyleRange><Br /> + </ParagraphStyleRange> + </Cell> + <Cell Name="3:1" AppliedCellStyle="CellStyle/Cell"> + <ParagraphStyleRange AppliedParagraphStyle="ParagraphStyle/TablePar > LeftAlign"> + <CharacterStyleRange AppliedCharacterStyle="$ID/NormalCharacterStyle"> + <Content>Example of a row that spans multiple lines.</Content> + </CharacterStyleRange><Br /> + </ParagraphStyleRange> + </Cell> + <Cell Name="0:2" AppliedCellStyle="CellStyle/Cell"> + <ParagraphStyleRange AppliedParagraphStyle="ParagraphStyle/TablePar > CenterAlign"> + <CharacterStyleRange AppliedCharacterStyle="$ID/NormalCharacterStyle"> + <Content>Second</Content> + </CharacterStyleRange><Br /> + </ParagraphStyleRange> + </Cell> + <Cell Name="1:2" AppliedCellStyle="CellStyle/Cell"> + <ParagraphStyleRange AppliedParagraphStyle="ParagraphStyle/TablePar > LeftAlign"> + <CharacterStyleRange AppliedCharacterStyle="$ID/NormalCharacterStyle"> + <Content>row</Content> + </CharacterStyleRange><Br /> + </ParagraphStyleRange> + </Cell> + <Cell Name="2:2" AppliedCellStyle="CellStyle/Cell"> + <ParagraphStyleRange AppliedParagraphStyle="ParagraphStyle/TablePar > RightAlign"> + <CharacterStyleRange AppliedCharacterStyle="$ID/NormalCharacterStyle"> + <Content>5.0</Content> + </CharacterStyleRange><Br /> + </ParagraphStyleRange> + </Cell> + <Cell Name="3:2" AppliedCellStyle="CellStyle/Cell"> + <ParagraphStyleRange AppliedParagraphStyle="ParagraphStyle/TablePar > LeftAlign"> + <CharacterStyleRange AppliedCharacterStyle="$ID/NormalCharacterStyle"> + <Content>Here's another one. Note the blank line between rows.</Content> + </CharacterStyleRange><Br /> + </ParagraphStyleRange> + </Cell> +</Table> +<ParagraphStyleRange AppliedParagraphStyle="ParagraphStyle/TableCaption"> + <Br /> +</ParagraphStyleRange> +<ParagraphStyleRange AppliedParagraphStyle="ParagraphStyle/Paragraph"> + <CharacterStyleRange AppliedCharacterStyle="$ID/NormalCharacterStyle"> + <Content>Table without column headers:</Content> + </CharacterStyleRange><Br /> +</ParagraphStyleRange> +<Table AppliedTableStyle="TableStyle/Table" HeaderRowCount="0" BodyRowCount="3" ColumnCount="4"> + <Column Name="0" /> + <Column Name="1" /> + <Column Name="2" /> + <Column Name="3" /> + <Cell Name="0:0" AppliedCellStyle="CellStyle/Cell"> + <ParagraphStyleRange AppliedParagraphStyle="ParagraphStyle/TablePar > RightAlign"> + <CharacterStyleRange AppliedCharacterStyle="$ID/NormalCharacterStyle"> + <Content>12</Content> + </CharacterStyleRange><Br /> + </ParagraphStyleRange> + </Cell> + <Cell Name="1:0" AppliedCellStyle="CellStyle/Cell"> + <ParagraphStyleRange AppliedParagraphStyle="ParagraphStyle/TablePar > LeftAlign"> + <CharacterStyleRange AppliedCharacterStyle="$ID/NormalCharacterStyle"> + <Content>12</Content> + </CharacterStyleRange><Br /> + </ParagraphStyleRange> + </Cell> + <Cell Name="2:0" AppliedCellStyle="CellStyle/Cell"> + <ParagraphStyleRange AppliedParagraphStyle="ParagraphStyle/TablePar > CenterAlign"> + <CharacterStyleRange AppliedCharacterStyle="$ID/NormalCharacterStyle"> + <Content>12</Content> + </CharacterStyleRange><Br /> + </ParagraphStyleRange> + </Cell> + <Cell Name="3:0" AppliedCellStyle="CellStyle/Cell"> + <ParagraphStyleRange AppliedParagraphStyle="ParagraphStyle/TablePar > RightAlign"> + <CharacterStyleRange AppliedCharacterStyle="$ID/NormalCharacterStyle"> + <Content>12</Content> + </CharacterStyleRange><Br /> + </ParagraphStyleRange> + </Cell> + <Cell Name="0:1" AppliedCellStyle="CellStyle/Cell"> + <ParagraphStyleRange AppliedParagraphStyle="ParagraphStyle/TablePar > RightAlign"> + <CharacterStyleRange AppliedCharacterStyle="$ID/NormalCharacterStyle"> + <Content>123</Content> + </CharacterStyleRange><Br /> + </ParagraphStyleRange> + </Cell> + <Cell Name="1:1" AppliedCellStyle="CellStyle/Cell"> + <ParagraphStyleRange AppliedParagraphStyle="ParagraphStyle/TablePar > LeftAlign"> + <CharacterStyleRange AppliedCharacterStyle="$ID/NormalCharacterStyle"> + <Content>123</Content> + </CharacterStyleRange><Br /> + </ParagraphStyleRange> + </Cell> + <Cell Name="2:1" AppliedCellStyle="CellStyle/Cell"> + <ParagraphStyleRange AppliedParagraphStyle="ParagraphStyle/TablePar > CenterAlign"> + <CharacterStyleRange AppliedCharacterStyle="$ID/NormalCharacterStyle"> + <Content>123</Content> + </CharacterStyleRange><Br /> + </ParagraphStyleRange> + </Cell> + <Cell Name="3:1" AppliedCellStyle="CellStyle/Cell"> + <ParagraphStyleRange AppliedParagraphStyle="ParagraphStyle/TablePar > RightAlign"> + <CharacterStyleRange AppliedCharacterStyle="$ID/NormalCharacterStyle"> + <Content>123</Content> + </CharacterStyleRange><Br /> + </ParagraphStyleRange> + </Cell> + <Cell Name="0:2" AppliedCellStyle="CellStyle/Cell"> + <ParagraphStyleRange AppliedParagraphStyle="ParagraphStyle/TablePar > RightAlign"> + <CharacterStyleRange AppliedCharacterStyle="$ID/NormalCharacterStyle"> + <Content>1</Content> + </CharacterStyleRange><Br /> + </ParagraphStyleRange> + </Cell> + <Cell Name="1:2" AppliedCellStyle="CellStyle/Cell"> + <ParagraphStyleRange AppliedParagraphStyle="ParagraphStyle/TablePar > LeftAlign"> + <CharacterStyleRange AppliedCharacterStyle="$ID/NormalCharacterStyle"> + <Content>1</Content> + </CharacterStyleRange><Br /> + </ParagraphStyleRange> + </Cell> + <Cell Name="2:2" AppliedCellStyle="CellStyle/Cell"> + <ParagraphStyleRange AppliedParagraphStyle="ParagraphStyle/TablePar > CenterAlign"> + <CharacterStyleRange AppliedCharacterStyle="$ID/NormalCharacterStyle"> + <Content>1</Content> + </CharacterStyleRange><Br /> + </ParagraphStyleRange> + </Cell> + <Cell Name="3:2" AppliedCellStyle="CellStyle/Cell"> + <ParagraphStyleRange AppliedParagraphStyle="ParagraphStyle/TablePar > RightAlign"> + <CharacterStyleRange AppliedCharacterStyle="$ID/NormalCharacterStyle"> + <Content>1</Content> + </CharacterStyleRange><Br /> + </ParagraphStyleRange> + </Cell> +</Table> +<ParagraphStyleRange AppliedParagraphStyle="ParagraphStyle/TableCaption"> + <Br /> +</ParagraphStyleRange> +<ParagraphStyleRange AppliedParagraphStyle="ParagraphStyle/Paragraph"> + <CharacterStyleRange AppliedCharacterStyle="$ID/NormalCharacterStyle"> + <Content>Multiline table without column headers:</Content> + </CharacterStyleRange><Br /> +</ParagraphStyleRange> +<Table AppliedTableStyle="TableStyle/Table" HeaderRowCount="0" BodyRowCount="2" ColumnCount="4"> + <Column Name="0" SingleColumnWidth="75.0" /> + <Column Name="1" SingleColumnWidth="68.75" /> + <Column Name="2" SingleColumnWidth="81.25" /> + <Column Name="3" SingleColumnWidth="168.75" /> + <Cell Name="0:0" AppliedCellStyle="CellStyle/Cell"> + <ParagraphStyleRange AppliedParagraphStyle="ParagraphStyle/TablePar > CenterAlign"> + <CharacterStyleRange AppliedCharacterStyle="$ID/NormalCharacterStyle"> + <Content>First</Content> + </CharacterStyleRange><Br /> + </ParagraphStyleRange> + </Cell> + <Cell Name="1:0" AppliedCellStyle="CellStyle/Cell"> + <ParagraphStyleRange AppliedParagraphStyle="ParagraphStyle/TablePar > LeftAlign"> + <CharacterStyleRange AppliedCharacterStyle="$ID/NormalCharacterStyle"> + <Content>row</Content> + </CharacterStyleRange><Br /> + </ParagraphStyleRange> + </Cell> + <Cell Name="2:0" AppliedCellStyle="CellStyle/Cell"> + <ParagraphStyleRange AppliedParagraphStyle="ParagraphStyle/TablePar > RightAlign"> + <CharacterStyleRange AppliedCharacterStyle="$ID/NormalCharacterStyle"> + <Content>12.0</Content> + </CharacterStyleRange><Br /> + </ParagraphStyleRange> + </Cell> + <Cell Name="3:0" AppliedCellStyle="CellStyle/Cell"> + <ParagraphStyleRange AppliedParagraphStyle="ParagraphStyle/TablePar"> + <CharacterStyleRange AppliedCharacterStyle="$ID/NormalCharacterStyle"> + <Content>Example of a row that spans multiple lines.</Content> + </CharacterStyleRange><Br /> + </ParagraphStyleRange> + </Cell> + <Cell Name="0:1" AppliedCellStyle="CellStyle/Cell"> + <ParagraphStyleRange AppliedParagraphStyle="ParagraphStyle/TablePar > CenterAlign"> + <CharacterStyleRange AppliedCharacterStyle="$ID/NormalCharacterStyle"> + <Content>Second</Content> + </CharacterStyleRange><Br /> + </ParagraphStyleRange> + </Cell> + <Cell Name="1:1" AppliedCellStyle="CellStyle/Cell"> + <ParagraphStyleRange AppliedParagraphStyle="ParagraphStyle/TablePar > LeftAlign"> + <CharacterStyleRange AppliedCharacterStyle="$ID/NormalCharacterStyle"> + <Content>row</Content> + </CharacterStyleRange><Br /> + </ParagraphStyleRange> + </Cell> + <Cell Name="2:1" AppliedCellStyle="CellStyle/Cell"> + <ParagraphStyleRange AppliedParagraphStyle="ParagraphStyle/TablePar > RightAlign"> + <CharacterStyleRange AppliedCharacterStyle="$ID/NormalCharacterStyle"> + <Content>5.0</Content> + </CharacterStyleRange><Br /> + </ParagraphStyleRange> + </Cell> + <Cell Name="3:1" AppliedCellStyle="CellStyle/Cell"> + <ParagraphStyleRange AppliedParagraphStyle="ParagraphStyle/TablePar"> + <CharacterStyleRange AppliedCharacterStyle="$ID/NormalCharacterStyle"> + <Content>Here's another one. Note the blank line between rows.</Content> + </CharacterStyleRange><Br /> + </ParagraphStyleRange> + </Cell> +</Table> +<ParagraphStyleRange AppliedParagraphStyle="ParagraphStyle/TableCaption"> + <Br /> +</ParagraphStyleRange> diff --git a/tests/tables.latex b/tests/tables.latex index 1a87c4f71..850629499 100644 --- a/tests/tables.latex +++ b/tests/tables.latex @@ -1,169 +1,168 @@ Simple table with caption: \begin{longtable}[c]{@{}rlcl@{}} -\toprule\addlinespace -Right & Left & Center & Default -\\\addlinespace -\midrule\endhead -12 & 12 & 12 & 12 -\\\addlinespace -123 & 123 & 123 & 123 -\\\addlinespace -1 & 1 & 1 & 1 -\\\addlinespace +\caption{Demonstration of simple table syntax.}\tabularnewline +\toprule +Right & Left & Center & Default\tabularnewline +\midrule +\endfirsthead +\toprule +Right & Left & Center & Default\tabularnewline +\midrule +\endhead +12 & 12 & 12 & 12\tabularnewline +123 & 123 & 123 & 123\tabularnewline +1 & 1 & 1 & 1\tabularnewline \bottomrule -\addlinespace -\caption{Demonstration of simple table syntax.} \end{longtable} Simple table without caption: \begin{longtable}[c]{@{}rlcl@{}} -\toprule\addlinespace -Right & Left & Center & Default -\\\addlinespace -\midrule\endhead -12 & 12 & 12 & 12 -\\\addlinespace -123 & 123 & 123 & 123 -\\\addlinespace -1 & 1 & 1 & 1 -\\\addlinespace +\toprule +Right & Left & Center & Default\tabularnewline +\midrule +\endhead +12 & 12 & 12 & 12\tabularnewline +123 & 123 & 123 & 123\tabularnewline +1 & 1 & 1 & 1\tabularnewline \bottomrule \end{longtable} Simple table indented two spaces: \begin{longtable}[c]{@{}rlcl@{}} -\toprule\addlinespace -Right & Left & Center & Default -\\\addlinespace -\midrule\endhead -12 & 12 & 12 & 12 -\\\addlinespace -123 & 123 & 123 & 123 -\\\addlinespace -1 & 1 & 1 & 1 -\\\addlinespace +\caption{Demonstration of simple table syntax.}\tabularnewline +\toprule +Right & Left & Center & Default\tabularnewline +\midrule +\endfirsthead +\toprule +Right & Left & Center & Default\tabularnewline +\midrule +\endhead +12 & 12 & 12 & 12\tabularnewline +123 & 123 & 123 & 123\tabularnewline +1 & 1 & 1 & 1\tabularnewline \bottomrule -\addlinespace -\caption{Demonstration of simple table syntax.} \end{longtable} Multiline table with caption: \begin{longtable}[c]{@{}clrl@{}} -\toprule\addlinespace -\begin{minipage}[b]{0.13\columnwidth}\centering +\caption{Here's the caption. It may span multiple lines.}\tabularnewline +\toprule +\begin{minipage}[b]{0.13\columnwidth}\centering\strut Centered Header -\end{minipage} & \begin{minipage}[b]{0.12\columnwidth}\raggedright +\strut\end{minipage} & \begin{minipage}[b]{0.12\columnwidth}\raggedright\strut Left Aligned -\end{minipage} & \begin{minipage}[b]{0.14\columnwidth}\raggedleft +\strut\end{minipage} & \begin{minipage}[b]{0.14\columnwidth}\raggedleft\strut Right Aligned -\end{minipage} & \begin{minipage}[b]{0.30\columnwidth}\raggedright +\strut\end{minipage} & \begin{minipage}[b]{0.30\columnwidth}\raggedright\strut Default aligned -\end{minipage} -\\\addlinespace -\midrule\endhead -\begin{minipage}[t]{0.13\columnwidth}\centering +\strut\end{minipage}\tabularnewline +\midrule +\endfirsthead +\toprule +\begin{minipage}[b]{0.13\columnwidth}\centering\strut +Centered Header +\strut\end{minipage} & \begin{minipage}[b]{0.12\columnwidth}\raggedright\strut +Left Aligned +\strut\end{minipage} & \begin{minipage}[b]{0.14\columnwidth}\raggedleft\strut +Right Aligned +\strut\end{minipage} & \begin{minipage}[b]{0.30\columnwidth}\raggedright\strut +Default aligned +\strut\end{minipage}\tabularnewline +\midrule +\endhead +\begin{minipage}[t]{0.13\columnwidth}\centering\strut First -\end{minipage} & \begin{minipage}[t]{0.12\columnwidth}\raggedright +\strut\end{minipage} & \begin{minipage}[t]{0.12\columnwidth}\raggedright\strut row -\end{minipage} & \begin{minipage}[t]{0.14\columnwidth}\raggedleft +\strut\end{minipage} & \begin{minipage}[t]{0.14\columnwidth}\raggedleft\strut 12.0 -\end{minipage} & \begin{minipage}[t]{0.30\columnwidth}\raggedright +\strut\end{minipage} & \begin{minipage}[t]{0.30\columnwidth}\raggedright\strut Example of a row that spans multiple lines. -\end{minipage} -\\\addlinespace -\begin{minipage}[t]{0.13\columnwidth}\centering +\strut\end{minipage}\tabularnewline +\begin{minipage}[t]{0.13\columnwidth}\centering\strut Second -\end{minipage} & \begin{minipage}[t]{0.12\columnwidth}\raggedright +\strut\end{minipage} & \begin{minipage}[t]{0.12\columnwidth}\raggedright\strut row -\end{minipage} & \begin{minipage}[t]{0.14\columnwidth}\raggedleft +\strut\end{minipage} & \begin{minipage}[t]{0.14\columnwidth}\raggedleft\strut 5.0 -\end{minipage} & \begin{minipage}[t]{0.30\columnwidth}\raggedright +\strut\end{minipage} & \begin{minipage}[t]{0.30\columnwidth}\raggedright\strut Here's another one. Note the blank line between rows. -\end{minipage} -\\\addlinespace +\strut\end{minipage}\tabularnewline \bottomrule -\addlinespace -\caption{Here's the caption. It may span multiple lines.} \end{longtable} Multiline table without caption: \begin{longtable}[c]{@{}clrl@{}} -\toprule\addlinespace -\begin{minipage}[b]{0.13\columnwidth}\centering +\toprule +\begin{minipage}[b]{0.13\columnwidth}\centering\strut Centered Header -\end{minipage} & \begin{minipage}[b]{0.12\columnwidth}\raggedright +\strut\end{minipage} & \begin{minipage}[b]{0.12\columnwidth}\raggedright\strut Left Aligned -\end{minipage} & \begin{minipage}[b]{0.14\columnwidth}\raggedleft +\strut\end{minipage} & \begin{minipage}[b]{0.14\columnwidth}\raggedleft\strut Right Aligned -\end{minipage} & \begin{minipage}[b]{0.30\columnwidth}\raggedright +\strut\end{minipage} & \begin{minipage}[b]{0.30\columnwidth}\raggedright\strut Default aligned -\end{minipage} -\\\addlinespace -\midrule\endhead -\begin{minipage}[t]{0.13\columnwidth}\centering +\strut\end{minipage}\tabularnewline +\midrule +\endhead +\begin{minipage}[t]{0.13\columnwidth}\centering\strut First -\end{minipage} & \begin{minipage}[t]{0.12\columnwidth}\raggedright +\strut\end{minipage} & \begin{minipage}[t]{0.12\columnwidth}\raggedright\strut row -\end{minipage} & \begin{minipage}[t]{0.14\columnwidth}\raggedleft +\strut\end{minipage} & \begin{minipage}[t]{0.14\columnwidth}\raggedleft\strut 12.0 -\end{minipage} & \begin{minipage}[t]{0.30\columnwidth}\raggedright +\strut\end{minipage} & \begin{minipage}[t]{0.30\columnwidth}\raggedright\strut Example of a row that spans multiple lines. -\end{minipage} -\\\addlinespace -\begin{minipage}[t]{0.13\columnwidth}\centering +\strut\end{minipage}\tabularnewline +\begin{minipage}[t]{0.13\columnwidth}\centering\strut Second -\end{minipage} & \begin{minipage}[t]{0.12\columnwidth}\raggedright +\strut\end{minipage} & \begin{minipage}[t]{0.12\columnwidth}\raggedright\strut row -\end{minipage} & \begin{minipage}[t]{0.14\columnwidth}\raggedleft +\strut\end{minipage} & \begin{minipage}[t]{0.14\columnwidth}\raggedleft\strut 5.0 -\end{minipage} & \begin{minipage}[t]{0.30\columnwidth}\raggedright +\strut\end{minipage} & \begin{minipage}[t]{0.30\columnwidth}\raggedright\strut Here's another one. Note the blank line between rows. -\end{minipage} -\\\addlinespace +\strut\end{minipage}\tabularnewline \bottomrule \end{longtable} Table without column headers: \begin{longtable}[c]{@{}rlcr@{}} -\toprule\addlinespace -12 & 12 & 12 & 12 -\\\addlinespace -123 & 123 & 123 & 123 -\\\addlinespace -1 & 1 & 1 & 1 -\\\addlinespace +\toprule +12 & 12 & 12 & 12\tabularnewline +123 & 123 & 123 & 123\tabularnewline +1 & 1 & 1 & 1\tabularnewline \bottomrule \end{longtable} Multiline table without column headers: \begin{longtable}[c]{@{}clrl@{}} -\toprule\addlinespace -\begin{minipage}[t]{0.13\columnwidth}\centering +\toprule +\begin{minipage}[t]{0.13\columnwidth}\centering\strut First -\end{minipage} & \begin{minipage}[t]{0.12\columnwidth}\raggedright +\strut\end{minipage} & \begin{minipage}[t]{0.12\columnwidth}\raggedright\strut row -\end{minipage} & \begin{minipage}[t]{0.14\columnwidth}\raggedleft +\strut\end{minipage} & \begin{minipage}[t]{0.14\columnwidth}\raggedleft\strut 12.0 -\end{minipage} & \begin{minipage}[t]{0.30\columnwidth}\raggedright +\strut\end{minipage} & \begin{minipage}[t]{0.30\columnwidth}\raggedright\strut Example of a row that spans multiple lines. -\end{minipage} -\\\addlinespace -\begin{minipage}[t]{0.13\columnwidth}\centering +\strut\end{minipage}\tabularnewline +\begin{minipage}[t]{0.13\columnwidth}\centering\strut Second -\end{minipage} & \begin{minipage}[t]{0.12\columnwidth}\raggedright +\strut\end{minipage} & \begin{minipage}[t]{0.12\columnwidth}\raggedright\strut row -\end{minipage} & \begin{minipage}[t]{0.14\columnwidth}\raggedleft +\strut\end{minipage} & \begin{minipage}[t]{0.14\columnwidth}\raggedleft\strut 5.0 -\end{minipage} & \begin{minipage}[t]{0.30\columnwidth}\raggedright +\strut\end{minipage} & \begin{minipage}[t]{0.30\columnwidth}\raggedright\strut Here's another one. Note the blank line between rows. -\end{minipage} -\\\addlinespace +\strut\end{minipage}\tabularnewline \bottomrule \end{longtable} diff --git a/tests/tables.org b/tests/tables.org index 8d9100d07..9eaf5e706 100644 --- a/tests/tables.org +++ b/tests/tables.org @@ -49,4 +49,3 @@ Multiline table without column headers: | First | row | 12.0 | Example of a row that spans multiple lines. | | Second | row | 5.0 | Here's another one. Note the blank line between rows. | - diff --git a/tests/tables.rst b/tests/tables.rst index e77f69d97..25d5932ea 100644 --- a/tests/tables.rst +++ b/tests/tables.rst @@ -88,4 +88,3 @@ Multiline table without column headers: | | | | the blank line between | | | | | rows. | +-------------+------------+--------------+----------------------------+ - diff --git a/tests/tables.rtf b/tests/tables.rtf index 011724967..e1fe4aab1 100644 --- a/tests/tables.rtf +++ b/tests/tables.rtf @@ -4,13 +4,13 @@ \clbrdrb\brdrs\cellx2160\clbrdrb\brdrs\cellx4320\clbrdrb\brdrs\cellx6480\clbrdrb\brdrs\cellx8640 \trkeep\intbl { -{\intbl {\pard \qr \f0 \sa0 \li0 \fi0 Right\par} +{{\pard\intbl \qr \f0 \sa0 \li0 \fi0 Right\par} \cell} -{\intbl {\pard \ql \f0 \sa0 \li0 \fi0 Left\par} +{{\pard\intbl \ql \f0 \sa0 \li0 \fi0 Left\par} \cell} -{\intbl {\pard \qc \f0 \sa0 \li0 \fi0 Center\par} +{{\pard\intbl \qc \f0 \sa0 \li0 \fi0 Center\par} \cell} -{\intbl {\pard \ql \f0 \sa0 \li0 \fi0 Default\par} +{{\pard\intbl \ql \f0 \sa0 \li0 \fi0 Default\par} \cell} } \intbl\row} @@ -19,13 +19,13 @@ \cellx2160\cellx4320\cellx6480\cellx8640 \trkeep\intbl { -{\intbl {\pard \qr \f0 \sa0 \li0 \fi0 12\par} +{{\pard\intbl \qr \f0 \sa0 \li0 \fi0 12\par} \cell} -{\intbl {\pard \ql \f0 \sa0 \li0 \fi0 12\par} +{{\pard\intbl \ql \f0 \sa0 \li0 \fi0 12\par} \cell} -{\intbl {\pard \qc \f0 \sa0 \li0 \fi0 12\par} +{{\pard\intbl \qc \f0 \sa0 \li0 \fi0 12\par} \cell} -{\intbl {\pard \ql \f0 \sa0 \li0 \fi0 12\par} +{{\pard\intbl \ql \f0 \sa0 \li0 \fi0 12\par} \cell} } \intbl\row} @@ -34,13 +34,13 @@ \cellx2160\cellx4320\cellx6480\cellx8640 \trkeep\intbl { -{\intbl {\pard \qr \f0 \sa0 \li0 \fi0 123\par} +{{\pard\intbl \qr \f0 \sa0 \li0 \fi0 123\par} \cell} -{\intbl {\pard \ql \f0 \sa0 \li0 \fi0 123\par} +{{\pard\intbl \ql \f0 \sa0 \li0 \fi0 123\par} \cell} -{\intbl {\pard \qc \f0 \sa0 \li0 \fi0 123\par} +{{\pard\intbl \qc \f0 \sa0 \li0 \fi0 123\par} \cell} -{\intbl {\pard \ql \f0 \sa0 \li0 \fi0 123\par} +{{\pard\intbl \ql \f0 \sa0 \li0 \fi0 123\par} \cell} } \intbl\row} @@ -49,13 +49,13 @@ \cellx2160\cellx4320\cellx6480\cellx8640 \trkeep\intbl { -{\intbl {\pard \qr \f0 \sa0 \li0 \fi0 1\par} +{{\pard\intbl \qr \f0 \sa0 \li0 \fi0 1\par} \cell} -{\intbl {\pard \ql \f0 \sa0 \li0 \fi0 1\par} +{{\pard\intbl \ql \f0 \sa0 \li0 \fi0 1\par} \cell} -{\intbl {\pard \qc \f0 \sa0 \li0 \fi0 1\par} +{{\pard\intbl \qc \f0 \sa0 \li0 \fi0 1\par} \cell} -{\intbl {\pard \ql \f0 \sa0 \li0 \fi0 1\par} +{{\pard\intbl \ql \f0 \sa0 \li0 \fi0 1\par} \cell} } \intbl\row} @@ -66,13 +66,13 @@ \clbrdrb\brdrs\cellx2160\clbrdrb\brdrs\cellx4320\clbrdrb\brdrs\cellx6480\clbrdrb\brdrs\cellx8640 \trkeep\intbl { -{\intbl {\pard \qr \f0 \sa0 \li0 \fi0 Right\par} +{{\pard\intbl \qr \f0 \sa0 \li0 \fi0 Right\par} \cell} -{\intbl {\pard \ql \f0 \sa0 \li0 \fi0 Left\par} +{{\pard\intbl \ql \f0 \sa0 \li0 \fi0 Left\par} \cell} -{\intbl {\pard \qc \f0 \sa0 \li0 \fi0 Center\par} +{{\pard\intbl \qc \f0 \sa0 \li0 \fi0 Center\par} \cell} -{\intbl {\pard \ql \f0 \sa0 \li0 \fi0 Default\par} +{{\pard\intbl \ql \f0 \sa0 \li0 \fi0 Default\par} \cell} } \intbl\row} @@ -81,13 +81,13 @@ \cellx2160\cellx4320\cellx6480\cellx8640 \trkeep\intbl { -{\intbl {\pard \qr \f0 \sa0 \li0 \fi0 12\par} +{{\pard\intbl \qr \f0 \sa0 \li0 \fi0 12\par} \cell} -{\intbl {\pard \ql \f0 \sa0 \li0 \fi0 12\par} +{{\pard\intbl \ql \f0 \sa0 \li0 \fi0 12\par} \cell} -{\intbl {\pard \qc \f0 \sa0 \li0 \fi0 12\par} +{{\pard\intbl \qc \f0 \sa0 \li0 \fi0 12\par} \cell} -{\intbl {\pard \ql \f0 \sa0 \li0 \fi0 12\par} +{{\pard\intbl \ql \f0 \sa0 \li0 \fi0 12\par} \cell} } \intbl\row} @@ -96,13 +96,13 @@ \cellx2160\cellx4320\cellx6480\cellx8640 \trkeep\intbl { -{\intbl {\pard \qr \f0 \sa0 \li0 \fi0 123\par} +{{\pard\intbl \qr \f0 \sa0 \li0 \fi0 123\par} \cell} -{\intbl {\pard \ql \f0 \sa0 \li0 \fi0 123\par} +{{\pard\intbl \ql \f0 \sa0 \li0 \fi0 123\par} \cell} -{\intbl {\pard \qc \f0 \sa0 \li0 \fi0 123\par} +{{\pard\intbl \qc \f0 \sa0 \li0 \fi0 123\par} \cell} -{\intbl {\pard \ql \f0 \sa0 \li0 \fi0 123\par} +{{\pard\intbl \ql \f0 \sa0 \li0 \fi0 123\par} \cell} } \intbl\row} @@ -111,13 +111,13 @@ \cellx2160\cellx4320\cellx6480\cellx8640 \trkeep\intbl { -{\intbl {\pard \qr \f0 \sa0 \li0 \fi0 1\par} +{{\pard\intbl \qr \f0 \sa0 \li0 \fi0 1\par} \cell} -{\intbl {\pard \ql \f0 \sa0 \li0 \fi0 1\par} +{{\pard\intbl \ql \f0 \sa0 \li0 \fi0 1\par} \cell} -{\intbl {\pard \qc \f0 \sa0 \li0 \fi0 1\par} +{{\pard\intbl \qc \f0 \sa0 \li0 \fi0 1\par} \cell} -{\intbl {\pard \ql \f0 \sa0 \li0 \fi0 1\par} +{{\pard\intbl \ql \f0 \sa0 \li0 \fi0 1\par} \cell} } \intbl\row} @@ -128,13 +128,13 @@ \clbrdrb\brdrs\cellx2160\clbrdrb\brdrs\cellx4320\clbrdrb\brdrs\cellx6480\clbrdrb\brdrs\cellx8640 \trkeep\intbl { -{\intbl {\pard \qr \f0 \sa0 \li0 \fi0 Right\par} +{{\pard\intbl \qr \f0 \sa0 \li0 \fi0 Right\par} \cell} -{\intbl {\pard \ql \f0 \sa0 \li0 \fi0 Left\par} +{{\pard\intbl \ql \f0 \sa0 \li0 \fi0 Left\par} \cell} -{\intbl {\pard \qc \f0 \sa0 \li0 \fi0 Center\par} +{{\pard\intbl \qc \f0 \sa0 \li0 \fi0 Center\par} \cell} -{\intbl {\pard \ql \f0 \sa0 \li0 \fi0 Default\par} +{{\pard\intbl \ql \f0 \sa0 \li0 \fi0 Default\par} \cell} } \intbl\row} @@ -143,13 +143,13 @@ \cellx2160\cellx4320\cellx6480\cellx8640 \trkeep\intbl { -{\intbl {\pard \qr \f0 \sa0 \li0 \fi0 12\par} +{{\pard\intbl \qr \f0 \sa0 \li0 \fi0 12\par} \cell} -{\intbl {\pard \ql \f0 \sa0 \li0 \fi0 12\par} +{{\pard\intbl \ql \f0 \sa0 \li0 \fi0 12\par} \cell} -{\intbl {\pard \qc \f0 \sa0 \li0 \fi0 12\par} +{{\pard\intbl \qc \f0 \sa0 \li0 \fi0 12\par} \cell} -{\intbl {\pard \ql \f0 \sa0 \li0 \fi0 12\par} +{{\pard\intbl \ql \f0 \sa0 \li0 \fi0 12\par} \cell} } \intbl\row} @@ -158,13 +158,13 @@ \cellx2160\cellx4320\cellx6480\cellx8640 \trkeep\intbl { -{\intbl {\pard \qr \f0 \sa0 \li0 \fi0 123\par} +{{\pard\intbl \qr \f0 \sa0 \li0 \fi0 123\par} \cell} -{\intbl {\pard \ql \f0 \sa0 \li0 \fi0 123\par} +{{\pard\intbl \ql \f0 \sa0 \li0 \fi0 123\par} \cell} -{\intbl {\pard \qc \f0 \sa0 \li0 \fi0 123\par} +{{\pard\intbl \qc \f0 \sa0 \li0 \fi0 123\par} \cell} -{\intbl {\pard \ql \f0 \sa0 \li0 \fi0 123\par} +{{\pard\intbl \ql \f0 \sa0 \li0 \fi0 123\par} \cell} } \intbl\row} @@ -173,13 +173,13 @@ \cellx2160\cellx4320\cellx6480\cellx8640 \trkeep\intbl { -{\intbl {\pard \qr \f0 \sa0 \li0 \fi0 1\par} +{{\pard\intbl \qr \f0 \sa0 \li0 \fi0 1\par} \cell} -{\intbl {\pard \ql \f0 \sa0 \li0 \fi0 1\par} +{{\pard\intbl \ql \f0 \sa0 \li0 \fi0 1\par} \cell} -{\intbl {\pard \qc \f0 \sa0 \li0 \fi0 1\par} +{{\pard\intbl \qc \f0 \sa0 \li0 \fi0 1\par} \cell} -{\intbl {\pard \ql \f0 \sa0 \li0 \fi0 1\par} +{{\pard\intbl \ql \f0 \sa0 \li0 \fi0 1\par} \cell} } \intbl\row} @@ -190,13 +190,13 @@ \clbrdrb\brdrs\cellx1296\clbrdrb\brdrs\cellx2484\clbrdrb\brdrs\cellx3888\clbrdrb\brdrs\cellx6804 \trkeep\intbl { -{\intbl {\pard \qc \f0 \sa0 \li0 \fi0 Centered Header\par} +{{\pard\intbl \qc \f0 \sa0 \li0 \fi0 Centered Header\par} \cell} -{\intbl {\pard \ql \f0 \sa0 \li0 \fi0 Left Aligned\par} +{{\pard\intbl \ql \f0 \sa0 \li0 \fi0 Left Aligned\par} \cell} -{\intbl {\pard \qr \f0 \sa0 \li0 \fi0 Right Aligned\par} +{{\pard\intbl \qr \f0 \sa0 \li0 \fi0 Right Aligned\par} \cell} -{\intbl {\pard \ql \f0 \sa0 \li0 \fi0 Default aligned\par} +{{\pard\intbl \ql \f0 \sa0 \li0 \fi0 Default aligned\par} \cell} } \intbl\row} @@ -205,13 +205,13 @@ \cellx1296\cellx2484\cellx3888\cellx6804 \trkeep\intbl { -{\intbl {\pard \qc \f0 \sa0 \li0 \fi0 First\par} +{{\pard\intbl \qc \f0 \sa0 \li0 \fi0 First\par} \cell} -{\intbl {\pard \ql \f0 \sa0 \li0 \fi0 row\par} +{{\pard\intbl \ql \f0 \sa0 \li0 \fi0 row\par} \cell} -{\intbl {\pard \qr \f0 \sa0 \li0 \fi0 12.0\par} +{{\pard\intbl \qr \f0 \sa0 \li0 \fi0 12.0\par} \cell} -{\intbl {\pard \ql \f0 \sa0 \li0 \fi0 Example of a row that spans multiple lines.\par} +{{\pard\intbl \ql \f0 \sa0 \li0 \fi0 Example of a row that spans multiple lines.\par} \cell} } \intbl\row} @@ -220,13 +220,13 @@ \cellx1296\cellx2484\cellx3888\cellx6804 \trkeep\intbl { -{\intbl {\pard \qc \f0 \sa0 \li0 \fi0 Second\par} +{{\pard\intbl \qc \f0 \sa0 \li0 \fi0 Second\par} \cell} -{\intbl {\pard \ql \f0 \sa0 \li0 \fi0 row\par} +{{\pard\intbl \ql \f0 \sa0 \li0 \fi0 row\par} \cell} -{\intbl {\pard \qr \f0 \sa0 \li0 \fi0 5.0\par} +{{\pard\intbl \qr \f0 \sa0 \li0 \fi0 5.0\par} \cell} -{\intbl {\pard \ql \f0 \sa0 \li0 \fi0 Here's another one. Note the blank line between rows.\par} +{{\pard\intbl \ql \f0 \sa0 \li0 \fi0 Here's another one. Note the blank line between rows.\par} \cell} } \intbl\row} @@ -237,13 +237,13 @@ \clbrdrb\brdrs\cellx1296\clbrdrb\brdrs\cellx2484\clbrdrb\brdrs\cellx3888\clbrdrb\brdrs\cellx6804 \trkeep\intbl { -{\intbl {\pard \qc \f0 \sa0 \li0 \fi0 Centered Header\par} +{{\pard\intbl \qc \f0 \sa0 \li0 \fi0 Centered Header\par} \cell} -{\intbl {\pard \ql \f0 \sa0 \li0 \fi0 Left Aligned\par} +{{\pard\intbl \ql \f0 \sa0 \li0 \fi0 Left Aligned\par} \cell} -{\intbl {\pard \qr \f0 \sa0 \li0 \fi0 Right Aligned\par} +{{\pard\intbl \qr \f0 \sa0 \li0 \fi0 Right Aligned\par} \cell} -{\intbl {\pard \ql \f0 \sa0 \li0 \fi0 Default aligned\par} +{{\pard\intbl \ql \f0 \sa0 \li0 \fi0 Default aligned\par} \cell} } \intbl\row} @@ -252,13 +252,13 @@ \cellx1296\cellx2484\cellx3888\cellx6804 \trkeep\intbl { -{\intbl {\pard \qc \f0 \sa0 \li0 \fi0 First\par} +{{\pard\intbl \qc \f0 \sa0 \li0 \fi0 First\par} \cell} -{\intbl {\pard \ql \f0 \sa0 \li0 \fi0 row\par} +{{\pard\intbl \ql \f0 \sa0 \li0 \fi0 row\par} \cell} -{\intbl {\pard \qr \f0 \sa0 \li0 \fi0 12.0\par} +{{\pard\intbl \qr \f0 \sa0 \li0 \fi0 12.0\par} \cell} -{\intbl {\pard \ql \f0 \sa0 \li0 \fi0 Example of a row that spans multiple lines.\par} +{{\pard\intbl \ql \f0 \sa0 \li0 \fi0 Example of a row that spans multiple lines.\par} \cell} } \intbl\row} @@ -267,13 +267,13 @@ \cellx1296\cellx2484\cellx3888\cellx6804 \trkeep\intbl { -{\intbl {\pard \qc \f0 \sa0 \li0 \fi0 Second\par} +{{\pard\intbl \qc \f0 \sa0 \li0 \fi0 Second\par} \cell} -{\intbl {\pard \ql \f0 \sa0 \li0 \fi0 row\par} +{{\pard\intbl \ql \f0 \sa0 \li0 \fi0 row\par} \cell} -{\intbl {\pard \qr \f0 \sa0 \li0 \fi0 5.0\par} +{{\pard\intbl \qr \f0 \sa0 \li0 \fi0 5.0\par} \cell} -{\intbl {\pard \ql \f0 \sa0 \li0 \fi0 Here's another one. Note the blank line between rows.\par} +{{\pard\intbl \ql \f0 \sa0 \li0 \fi0 Here's another one. Note the blank line between rows.\par} \cell} } \intbl\row} @@ -284,13 +284,13 @@ \cellx2160\cellx4320\cellx6480\cellx8640 \trkeep\intbl { -{\intbl {\pard \qr \f0 \sa0 \li0 \fi0 12\par} +{{\pard\intbl \qr \f0 \sa0 \li0 \fi0 12\par} \cell} -{\intbl {\pard \ql \f0 \sa0 \li0 \fi0 12\par} +{{\pard\intbl \ql \f0 \sa0 \li0 \fi0 12\par} \cell} -{\intbl {\pard \qc \f0 \sa0 \li0 \fi0 12\par} +{{\pard\intbl \qc \f0 \sa0 \li0 \fi0 12\par} \cell} -{\intbl {\pard \qr \f0 \sa0 \li0 \fi0 12\par} +{{\pard\intbl \qr \f0 \sa0 \li0 \fi0 12\par} \cell} } \intbl\row} @@ -299,13 +299,13 @@ \cellx2160\cellx4320\cellx6480\cellx8640 \trkeep\intbl { -{\intbl {\pard \qr \f0 \sa0 \li0 \fi0 123\par} +{{\pard\intbl \qr \f0 \sa0 \li0 \fi0 123\par} \cell} -{\intbl {\pard \ql \f0 \sa0 \li0 \fi0 123\par} +{{\pard\intbl \ql \f0 \sa0 \li0 \fi0 123\par} \cell} -{\intbl {\pard \qc \f0 \sa0 \li0 \fi0 123\par} +{{\pard\intbl \qc \f0 \sa0 \li0 \fi0 123\par} \cell} -{\intbl {\pard \qr \f0 \sa0 \li0 \fi0 123\par} +{{\pard\intbl \qr \f0 \sa0 \li0 \fi0 123\par} \cell} } \intbl\row} @@ -314,13 +314,13 @@ \cellx2160\cellx4320\cellx6480\cellx8640 \trkeep\intbl { -{\intbl {\pard \qr \f0 \sa0 \li0 \fi0 1\par} +{{\pard\intbl \qr \f0 \sa0 \li0 \fi0 1\par} \cell} -{\intbl {\pard \ql \f0 \sa0 \li0 \fi0 1\par} +{{\pard\intbl \ql \f0 \sa0 \li0 \fi0 1\par} \cell} -{\intbl {\pard \qc \f0 \sa0 \li0 \fi0 1\par} +{{\pard\intbl \qc \f0 \sa0 \li0 \fi0 1\par} \cell} -{\intbl {\pard \qr \f0 \sa0 \li0 \fi0 1\par} +{{\pard\intbl \qr \f0 \sa0 \li0 \fi0 1\par} \cell} } \intbl\row} @@ -331,13 +331,13 @@ \cellx1296\cellx2484\cellx3888\cellx6804 \trkeep\intbl { -{\intbl {\pard \qc \f0 \sa0 \li0 \fi0 First\par} +{{\pard\intbl \qc \f0 \sa0 \li0 \fi0 First\par} \cell} -{\intbl {\pard \ql \f0 \sa0 \li0 \fi0 row\par} +{{\pard\intbl \ql \f0 \sa0 \li0 \fi0 row\par} \cell} -{\intbl {\pard \qr \f0 \sa0 \li0 \fi0 12.0\par} +{{\pard\intbl \qr \f0 \sa0 \li0 \fi0 12.0\par} \cell} -{\intbl {\pard \ql \f0 \sa0 \li0 \fi0 Example of a row that spans multiple lines.\par} +{{\pard\intbl \ql \f0 \sa0 \li0 \fi0 Example of a row that spans multiple lines.\par} \cell} } \intbl\row} @@ -346,13 +346,13 @@ \cellx1296\cellx2484\cellx3888\cellx6804 \trkeep\intbl { -{\intbl {\pard \qc \f0 \sa0 \li0 \fi0 Second\par} +{{\pard\intbl \qc \f0 \sa0 \li0 \fi0 Second\par} \cell} -{\intbl {\pard \ql \f0 \sa0 \li0 \fi0 row\par} +{{\pard\intbl \ql \f0 \sa0 \li0 \fi0 row\par} \cell} -{\intbl {\pard \qr \f0 \sa0 \li0 \fi0 5.0\par} +{{\pard\intbl \qr \f0 \sa0 \li0 \fi0 5.0\par} \cell} -{\intbl {\pard \ql \f0 \sa0 \li0 \fi0 Here's another one. Note the blank line between rows.\par} +{{\pard\intbl \ql \f0 \sa0 \li0 \fi0 Here's another one. Note the blank line between rows.\par} \cell} } \intbl\row} diff --git a/tests/tables.textile b/tests/tables.textile index 4836ecd79..6c6b234e6 100644 --- a/tests/tables.textile +++ b/tests/tables.textile @@ -34,36 +34,10 @@ Simple table with caption: Simple table without caption: -<table> -<thead> -<tr class="header"> -<th align="right">Right</th> -<th align="left">Left</th> -<th align="center">Center</th> -<th align="left">Default</th> -</tr> -</thead> -<tbody> -<tr class="odd"> -<td align="right">12</td> -<td align="left">12</td> -<td align="center">12</td> -<td align="left">12</td> -</tr> -<tr class="even"> -<td align="right">123</td> -<td align="left">123</td> -<td align="center">123</td> -<td align="left">123</td> -</tr> -<tr class="odd"> -<td align="right">1</td> -<td align="left">1</td> -<td align="center">1</td> -<td align="left">1</td> -</tr> -</tbody> -</table> +|_. Right|_. Left|_. Center|_. Default| +|>. 12|<. 12|=. 12|12| +|>. 123|<. 123|=. 123|123| +|>. 1|<. 1|=. 1|1| Simple table indented two spaces: @@ -164,28 +138,9 @@ Multiline table without caption: Table without column headers: -<table> -<tbody> -<tr class="odd"> -<td align="right">12</td> -<td align="left">12</td> -<td align="center">12</td> -<td align="right">12</td> -</tr> -<tr class="even"> -<td align="right">123</td> -<td align="left">123</td> -<td align="center">123</td> -<td align="right">123</td> -</tr> -<tr class="odd"> -<td align="right">1</td> -<td align="left">1</td> -<td align="center">1</td> -<td align="right">1</td> -</tr> -</tbody> -</table> +|>. 12|<. 12|=. 12|>. 12| +|>. 123|<. 123|=. 123|>. 123| +|>. 1|<. 1|=. 1|>. 1| Multiline table without column headers: diff --git a/tests/test-pandoc.hs b/tests/test-pandoc.hs index ae521541a..b7b1c30b1 100644 --- a/tests/test-pandoc.hs +++ b/tests/test-pandoc.hs @@ -7,15 +7,23 @@ import GHC.IO.Encoding import qualified Tests.Old import qualified Tests.Readers.LaTeX import qualified Tests.Readers.Markdown +import qualified Tests.Readers.Org import qualified Tests.Readers.RST +import qualified Tests.Readers.Docx +import qualified Tests.Readers.Txt2Tags +import qualified Tests.Readers.EPUB import qualified Tests.Writers.ConTeXt import qualified Tests.Writers.LaTeX import qualified Tests.Writers.HTML +import qualified Tests.Writers.Docbook import qualified Tests.Writers.Native import qualified Tests.Writers.Markdown +import qualified Tests.Writers.Plain +import qualified Tests.Writers.AsciiDoc import qualified Tests.Shared import qualified Tests.Walk import Text.Pandoc.Shared (inDirectory) +import System.Environment (getArgs) tests :: [Test] tests = [ testGroup "Old" Tests.Old.tests @@ -26,19 +34,24 @@ tests = [ testGroup "Old" Tests.Old.tests , testGroup "ConTeXt" Tests.Writers.ConTeXt.tests , testGroup "LaTeX" Tests.Writers.LaTeX.tests , testGroup "HTML" Tests.Writers.HTML.tests + , testGroup "Docbook" Tests.Writers.Docbook.tests , testGroup "Markdown" Tests.Writers.Markdown.tests + , testGroup "Plain" Tests.Writers.Plain.tests + , testGroup "AsciiDoc" Tests.Writers.AsciiDoc.tests ] , testGroup "Readers" [ testGroup "LaTeX" Tests.Readers.LaTeX.tests , testGroup "Markdown" Tests.Readers.Markdown.tests + , testGroup "Org" Tests.Readers.Org.tests , testGroup "RST" Tests.Readers.RST.tests + , testGroup "Docx" Tests.Readers.Docx.tests + , testGroup "Txt2Tags" Tests.Readers.Txt2Tags.tests + , testGroup "EPUB" Tests.Readers.EPUB.tests ] ] main :: IO () main = do setLocaleEncoding utf8 - -- we ignore command-line arguments, since we're having cabal pass - -- the build directory as first argument, and we don't want test-framework - -- to choke on that. - inDirectory "tests" $ defaultMainWithArgs tests [] + args <- getArgs + inDirectory "tests" $ defaultMainWithArgs tests args diff --git a/tests/testsuite.native b/tests/testsuite.native index 678d7595f..93d2939ad 100644 --- a/tests/testsuite.native +++ b/tests/testsuite.native @@ -230,15 +230,21 @@ Pandoc (Meta {unMeta = fromList [("author",MetaList [MetaInlines [Str "John",Spa ,Para [Str "Simple",Space,Str "block",Space,Str "on",Space,Str "one",Space,Str "line:"] ,Div ("",[],[]) [Plain [Str "foo"]] ,Para [Str "And",Space,Str "nested",Space,Str "without",Space,Str "indentation:"] -,Div ("",[],[]) [Div ("",[],[]) [Div ("",[],[]) [Plain [Str "foo"]]],Div ("",[],[]) [Plain [Str "bar"]]] +,Div ("",[],[]) [Div ("",[],[]) [Div ("",[],[]) [Para [Str "foo"]]],Div ("",[],[]) [Plain [Str "bar"]]] ,Para [Str "Interpreted",Space,Str "markdown",Space,Str "in",Space,Str "a",Space,Str "table:"] -,RawBlock (Format "html") "<table>\n<tr>\n<td>" +,RawBlock (Format "html") "<table>" +,RawBlock (Format "html") "<tr>" +,RawBlock (Format "html") "<td>" ,Plain [Str "This",Space,Str "is",Space,Emph [Str "emphasized"]] -,RawBlock (Format "html") "</td>\n<td>" +,RawBlock (Format "html") "</td>" +,RawBlock (Format "html") "<td>" ,Plain [Str "And",Space,Str "this",Space,Str "is",Space,Strong [Str "strong"]] -,RawBlock (Format "html") "</td>\n</tr>\n</table>\n\n<script type=\"text/javascript\">document.write('This *should not* be interpreted as markdown');</script>\n" +,RawBlock (Format "html") "</td>" +,RawBlock (Format "html") "</tr>" +,RawBlock (Format "html") "</table>" +,RawBlock (Format "html") "<script type=\"text/javascript\">document.write('This *should not* be interpreted as markdown');</script>" ,Para [Str "Here\8217s",Space,Str "a",Space,Str "simple",Space,Str "block:"] -,Div ("",[],[]) [Plain [Str "foo"]] +,Div ("",[],[]) [Para [Str "foo"]] ,Para [Str "This",Space,Str "should",Space,Str "be",Space,Str "a",Space,Str "code",Space,Str "block,",Space,Str "though:"] ,CodeBlock ("",[],[]) "<div>\n foo\n</div>" ,Para [Str "As",Space,Str "should",Space,Str "this:"] @@ -246,17 +252,26 @@ Pandoc (Meta {unMeta = fromList [("author",MetaList [MetaInlines [Str "John",Spa ,Para [Str "Now,",Space,Str "nested:"] ,Div ("",[],[]) [Div ("",[],[]) [Div ("",[],[]) [Plain [Str "foo"]]]] ,Para [Str "This",Space,Str "should",Space,Str "just",Space,Str "be",Space,Str "an",Space,Str "HTML",Space,Str "comment:"] -,RawBlock (Format "html") "<!-- Comment -->\n" +,RawBlock (Format "html") "<!-- Comment -->" ,Para [Str "Multiline:"] -,RawBlock (Format "html") "<!--\nBlah\nBlah\n-->\n\n<!--\n This is another comment.\n-->\n" +,RawBlock (Format "html") "<!--\nBlah\nBlah\n-->" +,RawBlock (Format "html") "<!--\n This is another comment.\n-->" ,Para [Str "Code",Space,Str "block:"] ,CodeBlock ("",[],[]) "<!-- Comment -->" ,Para [Str "Just",Space,Str "plain",Space,Str "comment,",Space,Str "with",Space,Str "trailing",Space,Str "spaces",Space,Str "on",Space,Str "the",Space,Str "line:"] -,RawBlock (Format "html") "<!-- foo --> \n" +,RawBlock (Format "html") "<!-- foo -->" ,Para [Str "Code:"] ,CodeBlock ("",[],[]) "<hr />" ,Para [Str "Hr\8217s:"] -,RawBlock (Format "html") "<hr>\n\n<hr />\n\n<hr />\n\n<hr> \n\n<hr /> \n\n<hr /> \n\n<hr class=\"foo\" id=\"bar\" />\n\n<hr class=\"foo\" id=\"bar\" />\n\n<hr class=\"foo\" id=\"bar\">\n" +,RawBlock (Format "html") "<hr>" +,RawBlock (Format "html") "<hr />" +,RawBlock (Format "html") "<hr />" +,RawBlock (Format "html") "<hr>" +,RawBlock (Format "html") "<hr />" +,RawBlock (Format "html") "<hr />" +,RawBlock (Format "html") "<hr class=\"foo\" id=\"bar\" />" +,RawBlock (Format "html") "<hr class=\"foo\" id=\"bar\" />" +,RawBlock (Format "html") "<hr class=\"foo\" id=\"bar\">" ,HorizontalRule ,Header 1 ("inline-markup",[],[]) [Str "Inline",Space,Str "Markup"] ,Para [Str "This",Space,Str "is",Space,Emph [Str "emphasized"],Str ",",Space,Str "and",Space,Str "so",Space,Emph [Str "is",Space,Str "this"],Str "."] diff --git a/tests/testsuite.txt b/tests/testsuite.txt index 4ddaae23f..f6b0a7c95 100644 --- a/tests/testsuite.txt +++ b/tests/testsuite.txt @@ -270,8 +270,10 @@ Tight using spaces: apple : red fruit + orange : orange fruit + banana : yellow fruit @@ -279,31 +281,38 @@ Tight using tabs: apple : red fruit + orange : orange fruit + banana : yellow fruit Loose: apple + : red fruit orange + : orange fruit banana + : yellow fruit Multiple blocks with italics: *apple* + : red fruit contains seeds, crisp, pleasant to taste *orange* + : orange fruit { orange code block } @@ -315,6 +324,7 @@ Multiple definitions, tight: apple : red fruit : computer + orange : orange fruit : bank @@ -322,11 +332,13 @@ orange Multiple definitions, loose: apple + : red fruit : computer orange + : orange fruit : bank diff --git a/tests/textile-reader.native b/tests/textile-reader.native index ebfbc07fd..de0637f5f 100644 --- a/tests/textile-reader.native +++ b/tests/textile-reader.native @@ -1,5 +1,5 @@ Pandoc (Meta {unMeta = fromList []}) -[Para [Str "This",Space,Str "is",Space,Str "a",Space,Str "set",Space,Str "of",Space,Str "tests",Space,Str "for",Space,Str "pandoc",Space,Str "Textile",Space,Str "Reader",Str ".",Space,Str "Part",Space,Str "of",Space,Str "it",Space,Str "comes",LineBreak,Str "from",Space,Str "John",Space,Str "Gruber",Str "\8217",Str "s",Space,Str "markdown",Space,Str "test",Space,Str "suite",Str "."] +[Para [Str "This",Space,Str "is",Space,Str "a",Space,Str "set",Space,Str "of",Space,Str "tests",Space,Str "for",Space,Str "pandoc",Space,Str "Textile",Space,Str "Reader.",Space,Str "Part",Space,Str "of",Space,Str "it",Space,Str "comes",LineBreak,Str "from",Space,Str "John",Space,Str "Gruber\8217s",Space,Str "markdown",Space,Str "test",Space,Str "suite."] ,HorizontalRule ,Header 1 ("headers",[],[]) [Str "Headers"] ,Header 2 ("level-2-with-an-embeded-link",[],[]) [Str "Level",Space,Str "2",Space,Str "with",Space,Str "an",Space,Link [Str "embeded",Space,Str "link"] ("http://www.example.com","")] @@ -8,42 +8,42 @@ Pandoc (Meta {unMeta = fromList []}) ,Header 5 ("level-5",[],[]) [Str "Level",Space,Str "5"] ,Header 6 ("level-6",[],[]) [Str "Level",Space,Str "6"] ,Header 1 ("paragraphs",[],[]) [Str "Paragraphs"] -,Para [Str "Here",Str "\8217",Str "s",Space,Str "a",Space,Str "regular",Space,Str "paragraph",Str "."] -,Para [Str "Line",Space,Str "breaks",Space,Str "are",Space,Str "preserved",Space,Str "in",Space,Str "textile",Str ",",Space,Str "so",Space,Str "you",Space,Str "can",Space,Str "not",Space,Str "wrap",Space,Str "your",Space,Str "very",LineBreak,Str "long",Space,Str "paragraph",Space,Str "with",Space,Str "your",Space,Str "favourite",Space,Str "text",Space,Str "editor",Space,Str "and",Space,Str "have",Space,Str "it",Space,Str "rendered",LineBreak,Str "with",Space,Str "no",Space,Str "break",Str "."] -,Para [Str "Here",Str "\8217",Str "s",Space,Str "one",Space,Str "with",Space,Str "a",Space,Str "bullet",Str "."] +,Para [Str "Here\8217s",Space,Str "a",Space,Str "regular",Space,Str "paragraph."] +,Para [Str "Line",Space,Str "breaks",Space,Str "are",Space,Str "preserved",Space,Str "in",Space,Str "textile,",Space,Str "so",Space,Str "you",Space,Str "can",Space,Str "not",Space,Str "wrap",Space,Str "your",Space,Str "very",LineBreak,Str "long",Space,Str "paragraph",Space,Str "with",Space,Str "your",Space,Str "favourite",Space,Str "text",Space,Str "editor",Space,Str "and",Space,Str "have",Space,Str "it",Space,Str "rendered",LineBreak,Str "with",Space,Str "no",Space,Str "break."] +,Para [Str "Here\8217s",Space,Str "one",Space,Str "with",Space,Str "a",Space,Str "bullet."] ,BulletList - [[Plain [Str "criminey",Str "."]]] + [[Plain [Str "criminey."]]] ,Para [Str "There",Space,Str "should",Space,Str "be",Space,Str "a",Space,Str "paragraph",Space,Str "break",Space,Str "between",Space,Str "here"] -,Para [Str "and",Space,Str "here",Str "."] -,Para [Str "pandoc",Space,Str "converts",Space,Str "textile",Str "."] +,Para [Str "and",Space,Str "here."] +,Para [Str "pandoc",Space,Str "converts",Space,Str "textile."] ,Header 1 ("block-quotes",[],[]) [Str "Block",Space,Str "Quotes"] ,BlockQuote - [Para [Str "This",Space,Str "is",Space,Str "a",Space,Str "famous",Space,Str "quote",Space,Str "from",Space,Str "somebody",Str ".",Space,Str "He",Space,Str "had",Space,Str "a",Space,Str "lot",Space,Str "of",Space,Str "things",Space,Str "to",LineBreak,Str "say",Str ",",Space,Str "so",Space,Str "the",Space,Str "text",Space,Str "is",Space,Str "really",Space,Str "really",Space,Str "long",Space,Str "and",Space,Str "spans",Space,Str "on",Space,Str "multiple",Space,Str "lines",Str "."]] -,Para [Str "And",Space,Str "a",Space,Str "following",Space,Str "paragraph",Str "."] + [Para [Str "This",Space,Str "is",Space,Str "a",Space,Str "famous",Space,Str "quote",Space,Str "from",Space,Str "somebody.",Space,Str "He",Space,Str "had",Space,Str "a",Space,Str "lot",Space,Str "of",Space,Str "things",Space,Str "to",LineBreak,Str "say,",Space,Str "so",Space,Str "the",Space,Str "text",Space,Str "is",Space,Str "really",Space,Str "really",Space,Str "long",Space,Str "and",Space,Str "spans",Space,Str "on",Space,Str "multiple",Space,Str "lines."]] +,Para [Str "And",Space,Str "a",Space,Str "following",Space,Str "paragraph."] ,Header 1 ("code-blocks",[],[]) [Str "Code",Space,Str "Blocks"] -,Para [Str "Code",Str ":"] +,Para [Str "Code:"] ,CodeBlock ("",[],[]) " ---- (should be four hyphens)\n\n sub status {\n print \"working\";\n }\n\n this code block is indented by one tab" -,Para [Str "And",Str ":"] +,Para [Str "And:"] ,CodeBlock ("",[],[]) " this code block is indented by two tabs\n\n These should not be escaped: \\$ \\\\ \\> \\[ \\{" ,CodeBlock ("",[],[]) "Code block with .bc\n continued\n @</\\\n" -,Para [Str "Inline",Space,Str "code",Str ":",Space,Code ("",[],[]) "<tt>",Str ",",Space,Code ("",[],[]) "@",Str "."] +,Para [Str "Inline",Space,Str "code:",Space,Code ("",[],[]) "<tt>",Str ",",Space,Code ("",[],[]) "@",Str "."] ,Header 1 ("notextile",[],[]) [Str "Notextile"] ,Para [Str "A",Space,Str "block",Space,Str "of",Space,Str "text",Space,Str "can",Space,Str "be",Space,Str "protected",Space,Str "with",Space,Str "notextile",Space,Str ":"] ,Para [Str "\nNo *bold* and\n* no bullet\n"] -,Para [Str "and",Space,Str "inlines",Space,Str "can",Space,Str "be",Space,Str "protected",Space,Str "with",Space,Str "double *equals (=)* markup",Str "."] +,Para [Str "and",Space,Str "inlines",Space,Str "can",Space,Str "be",Space,Str "protected",Space,Str "with",Space,Str "double *equals (=)* markup."] ,Header 1 ("lists",[],[]) [Str "Lists"] ,Header 2 ("unordered",[],[]) [Str "Unordered"] -,Para [Str "Asterisks",Space,Str "tight",Str ":"] +,Para [Str "Asterisks",Space,Str "tight:"] ,BulletList [[Plain [Str "asterisk",Space,Str "1"]] ,[Plain [Str "asterisk",Space,Str "2"]] ,[Plain [Str "asterisk",Space,Str "3"]]] -,Para [Str "With",Space,Str "line",Space,Str "breaks",Str ":"] +,Para [Str "With",Space,Str "line",Space,Str "breaks:"] ,BulletList [[Plain [Str "asterisk",Space,Str "1",LineBreak,Str "newline"]] ,[Plain [Str "asterisk",Space,Str "2"]]] ,Header 2 ("ordered",[],[]) [Str "Ordered"] -,Para [Str "Tight",Str ":"] +,Para [Str "Tight:"] ,OrderedList (1,DefaultStyle,DefaultDelim) [[Plain [Str "First"]] ,[Plain [Str "Second"]] @@ -52,42 +52,51 @@ Pandoc (Meta {unMeta = fromList []}) ,BulletList [[Plain [Str "ui",Space,Str "1"] ,BulletList - [[Plain [Str "ui",Space,Str "1",Str ".",Str "1"] + [[Plain [Str "ui",Space,Str "1.1"] ,OrderedList (1,DefaultStyle,DefaultDelim) - [[Plain [Str "oi",Space,Str "1",Str ".",Str "1",Str ".",Str "1"]] - ,[Plain [Str "oi",Space,Str "1",Str ".",Str "1",Str ".",Str "2"]]]] - ,[Plain [Str "ui",Space,Str "1",Str ".",Str "2"]]]] + [[Plain [Str "oi",Space,Str "1.1.1"]] + ,[Plain [Str "oi",Space,Str "1.1.2"]]]] + ,[Plain [Str "ui",Space,Str "1.2"]]]] ,[Plain [Str "ui",Space,Str "2"] ,OrderedList (1,DefaultStyle,DefaultDelim) - [[Plain [Str "oi",Space,Str "2",Str ".",Str "1"] + [[Plain [Str "oi",Space,Str "2.1"] ,BulletList - [[Plain [Str "ui",Space,Str "2",Str ".",Str "1",Str ".",Str "1"]] - ,[Plain [Str "ui",Space,Str "2",Str ".",Str "1",Str ".",Str "2"]]]]]]] + [[Plain [Str "ui",Space,Str "2.1.1"]] + ,[Plain [Str "ui",Space,Str "2.1.2"]]]]]]] +,Header 2 ("issue-1500",[],[]) [Str "Issue",Space,Str "#1500"] +,BulletList + [[Plain [Str "one"]] + ,[Plain [Str "two",LineBreak,Str "->",Space,Str "and",Space,Str "more"]]] +,Header 2 ("issue-1513",[],[]) [Str "Issue",Space,Str "#1513"] +,Para [Str "List:"] +,BulletList + [[Plain [Str "one"]] + ,[Plain [Str "two"]]] ,Header 2 ("definition-list",[],[]) [Str "Definition",Space,Str "List"] ,DefinitionList [([Str "coffee"], [[Plain [Str "Hot",Space,Str "and",Space,Str "black"]]]) ,([Str "tea"], - [[Plain [Str "Also",Space,Str "hot",Str ",",Space,Str "but",Space,Str "a",Space,Str "little",Space,Str "less",Space,Str "black"]]]) + [[Plain [Str "Also",Space,Str "hot,",Space,Str "but",Space,Str "a",Space,Str "little",Space,Str "less",Space,Str "black"]]]) ,([Str "milk"], - [[Para [Str "Nourishing",Space,Str "beverage",Space,Str "for",Space,Str "baby",Space,Str "cows",Str "."] - ,Para [Str "Cold",Space,Str "drink",Space,Str "that",Space,Str "goes",Space,Str "great",Space,Str "with",Space,Str "cookies",Str "."]]]) + [[Para [Str "Nourishing",Space,Str "beverage",Space,Str "for",Space,Str "baby",Space,Str "cows."] + ,Para [Str "Cold",Space,Str "drink",Space,Str "that",Space,Str "goes",Space,Str "great",Space,Str "with",Space,Str "cookies."]]]) ,([Str "beer"], [[Plain [Str "fresh",Space,Str "and",Space,Str "bitter"]]])] ,Header 1 ("inline-markup",[],[]) [Str "Inline",Space,Str "Markup"] -,Para [Str "This",Space,Str "is",Space,Emph [Str "emphasized"],Str ",",Space,Str "and",Space,Str "so",Space,Emph [Str "is",Space,Str "this"],Str ".",LineBreak,Str "This",Space,Str "is",Space,Strong [Str "strong"],Str ",",Space,Str "and",Space,Str "so",Space,Strong [Str "is",Space,Str "this"],Str ".",LineBreak,Str "Hyphenated-words-are-ok",Str ",",Space,Str "as",Space,Str "well",Space,Str "as",Space,Str "strange_underscore_notation",Str ".",LineBreak,Str "A",Space,Link [Strong [Str "strong",Space,Str "link"]] ("http://www.foobar.com",""),Str "."] -,Para [Emph [Strong [Str "This",Space,Str "is",Space,Str "strong",Space,Str "and",Space,Str "em",Str "."]],LineBreak,Str "So",Space,Str "is",Space,Strong [Emph [Str "this"]],Space,Str "word",Space,Str "and",Space,Emph [Strong [Str "that",Space,Str "one"]],Str ".",LineBreak,Strikeout [Str "This",Space,Str "is",Space,Str "strikeout",Space,Str "and",Space,Strong [Str "strong"]]] -,Para [Str "Superscripts",Str ":",Space,Str "a",Superscript [Str "bc"],Str "d",Space,Str "a",Superscript [Strong [Str "hello"]],Space,Str "a",Superscript [Str "hello",Space,Str "there"],Str ".",LineBreak,Str "Subscripts",Str ":",Space,Subscript [Str "here"],Space,Str "H",Subscript [Str "2"],Str "O",Str ",",Space,Str "H",Subscript [Str "23"],Str "O",Str ",",Space,Str "H",Subscript [Str "many",Space,Str "of",Space,Str "them"],Str "O",Str "."] -,Para [Str "Dashes",Space,Str ":",Space,Str "How",Space,Str "cool",Space,Str "\8212",Space,Str "automatic",Space,Str "dashes",Str "."] -,Para [Str "Elipses",Space,Str ":",Space,Str "He",Space,Str "thought",Space,Str "and",Space,Str "thought",Space,Str "\8230",Space,Str "and",Space,Str "then",Space,Str "thought",Space,Str "some",Space,Str "more",Str "."] -,Para [Str "Quotes",Space,Str "and",Space,Str "apostrophes",Space,Str ":",Space,Quoted DoubleQuote [Str "I",Str "\8217",Str "d",Space,Str "like",Space,Str "to",Space,Str "thank",Space,Str "you"],Space,Str "for",Space,Str "example",Str "."] +,Para [Str "This",Space,Str "is",Space,Emph [Str "emphasized"],Str ",",Space,Str "and",Space,Str "so",Space,Emph [Str "is",Space,Str "this"],Str ".",LineBreak,Str "This",Space,Str "is",Space,Strong [Str "strong"],Str ",",Space,Str "and",Space,Str "so",Space,Strong [Str "is",Space,Str "this"],Str ".",LineBreak,Str "Hyphenated-words-are-ok,",Space,Str "as",Space,Str "well",Space,Str "as",Space,Str "strange_underscore_notation.",LineBreak,Str "A",Space,Link [Strong [Str "strong",Space,Str "link"]] ("http://www.foobar.com",""),Str "."] +,Para [Emph [Strong [Str "This",Space,Str "is",Space,Str "strong",Space,Str "and",Space,Str "em."]],LineBreak,Str "So",Space,Str "is",Space,Strong [Emph [Str "this"]],Space,Str "word",Space,Str "and",Space,Emph [Strong [Str "that",Space,Str "one"]],Str ".",LineBreak,Strikeout [Str "This",Space,Str "is",Space,Str "strikeout",Space,Str "and",Space,Strong [Str "strong"]]] +,Para [Str "Superscripts:",Space,Str "a",Superscript [Str "bc"],Str "d",Space,Str "a",Space,Superscript [Strong [Str "hello"]],Space,Str "a",Superscript [Str "hello",Space,Str "there"],Str ".",LineBreak,Str "Subscripts:",Space,Subscript [Str "here"],Space,Str "H",Space,Subscript [Str "2"],Str "O,",Space,Str "H",Space,Subscript [Str "23"],Str "O,",Space,Str "H",Space,Subscript [Str "many",Space,Str "of",Space,Str "them"],Str "O."] +,Para [Str "Dashes",Space,Str ":",Space,Str "How",Space,Str "cool",Space,Str "\8212",Space,Str "automatic",Space,Str "dashes."] +,Para [Str "Elipses",Space,Str ":",Space,Str "He",Space,Str "thought",Space,Str "and",Space,Str "thought",Space,Str "\8230",Space,Str "and",Space,Str "then",Space,Str "thought",Space,Str "some",Space,Str "more."] +,Para [Str "Quotes",Space,Str "and",Space,Str "apostrophes",Space,Str ":",Space,Quoted DoubleQuote [Str "I\8217d",Space,Str "like",Space,Str "to",Space,Str "thank",Space,Str "you"],Space,Str "for",Space,Str "example."] ,Header 1 ("links",[],[]) [Str "Links"] ,Header 2 ("explicit",[],[]) [Str "Explicit"] ,Para [Str "Just",Space,Str "a",Space,Link [Str "url"] ("http://www.url.com","")] ,Para [Link [Str "Email",Space,Str "link"] ("mailto:nobody@nowhere.net","")] ,Para [Str "Automatic",Space,Str "linking",Space,Str "to",Space,Link [Str "http://www.example.com"] ("http://www.example.com",""),Str "."] -,Para [Link [Str "Example"] ("http://www.example.com/",""),Str ":",Space,Str "Example",Space,Str "of",Space,Str "a",Space,Str "link",Space,Str "followed",Space,Str "by",Space,Str "a",Space,Str "colon",Str "."] -,Para [Str "A",Space,Str "link",Link [Str "with",Space,Str "brackets"] ("http://www.example.com",""),Str "and",Space,Str "no",Space,Str "spaces",Str "."] +,Para [Link [Str "Example"] ("http://www.example.com/",""),Str ":",Space,Str "Example",Space,Str "of",Space,Str "a",Space,Str "link",Space,Str "followed",Space,Str "by",Space,Str "a",Space,Str "colon."] +,Para [Str "A",Space,Str "link",Link [Str "with",Space,Str "brackets"] ("http://www.example.com",""),Str "and",Space,Str "no",Space,Str "spaces."] ,Header 1 ("tables",[],[]) [Str "Tables"] ,Para [Str "Textile",Space,Str "allows",Space,Str "tables",Space,Str "with",Space,Str "and",Space,Str "without",Space,Str "headers",Space,Str ":"] ,Header 2 ("without-headers",[],[]) [Str "Without",Space,Str "headers"] @@ -121,11 +130,11 @@ Pandoc (Meta {unMeta = fromList []}) ,[Plain [Str "45"]] ,[Plain [Str "f"]]]] ,Header 1 ("images",[],[]) [Str "Images"] -,Para [Str "Textile",Space,Str "inline",Space,Str "image",Space,Str "syntax",Str ",",Space,Str "like",Space,LineBreak,Str "here",Space,Image [Str "this is the alt text"] ("this_is_an_image.png","this is the alt text"),LineBreak,Str "and",Space,Str "here",Space,Image [Str ""] ("this_is_an_image.png",""),Str "."] +,Para [Str "Textile",Space,Str "inline",Space,Str "image",Space,Str "syntax,",Space,Str "like",LineBreak,Str "here",Space,Image [Str "this is the alt text"] ("this_is_an_image.png","this is the alt text"),LineBreak,Str "and",Space,Str "here",Space,Image [Str ""] ("this_is_an_image.png",""),Str "."] ,Header 1 ("attributes",[],[]) [Str "Attributes"] -,Header 2 ("ident",["bar","foo"],[("style","color:red"),("lang","en")]) [Str "HTML",Space,Str "and",Space,Str "CSS",Space,Str "attributes",Space,Str "are",Space,Str "parsed",Space,Str "in",Space,Str "headers",Str "."] -,Para [Str "as",Space,Str "well",Space,Str "as",Space,Strong [Str "inline",Space,Str "attributes"],Space,Str "of",Space,Str " all kind"] -,Para [Str "and",Space,Str "paragraph",Space,Str "attributes",Str ",",Space,Str "and",Space,Str "table",Space,Str "attributes",Str "."] +,Header 2 ("ident",["bar","foo"],[("style","color:red"),("lang","en")]) [Str "HTML",Space,Str "and",Space,Str "CSS",Space,Str "attributes",Space,Str "are",Space,Str "parsed",Space,Str "in",Space,Str "headers."] +,Para [Str "as",Space,Str "well",Space,Str "as",Space,Strong [Span ("",["foo"],[]) [Str "inline",Space,Str "attributes"]],Space,Str "of",Space,Span ("",[],[("style","color:red")]) [Str "all",Space,Str "kind"]] +,Para [Str "and",Space,Str "paragraph",Space,Str "attributes,",Space,Str "and",Space,Str "table",Space,Str "attributes."] ,Table [] [AlignDefault,AlignDefault,AlignDefault] [0.0,0.0,0.0] [] [[[Plain [Str "name"]] @@ -137,31 +146,22 @@ Pandoc (Meta {unMeta = fromList []}) ,Header 1 ("entities",[],[]) [Str "Entities"] ,Para [Str "*",LineBreak,Str "&"] ,Header 1 ("raw-html",[],[]) [Str "Raw",Space,Str "HTML"] -,Para [Str "However",Str ",",Space,RawInline (Format "html") "<strong>",Space,Str "raw",Space,Str "HTML",Space,Str "inlines",Space,RawInline (Format "html") "</strong>",Space,Str "are",Space,Str "accepted",Str ",",Space,Str "as",Space,Str "well",Space,Str "as",Space,Str ":"] +,Para [Str "However,",Space,RawInline (Format "html") "<strong>",Space,Str "raw",Space,Str "HTML",Space,Str "inlines",Space,RawInline (Format "html") "</strong>",Space,Str "are",Space,Str "accepted,",Space,Str "as",Space,Str "well",Space,Str "as",Space,Str ":"] ,RawBlock (Format "html") "<div class=\"foobar\">" ,Para [Str "any",Space,Strong [Str "Raw",Space,Str "HTML",Space,Str "Block"],Space,Str "with",Space,Str "bold"] ,RawBlock (Format "html") "</div>" -,Para [Str "Html",Space,Str "blocks",Space,Str "can",Space,Str "be"] -,RawBlock (Format "html") "<div>" -,Para [Str "inlined"] -,RawBlock (Format "html") "</div>" -,Para [Str "as",Space,Str "well",Str "."] +,Para [Str "Html",Space,Str "blocks",Space,Str "can",Space,Str "be",Space,RawInline (Format "html") "<div>",Str "inlined",RawInline (Format "html") "</div>",Space,Str "as",Space,Str "well."] ,BulletList - [[Plain [Str "this",Space,Str "<",Str "div",Str ">",Space,Str "won",Str "\8217",Str "t",Space,Str "produce",Space,Str "raw",Space,Str "html",Space,Str "blocks",Space,Str "<",Str "/div",Str ">"]] + [[Plain [Str "this",Space,RawInline (Format "html") "<div>",Space,Str "won\8217t",Space,Str "produce",Space,Str "raw",Space,Str "html",Space,Str "blocks",Space,RawInline (Format "html") "</div>"]] ,[Plain [Str "but",Space,Str "this",Space,RawInline (Format "html") "<strong>",Space,Str "will",Space,Str "produce",Space,Str "inline",Space,Str "html",Space,RawInline (Format "html") "</strong>"]]] ,Para [Str "Can",Space,Str "you",Space,Str "prove",Space,Str "that",Space,Str "2",Space,Str "<",Space,Str "3",Space,Str "?"] -,Header 1 ("raw-latex",[],[]) [Str "Raw",Space,Str "LaTeX"] -,Para [Str "This",Space,Str "Textile",Space,Str "reader",Space,Str "also",Space,Str "accepts",Space,Str "raw",Space,Str "LaTeX",Space,Str "for",Space,Str "blocks",Space,Str ":"] -,RawBlock (Format "latex") "\\begin{itemize}\n \\item one\n \\item two\n\\end{itemize}" -,Para [Str "and",Space,Str "for",Space,RawInline (Format "latex") "\\emph{inlines}",Str "."] ,Header 1 ("acronyms-and-marks",[],[]) [Str "Acronyms",Space,Str "and",Space,Str "marks"] ,Para [Str "PBS (Public Broadcasting System)"] -,Para [Str "Hi",Str "\8482"] +,Para [Str "Hi\8482"] ,Para [Str "Hi",Space,Str "\8482"] -,Para [Str "\174",Space,Str "Hi",Str "\174"] -,Para [Str "Hi",Str "\169",Str "2008",Space,Str "\169",Space,Str "2008"] +,Para [Str "\174",Space,Str "Hi\174"] +,Para [Str "Hi\169\&2008",Space,Str "\169",Space,Str "2008"] ,Header 1 ("footnotes",[],[]) [Str "Footnotes"] -,Para [Str "A",Space,Str "note",Str ".",Note [Para [Str "The",Space,Str "note",LineBreak,Str "is",Space,Str "here",Str "!"]],Space,Str "Another",Space,Str "note",Note [Para [Str "Other",Space,Str "note",Str "."]],Str "."] +,Para [Str "A",Space,Str "note.",Note [Para [Str "The",Space,Str "note",LineBreak,Str "is",Space,Str "here!"]],Space,Str "Another",Space,Str "note",Note [Para [Str "Other",Space,Str "note."]],Str "."] ,Header 1 ("comment-blocks",[],[]) [Str "Comment",Space,Str "blocks"] -,Null -,Para [Str "not",Space,Str "a",Space,Str "comment",Str "."]] +,Para [Str "not",Space,Str "a",Space,Str "comment."]] diff --git a/tests/textile-reader.textile b/tests/textile-reader.textile index e31052b6a..dab73b39f 100644 --- a/tests/textile-reader.textile +++ b/tests/textile-reader.textile @@ -117,6 +117,18 @@ h2. Nested *** ui 2.1.1 *** ui 2.1.2 +h2. Issue #1500 + +* one +* two +-> and more + +h2. Issue #1513 + +List: +* one +* two + h2. Definition List - coffee := Hot and black @@ -139,8 +151,8 @@ _*This is strong and em.*_ So is *_this_* word and __**that one**__. -This is strikeout and *strong*- -Superscripts: a[^bc^]d a^*hello*^ a[^hello there^]. -Subscripts: ~here~ H[~2~]O, H[~23~]O, H[~many of them~]O. +Superscripts: a[^bc^]d a ^*hello*^ a[^hello there^]. +Subscripts: ~here~ H[ ~2~]O, H[ ~23~]O, H[ ~many of them~]O. Dashes : How cool -- automatic dashes. @@ -187,7 +199,7 @@ h2. With headers h1. Images -Textile inline image syntax, like +Textile inline image syntax, like here !this_is_an_image.png(this is the alt text)! and here !this_is_an_image.png!. @@ -223,17 +235,6 @@ Html blocks can be <div>inlined</div> as well. Can you prove that 2 < 3 ? -h1. Raw LaTeX - -This Textile reader also accepts raw LaTeX for blocks : - -\begin{itemize} - \item one - \item two -\end{itemize} - -and for \emph{inlines}. - h1. Acronyms and marks PBS(Public Broadcasting System) diff --git a/tests/twiki-reader.native b/tests/twiki-reader.native new file mode 100644 index 000000000..bde55a378 --- /dev/null +++ b/tests/twiki-reader.native @@ -0,0 +1,174 @@ +Pandoc (Meta {unMeta = fromList []}) +[Header 1 ("header",[],[]) [Str "header"] +,Header 2 ("header-level-two",[],[]) [Str "header",Space,Str "level",Space,Str "two"] +,Header 3 ("header-level-3",[],[]) [Str "header",Space,Str "level",Space,Str "3"] +,Header 4 ("header-level-four",[],[]) [Str "header",Space,Emph [Str "level"],Space,Str "four"] +,Header 5 ("header-level-5",[],[]) [Str "header",Space,Str "level",Space,Str "5"] +,Header 6 ("header-level-6",[],[]) [Str "header",Space,Str "level",Space,Str "6"] +,Para [Str "---+++++++",Space,Str "not",Space,Str "a",Space,Str "header"] +,Para [Str "--++",Space,Str "not",Space,Str "a",Space,Str "header"] +,Header 1 ("emph-and-strong",[],[]) [Str "emph",Space,Str "and",Space,Str "strong"] +,Para [Emph [Str "emph"],Space,Strong [Str "strong"]] +,Para [Emph [Strong [Str "strong",Space,Str "and",Space,Str "emph"]]] +,Para [Strong [Emph [Str "emph",Space,Str "inside"],Space,Str "strong"]] +,Para [Strong [Str "strong",Space,Str "with",Space,Emph [Str "emph"]]] +,Para [Emph [Strong [Str "strong",Space,Str "inside"],Space,Str "emph"]] +,Header 1 ("horizontal-rule",[],[]) [Str "horizontal",Space,Str "rule"] +,Para [Str "top"] +,HorizontalRule +,Para [Str "bottom"] +,HorizontalRule +,Header 1 ("nop",[],[]) [Str "nop"] +,Para [Str "_not",Space,Str "emph_"] +,Header 1 ("entities",[],[]) [Str "entities"] +,Para [Str "hi",Space,Str "&",Space,Str "low"] +,Para [Str "hi",Space,Str "&",Space,Str "low"] +,Para [Str "G\246del"] +,Para [Str "\777\2730"] +,Header 1 ("comments",[],[]) [Str "comments"] +,Para [Str "inline",Space,Str "comment"] +,Para [Str "between",Space,Str "blocks"] +,Header 1 ("linebreaks",[],[]) [Str "linebreaks"] +,Para [Str "hi",LineBreak,Str "there"] +,Para [Str "hi",LineBreak,Space,Str "there"] +,Header 1 ("inline-code",[],[]) [Str "inline",Space,Str "code"] +,Para [Code ("",[],[]) "*\8594*",Space,Code ("",[],[]) "typed",Space,Code ("",["haskell"],[]) ">>="] +,Header 1 ("code-blocks",[],[]) [Str "code",Space,Str "blocks"] +,CodeBlock ("",[],[]) "case xs of\n (_:_) -> reverse xs\n [] -> ['*']" +,CodeBlock ("",["haskell"],[]) "case xs of\n (_:_) -> reverse xs\n [] -> ['*']" +,Header 1 ("block-quotes",[],[]) [Str "block",Space,Str "quotes"] +,Para [Str "Regular",Space,Str "paragraph"] +,BlockQuote + [Para [Str "This",Space,Str "is",Space,Str "a",Space,Str "block",Space,Str "quote."] + ,Para [Str "With",Space,Str "two",Space,Str "paragraphs."]] +,Para [Str "Nother",Space,Str "paragraph."] +,Header 1 ("external-links",[],[]) [Str "external",Space,Str "links"] +,Para [Link [Emph [Str "Google"],Space,Str "search",Space,Str "engine"] ("http://google.com","")] +,Para [Link [Str "http://johnmacfarlane.net/pandoc/"] ("http://johnmacfarlane.net/pandoc/","")] +,Para [Link [Str "http://google.com"] ("http://google.com",""),Space,Link [Str "http://yahoo.com"] ("http://yahoo.com","")] +,Para [Link [Str "email",Space,Str "me"] ("mailto:info@example.org","")] +,Para [Str "http://google.com"] +,Para [Str "http://google.com"] +,Para [Str "http://google.com"] +,Para [Str "info@example.org"] +,Para [Str "info@example.org"] +,Para [Str "info@example.org"] +,Header 1 ("lists",[],[]) [Str "lists"] +,BulletList + [[Plain [Str "Start",Space,Str "each",Space,Str "line"]] + ,[Plain [Str "with",Space,Str "an",Space,Str "asterisk",Space,Str "(*)."] + ,BulletList + [[Plain [Str "More",Space,Str "asterisks",Space,Str "gives",Space,Str "deeper"] + ,BulletList + [[Plain [Str "and",Space,Str "deeper",Space,Str "levels."]]]]]] + ,[Plain [Str "Line",Space,Str "breaks",LineBreak,Str "don't",Space,Str "break",Space,Str "levels."]] + ,[Plain [Str "Continuations",Space,Str "are",Space,Str "also",Space,Str "possible"] + ,BulletList + [[Plain [Str "and",Space,Str "do",Space,Str "not",Space,Str "break",Space,Str "the",Space,Str "list",Space,Str "flow"]]]] + ,[Plain [Str "Level",Space,Str "one"]]] +,Para [Str "Any",Space,Str "other",Space,Str "start",Space,Str "ends",Space,Str "the",Space,Str "list."] +,OrderedList (1,DefaultStyle,DefaultDelim) + [[Plain [Str "Start",Space,Str "each",Space,Str "line"]] + ,[Plain [Str "with",Space,Str "a",Space,Str "number",Space,Str "(1.)."] + ,OrderedList (1,DefaultStyle,DefaultDelim) + [[Plain [Str "More",Space,Str "number",Space,Str "signs",Space,Str "gives",Space,Str "deeper"] + ,OrderedList (1,DefaultStyle,DefaultDelim) + [[Plain [Str "and",Space,Str "deeper"]] + ,[Plain [Str "levels."]]]]]] + ,[Plain [Str "Line",Space,Str "breaks",LineBreak,Str "don't",Space,Str "break",Space,Str "levels."]] + ,[Plain [Str "Blank",Space,Str "lines"]]] +,OrderedList (1,DefaultStyle,DefaultDelim) + [[Plain [Str "end",Space,Str "the",Space,Str "list",Space,Str "and",Space,Str "start",Space,Str "another."]]] +,Para [Str "Any",Space,Str "other",Space,Str "start",Space,Str "also",Space,Str "ends",Space,Str "the",Space,Str "list."] +,DefinitionList + [([Str "item",Space,Str "1"], + [[Plain [Str "definition",Space,Str "1"]]]) + ,([Str "item",Space,Str "2"], + [[Plain [Str "definition",Space,Str "2-1",Space,Str "definition",Space,Str "2-2"]]]) + ,([Str "item",Space,Emph [Str "3"]], + [[Plain [Str "definition",Space,Emph [Str "3"]]]])] +,OrderedList (1,DefaultStyle,DefaultDelim) + [[Plain [Str "one"]] + ,[Plain [Str "two"] + ,BulletList + [[Plain [Str "two",Space,Str "point",Space,Str "one"]] + ,[Plain [Str "two",Space,Str "point",Space,Str "two"]]]] + ,[Plain [Str "three"] + ,DefinitionList + [([Str "three",Space,Str "item",Space,Str "one"], + [[Plain [Str "three",Space,Str "def",Space,Str "one"]]])]] + ,[Plain [Str "four"] + ,DefinitionList + [([Str "four",Space,Str "def",Space,Str "one"], + [[Plain [Str "this",Space,Str "is",Space,Str "a",Space,Str "continuation"]]])]] + ,[Plain [Str "five"] + ,OrderedList (1,DefaultStyle,DefaultDelim) + [[Plain [Str "five",Space,Str "sub",Space,Str "1"] + ,OrderedList (1,DefaultStyle,DefaultDelim) + [[Plain [Str "five",Space,Str "sub",Space,Str "1",Space,Str "sub",Space,Str "1"]]]] + ,[Plain [Str "five",Space,Str "sub",Space,Str "2"]]]]] +,OrderedList (1,DefaultStyle,DefaultDelim) + [[Plain [Str "other"] + ,OrderedList (1,UpperRoman,DefaultDelim) + [[Plain [Str "list"]] + ,[Plain [Str "styles"]]]] + ,[Plain [Str "are"] + ,OrderedList (1,LowerRoman,DefaultDelim) + [[Plain [Str "also"]] + ,[Plain [Str "possible"]]]] + ,[Plain [Str "all"] + ,OrderedList (1,LowerAlpha,DefaultDelim) + [[Plain [Str "the"]] + ,[Plain [Str "different"]] + ,[Plain [Str "styles"]]]] + ,[Plain [Str "are"] + ,OrderedList (1,UpperAlpha,DefaultDelim) + [[Plain [Str "implemented"]] + ,[Plain [Str "and"]] + ,[Plain [Str "supported"]]]]] +,Header 1 ("tables",[],[]) [Str "tables"] +,Table [] [AlignDefault,AlignDefault] [0.0,0.0] + [[] + ,[]] + [[[Plain [Str "Orange"]] + ,[Plain [Str "Apple"]]] + ,[[Plain [Str "Bread"]] + ,[Plain [Str "Pie"]]] + ,[[Plain [Str "Butter"]] + ,[Plain [Str "Ice",Space,Str "cream"]]]] +,Table [] [AlignLeft,AlignLeft] [0.0,0.0] + [[Plain [Str "Orange"]] + ,[Plain [Str "Apple"]]] + [[[Plain [Str "Bread"]] + ,[Plain [Str "Pie"]]] + ,[[Plain [Strong [Str "Butter"]]] + ,[Plain [Str "Ice",Space,Str "cream"]]]] +,Table [] [AlignLeft,AlignLeft] [0.0,0.0] + [[Plain [Str "Orange"]] + ,[Plain [Str "Apple"]]] + [[[Plain [Str "Bread",LineBreak,LineBreak,Str "and",Space,Str "cheese"]] + ,[Plain [Str "Pie",LineBreak,LineBreak,Strong [Str "apple"],Space,Str "and",Space,Emph [Str "carrot"]]]]] +,Table [] [AlignDefault,AlignDefault,AlignDefault] [0.0,0.0,0.0] + [[] + ,[] + ,[]] + [[[Plain [Str "Orange"]] + ,[Plain [Str "Apple"]] + ,[Plain [Str "more"]]] + ,[[Plain [Str "Bread"]] + ,[Plain [Str "Pie"]] + ,[Plain [Str "more"]]] + ,[[Plain [Str "Butter"]] + ,[Plain [Str "Ice",Space,Str "cream"]] + ,[Plain [Str "and",Space,Str "more"]]]] +,Header 1 ("macros",[],[]) [Str "macros"] +,Para [Span ("",["twiki-macro","TEST"],[]) []] +,Para [Span ("",["twiki-macro","TEST"],[]) [Str ""]] +,Para [Span ("",["twiki-macro","TEST"],[]) [Str "content with spaces"]] +,Para [Span ("",["twiki-macro","TEST"],[]) [Str "content with spaces"]] +,Para [Span ("",["twiki-macro","TEST"],[("ARG1","test")]) [Str "content with spaces"]] +,Para [Span ("",["twiki-macro","TEST"],[]) [Str "content with spaces ARG1=test"]] +,Para [Span ("",["twiki-macro","TEST"],[("ARG1","test")]) [Str "content with spaces"]] +,Para [Span ("",["twiki-macro","TEST"],[("ARG1","test"),("ARG2","test2")]) [Str ""]] +,Para [Span ("",["twiki-macro","TEST"],[("ARG1","test"),("ARG2","test2")]) [Str ""]] +,Para [Span ("",["twiki-macro","TEST"],[("ARG1","test"),("ARG2","test2")]) [Str "multiline\ndoes also work"]]] diff --git a/tests/twiki-reader.twiki b/tests/twiki-reader.twiki new file mode 100644 index 000000000..51828ef80 --- /dev/null +++ b/tests/twiki-reader.twiki @@ -0,0 +1,221 @@ +---+ header + +---++ header level two + +---+++ header level 3 + +---++++ header _level_ four + +---+++++ header level 5 + +---++++++ header level 6 + +---+++++++ not a header + + --++ not a header + +---+ emph and strong + +_emph_ *strong* + +__strong and emph__ + +*<i>emph inside</i> strong* + +*strong with <i>emph</i>* + +_<b>strong inside</b> emph_ + +---+ horizontal rule + +top +--- +bottom + +--- + +---+ nop + +<nop>_not emph_ + +---+ entities + +hi & low + +hi & low + +Gödel + +̉પ + +---+ comments + +inline <!-- secret --> comment + +<!-- secret --> + +between blocks + + <!-- secret --> + +---+ linebreaks + +hi%BR%there + +hi%BR% +there + +---+ inline code + +<code>*→*</code> =typed= <code class="haskell">>>=</code> + +---+ code blocks + +<verbatim> +case xs of + (_:_) -> reverse xs + [] -> ['*'] +</verbatim> + +<verbatim class="haskell"> +case xs of + (_:_) -> reverse xs + [] -> ['*'] +</verbatim> + +---+ block quotes + +Regular paragraph +<blockquote> +This is a block quote. + +With two paragraphs. +</blockquote> +Nother paragraph. + +---+ external links + +[[http://google.com][<i>Google</i> search engine]] + +http://johnmacfarlane.net/pandoc/ + +[[http://google.com]] [[http://yahoo.com]] + +[[mailto:info@example.org][email me]] + +!http://google.com + +<nop>http://google.com + +<noautolink> +http://google.com +</noautolink> + +!info@example.org + +<nop>info@example.org + +<noautolink> +info@example.org +</noautolink> + +---+ lists + + * Start each line + * with an asterisk (*). + * More asterisks gives deeper + * and deeper levels. + * Line breaks%BR%don't break levels. + * Continuations + are also possible + * and do not break the list flow + * Level one +Any other start ends the list. + + 1. Start each line + 1. with a number (1.). + 1. More number signs gives deeper + 1. and deeper + 1. levels. + 1. Line breaks%BR%don't break levels. + 1. Blank lines + + 1. end the list and start another. +Any other start also +ends the list. + + $ item 1: definition 1 + $ item 2: definition 2-1 + definition 2-2 + $ item _3_: definition _3_ + + 1. one + 1. two + * two point one + * two point two + 1. three + $ three item one: three def one + 1. four + $ four def one: this + is a continuation + 1. five + 1. five sub 1 + 1. five sub 1 sub 1 + 1. five sub 2 + + 1. other + I. list + I. styles + 1. are + i. also + i. possible + 1. all + a. the + a. different + a. styles + 1. are + A. implemented + A. and + A. supported + +---+ tables + +|Orange|Apple| +|Bread|Pie| +|Butter|Ice cream| + +|*Orange*|*Apple*| +|Bread|Pie| +|*Butter*|Ice cream| + +|*Orange*|*Apple*| +|Bread%BR%%BR%and cheese|Pie%BR%%BR%*apple* and <i>carrot</i>| + +| Orange | Apple | more | +| Bread | Pie | more | +| Butter | Ice cream | and more | + +---+ macros + +%TEST% + +%TEST{}% + +%TEST{content with spaces}% + +%TEST{"content with spaces"}% + +%TEST{"content with spaces" ARG1="test"}% + +%TEST{content with spaces ARG1=test}% + +%TEST{ARG1=test content with spaces}% + +%TEST{ARG1=test ARG2=test2}% + +%TEST{ARG1="test" ARG2="test2"}% + +%TEST{ARG1="test" +ARG2="test2" +multiline +does also work}% diff --git a/tests/txt2tags.native b/tests/txt2tags.native new file mode 100644 index 000000000..189c099e2 --- /dev/null +++ b/tests/txt2tags.native @@ -0,0 +1,552 @@ +Pandoc (Meta {unMeta = fromList [("author",MetaList [MetaInlines [Str "author"]]),("date",MetaInlines [Str "date"]),("includeconf",MetaString "rules.conf"),("title",MetaInlines [Str "Txt2tags",Space,Str "Markup",Space,Str "Rules"])]}) +[Para [Str "This",Space,Str "document",Space,Str "describes",Space,Str "all",Space,Str "the",Space,Str "details",Space,Str "about",Space,Str "each",Space,Str "txt2tags",Space,Str "mark.",Space,Str "The",Space,Str "target",Space,Str "audience",Space,Str "are",Space,Strong [Str "experienced"],Space,Str "users.",Space,Str "You",Space,Str "may",Space,Str "find",Space,Str "it",Space,Str "useful",Space,Str "if",Space,Str "you",Space,Str "want",Space,Str "to",Space,Str "master",Space,Str "the",Space,Str "marks",Space,Str "or",Space,Str "solve",Space,Str "a",Space,Str "specific",Space,Str "problem",Space,Str "about",Space,Str "a",Space,Str "mark."] +,Para [Str "If",Space,Str "you",Space,Str "are",Space,Str "new",Space,Str "to",Space,Str "txt2tags",Space,Str "or",Space,Str "just",Space,Str "want",Space,Str "to",Space,Str "know",Space,Str "which",Space,Str "are",Space,Str "the",Space,Str "available",Space,Str "marks,",Space,Str "please",Space,Str "read",Space,Str "the",Space,Link [Str "Markup",Space,Str "Demo"] ("MARKUPDEMO",""),Str "."] +,Para [Str "Note",Space,Str "1:",Space,Str "This",Space,Str "document",Space,Str "is",Space,Str "generated",Space,Str "directly",Space,Str "from",Space,Str "the",Space,Str "txt2tags",Space,Str "test-suite.",Space,Str "All",Space,Str "the",Space,Str "rules",Space,Str "mentioned",Space,Str "here",Space,Str "are",Space,Str "100%",Space,Str "in",Space,Str "sync",Space,Str "with",Space,Str "the",Space,Str "current",Space,Str "program",Space,Str "code."] +,Para [Str "Note",Space,Str "2:",Space,Str "A",Space,Str "good",Space,Str "practice",Space,Str "is",Space,Str "to",Space,Str "consult",Space,Link [Str "the",Space,Str "sources"] ("rules.t2t",""),Space,Str "when",Space,Str "reading,",Space,Str "to",Space,Str "see",Space,Str "how",Space,Str "the",Space,Str "texts",Space,Str "were",Space,Str "made."] +,Para [Str "Table",Space,Str "of",Space,Str "Contents:"] +,HorizontalRule +,Header 1 ("paragraph",[],[]) [Str "Paragraph"] +,Para [Str "A",Space,Str "paragraph",Space,Str "is",Space,Str "composed",Space,Str "by",Space,Str "one",Space,Str "or",Space,Str "more",Space,Str "lines.",Space,Str "A",Space,Str "blank",Space,Str "line",Space,Str "(or",Space,Str "a",Space,Str "table,",Space,Str "or",Space,Str "a",Space,Str "list)",Space,Str "ends",Space,Str "the",Space,Str "current",Space,Str "paragraph."] +,Para [Str "Leading",Space,Str "and",Space,Str "trailing",Space,Str "spaces",Space,Str "are",Space,Str "ignored."] +,Para [Str "A",Space,Str "comment",Space,Str "line",Space,Str "can",Space,Str "be",Space,Str "placed",Space,Str "inside",Space,Str "a",Space,Str "paragraph.",Space,Str "It",Space,Str "will",Space,Str "not",Space,Str "affect",Space,Str "it."] +,Para [Str "The",Space,Str "end",Space,Str "of",Space,Str "the",Space,Str "file",Space,Str "(EOF)",Space,Str "closes",Space,Str "the",Space,Str "currently",Space,Str "open",Space,Str "paragraph."] +,Header 1 ("comment",[],[]) [Str "Comment"] +,Para [Str "%",Space,Str "not",Space,Str "on",Space,Str "the",Space,Str "line",Space,Str "beginning",Space,Str "(at",Space,Str "column",Space,Str "2)"] +,Para [Str "some",Space,Str "text",Space,Str "%",Space,Str "half",Space,Str "line",Space,Str "comments",Space,Str "are",Space,Str "not",Space,Str "allowed"] +,Header 1 ("line",[],[]) [Str "Line"] +,HorizontalRule +,HorizontalRule +,HorizontalRule +,HorizontalRule +,HorizontalRule +,HorizontalRule +,HorizontalRule +,HorizontalRule +,HorizontalRule +,HorizontalRule +,HorizontalRule +,Para [Strikeout [Str "-----"],Space,Strikeout [Str "-------",Space,Str "--------"]] +,Para [Strikeout [Str "-------+--------"]] +,Para [Str "(",Space,Strikeout [Str "----------------"],Space,Str ")"] +,Header 1 ("inline",[],[]) [Str "Inline"] +,Para [Str "i)",Space,Strong [Str "b"],Space,Emph [Str "i"],Space,Emph [Str "u"],Space,Strikeout [Str "s"],Space,Code ("",[],[]) "m",Space,Str "r",Space,RawInline (Format "html") "t",Space,Str "i)",Space,Strong [Str "bo"],Space,Emph [Str "it"],Space,Emph [Str "un"],Space,Strikeout [Str "st"],Space,Code ("",[],[]) "mo",Space,Str "ra",Space,RawInline (Format "html") "tg",Space,Str "i)",Space,Strong [Str "bold"],Space,Emph [Str "ital"],Space,Emph [Str "undr"],Space,Strikeout [Str "strk"],Space,Code ("",[],[]) "mono",Space,Str "raw",Space,RawInline (Format "html") "tggd",Space,Str "i)",Space,Strong [Str "bo",Space,Str "ld"],Space,Emph [Str "it",Space,Str "al"],Space,Emph [Str "un",Space,Str "dr"],Space,Strikeout [Str "st",Space,Str "rk"],Space,Code ("",[],[]) "mo no",Space,Str "r",Space,Str "aw",Space,RawInline (Format "html") "tg gd",Space,Str "i)",Space,Strong [Str "bo",Space,Str "*",Space,Str "ld"],Space,Emph [Str "it",Space,Str "/",Space,Str "al"],Space,Emph [Str "un",Space,Str "_",Space,Str "dr"],Space,Strikeout [Str "st",Space,Str "-",Space,Str "rk"],Space,Code ("",[],[]) "mo ` no",Space,Str "r",Space,Str "\"",Space,Str "aw",Space,RawInline (Format "html") "tg ' gd",Space,Str "i)",Space,Strong [Str "bo",Space,Str "**ld"],Space,Emph [Str "it",Space,Str "//al"],Space,Emph [Str "un",Space,Str "__dr"],Space,Strikeout [Str "st",Space,Str "--rk"],Space,Code ("",[],[]) "mo ``no",Space,Str "r",Space,Str "\"\"aw",Space,RawInline (Format "html") "tg ''gd",Space,Str "i)",Space,Strong [Str "bo",Space,Str "**",Space,Str "ld"],Space,Emph [Str "it",Space,Str "//",Space,Str "al"],Space,Emph [Str "un",Space,Str "__",Space,Str "dr"],Space,Strikeout [Str "st",Space,Str "--",Space,Str "rk"],Space,Code ("",[],[]) "mo `` no",Space,Str "r",Space,Str "\"\"",Space,Str "aw",Space,RawInline (Format "html") "tg '' gd",Space,Str "i)",Space,Strong [Str "**bold**"],Space,Emph [Str "//ital//"],Space,Emph [Str "__undr__"],Space,Strikeout [Str "--strk--"],Space,Code ("",[],[]) "``mono``",Space,Str "\"\"raw\"\"",Space,RawInline (Format "html") "''tggd''",Space,Str "i)",Space,Strong [Str "*bold*"],Space,Emph [Str "/ital/"],Space,Emph [Str "_undr_"],Space,Strikeout [Str "-strk-"],Space,Code ("",[],[]) "`mono`",Space,Str "\"raw\"",Space,RawInline (Format "html") "'tggd'"] +,Para [Str "i)",Space,Strong [Str "*"],Space,Emph [Str "/"],Space,Emph [Str "_"],Space,Strikeout [Str "-"],Space,Code ("",[],[]) "`",Space,Str "\"",Space,RawInline (Format "html") "'",Space,Str "i)",Space,Strong [Str "**"],Space,Emph [Str "//"],Space,Emph [Str "__"],Space,Strikeout [Str "--"],Space,Code ("",[],[]) "``",Space,Str "\"\"",Space,RawInline (Format "html") "''",Space,Str "i)",Space,Strong [Str "***"],Space,Emph [Str "///"],Space,Emph [Str "___"],Space,Strikeout [Str "---"],Space,Code ("",[],[]) "```",Space,Str "\"\"\"",Space,RawInline (Format "html") "'''",Space,Str "i)",Space,Strong [Str "****"],Space,Emph [Str "////"],Space,Emph [Str "____"],Space,Strikeout [Str "----"],Space,Code ("",[],[]) "````",Space,Str "\"\"\"\"",Space,RawInline (Format "html") "''''",Space,Str "i)",Space,Strong [Str "*****"],Space,Emph [Str "/////"],Space,Emph [Str "_____"],Space,Strikeout [Str "-----"],Space,Code ("",[],[]) "`````",Space,Str "\"\"\"\"\"",Space,RawInline (Format "html") "'''''",Space,Str "i)",Space,Strong [Str "******"],Space,Emph [Str "//////"],Space,Emph [Str "______"],Space,Strikeout [Str "------"],Space,Code ("",[],[]) "``````",Space,Str "\"\"\"\"\"\"",Space,RawInline (Format "html") "''''''"] +,Para [Str "i)",Space,Str "****",Space,Str "////",Space,Str "____",Space,Str "----",Space,Str "````",Space,Str "\"\"\"\"",Space,Str "''''",Space,Str "i)",Space,Str "**",Space,Str "**",Space,Str "//",Space,Str "//",Space,Str "__",Space,Str "__",Space,Str "--",Space,Str "--",Space,Str "``",Space,Str "``",Space,Str "\"\"",Space,Str "\"\"",Space,Str "''",Space,Str "''"] +,Para [Str "i)",Space,Str "**",Space,Str "bold**",Space,Str "//",Space,Str "ital//",Space,Str "__",Space,Str "undr__",Space,Str "--",Space,Str "strk--",Space,Str "``",Space,Str "mono``",Space,Str "\"\"",Space,Str "raw\"\"",Space,Str "''",Space,Str "tggd''",Space,Str "i)",Space,Str "**bold",Space,Str "**",Space,Str "//ital",Space,Str "//",Space,Str "__undr",Space,Str "__",Space,Str "--strk",Space,Str "--",Space,Str "``mono",Space,Str "``",Space,Str "\"\"raw",Space,Str "\"\"",Space,Str "''tggd",Space,Str "''",Space,Str "i)",Space,Str "**",Space,Str "bold",Space,Str "**",Space,Str "//",Space,Str "ital",Space,Str "//",Space,Str "__",Space,Str "undr",Space,Str "__",Space,Str "--",Space,Str "strk",Space,Str "--",Space,Str "``",Space,Str "mono",Space,Str "``",Space,Str "\"\"",Space,Str "raw",Space,Str "\"\"",Space,Str "''",Space,Str "tggd",Space,Str "''"] +,Header 1 ("link",[],[]) [Str "Link"] +,Para [Link [Str "mailto:user@domain.com"] ("user@domain.com",""),Space,Link [Str "mailto:user@domain.com"] ("user@domain.com",""),Str ".",Space,Link [Str "mailto:user@domain.com"] ("user@domain.com",""),Str ".",Space,Str "any",Space,Str "text.",Space,Str "any",Space,Str "text:",Space,Link [Str "mailto:user@domain.com"] ("user@domain.com",""),Str ".",Space,Str "any",Space,Str "text.",Space,Link [Str "label"] ("user@domain.com",""),Space,Link [Str "mailto:user@domain.com?subject=bla"] ("user@domain.com?subject=bla",""),Space,Link [Str "mailto:user@domain.com?subject=bla"] ("user@domain.com?subject=bla",""),Str ".",Space,Link [Str "mailto:user@domain.com?subject=bla"] ("user@domain.com?subject=bla",""),Str ",",Space,Link [Str "mailto:user@domain.com?subject=bla&cc=otheruser@domain.com"] ("user@domain.com?subject=bla&cc=otheruser@domain.com",""),Space,Link [Str "mailto:user@domain.com?subject=bla&cc=otheruser@domain.com"] ("user@domain.com?subject=bla&cc=otheruser@domain.com",""),Str ".",Space,Link [Str "mailto:user@domain.com?subject=bla&cc=otheruser@domain.com"] ("user@domain.com?subject=bla&cc=otheruser@domain.com",""),Str ",",Space,Link [Str "label"] ("user@domain.com?subject=bla&cc=otheruser@domain.com",""),Str ".",Space,Link [Str "label"] ("user@domain.com?subject=bla&cc=otheruser@domain.com.",""),Str ".",Space,Link [Str "http://www.domain.com"] ("http://www.domain.com",""),Space,Link [Str "http://www.domain.com/dir/"] ("http://www.domain.com/dir/",""),Space,Link [Str "http://www.domain.com/dir///"] ("http://www.domain.com/dir///",""),Space,Link [Str "http://www.domain.com."] ("http://www.domain.com.",""),Space,Link [Str "http://www.domain.com,"] ("http://www.domain.com,",""),Space,Link [Str "http://www.domain.com."] ("http://www.domain.com.",""),Space,Str "any",Space,Str "text.",Space,Link [Str "http://www.domain.com,"] ("http://www.domain.com,",""),Space,Str "any",Space,Str "text.",Space,Link [Str "http://www.domain.com/dir/."] ("http://www.domain.com/dir/.",""),Space,Str "any",Space,Str "text.",Space,Str "any",Space,Str "text:",Space,Link [Str "http://www.domain.com."] ("http://www.domain.com.",""),Space,Str "any",Space,Str "text.",Space,Str "any",Space,Str "text:",Space,Link [Str "http://www.domain.com/dir/."] ("http://www.domain.com/dir/.",""),Space,Str "any",Space,Str "text.",Space,Str "any",Space,Str "text:",Space,Link [Str "http://www.domain.com/dir/index.html."] ("http://www.domain.com/dir/index.html.",""),Space,Str "any",Space,Str "text.",Space,Str "any",Space,Str "text:",Space,Link [Str "http://www.domain.com/dir/index.html,"] ("http://www.domain.com/dir/index.html,",""),Space,Str "any",Space,Str "text.",Space,Link [Str "http://www.domain.com/dir/#anchor"] ("http://www.domain.com/dir/#anchor",""),Space,Link [Str "http://www.domain.com/dir/index.html#anchor"] ("http://www.domain.com/dir/index.html#anchor",""),Space,Link [Str "http://www.domain.com/dir/index.html#anchor."] ("http://www.domain.com/dir/index.html#anchor.",""),Space,Link [Str "http://www.domain.com/dir/#anchor."] ("http://www.domain.com/dir/#anchor.",""),Space,Str "any",Space,Str "text.",Space,Link [Str "http://www.domain.com/dir/index.html#anchor."] ("http://www.domain.com/dir/index.html#anchor.",""),Space,Str "any",Space,Str "text.",Space,Str "any",Space,Str "text:",Space,Link [Str "http://www.domain.com/dir/#anchor."] ("http://www.domain.com/dir/#anchor.",""),Space,Str "any",Space,Str "text.",Space,Str "any",Space,Str "text:",Space,Link [Str "http://www.domain.com/dir/index.html#anchor."] ("http://www.domain.com/dir/index.html#anchor.",""),Space,Str "any",Space,Str "text.",Space,Link [Str "http://domain.com?a=a@a.a&b=a+b+c."] ("http://domain.com?a=a@a.a&b=a+b+c.",""),Space,Link [Str "http://domain.com?a=a@a.a&b=a+b+c,"] ("http://domain.com?a=a@a.a&b=a+b+c,",""),Space,Link [Str "http://domain.com/bla.cgi?a=a@a.a&b=a+b+c."] ("http://domain.com/bla.cgi?a=a@a.a&b=a+b+c.",""),Space,Link [Str "http://domain.com/bla.cgi?a=a@a.a&b=a+b+c@."] ("http://domain.com/bla.cgi?a=a@a.a&b=a+b+c@.",""),Space,Link [Str "http://domain.com?a=a@a.a&b=a+b+c.#anchor"] ("http://domain.com?a=a@a.a&b=a+b+c.#anchor",""),Space,Link [Str "http://domain.com/bla.cgi?a=a@a.a&b=a+b+c.#anchor"] ("http://domain.com/bla.cgi?a=a@a.a&b=a+b+c.#anchor",""),Space,Link [Str "http://domain.com/bla.cgi?a=a@a.a&b=a+b+c@.#anchor"] ("http://domain.com/bla.cgi?a=a@a.a&b=a+b+c@.#anchor",""),Space,Link [Str "http://user:password@domain.com/bla.html."] ("http://user:password@domain.com/bla.html.",""),Space,Link [Str "http://user:password@domain.com/dir/."] ("http://user:password@domain.com/dir/.",""),Space,Link [Str "http://user:password@domain.com."] ("http://user:password@domain.com.",""),Space,Link [Str "http://user:@domain.com."] ("http://user:@domain.com.",""),Space,Link [Str "http://user@domain.com."] ("http://user@domain.com.",""),Space,Link [Str "http://user:password@domain.com/bla.cgi?a=a@a.a&b=a+b+c.#anchor"] ("http://user:password@domain.com/bla.cgi?a=a@a.a&b=a+b+c.#anchor",""),Space,Link [Str "http://user:password@domain.com/bla.cgi?a=a@a.a&b=a+b+c@#anchor"] ("http://user:password@domain.com/bla.cgi?a=a@a.a&b=a+b+c@#anchor",""),Space,Link [Str "label"] ("www.domain.com",""),Space,Str "[",Space,Str "label",Space,Link [Str "www.domain.com"] ("www.domain.com",""),Str "]",Space,Link [Str "label",Space] ("www.domain.com",""),Space,Link [Str "anchor",Space] ("http://www.domain.com/dir/index.html#anchor.",""),Space,Link [Str "login",Space] ("http://user:password@domain.com/bla.html",""),Space,Link [Str "form",Space] ("http://www.domain.com/bla.cgi?a=a@a.a&b=a+b+c.",""),Space,Link [Str "form",Space,Str "&",Space,Str "anchor"] ("http://www.domain.com/bla.cgi?a=a@a.a&b=a+b+c.#anchor",""),Space,Link [Str "login",Space,Str "&",Space,Str "form",Space] ("http://user:password@domain.com/bla.cgi?a=a@a.a&b=a+b+c.",""),Space,Link [Str "local",Space,Str "link",Space,Str "up",Space] ("..",""),Space,Link [Str "local",Space,Str "link",Space,Str "file",Space] ("bla.html",""),Space,Link [Str "local",Space,Str "link",Space,Str "anchor",Space] ("#anchor",""),Space,Link [Str "local",Space,Str "link",Space,Str "file/anchor"] ("bla.html#anchor",""),Space,Link [Str "local",Space,Str "link",Space,Str "file/anchor"] ("bla.html#anchor.",""),Space,Link [Str "local",Space,Str "link",Space,Str "img",Space] ("abc.gif",""),Space,Link [Str "www.fake.com"] ("www.domain.com",""),Space,Link [Str "http://domain.com:8080/~user/_st-r@a=n$g,e/index%20new.htm"] ("http://domain.com:8080/~user/_st-r@a=n$g,e/index%20new.htm",""),Space,Link [Str "http://domain.com:8080/~user/_st-r@a=n$g,e/index%20new.htm?a=/%22&b=+.@*_-"] ("http://domain.com:8080/~user/_st-r@a=n$g,e/index%20new.htm?a=/%22&b=+.@*_-",""),Space,Link [Str "http://domain.com:8080/~user/_st-r@a=n$g,e/index%20new.htm?a=/%22&b=+.@*_-#anchor_"] ("http://domain.com:8080/~user/_st-r@a=n$g,e/index%20new.htm?a=/%22&b=+.@*_-#anchor_",""),Str "-1%.",Space,Link [Str "http://foo._user-9:pass!#$%&*()+word@domain.com:8080/~user/_st-r@a=n$g,e/index%20new.htm?a=/%22&b=+.@*_-#anchor_"] ("http://foo._user-9:pass!#$%&*()+word@domain.com:8080/~user/_st-r@a=n$g,e/index%20new.htm?a=/%22&b=+.@*_-#anchor_",""),Str "-1%.",Space,Link [Str "http://L1.com"] ("http://L1.com",""),Space,Str "!",Space,Link [Str "mailto:L2@www.com"] ("L2@www.com",""),Space,Str "!",Space,Link [Str "L3"] ("www.com",""),Space,Str "!",Space,Link [Str "L4"] ("w@ww.com",""),Space,Str "!",Space,Link [Str "www.L5.com"] ("www.L5.com",""),Space,Link [Str "www.domain.com"] ("www.domain.com",""),Space,Link [Str "www2.domain.com"] ("www2.domain.com",""),Space,Link [Str "ftp.domain.com"] ("ftp.domain.com",""),Space,Link [Str "WWW.DOMAIN.COM"] ("WWW.DOMAIN.COM",""),Space,Link [Str "FTP.DOMAIN.COM"] ("FTP.DOMAIN.COM",""),Space,Link [Str "label"] ("www.domain.com",""),Space,Link [Str "label"] ("ftp.domain.com",""),Space,Link [Str "label"] ("WWW.DOMAIN.COM",""),Space,Link [Str "label"] ("FTP.DOMAIN.COM",""),Space,Str "[label",Space,Link [Str "www.domain.com"] ("www.domain.com",""),Space,Str "]",Space,Str "[label]",Space,Link [Str "www.domain.com"] ("www.domain.com",""),Str "]"] +,Header 1 ("image",[],[]) [Str "Image"] +,Para [Image [] ("img.png","")] +,Para [Link [Image [] ("img.png","")] ("http://txt2tags.org","")] +,Para [Image [] ("img.png",""),Space,Str "Image",Space,Str "at",Space,Str "the",Space,Str "line",Space,Str "beginning."] +,Para [Str "Image",Space,Str "in",Space,Str "the",Space,Str "middle",Space,Image [] ("img.png",""),Space,Str "of",Space,Str "the",Space,Str "line."] +,Para [Str "Image",Space,Str "at",Space,Str "the",Space,Str "line",Space,Str "end.",Space,Image [] ("img.png","")] +,Para [Image [] ("img.png",""),Space,Image [] ("img.png",""),Space,Image [] ("img.png","")] +,Para [Image [] ("img.png",""),Image [] ("img.png","")] +,Para [Str "Images",Space,Image [] ("img.png",""),Space,Str "mixed",Space,Image [] ("img.png",""),Space,Str "with",Space,Image [] ("img.png",""),Space,Str "text."] +,Para [Str "Images",Space,Str "glued",Space,Str "together:",Space,Image [] ("img.png",""),Image [] ("img.png",""),Image [] ("img.png",""),Str "."] +,Para [Str "[img.png",Space,Str "]"] +,Para [Str "[",Space,Str "img.png]"] +,Para [Str "[",Space,Str "img.png",Space,Str "]"] +,Header 1 ("numtitle",[],[]) [Str "Numbered",Space,Str "Title"] +,Header 1 ("",[],[]) [Str "Title",Space,Str "Level",Space,Str "1"] +,Header 2 ("",[],[]) [Str "Title",Space,Str "Level",Space,Str "2"] +,Header 3 ("",[],[]) [Str "Title",Space,Str "Level",Space,Str "3"] +,Header 4 ("",[],[]) [Str "Title",Space,Str "Level",Space,Str "4"] +,Header 5 ("",[],[]) [Str "Title",Space,Str "Level",Space,Str "5"] +,Header 1 ("lab_el-1",[],[]) [Str "Title",Space,Str "Level",Space,Str "1"] +,Header 2 ("lab_el-2",[],[]) [Str "Title",Space,Str "Level",Space,Str "2"] +,Header 3 ("lab_el-3",[],[]) [Str "Title",Space,Str "Level",Space,Str "3"] +,Header 4 ("lab_el-4",[],[]) [Str "Title",Space,Str "Level",Space,Str "4"] +,Header 5 ("lab_el-5",[],[]) [Str "Title",Space,Str "Level",Space,Str "5"] +,Header 3 ("",[],[]) [Str "Title",Space,Str "Level",Space,Str "3"] +,Header 3 ("",[],[]) [Str "Title",Space,Str "Level",Space,Str "3"] +,Header 3 ("",[],[]) [Str "Title",Space,Str "Level",Space,Str "3"] +,Header 3 ("",[],[]) [Str "Title",Space,Str "Level",Space,Str "3"] +,Header 3 ("",[],[]) [Str "Title",Space,Str "Level",Space,Str "3"] +,Header 3 ("lab_el-9",[],[]) [Str "Title",Space,Str "Level",Space,Str "3"] +,Para [Str "+Not",Space,Str "Title"] +,Para [Str "++Not",Space,Str "Title+"] +,Para [Str "+++Not",Space,Str "Title++++",Space,Str "++++++Not",Space,Str "Title",Space,Str "6++++++"] +,Para [Str "+++++++Not",Space,Str "Title",Space,Str "7+++++++",Space,Str "+Not",Space,Str "Title+",Space,Str "[label1]",Space,Str "+Not",Space,Str "Title+[",Space,Str "label",Space,Str "]",Space,Str "+Not",Space,Str "Title+[la/bel]"] +,Header 1 ("title",[],[]) [Str "Title"] +,Header 1 ("",[],[]) [Str "Title",Space,Str "Level",Space,Str "1"] +,Header 2 ("",[],[]) [Str "Title",Space,Str "Level",Space,Str "2"] +,Header 3 ("",[],[]) [Str "Title",Space,Str "Level",Space,Str "3"] +,Header 4 ("",[],[]) [Str "Title",Space,Str "Level",Space,Str "4"] +,Header 5 ("",[],[]) [Str "Title",Space,Str "Level",Space,Str "5"] +,Header 1 ("lab_el-1",[],[]) [Str "Title",Space,Str "Level",Space,Str "1"] +,Header 2 ("lab_el-2",[],[]) [Str "Title",Space,Str "Level",Space,Str "2"] +,Header 3 ("lab_el-3",[],[]) [Str "Title",Space,Str "Level",Space,Str "3"] +,Header 4 ("lab_el-4",[],[]) [Str "Title",Space,Str "Level",Space,Str "4"] +,Header 5 ("lab_el-5",[],[]) [Str "Title",Space,Str "Level",Space,Str "5"] +,Header 3 ("",[],[]) [Str "Title",Space,Str "Level",Space,Str "3"] +,Header 3 ("",[],[]) [Str "Title",Space,Str "Level",Space,Str "3"] +,Header 3 ("",[],[]) [Str "Title",Space,Str "Level",Space,Str "3"] +,Header 3 ("",[],[]) [Str "Title",Space,Str "Level",Space,Str "3"] +,Header 3 ("",[],[]) [Str "Title",Space,Str "Level",Space,Str "3"] +,Header 3 ("lab_el-9",[],[]) [Str "Title",Space,Str "Level",Space,Str "3"] +,Para [Str "=Not",Space,Str "Title"] +,Para [Str "==Not",Space,Str "Title="] +,Para [Str "===Not",Space,Str "Title====",Space,Str "======Not",Space,Str "Title",Space,Str "6======"] +,Para [Str "=======Not",Space,Str "Title",Space,Str "7=======",Space,Str "=Not",Space,Str "Title=",Space,Str "[label1]",Space,Str "=Not",Space,Str "Title=[",Space,Str "label",Space,Str "]",Space,Str "=Not",Space,Str "Title=[la/bel]"] +,Header 1 ("quote",[],[]) [Str "Quote"] +,BlockQuote + [Para [Str "To",Space,Str "quote",Space,Str "a",Space,Str "paragraph,",Space,Str "just",Space,Str "prefix",Space,Str "it",Space,Str "by",Space,Str "a",Space,Str "TAB",Space,Str "character.",Space,Str "All",Space,Str "the",Space,Str "lines",Space,Str "of",Space,Str "the",Space,Str "paragraph",Space,Str "must",Space,Str "begin",Space,Str "with",Space,Str "a",Space,Str "TAB."]] +,Para [Str "Any",Space,Str "non-tabbed",Space,Str "line",Space,Str "closes",Space,Str "the",Space,Str "quote",Space,Str "block."] +,BlockQuote + [Para [Str "The",Space,Str "number",Space,Str "of",Space,Str "leading",Space,Str "TABs",Space,Str "identifies",Space,Str "the",Space,Str "quote",Space,Str "block",Space,Str "depth.",Space,Str "This",Space,Str "is",Space,Str "quote",Space,Str "level",Space,Str "1."] + ,BlockQuote + [Para [Str "With",Space,Str "two",Space,Str "TABs,",Space,Str "we",Space,Str "are",Space,Str "on",Space,Str "the",Space,Str "quote",Space,Str "level",Space,Str "2."] + ,BlockQuote + [Para [Str "The",Space,Str "more",Space,Str "TABs,",Space,Str "more",Space,Str "deep",Space,Str "is",Space,Str "the",Space,Str "quote",Space,Str "level."] + ,BlockQuote + [Para [Str "There",Space,Str "isn't",Space,Str "a",Space,Str "limit."]]]]] +,BlockQuote + [BlockQuote + [BlockQuote + [BlockQuote + [Para [Str "This",Space,Str "quote",Space,Str "starts",Space,Str "at",Space,Str "level",Space,Str "4."]] + ,Para [Str "Then",Space,Str "its",Space,Str "depth",Space,Str "is",Space,Str "decreased."]] + ,Para [Str "Counting",Space,Str "down,",Space,Str "one",Space,Str "by",Space,Str "one."]] + ,Para [Str "Until",Space,Str "the",Space,Str "level",Space,Str "1."]] +,BlockQuote + [BlockQuote + [BlockQuote + [Para [Str "Unlike",Space,Str "lists,",Space,Str "any",Space,Str "quote",Space,Str "block",Space,Str "is",Space,Str "independent,",Space,Str "not",Space,Str "part",Space,Str "of",Space,Str "a",Space,Str "tree."]]] + ,Para [Str "The",Space,Str "TAB",Space,Str "count",Space,Str "don't",Space,Str "need",Space,Str "to",Space,Str "be",Space,Str "incremental",Space,Str "by",Space,Str "one."] + ,BlockQuote + [BlockQuote + [BlockQuote + [Para [Str "The",Space,Str "nesting",Space,Str "don't",Space,Str "need",Space,Str "to",Space,Str "follow",Space,Str "any",Space,Str "rule."]]] + ,Para [Str "Quotes",Space,Str "can",Space,Str "be",Space,Str "opened",Space,Str "and",Space,Str "closed",Space,Str "in",Space,Str "any",Space,Str "way."] + ,BlockQuote + [BlockQuote + [BlockQuote + [Para [Str "You",Space,Str "choose."]]]]]] +,BlockQuote + [Para [Str "Some",Space,Str "targets",Space,Str "(as",Space,Str "sgml)",Space,Str "don't",Space,Str "support",Space,Str "the",Space,Str "nesting",Space,Str "of",Space,Str "quotes.",Space,Str "There",Space,Str "is",Space,Str "only",Space,Str "one",Space,Str "quote",Space,Str "level."] + ,BlockQuote + [Para [Str "In",Space,Str "this",Space,Str "case,",Space,Str "no",Space,Str "matter",Space,Str "how",Space,Str "much",Space,Str "TABs",Space,Str "are",Space,Str "used",Space,Str "to",Space,Str "define",Space,Str "the",Space,Str "quote",Space,Str "block,",Space,Str "it",Space,Str "always",Space,Str "will",Space,Str "be",Space,Str "level",Space,Str "1."]]] +,BlockQuote + [Para [Str "Spaces",Space,Str "AFTER",Space,Str "the",Space,Str "TAB",Space,Str "character",Space,Str "are",Space,Str "allowed.",Space,Str "But",Space,Str "be",Space,Str "careful,",Space,Str "it",Space,Str "can",Space,Str "be",Space,Str "confusing."]] +,Para [Str "Spaces",Space,Str "BEFORE",Space,Str "the",Space,Str "TAB",Space,Str "character",Space,Str "invalidate",Space,Str "the",Space,Str "mark.",Space,Str "It's",Space,Str "not",Space,Str "quote."] +,BlockQuote + [Para [Str "Paragraph",Space,Str "breaks",Space,Str "inside",Space,Str "a",Space,Str "quote",Space,Str "aren't",Space,Str "possible."] + ,Para [Str "This",Space,Str "sample",Space,Str "are",Space,Str "two",Space,Str "separated",Space,Str "quoted",Space,Str "paragraphs,",Space,Str "not",Space,Str "a",Space,Str "quote",Space,Str "block",Space,Str "with",Space,Str "two",Space,Str "paragraphs",Space,Str "inside."]] +,BlockQuote + [Para [Str "The",Space,Str "end",Space,Str "of",Space,Str "the",Space,Str "file",Space,Str "(EOF)",Space,Str "closes",Space,Str "the",Space,Str "currently",Space,Str "open",Space,Str "quote",Space,Str "block."]] +,Header 1 ("raw",[],[]) [Str "Raw"] +,Para [Str "A raw line.\n"] +,Para [Str " Another raw line, with leading spaces.\n"] +,Para [Str "A raw area delimited\n by lines with marks.\n"] +,Para [Str "Trailing spaces and TABs after the area marks\nare allowed, but not encouraged nor documented.\n"] +,Para [Str "\"\"\"Not",Space,Str "a",Space,Str "raw",Space,Str "line,",Space,Str "need",Space,Str "one",Space,Str "space",Space,Str "after",Space,Str "mark."] +,Para [Str "\"\"\"",Space,Str "Not",Space,Str "a",Space,Str "raw",Space,Str "area.",Space,Str "The",Space,Str "marks",Space,Str "must",Space,Str "be",Space,Str "at",Space,Str "the",Space,Str "line",Space,Str "beginning,",Space,Str "no",Space,Str "leading",Space,Str "spaces.",Space,Str "\"\"\""] +,Para [Str "The end of the file (EOF) closes\nthe currently open raw area.\n"] +,Header 1 ("verbatim",[],[]) [Str "Verbatim"] +,CodeBlock ("",[],[]) "A verbatim line.\n" +,CodeBlock ("",[],[]) " Another verbatim line, with leading spaces.\n" +,CodeBlock ("",[],[]) "A verbatim area delimited\n by lines with marks.\n" +,CodeBlock ("",[],[]) "Trailing spaces and TABs after the area marks\nare allowed, but not encouraged nor documented.\n" +,Para [Str "```Not",Space,Str "a",Space,Str "verbatim",Space,Str "line,",Space,Str "need",Space,Str "one",Space,Str "space",Space,Str "after",Space,Str "mark."] +,Para [Str "```",Space,Str "Not",Space,Str "a",Space,Str "verbatim",Space,Str "area.",Space,Str "The",Space,Str "marks",Space,Str "must",Space,Str "be",Space,Str "at",Space,Str "the",Space,Str "line",Space,Str "beginning,",Space,Str "no",Space,Str "leading",Space,Str "spaces.",Space,Str "```"] +,CodeBlock ("",[],[]) "The end of the file (EOF) closes\nthe currently open verbatim area.\n" +,Header 1 ("deflist",[],[]) [Str "Definition",Space,Str "List"] +,DefinitionList + [([Str "Definition",Space,Str "list"], + [[Plain [Str "A",Space,Str "list",Space,Str "with",Space,Str "terms"]]]) + ,([Str "Start",Space,Str "term",Space,Str "with",Space,Str "colon"], + [[Plain [Str "And",Space,Str "its",Space,Str "definition",Space,Str "follows"]]])] +,Header 1 ("numlist",[],[]) [Str "Numbered",Space,Str "List"] +,Para [Str "See",Space,Link [Str "List"] ("#list",""),Str ",",Space,Str "the",Space,Str "same",Space,Str "rules",Space,Str "apply."] +,Header 1 ("list",[],[]) [Str "List"] +,BulletList + [[Plain [Str "Use",Space,Str "the",Space,Str "hyphen",Space,Str "to",Space,Str "prefix",Space,Str "list",Space,Str "items."]] + ,[Plain [Str "There",Space,Str "must",Space,Str "be",Space,Str "one",Space,Str "space",Space,Str "after",Space,Str "the",Space,Str "hyphen."]] + ,[Plain [Str "The",Space,Str "list",Space,Str "is",Space,Str "closed",Space,Str "by",Space,Str "two",Space,Str "consecutive",Space,Str "blank",Space,Str "lines."]]] +,BulletList + [[Plain [Str "The",Space,Str "list",Space,Str "can",Space,Str "be",Space,Str "indented",Space,Str "on",Space,Str "the",Space,Str "source",Space,Str "document."]] + ,[Plain [Str "You",Space,Str "can",Space,Str "use",Space,Str "any",Space,Str "number",Space,Str "of",Space,Str "spaces."]] + ,[Plain [Str "The",Space,Str "result",Space,Str "will",Space,Str "be",Space,Str "the",Space,Str "same."]]] +,BulletList + [[Para [Str "Let",Space,Str "one",Space,Str "blank",Space,Str "line",Space,Str "between",Space,Str "the",Space,Str "list",Space,Str "items."]] + ,[Para [Str "It",Space,Str "will",Space,Str "be",Space,Str "maintained",Space,Str "on",Space,Str "the",Space,Str "conversion."]] + ,[Para [Str "Some",Space,Str "targets",Space,Str "don't",Space,Str "support",Space,Str "this",Space,Str "behavior."]] + ,[Para [Str "This",Space,Str "one",Space,Str "was",Space,Str "separated",Space,Str "by",Space,Str "a",Space,Str "line",Space,Str "with",Space,Str "blanks.",Space,Str "You",Space,Str "can",Space,Str "also",Space,Str "put",Space,Str "a",Space,Str "blank",Space,Str "line",Space,Str "inside"] + ,Para [Str "the",Space,Str "item",Space,Str "contents",Space,Str "and",Space,Str "it",Space,Str "will",Space,Str "be",Space,Str "preserved."]]] +,Para [Str "-This",Space,Str "is",Space,Str "not",Space,Str "a",Space,Str "list",Space,Str "(no",Space,Str "space)"] +,Para [Str "-",Space,Str "This",Space,Str "is",Space,Str "not",Space,Str "a",Space,Str "list",Space,Str "(more",Space,Str "than",Space,Str "one",Space,Str "space)"] +,Para [Str "-",Space,Str "This",Space,Str "is",Space,Str "not",Space,Str "a",Space,Str "list",Space,Str "(a",Space,Str "TAB",Space,Str "instead",Space,Str "the",Space,Str "space)"] +,BulletList + [[BulletList + [[Plain [Str "This",Space,Str "is",Space,Str "a",Space,Str "list"]]]] + ,[OrderedList (1,DefaultStyle,DefaultDelim) + [[Plain [Str "This",Space,Str "is",Space,Str "a",Space,Str "list"]]]] + ,[DefinitionList + [([Str "This",Space,Str "is",Space,Str "a",Space,Str "list"], + [[]])]]] +,BulletList + [[Plain [Str "This",Space,Str "is",Space,Str "the",Space,Str "\"mother\"",Space,Str "list",Space,Str "first",Space,Str "item."]] + ,[Plain [Str "Here",Space,Str "is",Space,Str "the",Space,Str "second,",Space,Str "but",Space,Str "inside",Space,Str "this",Space,Str "item,"] + ,BulletList + [[Plain [Str "there",Space,Str "is",Space,Str "a",Space,Str "sublist,",Space,Str "with",Space,Str "its",Space,Str "own",Space,Str "items."]] + ,[Plain [Str "Note",Space,Str "that",Space,Str "the",Space,Str "items",Space,Str "of",Space,Str "the",Space,Str "same",Space,Str "sublist"]] + ,[Plain [Str "must",Space,Str "have",Space,Str "the",Space,Str "same",Space,Str "indentation."] + ,BulletList + [[Plain [Str "And",Space,Str "this",Space,Str "can",Space,Str "go",Space,Str "on,",Space,Str "opening",Space,Str "sublists."] + ,BulletList + [[Plain [Str "Just",Space,Str "add",Space,Str "leading",Space,Str "spaces",Space,Str "before",Space,Str "the"]] + ,[Plain [Str "hyphen",Space,Str "and",Space,Str "sublists",Space,Str "will",Space,Str "be",Space,Str "opened."]] + ,[Plain [Str "The",Space,Str "two",Space,Str "blank",Space,Str "lines",Space,Str "closes",Space,Str "them",Space,Str "all."]]]]]]]]] +,BulletList + [[Plain [Str "When",Space,Str "nesting",Space,Str "lists,",Space,Str "the",Space,Str "additional",Space,Str "spaces",Space,Str "are",Space,Str "free."]] + ,[Plain [Str "You",Space,Str "can",Space,Str "add",Space,Str "just",Space,Str "one,"] + ,BulletList + [[Plain [Str "or",Space,Str "many."] + ,BulletList + [[Plain [Str "What",Space,Str "matters",Space,Str "is",Space,Str "to",Space,Str "put",Space,Str "more",Space,Str "than",Space,Str "the",Space,Str "previous."]] + ,[Plain [Str "But",Space,Str "remember",Space,Str "that",Space,Str "the",Space,Str "other",Space,Str "items",Space,Str "of",Space,Str "the",Space,Str "same",Space,Str "list"]] + ,[Plain [Str "must",Space,Str "use",Space,Str "the",Space,Str "same",Space,Str "indentation."]]]]]]] +,BulletList + [[Plain [Str "There",Space,Str "is",Space,Str "not",Space,Str "a",Space,Str "depth",Space,Str "limit,"] + ,BulletList + [[Plain [Str "you",Space,Str "can",Space,Str "go",Space,Str "deeper",Space,Str "and",Space,Str "deeper."] + ,BulletList + [[Plain [Str "But",Space,Str "some",Space,Str "targets",Space,Str "may",Space,Str "have",Space,Str "restrictions."] + ,BulletList + [[Plain [Str "The",Space,Str "LaTeX",Space,Str "maximum",Space,Str "is",Space,Str "here,",Space,Str "4",Space,Str "levels."]]]]]]]]] +,BulletList + [[Plain [Str "Reverse",Space,Str "nesting",Space,Str "doesn't",Space,Str "work."]] + ,[Plain [Str "Because",Space,Str "a",Space,Str "sublist",Space,Str "*must*",Space,Str "have",Space,Str "a",Space,Str "mother",Space,Str "list."]] + ,[Plain [Str "It's",Space,Str "the",Space,Str "list",Space,Str "concept,",Space,Str "not",Space,Str "a",Space,Str "txt2tags",Space,Str "limitation."]] + ,[Plain [Str "All",Space,Str "this",Space,Str "sublists",Space,Str "will",Space,Str "be",Space,Str "bumped",Space,Str "to",Space,Str "mother",Space,Str "lists."]] + ,[Plain [Str "At",Space,Str "level",Space,Str "1,",Space,Str "like",Space,Str "this",Space,Str "one."]]] +,BulletList + [[Plain [Str "Level",Space,Str "1"] + ,BulletList + [[Plain [Str "Level",Space,Str "2"] + ,BulletList + [[Plain [Str "Level",Space,Str "3"] + ,BulletList + [[Plain [Str "Level",Space,Str "4"]]]] + ,[Plain [Str "Level",Space,Str "3",Space,Str "--",Space,Str "(closed",Space,Str "Level",Space,Str "4)"]]]] + ,[Plain [Str "Level",Space,Str "2",Space,Str "--",Space,Str "(closed",Space,Str "Level",Space,Str "3)"]]]] + ,[Plain [Str "Level",Space,Str "1",Space,Str "--",Space,Str "(closed",Space,Str "Level",Space,Str "2)"]]] +,BulletList + [[Plain [Str "Level",Space,Str "1"] + ,BulletList + [[Plain [Str "Level",Space,Str "2"] + ,BulletList + [[Plain [Str "Level",Space,Str "3"] + ,BulletList + [[Plain [Str "Level",Space,Str "4"]]]]]]]] + ,[Plain [Str "Level",Space,Str "1",Space,Str "--",Space,Str "(closed",Space,Str "Level",Space,Str "4,",Space,Str "Level",Space,Str "3",Space,Str "and",Space,Str "Level",Space,Str "2)"]]] +,BulletList + [[Para [Str "Level",Space,Str "1"] + ,BulletList + [[Para [Str "Level",Space,Str "2",Space,Str "--",Space,Str "blank",Space,Str "BEFORE",Space,Str "and",Space,Str "AFTER",Space,Str "(in)"] + ,BulletList + [[Plain [Str "Level",Space,Str "3"]]]]]]] +,BulletList + [[Plain [Str "Level",Space,Str "4"]]] +,BulletList + [[Para [Str "Level",Space,Str "3"]] + ,[Para [Str "Level",Space,Str "2",Space,Str "--",Space,Str "blank",Space,Str "BEFORE",Space,Str "and",Space,Str "AFTER",Space,Str "(out)"]] + ,[Para [Str "Level",Space,Str "1"] + ,BulletList + [[Para [Str "Level",Space,Str "2",Space,Str "--",Space,Str "blank",Space,Str "BEFORE",Space,Str "(spaces)",Space,Str "and",Space,Str "AFTER",Space,Str "(TAB)"] + ,BulletList + [[Plain [Str "Level",Space,Str "3"]]]]]]] +,BulletList + [[Plain [Str "Level",Space,Str "1"] + ,BulletList + [[Plain [Str "Level",Space,Str "2"] + ,BulletList + [[Plain [Str "Level",Space,Str "3"] + ,BulletList + [[Plain [Str "Level",Space,Str "4"]] + ,[Plain [Str "Level",Space,Str "3.5",Space,Str "???"]]]] + ,[Plain [Str "Level",Space,Str "3"]] + ,[Plain [Str "Level",Space,Str "2.5",Space,Str "???"]]]] + ,[Plain [Str "Level",Space,Str "2"]] + ,[Plain [Str "Level",Space,Str "1.5",Space,Str "???"]]]] + ,[Plain [Str "Level",Space,Str "1"]]] +,BulletList + [[Plain [Str "This",Space,Str "list",Space,Str "is",Space,Str "closed",Space,Str "by",Space,Str "a",Space,Str "line",Space,Str "with",Space,Str "spaces",Space,Str "and",Space,Str "other",Space,Str "with",Space,Str "TABs"]]] +,BulletList + [[Plain [Str "This",Space,Str "list",Space,Str "is",Space,Str "NOT",Space,Str "closed",Space,Str "by",Space,Str "two",Space,Str "comment",Space,Str "lines"]]] +,BulletList + [[Plain [Str "This",Space,Str "list",Space,Str "is",Space,Str "closed",Space,Str "by",Space,Str "a",Space,Str "line",Space,Str "with",Space,Str "spaces",Space,Str "and",Space,Str "TAB,"]] + ,[Plain [Str "then",Space,Str "a",Space,Str "comment",Space,Str "line,",Space,Str "then",Space,Str "an",Space,Str "empty",Space,Str "line."]]] +,BulletList + [[Plain [Str "Level",Space,Str "1"] + ,BulletList + [[Plain [Str "Level",Space,Str "2"] + ,BulletList + [[Plain [Str "Level",Space,Str "3"]]] + ,Plain [Str "-",Space,Str "Level",Space,Str "2"]]] + ,Plain [Str "-",Space,Str "Level",Space,Str "1"]]] +,Para [Str "-"] +,BulletList + [[Plain [Str "Empty",Space,Str "item",Space,Str "with",Space,Str "trailing",Space,Str "spaces."]]] +,Para [Str "-"] +,BulletList + [[Plain [Str "Empty",Space,Str "item",Space,Str "with",Space,Str "trailing",Space,Str "TAB."]]] +,Para [Str "-"] +,BulletList + [[Plain [Str "If",Space,Str "the",Space,Str "end",Space,Str "of",Space,Str "the",Space,Str "file",Space,Str "(EOF)",Space,Str "is",Space,Str "hit,"] + ,BulletList + [[Plain [Str "all",Space,Str "the",Space,Str "currently",Space,Str "opened",Space,Str "list",Space,Str "are",Space,Str "closed,"] + ,BulletList + [[Plain [Str "just",Space,Str "like",Space,Str "when",Space,Str "using",Space,Str "the",Space,Str "two",Space,Str "blank",Space,Str "lines."]]]]]]] +,Header 1 ("table",[],[]) [Str "Table"] +,Table [] [AlignRight] [0.0] + [] + [[[Plain [Str "Cell",Space,Str "1"]]]] +,Table [] [AlignCenter,AlignCenter,AlignRight] [0.0,0.0,0.0] + [] + [[[Plain [Str "Cell",Space,Str "1"]] + ,[Plain [Str "Cell",Space,Str "2"]] + ,[Plain [Str "Cell",Space,Str "3"]]]] +,Table [] [AlignCenter,AlignCenter,AlignCenter] [0.0,0.0,0.0] + [] + [[[Plain [Str "Cell",Space,Str "1"]] + ,[Plain [Str "Cell",Space,Str "2"]] + ,[Plain [Str "Cell",Space,Str "3"]]]] +,Para [Str "||",Space,Str "Cell",Space,Str "1",Space,Str "|",Space,Str "Cell",Space,Str "2",Space,Str "|",Space,Str "Cell",Space,Str "3",Space,Str "|"] +,Table [] [AlignCenter,AlignCenter,AlignCenter] [0.0,0.0,0.0] + [] + [[[Plain [Str "Cell",Space,Str "1"]] + ,[Plain [Str "Cell",Space,Str "2"]] + ,[Plain [Str "Cell",Space,Str "3"]]]] +,Table [] [AlignDefault,AlignCenter,AlignDefault] [0.0,0.0,0.0] + [[Plain [Str "Heading"]] + ,[Plain [Str "Heading"]] + ,[Plain [Str "Heading"]]] + [[[Plain [Str "<-"]] + ,[Plain [Str "--"]] + ,[Plain [Str "->"]]] + ,[[Plain [Str "--"]] + ,[Plain [Str "--"]] + ,[Plain [Str "--"]]] + ,[[Plain [Str "->"]] + ,[Plain [Str "--"]] + ,[Plain [Str "<-"]]]] +,Table [] [AlignDefault,AlignDefault,AlignCenter,AlignCenter] [0.0,0.0,0.0,0.0] + [[Plain [Str "1"]] + ,[Plain [Str "2"]] + ,[Plain [Str "3+4"]] + ,[]] + [[[Plain [Str "1"]] + ,[Plain [Str "2"]] + ,[Plain [Str "3"]] + ,[Plain [Str "4"]]] + ,[[Plain [Str "1+2+3"]] + ,[Plain [Str "4"]] + ,[] + ,[]] + ,[[Plain [Str "1"]] + ,[Plain [Str "2+3"]] + ,[Plain [Str "4"]] + ,[]] + ,[[Plain [Str "1+2+3+4"]] + ,[] + ,[] + ,[]]] +,Table [] [AlignCenter,AlignCenter,AlignCenter,AlignCenter] [0.0,0.0,0.0,0.0] + [] + [[[Plain [Str "0"]] + ,[Plain [Str "1"]] + ,[Plain [Str "2"]] + ,[]] + ,[[Plain [Str "4"]] + ,[Plain [Str "5"]] + ,[] + ,[Plain [Str "7"]]] + ,[[Plain [Str "8"]] + ,[] + ,[Plain [Str "A"]] + ,[Plain [Str "B"]]] + ,[[] + ,[Plain [Str "D"]] + ,[Plain [Str "E"]] + ,[Plain [Str "F"]]]] +,Table [] [AlignCenter,AlignCenter,AlignCenter,AlignCenter,AlignCenter] [0.0,0.0,0.0,0.0,0.0] + [] + [[[Plain [Str "1"]] + ,[] + ,[] + ,[] + ,[]] + ,[[Plain [Str "1"]] + ,[Plain [Str "2"]] + ,[] + ,[] + ,[]] + ,[[Plain [Str "1"]] + ,[Plain [Str "2"]] + ,[Plain [Str "3"]] + ,[] + ,[]] + ,[[Plain [Str "1"]] + ,[Plain [Str "2"]] + ,[Plain [Str "3"]] + ,[Plain [Str "4"]] + ,[]] + ,[[Plain [Str "1"]] + ,[Plain [Str "2"]] + ,[Plain [Str "3"]] + ,[Plain [Str "4"]] + ,[Plain [Str "5"]]]] +,Table [] [AlignDefault,AlignCenter,AlignCenter,AlignCenter,AlignCenter] [0.0,0.0,0.0,0.0,0.0] + [] + [[[Plain [Str "Jan"]] + ,[] + ,[] + ,[] + ,[]] + ,[[Plain [Str "Fev"]] + ,[] + ,[] + ,[] + ,[]] + ,[[Plain [Str "Mar"]] + ,[] + ,[] + ,[] + ,[]] + ,[[Plain [Str "Apr"]] + ,[] + ,[] + ,[] + ,[]] + ,[[Plain [Str "May"]] + ,[] + ,[] + ,[] + ,[]] + ,[[Plain [Str "20%"]] + ,[Plain [Str "40%"]] + ,[Plain [Str "60%"]] + ,[Plain [Str "80%"]] + ,[Plain [Str "100%"]]]] +,Table [] [AlignCenter,AlignDefault,AlignDefault,AlignCenter,AlignCenter] [0.0,0.0,0.0,0.0,0.0] + [] + [[[] + ,[] + ,[Plain [Str "/"]] + ,[] + ,[]] + ,[[] + ,[Plain [Str "/",Space,Str "/",Space,Str "/",Space,Str "/",Space,Str "/"]] + ,[] + ,[] + ,[]] + ,[[Plain [Str "/",Space,Str "/",Space,Str "/",Space,Str "/",Space,Str "/",Space,Str "/",Space,Str "/",Space,Str "/",Space,Str "/"]] + ,[] + ,[] + ,[] + ,[]] + ,[[] + ,[Plain [Str "o"]] + ,[] + ,[Plain [Str "o"]] + ,[]] + ,[[] + ,[] + ,[Plain [Str "."]] + ,[] + ,[]] + ,[[] + ,[Plain [Str "=",Space,Str "=",Space,Str "=",Space,Str "="]] + ,[] + ,[] + ,[]]] +,Table [] [AlignCenter,AlignCenter,AlignCenter,AlignCenter,AlignCenter,AlignCenter,AlignCenter,AlignCenter] [0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0] + [] + [[[Plain [Str "01"]] + ,[Plain [Str "02"]] + ,[] + ,[] + ,[Plain [Str "05"]] + ,[] + ,[Plain [Str "07"]] + ,[]] + ,[[] + ,[] + ,[Plain [Str "11"]] + ,[] + ,[Plain [Str "13"]] + ,[] + ,[] + ,[Plain [Str "16"]]] + ,[[Plain [Str "17"]] + ,[] + ,[Plain [Str "19"]] + ,[Plain [Str "20"]] + ,[] + ,[] + ,[Plain [Str "23"]] + ,[]] + ,[[Plain [Str "25"]] + ,[Plain [Str "26"]] + ,[] + ,[] + ,[Plain [Str "29"]] + ,[Plain [Str "30"]] + ,[] + ,[Plain [Str "32"]]] + ,[[] + ,[] + ,[Plain [Str "35"]] + ,[] + ,[Plain [Str "37"]] + ,[] + ,[Plain [Str "39"]] + ,[Plain [Str "40"]]]] +,Table [] [AlignCenter,AlignCenter,AlignCenter,AlignCenter,AlignCenter,AlignCenter,AlignCenter,AlignCenter,AlignCenter,AlignCenter,AlignCenter,AlignCenter,AlignCenter,AlignCenter,AlignCenter,AlignCenter,AlignCenter,AlignCenter,AlignCenter,AlignCenter,AlignCenter,AlignCenter,AlignCenter,AlignCenter,AlignCenter,AlignCenter,AlignCenter,AlignCenter,AlignCenter,AlignCenter,AlignCenter,AlignCenter] [0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0] + [] + [[[Plain [Str "0"]] + ,[Plain [Str "1"]] + ,[Plain [Str "2"]] + ,[Plain [Str "3"]] + ,[Plain [Str "4"]] + ,[Plain [Str "5"]] + ,[Plain [Str "6"]] + ,[Plain [Str "7"]] + ,[Plain [Str "8"]] + ,[Plain [Str "9"]] + ,[Plain [Str "A"]] + ,[Plain [Str "B"]] + ,[Plain [Str "C"]] + ,[Plain [Str "D"]] + ,[Plain [Str "E"]] + ,[Plain [Str "F"]] + ,[Plain [Str "0"]] + ,[Plain [Str "1"]] + ,[Plain [Str "2"]] + ,[Plain [Str "3"]] + ,[Plain [Str "4"]] + ,[Plain [Str "5"]] + ,[Plain [Str "6"]] + ,[Plain [Str "7"]] + ,[Plain [Str "8"]] + ,[Plain [Str "9"]] + ,[Plain [Str "A"]] + ,[Plain [Str "B"]] + ,[Plain [Str "C"]] + ,[Plain [Str "D"]] + ,[Plain [Str "E"]] + ,[Plain [Str "F"]]]] +,Table [] [AlignCenter] [0.0] + [] + [[[]] + ,[[]] + ,[[]]] +,Para [Str "|this|is|not|a|table|"] +,Para [Str "|this|",Space,Str "is|",Space,Str "not|",Space,Str "a|",Space,Str "table|"] +,Para [Str "|this",Space,Str "|is",Space,Str "|not",Space,Str "|a",Space,Str "|table",Space,Str "|"] +,Para [Str "|",Space,Str "this\t|",Space,Str "is\t|",Space,Str "not\t|",Space,Str "a\t|",Space,Str "table\t|"] +,HorizontalRule +,Para [Str "The",Space,Str "End."]] diff --git a/tests/txt2tags.t2t b/tests/txt2tags.t2t new file mode 100644 index 000000000..d374b7a85 --- /dev/null +++ b/tests/txt2tags.t2t @@ -0,0 +1,797 @@ +Txt2tags Markup Rules +author +date +%!includeconf: rules.conf + +This document describes all the details about each txt2tags mark. +The target audience are **experienced** users. You may find it +useful if you want to master the marks or solve a specific problem +about a mark. + +If you are new to txt2tags or just want to know which are the +available marks, please read the [Markup Demo MARKUPDEMO]. + +Note 1: This document is generated directly from the txt2tags +test-suite. All the rules mentioned here are 100% in sync with the +current program code. + +Note 2: A good practice is to consult [the sources rules.t2t] when +reading, to see how the texts were made. + +Table of Contents: + +%%TOC + +------------------------------------------------------------- + += Paragraph =[paragraph] + +%INCLUDED(t2t) starts here: ../../../test/marks/paragraph.t2t + + +%%% Syntax: Lines grouped together +A paragraph is composed by one or more lines. +A blank line (or a table, or a list) ends the +current paragraph. + +%%% Syntax: Leading and trailing spaces are ignored + Leading and trailing spaces are ignored. + +%%% Syntax: A comment don't close a paragraph +A comment line can be placed inside a paragraph. +% this comment will be ignored +It will not affect it. + +%%% Closing: EOF closes the open paragraph +The end of the file (EOF) closes the +currently open paragraph. + += Comment =[comment] + +%INCLUDED(t2t) starts here: ../../../test/marks/comment.t2t + + +%%% Syntax: The % character at the line beginning (column 1) +%glued with the % mark +% separated from the % mark +% very distant from the % mark +%%%%%%% lots of % marks +% a blank comment, used for vertical spacing: +% +% NOTE: what matters is the first % being at the line beginning, +% the rest of the line is just ignored. + +%%% Syntax: Area (block) +%%% +You're not seeing this. +%%% + +%%% Syntax: Area (block) with trailing spaces +%%% +You're not seeing this. +%%% + +%%% Invalid: The % in any other position + % not on the line beginning (at column 2) + +some text % half line comments are not allowed + + += Line =[line] + +%INCLUDED(t2t) starts here: ../../../test/marks/line.t2t + + +%%% Syntax: At least 20 chars of - = _ +-------------------- +==================== +____________________ +%%% Syntax: Any kind of mixing is allowed +%% Free mixing is allowed to make the line, +%% but the first char is the identifier for +%% the difference between separator ( - _ ) +%% and strong ( = ) lines. +=========----------- +-_-_-_-_-_-_-_-_-_-_ +=-=-=-=-=-=-=-=-=-=- +=------------------= +--------====-------- +%%% Syntax: Leading and/or trailing spaces are allowed + -------------------- +-------------------- + -------------------- +%%% Invalid: Less than 20 chars (but strike matches) +--------- +%%% Invalid: Strange chars (but strike matches) +--------- ---------- + +---------+---------- + +( -------------------- ) + += Inline =[inline] + +%INCLUDED(t2t) starts here: ../../../test/marks/inline.t2t + + +%%% Syntax: Marks are greedy and must be "glued" with contents +%% GLUED: The contents must be glued with the marks, no spaces +%% between them. Right after the opening mark there must be a +%% non-blank character, as well as right before the closing mark. +%% +%% GREEDY: If the contents boundary character is the same as +%% the mark character, it is considered contents, not mark. +%% So ""****bold****"" turns to ""<B>**bold**</B>"" in HTML. + +i) **b** //i// __u__ --s-- ``m`` ""r"" ''t'' +i) **bo** //it// __un__ --st-- ``mo`` ""ra"" ''tg'' +i) **bold** //ital// __undr__ --strk-- ``mono`` ""raw"" ''tggd'' +i) **bo ld** //it al// __un dr__ --st rk-- ``mo no`` ""r aw"" ''tg gd'' +i) **bo * ld** //it / al// __un _ dr__ --st - rk-- ``mo ` no`` ""r " aw"" ''tg ' gd'' +i) **bo **ld** //it //al// __un __dr__ --st --rk-- ``mo ``no`` ""r ""aw"" ''tg ''gd'' +i) **bo ** ld** //it // al// __un __ dr__ --st -- rk-- ``mo `` no`` ""r "" aw"" ''tg '' gd'' +i) ****bold**** ////ital//// ____undr____ ----strk---- ````mono```` """"raw"""" ''''tggd'''' +i) ***bold*** ///ital/// ___undr___ ---strk--- ```mono``` """raw""" '''tggd''' + +%%% Syntax: Repetition is greedy +%% When the mark character is repeated many times, +%% the contents are expanded to the largest possible. +%% Thats why they are greedy, the outer marks are +%% the ones used. + +i) ***** ///// _____ ----- ````` """"" ''''' +i) ****** ////// ______ ------ `````` """""" '''''' +i) ******* /////// _______ ------- ``````` """"""" ''''''' +i) ******** //////// ________ -------- ```````` """""""" '''''''' +i) ********* ///////// _________ --------- ````````` """"""""" ''''''''' +i) ********** ////////// __________ ---------- `````````` """""""""" '''''''''' + +%%% Invalid: No contents + +i) **** //// ____ ---- ```` """" '''' +i) ** ** // // __ __ -- -- `` `` "" "" '' '' + +%%% Invalid: Contents not "glued" with marks +%% Spaces between the marks and the contents in any side +%% invalidate the mark. + +i) ** bold** // ital// __ undr__ -- strk-- `` mono`` "" raw"" '' tggd'' +i) **bold ** //ital // __undr __ --strk -- ``mono `` ""raw "" ''tggd '' +i) ** bold ** // ital // __ undr __ -- strk -- `` mono `` "" raw "" '' tggd '' + += Link =[link] + +%INCLUDED(t2t) starts here: ../../../test/marks/link.t2t + + +%%% Syntax: E-mail +user@domain.com +user@domain.com. +user@domain.com. any text. +any text: user@domain.com. any text. +[label user@domain.com] +%%% Syntax: E-mail with form data +user@domain.com?subject=bla +user@domain.com?subject=bla. +user@domain.com?subject=bla, +user@domain.com?subject=bla&cc=otheruser@domain.com +user@domain.com?subject=bla&cc=otheruser@domain.com. +user@domain.com?subject=bla&cc=otheruser@domain.com, +[label user@domain.com?subject=bla&cc=otheruser@domain.com]. +[label user@domain.com?subject=bla&cc=otheruser@domain.com.]. +%%% Syntax: URL +http://www.domain.com +http://www.domain.com/dir/ +http://www.domain.com/dir/// +http://www.domain.com. +http://www.domain.com, +http://www.domain.com. any text. +http://www.domain.com, any text. +http://www.domain.com/dir/. any text. +any text: http://www.domain.com. any text. +any text: http://www.domain.com/dir/. any text. +any text: http://www.domain.com/dir/index.html. any text. +any text: http://www.domain.com/dir/index.html, any text. +%%% Syntax: URL with anchor +http://www.domain.com/dir/#anchor +http://www.domain.com/dir/index.html#anchor +http://www.domain.com/dir/index.html#anchor. +http://www.domain.com/dir/#anchor. any text. +http://www.domain.com/dir/index.html#anchor. any text. +any text: http://www.domain.com/dir/#anchor. any text. +any text: http://www.domain.com/dir/index.html#anchor. any text. +%%% Syntax: URL with form data +http://domain.com?a=a@a.a&b=a+b+c. +http://domain.com?a=a@a.a&b=a+b+c, +http://domain.com/bla.cgi?a=a@a.a&b=a+b+c. +http://domain.com/bla.cgi?a=a@a.a&b=a+b+c@. +%%% Syntax: URL with form data and anchor +http://domain.com?a=a@a.a&b=a+b+c.#anchor +http://domain.com/bla.cgi?a=a@a.a&b=a+b+c.#anchor +http://domain.com/bla.cgi?a=a@a.a&b=a+b+c@.#anchor +%%% Syntax: URL with login data +http://user:password@domain.com/bla.html. +http://user:password@domain.com/dir/. +http://user:password@domain.com. +http://user:@domain.com. +http://user@domain.com. +%%% Syntax: URL with login, form and anchor +http://user:password@domain.com/bla.cgi?a=a@a.a&b=a+b+c.#anchor +http://user:password@domain.com/bla.cgi?a=a@a.a&b=a+b+c@#anchor +%%% Syntax: URL with label +[label www.domain.com] +%%% Syntax: URL with label (trailing spaces are discarded, leading are maintained) +%TODO normalize this behavior +[ label www.domain.com] +[label www.domain.com] +%%% Syntax: URL with label, stressing +[anchor http://www.domain.com/dir/index.html#anchor.] +[login http://user:password@domain.com/bla.html] +[form http://www.domain.com/bla.cgi?a=a@a.a&b=a+b+c.] +[form & anchor http://www.domain.com/bla.cgi?a=a@a.a&b=a+b+c.#anchor] +[login & form http://user:password@domain.com/bla.cgi?a=a@a.a&b=a+b+c.] +%%% Syntax: Link with label for local files +[local link up ..] +[local link file bla.html] +[local link anchor #anchor] +[local link file/anchor bla.html#anchor] +[local link file/anchor bla.html#anchor.] +[local link img abc.gif] +%%% Syntax: Another link as a label +[www.fake.com www.domain.com] +%%% Syntax: URL with funny chars +http://domain.com:8080/~user/_st-r@a=n$g,e/index%20new.htm +http://domain.com:8080/~user/_st-r@a=n$g,e/index%20new.htm?a=/%22&b=+.@*_- +http://domain.com:8080/~user/_st-r@a=n$g,e/index%20new.htm?a=/%22&b=+.@*_-#anchor_-1%. +http://foo._user-9:pass!#$%&*()+word@domain.com:8080/~user/_st-r@a=n$g,e/index%20new.htm?a=/%22&b=+.@*_-#anchor_-1%. +%%% Test: Various per line +http://L1.com ! L2@www.com ! [L3 www.com] ! [L4 w@ww.com] ! www.L5.com +%%% Feature: Guessed link, adding protocol automatically +www.domain.com +www2.domain.com +ftp.domain.com +WWW.DOMAIN.COM +FTP.DOMAIN.COM +[label www.domain.com] +[label ftp.domain.com] +[label WWW.DOMAIN.COM] +[label FTP.DOMAIN.COM] +%%% Invalid: Trailing space on link +[label www.domain.com ] +%%% Invalid: Label with ] char (use postproc) +[label] www.domain.com] + += Image =[image] + +%INCLUDED(t2t) starts here: ../../../test/marks/image.t2t + + +%%% Syntax: Image name inside brackets: [img] +[img.png] + +%%% Syntax: Image pointing to a link: [[img] link] +[[img.png] http://txt2tags.org] + +%%% Align: Image position is preserved when inside paragraph +[img.png] Image at the line beginning. + +Image in the middle [img.png] of the line. + +Image at the line end. [img.png] + +%%% Align: Image alone with spaces around is aligned +[img.png] + [img.png] + [img.png] + +%%% Test: Two glued images with no spaces (left & right) +[img.png][img.png] + +%%% Test: Various per line +Images [img.png] mixed [img.png] with [img.png] text. + +Images glued together: [img.png][img.png][img.png]. + +%%% Invalid: Spaces inside are not allowed +[img.png ] + +[ img.png] + +[ img.png ] + +% Ignored as they change every time when run + += Numbered Title =[numtitle] + +%%% Syntax: Balanced equal signs (from 1 to 5) ++ Title Level 1 + +++ Title Level 2 ++ ++++ Title Level 3 +++ +++++ Title Level 4 ++++ ++++++ Title Level 5 +++++ +%%% Label: Between brackets, alphanumeric [A-Za-z0-9_-] ++ Title Level 1 +[lab_el-1] +++ Title Level 2 ++[lab_el-2] ++++ Title Level 3 +++[lab_el-3] +++++ Title Level 4 ++++[lab_el-4] ++++++ Title Level 5 +++++[lab_el-5] +%%% Syntax: Spaces around and/or inside are allowed (and ignored) + +++Title Level 3+++ + +++ Title Level 3 +++ + +++ Title Level 3 +++ ++++ Title Level 3 +++ ++++ Title Level 3 +++ + +++ Title Level 3 +++[lab_el-9] +%%% Invalid: Unbalanced equal signs + +Not Title + + ++Not Title+ + + +++Not Title++++ +%%% Invalid: Level deeper than 5 + ++++++Not Title 6++++++ + ++++++++Not Title 7+++++++ +%%% Invalid: Space between title and label ++Not Title+ [label1] +%%% Invalid: Space inside label ++Not Title+[ label ] +%%% Invalid: Strange chars inside label ++Not Title+[la/bel] + += Title =[title] + +%INCLUDED(t2t) starts here: ../../../test/marks/title.t2t + + +%%% Syntax: Balanced equal signs (from 1 to 5) += Title Level 1 = +== Title Level 2 == +=== Title Level 3 === +==== Title Level 4 ==== +===== Title Level 5 ===== +%%% Label: Between brackets, alphanumeric [A-Za-z0-9_-] += Title Level 1 =[lab_el-1] +== Title Level 2 ==[lab_el-2] +=== Title Level 3 ===[lab_el-3] +==== Title Level 4 ====[lab_el-4] +===== Title Level 5 =====[lab_el-5] +%%% Syntax: Spaces around and/or inside are allowed (and ignored) + ===Title Level 3=== + === Title Level 3 === + === Title Level 3 === +=== Title Level 3 === +=== Title Level 3 === + === Title Level 3 ===[lab_el-9] +%%% Invalid: Unbalanced equal signs + =Not Title + + ==Not Title= + + ===Not Title==== +%%% Invalid: Level deeper than 5 + ======Not Title 6====== + +=======Not Title 7======= +%%% Invalid: Space between title and label +=Not Title= [label1] +%%% Invalid: Space inside label +=Not Title=[ label ] +%%% Invalid: Strange chars inside label +=Not Title=[la/bel] + += Quote =[quote] + +%INCLUDED(t2t) starts here: ../../../test/marks/quote.t2t + + + To quote a paragraph, just prefix it by a TAB + character. All the lines of the paragraph must + begin with a TAB. +Any non-tabbed line closes the quote block. + +%%% Nesting: Creating deeper quotes + The number of leading TABs identifies the quote + block depth. This is quote level 1. + With two TABs, we are on the quote + level 2. + The more TABs, more deep is + the quote level. + There isn't a limit. + +%%% Nesting: Reverse nesting works + This quote starts at + level 4. + Then its depth is decreased. + Counting down, one by one. + Until the level 1. + +%%% Nesting: Random count + Unlike lists, any quote block is + independent, not part of a tree. + The TAB count don't need to be incremental + by one. + The nesting don't need + to follow any rule. + Quotes can be opened and closed + in any way. + You choose. + +%%% Nesting: When not supported + Some targets (as sgml) don't support the + nesting of quotes. There is only one quote + level. + In this case, no matter how much + TABs are used to define the quote + block, it always will be level 1. + +%%% Syntax: Spaces after TAB + Spaces AFTER the TAB character are allowed. + But be careful, it can be confusing. + +%%% Invalid: Spaces before TAB + Spaces BEFORE the TAB character + invalidate the mark. It's not quote. + +%%% Invalid: Paragraphs inside + Paragraph breaks inside a quote aren't + possible. + + This sample are two separated quoted + paragraphs, not a quote block with + two paragraphs inside. + +%%% Closing: EOF closes the open block + The end of the file (EOF) closes the + currently open quote block. + += Raw =[raw] + +%%% Syntax: A single line +""" A raw line. + +%%% Syntax: A single line with leading spaces +""" Another raw line, with leading spaces. + +%%% Syntax: Area (block) +""" +A raw area delimited + by lines with marks. +""" + +%%% Syntax: Area (block) with trailing spaces +""" +Trailing spaces and TABs after the area marks +are allowed, but not encouraged nor documented. +""" + +%%% Invalid: No space between mark and contents +"""Not a raw line, need one space after mark. + +%%% Invalid: Leading spaces on block marks + """ + Not a raw area. + The marks must be at the line beginning, + no leading spaces. + """ + +%%% Closing: EOF closes the open block +""" +The end of the file (EOF) closes +the currently open raw area. +""" + += Verbatim =[verbatim] + +%INCLUDED(t2t) starts here: ../../../test/marks/verbatim.t2t + + +%%% Syntax: A single line +``` A verbatim line. + +%%% Syntax: A single line with leading spaces +``` Another verbatim line, with leading spaces. + +%%% Syntax: Area (block) +``` +A verbatim area delimited + by lines with marks. +``` + +%%% Syntax: Area (block) with trailing spaces +``` +Trailing spaces and TABs after the area marks +are allowed, but not encouraged nor documented. +``` + +%%% Invalid: No space between mark and contents +```Not a verbatim line, need one space after mark. + +%%% Invalid: Leading spaces on block marks + ``` + Not a verbatim area. + The marks must be at the line beginning, + no leading spaces. + ``` + +%%% Closing: EOF closes the open block +``` +The end of the file (EOF) closes +the currently open verbatim area. +``` + += Definition List =[deflist] + +: Definition list + A list with terms +: Start term with colon + And its definition follows + + += Numbered List =[numlist] + +See [List #list], the same rules apply. + += List =[list] + +%INCLUDED(t2t) starts here: ../../../test/marks/list.t2t + + +%%% Items: Prefixed by hyphen +- Use the hyphen to prefix list items. +- There must be one space after the hyphen. +- The list is closed by two consecutive blank lines. + + +%%% Items: Free leading spacing (indentation) + - The list can be indented on the source document. + - You can use any number of spaces. + - The result will be the same. + + +%%% Items: Vertical spacing between items +- Let one blank line between the list items. + +- It will be maintained on the conversion. + +- Some targets don't support this behavior. + +- This one was separated by a line with blanks. + You can also put a blank line inside + + the item contents and it will be preserved. + + +%%% Items: Exactly ONE space after the hyphen +-This is not a list (no space) + +- This is not a list (more than one space) + +- This is not a list (a TAB instead the space) + + +%%% Items: Catchy cases +- - This is a list +- + This is a list +- : This is a list + + +%%% Nesting: Creating sublists +- This is the "mother" list first item. +- Here is the second, but inside this item, + - there is a sublist, with its own items. + - Note that the items of the same sublist + - must have the same indentation. + - And this can go on, opening sublists. + - Just add leading spaces before the + - hyphen and sublists will be opened. + - The two blank lines closes them all. + + +%%% Nesting: Free leading spacing (indentation) +- When nesting lists, the additional spaces are free. + - You can add just one, + - or many. + - What matters is to put more than the previous. + - But remember that the other items of the same list + - must use the same indentation. + + +%%% Nesting: Maximum depth +- There is not a depth limit, + - you can go deeper and deeper. + - But some targets may have restrictions. + - The LaTeX maximum is here, 4 levels. + + +%%% Nesting: Reverse doesn't work + - Reverse nesting doesn't work. + - Because a sublist *must* have a mother list. + - It's the list concept, not a txt2tags limitation. + - All this sublists will be bumped to mother lists. +- At level 1, like this one. + + +%%% Nesting: Going deeper and back + +%% When nesting back to an upper level, the previous sublist +%% is automatically closed. +- Level 1 + - Level 2 + - Level 3 + - Level 4 + - Level 3 -- (closed Level 4) + - Level 2 -- (closed Level 3) +- Level 1 -- (closed Level 2) + + +%% More than one list can be closed when nesting back. +- Level 1 + - Level 2 + - Level 3 + - Level 4 +- Level 1 -- (closed Level 4, Level 3 and Level 2) + + +%%% Nesting: Vertical spacing between lists +- Level 1 + + - Level 2 -- blank BEFORE and AFTER (in) + + - Level 3 +% comment lines are NOT considered blank lines + - Level 4 +% comment lines are NOT considered blank lines + - Level 3 + + - Level 2 -- blank BEFORE and AFTER (out) + +- Level 1 + + - Level 2 -- blank BEFORE (spaces) and AFTER (TAB) + + - Level 3 + + +%%% Nesting: Messing up +%% Be careful when going back on the nesting, +%% it must be on a valid level! If not, it will +%% be bumped up to the previous valid level. +- Level 1 + - Level 2 + - Level 3 + - Level 4 + - Level 3.5 ??? + - Level 3 + - Level 2.5 ??? + - Level 2 + - Level 1.5 ??? +- Level 1 + + +%%% Closing: Two (not so) empty lines +- This list is closed by a line with spaces and other with TABs + + +- This list is NOT closed by two comment lines +% comment lines are NOT considered blank lines +% comment lines are NOT considered blank lines +- This list is closed by a line with spaces and TAB, +- then a comment line, then an empty line. + +% comment lines are NOT considered blank lines + +%%% Closing: Empty item closes current (sub)list + +%% The two blank lines closes ALL the lists. +%% To close just the current, use an empty item. +- Level 1 + - Level 2 + - Level 3 + - + Level 2 + - + Level 1 +- + +%% The empty item can have trailing blanks. +- Empty item with trailing spaces. +- + +- Empty item with trailing TAB. +- + +%%% Closing: EOF closes the lists +- If the end of the file (EOF) is hit, + - all the currently opened list are closed, + - just like when using the two blank lines. + + += Table =[table] + +%INCLUDED(t2t) starts here: ../../../test/marks/table.t2t + +%%% Syntax: Lines starting with a pipe | +| Cell 1 + +%%% Syntax: Extra pipes separate cells +| Cell 1 | Cell 2 | Cell 3 + +%%% Syntax: With a trailing pipe, make border +| Cell 1 | Cell 2 | Cell 3 | + +%%% Syntax: Table lines starting with double pipe are heading +|| Cell 1 | Cell 2 | Cell 3 | + +%%% Align: Spaces before the leading pipe centralize the table + | Cell 1 | Cell 2 | Cell 3 | + +%%% Align: Spaces inside the cell denote its alignment + || Heading | Heading | Heading | +% comments don't close an opened table + | <- | -- | -> | + | -- | -- | -- | + | -> | -- | <- | + +%%% Span: Column span is defined by extra pipes at cell closing + || 1 | 2 | 3+4 || + | 1 | 2 | 3 | 4 | + | 1+2+3 ||| 4 | + | 1 | 2+3 || 4 | + | 1+2+3+4 |||| + +%%% Test: Empty cells are placed as expected + | 0 | 1 | 2 | | + | 4 | 5 | | 7 | + | 8 | | A | B | + | | D | E | F | + +%%% Test: Lines with different number of cells + | 1 | + | 1 | 2 | + | 1 | 2 | 3 | + | 1 | 2 | 3 | 4 | + | 1 | 2 | 3 | 4 | 5 | + +%%% Test: Empty cells + Span + Messy cell number = Fun! + | Jan | + | Fev || + | Mar ||| + | Apr |||| + | May ||||| + | 20% | 40% | 60% | 80% | 100% | + + | | | / | | | + | | / / / / / ||| | + | / / / / / / / / / ||||| + | | o | | o | | + | | | . | | | + | | = = = = ||| | + + | 01 | 02 | | | 05 | | 07 | | + | | | 11 | | 13 | | | 16 | + | 17 | | 19 | 20 | | | 23 | | + | 25 | 26 | | | 29 | 30 | | 32 | + | | | 35 | | 37 | | 39 | 40 | + +%%% Test: Lots of cells at the same line +| 0 | 1 | 2 | 3 | 4 | 5 | 6 | 7 | 8 | 9 | A | B | C | D | E | F | 0 | 1 | 2 | 3 | 4 | 5 | 6 | 7 | 8 | 9 | A | B | C | D | E | F | + +%%% Test: Empty lines +| | +| | +| | + +%%% Invalid: There must be at least one space around the pipe +|this|is|not|a|table| + +|this| is| not| a| table| + +|this |is |not |a |table | + +%%% Invalid: You must use spaces, not TABs +| this | is | not | a | table | + +------------------------------------------------------------ + +The End. diff --git a/tests/writer.asciidoc b/tests/writer.asciidoc index fbe0036d8..4b063fe68 100644 --- a/tests/writer.asciidoc +++ b/tests/writer.asciidoc @@ -378,6 +378,7 @@ foo And nested without indentation: foo + bar Interpreted markdown in a table: @@ -386,6 +387,7 @@ And this is *strong* Here’s a simple block: foo + This should be a code block, though: ------- @@ -429,11 +431,11 @@ Hr’s: Inline Markup ------------- -This is _emphasized_, and so _is this_. +This is __emphasized__, and so __is this__. -This is *strong*, and so *is this*. +This is **strong**, and so **is this**. -An _link:/url[emphasized link]_. +An __link:/url[emphasized link]__. *_This is strong and em._* @@ -445,7 +447,7 @@ So is *_this_* word. This is code: `>`, `$`, `\`, `\$`, `<html>`. -[line-through]*This is _strikeout_.* +[line-through]*This is __strikeout__.* Superscripts: a^bc^d a^_hello_^ a^hello there^. diff --git a/tests/writer.context b/tests/writer.context index 0b031fd76..244463f93 100644 --- a/tests/writer.context +++ b/tests/writer.context @@ -548,6 +548,7 @@ foo And nested without indentation: foo + bar Interpreted markdown in a table: @@ -556,6 +557,7 @@ And this is {\bf strong} Here's a simple block: foo + This should be a code block, though: \starttyping @@ -813,24 +815,22 @@ braces]\from[url26]. \subsection[autolinks]{Autolinks} -With an ampersand: -\useURL[url27][http://example.com/?foo=1&bar=2][][\hyphenatedurl{http://example.com/?foo=1&bar=2}]\from[url27] +With an ampersand: \useURL[url27][http://example.com/?foo=1&bar=2]\from[url27] \startitemize[packed] \item In a list? \item - \useURL[url28][http://example.com/][][\hyphenatedurl{http://example.com/}]\from[url28] + \useURL[url28][http://example.com/]\from[url28] \item It should. \stopitemize An e-mail address: -\useURL[url29][mailto:nobody@nowhere.net][][\hyphenatedurl{nobody@nowhere.net}]\from[url29] +\useURL[url29][mailto:nobody@nowhere.net][][nobody@nowhere.net]\from[url29] \startblockquote -Blockquoted: -\useURL[url30][http://example.com/][][\hyphenatedurl{http://example.com/}]\from[url30] +Blockquoted: \useURL[url30][http://example.com/]\from[url30] \stopblockquote Auto-links should not occur here: \type{<http://example.com/>} diff --git a/tests/writer.docbook b/tests/writer.docbook index 1d4da4842..eee19cdd9 100644 --- a/tests/writer.docbook +++ b/tests/writer.docbook @@ -4,14 +4,16 @@ <article> <articleinfo> <title>Pandoc Test Suite</title> - <author> - <firstname>John</firstname> - <surname>MacFarlane</surname> - </author> - <author> - <firstname></firstname> - <surname>Anonymous</surname> - </author> + <authorgroup> + <author> + <firstname>John</firstname> + <surname>MacFarlane</surname> + </author> + <author> + <firstname></firstname> + <surname>Anonymous</surname> + </author> + </authorgroup> <date>July 17, 2006</date> </articleinfo> <para> @@ -66,10 +68,8 @@ <para> Here’s one with a bullet. * criminey. </para> - <para> - There should be a hard line break<literallayout> -</literallayout>here. - </para> +<literallayout>There should be a hard line break +here.</literallayout> </sect1> <sect1 id="block-quotes"> <title>Block Quotes</title> @@ -93,7 +93,7 @@ sub status { <para> A list: </para> - <orderedlist numeration="arabic"> + <orderedlist numeration="arabic" spacing="compact"> <listitem> <para> item one @@ -156,7 +156,7 @@ These should not be escaped: \$ \\ \> \[ \{ <para> Asterisks tight: </para> - <itemizedlist> + <itemizedlist spacing="compact"> <listitem> <para> asterisk 1 @@ -196,7 +196,7 @@ These should not be escaped: \$ \\ \> \[ \{ <para> Pluses tight: </para> - <itemizedlist> + <itemizedlist spacing="compact"> <listitem> <para> Plus 1 @@ -236,7 +236,7 @@ These should not be escaped: \$ \\ \> \[ \{ <para> Minuses tight: </para> - <itemizedlist> + <itemizedlist spacing="compact"> <listitem> <para> Minus 1 @@ -279,7 +279,7 @@ These should not be escaped: \$ \\ \> \[ \{ <para> Tight: </para> - <orderedlist numeration="arabic"> + <orderedlist numeration="arabic" spacing="compact"> <listitem> <para> First @@ -299,7 +299,7 @@ These should not be escaped: \$ \\ \> \[ \{ <para> and: </para> - <orderedlist numeration="arabic"> + <orderedlist numeration="arabic" spacing="compact"> <listitem> <para> One @@ -383,17 +383,17 @@ These should not be escaped: \$ \\ \> \[ \{ </sect2> <sect2 id="nested"> <title>Nested</title> - <itemizedlist> + <itemizedlist spacing="compact"> <listitem> <para> Tab </para> - <itemizedlist> + <itemizedlist spacing="compact"> <listitem> <para> Tab </para> - <itemizedlist> + <itemizedlist spacing="compact"> <listitem> <para> Tab @@ -407,7 +407,7 @@ These should not be escaped: \$ \\ \> \[ \{ <para> Here’s another: </para> - <orderedlist numeration="arabic"> + <orderedlist numeration="arabic" spacing="compact"> <listitem> <para> First @@ -417,7 +417,7 @@ These should not be escaped: \$ \\ \> \[ \{ <para> Second: </para> - <itemizedlist> + <itemizedlist spacing="compact"> <listitem> <para> Fee @@ -454,7 +454,7 @@ These should not be escaped: \$ \\ \> \[ \{ <para> Second: </para> - <itemizedlist> + <itemizedlist spacing="compact"> <listitem> <para> Fee @@ -521,7 +521,7 @@ These should not be escaped: \$ \\ \> \[ \{ <para> with a continuation </para> - <orderedlist numeration="lowerroman"> + <orderedlist numeration="lowerroman" spacing="compact"> <listitem override="4"> <para> sublist with roman numerals, starting with 4 @@ -531,7 +531,7 @@ These should not be escaped: \$ \\ \> \[ \{ <para> more items </para> - <orderedlist numeration="upperalpha"> + <orderedlist numeration="upperalpha" spacing="compact"> <listitem> <para> a subsublist @@ -550,22 +550,22 @@ These should not be escaped: \$ \\ \> \[ \{ <para> Nesting: </para> - <orderedlist numeration="upperalpha"> + <orderedlist numeration="upperalpha" spacing="compact"> <listitem> <para> Upper Alpha </para> - <orderedlist numeration="upperroman"> + <orderedlist numeration="upperroman" spacing="compact"> <listitem> <para> Upper Roman. </para> - <orderedlist numeration="arabic"> + <orderedlist numeration="arabic" spacing="compact"> <listitem override="6"> <para> Decimal start with 6 </para> - <orderedlist numeration="loweralpha"> + <orderedlist numeration="loweralpha" spacing="compact"> <listitem override="3"> <para> Lower alpha with paren @@ -581,7 +581,7 @@ These should not be escaped: \$ \\ \> \[ \{ <para> Autonumbering: </para> - <orderedlist> + <orderedlist spacing="compact"> <listitem> <para> Autonumber. @@ -591,7 +591,7 @@ These should not be escaped: \$ \\ \> \[ \{ <para> More. </para> - <orderedlist> + <orderedlist spacing="compact"> <listitem> <para> Nested. @@ -616,7 +616,7 @@ These should not be escaped: \$ \\ \> \[ \{ <para> Tight using spaces: </para> - <variablelist> + <variablelist spacing="compact"> <varlistentry> <term> apple @@ -651,7 +651,7 @@ These should not be escaped: \$ \\ \> \[ \{ <para> Tight using tabs: </para> - <variablelist> + <variablelist spacing="compact"> <varlistentry> <term> apple @@ -757,7 +757,7 @@ These should not be escaped: \$ \\ \> \[ \{ <para> Multiple definitions, tight: </para> - <variablelist> + <variablelist spacing="compact"> <varlistentry> <term> apple @@ -841,7 +841,7 @@ These should not be escaped: \$ \\ \> \[ \{ <para> orange fruit </para> - <orderedlist numeration="arabic"> + <orderedlist numeration="arabic" spacing="compact"> <listitem> <para> sublist @@ -887,7 +887,6 @@ These should not be escaped: \$ \\ \> \[ \{ </td> </tr> </table> - <script type="text/javascript">document.write('This *should not* be interpreted as markdown');</script> <para> Here’s a simple block: @@ -926,7 +925,6 @@ These should not be escaped: \$ \\ \> \[ \{ Blah Blah --> - <!-- This is another comment. --> @@ -939,7 +937,7 @@ These should not be escaped: \$ \\ \> \[ \{ <para> Just plain comment, with trailing spaces on the line: </para> - <!-- foo --> + <!-- foo --> <para> Code: </para> @@ -950,21 +948,13 @@ These should not be escaped: \$ \\ \> \[ \{ Hr’s: </para> <hr> - <hr /> - <hr /> - - <hr> - - <hr /> - - <hr /> - + <hr> + <hr /> + <hr /> <hr class="foo" id="bar" /> - <hr class="foo" id="bar" /> - <hr class="foo" id="bar"> </sect1> <sect1 id="inline-markup"> @@ -1051,7 +1041,7 @@ These should not be escaped: \$ \\ \> \[ \{ </sect1> <sect1 id="latex"> <title>LaTeX</title> - <itemizedlist> + <itemizedlist spacing="compact"> <listitem> <para> </para> @@ -1097,7 +1087,7 @@ These should not be escaped: \$ \\ \> \[ \{ <para> These shouldn’t be math: </para> - <itemizedlist> + <itemizedlist spacing="compact"> <listitem> <para> To get the famous equation, write <literal>$e = mc^2$</literal>. @@ -1130,7 +1120,7 @@ These should not be escaped: \$ \\ \> \[ \{ <para> Here is some unicode: </para> - <itemizedlist> + <itemizedlist spacing="compact"> <listitem> <para> I hat: Î @@ -1316,7 +1306,7 @@ These should not be escaped: \$ \\ \> \[ \{ With an ampersand: <ulink url="http://example.com/?foo=1&bar=2">http://example.com/?foo=1&bar=2</ulink> </para> - <itemizedlist> + <itemizedlist spacing="compact"> <listitem> <para> In a list? @@ -1414,7 +1404,7 @@ or here: <http://example.com/> </footnote> </para> </blockquote> - <orderedlist numeration="arabic"> + <orderedlist numeration="arabic" spacing="compact"> <listitem> <para> And in list items.<footnote> diff --git a/tests/writer.dokuwiki b/tests/writer.dokuwiki new file mode 100644 index 000000000..dc14e9b00 --- /dev/null +++ b/tests/writer.dokuwiki @@ -0,0 +1,619 @@ +This is a set of tests for pandoc. Most of them are adapted from John Gruber’s markdown test suite. + + +---- + +====== Headers ====== + +===== Level 2 with an embedded link ===== + +==== Level 3 with emphasis ==== + +=== Level 4 === + +== Level 5 == + +====== Level 1 ====== + +===== Level 2 with emphasis ===== + +==== Level 3 ==== + +with no blank line + +===== Level 2 ===== + +with no blank line + + +---- + +====== Paragraphs ====== + +Here’s a regular paragraph. + +In Markdown 1.0.0 and earlier. Version 8. This line turns into a list item. Because a hard-wrapped line in the middle of a paragraph looked like a list item. + +Here’s one with a bullet. * criminey. + +There should be a hard line break\\ here. + + +---- + +====== Block Quotes ====== + +E-mail style: + +> This is a block quote. It is pretty short. + +<HTML><blockquote> +Code in a block quote: + +<code>sub status { + print "working"; +}</code> +A list: + + - item one + - item two + +Nested block quotes: + +> nested + +> nested +</blockquote></HTML> +This should not be a block quote: 2 > 1. + +And a following paragraph. + + +---- + +====== Code Blocks ====== + +Code: + +<code>---- (should be four hyphens) + +sub status { + print "working"; +} + +this code block is indented by one tab</code> +And: + +<code> this code block is indented by two tabs + +These should not be escaped: \$ \\ \> \[ \{</code> + +---- + +====== Lists ====== + +===== Unordered ===== + +Asterisks tight: + + * asterisk 1 + * asterisk 2 + * asterisk 3 + +Asterisks loose: + + * asterisk 1 + * asterisk 2 + * asterisk 3 + +Pluses tight: + + * Plus 1 + * Plus 2 + * Plus 3 + +Pluses loose: + + * Plus 1 + * Plus 2 + * Plus 3 + +Minuses tight: + + * Minus 1 + * Minus 2 + * Minus 3 + +Minuses loose: + + * Minus 1 + * Minus 2 + * Minus 3 + +===== Ordered ===== + +Tight: + + - First + - Second + - Third + +and: + + - One + - Two + - Three + +Loose using tabs: + + - First + - Second + - Third + +and using spaces: + + - One + - Two + - Three + +Multiple paragraphs: + +<HTML><ol style="list-style-type: decimal;"></HTML> +<HTML><li></HTML><HTML><p></HTML>Item 1, graf one.<HTML></p></HTML> +<HTML><p></HTML>Item 1. graf two. The quick brown fox jumped over the lazy dog’s back.<HTML></p></HTML><HTML></li></HTML> +<HTML><li></HTML><HTML><p></HTML>Item 2.<HTML></p></HTML><HTML></li></HTML> +<HTML><li></HTML><HTML><p></HTML>Item 3.<HTML></p></HTML><HTML></li></HTML><HTML></ol></HTML> + +===== Nested ===== + + * Tab + * Tab + * Tab + +Here’s another: + + - First + - Second: + * Fee + * Fie + * Foe + - Third + +Same thing but with paragraphs: + + - First + - Second: + * Fee + * Fie + * Foe + - Third + +===== Tabs and spaces ===== + + * this is a list item indented with tabs + * this is a list item indented with spaces + * this is an example list item indented with tabs + * this is an example list item indented with spaces + +===== Fancy list markers ===== + +<HTML><ol start="2" style="list-style-type: decimal;"></HTML> +<HTML><li></HTML>begins with 2<HTML></li></HTML> +<HTML><li></HTML><HTML><p></HTML>and now 3<HTML></p></HTML> +<HTML><p></HTML>with a continuation<HTML></p></HTML> +<HTML><ol start="4" style="list-style-type: lower-roman;"></HTML> +<HTML><li></HTML>sublist with roman numerals, starting with 4<HTML></li></HTML> +<HTML><li></HTML>more items +<HTML><ol style="list-style-type: upper-alpha;"></HTML> +<HTML><li></HTML>a subsublist<HTML></li></HTML> +<HTML><li></HTML>a subsublist<HTML></li></HTML><HTML></ol></HTML> +<HTML></li></HTML><HTML></ol></HTML> +<HTML></li></HTML><HTML></ol></HTML> + +Nesting: + +<HTML><ol style="list-style-type: upper-alpha;"></HTML> +<HTML><li></HTML>Upper Alpha +<HTML><ol style="list-style-type: upper-roman;"></HTML> +<HTML><li></HTML>Upper Roman. +<HTML><ol start="6" style="list-style-type: decimal;"></HTML> +<HTML><li></HTML>Decimal start with 6 +<HTML><ol start="3" style="list-style-type: lower-alpha;"></HTML> +<HTML><li></HTML>Lower alpha with paren<HTML></li></HTML><HTML></ol></HTML> +<HTML></li></HTML><HTML></ol></HTML> +<HTML></li></HTML><HTML></ol></HTML> +<HTML></li></HTML><HTML></ol></HTML> + +Autonumbering: + + - Autonumber. + - More. + - Nested. + +Should not be a list item: + +M.A. 2007 + +B. Williams + + +---- + +====== Definition Lists ====== + +Tight using spaces: + + * **apple** red fruit + * **orange** orange fruit + * **banana** yellow fruit + +Tight using tabs: + + * **apple** red fruit + * **orange** orange fruit + * **banana** yellow fruit + +Loose: + + * **apple** red fruit + * **orange** orange fruit + * **banana** yellow fruit + +Multiple blocks with italics: + +<HTML><dl></HTML> +<HTML><dt></HTML>//apple//<HTML></dt></HTML> +<HTML><dd></HTML><HTML><p></HTML>red fruit<HTML></p></HTML> +<HTML><p></HTML>contains seeds, crisp, pleasant to taste<HTML></p></HTML><HTML></dd></HTML> +<HTML><dt></HTML>//orange//<HTML></dt></HTML> +<HTML><dd></HTML><HTML><p></HTML>orange fruit<HTML></p></HTML> +<code>{ orange code block }</code> +> <HTML><p></HTML>orange block quote<HTML></p></HTML> +<HTML></dd></HTML><HTML></dl></HTML> + +Multiple definitions, tight: + + * **apple** red fruitcomputer + * **orange** orange fruitbank + +Multiple definitions, loose: + + * **apple** red fruitcomputer + * **orange** orange fruitbank + +Blank line after term, indented marker, alternate markers: + + * **apple** red fruitcomputer + * **orange** orange fruit + - sublist + - sublist + +====== HTML Blocks ====== + +Simple block on one line: + +foo + +And nested without indentation: + +foo + + + +bar + + +Interpreted markdown in a table: + +<HTML> +<table> +<tr> +<td> +</HTML> +This is //emphasized// +<HTML> +</td> +<td> +</HTML> +And this is **strong** +<HTML> +</td> +</tr> +</table> +<script type="text/javascript">document.write('This *should not* be interpreted as markdown');</script> +</HTML> +Here’s a simple block: + +foo + + +This should be a code block, though: + +<code><div> + foo +</div></code> +As should this: + +<code><div>foo</div></code> +Now, nested: + +foo + + + +This should just be an HTML comment: + +<HTML> +<!-- Comment --> +</HTML> +Multiline: + +<HTML> +<!-- +Blah +Blah +--> +<!-- + This is another comment. +--> +</HTML> +Code block: + +<code><!-- Comment --></code> +Just plain comment, with trailing spaces on the line: + +<HTML> +<!-- foo --> +</HTML> +Code: + +<code><hr /></code> +Hr’s: + +<HTML> +<hr> +<hr /> +<hr /> +<hr> +<hr /> +<hr /> +<hr class="foo" id="bar" /> +<hr class="foo" id="bar" /> +<hr class="foo" id="bar"> +</HTML> + +---- + +====== Inline Markup ====== + +This is //emphasized//, and so //is this//. + +This is **strong**, and so **is this**. + +An //[[url|emphasized link]]//. + +**//This is strong and em.//** + +So is **//this//** word. + +**//This is strong and em.//** + +So is **//this//** word. + +This is code: ''%%>%%'', ''%%$%%'', ''%%\%%'', ''%%\$%%'', ''%%<html>%%''. + +<del>This is //strikeout//.</del> + +Superscripts: a<sup>bc</sup>d a<sup>//hello//</sup> a<sup>hello there</sup>. + +Subscripts: H<sub>2</sub>O, H<sub>23</sub>O, H<sub>many of them</sub>O. + +These should not be superscripts or subscripts, because of the unescaped spaces: a^b c^d, a~b c~d. + + +---- + +====== Smart quotes, ellipses, dashes ====== + +“Hello,” said the spider. “‘Shelob’ is my name.” + +‘A’, ‘B’, and ‘C’ are letters. + +‘Oak,’ ‘elm,’ and ‘beech’ are names of trees. So is ‘pine.’ + +‘He said, “I want to go.”’ Were you alive in the 70’s? + +Here is some quoted ‘''%%code%%''’ and a “[[http://example.com/?foo=1&bar=2|quoted link]]”. + +Some dashes: one—two — three—four — five. + +Dashes between numbers: 5–7, 255–66, 1987–1999. + +Ellipses…and…and…. + + +---- + +====== LaTeX ====== + + * + * <math>2+2=4</math> + * <math>x \in y</math> + * <math>\alpha \wedge \omega</math> + * <math>223</math> + * <math>p</math>-Tree + * Here’s some display math: <math>\frac{d}{dx}f(x)=\lim_{h\to 0}\frac{f(x+h)-f(x)}{h}</math> + * Here’s one that has a line break in it: <math>\alpha + \omega \times x^2</math>. + +These shouldn’t be math: + + * To get the famous equation, write ''%%$e = mc^2$%%''. + * $22,000 is a //lot// of money. So is $34,000. (It worked if “lot” is emphasized.) + * Shoes ($20) and socks ($5). + * Escaped ''%%$%%'': $73 //this should be emphasized// 23$. + +Here’s a LaTeX table: + + + +---- + +====== Special Characters ====== + +Here is some unicode: + + * I hat: Î + * o umlaut: ö + * section: § + * set membership: ∈ + * copyright: © + +AT&T has an ampersand in their name. + +AT&T is another way to write it. + +This & that. + +4 < 5. + +6 > 5. + +Backslash: \ + +Backtick: ` + +Asterisk: * + +Underscore: _ + +Left brace: { + +Right brace: } + +Left bracket: [ + +Right bracket: ] + +Left paren: ( + +Right paren: ) + +Greater-than: > + +Hash: # + +Period: . + +Bang: ! + +Plus: + + +Minus: - + + +---- + +====== Links ====== + +===== Explicit ===== + +Just a [[url/|URL]]. + +[[url/|URL and title]]. + +[[url/|URL and title]]. + +[[url/|URL and title]]. + +[[url/|URL and title]] + +[[url/|URL and title]] + +[[url/with_underscore|with_underscore]] + +[[mailto:nobody@nowhere.net|Email link]] + +[[|Empty]]. + +===== Reference ===== + +Foo [[url/|bar]]. + +Foo [[url/|bar]]. + +Foo [[url/|bar]]. + +With [[url/|embedded [brackets]]]. + +[[url/|b]] by itself should be a link. + +Indented [[url|once]]. + +Indented [[url|twice]]. + +Indented [[url|thrice]]. + +This should [not][] be a link. + +<code>[not]: /url</code> +Foo [[url/|bar]]. + +Foo [[url/|biz]]. + +===== With ampersands ===== + +Here’s a [[http://example.com/?foo=1&bar=2|link with an ampersand in the URL]]. + +Here’s a link with an amersand in the link text: [[http://att.com/|AT&T]]. + +Here’s an [[script?foo=1&bar=2|inline link]]. + +Here’s an [[script?foo=1&bar=2|inline link in pointy braces]]. + +===== Autolinks ===== + +With an ampersand: http://example.com/?foo=1&bar=2 + + * In a list? + * http://example.com/ + * It should. + +An e-mail address: <nobody@nowhere.net> + +> Blockquoted: http://example.com/ + +Auto-links should not occur here: ''%%<http://example.com/>%%'' + +<code>or here: <http://example.com/></code> + +---- + +====== Images ====== + +From “Voyage dans la Lune” by Georges Melies (1902): + +{{:lalune.jpg|Voyage dans la Lune lalune}} + +Here is a movie {{:movie.jpg|movie}} icon. + + +---- + +====== Footnotes ====== + +Here is a footnote reference,((Here is the footnote. It can go anywhere after the footnote reference. It need not be placed at the end of the document. +)) and another.((Here’s the long note. This one contains multiple blocks. + +Subsequent blocks are indented to show that they belong to the footnote (as with list items). + +<code> { <code> }</code> +If you want, you can indent every line, but you can also be lazy and just indent the first line of each block. +)) This should //not// be a footnote reference, because it contains a space.[^my note] Here is an inline note.((This is //easier// to type. Inline notes may contain [[http://google.com|links]] and ''%%]%%'' verbatim characters, as well as [bracketed text]. +)) + +> Notes can go in quotes.((In quote. +> )) + + - And in list items.((In list.)) + +This paragraph should not be part of the note, as it is not indented. diff --git a/tests/writer.fb2 b/tests/writer.fb2 index 8106d2b91..ce00cbef3 100644 --- a/tests/writer.fb2 +++ b/tests/writer.fb2 @@ -1,2 +1,2 @@ <?xml version="1.0" encoding="UTF-8"?> -<FictionBook xmlns="http://www.gribuser.ru/xml/fictionbook/2.0" xmlns:l="http://www.w3.org/1999/xlink"><description><title-info><book-title>Pandoc Test Suite</book-title><author><first-name>John</first-name><last-name>MacFarlane</last-name></author><author><nickname>Anonymous</nickname></author><date>July 17, 2006</date></title-info><document-info><program-used>pandoc</program-used></document-info></description><body><title><p>Pandoc Test Suite</p></title><annotation><p>John MacFarlane</p><p>Anonymous</p><p>July 17, 2006</p></annotation><section><p>This is a set of tests for pandoc. Most of them are adapted from John Gruber’s markdown test suite.</p><empty-line /><p>——————————</p><empty-line /></section><section><title><p>Headers</p></title><section><title><p>Level 2 with an embedded link </url></p></title><section><title><p>Level 3 with emphasis</p></title><section><title><p>Level 4</p></title><section><title><p>Level 5</p></title></section></section></section></section></section><section><title><p>Level 1</p></title><section><title><p>Level 2 with emphasis</p></title><section><title><p>Level 3</p></title><p>with no blank line</p></section></section><section><title><p>Level 2</p></title><p>with no blank line</p><empty-line /><p>——————————</p><empty-line /></section></section><section><title><p>Paragraphs</p></title><p>Here’s a regular paragraph.</p><p>In Markdown 1.0.0 and earlier. Version 8. This line turns into a list item. Because a hard-wrapped line in the middle of a paragraph looked like a list item.</p><p>Here’s one with a bullet. * criminey.</p><p>There should be a hard line break<empty-line />here.</p><empty-line /><p>——————————</p><empty-line /></section><section><title><p>Block Quotes</p></title><p>E-mail style:</p><cite><p>This is a block quote. It is pretty short.</p></cite><cite><p>Code in a block quote:</p><empty-line /><p><code>sub status {</code></p><p><code> print "working";</code></p><p><code>}</code></p><empty-line /><p>A list:</p><p> 1. item one</p><p> 2. item two</p><p>Nested block quotes:</p><cite><p>nested</p></cite><cite><p>nested</p></cite></cite><p>This should not be a block quote: 2 > 1.</p><p>And a following paragraph.</p><empty-line /><p>——————————</p><empty-line /></section><section><title><p>Code Blocks</p></title><p>Code:</p><empty-line /><p><code>---- (should be four hyphens)</code></p><p><code></code></p><p><code>sub status {</code></p><p><code> print "working";</code></p><p><code>}</code></p><p><code></code></p><p><code>this code block is indented by one tab</code></p><empty-line /><p>And:</p><empty-line /><p><code> this code block is indented by two tabs</code></p><p><code></code></p><p><code>These should not be escaped: \$ \\ \> \[ \{</code></p><empty-line /><empty-line /><p>——————————</p><empty-line /></section><section><title><p>Lists</p></title><section><title><p>Unordered</p></title><p>Asterisks tight:</p><p>• asterisk 1</p><p>• asterisk 2</p><p>• asterisk 3</p><p>Asterisks loose:</p><p>• asterisk 1<empty-line /></p><p>• asterisk 2<empty-line /></p><p>• asterisk 3<empty-line /></p><p>Pluses tight:</p><p>• Plus 1</p><p>• Plus 2</p><p>• Plus 3</p><p>Pluses loose:</p><p>• Plus 1<empty-line /></p><p>• Plus 2<empty-line /></p><p>• Plus 3<empty-line /></p><p>Minuses tight:</p><p>• Minus 1</p><p>• Minus 2</p><p>• Minus 3</p><p>Minuses loose:</p><p>• Minus 1<empty-line /></p><p>• Minus 2<empty-line /></p><p>• Minus 3<empty-line /></p></section><section><title><p>Ordered</p></title><p>Tight:</p><p> 1. First</p><p> 2. Second</p><p> 3. Third</p><p>and:</p><p> 1. One</p><p> 2. Two</p><p> 3. Three</p><p>Loose using tabs:</p><p> 1. First<empty-line /></p><p> 2. Second<empty-line /></p><p> 3. Third<empty-line /></p><p>and using spaces:</p><p> 1. One<empty-line /></p><p> 2. Two<empty-line /></p><p> 3. Three<empty-line /></p><p>Multiple paragraphs:</p><p> 1. Item 1, graf one.<empty-line />Item 1. graf two. The quick brown fox jumped over the lazy dog’s back.<empty-line /></p><p> 2. Item 2.<empty-line /></p><p> 3. Item 3.<empty-line /></p></section><section><title><p>Nested</p></title><p>• Tab<p>◦ Tab<p>* Tab</p></p></p><p>Here’s another:</p><p> 1. First</p><p> 2. Second:<p> • Fee</p><p> • Fie</p><p> • Foe</p></p><p> 3. Third</p><p>Same thing but with paragraphs:</p><p> 1. First<empty-line /></p><p> 2. Second:<empty-line /><p> • Fee</p><p> • Fie</p><p> • Foe</p></p><p> 3. Third<empty-line /></p></section><section><title><p>Tabs and spaces</p></title><p>• this is a list item indented with tabs<empty-line /></p><p>• this is a list item indented with spaces<empty-line /><p>◦ this is an example list item indented with tabs<empty-line /></p><p>◦ this is an example list item indented with spaces<empty-line /></p></p></section><section><title><p>Fancy list markers</p></title><p> (2) begins with 2</p><p> (3) and now 3<empty-line />with a continuation<empty-line /><p> (3) iv. sublist with roman numerals, starting with 4</p><p> (3) v. more items<p> (3) v. (A) a subsublist</p><p> (3) v. (B) a subsublist</p></p></p><p>Nesting:</p><p> A. Upper Alpha<p> A. I. Upper Roman.<p> A. I. (6) Decimal start with 6<p> A. I. (6) c) Lower alpha with paren</p></p></p></p><p>Autonumbering:</p><p> 1. Autonumber.</p><p> 2. More.<p> 2. 1. Nested.</p></p><p>Should not be a list item:</p><p>M.A. 2007</p><p>B. Williams</p><empty-line /><p>——————————</p><empty-line /></section></section><section><title><p>Definition Lists</p></title><p>Tight using spaces:</p><p><strong>apple</strong></p><p> red fruit<empty-line /></p><p><strong>orange</strong></p><p> orange fruit<empty-line /></p><p><strong>banana</strong></p><p> yellow fruit<empty-line /></p><p>Tight using tabs:</p><p><strong>apple</strong></p><p> red fruit<empty-line /></p><p><strong>orange</strong></p><p> orange fruit<empty-line /></p><p><strong>banana</strong></p><p> yellow fruit<empty-line /></p><p>Loose:</p><p><strong>apple</strong></p><p> red fruit<empty-line /></p><p><strong>orange</strong></p><p> orange fruit<empty-line /></p><p><strong>banana</strong></p><p> yellow fruit<empty-line /></p><p>Multiple blocks with italics:</p><p><strong><emphasis>apple</emphasis></strong></p><p> red fruit<empty-line /> contains seeds, crisp, pleasant to taste<empty-line /></p><p><strong><emphasis>orange</emphasis></strong></p><p> orange fruit<empty-line /><empty-line /><p><code> { orange code block }</code></p><empty-line /><cite><p> orange block quote</p></cite></p><p>Multiple definitions, tight:</p><p><strong>apple</strong></p><p> red fruit<empty-line /> computer<empty-line /></p><p><strong>orange</strong></p><p> orange fruit<empty-line /> bank<empty-line /></p><p>Multiple definitions, loose:</p><p><strong>apple</strong></p><p> red fruit<empty-line /> computer<empty-line /></p><p><strong>orange</strong></p><p> orange fruit<empty-line /> bank<empty-line /></p><p>Blank line after term, indented marker, alternate markers:</p><p><strong>apple</strong></p><p> red fruit<empty-line /> computer<empty-line /></p><p><strong>orange</strong></p><p> orange fruit<empty-line /><p> 1. sublist</p><p> 2. sublist</p></p></section><section><title><p>HTML Blocks</p></title><p>Simple block on one line:</p>foo<p>And nested without indentation:</p>foobar<p>Interpreted markdown in a table:</p><empty-line /><p><code><table></code></p><p><code><tr></code></p><p><code><td></code></p><empty-line />This is <emphasis>emphasized</emphasis><empty-line /><p><code></td></code></p><p><code><td></code></p><empty-line />And this is <strong>strong</strong><empty-line /><p><code></td></code></p><p><code></tr></code></p><p><code></table></code></p><p><code></code></p><p><code><script type="text/javascript">document.write('This *should not* be interpreted as markdown');</script></code></p><empty-line /><p>Here’s a simple block:</p>foo<p>This should be a code block, though:</p><empty-line /><p><code><div></code></p><p><code> foo</code></p><p><code></div></code></p><empty-line /><p>As should this:</p><empty-line /><p><code><div>foo</div></code></p><empty-line /><p>Now, nested:</p>foo<p>This should just be an HTML comment:</p><empty-line /><p><code><!-- Comment --></code></p><empty-line /><p>Multiline:</p><empty-line /><p><code><!--</code></p><p><code>Blah</code></p><p><code>Blah</code></p><p><code>--></code></p><p><code></code></p><p><code><!--</code></p><p><code> This is another comment.</code></p><p><code>--></code></p><empty-line /><p>Code block:</p><empty-line /><p><code><!-- Comment --></code></p><empty-line /><p>Just plain comment, with trailing spaces on the line:</p><empty-line /><p><code><!-- foo --> </code></p><empty-line /><p>Code:</p><empty-line /><p><code><hr /></code></p><empty-line /><p>Hr’s:</p><empty-line /><p><code><hr></code></p><p><code></code></p><p><code><hr /></code></p><p><code></code></p><p><code><hr /></code></p><p><code></code></p><p><code><hr> </code></p><p><code></code></p><p><code><hr /> </code></p><p><code></code></p><p><code><hr /> </code></p><p><code></code></p><p><code><hr class="foo" id="bar" /></code></p><p><code></code></p><p><code><hr class="foo" id="bar" /></code></p><p><code></code></p><p><code><hr class="foo" id="bar"></code></p><empty-line /><empty-line /><p>——————————</p><empty-line /></section><section><title><p>Inline Markup</p></title><p>This is <emphasis>emphasized</emphasis>, and so <emphasis>is this</emphasis>.</p><p>This is <strong>strong</strong>, and so <strong>is this</strong>.</p><p>An <emphasis>emphasized link<a l:href="#l1" type="note"><sup>[1]</sup></a></emphasis>.</p><p><strong><emphasis>This is strong and em.</emphasis></strong></p><p>So is <strong><emphasis>this</emphasis></strong> word.</p><p><strong><emphasis>This is strong and em.</emphasis></strong></p><p>So is <strong><emphasis>this</emphasis></strong> word.</p><p>This is code: <code>></code>, <code>$</code>, <code>\</code>, <code>\$</code>, <code><html></code>.</p><p><strikethrough>This is <emphasis>strikeout</emphasis>.</strikethrough></p><p>Superscripts: a<sup>bc</sup>d a<sup><emphasis>hello</emphasis></sup> a<sup>hello there</sup>.</p><p>Subscripts: H<sub>2</sub>O, H<sub>23</sub>O, H<sub>many of them</sub>O.</p><p>These should not be superscripts or subscripts, because of the unescaped spaces: a^b c^d, a~b c~d.</p><empty-line /><p>——————————</p><empty-line /></section><section><title><p>Smart quotes, ellipses, dashes</p></title><p>“Hello,” said the spider. “‘Shelob’ is my name.”</p><p>‘A’, ‘B’, and ‘C’ are letters.</p><p>‘Oak,’ ‘elm,’ and ‘beech’ are names of trees. So is ‘pine.’</p><p>‘He said, “I want to go.”’ Were you alive in the 70’s?</p><p>Here is some quoted ‘<code>code</code>’ and a “quoted link<a l:href="#l2" type="note"><sup>[2]</sup></a>”.</p><p>Some dashes: one—two — three—four — five.</p><p>Dashes between numbers: 5–7, 255–66, 1987–1999.</p><p>Ellipses…and…and….</p><empty-line /><p>——————————</p><empty-line /></section><section><title><p>LaTeX</p></title><p>• </p><p>• <code>2+2=4</code></p><p>• <code>x \in y</code></p><p>• <code>\alpha \wedge \omega</code></p><p>• <code>223</code></p><p>• <code>p</code>-Tree</p><p>• Here’s some display math: <code>\frac{d}{dx}f(x)=\lim_{h\to 0}\frac{f(x+h)-f(x)}{h}</code></p><p>• Here’s one that has a line break in it: <code>\alpha + \omega \times x^2</code>.</p><p>These shouldn’t be math:</p><p>• To get the famous equation, write <code>$e = mc^2$</code>.</p><p>• $22,000 is a <emphasis>lot</emphasis> of money. So is $34,000. (It worked if “lot” is emphasized.)</p><p>• Shoes ($20) and socks ($5).</p><p>• Escaped <code>$</code>: $73 <emphasis>this should be emphasized</emphasis> 23$.</p><p>Here’s a LaTeX table:</p><empty-line /><p><code>\begin{tabular}{|l|l|}\hline</code></p><p><code>Animal & Number \\ \hline</code></p><p><code>Dog & 2 \\</code></p><p><code>Cat & 1 \\ \hline</code></p><p><code>\end{tabular}</code></p><empty-line /><empty-line /><p>——————————</p><empty-line /></section><section><title><p>Special Characters</p></title><p>Here is some unicode:</p><p>• I hat: Î</p><p>• o umlaut: ö</p><p>• section: §</p><p>• set membership: ∈</p><p>• copyright: ©</p><p>AT&T has an ampersand in their name.</p><p>AT&T is another way to write it.</p><p>This & that.</p><p>4 < 5.</p><p>6 > 5.</p><p>Backslash: \</p><p>Backtick: `</p><p>Asterisk: *</p><p>Underscore: _</p><p>Left brace: {</p><p>Right brace: }</p><p>Left bracket: [</p><p>Right bracket: ]</p><p>Left paren: (</p><p>Right paren: )</p><p>Greater-than: ></p><p>Hash: #</p><p>Period: .</p><p>Bang: !</p><p>Plus: +</p><p>Minus: -</p><empty-line /><p>——————————</p><empty-line /></section><section><title><p>Links</p></title><section><title><p>Explicit</p></title><p>Just a URL<a l:href="#l3" type="note"><sup>[3]</sup></a>.</p><p>URL and title<a l:href="#l4" type="note"><sup>[4]</sup></a>.</p><p>URL and title<a l:href="#l5" type="note"><sup>[5]</sup></a>.</p><p>URL and title<a l:href="#l6" type="note"><sup>[6]</sup></a>.</p><p>URL and title<a l:href="#l7" type="note"><sup>[7]</sup></a></p><p>URL and title<a l:href="#l8" type="note"><sup>[8]</sup></a></p><p>with_underscore<a l:href="#l9" type="note"><sup>[9]</sup></a></p><p>Email link<a l:href="#l10" type="note"><sup>[10]</sup></a></p><p>Empty<a l:href="#l11" type="note"><sup>[11]</sup></a>.</p></section><section><title><p>Reference</p></title><p>Foo bar<a l:href="#l12" type="note"><sup>[12]</sup></a>.</p><p>Foo bar<a l:href="#l13" type="note"><sup>[13]</sup></a>.</p><p>Foo bar<a l:href="#l14" type="note"><sup>[14]</sup></a>.</p><p>With embedded [brackets]<a l:href="#l15" type="note"><sup>[15]</sup></a>.</p><p>b<a l:href="#l16" type="note"><sup>[16]</sup></a> by itself should be a link.</p><p>Indented once<a l:href="#l17" type="note"><sup>[17]</sup></a>.</p><p>Indented twice<a l:href="#l18" type="note"><sup>[18]</sup></a>.</p><p>Indented thrice<a l:href="#l19" type="note"><sup>[19]</sup></a>.</p><p>This should [not][] be a link.</p><empty-line /><p><code>[not]: /url</code></p><empty-line /><p>Foo bar<a l:href="#l20" type="note"><sup>[20]</sup></a>.</p><p>Foo biz<a l:href="#l21" type="note"><sup>[21]</sup></a>.</p></section><section><title><p>With ampersands</p></title><p>Here’s a link with an ampersand in the URL<a l:href="#l22" type="note"><sup>[22]</sup></a>.</p><p>Here’s a link with an amersand in the link text: AT&T<a l:href="#l23" type="note"><sup>[23]</sup></a>.</p><p>Here’s an inline link<a l:href="#l24" type="note"><sup>[24]</sup></a>.</p><p>Here’s an inline link in pointy braces<a l:href="#l25" type="note"><sup>[25]</sup></a>.</p></section><section><title><p>Autolinks</p></title><p>With an ampersand: http://example.com/?foo=1&bar=2<a l:href="#l26" type="note"><sup>[26]</sup></a></p><p>• In a list?</p><p>• http://example.com/<a l:href="#l27" type="note"><sup>[27]</sup></a></p><p>• It should.</p><p>An e-mail address: nobody@nowhere.net<a l:href="#l28" type="note"><sup>[28]</sup></a></p><cite><p>Blockquoted: http://example.com/<a l:href="#l29" type="note"><sup>[29]</sup></a></p></cite><p>Auto-links should not occur here: <code><http://example.com/></code></p><empty-line /><p><code>or here: <http://example.com/></code></p><empty-line /><empty-line /><p>——————————</p><empty-line /></section></section><section><title><p>Images</p></title><p>From “Voyage dans la Lune” by Georges Melies (1902):</p><image l:href="#image1" l:type="imageType" alt="lalune" title="Voyage dans la Lune" /><p>Here is a movie <image l:href="#image2" l:type="inlineImageType" alt="movie" /> icon.</p><empty-line /><p>——————————</p><empty-line /></section><section><title><p>Footnotes</p></title><p>Here is a footnote reference,<a l:href="#n30" type="note"><sup>[30]</sup></a> and another.<a l:href="#n31" type="note"><sup>[31]</sup></a> This should <emphasis>not</emphasis> be a footnote reference, because it contains a space.[^my note] Here is an inline note.<a l:href="#n32" type="note"><sup>[32]</sup></a></p><cite><p>Notes can go in quotes.<a l:href="#n33" type="note"><sup>[33]</sup></a></p></cite><p> 1. And in list items.<a l:href="#n34" type="note"><sup>[34]</sup></a></p><p>This paragraph should not be part of the note, as it is not indented.</p></section></body><body name="notes"><section id="l1"><title><p>1</p></title><p><code>/url</code></p></section><section id="l2"><title><p>2</p></title><p><code>http://example.com/?foo=1&bar=2</code></p></section><section id="l3"><title><p>3</p></title><p><code>/url/</code></p></section><section id="l4"><title><p>4</p></title><p>title: <code>/url/</code></p></section><section id="l5"><title><p>5</p></title><p>title preceded by two spaces: <code>/url/</code></p></section><section id="l6"><title><p>6</p></title><p>title preceded by a tab: <code>/url/</code></p></section><section id="l7"><title><p>7</p></title><p>title with "quotes" in it: <code>/url/</code></p></section><section id="l8"><title><p>8</p></title><p>title with single quotes: <code>/url/</code></p></section><section id="l9"><title><p>9</p></title><p><code>/url/with_underscore</code></p></section><section id="l10"><title><p>10</p></title><p><code>mailto:nobody@nowhere.net</code></p></section><section id="l11"><title><p>11</p></title><p><code></code></p></section><section id="l12"><title><p>12</p></title><p><code>/url/</code></p></section><section id="l13"><title><p>13</p></title><p><code>/url/</code></p></section><section id="l14"><title><p>14</p></title><p><code>/url/</code></p></section><section id="l15"><title><p>15</p></title><p><code>/url/</code></p></section><section id="l16"><title><p>16</p></title><p><code>/url/</code></p></section><section id="l17"><title><p>17</p></title><p><code>/url</code></p></section><section id="l18"><title><p>18</p></title><p><code>/url</code></p></section><section id="l19"><title><p>19</p></title><p><code>/url</code></p></section><section id="l20"><title><p>20</p></title><p>Title with "quotes" inside: <code>/url/</code></p></section><section id="l21"><title><p>21</p></title><p>Title with "quote" inside: <code>/url/</code></p></section><section id="l22"><title><p>22</p></title><p><code>http://example.com/?foo=1&bar=2</code></p></section><section id="l23"><title><p>23</p></title><p>AT&T: <code>http://att.com/</code></p></section><section id="l24"><title><p>24</p></title><p><code>/script?foo=1&bar=2</code></p></section><section id="l25"><title><p>25</p></title><p><code>/script?foo=1&bar=2</code></p></section><section id="l26"><title><p>26</p></title><p><code>http://example.com/?foo=1&bar=2</code></p></section><section id="l27"><title><p>27</p></title><p><code>http://example.com/</code></p></section><section id="l28"><title><p>28</p></title><p><code>mailto:nobody@nowhere.net</code></p></section><section id="l29"><title><p>29</p></title><p><code>http://example.com/</code></p></section><section id="n30"><title><p>30</p></title><p>Here is the footnote. It can go anywhere after the footnote reference. It need not be placed at the end of the document.</p></section><section id="n31"><title><p>31</p></title><p>Here’s the long note. This one contains multiple blocks.</p><p>Subsequent blocks are indented to show that they belong to the footnote (as with list items).</p><empty-line /><p><code> { <code> }</code></p><empty-line /><p>If you want, you can indent every line, but you can also be lazy and just indent the first line of each block.</p></section><section id="n32"><title><p>32</p></title><p>This is <emphasis>easier</emphasis> to type. Inline notes may contain links<a l:href="#l32" type="note"><sup>[32]</sup></a> and <code>]</code> verbatim characters, as well as [bracketed text].</p></section><section id="n33"><title><p>33</p></title><p>In quote.</p></section><section id="n34"><title><p>34</p></title><p>In list.</p></section></body><binary id="image2" content-type="image/jpeg">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</binary><binary id="image1" content-type="image/jpeg">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</binary></FictionBook>
\ No newline at end of file +<FictionBook xmlns="http://www.gribuser.ru/xml/fictionbook/2.0" xmlns:l="http://www.w3.org/1999/xlink"><description><title-info><book-title>Pandoc Test Suite</book-title><author><first-name>John</first-name><last-name>MacFarlane</last-name></author><author><nickname>Anonymous</nickname></author><date>July 17, 2006</date></title-info><document-info><program-used>pandoc</program-used></document-info></description><body><title><p>Pandoc Test Suite</p></title><annotation><p>John MacFarlane</p><p>Anonymous</p><p>July 17, 2006</p></annotation><section><p>This is a set of tests for pandoc. Most of them are adapted from John Gruber’s markdown test suite.</p><empty-line /><p>——————————</p><empty-line /></section><section><title><p>Headers</p></title><section><title><p>Level 2 with an embedded link </url></p></title><section><title><p>Level 3 with emphasis</p></title><section><title><p>Level 4</p></title><section><title><p>Level 5</p></title></section></section></section></section></section><section><title><p>Level 1</p></title><section><title><p>Level 2 with emphasis</p></title><section><title><p>Level 3</p></title><p>with no blank line</p></section></section><section><title><p>Level 2</p></title><p>with no blank line</p><empty-line /><p>——————————</p><empty-line /></section></section><section><title><p>Paragraphs</p></title><p>Here’s a regular paragraph.</p><p>In Markdown 1.0.0 and earlier. Version 8. This line turns into a list item. Because a hard-wrapped line in the middle of a paragraph looked like a list item.</p><p>Here’s one with a bullet. * criminey.</p><p>There should be a hard line break<empty-line />here.</p><empty-line /><p>——————————</p><empty-line /></section><section><title><p>Block Quotes</p></title><p>E-mail style:</p><cite><p>This is a block quote. It is pretty short.</p></cite><cite><p>Code in a block quote:</p><empty-line /><p><code>sub status {</code></p><p><code> print "working";</code></p><p><code>}</code></p><empty-line /><p>A list:</p><p> 1. item one</p><p> 2. item two</p><p>Nested block quotes:</p><cite><p>nested</p></cite><cite><p>nested</p></cite></cite><p>This should not be a block quote: 2 > 1.</p><p>And a following paragraph.</p><empty-line /><p>——————————</p><empty-line /></section><section><title><p>Code Blocks</p></title><p>Code:</p><empty-line /><p><code>---- (should be four hyphens)</code></p><p><code></code></p><p><code>sub status {</code></p><p><code> print "working";</code></p><p><code>}</code></p><p><code></code></p><p><code>this code block is indented by one tab</code></p><empty-line /><p>And:</p><empty-line /><p><code> this code block is indented by two tabs</code></p><p><code></code></p><p><code>These should not be escaped: \$ \\ \> \[ \{</code></p><empty-line /><empty-line /><p>——————————</p><empty-line /></section><section><title><p>Lists</p></title><section><title><p>Unordered</p></title><p>Asterisks tight:</p><p>• asterisk 1</p><p>• asterisk 2</p><p>• asterisk 3</p><p>Asterisks loose:</p><p>• asterisk 1<empty-line /></p><p>• asterisk 2<empty-line /></p><p>• asterisk 3<empty-line /></p><p>Pluses tight:</p><p>• Plus 1</p><p>• Plus 2</p><p>• Plus 3</p><p>Pluses loose:</p><p>• Plus 1<empty-line /></p><p>• Plus 2<empty-line /></p><p>• Plus 3<empty-line /></p><p>Minuses tight:</p><p>• Minus 1</p><p>• Minus 2</p><p>• Minus 3</p><p>Minuses loose:</p><p>• Minus 1<empty-line /></p><p>• Minus 2<empty-line /></p><p>• Minus 3<empty-line /></p></section><section><title><p>Ordered</p></title><p>Tight:</p><p> 1. First</p><p> 2. Second</p><p> 3. Third</p><p>and:</p><p> 1. One</p><p> 2. Two</p><p> 3. Three</p><p>Loose using tabs:</p><p> 1. First<empty-line /></p><p> 2. Second<empty-line /></p><p> 3. Third<empty-line /></p><p>and using spaces:</p><p> 1. One<empty-line /></p><p> 2. Two<empty-line /></p><p> 3. Three<empty-line /></p><p>Multiple paragraphs:</p><p> 1. Item 1, graf one.<empty-line />Item 1. graf two. The quick brown fox jumped over the lazy dog’s back.<empty-line /></p><p> 2. Item 2.<empty-line /></p><p> 3. Item 3.<empty-line /></p></section><section><title><p>Nested</p></title><p>• Tab<p>◦ Tab<p>* Tab</p></p></p><p>Here’s another:</p><p> 1. First</p><p> 2. Second:<p> • Fee</p><p> • Fie</p><p> • Foe</p></p><p> 3. Third</p><p>Same thing but with paragraphs:</p><p> 1. First<empty-line /></p><p> 2. Second:<empty-line /><p> • Fee</p><p> • Fie</p><p> • Foe</p></p><p> 3. Third<empty-line /></p></section><section><title><p>Tabs and spaces</p></title><p>• this is a list item indented with tabs<empty-line /></p><p>• this is a list item indented with spaces<empty-line /><p>◦ this is an example list item indented with tabs<empty-line /></p><p>◦ this is an example list item indented with spaces<empty-line /></p></p></section><section><title><p>Fancy list markers</p></title><p> (2) begins with 2</p><p> (3) and now 3<empty-line />with a continuation<empty-line /><p> (3) iv. sublist with roman numerals, starting with 4</p><p> (3) v. more items<p> (3) v. (A) a subsublist</p><p> (3) v. (B) a subsublist</p></p></p><p>Nesting:</p><p> A. Upper Alpha<p> A. I. Upper Roman.<p> A. I. (6) Decimal start with 6<p> A. I. (6) c) Lower alpha with paren</p></p></p></p><p>Autonumbering:</p><p> 1. Autonumber.</p><p> 2. More.<p> 2. 1. Nested.</p></p><p>Should not be a list item:</p><p>M.A. 2007</p><p>B. Williams</p><empty-line /><p>——————————</p><empty-line /></section></section><section><title><p>Definition Lists</p></title><p>Tight using spaces:</p><p><strong>apple</strong></p><p> red fruit<empty-line /></p><p><strong>orange</strong></p><p> orange fruit<empty-line /></p><p><strong>banana</strong></p><p> yellow fruit<empty-line /></p><p>Tight using tabs:</p><p><strong>apple</strong></p><p> red fruit<empty-line /></p><p><strong>orange</strong></p><p> orange fruit<empty-line /></p><p><strong>banana</strong></p><p> yellow fruit<empty-line /></p><p>Loose:</p><p><strong>apple</strong></p><p> red fruit<empty-line /></p><p><strong>orange</strong></p><p> orange fruit<empty-line /></p><p><strong>banana</strong></p><p> yellow fruit<empty-line /></p><p>Multiple blocks with italics:</p><p><strong><emphasis>apple</emphasis></strong></p><p> red fruit<empty-line /> contains seeds, crisp, pleasant to taste<empty-line /></p><p><strong><emphasis>orange</emphasis></strong></p><p> orange fruit<empty-line /><empty-line /><p><code> { orange code block }</code></p><empty-line /><cite><p> orange block quote</p></cite></p><p>Multiple definitions, tight:</p><p><strong>apple</strong></p><p> red fruit<empty-line /> computer<empty-line /></p><p><strong>orange</strong></p><p> orange fruit<empty-line /> bank<empty-line /></p><p>Multiple definitions, loose:</p><p><strong>apple</strong></p><p> red fruit<empty-line /> computer<empty-line /></p><p><strong>orange</strong></p><p> orange fruit<empty-line /> bank<empty-line /></p><p>Blank line after term, indented marker, alternate markers:</p><p><strong>apple</strong></p><p> red fruit<empty-line /> computer<empty-line /></p><p><strong>orange</strong></p><p> orange fruit<empty-line /><p> 1. sublist</p><p> 2. sublist</p></p></section><section><title><p>HTML Blocks</p></title><p>Simple block on one line:</p>foo<p>And nested without indentation:</p><p>foo</p>bar<p>Interpreted markdown in a table:</p><empty-line /><p><code><table></code></p><empty-line /><empty-line /><p><code><tr></code></p><empty-line /><empty-line /><p><code><td></code></p><empty-line />This is <emphasis>emphasized</emphasis><empty-line /><p><code></td></code></p><empty-line /><empty-line /><p><code><td></code></p><empty-line />And this is <strong>strong</strong><empty-line /><p><code></td></code></p><empty-line /><empty-line /><p><code></tr></code></p><empty-line /><empty-line /><p><code></table></code></p><empty-line /><empty-line /><p><code><script type="text/javascript">document.write('This *should not* be interpreted as markdown');</script></code></p><empty-line /><p>Here’s a simple block:</p><p>foo</p><p>This should be a code block, though:</p><empty-line /><p><code><div></code></p><p><code> foo</code></p><p><code></div></code></p><empty-line /><p>As should this:</p><empty-line /><p><code><div>foo</div></code></p><empty-line /><p>Now, nested:</p>foo<p>This should just be an HTML comment:</p><empty-line /><p><code><!-- Comment --></code></p><empty-line /><p>Multiline:</p><empty-line /><p><code><!--</code></p><p><code>Blah</code></p><p><code>Blah</code></p><p><code>--></code></p><empty-line /><empty-line /><p><code><!--</code></p><p><code> This is another comment.</code></p><p><code>--></code></p><empty-line /><p>Code block:</p><empty-line /><p><code><!-- Comment --></code></p><empty-line /><p>Just plain comment, with trailing spaces on the line:</p><empty-line /><p><code><!-- foo --></code></p><empty-line /><p>Code:</p><empty-line /><p><code><hr /></code></p><empty-line /><p>Hr’s:</p><empty-line /><p><code><hr></code></p><empty-line /><empty-line /><p><code><hr /></code></p><empty-line /><empty-line /><p><code><hr /></code></p><empty-line /><empty-line /><p><code><hr></code></p><empty-line /><empty-line /><p><code><hr /></code></p><empty-line /><empty-line /><p><code><hr /></code></p><empty-line /><empty-line /><p><code><hr class="foo" id="bar" /></code></p><empty-line /><empty-line /><p><code><hr class="foo" id="bar" /></code></p><empty-line /><empty-line /><p><code><hr class="foo" id="bar"></code></p><empty-line /><empty-line /><p>——————————</p><empty-line /></section><section><title><p>Inline Markup</p></title><p>This is <emphasis>emphasized</emphasis>, and so <emphasis>is this</emphasis>.</p><p>This is <strong>strong</strong>, and so <strong>is this</strong>.</p><p>An <emphasis>emphasized link<a l:href="#l1" type="note"><sup>[1]</sup></a></emphasis>.</p><p><strong><emphasis>This is strong and em.</emphasis></strong></p><p>So is <strong><emphasis>this</emphasis></strong> word.</p><p><strong><emphasis>This is strong and em.</emphasis></strong></p><p>So is <strong><emphasis>this</emphasis></strong> word.</p><p>This is code: <code>></code>, <code>$</code>, <code>\</code>, <code>\$</code>, <code><html></code>.</p><p><strikethrough>This is <emphasis>strikeout</emphasis>.</strikethrough></p><p>Superscripts: a<sup>bc</sup>d a<sup><emphasis>hello</emphasis></sup> a<sup>hello there</sup>.</p><p>Subscripts: H<sub>2</sub>O, H<sub>23</sub>O, H<sub>many of them</sub>O.</p><p>These should not be superscripts or subscripts, because of the unescaped spaces: a^b c^d, a~b c~d.</p><empty-line /><p>——————————</p><empty-line /></section><section><title><p>Smart quotes, ellipses, dashes</p></title><p>“Hello,” said the spider. “‘Shelob’ is my name.”</p><p>‘A’, ‘B’, and ‘C’ are letters.</p><p>‘Oak,’ ‘elm,’ and ‘beech’ are names of trees. So is ‘pine.’</p><p>‘He said, “I want to go.”’ Were you alive in the 70’s?</p><p>Here is some quoted ‘<code>code</code>’ and a “quoted link<a l:href="#l2" type="note"><sup>[2]</sup></a>”.</p><p>Some dashes: one—two — three—four — five.</p><p>Dashes between numbers: 5–7, 255–66, 1987–1999.</p><p>Ellipses…and…and….</p><empty-line /><p>——————————</p><empty-line /></section><section><title><p>LaTeX</p></title><p>• </p><p>• <code>2+2=4</code></p><p>• <code>x \in y</code></p><p>• <code>\alpha \wedge \omega</code></p><p>• <code>223</code></p><p>• <code>p</code>-Tree</p><p>• Here’s some display math: <code>\frac{d}{dx}f(x)=\lim_{h\to 0}\frac{f(x+h)-f(x)}{h}</code></p><p>• Here’s one that has a line break in it: <code>\alpha + \omega \times x^2</code>.</p><p>These shouldn’t be math:</p><p>• To get the famous equation, write <code>$e = mc^2$</code>.</p><p>• $22,000 is a <emphasis>lot</emphasis> of money. So is $34,000. (It worked if “lot” is emphasized.)</p><p>• Shoes ($20) and socks ($5).</p><p>• Escaped <code>$</code>: $73 <emphasis>this should be emphasized</emphasis> 23$.</p><p>Here’s a LaTeX table:</p><empty-line /><p><code>\begin{tabular}{|l|l|}\hline</code></p><p><code>Animal & Number \\ \hline</code></p><p><code>Dog & 2 \\</code></p><p><code>Cat & 1 \\ \hline</code></p><p><code>\end{tabular}</code></p><empty-line /><empty-line /><p>——————————</p><empty-line /></section><section><title><p>Special Characters</p></title><p>Here is some unicode:</p><p>• I hat: Î</p><p>• o umlaut: ö</p><p>• section: §</p><p>• set membership: ∈</p><p>• copyright: ©</p><p>AT&T has an ampersand in their name.</p><p>AT&T is another way to write it.</p><p>This & that.</p><p>4 < 5.</p><p>6 > 5.</p><p>Backslash: \</p><p>Backtick: `</p><p>Asterisk: *</p><p>Underscore: _</p><p>Left brace: {</p><p>Right brace: }</p><p>Left bracket: [</p><p>Right bracket: ]</p><p>Left paren: (</p><p>Right paren: )</p><p>Greater-than: ></p><p>Hash: #</p><p>Period: .</p><p>Bang: !</p><p>Plus: +</p><p>Minus: -</p><empty-line /><p>——————————</p><empty-line /></section><section><title><p>Links</p></title><section><title><p>Explicit</p></title><p>Just a URL<a l:href="#l3" type="note"><sup>[3]</sup></a>.</p><p>URL and title<a l:href="#l4" type="note"><sup>[4]</sup></a>.</p><p>URL and title<a l:href="#l5" type="note"><sup>[5]</sup></a>.</p><p>URL and title<a l:href="#l6" type="note"><sup>[6]</sup></a>.</p><p>URL and title<a l:href="#l7" type="note"><sup>[7]</sup></a></p><p>URL and title<a l:href="#l8" type="note"><sup>[8]</sup></a></p><p>with_underscore<a l:href="#l9" type="note"><sup>[9]</sup></a></p><p>Email link<a l:href="#l10" type="note"><sup>[10]</sup></a></p><p>Empty<a l:href="#l11" type="note"><sup>[11]</sup></a>.</p></section><section><title><p>Reference</p></title><p>Foo bar<a l:href="#l12" type="note"><sup>[12]</sup></a>.</p><p>Foo bar<a l:href="#l13" type="note"><sup>[13]</sup></a>.</p><p>Foo bar<a l:href="#l14" type="note"><sup>[14]</sup></a>.</p><p>With embedded [brackets]<a l:href="#l15" type="note"><sup>[15]</sup></a>.</p><p>b<a l:href="#l16" type="note"><sup>[16]</sup></a> by itself should be a link.</p><p>Indented once<a l:href="#l17" type="note"><sup>[17]</sup></a>.</p><p>Indented twice<a l:href="#l18" type="note"><sup>[18]</sup></a>.</p><p>Indented thrice<a l:href="#l19" type="note"><sup>[19]</sup></a>.</p><p>This should [not][] be a link.</p><empty-line /><p><code>[not]: /url</code></p><empty-line /><p>Foo bar<a l:href="#l20" type="note"><sup>[20]</sup></a>.</p><p>Foo biz<a l:href="#l21" type="note"><sup>[21]</sup></a>.</p></section><section><title><p>With ampersands</p></title><p>Here’s a link with an ampersand in the URL<a l:href="#l22" type="note"><sup>[22]</sup></a>.</p><p>Here’s a link with an amersand in the link text: AT&T<a l:href="#l23" type="note"><sup>[23]</sup></a>.</p><p>Here’s an inline link<a l:href="#l24" type="note"><sup>[24]</sup></a>.</p><p>Here’s an inline link in pointy braces<a l:href="#l25" type="note"><sup>[25]</sup></a>.</p></section><section><title><p>Autolinks</p></title><p>With an ampersand: http://example.com/?foo=1&bar=2<a l:href="#l26" type="note"><sup>[26]</sup></a></p><p>• In a list?</p><p>• http://example.com/<a l:href="#l27" type="note"><sup>[27]</sup></a></p><p>• It should.</p><p>An e-mail address: nobody@nowhere.net<a l:href="#l28" type="note"><sup>[28]</sup></a></p><cite><p>Blockquoted: http://example.com/<a l:href="#l29" type="note"><sup>[29]</sup></a></p></cite><p>Auto-links should not occur here: <code><http://example.com/></code></p><empty-line /><p><code>or here: <http://example.com/></code></p><empty-line /><empty-line /><p>——————————</p><empty-line /></section></section><section><title><p>Images</p></title><p>From “Voyage dans la Lune” by Georges Melies (1902):</p><image l:href="#image1" l:type="imageType" alt="lalune" title="Voyage dans la Lune" /><p>Here is a movie <image l:href="#image2" l:type="inlineImageType" alt="movie" /> icon.</p><empty-line /><p>——————————</p><empty-line /></section><section><title><p>Footnotes</p></title><p>Here is a footnote reference,<a l:href="#n30" type="note"><sup>[30]</sup></a> and another.<a l:href="#n31" type="note"><sup>[31]</sup></a> This should <emphasis>not</emphasis> be a footnote reference, because it contains a space.[^my note] Here is an inline note.<a l:href="#n32" type="note"><sup>[32]</sup></a></p><cite><p>Notes can go in quotes.<a l:href="#n33" type="note"><sup>[33]</sup></a></p></cite><p> 1. And in list items.<a l:href="#n34" type="note"><sup>[34]</sup></a></p><p>This paragraph should not be part of the note, as it is not indented.</p></section></body><body name="notes"><section id="l1"><title><p>1</p></title><p><code>/url</code></p></section><section id="l2"><title><p>2</p></title><p><code>http://example.com/?foo=1&bar=2</code></p></section><section id="l3"><title><p>3</p></title><p><code>/url/</code></p></section><section id="l4"><title><p>4</p></title><p>title: <code>/url/</code></p></section><section id="l5"><title><p>5</p></title><p>title preceded by two spaces: <code>/url/</code></p></section><section id="l6"><title><p>6</p></title><p>title preceded by a tab: <code>/url/</code></p></section><section id="l7"><title><p>7</p></title><p>title with "quotes" in it: <code>/url/</code></p></section><section id="l8"><title><p>8</p></title><p>title with single quotes: <code>/url/</code></p></section><section id="l9"><title><p>9</p></title><p><code>/url/with_underscore</code></p></section><section id="l10"><title><p>10</p></title><p><code>mailto:nobody@nowhere.net</code></p></section><section id="l11"><title><p>11</p></title><p><code></code></p></section><section id="l12"><title><p>12</p></title><p><code>/url/</code></p></section><section id="l13"><title><p>13</p></title><p><code>/url/</code></p></section><section id="l14"><title><p>14</p></title><p><code>/url/</code></p></section><section id="l15"><title><p>15</p></title><p><code>/url/</code></p></section><section id="l16"><title><p>16</p></title><p><code>/url/</code></p></section><section id="l17"><title><p>17</p></title><p><code>/url</code></p></section><section id="l18"><title><p>18</p></title><p><code>/url</code></p></section><section id="l19"><title><p>19</p></title><p><code>/url</code></p></section><section id="l20"><title><p>20</p></title><p>Title with "quotes" inside: <code>/url/</code></p></section><section id="l21"><title><p>21</p></title><p>Title with "quote" inside: <code>/url/</code></p></section><section id="l22"><title><p>22</p></title><p><code>http://example.com/?foo=1&bar=2</code></p></section><section id="l23"><title><p>23</p></title><p>AT&T: <code>http://att.com/</code></p></section><section id="l24"><title><p>24</p></title><p><code>/script?foo=1&bar=2</code></p></section><section id="l25"><title><p>25</p></title><p><code>/script?foo=1&bar=2</code></p></section><section id="l26"><title><p>26</p></title><p><code>http://example.com/?foo=1&bar=2</code></p></section><section id="l27"><title><p>27</p></title><p><code>http://example.com/</code></p></section><section id="l28"><title><p>28</p></title><p><code>mailto:nobody@nowhere.net</code></p></section><section id="l29"><title><p>29</p></title><p><code>http://example.com/</code></p></section><section id="n30"><title><p>30</p></title><p>Here is the footnote. It can go anywhere after the footnote reference. It need not be placed at the end of the document.</p></section><section id="n31"><title><p>31</p></title><p>Here’s the long note. This one contains multiple blocks.</p><p>Subsequent blocks are indented to show that they belong to the footnote (as with list items).</p><empty-line /><p><code> { <code> }</code></p><empty-line /><p>If you want, you can indent every line, but you can also be lazy and just indent the first line of each block.</p></section><section id="n32"><title><p>32</p></title><p>This is <emphasis>easier</emphasis> to type. Inline notes may contain links<a l:href="#l32" type="note"><sup>[32]</sup></a> and <code>]</code> verbatim characters, as well as [bracketed text].</p></section><section id="n33"><title><p>33</p></title><p>In quote.</p></section><section id="n34"><title><p>34</p></title><p>In list.</p></section></body><binary id="image2" content-type="image/jpeg">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</binary><binary id="image1" content-type="image/jpeg">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</binary></FictionBook>
\ No newline at end of file diff --git a/tests/writer.haddock b/tests/writer.haddock new file mode 100644 index 000000000..0772331e3 --- /dev/null +++ b/tests/writer.haddock @@ -0,0 +1,660 @@ +This is a set of tests for pandoc. Most of them are adapted from John Gruber’s +markdown test suite. + +______________________________________________________________________________ + += Headers +#headers# + +== Level 2 with an </url embedded link> +#level-2-with-an-embedded-link# + +=== Level 3 with /emphasis/ +#level-3-with-emphasis# + +==== Level 4 +#level-4# + +===== Level 5 +#level-5# + += Level 1 +#level-1# + +== Level 2 with /emphasis/ +#level-2-with-emphasis# + +=== Level 3 +#level-3# + +with no blank line + +== Level 2 +#level-2# + +with no blank line + +______________________________________________________________________________ + += Paragraphs +#paragraphs# + +Here’s a regular paragraph. + +In Markdown 1.0.0 and earlier. Version 8. This line turns into a list item. +Because a hard-wrapped line in the middle of a paragraph looked like a list +item. + +Here’s one with a bullet. * criminey. + +There should be a hard line break +here. + +______________________________________________________________________________ + += Block Quotes +#block-quotes# + +E-mail style: + +This is a block quote. It is pretty short. + +Code in a block quote: + +> sub status { +> print "working"; +> } + +A list: + +1. item one +2. item two + +Nested block quotes: + +nested + +nested + +This should not be a block quote: 2 > 1. + +And a following paragraph. + +______________________________________________________________________________ + += Code Blocks +#code-blocks# + +Code: + +> ---- (should be four hyphens) +> +> sub status { +> print "working"; +> } +> +> this code block is indented by one tab + +And: + +> this code block is indented by two tabs +> +> These should not be escaped: \$ \\ \> \[ \{ + +______________________________________________________________________________ + += Lists +#lists# + +== Unordered +#unordered# + +Asterisks tight: + +- asterisk 1 +- asterisk 2 +- asterisk 3 + +Asterisks loose: + +- asterisk 1 + +- asterisk 2 + +- asterisk 3 + +Pluses tight: + +- Plus 1 +- Plus 2 +- Plus 3 + +Pluses loose: + +- Plus 1 + +- Plus 2 + +- Plus 3 + +Minuses tight: + +- Minus 1 +- Minus 2 +- Minus 3 + +Minuses loose: + +- Minus 1 + +- Minus 2 + +- Minus 3 + +== Ordered +#ordered# + +Tight: + +1. First +2. Second +3. Third + +and: + +1. One +2. Two +3. Three + +Loose using tabs: + +1. First + +2. Second + +3. Third + +and using spaces: + +1. One + +2. Two + +3. Three + +Multiple paragraphs: + +1. Item 1, graf one. + + Item 1. graf two. The quick brown fox jumped over the lazy dog’s back. + +2. Item 2. + +3. Item 3. + +== Nested +#nested# + +- Tab + - Tab + - Tab + +Here’s another: + +1. First +2. Second: + - Fee + - Fie + - Foe + +3. Third + +Same thing but with paragraphs: + +1. First + +2. Second: + + - Fee + - Fie + - Foe + +3. Third + +== Tabs and spaces +#tabs-and-spaces# + +- this is a list item indented with tabs + +- this is a list item indented with spaces + + - this is an example list item indented with tabs + + - this is an example list item indented with spaces + +== Fancy list markers +#fancy-list-markers# + +(2) begins with 2 +(3) and now 3 + + with a continuation + + 4. sublist with roman numerals, starting with 4 + 5. more items + (1) a subsublist + (2) a subsublist + +Nesting: + +1. Upper Alpha + 1. Upper Roman. + (6) Decimal start with 6 + 3) Lower alpha with paren + +Autonumbering: + +1. Autonumber. +2. More. + 1. Nested. + +Should not be a list item: + +M.A. 2007 + +B. Williams + +______________________________________________________________________________ + += Definition Lists +#definition-lists# + +Tight using spaces: + +[apple] + red fruit +[orange] + orange fruit +[banana] + yellow fruit + +Tight using tabs: + +[apple] + red fruit +[orange] + orange fruit +[banana] + yellow fruit + +Loose: + +[apple] + red fruit + +[orange] + orange fruit + +[banana] + yellow fruit + +Multiple blocks with italics: + +[/apple/] + red fruit + + contains seeds, crisp, pleasant to taste + +[/orange/] + orange fruit + + > { orange code block } + + orange block quote + +Multiple definitions, tight: + +[apple] + red fruit + computer +[orange] + orange fruit + bank + +Multiple definitions, loose: + +[apple] + red fruit + + computer + +[orange] + orange fruit + + bank + +Blank line after term, indented marker, alternate markers: + +[apple] + red fruit + + computer + +[orange] + orange fruit + + 1. sublist + 2. sublist + += HTML Blocks +#html-blocks# + +Simple block on one line: + +foo + +And nested without indentation: + +foo + +bar + +Interpreted markdown in a table: + +This is /emphasized/ +And this is __strong__ +Here’s a simple block: + +foo + +This should be a code block, though: + +> <div> +> foo +> </div> + +As should this: + +> <div>foo</div> + +Now, nested: + +foo + +This should just be an HTML comment: + +Multiline: + +Code block: + +> <!-- Comment --> + +Just plain comment, with trailing spaces on the line: + +Code: + +> <hr /> + +Hr’s: + +______________________________________________________________________________ + += Inline Markup +#inline-markup# + +This is /emphasized/, and so /is this/. + +This is __strong__, and so __is this__. + +An /</url emphasized link>/. + +__/This is strong and em./__ + +So is __/this/__ word. + +__/This is strong and em./__ + +So is __/this/__ word. + +This is code: @>@, @$@, @\\@, @\\$@, @\<html>@. + +~~This is /strikeout/.~~ + +Superscripts: abcd a/hello/ ahello there. + +Subscripts: H2O, H23O, Hmany of themO. + +These should not be superscripts or subscripts, because of the unescaped +spaces: a^b c^d, a~b c~d. + +______________________________________________________________________________ + += Smart quotes, ellipses, dashes +#smart-quotes-ellipses-dashes# + +“Hello,” said the spider. “‘Shelob’ is my name.” + +‘A’, ‘B’, and ‘C’ are letters. + +‘Oak,’ ‘elm,’ and ‘beech’ are names of trees. So is ‘pine.’ + +‘He said, “I want to go.”’ Were you alive in the 70’s? + +Here is some quoted ‘@code@’ and a +“<http://example.com/?foo=1&bar=2 quoted link>”. + +Some dashes: one—two — three—four — five. + +Dashes between numbers: 5–7, 255–66, 1987–1999. + +Ellipses…and…and…. + +______________________________________________________________________________ + += LaTeX +#latex# + +- +- 2 + 2 = 4 +- /x/ ∈ /y/ +- /α/ ∧ /ω/ +- 223 +- /p/-Tree +- Here’s some display math: + $$\\frac{d}{dx}f(x)=\\lim_{h\\to 0}\\frac{f(x+h)-f(x)}{h}$$ +- Here’s one that has a line break in it: /α/ + /ω/ × /x/2. + +These shouldn’t be math: + +- To get the famous equation, write @$e = mc^2$@. +- $22,000 is a /lot/ of money. So is $34,000. (It worked if “lot” is + emphasized.) +- Shoes ($20) and socks ($5). +- Escaped @$@: $73 /this should be emphasized/ 23$. + +Here’s a LaTeX table: + +______________________________________________________________________________ + += Special Characters +#special-characters# + +Here is some unicode: + +- I hat: Î +- o umlaut: ö +- section: § +- set membership: ∈ +- copyright: © + +AT&T has an ampersand in their name. + +AT&T is another way to write it. + +This & that. + +4 \< 5. + +6 > 5. + +Backslash: \\ + +Backtick: \` + +Asterisk: * + +Underscore: _ + +Left brace: { + +Right brace: } + +Left bracket: [ + +Right bracket: ] + +Left paren: ( + +Right paren: ) + +Greater-than: > + +Hash: # + +Period: . + +Bang: ! + +Plus: + + +Minus: - + +______________________________________________________________________________ + += Links +#links# + +== Explicit +#explicit# + +Just a </url/ URL>. + +</url/ URL and title>. + +</url/ URL and title>. + +</url/ URL and title>. + +</url/ URL and title> + +</url/ URL and title> + +</url/with_underscore with_underscore> + +<mailto:nobody@nowhere.net Email link> + +< Empty>. + +== Reference +#reference# + +Foo </url/ bar>. + +Foo </url/ bar>. + +Foo </url/ bar>. + +With </url/ embedded [brackets]>. + +</url/ b> by itself should be a link. + +Indented </url once>. + +Indented </url twice>. + +Indented </url thrice>. + +This should [not][] be a link. + +> [not]: /url + +Foo </url/ bar>. + +Foo </url/ biz>. + +== With ampersands +#with-ampersands# + +Here’s a <http://example.com/?foo=1&bar=2 link with an ampersand in the URL>. + +Here’s a link with an amersand in the link text: <http://att.com/ AT&T>. + +Here’s an </script?foo=1&bar=2 inline link>. + +Here’s an </script?foo=1&bar=2 inline link in pointy braces>. + +== Autolinks +#autolinks# + +With an ampersand: <http://example.com/?foo=1&bar=2> + +- In a list? +- <http://example.com/> +- It should. + +An e-mail address: <mailto:nobody@nowhere.net nobody\@nowhere.net> + +Blockquoted: <http://example.com/> + +Auto-links should not occur here: @\<http:\/\/example.com\/>@ + +> or here: <http://example.com/> + +______________________________________________________________________________ + += Images +#images# + +From “Voyage dans la Lune” by Georges Melies (1902): + +<<lalune.jpg lalune>> + +Here is a movie <<movie.jpg movie>> icon. + +______________________________________________________________________________ + += Footnotes +#footnotes# + +Here is a footnote reference,<#notes [1]> and another.<#notes [2]> This should +/not/ be a footnote reference, because it contains a space.[^my note] Here is +an inline note.<#notes [3]> + +Notes can go in quotes.<#notes [4]> + +1. And in list items.<#notes [5]> + +This paragraph should not be part of the note, as it is not indented. + +#notes# + +1. Here is the footnote. It can go anywhere after the footnote reference. It + need not be placed at the end of the document. + +2. Here’s the long note. This one contains multiple blocks. + + Subsequent blocks are indented to show that they belong to the footnote + (as with list items). + + > { <code> } + + If you want, you can indent every line, but you can also be lazy and just + indent the first line of each block. + +3. This is /easier/ to type. Inline notes may contain + <http://google.com links> and @]@ verbatim characters, as well as + [bracketed text]. + +4. In quote. + +5. In list. diff --git a/tests/writer.html b/tests/writer.html index d00b8ca66..b56e81292 100644 --- a/tests/writer.html +++ b/tests/writer.html @@ -328,7 +328,7 @@ foo <div> <div> <div> -foo +<p>foo</p> </div> </div> <div> @@ -346,12 +346,10 @@ And this is <strong>strong</strong> </td> </tr> </table> - <script type="text/javascript">document.write('This *should not* be interpreted as markdown');</script> - <p>Here’s a simple block:</p> <div> -foo +<p>foo</p> </div> <p>This should be a code block, though:</p> <pre><code><div> @@ -369,43 +367,30 @@ foo </div> <p>This should just be an HTML comment:</p> <!-- Comment --> - <p>Multiline:</p> <!-- Blah Blah --> - <!-- This is another comment. --> - <p>Code block:</p> <pre><code><!-- Comment --></code></pre> <p>Just plain comment, with trailing spaces on the line:</p> -<!-- foo --> - +<!-- foo --> <p>Code:</p> <pre><code><hr /></code></pre> <p>Hr’s:</p> <hr> - <hr /> - <hr /> - -<hr> - -<hr /> - -<hr /> - +<hr> +<hr /> +<hr /> <hr class="foo" id="bar" /> - <hr class="foo" id="bar" /> - <hr class="foo" id="bar"> - <hr /> <h1 id="inline-markup">Inline Markup</h1> <p>This is <em>emphasized</em>, and so <em>is this</em>.</p> @@ -495,7 +480,7 @@ Blah <p><script type="text/javascript"> <!-- h='nowhere.net';a='@';n='nobody';e=n+a+h; -document.write('<a h'+'ref'+'="ma'+'ilto'+':'+e+'">'+'Email link'+'<\/'+'a'+'>'); +document.write('<a h'+'ref'+'="ma'+'ilto'+':'+e+'" clas'+'s="em' + 'ail">'+'Email link'+'<\/'+'a'+'>'); // --> </script><noscript>Email link (nobody at nowhere dot net)</noscript></p> <p><a href="">Empty</a>.</p> @@ -518,20 +503,20 @@ document.write('<a h'+'ref'+'="ma'+'ilto'+':'+e+'">'+'Email link'+'<\/'+'a'+'>') <p>Here’s an <a href="/script?foo=1&bar=2">inline link</a>.</p> <p>Here’s an <a href="/script?foo=1&bar=2">inline link in pointy braces</a>.</p> <h2 id="autolinks">Autolinks</h2> -<p>With an ampersand: <a href="http://example.com/?foo=1&bar=2">http://example.com/?foo=1&bar=2</a></p> +<p>With an ampersand: <a href="http://example.com/?foo=1&bar=2" class="uri">http://example.com/?foo=1&bar=2</a></p> <ul> <li>In a list?</li> -<li><a href="http://example.com/">http://example.com/</a></li> +<li><a href="http://example.com/" class="uri">http://example.com/</a></li> <li>It should.</li> </ul> <p>An e-mail address: <script type="text/javascript"> <!-- h='nowhere.net';a='@';n='nobody';e=n+a+h; -document.write('<a h'+'ref'+'="ma'+'ilto'+':'+e+'">'+e+'<\/'+'a'+'>'); +document.write('<a h'+'ref'+'="ma'+'ilto'+':'+e+'" clas'+'s="em' + 'ail">'+e+'<\/'+'a'+'>'); // --> </script><noscript>nobody at nowhere dot net</noscript></p> <blockquote> -<p>Blockquoted: <a href="http://example.com/">http://example.com/</a></p> +<p>Blockquoted: <a href="http://example.com/" class="uri">http://example.com/</a></p> </blockquote> <p>Auto-links should not occur here: <code><http://example.com/></code></p> <pre><code>or here: <http://example.com/></code></pre> diff --git a/tests/writer.icml b/tests/writer.icml new file mode 100644 index 000000000..8922da7ed --- /dev/null +++ b/tests/writer.icml @@ -0,0 +1,3068 @@ +<?xml version="1.0" encoding="UTF-8" standalone="yes"?> +<?aid style="50" type="snippet" readerVersion="6.0" featureSet="513" product="8.0(370)" ?> +<?aid SnippetType="InCopyInterchange"?> +<Document DOMVersion="8.0" Self="pandoc_doc"> + <RootCharacterStyleGroup Self="pandoc_character_styles"> + <CharacterStyle Self="$ID/NormalCharacterStyle" Name="Default" /> + <CharacterStyle Self="CharacterStyle/" Name=""> + <Properties> + <BasedOn type="object">$ID/NormalCharacterStyle</BasedOn> + </Properties> + </CharacterStyle> + <CharacterStyle Self="CharacterStyle/Bold" Name="Bold" FontStyle="Bold"> + <Properties> + <BasedOn type="object">$ID/NormalCharacterStyle</BasedOn> + </Properties> + </CharacterStyle> + <CharacterStyle Self="CharacterStyle/Bold Italic" Name="Bold Italic" FontStyle="Bold Italic"> + <Properties> + <BasedOn type="object">$ID/NormalCharacterStyle</BasedOn> + </Properties> + </CharacterStyle> + <CharacterStyle Self="CharacterStyle/Code" Name="Code"> + <Properties> + <BasedOn type="object">$ID/NormalCharacterStyle</BasedOn> + <AppliedFont type="string">Courier New</AppliedFont> + </Properties> + </CharacterStyle> + <CharacterStyle Self="CharacterStyle/Italic" Name="Italic" FontStyle="Italic"> + <Properties> + <BasedOn type="object">$ID/NormalCharacterStyle</BasedOn> + </Properties> + </CharacterStyle> + <CharacterStyle Self="CharacterStyle/Italic Link" Name="Italic Link" FontStyle="Italic"> + <Properties> + <BasedOn type="object">$ID/NormalCharacterStyle</BasedOn> + </Properties> + </CharacterStyle> + <CharacterStyle Self="CharacterStyle/Italic Strikeout" Name="Italic Strikeout" FontStyle="Italic" StrikeThru="true"> + <Properties> + <BasedOn type="object">$ID/NormalCharacterStyle</BasedOn> + </Properties> + </CharacterStyle> + <CharacterStyle Self="CharacterStyle/Italic Superscript" Name="Italic Superscript" FontStyle="Italic" Position="Superscript"> + <Properties> + <BasedOn type="object">$ID/NormalCharacterStyle</BasedOn> + </Properties> + </CharacterStyle> + <CharacterStyle Self="CharacterStyle/Link" Name="Link"> + <Properties> + <BasedOn type="object">$ID/NormalCharacterStyle</BasedOn> + </Properties> + </CharacterStyle> + <CharacterStyle Self="CharacterStyle/Strikeout" Name="Strikeout" StrikeThru="true"> + <Properties> + <BasedOn type="object">$ID/NormalCharacterStyle</BasedOn> + </Properties> + </CharacterStyle> + <CharacterStyle Self="CharacterStyle/Subscript" Name="Subscript" Position="Subscript"> + <Properties> + <BasedOn type="object">$ID/NormalCharacterStyle</BasedOn> + </Properties> + </CharacterStyle> + <CharacterStyle Self="CharacterStyle/Superscript" Name="Superscript" Position="Superscript"> + <Properties> + <BasedOn type="object">$ID/NormalCharacterStyle</BasedOn> + </Properties> + </CharacterStyle> + </RootCharacterStyleGroup> + <RootParagraphStyleGroup Self="pandoc_paragraph_styles"> + <ParagraphStyle Self="$ID/NormalParagraphStyle" Name="$ID/NormalParagraphStyle" + SpaceBefore="6" SpaceAfter="6"> <!-- paragraph spacing --> + <Properties> + <TabList type="list"> + <ListItem type="record"> + <Alignment type="enumeration">LeftAlign</Alignment> + <AlignmentCharacter type="string">.</AlignmentCharacter> + <Leader type="string"></Leader> + <Position type="unit">10</Position> <!-- first tab stop --> + </ListItem> + </TabList> + </Properties> + </ParagraphStyle> + <ParagraphStyle Self="ParagraphStyle/" Name="" LeftIndent="0"> + <Properties> + <BasedOn type="object">$ID/NormalParagraphStyle</BasedOn> + </Properties> + </ParagraphStyle> + <ParagraphStyle Self="ParagraphStyle/Blockquote > Blockquote > Paragraph" Name="Blockquote > Blockquote > Paragraph" LeftIndent="30"> + <Properties> + <BasedOn type="object">$ID/NormalParagraphStyle</BasedOn> + </Properties> + </ParagraphStyle> + <ParagraphStyle Self="ParagraphStyle/Blockquote > CodeBlock" Name="Blockquote > CodeBlock" LeftIndent="10"> + <Properties> + <BasedOn type="object">$ID/NormalParagraphStyle</BasedOn> + <AppliedFont type="string">Courier New</AppliedFont> + </Properties> + </ParagraphStyle> + <ParagraphStyle Self="ParagraphStyle/Blockquote > NumList" Name="Blockquote > NumList" NumberingExpression="^#.^t" NumberingLevel="1" BulletsAndNumberingListType="NumberedList" LeftIndent="20"> + <Properties> + <BasedOn type="object">$ID/NormalParagraphStyle</BasedOn> + </Properties> + </ParagraphStyle> + <ParagraphStyle Self="ParagraphStyle/Blockquote > NumList > first" Name="Blockquote > NumList > first" NumberingExpression="^#.^t" NumberingLevel="1" BulletsAndNumberingListType="NumberedList" LeftIndent="20"> + <Properties> + <BasedOn type="object">$ID/NormalParagraphStyle</BasedOn> + </Properties> + </ParagraphStyle> + <ParagraphStyle Self="ParagraphStyle/Blockquote > Paragraph" Name="Blockquote > Paragraph" LeftIndent="10"> + <Properties> + <BasedOn type="object">$ID/NormalParagraphStyle</BasedOn> + </Properties> + </ParagraphStyle> + <ParagraphStyle Self="ParagraphStyle/BulList" Name="BulList" BulletsAndNumberingListType="BulletList" LeftIndent="0"> + <Properties> + <BasedOn type="object">$ID/NormalParagraphStyle</BasedOn> + <TabList type="list"> + <ListItem type="record"> + <Alignment type="enumeration">LeftAlign</Alignment> + <AlignmentCharacter type="string">.</AlignmentCharacter> + <Leader type="string" /> + <Position type="unit">10</Position> + </ListItem> + </TabList> + </Properties> + </ParagraphStyle> + <ParagraphStyle Self="ParagraphStyle/BulList > BulList > BulList > first" Name="BulList > BulList > BulList > first" BulletsAndNumberingListType="BulletList" LeftIndent="20"> + <Properties> + <BasedOn type="object">$ID/NormalParagraphStyle</BasedOn> + <TabList type="list"> + <ListItem type="record"> + <Alignment type="enumeration">LeftAlign</Alignment> + <AlignmentCharacter type="string">.</AlignmentCharacter> + <Leader type="string" /> + <Position type="unit">30</Position> + </ListItem> + </TabList> + </Properties> + </ParagraphStyle> + <ParagraphStyle Self="ParagraphStyle/BulList > BulList > Paragraph" Name="BulList > BulList > Paragraph" BulletsAndNumberingListType="BulletList" LeftIndent="10"> + <Properties> + <BasedOn type="object">$ID/NormalParagraphStyle</BasedOn> + <TabList type="list"> + <ListItem type="record"> + <Alignment type="enumeration">LeftAlign</Alignment> + <AlignmentCharacter type="string">.</AlignmentCharacter> + <Leader type="string" /> + <Position type="unit">20</Position> + </ListItem> + </TabList> + </Properties> + </ParagraphStyle> + <ParagraphStyle Self="ParagraphStyle/BulList > BulList > first" Name="BulList > BulList > first" BulletsAndNumberingListType="BulletList" LeftIndent="10"> + <Properties> + <BasedOn type="object">$ID/NormalParagraphStyle</BasedOn> + <TabList type="list"> + <ListItem type="record"> + <Alignment type="enumeration">LeftAlign</Alignment> + <AlignmentCharacter type="string">.</AlignmentCharacter> + <Leader type="string" /> + <Position type="unit">20</Position> + </ListItem> + </TabList> + </Properties> + </ParagraphStyle> + <ParagraphStyle Self="ParagraphStyle/BulList > BulList > first > Paragraph" Name="BulList > BulList > first > Paragraph" BulletsAndNumberingListType="BulletList" LeftIndent="10"> + <Properties> + <BasedOn type="object">$ID/NormalParagraphStyle</BasedOn> + <TabList type="list"> + <ListItem type="record"> + <Alignment type="enumeration">LeftAlign</Alignment> + <AlignmentCharacter type="string">.</AlignmentCharacter> + <Leader type="string" /> + <Position type="unit">20</Position> + </ListItem> + </TabList> + </Properties> + </ParagraphStyle> + <ParagraphStyle Self="ParagraphStyle/BulList > Paragraph" Name="BulList > Paragraph" BulletsAndNumberingListType="BulletList" LeftIndent="0"> + <Properties> + <BasedOn type="object">$ID/NormalParagraphStyle</BasedOn> + <TabList type="list"> + <ListItem type="record"> + <Alignment type="enumeration">LeftAlign</Alignment> + <AlignmentCharacter type="string">.</AlignmentCharacter> + <Leader type="string" /> + <Position type="unit">10</Position> + </ListItem> + </TabList> + </Properties> + </ParagraphStyle> + <ParagraphStyle Self="ParagraphStyle/BulList > first" Name="BulList > first" BulletsAndNumberingListType="BulletList" LeftIndent="0"> + <Properties> + <BasedOn type="object">$ID/NormalParagraphStyle</BasedOn> + <TabList type="list"> + <ListItem type="record"> + <Alignment type="enumeration">LeftAlign</Alignment> + <AlignmentCharacter type="string">.</AlignmentCharacter> + <Leader type="string" /> + <Position type="unit">10</Position> + </ListItem> + </TabList> + </Properties> + </ParagraphStyle> + <ParagraphStyle Self="ParagraphStyle/BulList > first > Paragraph" Name="BulList > first > Paragraph" BulletsAndNumberingListType="BulletList" LeftIndent="0"> + <Properties> + <BasedOn type="object">$ID/NormalParagraphStyle</BasedOn> + <TabList type="list"> + <ListItem type="record"> + <Alignment type="enumeration">LeftAlign</Alignment> + <AlignmentCharacter type="string">.</AlignmentCharacter> + <Leader type="string" /> + <Position type="unit">10</Position> + </ListItem> + </TabList> + </Properties> + </ParagraphStyle> + <ParagraphStyle Self="ParagraphStyle/CodeBlock" Name="CodeBlock" LeftIndent="0"> + <Properties> + <BasedOn type="object">$ID/NormalParagraphStyle</BasedOn> + <AppliedFont type="string">Courier New</AppliedFont> + </Properties> + </ParagraphStyle> + <ParagraphStyle Self="ParagraphStyle/DefListDef" Name="DefListDef" LeftIndent="10"> + <Properties> + <BasedOn type="object">$ID/NormalParagraphStyle</BasedOn> + </Properties> + </ParagraphStyle> + <ParagraphStyle Self="ParagraphStyle/DefListDef > Blockquote > Paragraph" Name="DefListDef > Blockquote > Paragraph" LeftIndent="30"> + <Properties> + <BasedOn type="object">$ID/NormalParagraphStyle</BasedOn> + </Properties> + </ParagraphStyle> + <ParagraphStyle Self="ParagraphStyle/DefListDef > CodeBlock" Name="DefListDef > CodeBlock" LeftIndent="10"> + <Properties> + <BasedOn type="object">$ID/NormalParagraphStyle</BasedOn> + <AppliedFont type="string">Courier New</AppliedFont> + </Properties> + </ParagraphStyle> + <ParagraphStyle Self="ParagraphStyle/DefListDef > NumList" Name="DefListDef > NumList" NumberingExpression="^#.^t" NumberingLevel="1" BulletsAndNumberingListType="NumberedList" LeftIndent="20"> + <Properties> + <BasedOn type="object">$ID/NormalParagraphStyle</BasedOn> + </Properties> + </ParagraphStyle> + <ParagraphStyle Self="ParagraphStyle/DefListDef > NumList > first" Name="DefListDef > NumList > first" NumberingExpression="^#.^t" NumberingLevel="1" BulletsAndNumberingListType="NumberedList" LeftIndent="20"> + <Properties> + <BasedOn type="object">$ID/NormalParagraphStyle</BasedOn> + </Properties> + </ParagraphStyle> + <ParagraphStyle Self="ParagraphStyle/DefListDef > Paragraph" Name="DefListDef > Paragraph" LeftIndent="10"> + <Properties> + <BasedOn type="object">$ID/NormalParagraphStyle</BasedOn> + </Properties> + </ParagraphStyle> + <ParagraphStyle Self="ParagraphStyle/DefListTerm" Name="DefListTerm" LeftIndent="0" BulletsAndNumberingListType="BulletList" FontStyle="Bold"> + <Properties> + <BasedOn type="object">$ID/NormalParagraphStyle</BasedOn> + </Properties> + </ParagraphStyle> + <ParagraphStyle Self="ParagraphStyle/Footnote > CodeBlock" Name="Footnote > CodeBlock" LeftIndent="0"> + <Properties> + <BasedOn type="object">$ID/NormalParagraphStyle</BasedOn> + <AppliedFont type="string">Courier New</AppliedFont> + </Properties> + </ParagraphStyle> + <ParagraphStyle Self="ParagraphStyle/Footnote > Paragraph" Name="Footnote > Paragraph" LeftIndent="0"> + <Properties> + <BasedOn type="object">$ID/NormalParagraphStyle</BasedOn> + </Properties> + </ParagraphStyle> + <ParagraphStyle Self="ParagraphStyle/Header1" Name="Header1" LeftIndent="0" PointSize="36"> + <Properties> + <BasedOn type="object">$ID/NormalParagraphStyle</BasedOn> + </Properties> + </ParagraphStyle> + <ParagraphStyle Self="ParagraphStyle/Header2" Name="Header2" LeftIndent="0" PointSize="30"> + <Properties> + <BasedOn type="object">$ID/NormalParagraphStyle</BasedOn> + </Properties> + </ParagraphStyle> + <ParagraphStyle Self="ParagraphStyle/Header3" Name="Header3" LeftIndent="0" PointSize="24"> + <Properties> + <BasedOn type="object">$ID/NormalParagraphStyle</BasedOn> + </Properties> + </ParagraphStyle> + <ParagraphStyle Self="ParagraphStyle/Header4" Name="Header4" LeftIndent="0" PointSize="18"> + <Properties> + <BasedOn type="object">$ID/NormalParagraphStyle</BasedOn> + </Properties> + </ParagraphStyle> + <ParagraphStyle Self="ParagraphStyle/Header5" Name="Header5" LeftIndent="0" PointSize="14"> + <Properties> + <BasedOn type="object">$ID/NormalParagraphStyle</BasedOn> + </Properties> + </ParagraphStyle> + <ParagraphStyle Self="ParagraphStyle/NumList" Name="NumList" NumberingExpression="^#.^t" NumberingLevel="1" BulletsAndNumberingListType="NumberedList" LeftIndent="0"> + <Properties> + <BasedOn type="object">$ID/NormalParagraphStyle</BasedOn> + </Properties> + </ParagraphStyle> + <ParagraphStyle Self="ParagraphStyle/NumList > BulList" Name="NumList > BulList" BulletsAndNumberingListType="BulletList" LeftIndent="10"> + <Properties> + <BasedOn type="object">$ID/NormalParagraphStyle</BasedOn> + <TabList type="list"> + <ListItem type="record"> + <Alignment type="enumeration">LeftAlign</Alignment> + <AlignmentCharacter type="string">.</AlignmentCharacter> + <Leader type="string" /> + <Position type="unit">20</Position> + </ListItem> + </TabList> + </Properties> + </ParagraphStyle> + <ParagraphStyle Self="ParagraphStyle/NumList > BulList > first" Name="NumList > BulList > first" BulletsAndNumberingListType="BulletList" LeftIndent="10"> + <Properties> + <BasedOn type="object">$ID/NormalParagraphStyle</BasedOn> + <TabList type="list"> + <ListItem type="record"> + <Alignment type="enumeration">LeftAlign</Alignment> + <AlignmentCharacter type="string">.</AlignmentCharacter> + <Leader type="string" /> + <Position type="unit">20</Position> + </ListItem> + </TabList> + </Properties> + </ParagraphStyle> + <ParagraphStyle Self="ParagraphStyle/NumList > NumList > NumList > NumList > first > beginsWith-3 > lowerAlpha" Name="NumList > NumList > NumList > NumList > first > beginsWith-3 > lowerAlpha" NumberingExpression="^#.^t" NumberingLevel="4" BulletsAndNumberingListType="NumberedList" LeftIndent="30"> + <Properties> + <BasedOn type="object">$ID/NormalParagraphStyle</BasedOn> + <NumberingFormat type="string">a, b, c, d...</NumberingFormat> + </Properties> + </ParagraphStyle> + <ParagraphStyle Self="ParagraphStyle/NumList > NumList > NumList > first > beginsWith-6" Name="NumList > NumList > NumList > first > beginsWith-6" NumberingExpression="^#.^t" NumberingLevel="3" BulletsAndNumberingListType="NumberedList" LeftIndent="20"> + <Properties> + <BasedOn type="object">$ID/NormalParagraphStyle</BasedOn> + </Properties> + </ParagraphStyle> + <ParagraphStyle Self="ParagraphStyle/NumList > NumList > NumList > first > upperAlpha" Name="NumList > NumList > NumList > first > upperAlpha" NumberingExpression="^#.^t" NumberingLevel="3" BulletsAndNumberingListType="NumberedList" LeftIndent="20"> + <Properties> + <BasedOn type="object">$ID/NormalParagraphStyle</BasedOn> + <NumberingFormat type="string">A, B, C, D...</NumberingFormat> + </Properties> + </ParagraphStyle> + <ParagraphStyle Self="ParagraphStyle/NumList > NumList > NumList > upperAlpha" Name="NumList > NumList > NumList > upperAlpha" NumberingExpression="^#.^t" NumberingLevel="3" BulletsAndNumberingListType="NumberedList" LeftIndent="20"> + <Properties> + <BasedOn type="object">$ID/NormalParagraphStyle</BasedOn> + <NumberingFormat type="string">A, B, C, D...</NumberingFormat> + </Properties> + </ParagraphStyle> + <ParagraphStyle Self="ParagraphStyle/NumList > NumList > beginsWith-4 > lowerRoman" Name="NumList > NumList > beginsWith-4 > lowerRoman" NumberingExpression="^#.^t" NumberingLevel="2" BulletsAndNumberingListType="NumberedList" LeftIndent="10"> + <Properties> + <BasedOn type="object">$ID/NormalParagraphStyle</BasedOn> + <NumberingFormat type="string">i, ii, iii, iv...</NumberingFormat> + </Properties> + </ParagraphStyle> + <ParagraphStyle Self="ParagraphStyle/NumList > NumList > first" Name="NumList > NumList > first" NumberingExpression="^#.^t" NumberingLevel="2" BulletsAndNumberingListType="NumberedList" LeftIndent="10"> + <Properties> + <BasedOn type="object">$ID/NormalParagraphStyle</BasedOn> + </Properties> + </ParagraphStyle> + <ParagraphStyle Self="ParagraphStyle/NumList > NumList > first > beginsWith-4 > lowerRoman" Name="NumList > NumList > first > beginsWith-4 > lowerRoman" NumberingExpression="^#.^t" NumberingLevel="2" BulletsAndNumberingListType="NumberedList" LeftIndent="10"> + <Properties> + <BasedOn type="object">$ID/NormalParagraphStyle</BasedOn> + <NumberingFormat type="string">i, ii, iii, iv...</NumberingFormat> + </Properties> + </ParagraphStyle> + <ParagraphStyle Self="ParagraphStyle/NumList > NumList > first > upperRoman" Name="NumList > NumList > first > upperRoman" NumberingExpression="^#.^t" NumberingLevel="2" BulletsAndNumberingListType="NumberedList" LeftIndent="10"> + <Properties> + <BasedOn type="object">$ID/NormalParagraphStyle</BasedOn> + <NumberingFormat type="string">I, II, III, IV...</NumberingFormat> + </Properties> + </ParagraphStyle> + <ParagraphStyle Self="ParagraphStyle/NumList > Paragraph" Name="NumList > Paragraph" NumberingExpression="^#.^t" NumberingLevel="1" BulletsAndNumberingListType="NumberedList" LeftIndent="0"> + <Properties> + <BasedOn type="object">$ID/NormalParagraphStyle</BasedOn> + </Properties> + </ParagraphStyle> + <ParagraphStyle Self="ParagraphStyle/NumList > beginsWith-2 > Paragraph" Name="NumList > beginsWith-2 > Paragraph" NumberingExpression="^#.^t" NumberingLevel="1" BulletsAndNumberingListType="NumberedList" LeftIndent="0"> + <Properties> + <BasedOn type="object">$ID/NormalParagraphStyle</BasedOn> + </Properties> + </ParagraphStyle> + <ParagraphStyle Self="ParagraphStyle/NumList > first" Name="NumList > first" NumberingExpression="^#.^t" NumberingLevel="1" BulletsAndNumberingListType="NumberedList" LeftIndent="0"> + <Properties> + <BasedOn type="object">$ID/NormalParagraphStyle</BasedOn> + </Properties> + </ParagraphStyle> + <ParagraphStyle Self="ParagraphStyle/NumList > first > Paragraph" Name="NumList > first > Paragraph" NumberingExpression="^#.^t" NumberingLevel="1" BulletsAndNumberingListType="NumberedList" LeftIndent="0"> + <Properties> + <BasedOn type="object">$ID/NormalParagraphStyle</BasedOn> + </Properties> + </ParagraphStyle> + <ParagraphStyle Self="ParagraphStyle/NumList > first > beginsWith-2" Name="NumList > first > beginsWith-2" NumberingExpression="^#.^t" NumberingLevel="1" BulletsAndNumberingListType="NumberedList" LeftIndent="0"> + <Properties> + <BasedOn type="object">$ID/NormalParagraphStyle</BasedOn> + </Properties> + </ParagraphStyle> + <ParagraphStyle Self="ParagraphStyle/NumList > first > upperAlpha" Name="NumList > first > upperAlpha" NumberingExpression="^#.^t" NumberingLevel="1" BulletsAndNumberingListType="NumberedList" LeftIndent="0"> + <Properties> + <BasedOn type="object">$ID/NormalParagraphStyle</BasedOn> + <NumberingFormat type="string">A, B, C, D...</NumberingFormat> + </Properties> + </ParagraphStyle> + <ParagraphStyle Self="ParagraphStyle/NumList > subParagraph > Paragraph" Name="NumList > subParagraph > Paragraph" NumberingExpression="^#.^t" NumberingLevel="1" LeftIndent="0"> + <Properties> + <BasedOn type="object">$ID/NormalParagraphStyle</BasedOn> + </Properties> + </ParagraphStyle> + <ParagraphStyle Self="ParagraphStyle/Paragraph" Name="Paragraph" LeftIndent="0"> + <Properties> + <BasedOn type="object">$ID/NormalParagraphStyle</BasedOn> + </Properties> + </ParagraphStyle> + <ParagraphStyle Self="ParagraphStyle/Rawblock" Name="Rawblock" LeftIndent="0"> + <Properties> + <BasedOn type="object">$ID/NormalParagraphStyle</BasedOn> + </Properties> + </ParagraphStyle> + </RootParagraphStyleGroup> + <RootTableStyleGroup Self="pandoc_table_styles"> + <TableStyle Self="TableStyle/Table" Name="Table" /> + </RootTableStyleGroup> + <RootCellStyleGroup Self="pandoc_cell_styles"> + <CellStyle Self="CellStyle/Cell" AppliedParagraphStyle="ParagraphStyle/$ID/[No paragraph style]" Name="Cell" /> + </RootCellStyleGroup> + <Story Self="pandoc_story" + TrackChanges="false" + StoryTitle="" + AppliedTOCStyle="n" + AppliedNamedGrid="n" > + <StoryPreference OpticalMarginAlignment="true" OpticalMarginSize="12" /> + +<!-- body needs to be non-indented, otherwise code blocks are indented too far --> +<ParagraphStyleRange AppliedParagraphStyle="ParagraphStyle/Paragraph"> + <CharacterStyleRange AppliedCharacterStyle="$ID/NormalCharacterStyle"> + <Content>This is a set of tests for pandoc. Most of them are adapted from John Gruber’s markdown test suite.</Content> + </CharacterStyleRange><Br /> +</ParagraphStyleRange> +<ParagraphStyleRange AppliedParagraphStyle="ParagraphStyle/Header1"> + <CharacterStyleRange AppliedCharacterStyle="$ID/NormalCharacterStyle"> + <Content>Headers</Content> + </CharacterStyleRange><Br /> +</ParagraphStyleRange> +<ParagraphStyleRange AppliedParagraphStyle="ParagraphStyle/Header2"> + <CharacterStyleRange AppliedCharacterStyle="$ID/NormalCharacterStyle"> + <Content>Level 2 with an </Content> + </CharacterStyleRange> + <HyperlinkTextSource Self="htss-1" Name="" Hidden="false"> + <CharacterStyleRange AppliedCharacterStyle="CharacterStyle/Link"> + <Content>embedded link</Content> + </CharacterStyleRange> + </HyperlinkTextSource><Br /> +</ParagraphStyleRange> +<ParagraphStyleRange AppliedParagraphStyle="ParagraphStyle/Header3"> + <CharacterStyleRange AppliedCharacterStyle="$ID/NormalCharacterStyle"> + <Content>Level 3 with </Content> + </CharacterStyleRange> + <CharacterStyleRange AppliedCharacterStyle="CharacterStyle/Italic"> + <Content>emphasis</Content> + </CharacterStyleRange><Br /> +</ParagraphStyleRange> +<ParagraphStyleRange AppliedParagraphStyle="ParagraphStyle/Header4"> + <CharacterStyleRange AppliedCharacterStyle="$ID/NormalCharacterStyle"> + <Content>Level 4</Content> + </CharacterStyleRange><Br /> +</ParagraphStyleRange> +<ParagraphStyleRange AppliedParagraphStyle="ParagraphStyle/Header5"> + <CharacterStyleRange AppliedCharacterStyle="$ID/NormalCharacterStyle"> + <Content>Level 5</Content> + </CharacterStyleRange><Br /> +</ParagraphStyleRange> +<ParagraphStyleRange AppliedParagraphStyle="ParagraphStyle/Header1"> + <CharacterStyleRange AppliedCharacterStyle="$ID/NormalCharacterStyle"> + <Content>Level 1</Content> + </CharacterStyleRange><Br /> +</ParagraphStyleRange> +<ParagraphStyleRange AppliedParagraphStyle="ParagraphStyle/Header2"> + <CharacterStyleRange AppliedCharacterStyle="$ID/NormalCharacterStyle"> + <Content>Level 2 with </Content> + </CharacterStyleRange> + <CharacterStyleRange AppliedCharacterStyle="CharacterStyle/Italic"> + <Content>emphasis</Content> + </CharacterStyleRange><Br /> +</ParagraphStyleRange> +<ParagraphStyleRange AppliedParagraphStyle="ParagraphStyle/Header3"> + <CharacterStyleRange AppliedCharacterStyle="$ID/NormalCharacterStyle"> + <Content>Level 3</Content> + </CharacterStyleRange><Br /> +</ParagraphStyleRange> +<ParagraphStyleRange AppliedParagraphStyle="ParagraphStyle/Paragraph"> + <CharacterStyleRange AppliedCharacterStyle="$ID/NormalCharacterStyle"> + <Content>with no blank line</Content> + </CharacterStyleRange><Br /> +</ParagraphStyleRange> +<ParagraphStyleRange AppliedParagraphStyle="ParagraphStyle/Header2"> + <CharacterStyleRange AppliedCharacterStyle="$ID/NormalCharacterStyle"> + <Content>Level 2</Content> + </CharacterStyleRange><Br /> +</ParagraphStyleRange> +<ParagraphStyleRange AppliedParagraphStyle="ParagraphStyle/Paragraph"> + <CharacterStyleRange AppliedCharacterStyle="$ID/NormalCharacterStyle"> + <Content>with no blank line</Content> + </CharacterStyleRange><Br /> +</ParagraphStyleRange> +<ParagraphStyleRange AppliedParagraphStyle="ParagraphStyle/Header1"> + <CharacterStyleRange AppliedCharacterStyle="$ID/NormalCharacterStyle"> + <Content>Paragraphs</Content> + </CharacterStyleRange><Br /> +</ParagraphStyleRange> +<ParagraphStyleRange AppliedParagraphStyle="ParagraphStyle/Paragraph"> + <CharacterStyleRange AppliedCharacterStyle="$ID/NormalCharacterStyle"> + <Content>Here’s a regular paragraph.</Content> + </CharacterStyleRange><Br /> +</ParagraphStyleRange> +<ParagraphStyleRange AppliedParagraphStyle="ParagraphStyle/Paragraph"> + <CharacterStyleRange AppliedCharacterStyle="$ID/NormalCharacterStyle"> + <Content>In Markdown 1.0.0 and earlier. Version 8. This line turns into a list item. Because a hard-wrapped line in the middle of a paragraph looked like a list item.</Content> + </CharacterStyleRange><Br /> +</ParagraphStyleRange> +<ParagraphStyleRange AppliedParagraphStyle="ParagraphStyle/Paragraph"> + <CharacterStyleRange AppliedCharacterStyle="$ID/NormalCharacterStyle"> + <Content>Here’s one with a bullet. * criminey.</Content> + </CharacterStyleRange><Br /> +</ParagraphStyleRange> +<ParagraphStyleRange AppliedParagraphStyle="ParagraphStyle/Paragraph"> + <CharacterStyleRange AppliedCharacterStyle="$ID/NormalCharacterStyle"> + <Content>There should be a hard line break</Content> + </CharacterStyleRange> + <CharacterStyleRange AppliedCharacterStyle="$ID/NormalCharacterStyle"> + <Content>
</Content> + </CharacterStyleRange> + <CharacterStyleRange AppliedCharacterStyle="$ID/NormalCharacterStyle"> + <Content>here.</Content> + </CharacterStyleRange><Br /> +</ParagraphStyleRange> +<ParagraphStyleRange AppliedParagraphStyle="ParagraphStyle/Header1"> + <CharacterStyleRange AppliedCharacterStyle="$ID/NormalCharacterStyle"> + <Content>Block Quotes</Content> + </CharacterStyleRange><Br /> +</ParagraphStyleRange> +<ParagraphStyleRange AppliedParagraphStyle="ParagraphStyle/Paragraph"> + <CharacterStyleRange AppliedCharacterStyle="$ID/NormalCharacterStyle"> + <Content>E-mail style:</Content> + </CharacterStyleRange><Br /> +</ParagraphStyleRange> +<ParagraphStyleRange AppliedParagraphStyle="ParagraphStyle/Blockquote > Paragraph"> + <CharacterStyleRange AppliedCharacterStyle="$ID/NormalCharacterStyle"> + <Content>This is a block quote. It is pretty short.</Content> + </CharacterStyleRange><Br /> +</ParagraphStyleRange> +<ParagraphStyleRange AppliedParagraphStyle="ParagraphStyle/Blockquote > Paragraph"> + <CharacterStyleRange AppliedCharacterStyle="$ID/NormalCharacterStyle"> + <Content>Code in a block quote:</Content> + </CharacterStyleRange><Br /> +</ParagraphStyleRange> +<ParagraphStyleRange AppliedParagraphStyle="ParagraphStyle/Blockquote > CodeBlock"> + <CharacterStyleRange AppliedCharacterStyle="$ID/NormalCharacterStyle"> + <Content>sub status { + print "working"; +}</Content> + </CharacterStyleRange><Br /> +</ParagraphStyleRange> +<ParagraphStyleRange AppliedParagraphStyle="ParagraphStyle/Blockquote > Paragraph"> + <CharacterStyleRange AppliedCharacterStyle="$ID/NormalCharacterStyle"> + <Content>A list:</Content> + </CharacterStyleRange><Br /> +</ParagraphStyleRange> +<ParagraphStyleRange AppliedParagraphStyle="ParagraphStyle/Blockquote > NumList > first" NumberingContinue="false"> + <CharacterStyleRange AppliedCharacterStyle="$ID/NormalCharacterStyle"> + <Content>item one</Content> + </CharacterStyleRange><Br /> +</ParagraphStyleRange> +<ParagraphStyleRange AppliedParagraphStyle="ParagraphStyle/Blockquote > NumList"> + <CharacterStyleRange AppliedCharacterStyle="$ID/NormalCharacterStyle"> + <Content>item two</Content> + </CharacterStyleRange><Br /> +</ParagraphStyleRange> +<ParagraphStyleRange AppliedParagraphStyle="ParagraphStyle/Blockquote > Paragraph"> + <CharacterStyleRange AppliedCharacterStyle="$ID/NormalCharacterStyle"> + <Content>Nested block quotes:</Content> + </CharacterStyleRange><Br /> +</ParagraphStyleRange> +<ParagraphStyleRange AppliedParagraphStyle="ParagraphStyle/Blockquote > Blockquote > Paragraph"> + <CharacterStyleRange AppliedCharacterStyle="$ID/NormalCharacterStyle"> + <Content>nested</Content> + </CharacterStyleRange><Br /> +</ParagraphStyleRange> +<ParagraphStyleRange AppliedParagraphStyle="ParagraphStyle/Blockquote > Blockquote > Paragraph"> + <CharacterStyleRange AppliedCharacterStyle="$ID/NormalCharacterStyle"> + <Content>nested</Content> + </CharacterStyleRange><Br /> +</ParagraphStyleRange> +<ParagraphStyleRange AppliedParagraphStyle="ParagraphStyle/Paragraph"> + <CharacterStyleRange AppliedCharacterStyle="$ID/NormalCharacterStyle"> + <Content>This should not be a block quote: 2 > 1.</Content> + </CharacterStyleRange><Br /> +</ParagraphStyleRange> +<ParagraphStyleRange AppliedParagraphStyle="ParagraphStyle/Paragraph"> + <CharacterStyleRange AppliedCharacterStyle="$ID/NormalCharacterStyle"> + <Content>And a following paragraph.</Content> + </CharacterStyleRange><Br /> +</ParagraphStyleRange> +<ParagraphStyleRange AppliedParagraphStyle="ParagraphStyle/Header1"> + <CharacterStyleRange AppliedCharacterStyle="$ID/NormalCharacterStyle"> + <Content>Code Blocks</Content> + </CharacterStyleRange><Br /> +</ParagraphStyleRange> +<ParagraphStyleRange AppliedParagraphStyle="ParagraphStyle/Paragraph"> + <CharacterStyleRange AppliedCharacterStyle="$ID/NormalCharacterStyle"> + <Content>Code:</Content> + </CharacterStyleRange><Br /> +</ParagraphStyleRange> +<ParagraphStyleRange AppliedParagraphStyle="ParagraphStyle/CodeBlock"> + <CharacterStyleRange AppliedCharacterStyle="$ID/NormalCharacterStyle"> + <Content>---- (should be four hyphens) + +sub status { + print "working"; +} + +this code block is indented by one tab</Content> + </CharacterStyleRange><Br /> +</ParagraphStyleRange> +<ParagraphStyleRange AppliedParagraphStyle="ParagraphStyle/Paragraph"> + <CharacterStyleRange AppliedCharacterStyle="$ID/NormalCharacterStyle"> + <Content>And:</Content> + </CharacterStyleRange><Br /> +</ParagraphStyleRange> +<ParagraphStyleRange AppliedParagraphStyle="ParagraphStyle/CodeBlock"> + <CharacterStyleRange AppliedCharacterStyle="$ID/NormalCharacterStyle"> + <Content> this code block is indented by two tabs + +These should not be escaped: \$ \\ \> \[ \{</Content> + </CharacterStyleRange><Br /> +</ParagraphStyleRange> +<ParagraphStyleRange AppliedParagraphStyle="ParagraphStyle/Header1"> + <CharacterStyleRange AppliedCharacterStyle="$ID/NormalCharacterStyle"> + <Content>Lists</Content> + </CharacterStyleRange><Br /> +</ParagraphStyleRange> +<ParagraphStyleRange AppliedParagraphStyle="ParagraphStyle/Header2"> + <CharacterStyleRange AppliedCharacterStyle="$ID/NormalCharacterStyle"> + <Content>Unordered</Content> + </CharacterStyleRange><Br /> +</ParagraphStyleRange> +<ParagraphStyleRange AppliedParagraphStyle="ParagraphStyle/Paragraph"> + <CharacterStyleRange AppliedCharacterStyle="$ID/NormalCharacterStyle"> + <Content>Asterisks tight:</Content> + </CharacterStyleRange><Br /> +</ParagraphStyleRange> +<ParagraphStyleRange AppliedParagraphStyle="ParagraphStyle/BulList > first" NumberingContinue="false"> + <CharacterStyleRange AppliedCharacterStyle="$ID/NormalCharacterStyle"> + <Content>asterisk 1</Content> + </CharacterStyleRange><Br /> +</ParagraphStyleRange> +<ParagraphStyleRange AppliedParagraphStyle="ParagraphStyle/BulList"> + <CharacterStyleRange AppliedCharacterStyle="$ID/NormalCharacterStyle"> + <Content>asterisk 2</Content> + </CharacterStyleRange><Br /> +</ParagraphStyleRange> +<ParagraphStyleRange AppliedParagraphStyle="ParagraphStyle/BulList"> + <CharacterStyleRange AppliedCharacterStyle="$ID/NormalCharacterStyle"> + <Content>asterisk 3</Content> + </CharacterStyleRange><Br /> +</ParagraphStyleRange> +<ParagraphStyleRange AppliedParagraphStyle="ParagraphStyle/Paragraph"> + <CharacterStyleRange AppliedCharacterStyle="$ID/NormalCharacterStyle"> + <Content>Asterisks loose:</Content> + </CharacterStyleRange><Br /> +</ParagraphStyleRange> +<ParagraphStyleRange AppliedParagraphStyle="ParagraphStyle/BulList > first > Paragraph" NumberingContinue="false"> + <CharacterStyleRange AppliedCharacterStyle="$ID/NormalCharacterStyle"> + <Content>asterisk 1</Content> + </CharacterStyleRange><Br /> +</ParagraphStyleRange> +<ParagraphStyleRange AppliedParagraphStyle="ParagraphStyle/BulList > Paragraph"> + <CharacterStyleRange AppliedCharacterStyle="$ID/NormalCharacterStyle"> + <Content>asterisk 2</Content> + </CharacterStyleRange><Br /> +</ParagraphStyleRange> +<ParagraphStyleRange AppliedParagraphStyle="ParagraphStyle/BulList > Paragraph"> + <CharacterStyleRange AppliedCharacterStyle="$ID/NormalCharacterStyle"> + <Content>asterisk 3</Content> + </CharacterStyleRange><Br /> +</ParagraphStyleRange> +<ParagraphStyleRange AppliedParagraphStyle="ParagraphStyle/Paragraph"> + <CharacterStyleRange AppliedCharacterStyle="$ID/NormalCharacterStyle"> + <Content>Pluses tight:</Content> + </CharacterStyleRange><Br /> +</ParagraphStyleRange> +<ParagraphStyleRange AppliedParagraphStyle="ParagraphStyle/BulList > first" NumberingContinue="false"> + <CharacterStyleRange AppliedCharacterStyle="$ID/NormalCharacterStyle"> + <Content>Plus 1</Content> + </CharacterStyleRange><Br /> +</ParagraphStyleRange> +<ParagraphStyleRange AppliedParagraphStyle="ParagraphStyle/BulList"> + <CharacterStyleRange AppliedCharacterStyle="$ID/NormalCharacterStyle"> + <Content>Plus 2</Content> + </CharacterStyleRange><Br /> +</ParagraphStyleRange> +<ParagraphStyleRange AppliedParagraphStyle="ParagraphStyle/BulList"> + <CharacterStyleRange AppliedCharacterStyle="$ID/NormalCharacterStyle"> + <Content>Plus 3</Content> + </CharacterStyleRange><Br /> +</ParagraphStyleRange> +<ParagraphStyleRange AppliedParagraphStyle="ParagraphStyle/Paragraph"> + <CharacterStyleRange AppliedCharacterStyle="$ID/NormalCharacterStyle"> + <Content>Pluses loose:</Content> + </CharacterStyleRange><Br /> +</ParagraphStyleRange> +<ParagraphStyleRange AppliedParagraphStyle="ParagraphStyle/BulList > first > Paragraph" NumberingContinue="false"> + <CharacterStyleRange AppliedCharacterStyle="$ID/NormalCharacterStyle"> + <Content>Plus 1</Content> + </CharacterStyleRange><Br /> +</ParagraphStyleRange> +<ParagraphStyleRange AppliedParagraphStyle="ParagraphStyle/BulList > Paragraph"> + <CharacterStyleRange AppliedCharacterStyle="$ID/NormalCharacterStyle"> + <Content>Plus 2</Content> + </CharacterStyleRange><Br /> +</ParagraphStyleRange> +<ParagraphStyleRange AppliedParagraphStyle="ParagraphStyle/BulList > Paragraph"> + <CharacterStyleRange AppliedCharacterStyle="$ID/NormalCharacterStyle"> + <Content>Plus 3</Content> + </CharacterStyleRange><Br /> +</ParagraphStyleRange> +<ParagraphStyleRange AppliedParagraphStyle="ParagraphStyle/Paragraph"> + <CharacterStyleRange AppliedCharacterStyle="$ID/NormalCharacterStyle"> + <Content>Minuses tight:</Content> + </CharacterStyleRange><Br /> +</ParagraphStyleRange> +<ParagraphStyleRange AppliedParagraphStyle="ParagraphStyle/BulList > first" NumberingContinue="false"> + <CharacterStyleRange AppliedCharacterStyle="$ID/NormalCharacterStyle"> + <Content>Minus 1</Content> + </CharacterStyleRange><Br /> +</ParagraphStyleRange> +<ParagraphStyleRange AppliedParagraphStyle="ParagraphStyle/BulList"> + <CharacterStyleRange AppliedCharacterStyle="$ID/NormalCharacterStyle"> + <Content>Minus 2</Content> + </CharacterStyleRange><Br /> +</ParagraphStyleRange> +<ParagraphStyleRange AppliedParagraphStyle="ParagraphStyle/BulList"> + <CharacterStyleRange AppliedCharacterStyle="$ID/NormalCharacterStyle"> + <Content>Minus 3</Content> + </CharacterStyleRange><Br /> +</ParagraphStyleRange> +<ParagraphStyleRange AppliedParagraphStyle="ParagraphStyle/Paragraph"> + <CharacterStyleRange AppliedCharacterStyle="$ID/NormalCharacterStyle"> + <Content>Minuses loose:</Content> + </CharacterStyleRange><Br /> +</ParagraphStyleRange> +<ParagraphStyleRange AppliedParagraphStyle="ParagraphStyle/BulList > first > Paragraph" NumberingContinue="false"> + <CharacterStyleRange AppliedCharacterStyle="$ID/NormalCharacterStyle"> + <Content>Minus 1</Content> + </CharacterStyleRange><Br /> +</ParagraphStyleRange> +<ParagraphStyleRange AppliedParagraphStyle="ParagraphStyle/BulList > Paragraph"> + <CharacterStyleRange AppliedCharacterStyle="$ID/NormalCharacterStyle"> + <Content>Minus 2</Content> + </CharacterStyleRange><Br /> +</ParagraphStyleRange> +<ParagraphStyleRange AppliedParagraphStyle="ParagraphStyle/BulList > Paragraph"> + <CharacterStyleRange AppliedCharacterStyle="$ID/NormalCharacterStyle"> + <Content>Minus 3</Content> + </CharacterStyleRange><Br /> +</ParagraphStyleRange> +<ParagraphStyleRange AppliedParagraphStyle="ParagraphStyle/Header2"> + <CharacterStyleRange AppliedCharacterStyle="$ID/NormalCharacterStyle"> + <Content>Ordered</Content> + </CharacterStyleRange><Br /> +</ParagraphStyleRange> +<ParagraphStyleRange AppliedParagraphStyle="ParagraphStyle/Paragraph"> + <CharacterStyleRange AppliedCharacterStyle="$ID/NormalCharacterStyle"> + <Content>Tight:</Content> + </CharacterStyleRange><Br /> +</ParagraphStyleRange> +<ParagraphStyleRange AppliedParagraphStyle="ParagraphStyle/NumList > first" NumberingContinue="false"> + <CharacterStyleRange AppliedCharacterStyle="$ID/NormalCharacterStyle"> + <Content>First</Content> + </CharacterStyleRange><Br /> +</ParagraphStyleRange> +<ParagraphStyleRange AppliedParagraphStyle="ParagraphStyle/NumList"> + <CharacterStyleRange AppliedCharacterStyle="$ID/NormalCharacterStyle"> + <Content>Second</Content> + </CharacterStyleRange><Br /> +</ParagraphStyleRange> +<ParagraphStyleRange AppliedParagraphStyle="ParagraphStyle/NumList"> + <CharacterStyleRange AppliedCharacterStyle="$ID/NormalCharacterStyle"> + <Content>Third</Content> + </CharacterStyleRange><Br /> +</ParagraphStyleRange> +<ParagraphStyleRange AppliedParagraphStyle="ParagraphStyle/Paragraph"> + <CharacterStyleRange AppliedCharacterStyle="$ID/NormalCharacterStyle"> + <Content>and:</Content> + </CharacterStyleRange><Br /> +</ParagraphStyleRange> +<ParagraphStyleRange AppliedParagraphStyle="ParagraphStyle/NumList > first" NumberingContinue="false"> + <CharacterStyleRange AppliedCharacterStyle="$ID/NormalCharacterStyle"> + <Content>One</Content> + </CharacterStyleRange><Br /> +</ParagraphStyleRange> +<ParagraphStyleRange AppliedParagraphStyle="ParagraphStyle/NumList"> + <CharacterStyleRange AppliedCharacterStyle="$ID/NormalCharacterStyle"> + <Content>Two</Content> + </CharacterStyleRange><Br /> +</ParagraphStyleRange> +<ParagraphStyleRange AppliedParagraphStyle="ParagraphStyle/NumList"> + <CharacterStyleRange AppliedCharacterStyle="$ID/NormalCharacterStyle"> + <Content>Three</Content> + </CharacterStyleRange><Br /> +</ParagraphStyleRange> +<ParagraphStyleRange AppliedParagraphStyle="ParagraphStyle/Paragraph"> + <CharacterStyleRange AppliedCharacterStyle="$ID/NormalCharacterStyle"> + <Content>Loose using tabs:</Content> + </CharacterStyleRange><Br /> +</ParagraphStyleRange> +<ParagraphStyleRange AppliedParagraphStyle="ParagraphStyle/NumList > first > Paragraph" NumberingContinue="false"> + <CharacterStyleRange AppliedCharacterStyle="$ID/NormalCharacterStyle"> + <Content>First</Content> + </CharacterStyleRange><Br /> +</ParagraphStyleRange> +<ParagraphStyleRange AppliedParagraphStyle="ParagraphStyle/NumList > Paragraph"> + <CharacterStyleRange AppliedCharacterStyle="$ID/NormalCharacterStyle"> + <Content>Second</Content> + </CharacterStyleRange><Br /> +</ParagraphStyleRange> +<ParagraphStyleRange AppliedParagraphStyle="ParagraphStyle/NumList > Paragraph"> + <CharacterStyleRange AppliedCharacterStyle="$ID/NormalCharacterStyle"> + <Content>Third</Content> + </CharacterStyleRange><Br /> +</ParagraphStyleRange> +<ParagraphStyleRange AppliedParagraphStyle="ParagraphStyle/Paragraph"> + <CharacterStyleRange AppliedCharacterStyle="$ID/NormalCharacterStyle"> + <Content>and using spaces:</Content> + </CharacterStyleRange><Br /> +</ParagraphStyleRange> +<ParagraphStyleRange AppliedParagraphStyle="ParagraphStyle/NumList > first > Paragraph" NumberingContinue="false"> + <CharacterStyleRange AppliedCharacterStyle="$ID/NormalCharacterStyle"> + <Content>One</Content> + </CharacterStyleRange><Br /> +</ParagraphStyleRange> +<ParagraphStyleRange AppliedParagraphStyle="ParagraphStyle/NumList > Paragraph"> + <CharacterStyleRange AppliedCharacterStyle="$ID/NormalCharacterStyle"> + <Content>Two</Content> + </CharacterStyleRange><Br /> +</ParagraphStyleRange> +<ParagraphStyleRange AppliedParagraphStyle="ParagraphStyle/NumList > Paragraph"> + <CharacterStyleRange AppliedCharacterStyle="$ID/NormalCharacterStyle"> + <Content>Three</Content> + </CharacterStyleRange><Br /> +</ParagraphStyleRange> +<ParagraphStyleRange AppliedParagraphStyle="ParagraphStyle/Paragraph"> + <CharacterStyleRange AppliedCharacterStyle="$ID/NormalCharacterStyle"> + <Content>Multiple paragraphs:</Content> + </CharacterStyleRange><Br /> +</ParagraphStyleRange> +<ParagraphStyleRange AppliedParagraphStyle="ParagraphStyle/NumList > first > Paragraph" NumberingContinue="false"> + <CharacterStyleRange AppliedCharacterStyle="$ID/NormalCharacterStyle"> + <Content>Item 1, graf one.</Content> + </CharacterStyleRange><Br /> +</ParagraphStyleRange> +<ParagraphStyleRange AppliedParagraphStyle="ParagraphStyle/NumList > subParagraph > Paragraph"> + <CharacterStyleRange AppliedCharacterStyle="$ID/NormalCharacterStyle"> + <Content> </Content> + </CharacterStyleRange> + <CharacterStyleRange AppliedCharacterStyle="$ID/NormalCharacterStyle"> + <Content>Item 1. graf two. The quick brown fox jumped over the lazy dog’s back.</Content> + </CharacterStyleRange><Br /> +</ParagraphStyleRange> +<ParagraphStyleRange AppliedParagraphStyle="ParagraphStyle/NumList > Paragraph"> + <CharacterStyleRange AppliedCharacterStyle="$ID/NormalCharacterStyle"> + <Content>Item 2.</Content> + </CharacterStyleRange><Br /> +</ParagraphStyleRange> +<ParagraphStyleRange AppliedParagraphStyle="ParagraphStyle/NumList > Paragraph"> + <CharacterStyleRange AppliedCharacterStyle="$ID/NormalCharacterStyle"> + <Content>Item 3.</Content> + </CharacterStyleRange><Br /> +</ParagraphStyleRange> +<ParagraphStyleRange AppliedParagraphStyle="ParagraphStyle/Header2"> + <CharacterStyleRange AppliedCharacterStyle="$ID/NormalCharacterStyle"> + <Content>Nested</Content> + </CharacterStyleRange><Br /> +</ParagraphStyleRange> +<ParagraphStyleRange AppliedParagraphStyle="ParagraphStyle/BulList > first" NumberingContinue="false"> + <CharacterStyleRange AppliedCharacterStyle="$ID/NormalCharacterStyle"> + <Content>Tab</Content> + </CharacterStyleRange><Br /> +</ParagraphStyleRange> +<ParagraphStyleRange AppliedParagraphStyle="ParagraphStyle/BulList > BulList > first" NumberingContinue="false"> + <CharacterStyleRange AppliedCharacterStyle="$ID/NormalCharacterStyle"> + <Content>Tab</Content> + </CharacterStyleRange><Br /> +</ParagraphStyleRange> +<ParagraphStyleRange AppliedParagraphStyle="ParagraphStyle/BulList > BulList > BulList > first" NumberingContinue="false"> + <CharacterStyleRange AppliedCharacterStyle="$ID/NormalCharacterStyle"> + <Content>Tab</Content> + </CharacterStyleRange><Br /> +</ParagraphStyleRange> +<ParagraphStyleRange AppliedParagraphStyle="ParagraphStyle/Paragraph"> + <CharacterStyleRange AppliedCharacterStyle="$ID/NormalCharacterStyle"> + <Content>Here’s another:</Content> + </CharacterStyleRange><Br /> +</ParagraphStyleRange> +<ParagraphStyleRange AppliedParagraphStyle="ParagraphStyle/NumList > first" NumberingContinue="false"> + <CharacterStyleRange AppliedCharacterStyle="$ID/NormalCharacterStyle"> + <Content>First</Content> + </CharacterStyleRange><Br /> +</ParagraphStyleRange> +<ParagraphStyleRange AppliedParagraphStyle="ParagraphStyle/NumList"> + <CharacterStyleRange AppliedCharacterStyle="$ID/NormalCharacterStyle"> + <Content>Second:</Content> + </CharacterStyleRange><Br /> +</ParagraphStyleRange> +<ParagraphStyleRange AppliedParagraphStyle="ParagraphStyle/NumList > BulList > first" NumberingContinue="false"> + <CharacterStyleRange AppliedCharacterStyle="$ID/NormalCharacterStyle"> + <Content>Fee</Content> + </CharacterStyleRange><Br /> +</ParagraphStyleRange> +<ParagraphStyleRange AppliedParagraphStyle="ParagraphStyle/NumList > BulList"> + <CharacterStyleRange AppliedCharacterStyle="$ID/NormalCharacterStyle"> + <Content>Fie</Content> + </CharacterStyleRange><Br /> +</ParagraphStyleRange> +<ParagraphStyleRange AppliedParagraphStyle="ParagraphStyle/NumList > BulList"> + <CharacterStyleRange AppliedCharacterStyle="$ID/NormalCharacterStyle"> + <Content>Foe</Content> + </CharacterStyleRange><Br /> +</ParagraphStyleRange> +<ParagraphStyleRange AppliedParagraphStyle="ParagraphStyle/NumList"> + <CharacterStyleRange AppliedCharacterStyle="$ID/NormalCharacterStyle"> + <Content>Third</Content> + </CharacterStyleRange><Br /> +</ParagraphStyleRange> +<ParagraphStyleRange AppliedParagraphStyle="ParagraphStyle/Paragraph"> + <CharacterStyleRange AppliedCharacterStyle="$ID/NormalCharacterStyle"> + <Content>Same thing but with paragraphs:</Content> + </CharacterStyleRange><Br /> +</ParagraphStyleRange> +<ParagraphStyleRange AppliedParagraphStyle="ParagraphStyle/NumList > first > Paragraph" NumberingContinue="false"> + <CharacterStyleRange AppliedCharacterStyle="$ID/NormalCharacterStyle"> + <Content>First</Content> + </CharacterStyleRange><Br /> +</ParagraphStyleRange> +<ParagraphStyleRange AppliedParagraphStyle="ParagraphStyle/NumList > Paragraph"> + <CharacterStyleRange AppliedCharacterStyle="$ID/NormalCharacterStyle"> + <Content>Second:</Content> + </CharacterStyleRange><Br /> +</ParagraphStyleRange> +<ParagraphStyleRange AppliedParagraphStyle="ParagraphStyle/NumList > BulList > first" NumberingContinue="false"> + <CharacterStyleRange AppliedCharacterStyle="$ID/NormalCharacterStyle"> + <Content>Fee</Content> + </CharacterStyleRange><Br /> +</ParagraphStyleRange> +<ParagraphStyleRange AppliedParagraphStyle="ParagraphStyle/NumList > BulList"> + <CharacterStyleRange AppliedCharacterStyle="$ID/NormalCharacterStyle"> + <Content>Fie</Content> + </CharacterStyleRange><Br /> +</ParagraphStyleRange> +<ParagraphStyleRange AppliedParagraphStyle="ParagraphStyle/NumList > BulList"> + <CharacterStyleRange AppliedCharacterStyle="$ID/NormalCharacterStyle"> + <Content>Foe</Content> + </CharacterStyleRange><Br /> +</ParagraphStyleRange> +<ParagraphStyleRange AppliedParagraphStyle="ParagraphStyle/NumList > Paragraph"> + <CharacterStyleRange AppliedCharacterStyle="$ID/NormalCharacterStyle"> + <Content>Third</Content> + </CharacterStyleRange><Br /> +</ParagraphStyleRange> +<ParagraphStyleRange AppliedParagraphStyle="ParagraphStyle/Header2"> + <CharacterStyleRange AppliedCharacterStyle="$ID/NormalCharacterStyle"> + <Content>Tabs and spaces</Content> + </CharacterStyleRange><Br /> +</ParagraphStyleRange> +<ParagraphStyleRange AppliedParagraphStyle="ParagraphStyle/BulList > first > Paragraph" NumberingContinue="false"> + <CharacterStyleRange AppliedCharacterStyle="$ID/NormalCharacterStyle"> + <Content>this is a list item indented with tabs</Content> + </CharacterStyleRange><Br /> +</ParagraphStyleRange> +<ParagraphStyleRange AppliedParagraphStyle="ParagraphStyle/BulList > Paragraph"> + <CharacterStyleRange AppliedCharacterStyle="$ID/NormalCharacterStyle"> + <Content>this is a list item indented with spaces</Content> + </CharacterStyleRange><Br /> +</ParagraphStyleRange> +<ParagraphStyleRange AppliedParagraphStyle="ParagraphStyle/BulList > BulList > first > Paragraph" NumberingContinue="false"> + <CharacterStyleRange AppliedCharacterStyle="$ID/NormalCharacterStyle"> + <Content>this is an example list item indented with tabs</Content> + </CharacterStyleRange><Br /> +</ParagraphStyleRange> +<ParagraphStyleRange AppliedParagraphStyle="ParagraphStyle/BulList > BulList > Paragraph"> + <CharacterStyleRange AppliedCharacterStyle="$ID/NormalCharacterStyle"> + <Content>this is an example list item indented with spaces</Content> + </CharacterStyleRange><Br /> +</ParagraphStyleRange> +<ParagraphStyleRange AppliedParagraphStyle="ParagraphStyle/Header2"> + <CharacterStyleRange AppliedCharacterStyle="$ID/NormalCharacterStyle"> + <Content>Fancy list markers</Content> + </CharacterStyleRange><Br /> +</ParagraphStyleRange> +<ParagraphStyleRange NumberingStartAt="2" AppliedParagraphStyle="ParagraphStyle/NumList > first > beginsWith-2" NumberingContinue="false"> + <CharacterStyleRange AppliedCharacterStyle="$ID/NormalCharacterStyle"> + <Content>begins with 2</Content> + </CharacterStyleRange><Br /> +</ParagraphStyleRange> +<ParagraphStyleRange AppliedParagraphStyle="ParagraphStyle/NumList > beginsWith-2 > Paragraph"> + <CharacterStyleRange AppliedCharacterStyle="$ID/NormalCharacterStyle"> + <Content>and now 3</Content> + </CharacterStyleRange><Br /> +</ParagraphStyleRange> +<ParagraphStyleRange AppliedParagraphStyle="ParagraphStyle/NumList > subParagraph > Paragraph"> + <CharacterStyleRange AppliedCharacterStyle="$ID/NormalCharacterStyle"> + <Content> </Content> + </CharacterStyleRange> + <CharacterStyleRange AppliedCharacterStyle="$ID/NormalCharacterStyle"> + <Content>with a continuation</Content> + </CharacterStyleRange><Br /> +</ParagraphStyleRange> +<ParagraphStyleRange NumberingStartAt="4" AppliedParagraphStyle="ParagraphStyle/NumList > NumList > first > beginsWith-4 > lowerRoman" NumberingContinue="false"> + <CharacterStyleRange AppliedCharacterStyle="$ID/NormalCharacterStyle"> + <Content>sublist with roman numerals, starting with 4</Content> + </CharacterStyleRange><Br /> +</ParagraphStyleRange> +<ParagraphStyleRange AppliedParagraphStyle="ParagraphStyle/NumList > NumList > beginsWith-4 > lowerRoman"> + <CharacterStyleRange AppliedCharacterStyle="$ID/NormalCharacterStyle"> + <Content>more items</Content> + </CharacterStyleRange><Br /> +</ParagraphStyleRange> +<ParagraphStyleRange AppliedParagraphStyle="ParagraphStyle/NumList > NumList > NumList > first > upperAlpha" NumberingContinue="false"> + <CharacterStyleRange AppliedCharacterStyle="$ID/NormalCharacterStyle"> + <Content>a subsublist</Content> + </CharacterStyleRange><Br /> +</ParagraphStyleRange> +<ParagraphStyleRange AppliedParagraphStyle="ParagraphStyle/NumList > NumList > NumList > upperAlpha"> + <CharacterStyleRange AppliedCharacterStyle="$ID/NormalCharacterStyle"> + <Content>a subsublist</Content> + </CharacterStyleRange><Br /> +</ParagraphStyleRange> +<ParagraphStyleRange AppliedParagraphStyle="ParagraphStyle/Paragraph"> + <CharacterStyleRange AppliedCharacterStyle="$ID/NormalCharacterStyle"> + <Content>Nesting:</Content> + </CharacterStyleRange><Br /> +</ParagraphStyleRange> +<ParagraphStyleRange AppliedParagraphStyle="ParagraphStyle/NumList > first > upperAlpha" NumberingContinue="false"> + <CharacterStyleRange AppliedCharacterStyle="$ID/NormalCharacterStyle"> + <Content>Upper Alpha</Content> + </CharacterStyleRange><Br /> +</ParagraphStyleRange> +<ParagraphStyleRange AppliedParagraphStyle="ParagraphStyle/NumList > NumList > first > upperRoman" NumberingContinue="false"> + <CharacterStyleRange AppliedCharacterStyle="$ID/NormalCharacterStyle"> + <Content>Upper Roman.</Content> + </CharacterStyleRange><Br /> +</ParagraphStyleRange> +<ParagraphStyleRange NumberingStartAt="6" AppliedParagraphStyle="ParagraphStyle/NumList > NumList > NumList > first > beginsWith-6" NumberingContinue="false"> + <CharacterStyleRange AppliedCharacterStyle="$ID/NormalCharacterStyle"> + <Content>Decimal start with 6</Content> + </CharacterStyleRange><Br /> +</ParagraphStyleRange> +<ParagraphStyleRange NumberingStartAt="3" AppliedParagraphStyle="ParagraphStyle/NumList > NumList > NumList > NumList > first > beginsWith-3 > lowerAlpha" NumberingContinue="false"> + <CharacterStyleRange AppliedCharacterStyle="$ID/NormalCharacterStyle"> + <Content>Lower alpha with paren</Content> + </CharacterStyleRange><Br /> +</ParagraphStyleRange> +<ParagraphStyleRange AppliedParagraphStyle="ParagraphStyle/Paragraph"> + <CharacterStyleRange AppliedCharacterStyle="$ID/NormalCharacterStyle"> + <Content>Autonumbering:</Content> + </CharacterStyleRange><Br /> +</ParagraphStyleRange> +<ParagraphStyleRange AppliedParagraphStyle="ParagraphStyle/NumList > first" NumberingContinue="false"> + <CharacterStyleRange AppliedCharacterStyle="$ID/NormalCharacterStyle"> + <Content>Autonumber.</Content> + </CharacterStyleRange><Br /> +</ParagraphStyleRange> +<ParagraphStyleRange AppliedParagraphStyle="ParagraphStyle/NumList"> + <CharacterStyleRange AppliedCharacterStyle="$ID/NormalCharacterStyle"> + <Content>More.</Content> + </CharacterStyleRange><Br /> +</ParagraphStyleRange> +<ParagraphStyleRange AppliedParagraphStyle="ParagraphStyle/NumList > NumList > first" NumberingContinue="false"> + <CharacterStyleRange AppliedCharacterStyle="$ID/NormalCharacterStyle"> + <Content>Nested.</Content> + </CharacterStyleRange><Br /> +</ParagraphStyleRange> +<ParagraphStyleRange AppliedParagraphStyle="ParagraphStyle/Paragraph"> + <CharacterStyleRange AppliedCharacterStyle="$ID/NormalCharacterStyle"> + <Content>Should not be a list item:</Content> + </CharacterStyleRange><Br /> +</ParagraphStyleRange> +<ParagraphStyleRange AppliedParagraphStyle="ParagraphStyle/Paragraph"> + <CharacterStyleRange AppliedCharacterStyle="$ID/NormalCharacterStyle"> + <Content>M.A. 2007</Content> + </CharacterStyleRange><Br /> +</ParagraphStyleRange> +<ParagraphStyleRange AppliedParagraphStyle="ParagraphStyle/Paragraph"> + <CharacterStyleRange AppliedCharacterStyle="$ID/NormalCharacterStyle"> + <Content>B. Williams</Content> + </CharacterStyleRange><Br /> +</ParagraphStyleRange> +<ParagraphStyleRange AppliedParagraphStyle="ParagraphStyle/Header1"> + <CharacterStyleRange AppliedCharacterStyle="$ID/NormalCharacterStyle"> + <Content>Definition Lists</Content> + </CharacterStyleRange><Br /> +</ParagraphStyleRange> +<ParagraphStyleRange AppliedParagraphStyle="ParagraphStyle/Paragraph"> + <CharacterStyleRange AppliedCharacterStyle="$ID/NormalCharacterStyle"> + <Content>Tight using spaces:</Content> + </CharacterStyleRange><Br /> +</ParagraphStyleRange> +<ParagraphStyleRange AppliedParagraphStyle="ParagraphStyle/DefListTerm"> + <CharacterStyleRange AppliedCharacterStyle="$ID/NormalCharacterStyle"> + <Content>apple</Content> + </CharacterStyleRange><Br /> +</ParagraphStyleRange> +<ParagraphStyleRange AppliedParagraphStyle="ParagraphStyle/DefListDef"> + <CharacterStyleRange AppliedCharacterStyle="$ID/NormalCharacterStyle"> + <Content>red fruit</Content> + </CharacterStyleRange><Br /> +</ParagraphStyleRange> +<ParagraphStyleRange AppliedParagraphStyle="ParagraphStyle/DefListTerm"> + <CharacterStyleRange AppliedCharacterStyle="$ID/NormalCharacterStyle"> + <Content>orange</Content> + </CharacterStyleRange><Br /> +</ParagraphStyleRange> +<ParagraphStyleRange AppliedParagraphStyle="ParagraphStyle/DefListDef"> + <CharacterStyleRange AppliedCharacterStyle="$ID/NormalCharacterStyle"> + <Content>orange fruit</Content> + </CharacterStyleRange><Br /> +</ParagraphStyleRange> +<ParagraphStyleRange AppliedParagraphStyle="ParagraphStyle/DefListTerm"> + <CharacterStyleRange AppliedCharacterStyle="$ID/NormalCharacterStyle"> + <Content>banana</Content> + </CharacterStyleRange><Br /> +</ParagraphStyleRange> +<ParagraphStyleRange AppliedParagraphStyle="ParagraphStyle/DefListDef"> + <CharacterStyleRange AppliedCharacterStyle="$ID/NormalCharacterStyle"> + <Content>yellow fruit</Content> + </CharacterStyleRange><Br /> +</ParagraphStyleRange> +<ParagraphStyleRange AppliedParagraphStyle="ParagraphStyle/Paragraph"> + <CharacterStyleRange AppliedCharacterStyle="$ID/NormalCharacterStyle"> + <Content>Tight using tabs:</Content> + </CharacterStyleRange><Br /> +</ParagraphStyleRange> +<ParagraphStyleRange AppliedParagraphStyle="ParagraphStyle/DefListTerm"> + <CharacterStyleRange AppliedCharacterStyle="$ID/NormalCharacterStyle"> + <Content>apple</Content> + </CharacterStyleRange><Br /> +</ParagraphStyleRange> +<ParagraphStyleRange AppliedParagraphStyle="ParagraphStyle/DefListDef"> + <CharacterStyleRange AppliedCharacterStyle="$ID/NormalCharacterStyle"> + <Content>red fruit</Content> + </CharacterStyleRange><Br /> +</ParagraphStyleRange> +<ParagraphStyleRange AppliedParagraphStyle="ParagraphStyle/DefListTerm"> + <CharacterStyleRange AppliedCharacterStyle="$ID/NormalCharacterStyle"> + <Content>orange</Content> + </CharacterStyleRange><Br /> +</ParagraphStyleRange> +<ParagraphStyleRange AppliedParagraphStyle="ParagraphStyle/DefListDef"> + <CharacterStyleRange AppliedCharacterStyle="$ID/NormalCharacterStyle"> + <Content>orange fruit</Content> + </CharacterStyleRange><Br /> +</ParagraphStyleRange> +<ParagraphStyleRange AppliedParagraphStyle="ParagraphStyle/DefListTerm"> + <CharacterStyleRange AppliedCharacterStyle="$ID/NormalCharacterStyle"> + <Content>banana</Content> + </CharacterStyleRange><Br /> +</ParagraphStyleRange> +<ParagraphStyleRange AppliedParagraphStyle="ParagraphStyle/DefListDef"> + <CharacterStyleRange AppliedCharacterStyle="$ID/NormalCharacterStyle"> + <Content>yellow fruit</Content> + </CharacterStyleRange><Br /> +</ParagraphStyleRange> +<ParagraphStyleRange AppliedParagraphStyle="ParagraphStyle/Paragraph"> + <CharacterStyleRange AppliedCharacterStyle="$ID/NormalCharacterStyle"> + <Content>Loose:</Content> + </CharacterStyleRange><Br /> +</ParagraphStyleRange> +<ParagraphStyleRange AppliedParagraphStyle="ParagraphStyle/DefListTerm"> + <CharacterStyleRange AppliedCharacterStyle="$ID/NormalCharacterStyle"> + <Content>apple</Content> + </CharacterStyleRange><Br /> +</ParagraphStyleRange> +<ParagraphStyleRange AppliedParagraphStyle="ParagraphStyle/DefListDef > Paragraph"> + <CharacterStyleRange AppliedCharacterStyle="$ID/NormalCharacterStyle"> + <Content>red fruit</Content> + </CharacterStyleRange><Br /> +</ParagraphStyleRange> +<ParagraphStyleRange AppliedParagraphStyle="ParagraphStyle/DefListTerm"> + <CharacterStyleRange AppliedCharacterStyle="$ID/NormalCharacterStyle"> + <Content>orange</Content> + </CharacterStyleRange><Br /> +</ParagraphStyleRange> +<ParagraphStyleRange AppliedParagraphStyle="ParagraphStyle/DefListDef > Paragraph"> + <CharacterStyleRange AppliedCharacterStyle="$ID/NormalCharacterStyle"> + <Content>orange fruit</Content> + </CharacterStyleRange><Br /> +</ParagraphStyleRange> +<ParagraphStyleRange AppliedParagraphStyle="ParagraphStyle/DefListTerm"> + <CharacterStyleRange AppliedCharacterStyle="$ID/NormalCharacterStyle"> + <Content>banana</Content> + </CharacterStyleRange><Br /> +</ParagraphStyleRange> +<ParagraphStyleRange AppliedParagraphStyle="ParagraphStyle/DefListDef > Paragraph"> + <CharacterStyleRange AppliedCharacterStyle="$ID/NormalCharacterStyle"> + <Content>yellow fruit</Content> + </CharacterStyleRange><Br /> +</ParagraphStyleRange> +<ParagraphStyleRange AppliedParagraphStyle="ParagraphStyle/Paragraph"> + <CharacterStyleRange AppliedCharacterStyle="$ID/NormalCharacterStyle"> + <Content>Multiple blocks with italics:</Content> + </CharacterStyleRange><Br /> +</ParagraphStyleRange> +<ParagraphStyleRange AppliedParagraphStyle="ParagraphStyle/DefListTerm"> + <CharacterStyleRange AppliedCharacterStyle="CharacterStyle/Italic"> + <Content>apple</Content> + </CharacterStyleRange><Br /> +</ParagraphStyleRange> +<ParagraphStyleRange AppliedParagraphStyle="ParagraphStyle/DefListDef > Paragraph"> + <CharacterStyleRange AppliedCharacterStyle="$ID/NormalCharacterStyle"> + <Content>red fruit</Content> + </CharacterStyleRange><Br /> +</ParagraphStyleRange> +<ParagraphStyleRange AppliedParagraphStyle="ParagraphStyle/DefListDef > Paragraph"> + <CharacterStyleRange AppliedCharacterStyle="$ID/NormalCharacterStyle"> + <Content>contains seeds, crisp, pleasant to taste</Content> + </CharacterStyleRange><Br /> +</ParagraphStyleRange> +<ParagraphStyleRange AppliedParagraphStyle="ParagraphStyle/DefListTerm"> + <CharacterStyleRange AppliedCharacterStyle="CharacterStyle/Italic"> + <Content>orange</Content> + </CharacterStyleRange><Br /> +</ParagraphStyleRange> +<ParagraphStyleRange AppliedParagraphStyle="ParagraphStyle/DefListDef > Paragraph"> + <CharacterStyleRange AppliedCharacterStyle="$ID/NormalCharacterStyle"> + <Content>orange fruit</Content> + </CharacterStyleRange><Br /> +</ParagraphStyleRange> +<ParagraphStyleRange AppliedParagraphStyle="ParagraphStyle/DefListDef > CodeBlock"> + <CharacterStyleRange AppliedCharacterStyle="$ID/NormalCharacterStyle"> + <Content>{ orange code block }</Content> + </CharacterStyleRange><Br /> +</ParagraphStyleRange> +<ParagraphStyleRange AppliedParagraphStyle="ParagraphStyle/DefListDef > Blockquote > Paragraph"> + <CharacterStyleRange AppliedCharacterStyle="$ID/NormalCharacterStyle"> + <Content>orange block quote</Content> + </CharacterStyleRange><Br /> +</ParagraphStyleRange> +<ParagraphStyleRange AppliedParagraphStyle="ParagraphStyle/Paragraph"> + <CharacterStyleRange AppliedCharacterStyle="$ID/NormalCharacterStyle"> + <Content>Multiple definitions, tight:</Content> + </CharacterStyleRange><Br /> +</ParagraphStyleRange> +<ParagraphStyleRange AppliedParagraphStyle="ParagraphStyle/DefListTerm"> + <CharacterStyleRange AppliedCharacterStyle="$ID/NormalCharacterStyle"> + <Content>apple</Content> + </CharacterStyleRange><Br /> +</ParagraphStyleRange> +<ParagraphStyleRange AppliedParagraphStyle="ParagraphStyle/DefListDef"> + <CharacterStyleRange AppliedCharacterStyle="$ID/NormalCharacterStyle"> + <Content>red fruit</Content> + </CharacterStyleRange><Br /> +</ParagraphStyleRange> +<ParagraphStyleRange AppliedParagraphStyle="ParagraphStyle/DefListDef"> + <CharacterStyleRange AppliedCharacterStyle="$ID/NormalCharacterStyle"> + <Content>computer</Content> + </CharacterStyleRange><Br /> +</ParagraphStyleRange> +<ParagraphStyleRange AppliedParagraphStyle="ParagraphStyle/DefListTerm"> + <CharacterStyleRange AppliedCharacterStyle="$ID/NormalCharacterStyle"> + <Content>orange</Content> + </CharacterStyleRange><Br /> +</ParagraphStyleRange> +<ParagraphStyleRange AppliedParagraphStyle="ParagraphStyle/DefListDef"> + <CharacterStyleRange AppliedCharacterStyle="$ID/NormalCharacterStyle"> + <Content>orange fruit</Content> + </CharacterStyleRange><Br /> +</ParagraphStyleRange> +<ParagraphStyleRange AppliedParagraphStyle="ParagraphStyle/DefListDef"> + <CharacterStyleRange AppliedCharacterStyle="$ID/NormalCharacterStyle"> + <Content>bank</Content> + </CharacterStyleRange><Br /> +</ParagraphStyleRange> +<ParagraphStyleRange AppliedParagraphStyle="ParagraphStyle/Paragraph"> + <CharacterStyleRange AppliedCharacterStyle="$ID/NormalCharacterStyle"> + <Content>Multiple definitions, loose:</Content> + </CharacterStyleRange><Br /> +</ParagraphStyleRange> +<ParagraphStyleRange AppliedParagraphStyle="ParagraphStyle/DefListTerm"> + <CharacterStyleRange AppliedCharacterStyle="$ID/NormalCharacterStyle"> + <Content>apple</Content> + </CharacterStyleRange><Br /> +</ParagraphStyleRange> +<ParagraphStyleRange AppliedParagraphStyle="ParagraphStyle/DefListDef > Paragraph"> + <CharacterStyleRange AppliedCharacterStyle="$ID/NormalCharacterStyle"> + <Content>red fruit</Content> + </CharacterStyleRange><Br /> +</ParagraphStyleRange> +<ParagraphStyleRange AppliedParagraphStyle="ParagraphStyle/DefListDef > Paragraph"> + <CharacterStyleRange AppliedCharacterStyle="$ID/NormalCharacterStyle"> + <Content>computer</Content> + </CharacterStyleRange><Br /> +</ParagraphStyleRange> +<ParagraphStyleRange AppliedParagraphStyle="ParagraphStyle/DefListTerm"> + <CharacterStyleRange AppliedCharacterStyle="$ID/NormalCharacterStyle"> + <Content>orange</Content> + </CharacterStyleRange><Br /> +</ParagraphStyleRange> +<ParagraphStyleRange AppliedParagraphStyle="ParagraphStyle/DefListDef > Paragraph"> + <CharacterStyleRange AppliedCharacterStyle="$ID/NormalCharacterStyle"> + <Content>orange fruit</Content> + </CharacterStyleRange><Br /> +</ParagraphStyleRange> +<ParagraphStyleRange AppliedParagraphStyle="ParagraphStyle/DefListDef > Paragraph"> + <CharacterStyleRange AppliedCharacterStyle="$ID/NormalCharacterStyle"> + <Content>bank</Content> + </CharacterStyleRange><Br /> +</ParagraphStyleRange> +<ParagraphStyleRange AppliedParagraphStyle="ParagraphStyle/Paragraph"> + <CharacterStyleRange AppliedCharacterStyle="$ID/NormalCharacterStyle"> + <Content>Blank line after term, indented marker, alternate markers:</Content> + </CharacterStyleRange><Br /> +</ParagraphStyleRange> +<ParagraphStyleRange AppliedParagraphStyle="ParagraphStyle/DefListTerm"> + <CharacterStyleRange AppliedCharacterStyle="$ID/NormalCharacterStyle"> + <Content>apple</Content> + </CharacterStyleRange><Br /> +</ParagraphStyleRange> +<ParagraphStyleRange AppliedParagraphStyle="ParagraphStyle/DefListDef > Paragraph"> + <CharacterStyleRange AppliedCharacterStyle="$ID/NormalCharacterStyle"> + <Content>red fruit</Content> + </CharacterStyleRange><Br /> +</ParagraphStyleRange> +<ParagraphStyleRange AppliedParagraphStyle="ParagraphStyle/DefListDef > Paragraph"> + <CharacterStyleRange AppliedCharacterStyle="$ID/NormalCharacterStyle"> + <Content>computer</Content> + </CharacterStyleRange><Br /> +</ParagraphStyleRange> +<ParagraphStyleRange AppliedParagraphStyle="ParagraphStyle/DefListTerm"> + <CharacterStyleRange AppliedCharacterStyle="$ID/NormalCharacterStyle"> + <Content>orange</Content> + </CharacterStyleRange><Br /> +</ParagraphStyleRange> +<ParagraphStyleRange AppliedParagraphStyle="ParagraphStyle/DefListDef > Paragraph"> + <CharacterStyleRange AppliedCharacterStyle="$ID/NormalCharacterStyle"> + <Content>orange fruit</Content> + </CharacterStyleRange><Br /> +</ParagraphStyleRange> +<ParagraphStyleRange AppliedParagraphStyle="ParagraphStyle/DefListDef > NumList > first" NumberingContinue="false"> + <CharacterStyleRange AppliedCharacterStyle="$ID/NormalCharacterStyle"> + <Content>sublist</Content> + </CharacterStyleRange><Br /> +</ParagraphStyleRange> +<ParagraphStyleRange AppliedParagraphStyle="ParagraphStyle/DefListDef > NumList"> + <CharacterStyleRange AppliedCharacterStyle="$ID/NormalCharacterStyle"> + <Content>sublist</Content> + </CharacterStyleRange><Br /> +</ParagraphStyleRange> +<ParagraphStyleRange AppliedParagraphStyle="ParagraphStyle/Header1"> + <CharacterStyleRange AppliedCharacterStyle="$ID/NormalCharacterStyle"> + <Content>HTML Blocks</Content> + </CharacterStyleRange><Br /> +</ParagraphStyleRange> +<ParagraphStyleRange AppliedParagraphStyle="ParagraphStyle/Paragraph"> + <CharacterStyleRange AppliedCharacterStyle="$ID/NormalCharacterStyle"> + <Content>Simple block on one line:</Content> + </CharacterStyleRange><Br /> +</ParagraphStyleRange> +<ParagraphStyleRange AppliedParagraphStyle=""> + <CharacterStyleRange AppliedCharacterStyle="$ID/NormalCharacterStyle"> + <Content>foo</Content> + </CharacterStyleRange><Br /> +</ParagraphStyleRange> +<ParagraphStyleRange AppliedParagraphStyle="ParagraphStyle/Paragraph"> + <CharacterStyleRange AppliedCharacterStyle="$ID/NormalCharacterStyle"> + <Content>And nested without indentation:</Content> + </CharacterStyleRange><Br /> +</ParagraphStyleRange> +<ParagraphStyleRange AppliedParagraphStyle="ParagraphStyle/Paragraph"> + <CharacterStyleRange AppliedCharacterStyle="$ID/NormalCharacterStyle"> + <Content>foo</Content> + </CharacterStyleRange><Br /> +</ParagraphStyleRange> +<ParagraphStyleRange AppliedParagraphStyle=""> + <CharacterStyleRange AppliedCharacterStyle="$ID/NormalCharacterStyle"> + <Content>bar</Content> + </CharacterStyleRange><Br /> +</ParagraphStyleRange> +<ParagraphStyleRange AppliedParagraphStyle="ParagraphStyle/Paragraph"> + <CharacterStyleRange AppliedCharacterStyle="$ID/NormalCharacterStyle"> + <Content>Interpreted markdown in a table:</Content> + </CharacterStyleRange><Br /> +</ParagraphStyleRange> +<ParagraphStyleRange AppliedParagraphStyle="ParagraphStyle/Rawblock"> + <CharacterStyleRange AppliedCharacterStyle="$ID/NormalCharacterStyle"> + <Content><table></Content> + </CharacterStyleRange><Br /> +</ParagraphStyleRange> +<ParagraphStyleRange AppliedParagraphStyle="ParagraphStyle/Rawblock"> + <CharacterStyleRange AppliedCharacterStyle="$ID/NormalCharacterStyle"> + <Content><tr></Content> + </CharacterStyleRange><Br /> +</ParagraphStyleRange> +<ParagraphStyleRange AppliedParagraphStyle="ParagraphStyle/Rawblock"> + <CharacterStyleRange AppliedCharacterStyle="$ID/NormalCharacterStyle"> + <Content><td></Content> + </CharacterStyleRange><Br /> +</ParagraphStyleRange> +<ParagraphStyleRange AppliedParagraphStyle=""> + <CharacterStyleRange AppliedCharacterStyle="$ID/NormalCharacterStyle"> + <Content>This is </Content> + </CharacterStyleRange> + <CharacterStyleRange AppliedCharacterStyle="CharacterStyle/Italic"> + <Content>emphasized</Content> + </CharacterStyleRange><Br /> +</ParagraphStyleRange> +<ParagraphStyleRange AppliedParagraphStyle="ParagraphStyle/Rawblock"> + <CharacterStyleRange AppliedCharacterStyle="$ID/NormalCharacterStyle"> + <Content></td></Content> + </CharacterStyleRange><Br /> +</ParagraphStyleRange> +<ParagraphStyleRange AppliedParagraphStyle="ParagraphStyle/Rawblock"> + <CharacterStyleRange AppliedCharacterStyle="$ID/NormalCharacterStyle"> + <Content><td></Content> + </CharacterStyleRange><Br /> +</ParagraphStyleRange> +<ParagraphStyleRange AppliedParagraphStyle=""> + <CharacterStyleRange AppliedCharacterStyle="$ID/NormalCharacterStyle"> + <Content>And this is </Content> + </CharacterStyleRange> + <CharacterStyleRange AppliedCharacterStyle="CharacterStyle/Bold"> + <Content>strong</Content> + </CharacterStyleRange><Br /> +</ParagraphStyleRange> +<ParagraphStyleRange AppliedParagraphStyle="ParagraphStyle/Rawblock"> + <CharacterStyleRange AppliedCharacterStyle="$ID/NormalCharacterStyle"> + <Content></td></Content> + </CharacterStyleRange><Br /> +</ParagraphStyleRange> +<ParagraphStyleRange AppliedParagraphStyle="ParagraphStyle/Rawblock"> + <CharacterStyleRange AppliedCharacterStyle="$ID/NormalCharacterStyle"> + <Content></tr></Content> + </CharacterStyleRange><Br /> +</ParagraphStyleRange> +<ParagraphStyleRange AppliedParagraphStyle="ParagraphStyle/Rawblock"> + <CharacterStyleRange AppliedCharacterStyle="$ID/NormalCharacterStyle"> + <Content></table></Content> + </CharacterStyleRange><Br /> +</ParagraphStyleRange> +<ParagraphStyleRange AppliedParagraphStyle="ParagraphStyle/Rawblock"> + <CharacterStyleRange AppliedCharacterStyle="$ID/NormalCharacterStyle"> + <Content><script type="text/javascript">document.write('This *should not* be interpreted as markdown');</script></Content> + </CharacterStyleRange><Br /> +</ParagraphStyleRange> +<ParagraphStyleRange AppliedParagraphStyle="ParagraphStyle/Paragraph"> + <CharacterStyleRange AppliedCharacterStyle="$ID/NormalCharacterStyle"> + <Content>Here’s a simple block:</Content> + </CharacterStyleRange><Br /> +</ParagraphStyleRange> +<ParagraphStyleRange AppliedParagraphStyle="ParagraphStyle/Paragraph"> + <CharacterStyleRange AppliedCharacterStyle="$ID/NormalCharacterStyle"> + <Content>foo</Content> + </CharacterStyleRange><Br /> +</ParagraphStyleRange> +<ParagraphStyleRange AppliedParagraphStyle="ParagraphStyle/Paragraph"> + <CharacterStyleRange AppliedCharacterStyle="$ID/NormalCharacterStyle"> + <Content>This should be a code block, though:</Content> + </CharacterStyleRange><Br /> +</ParagraphStyleRange> +<ParagraphStyleRange AppliedParagraphStyle="ParagraphStyle/CodeBlock"> + <CharacterStyleRange AppliedCharacterStyle="$ID/NormalCharacterStyle"> + <Content><div> + foo +</div></Content> + </CharacterStyleRange><Br /> +</ParagraphStyleRange> +<ParagraphStyleRange AppliedParagraphStyle="ParagraphStyle/Paragraph"> + <CharacterStyleRange AppliedCharacterStyle="$ID/NormalCharacterStyle"> + <Content>As should this:</Content> + </CharacterStyleRange><Br /> +</ParagraphStyleRange> +<ParagraphStyleRange AppliedParagraphStyle="ParagraphStyle/CodeBlock"> + <CharacterStyleRange AppliedCharacterStyle="$ID/NormalCharacterStyle"> + <Content><div>foo</div></Content> + </CharacterStyleRange><Br /> +</ParagraphStyleRange> +<ParagraphStyleRange AppliedParagraphStyle="ParagraphStyle/Paragraph"> + <CharacterStyleRange AppliedCharacterStyle="$ID/NormalCharacterStyle"> + <Content>Now, nested:</Content> + </CharacterStyleRange><Br /> +</ParagraphStyleRange> +<ParagraphStyleRange AppliedParagraphStyle=""> + <CharacterStyleRange AppliedCharacterStyle="$ID/NormalCharacterStyle"> + <Content>foo</Content> + </CharacterStyleRange><Br /> +</ParagraphStyleRange> +<ParagraphStyleRange AppliedParagraphStyle="ParagraphStyle/Paragraph"> + <CharacterStyleRange AppliedCharacterStyle="$ID/NormalCharacterStyle"> + <Content>This should just be an HTML comment:</Content> + </CharacterStyleRange><Br /> +</ParagraphStyleRange> +<ParagraphStyleRange AppliedParagraphStyle="ParagraphStyle/Rawblock"> + <CharacterStyleRange AppliedCharacterStyle="$ID/NormalCharacterStyle"> + <Content><!-- Comment --></Content> + </CharacterStyleRange><Br /> +</ParagraphStyleRange> +<ParagraphStyleRange AppliedParagraphStyle="ParagraphStyle/Paragraph"> + <CharacterStyleRange AppliedCharacterStyle="$ID/NormalCharacterStyle"> + <Content>Multiline:</Content> + </CharacterStyleRange><Br /> +</ParagraphStyleRange> +<ParagraphStyleRange AppliedParagraphStyle="ParagraphStyle/Rawblock"> + <CharacterStyleRange AppliedCharacterStyle="$ID/NormalCharacterStyle"> + <Content><!-- +Blah +Blah +--></Content> + </CharacterStyleRange><Br /> +</ParagraphStyleRange> +<ParagraphStyleRange AppliedParagraphStyle="ParagraphStyle/Rawblock"> + <CharacterStyleRange AppliedCharacterStyle="$ID/NormalCharacterStyle"> + <Content><!-- + This is another comment. +--></Content> + </CharacterStyleRange><Br /> +</ParagraphStyleRange> +<ParagraphStyleRange AppliedParagraphStyle="ParagraphStyle/Paragraph"> + <CharacterStyleRange AppliedCharacterStyle="$ID/NormalCharacterStyle"> + <Content>Code block:</Content> + </CharacterStyleRange><Br /> +</ParagraphStyleRange> +<ParagraphStyleRange AppliedParagraphStyle="ParagraphStyle/CodeBlock"> + <CharacterStyleRange AppliedCharacterStyle="$ID/NormalCharacterStyle"> + <Content><!-- Comment --></Content> + </CharacterStyleRange><Br /> +</ParagraphStyleRange> +<ParagraphStyleRange AppliedParagraphStyle="ParagraphStyle/Paragraph"> + <CharacterStyleRange AppliedCharacterStyle="$ID/NormalCharacterStyle"> + <Content>Just plain comment, with trailing spaces on the line:</Content> + </CharacterStyleRange><Br /> +</ParagraphStyleRange> +<ParagraphStyleRange AppliedParagraphStyle="ParagraphStyle/Rawblock"> + <CharacterStyleRange AppliedCharacterStyle="$ID/NormalCharacterStyle"> + <Content><!-- foo --></Content> + </CharacterStyleRange><Br /> +</ParagraphStyleRange> +<ParagraphStyleRange AppliedParagraphStyle="ParagraphStyle/Paragraph"> + <CharacterStyleRange AppliedCharacterStyle="$ID/NormalCharacterStyle"> + <Content>Code:</Content> + </CharacterStyleRange><Br /> +</ParagraphStyleRange> +<ParagraphStyleRange AppliedParagraphStyle="ParagraphStyle/CodeBlock"> + <CharacterStyleRange AppliedCharacterStyle="$ID/NormalCharacterStyle"> + <Content><hr /></Content> + </CharacterStyleRange><Br /> +</ParagraphStyleRange> +<ParagraphStyleRange AppliedParagraphStyle="ParagraphStyle/Paragraph"> + <CharacterStyleRange AppliedCharacterStyle="$ID/NormalCharacterStyle"> + <Content>Hr’s:</Content> + </CharacterStyleRange><Br /> +</ParagraphStyleRange> +<ParagraphStyleRange AppliedParagraphStyle="ParagraphStyle/Rawblock"> + <CharacterStyleRange AppliedCharacterStyle="$ID/NormalCharacterStyle"> + <Content><hr></Content> + </CharacterStyleRange><Br /> +</ParagraphStyleRange> +<ParagraphStyleRange AppliedParagraphStyle="ParagraphStyle/Rawblock"> + <CharacterStyleRange AppliedCharacterStyle="$ID/NormalCharacterStyle"> + <Content><hr /></Content> + </CharacterStyleRange><Br /> +</ParagraphStyleRange> +<ParagraphStyleRange AppliedParagraphStyle="ParagraphStyle/Rawblock"> + <CharacterStyleRange AppliedCharacterStyle="$ID/NormalCharacterStyle"> + <Content><hr /></Content> + </CharacterStyleRange><Br /> +</ParagraphStyleRange> +<ParagraphStyleRange AppliedParagraphStyle="ParagraphStyle/Rawblock"> + <CharacterStyleRange AppliedCharacterStyle="$ID/NormalCharacterStyle"> + <Content><hr></Content> + </CharacterStyleRange><Br /> +</ParagraphStyleRange> +<ParagraphStyleRange AppliedParagraphStyle="ParagraphStyle/Rawblock"> + <CharacterStyleRange AppliedCharacterStyle="$ID/NormalCharacterStyle"> + <Content><hr /></Content> + </CharacterStyleRange><Br /> +</ParagraphStyleRange> +<ParagraphStyleRange AppliedParagraphStyle="ParagraphStyle/Rawblock"> + <CharacterStyleRange AppliedCharacterStyle="$ID/NormalCharacterStyle"> + <Content><hr /></Content> + </CharacterStyleRange><Br /> +</ParagraphStyleRange> +<ParagraphStyleRange AppliedParagraphStyle="ParagraphStyle/Rawblock"> + <CharacterStyleRange AppliedCharacterStyle="$ID/NormalCharacterStyle"> + <Content><hr class="foo" id="bar" /></Content> + </CharacterStyleRange><Br /> +</ParagraphStyleRange> +<ParagraphStyleRange AppliedParagraphStyle="ParagraphStyle/Rawblock"> + <CharacterStyleRange AppliedCharacterStyle="$ID/NormalCharacterStyle"> + <Content><hr class="foo" id="bar" /></Content> + </CharacterStyleRange><Br /> +</ParagraphStyleRange> +<ParagraphStyleRange AppliedParagraphStyle="ParagraphStyle/Rawblock"> + <CharacterStyleRange AppliedCharacterStyle="$ID/NormalCharacterStyle"> + <Content><hr class="foo" id="bar"></Content> + </CharacterStyleRange><Br /> +</ParagraphStyleRange> +<ParagraphStyleRange AppliedParagraphStyle="ParagraphStyle/Header1"> + <CharacterStyleRange AppliedCharacterStyle="$ID/NormalCharacterStyle"> + <Content>Inline Markup</Content> + </CharacterStyleRange><Br /> +</ParagraphStyleRange> +<ParagraphStyleRange AppliedParagraphStyle="ParagraphStyle/Paragraph"> + <CharacterStyleRange AppliedCharacterStyle="$ID/NormalCharacterStyle"> + <Content>This is </Content> + </CharacterStyleRange> + <CharacterStyleRange AppliedCharacterStyle="CharacterStyle/Italic"> + <Content>emphasized</Content> + </CharacterStyleRange> + <CharacterStyleRange AppliedCharacterStyle="$ID/NormalCharacterStyle"> + <Content>, and so </Content> + </CharacterStyleRange> + <CharacterStyleRange AppliedCharacterStyle="CharacterStyle/Italic"> + <Content>is this</Content> + </CharacterStyleRange> + <CharacterStyleRange AppliedCharacterStyle="$ID/NormalCharacterStyle"> + <Content>.</Content> + </CharacterStyleRange><Br /> +</ParagraphStyleRange> +<ParagraphStyleRange AppliedParagraphStyle="ParagraphStyle/Paragraph"> + <CharacterStyleRange AppliedCharacterStyle="$ID/NormalCharacterStyle"> + <Content>This is </Content> + </CharacterStyleRange> + <CharacterStyleRange AppliedCharacterStyle="CharacterStyle/Bold"> + <Content>strong</Content> + </CharacterStyleRange> + <CharacterStyleRange AppliedCharacterStyle="$ID/NormalCharacterStyle"> + <Content>, and so </Content> + </CharacterStyleRange> + <CharacterStyleRange AppliedCharacterStyle="CharacterStyle/Bold"> + <Content>is this</Content> + </CharacterStyleRange> + <CharacterStyleRange AppliedCharacterStyle="$ID/NormalCharacterStyle"> + <Content>.</Content> + </CharacterStyleRange><Br /> +</ParagraphStyleRange> +<ParagraphStyleRange AppliedParagraphStyle="ParagraphStyle/Paragraph"> + <CharacterStyleRange AppliedCharacterStyle="$ID/NormalCharacterStyle"> + <Content>An </Content> + </CharacterStyleRange> + <HyperlinkTextSource Self="htss-2" Name="" Hidden="false"> + <CharacterStyleRange AppliedCharacterStyle="CharacterStyle/Italic Link"> + <Content>emphasized link</Content> + </CharacterStyleRange> + </HyperlinkTextSource> + <CharacterStyleRange AppliedCharacterStyle="$ID/NormalCharacterStyle"> + <Content>.</Content> + </CharacterStyleRange><Br /> +</ParagraphStyleRange> +<ParagraphStyleRange AppliedParagraphStyle="ParagraphStyle/Paragraph"> + <CharacterStyleRange AppliedCharacterStyle="CharacterStyle/Bold Italic"> + <Content>This is strong and em.</Content> + </CharacterStyleRange><Br /> +</ParagraphStyleRange> +<ParagraphStyleRange AppliedParagraphStyle="ParagraphStyle/Paragraph"> + <CharacterStyleRange AppliedCharacterStyle="$ID/NormalCharacterStyle"> + <Content>So is </Content> + </CharacterStyleRange> + <CharacterStyleRange AppliedCharacterStyle="CharacterStyle/Bold Italic"> + <Content>this</Content> + </CharacterStyleRange> + <CharacterStyleRange AppliedCharacterStyle="$ID/NormalCharacterStyle"> + <Content> word.</Content> + </CharacterStyleRange><Br /> +</ParagraphStyleRange> +<ParagraphStyleRange AppliedParagraphStyle="ParagraphStyle/Paragraph"> + <CharacterStyleRange AppliedCharacterStyle="CharacterStyle/Bold Italic"> + <Content>This is strong and em.</Content> + </CharacterStyleRange><Br /> +</ParagraphStyleRange> +<ParagraphStyleRange AppliedParagraphStyle="ParagraphStyle/Paragraph"> + <CharacterStyleRange AppliedCharacterStyle="$ID/NormalCharacterStyle"> + <Content>So is </Content> + </CharacterStyleRange> + <CharacterStyleRange AppliedCharacterStyle="CharacterStyle/Bold Italic"> + <Content>this</Content> + </CharacterStyleRange> + <CharacterStyleRange AppliedCharacterStyle="$ID/NormalCharacterStyle"> + <Content> word.</Content> + </CharacterStyleRange><Br /> +</ParagraphStyleRange> +<ParagraphStyleRange AppliedParagraphStyle="ParagraphStyle/Paragraph"> + <CharacterStyleRange AppliedCharacterStyle="$ID/NormalCharacterStyle"> + <Content>This is code: </Content> + </CharacterStyleRange> + <CharacterStyleRange AppliedCharacterStyle="CharacterStyle/Code"> + <Content>></Content> + </CharacterStyleRange> + <CharacterStyleRange AppliedCharacterStyle="$ID/NormalCharacterStyle"> + <Content>, </Content> + </CharacterStyleRange> + <CharacterStyleRange AppliedCharacterStyle="CharacterStyle/Code"> + <Content>$</Content> + </CharacterStyleRange> + <CharacterStyleRange AppliedCharacterStyle="$ID/NormalCharacterStyle"> + <Content>, </Content> + </CharacterStyleRange> + <CharacterStyleRange AppliedCharacterStyle="CharacterStyle/Code"> + <Content>\</Content> + </CharacterStyleRange> + <CharacterStyleRange AppliedCharacterStyle="$ID/NormalCharacterStyle"> + <Content>, </Content> + </CharacterStyleRange> + <CharacterStyleRange AppliedCharacterStyle="CharacterStyle/Code"> + <Content>\$</Content> + </CharacterStyleRange> + <CharacterStyleRange AppliedCharacterStyle="$ID/NormalCharacterStyle"> + <Content>, </Content> + </CharacterStyleRange> + <CharacterStyleRange AppliedCharacterStyle="CharacterStyle/Code"> + <Content><html></Content> + </CharacterStyleRange> + <CharacterStyleRange AppliedCharacterStyle="$ID/NormalCharacterStyle"> + <Content>.</Content> + </CharacterStyleRange><Br /> +</ParagraphStyleRange> +<ParagraphStyleRange AppliedParagraphStyle="ParagraphStyle/Paragraph"> + <CharacterStyleRange AppliedCharacterStyle="CharacterStyle/Strikeout"> + <Content>This is </Content> + </CharacterStyleRange> + <CharacterStyleRange AppliedCharacterStyle="CharacterStyle/Italic Strikeout"> + <Content>strikeout</Content> + </CharacterStyleRange> + <CharacterStyleRange AppliedCharacterStyle="CharacterStyle/Strikeout"> + <Content>.</Content> + </CharacterStyleRange><Br /> +</ParagraphStyleRange> +<ParagraphStyleRange AppliedParagraphStyle="ParagraphStyle/Paragraph"> + <CharacterStyleRange AppliedCharacterStyle="$ID/NormalCharacterStyle"> + <Content>Superscripts: a</Content> + </CharacterStyleRange> + <CharacterStyleRange AppliedCharacterStyle="CharacterStyle/Superscript"> + <Content>bc</Content> + </CharacterStyleRange> + <CharacterStyleRange AppliedCharacterStyle="$ID/NormalCharacterStyle"> + <Content>d a</Content> + </CharacterStyleRange> + <CharacterStyleRange AppliedCharacterStyle="CharacterStyle/Italic Superscript"> + <Content>hello</Content> + </CharacterStyleRange> + <CharacterStyleRange AppliedCharacterStyle="$ID/NormalCharacterStyle"> + <Content> a</Content> + </CharacterStyleRange> + <CharacterStyleRange AppliedCharacterStyle="CharacterStyle/Superscript"> + <Content>hello there</Content> + </CharacterStyleRange> + <CharacterStyleRange AppliedCharacterStyle="$ID/NormalCharacterStyle"> + <Content>.</Content> + </CharacterStyleRange><Br /> +</ParagraphStyleRange> +<ParagraphStyleRange AppliedParagraphStyle="ParagraphStyle/Paragraph"> + <CharacterStyleRange AppliedCharacterStyle="$ID/NormalCharacterStyle"> + <Content>Subscripts: H</Content> + </CharacterStyleRange> + <CharacterStyleRange AppliedCharacterStyle="CharacterStyle/Subscript"> + <Content>2</Content> + </CharacterStyleRange> + <CharacterStyleRange AppliedCharacterStyle="$ID/NormalCharacterStyle"> + <Content>O, H</Content> + </CharacterStyleRange> + <CharacterStyleRange AppliedCharacterStyle="CharacterStyle/Subscript"> + <Content>23</Content> + </CharacterStyleRange> + <CharacterStyleRange AppliedCharacterStyle="$ID/NormalCharacterStyle"> + <Content>O, H</Content> + </CharacterStyleRange> + <CharacterStyleRange AppliedCharacterStyle="CharacterStyle/Subscript"> + <Content>many of them</Content> + </CharacterStyleRange> + <CharacterStyleRange AppliedCharacterStyle="$ID/NormalCharacterStyle"> + <Content>O.</Content> + </CharacterStyleRange><Br /> +</ParagraphStyleRange> +<ParagraphStyleRange AppliedParagraphStyle="ParagraphStyle/Paragraph"> + <CharacterStyleRange AppliedCharacterStyle="$ID/NormalCharacterStyle"> + <Content>These should not be superscripts or subscripts, because of the unescaped spaces: a^b c^d, a~b c~d.</Content> + </CharacterStyleRange><Br /> +</ParagraphStyleRange> +<ParagraphStyleRange AppliedParagraphStyle="ParagraphStyle/Header1"> + <CharacterStyleRange AppliedCharacterStyle="$ID/NormalCharacterStyle"> + <Content>Smart quotes, ellipses, dashes</Content> + </CharacterStyleRange><Br /> +</ParagraphStyleRange> +<ParagraphStyleRange AppliedParagraphStyle="ParagraphStyle/Paragraph"> + <CharacterStyleRange AppliedCharacterStyle="$ID/NormalCharacterStyle"> + <Content>“</Content> + </CharacterStyleRange> + <CharacterStyleRange AppliedCharacterStyle="$ID/NormalCharacterStyle"> + <Content>Hello,</Content> + </CharacterStyleRange> + <CharacterStyleRange AppliedCharacterStyle="$ID/NormalCharacterStyle"> + <Content>”</Content> + </CharacterStyleRange> + <CharacterStyleRange AppliedCharacterStyle="$ID/NormalCharacterStyle"> + <Content> said the spider. </Content> + </CharacterStyleRange> + <CharacterStyleRange AppliedCharacterStyle="$ID/NormalCharacterStyle"> + <Content>“</Content> + </CharacterStyleRange> + <CharacterStyleRange AppliedCharacterStyle="$ID/NormalCharacterStyle"> + <Content>‘</Content> + </CharacterStyleRange> + <CharacterStyleRange AppliedCharacterStyle="$ID/NormalCharacterStyle"> + <Content>Shelob</Content> + </CharacterStyleRange> + <CharacterStyleRange AppliedCharacterStyle="$ID/NormalCharacterStyle"> + <Content>’</Content> + </CharacterStyleRange> + <CharacterStyleRange AppliedCharacterStyle="$ID/NormalCharacterStyle"> + <Content> is my name.</Content> + </CharacterStyleRange> + <CharacterStyleRange AppliedCharacterStyle="$ID/NormalCharacterStyle"> + <Content>”</Content> + </CharacterStyleRange><Br /> +</ParagraphStyleRange> +<ParagraphStyleRange AppliedParagraphStyle="ParagraphStyle/Paragraph"> + <CharacterStyleRange AppliedCharacterStyle="$ID/NormalCharacterStyle"> + <Content>‘</Content> + </CharacterStyleRange> + <CharacterStyleRange AppliedCharacterStyle="$ID/NormalCharacterStyle"> + <Content>A</Content> + </CharacterStyleRange> + <CharacterStyleRange AppliedCharacterStyle="$ID/NormalCharacterStyle"> + <Content>’</Content> + </CharacterStyleRange> + <CharacterStyleRange AppliedCharacterStyle="$ID/NormalCharacterStyle"> + <Content>, </Content> + </CharacterStyleRange> + <CharacterStyleRange AppliedCharacterStyle="$ID/NormalCharacterStyle"> + <Content>‘</Content> + </CharacterStyleRange> + <CharacterStyleRange AppliedCharacterStyle="$ID/NormalCharacterStyle"> + <Content>B</Content> + </CharacterStyleRange> + <CharacterStyleRange AppliedCharacterStyle="$ID/NormalCharacterStyle"> + <Content>’</Content> + </CharacterStyleRange> + <CharacterStyleRange AppliedCharacterStyle="$ID/NormalCharacterStyle"> + <Content>, and </Content> + </CharacterStyleRange> + <CharacterStyleRange AppliedCharacterStyle="$ID/NormalCharacterStyle"> + <Content>‘</Content> + </CharacterStyleRange> + <CharacterStyleRange AppliedCharacterStyle="$ID/NormalCharacterStyle"> + <Content>C</Content> + </CharacterStyleRange> + <CharacterStyleRange AppliedCharacterStyle="$ID/NormalCharacterStyle"> + <Content>’</Content> + </CharacterStyleRange> + <CharacterStyleRange AppliedCharacterStyle="$ID/NormalCharacterStyle"> + <Content> are letters.</Content> + </CharacterStyleRange><Br /> +</ParagraphStyleRange> +<ParagraphStyleRange AppliedParagraphStyle="ParagraphStyle/Paragraph"> + <CharacterStyleRange AppliedCharacterStyle="$ID/NormalCharacterStyle"> + <Content>‘</Content> + </CharacterStyleRange> + <CharacterStyleRange AppliedCharacterStyle="$ID/NormalCharacterStyle"> + <Content>Oak,</Content> + </CharacterStyleRange> + <CharacterStyleRange AppliedCharacterStyle="$ID/NormalCharacterStyle"> + <Content>’</Content> + </CharacterStyleRange> + <CharacterStyleRange AppliedCharacterStyle="$ID/NormalCharacterStyle"> + <Content> </Content> + </CharacterStyleRange> + <CharacterStyleRange AppliedCharacterStyle="$ID/NormalCharacterStyle"> + <Content>‘</Content> + </CharacterStyleRange> + <CharacterStyleRange AppliedCharacterStyle="$ID/NormalCharacterStyle"> + <Content>elm,</Content> + </CharacterStyleRange> + <CharacterStyleRange AppliedCharacterStyle="$ID/NormalCharacterStyle"> + <Content>’</Content> + </CharacterStyleRange> + <CharacterStyleRange AppliedCharacterStyle="$ID/NormalCharacterStyle"> + <Content> and </Content> + </CharacterStyleRange> + <CharacterStyleRange AppliedCharacterStyle="$ID/NormalCharacterStyle"> + <Content>‘</Content> + </CharacterStyleRange> + <CharacterStyleRange AppliedCharacterStyle="$ID/NormalCharacterStyle"> + <Content>beech</Content> + </CharacterStyleRange> + <CharacterStyleRange AppliedCharacterStyle="$ID/NormalCharacterStyle"> + <Content>’</Content> + </CharacterStyleRange> + <CharacterStyleRange AppliedCharacterStyle="$ID/NormalCharacterStyle"> + <Content> are names of trees. So is </Content> + </CharacterStyleRange> + <CharacterStyleRange AppliedCharacterStyle="$ID/NormalCharacterStyle"> + <Content>‘</Content> + </CharacterStyleRange> + <CharacterStyleRange AppliedCharacterStyle="$ID/NormalCharacterStyle"> + <Content>pine.</Content> + </CharacterStyleRange> + <CharacterStyleRange AppliedCharacterStyle="$ID/NormalCharacterStyle"> + <Content>’</Content> + </CharacterStyleRange><Br /> +</ParagraphStyleRange> +<ParagraphStyleRange AppliedParagraphStyle="ParagraphStyle/Paragraph"> + <CharacterStyleRange AppliedCharacterStyle="$ID/NormalCharacterStyle"> + <Content>‘</Content> + </CharacterStyleRange> + <CharacterStyleRange AppliedCharacterStyle="$ID/NormalCharacterStyle"> + <Content>He said, </Content> + </CharacterStyleRange> + <CharacterStyleRange AppliedCharacterStyle="$ID/NormalCharacterStyle"> + <Content>“</Content> + </CharacterStyleRange> + <CharacterStyleRange AppliedCharacterStyle="$ID/NormalCharacterStyle"> + <Content>I want to go.</Content> + </CharacterStyleRange> + <CharacterStyleRange AppliedCharacterStyle="$ID/NormalCharacterStyle"> + <Content>”</Content> + </CharacterStyleRange> + <CharacterStyleRange AppliedCharacterStyle="$ID/NormalCharacterStyle"> + <Content>’</Content> + </CharacterStyleRange> + <CharacterStyleRange AppliedCharacterStyle="$ID/NormalCharacterStyle"> + <Content> Were you alive in the 70’s?</Content> + </CharacterStyleRange><Br /> +</ParagraphStyleRange> +<ParagraphStyleRange AppliedParagraphStyle="ParagraphStyle/Paragraph"> + <CharacterStyleRange AppliedCharacterStyle="$ID/NormalCharacterStyle"> + <Content>Here is some quoted </Content> + </CharacterStyleRange> + <CharacterStyleRange AppliedCharacterStyle="$ID/NormalCharacterStyle"> + <Content>‘</Content> + </CharacterStyleRange> + <CharacterStyleRange AppliedCharacterStyle="CharacterStyle/Code"> + <Content>code</Content> + </CharacterStyleRange> + <CharacterStyleRange AppliedCharacterStyle="$ID/NormalCharacterStyle"> + <Content>’</Content> + </CharacterStyleRange> + <CharacterStyleRange AppliedCharacterStyle="$ID/NormalCharacterStyle"> + <Content> and a </Content> + </CharacterStyleRange> + <CharacterStyleRange AppliedCharacterStyle="$ID/NormalCharacterStyle"> + <Content>“</Content> + </CharacterStyleRange> + <HyperlinkTextSource Self="htss-3" Name="" Hidden="false"> + <CharacterStyleRange AppliedCharacterStyle="CharacterStyle/Link"> + <Content>quoted link</Content> + </CharacterStyleRange> + </HyperlinkTextSource> + <CharacterStyleRange AppliedCharacterStyle="$ID/NormalCharacterStyle"> + <Content>”</Content> + </CharacterStyleRange> + <CharacterStyleRange AppliedCharacterStyle="$ID/NormalCharacterStyle"> + <Content>.</Content> + </CharacterStyleRange><Br /> +</ParagraphStyleRange> +<ParagraphStyleRange AppliedParagraphStyle="ParagraphStyle/Paragraph"> + <CharacterStyleRange AppliedCharacterStyle="$ID/NormalCharacterStyle"> + <Content>Some dashes: one—two — three—four — five.</Content> + </CharacterStyleRange><Br /> +</ParagraphStyleRange> +<ParagraphStyleRange AppliedParagraphStyle="ParagraphStyle/Paragraph"> + <CharacterStyleRange AppliedCharacterStyle="$ID/NormalCharacterStyle"> + <Content>Dashes between numbers: 5–7, 255–66, 1987–1999.</Content> + </CharacterStyleRange><Br /> +</ParagraphStyleRange> +<ParagraphStyleRange AppliedParagraphStyle="ParagraphStyle/Paragraph"> + <CharacterStyleRange AppliedCharacterStyle="$ID/NormalCharacterStyle"> + <Content>Ellipses…and…and….</Content> + </CharacterStyleRange><Br /> +</ParagraphStyleRange> +<ParagraphStyleRange AppliedParagraphStyle="ParagraphStyle/Header1"> + <CharacterStyleRange AppliedCharacterStyle="$ID/NormalCharacterStyle"> + <Content>LaTeX</Content> + </CharacterStyleRange><Br /> +</ParagraphStyleRange> +<ParagraphStyleRange AppliedParagraphStyle="ParagraphStyle/BulList > first" NumberingContinue="false"> + <CharacterStyleRange AppliedCharacterStyle="$ID/NormalCharacterStyle"> + <Content>\cite[22-23]{smith.1899}</Content> + </CharacterStyleRange><Br /> +</ParagraphStyleRange> +<ParagraphStyleRange AppliedParagraphStyle="ParagraphStyle/BulList"> + <CharacterStyleRange AppliedCharacterStyle="$ID/NormalCharacterStyle"> + <Content>2+2=4</Content> + </CharacterStyleRange><Br /> +</ParagraphStyleRange> +<ParagraphStyleRange AppliedParagraphStyle="ParagraphStyle/BulList"> + <CharacterStyleRange AppliedCharacterStyle="$ID/NormalCharacterStyle"> + <Content>x \in y</Content> + </CharacterStyleRange><Br /> +</ParagraphStyleRange> +<ParagraphStyleRange AppliedParagraphStyle="ParagraphStyle/BulList"> + <CharacterStyleRange AppliedCharacterStyle="$ID/NormalCharacterStyle"> + <Content>\alpha \wedge \omega</Content> + </CharacterStyleRange><Br /> +</ParagraphStyleRange> +<ParagraphStyleRange AppliedParagraphStyle="ParagraphStyle/BulList"> + <CharacterStyleRange AppliedCharacterStyle="$ID/NormalCharacterStyle"> + <Content>223</Content> + </CharacterStyleRange><Br /> +</ParagraphStyleRange> +<ParagraphStyleRange AppliedParagraphStyle="ParagraphStyle/BulList"> + <CharacterStyleRange AppliedCharacterStyle="$ID/NormalCharacterStyle"> + <Content>p</Content> + </CharacterStyleRange> + <CharacterStyleRange AppliedCharacterStyle="$ID/NormalCharacterStyle"> + <Content>-Tree</Content> + </CharacterStyleRange><Br /> +</ParagraphStyleRange> +<ParagraphStyleRange AppliedParagraphStyle="ParagraphStyle/BulList"> + <CharacterStyleRange AppliedCharacterStyle="$ID/NormalCharacterStyle"> + <Content>Here’s some display math: </Content> + </CharacterStyleRange> + <CharacterStyleRange AppliedCharacterStyle="$ID/NormalCharacterStyle"> + <Content>\frac{d}{dx}f(x)=\lim_{h\to 0}\frac{f(x+h)-f(x)}{h}</Content> + </CharacterStyleRange><Br /> +</ParagraphStyleRange> +<ParagraphStyleRange AppliedParagraphStyle="ParagraphStyle/BulList"> + <CharacterStyleRange AppliedCharacterStyle="$ID/NormalCharacterStyle"> + <Content>Here’s one that has a line break in it: </Content> + </CharacterStyleRange> + <CharacterStyleRange AppliedCharacterStyle="$ID/NormalCharacterStyle"> + <Content>\alpha + \omega \times x^2</Content> + </CharacterStyleRange> + <CharacterStyleRange AppliedCharacterStyle="$ID/NormalCharacterStyle"> + <Content>.</Content> + </CharacterStyleRange><Br /> +</ParagraphStyleRange> +<ParagraphStyleRange AppliedParagraphStyle="ParagraphStyle/Paragraph"> + <CharacterStyleRange AppliedCharacterStyle="$ID/NormalCharacterStyle"> + <Content>These shouldn’t be math:</Content> + </CharacterStyleRange><Br /> +</ParagraphStyleRange> +<ParagraphStyleRange AppliedParagraphStyle="ParagraphStyle/BulList > first" NumberingContinue="false"> + <CharacterStyleRange AppliedCharacterStyle="$ID/NormalCharacterStyle"> + <Content>To get the famous equation, write </Content> + </CharacterStyleRange> + <CharacterStyleRange AppliedCharacterStyle="CharacterStyle/Code"> + <Content>$e = mc^2$</Content> + </CharacterStyleRange> + <CharacterStyleRange AppliedCharacterStyle="$ID/NormalCharacterStyle"> + <Content>.</Content> + </CharacterStyleRange><Br /> +</ParagraphStyleRange> +<ParagraphStyleRange AppliedParagraphStyle="ParagraphStyle/BulList"> + <CharacterStyleRange AppliedCharacterStyle="$ID/NormalCharacterStyle"> + <Content>$22,000 is a </Content> + </CharacterStyleRange> + <CharacterStyleRange AppliedCharacterStyle="CharacterStyle/Italic"> + <Content>lot</Content> + </CharacterStyleRange> + <CharacterStyleRange AppliedCharacterStyle="$ID/NormalCharacterStyle"> + <Content> of money. So is $34,000. (It worked if </Content> + </CharacterStyleRange> + <CharacterStyleRange AppliedCharacterStyle="$ID/NormalCharacterStyle"> + <Content>“</Content> + </CharacterStyleRange> + <CharacterStyleRange AppliedCharacterStyle="$ID/NormalCharacterStyle"> + <Content>lot</Content> + </CharacterStyleRange> + <CharacterStyleRange AppliedCharacterStyle="$ID/NormalCharacterStyle"> + <Content>”</Content> + </CharacterStyleRange> + <CharacterStyleRange AppliedCharacterStyle="$ID/NormalCharacterStyle"> + <Content> is emphasized.)</Content> + </CharacterStyleRange><Br /> +</ParagraphStyleRange> +<ParagraphStyleRange AppliedParagraphStyle="ParagraphStyle/BulList"> + <CharacterStyleRange AppliedCharacterStyle="$ID/NormalCharacterStyle"> + <Content>Shoes ($20) and socks ($5).</Content> + </CharacterStyleRange><Br /> +</ParagraphStyleRange> +<ParagraphStyleRange AppliedParagraphStyle="ParagraphStyle/BulList"> + <CharacterStyleRange AppliedCharacterStyle="$ID/NormalCharacterStyle"> + <Content>Escaped </Content> + </CharacterStyleRange> + <CharacterStyleRange AppliedCharacterStyle="CharacterStyle/Code"> + <Content>$</Content> + </CharacterStyleRange> + <CharacterStyleRange AppliedCharacterStyle="$ID/NormalCharacterStyle"> + <Content>: $73 </Content> + </CharacterStyleRange> + <CharacterStyleRange AppliedCharacterStyle="CharacterStyle/Italic"> + <Content>this should be emphasized</Content> + </CharacterStyleRange> + <CharacterStyleRange AppliedCharacterStyle="$ID/NormalCharacterStyle"> + <Content> 23$.</Content> + </CharacterStyleRange><Br /> +</ParagraphStyleRange> +<ParagraphStyleRange AppliedParagraphStyle="ParagraphStyle/Paragraph"> + <CharacterStyleRange AppliedCharacterStyle="$ID/NormalCharacterStyle"> + <Content>Here’s a LaTeX table:</Content> + </CharacterStyleRange><Br /> +</ParagraphStyleRange> +<ParagraphStyleRange AppliedParagraphStyle="ParagraphStyle/Rawblock"> + <CharacterStyleRange AppliedCharacterStyle="$ID/NormalCharacterStyle"> + <Content>\begin{tabular}{|l|l|}\hline +Animal & Number \\ \hline +Dog & 2 \\ +Cat & 1 \\ \hline +\end{tabular}</Content> + </CharacterStyleRange><Br /> +</ParagraphStyleRange> +<ParagraphStyleRange AppliedParagraphStyle="ParagraphStyle/Header1"> + <CharacterStyleRange AppliedCharacterStyle="$ID/NormalCharacterStyle"> + <Content>Special Characters</Content> + </CharacterStyleRange><Br /> +</ParagraphStyleRange> +<ParagraphStyleRange AppliedParagraphStyle="ParagraphStyle/Paragraph"> + <CharacterStyleRange AppliedCharacterStyle="$ID/NormalCharacterStyle"> + <Content>Here is some unicode:</Content> + </CharacterStyleRange><Br /> +</ParagraphStyleRange> +<ParagraphStyleRange AppliedParagraphStyle="ParagraphStyle/BulList > first" NumberingContinue="false"> + <CharacterStyleRange AppliedCharacterStyle="$ID/NormalCharacterStyle"> + <Content>I hat: Î</Content> + </CharacterStyleRange><Br /> +</ParagraphStyleRange> +<ParagraphStyleRange AppliedParagraphStyle="ParagraphStyle/BulList"> + <CharacterStyleRange AppliedCharacterStyle="$ID/NormalCharacterStyle"> + <Content>o umlaut: ö</Content> + </CharacterStyleRange><Br /> +</ParagraphStyleRange> +<ParagraphStyleRange AppliedParagraphStyle="ParagraphStyle/BulList"> + <CharacterStyleRange AppliedCharacterStyle="$ID/NormalCharacterStyle"> + <Content>section: §</Content> + </CharacterStyleRange><Br /> +</ParagraphStyleRange> +<ParagraphStyleRange AppliedParagraphStyle="ParagraphStyle/BulList"> + <CharacterStyleRange AppliedCharacterStyle="$ID/NormalCharacterStyle"> + <Content>set membership: ∈</Content> + </CharacterStyleRange><Br /> +</ParagraphStyleRange> +<ParagraphStyleRange AppliedParagraphStyle="ParagraphStyle/BulList"> + <CharacterStyleRange AppliedCharacterStyle="$ID/NormalCharacterStyle"> + <Content>copyright: ©</Content> + </CharacterStyleRange><Br /> +</ParagraphStyleRange> +<ParagraphStyleRange AppliedParagraphStyle="ParagraphStyle/Paragraph"> + <CharacterStyleRange AppliedCharacterStyle="$ID/NormalCharacterStyle"> + <Content>AT&T has an ampersand in their name.</Content> + </CharacterStyleRange><Br /> +</ParagraphStyleRange> +<ParagraphStyleRange AppliedParagraphStyle="ParagraphStyle/Paragraph"> + <CharacterStyleRange AppliedCharacterStyle="$ID/NormalCharacterStyle"> + <Content>AT&T is another way to write it.</Content> + </CharacterStyleRange><Br /> +</ParagraphStyleRange> +<ParagraphStyleRange AppliedParagraphStyle="ParagraphStyle/Paragraph"> + <CharacterStyleRange AppliedCharacterStyle="$ID/NormalCharacterStyle"> + <Content>This & that.</Content> + </CharacterStyleRange><Br /> +</ParagraphStyleRange> +<ParagraphStyleRange AppliedParagraphStyle="ParagraphStyle/Paragraph"> + <CharacterStyleRange AppliedCharacterStyle="$ID/NormalCharacterStyle"> + <Content>4 < 5.</Content> + </CharacterStyleRange><Br /> +</ParagraphStyleRange> +<ParagraphStyleRange AppliedParagraphStyle="ParagraphStyle/Paragraph"> + <CharacterStyleRange AppliedCharacterStyle="$ID/NormalCharacterStyle"> + <Content>6 > 5.</Content> + </CharacterStyleRange><Br /> +</ParagraphStyleRange> +<ParagraphStyleRange AppliedParagraphStyle="ParagraphStyle/Paragraph"> + <CharacterStyleRange AppliedCharacterStyle="$ID/NormalCharacterStyle"> + <Content>Backslash: \</Content> + </CharacterStyleRange><Br /> +</ParagraphStyleRange> +<ParagraphStyleRange AppliedParagraphStyle="ParagraphStyle/Paragraph"> + <CharacterStyleRange AppliedCharacterStyle="$ID/NormalCharacterStyle"> + <Content>Backtick: `</Content> + </CharacterStyleRange><Br /> +</ParagraphStyleRange> +<ParagraphStyleRange AppliedParagraphStyle="ParagraphStyle/Paragraph"> + <CharacterStyleRange AppliedCharacterStyle="$ID/NormalCharacterStyle"> + <Content>Asterisk: *</Content> + </CharacterStyleRange><Br /> +</ParagraphStyleRange> +<ParagraphStyleRange AppliedParagraphStyle="ParagraphStyle/Paragraph"> + <CharacterStyleRange AppliedCharacterStyle="$ID/NormalCharacterStyle"> + <Content>Underscore: _</Content> + </CharacterStyleRange><Br /> +</ParagraphStyleRange> +<ParagraphStyleRange AppliedParagraphStyle="ParagraphStyle/Paragraph"> + <CharacterStyleRange AppliedCharacterStyle="$ID/NormalCharacterStyle"> + <Content>Left brace: {</Content> + </CharacterStyleRange><Br /> +</ParagraphStyleRange> +<ParagraphStyleRange AppliedParagraphStyle="ParagraphStyle/Paragraph"> + <CharacterStyleRange AppliedCharacterStyle="$ID/NormalCharacterStyle"> + <Content>Right brace: }</Content> + </CharacterStyleRange><Br /> +</ParagraphStyleRange> +<ParagraphStyleRange AppliedParagraphStyle="ParagraphStyle/Paragraph"> + <CharacterStyleRange AppliedCharacterStyle="$ID/NormalCharacterStyle"> + <Content>Left bracket: [</Content> + </CharacterStyleRange><Br /> +</ParagraphStyleRange> +<ParagraphStyleRange AppliedParagraphStyle="ParagraphStyle/Paragraph"> + <CharacterStyleRange AppliedCharacterStyle="$ID/NormalCharacterStyle"> + <Content>Right bracket: ]</Content> + </CharacterStyleRange><Br /> +</ParagraphStyleRange> +<ParagraphStyleRange AppliedParagraphStyle="ParagraphStyle/Paragraph"> + <CharacterStyleRange AppliedCharacterStyle="$ID/NormalCharacterStyle"> + <Content>Left paren: (</Content> + </CharacterStyleRange><Br /> +</ParagraphStyleRange> +<ParagraphStyleRange AppliedParagraphStyle="ParagraphStyle/Paragraph"> + <CharacterStyleRange AppliedCharacterStyle="$ID/NormalCharacterStyle"> + <Content>Right paren: )</Content> + </CharacterStyleRange><Br /> +</ParagraphStyleRange> +<ParagraphStyleRange AppliedParagraphStyle="ParagraphStyle/Paragraph"> + <CharacterStyleRange AppliedCharacterStyle="$ID/NormalCharacterStyle"> + <Content>Greater-than: ></Content> + </CharacterStyleRange><Br /> +</ParagraphStyleRange> +<ParagraphStyleRange AppliedParagraphStyle="ParagraphStyle/Paragraph"> + <CharacterStyleRange AppliedCharacterStyle="$ID/NormalCharacterStyle"> + <Content>Hash: #</Content> + </CharacterStyleRange><Br /> +</ParagraphStyleRange> +<ParagraphStyleRange AppliedParagraphStyle="ParagraphStyle/Paragraph"> + <CharacterStyleRange AppliedCharacterStyle="$ID/NormalCharacterStyle"> + <Content>Period: .</Content> + </CharacterStyleRange><Br /> +</ParagraphStyleRange> +<ParagraphStyleRange AppliedParagraphStyle="ParagraphStyle/Paragraph"> + <CharacterStyleRange AppliedCharacterStyle="$ID/NormalCharacterStyle"> + <Content>Bang: !</Content> + </CharacterStyleRange><Br /> +</ParagraphStyleRange> +<ParagraphStyleRange AppliedParagraphStyle="ParagraphStyle/Paragraph"> + <CharacterStyleRange AppliedCharacterStyle="$ID/NormalCharacterStyle"> + <Content>Plus: +</Content> + </CharacterStyleRange><Br /> +</ParagraphStyleRange> +<ParagraphStyleRange AppliedParagraphStyle="ParagraphStyle/Paragraph"> + <CharacterStyleRange AppliedCharacterStyle="$ID/NormalCharacterStyle"> + <Content>Minus: -</Content> + </CharacterStyleRange><Br /> +</ParagraphStyleRange> +<ParagraphStyleRange AppliedParagraphStyle="ParagraphStyle/Header1"> + <CharacterStyleRange AppliedCharacterStyle="$ID/NormalCharacterStyle"> + <Content>Links</Content> + </CharacterStyleRange><Br /> +</ParagraphStyleRange> +<ParagraphStyleRange AppliedParagraphStyle="ParagraphStyle/Header2"> + <CharacterStyleRange AppliedCharacterStyle="$ID/NormalCharacterStyle"> + <Content>Explicit</Content> + </CharacterStyleRange><Br /> +</ParagraphStyleRange> +<ParagraphStyleRange AppliedParagraphStyle="ParagraphStyle/Paragraph"> + <CharacterStyleRange AppliedCharacterStyle="$ID/NormalCharacterStyle"> + <Content>Just a </Content> + </CharacterStyleRange> + <HyperlinkTextSource Self="htss-4" Name="" Hidden="false"> + <CharacterStyleRange AppliedCharacterStyle="CharacterStyle/Link"> + <Content>URL</Content> + </CharacterStyleRange> + </HyperlinkTextSource> + <CharacterStyleRange AppliedCharacterStyle="$ID/NormalCharacterStyle"> + <Content>.</Content> + </CharacterStyleRange><Br /> +</ParagraphStyleRange> +<ParagraphStyleRange AppliedParagraphStyle="ParagraphStyle/Paragraph"> + <HyperlinkTextSource Self="htss-5" Name="title" Hidden="false"> + <CharacterStyleRange AppliedCharacterStyle="CharacterStyle/Link"> + <Content>URL and title</Content> + </CharacterStyleRange> + </HyperlinkTextSource> + <CharacterStyleRange AppliedCharacterStyle="$ID/NormalCharacterStyle"> + <Content>.</Content> + </CharacterStyleRange><Br /> +</ParagraphStyleRange> +<ParagraphStyleRange AppliedParagraphStyle="ParagraphStyle/Paragraph"> + <HyperlinkTextSource Self="htss-6" Name="title preceded by two spaces" Hidden="false"> + <CharacterStyleRange AppliedCharacterStyle="CharacterStyle/Link"> + <Content>URL and title</Content> + </CharacterStyleRange> + </HyperlinkTextSource> + <CharacterStyleRange AppliedCharacterStyle="$ID/NormalCharacterStyle"> + <Content>.</Content> + </CharacterStyleRange><Br /> +</ParagraphStyleRange> +<ParagraphStyleRange AppliedParagraphStyle="ParagraphStyle/Paragraph"> + <HyperlinkTextSource Self="htss-7" Name="title preceded by a tab" Hidden="false"> + <CharacterStyleRange AppliedCharacterStyle="CharacterStyle/Link"> + <Content>URL and title</Content> + </CharacterStyleRange> + </HyperlinkTextSource> + <CharacterStyleRange AppliedCharacterStyle="$ID/NormalCharacterStyle"> + <Content>.</Content> + </CharacterStyleRange><Br /> +</ParagraphStyleRange> +<ParagraphStyleRange AppliedParagraphStyle="ParagraphStyle/Paragraph"> + <HyperlinkTextSource Self="htss-8" Name="title with "quotes" in it" Hidden="false"> + <CharacterStyleRange AppliedCharacterStyle="CharacterStyle/Link"> + <Content>URL and title</Content> + </CharacterStyleRange> + </HyperlinkTextSource><Br /> +</ParagraphStyleRange> +<ParagraphStyleRange AppliedParagraphStyle="ParagraphStyle/Paragraph"> + <HyperlinkTextSource Self="htss-9" Name="title with single quotes" Hidden="false"> + <CharacterStyleRange AppliedCharacterStyle="CharacterStyle/Link"> + <Content>URL and title</Content> + </CharacterStyleRange> + </HyperlinkTextSource><Br /> +</ParagraphStyleRange> +<ParagraphStyleRange AppliedParagraphStyle="ParagraphStyle/Paragraph"> + <HyperlinkTextSource Self="htss-10" Name="" Hidden="false"> + <CharacterStyleRange AppliedCharacterStyle="CharacterStyle/Link"> + <Content>with_underscore</Content> + </CharacterStyleRange> + </HyperlinkTextSource><Br /> +</ParagraphStyleRange> +<ParagraphStyleRange AppliedParagraphStyle="ParagraphStyle/Paragraph"> + <HyperlinkTextSource Self="htss-11" Name="" Hidden="false"> + <CharacterStyleRange AppliedCharacterStyle="CharacterStyle/Link"> + <Content>Email link</Content> + </CharacterStyleRange> + </HyperlinkTextSource><Br /> +</ParagraphStyleRange> +<ParagraphStyleRange AppliedParagraphStyle="ParagraphStyle/Paragraph"> + <HyperlinkTextSource Self="htss-12" Name="" Hidden="false"> + <CharacterStyleRange AppliedCharacterStyle="CharacterStyle/Link"> + <Content>Empty</Content> + </CharacterStyleRange> + </HyperlinkTextSource> + <CharacterStyleRange AppliedCharacterStyle="$ID/NormalCharacterStyle"> + <Content>.</Content> + </CharacterStyleRange><Br /> +</ParagraphStyleRange> +<ParagraphStyleRange AppliedParagraphStyle="ParagraphStyle/Header2"> + <CharacterStyleRange AppliedCharacterStyle="$ID/NormalCharacterStyle"> + <Content>Reference</Content> + </CharacterStyleRange><Br /> +</ParagraphStyleRange> +<ParagraphStyleRange AppliedParagraphStyle="ParagraphStyle/Paragraph"> + <CharacterStyleRange AppliedCharacterStyle="$ID/NormalCharacterStyle"> + <Content>Foo </Content> + </CharacterStyleRange> + <HyperlinkTextSource Self="htss-13" Name="" Hidden="false"> + <CharacterStyleRange AppliedCharacterStyle="CharacterStyle/Link"> + <Content>bar</Content> + </CharacterStyleRange> + </HyperlinkTextSource> + <CharacterStyleRange AppliedCharacterStyle="$ID/NormalCharacterStyle"> + <Content>.</Content> + </CharacterStyleRange><Br /> +</ParagraphStyleRange> +<ParagraphStyleRange AppliedParagraphStyle="ParagraphStyle/Paragraph"> + <CharacterStyleRange AppliedCharacterStyle="$ID/NormalCharacterStyle"> + <Content>Foo </Content> + </CharacterStyleRange> + <HyperlinkTextSource Self="htss-14" Name="" Hidden="false"> + <CharacterStyleRange AppliedCharacterStyle="CharacterStyle/Link"> + <Content>bar</Content> + </CharacterStyleRange> + </HyperlinkTextSource> + <CharacterStyleRange AppliedCharacterStyle="$ID/NormalCharacterStyle"> + <Content>.</Content> + </CharacterStyleRange><Br /> +</ParagraphStyleRange> +<ParagraphStyleRange AppliedParagraphStyle="ParagraphStyle/Paragraph"> + <CharacterStyleRange AppliedCharacterStyle="$ID/NormalCharacterStyle"> + <Content>Foo </Content> + </CharacterStyleRange> + <HyperlinkTextSource Self="htss-15" Name="" Hidden="false"> + <CharacterStyleRange AppliedCharacterStyle="CharacterStyle/Link"> + <Content>bar</Content> + </CharacterStyleRange> + </HyperlinkTextSource> + <CharacterStyleRange AppliedCharacterStyle="$ID/NormalCharacterStyle"> + <Content>.</Content> + </CharacterStyleRange><Br /> +</ParagraphStyleRange> +<ParagraphStyleRange AppliedParagraphStyle="ParagraphStyle/Paragraph"> + <CharacterStyleRange AppliedCharacterStyle="$ID/NormalCharacterStyle"> + <Content>With </Content> + </CharacterStyleRange> + <HyperlinkTextSource Self="htss-16" Name="" Hidden="false"> + <CharacterStyleRange AppliedCharacterStyle="CharacterStyle/Link"> + <Content>embedded [brackets]</Content> + </CharacterStyleRange> + </HyperlinkTextSource> + <CharacterStyleRange AppliedCharacterStyle="$ID/NormalCharacterStyle"> + <Content>.</Content> + </CharacterStyleRange><Br /> +</ParagraphStyleRange> +<ParagraphStyleRange AppliedParagraphStyle="ParagraphStyle/Paragraph"> + <HyperlinkTextSource Self="htss-17" Name="" Hidden="false"> + <CharacterStyleRange AppliedCharacterStyle="CharacterStyle/Link"> + <Content>b</Content> + </CharacterStyleRange> + </HyperlinkTextSource> + <CharacterStyleRange AppliedCharacterStyle="$ID/NormalCharacterStyle"> + <Content> by itself should be a link.</Content> + </CharacterStyleRange><Br /> +</ParagraphStyleRange> +<ParagraphStyleRange AppliedParagraphStyle="ParagraphStyle/Paragraph"> + <CharacterStyleRange AppliedCharacterStyle="$ID/NormalCharacterStyle"> + <Content>Indented </Content> + </CharacterStyleRange> + <HyperlinkTextSource Self="htss-18" Name="" Hidden="false"> + <CharacterStyleRange AppliedCharacterStyle="CharacterStyle/Link"> + <Content>once</Content> + </CharacterStyleRange> + </HyperlinkTextSource> + <CharacterStyleRange AppliedCharacterStyle="$ID/NormalCharacterStyle"> + <Content>.</Content> + </CharacterStyleRange><Br /> +</ParagraphStyleRange> +<ParagraphStyleRange AppliedParagraphStyle="ParagraphStyle/Paragraph"> + <CharacterStyleRange AppliedCharacterStyle="$ID/NormalCharacterStyle"> + <Content>Indented </Content> + </CharacterStyleRange> + <HyperlinkTextSource Self="htss-19" Name="" Hidden="false"> + <CharacterStyleRange AppliedCharacterStyle="CharacterStyle/Link"> + <Content>twice</Content> + </CharacterStyleRange> + </HyperlinkTextSource> + <CharacterStyleRange AppliedCharacterStyle="$ID/NormalCharacterStyle"> + <Content>.</Content> + </CharacterStyleRange><Br /> +</ParagraphStyleRange> +<ParagraphStyleRange AppliedParagraphStyle="ParagraphStyle/Paragraph"> + <CharacterStyleRange AppliedCharacterStyle="$ID/NormalCharacterStyle"> + <Content>Indented </Content> + </CharacterStyleRange> + <HyperlinkTextSource Self="htss-20" Name="" Hidden="false"> + <CharacterStyleRange AppliedCharacterStyle="CharacterStyle/Link"> + <Content>thrice</Content> + </CharacterStyleRange> + </HyperlinkTextSource> + <CharacterStyleRange AppliedCharacterStyle="$ID/NormalCharacterStyle"> + <Content>.</Content> + </CharacterStyleRange><Br /> +</ParagraphStyleRange> +<ParagraphStyleRange AppliedParagraphStyle="ParagraphStyle/Paragraph"> + <CharacterStyleRange AppliedCharacterStyle="$ID/NormalCharacterStyle"> + <Content>This should [not][] be a link.</Content> + </CharacterStyleRange><Br /> +</ParagraphStyleRange> +<ParagraphStyleRange AppliedParagraphStyle="ParagraphStyle/CodeBlock"> + <CharacterStyleRange AppliedCharacterStyle="$ID/NormalCharacterStyle"> + <Content>[not]: /url</Content> + </CharacterStyleRange><Br /> +</ParagraphStyleRange> +<ParagraphStyleRange AppliedParagraphStyle="ParagraphStyle/Paragraph"> + <CharacterStyleRange AppliedCharacterStyle="$ID/NormalCharacterStyle"> + <Content>Foo </Content> + </CharacterStyleRange> + <HyperlinkTextSource Self="htss-21" Name="Title with "quotes" inside" Hidden="false"> + <CharacterStyleRange AppliedCharacterStyle="CharacterStyle/Link"> + <Content>bar</Content> + </CharacterStyleRange> + </HyperlinkTextSource> + <CharacterStyleRange AppliedCharacterStyle="$ID/NormalCharacterStyle"> + <Content>.</Content> + </CharacterStyleRange><Br /> +</ParagraphStyleRange> +<ParagraphStyleRange AppliedParagraphStyle="ParagraphStyle/Paragraph"> + <CharacterStyleRange AppliedCharacterStyle="$ID/NormalCharacterStyle"> + <Content>Foo </Content> + </CharacterStyleRange> + <HyperlinkTextSource Self="htss-22" Name="Title with "quote" inside" Hidden="false"> + <CharacterStyleRange AppliedCharacterStyle="CharacterStyle/Link"> + <Content>biz</Content> + </CharacterStyleRange> + </HyperlinkTextSource> + <CharacterStyleRange AppliedCharacterStyle="$ID/NormalCharacterStyle"> + <Content>.</Content> + </CharacterStyleRange><Br /> +</ParagraphStyleRange> +<ParagraphStyleRange AppliedParagraphStyle="ParagraphStyle/Header2"> + <CharacterStyleRange AppliedCharacterStyle="$ID/NormalCharacterStyle"> + <Content>With ampersands</Content> + </CharacterStyleRange><Br /> +</ParagraphStyleRange> +<ParagraphStyleRange AppliedParagraphStyle="ParagraphStyle/Paragraph"> + <CharacterStyleRange AppliedCharacterStyle="$ID/NormalCharacterStyle"> + <Content>Here’s a </Content> + </CharacterStyleRange> + <HyperlinkTextSource Self="htss-23" Name="" Hidden="false"> + <CharacterStyleRange AppliedCharacterStyle="CharacterStyle/Link"> + <Content>link with an ampersand in the URL</Content> + </CharacterStyleRange> + </HyperlinkTextSource> + <CharacterStyleRange AppliedCharacterStyle="$ID/NormalCharacterStyle"> + <Content>.</Content> + </CharacterStyleRange><Br /> +</ParagraphStyleRange> +<ParagraphStyleRange AppliedParagraphStyle="ParagraphStyle/Paragraph"> + <CharacterStyleRange AppliedCharacterStyle="$ID/NormalCharacterStyle"> + <Content>Here’s a link with an amersand in the link text: </Content> + </CharacterStyleRange> + <HyperlinkTextSource Self="htss-24" Name="AT&T" Hidden="false"> + <CharacterStyleRange AppliedCharacterStyle="CharacterStyle/Link"> + <Content>AT&T</Content> + </CharacterStyleRange> + </HyperlinkTextSource> + <CharacterStyleRange AppliedCharacterStyle="$ID/NormalCharacterStyle"> + <Content>.</Content> + </CharacterStyleRange><Br /> +</ParagraphStyleRange> +<ParagraphStyleRange AppliedParagraphStyle="ParagraphStyle/Paragraph"> + <CharacterStyleRange AppliedCharacterStyle="$ID/NormalCharacterStyle"> + <Content>Here’s an </Content> + </CharacterStyleRange> + <HyperlinkTextSource Self="htss-25" Name="" Hidden="false"> + <CharacterStyleRange AppliedCharacterStyle="CharacterStyle/Link"> + <Content>inline link</Content> + </CharacterStyleRange> + </HyperlinkTextSource> + <CharacterStyleRange AppliedCharacterStyle="$ID/NormalCharacterStyle"> + <Content>.</Content> + </CharacterStyleRange><Br /> +</ParagraphStyleRange> +<ParagraphStyleRange AppliedParagraphStyle="ParagraphStyle/Paragraph"> + <CharacterStyleRange AppliedCharacterStyle="$ID/NormalCharacterStyle"> + <Content>Here’s an </Content> + </CharacterStyleRange> + <HyperlinkTextSource Self="htss-26" Name="" Hidden="false"> + <CharacterStyleRange AppliedCharacterStyle="CharacterStyle/Link"> + <Content>inline link in pointy braces</Content> + </CharacterStyleRange> + </HyperlinkTextSource> + <CharacterStyleRange AppliedCharacterStyle="$ID/NormalCharacterStyle"> + <Content>.</Content> + </CharacterStyleRange><Br /> +</ParagraphStyleRange> +<ParagraphStyleRange AppliedParagraphStyle="ParagraphStyle/Header2"> + <CharacterStyleRange AppliedCharacterStyle="$ID/NormalCharacterStyle"> + <Content>Autolinks</Content> + </CharacterStyleRange><Br /> +</ParagraphStyleRange> +<ParagraphStyleRange AppliedParagraphStyle="ParagraphStyle/Paragraph"> + <CharacterStyleRange AppliedCharacterStyle="$ID/NormalCharacterStyle"> + <Content>With an ampersand: </Content> + </CharacterStyleRange> + <HyperlinkTextSource Self="htss-27" Name="" Hidden="false"> + <CharacterStyleRange AppliedCharacterStyle="CharacterStyle/Link"> + <Content>http://example.com/?foo=1&bar=2</Content> + </CharacterStyleRange> + </HyperlinkTextSource><Br /> +</ParagraphStyleRange> +<ParagraphStyleRange AppliedParagraphStyle="ParagraphStyle/BulList > first" NumberingContinue="false"> + <CharacterStyleRange AppliedCharacterStyle="$ID/NormalCharacterStyle"> + <Content>In a list?</Content> + </CharacterStyleRange><Br /> +</ParagraphStyleRange> +<ParagraphStyleRange AppliedParagraphStyle="ParagraphStyle/BulList"> + <HyperlinkTextSource Self="htss-28" Name="" Hidden="false"> + <CharacterStyleRange AppliedCharacterStyle="CharacterStyle/Link"> + <Content>http://example.com/</Content> + </CharacterStyleRange> + </HyperlinkTextSource><Br /> +</ParagraphStyleRange> +<ParagraphStyleRange AppliedParagraphStyle="ParagraphStyle/BulList"> + <CharacterStyleRange AppliedCharacterStyle="$ID/NormalCharacterStyle"> + <Content>It should.</Content> + </CharacterStyleRange><Br /> +</ParagraphStyleRange> +<ParagraphStyleRange AppliedParagraphStyle="ParagraphStyle/Paragraph"> + <CharacterStyleRange AppliedCharacterStyle="$ID/NormalCharacterStyle"> + <Content>An e-mail address: </Content> + </CharacterStyleRange> + <HyperlinkTextSource Self="htss-29" Name="" Hidden="false"> + <CharacterStyleRange AppliedCharacterStyle="CharacterStyle/Link"> + <Content>nobody@nowhere.net</Content> + </CharacterStyleRange> + </HyperlinkTextSource><Br /> +</ParagraphStyleRange> +<ParagraphStyleRange AppliedParagraphStyle="ParagraphStyle/Blockquote > Paragraph"> + <CharacterStyleRange AppliedCharacterStyle="$ID/NormalCharacterStyle"> + <Content>Blockquoted: </Content> + </CharacterStyleRange> + <HyperlinkTextSource Self="htss-30" Name="" Hidden="false"> + <CharacterStyleRange AppliedCharacterStyle="CharacterStyle/Link"> + <Content>http://example.com/</Content> + </CharacterStyleRange> + </HyperlinkTextSource><Br /> +</ParagraphStyleRange> +<ParagraphStyleRange AppliedParagraphStyle="ParagraphStyle/Paragraph"> + <CharacterStyleRange AppliedCharacterStyle="$ID/NormalCharacterStyle"> + <Content>Auto-links should not occur here: </Content> + </CharacterStyleRange> + <CharacterStyleRange AppliedCharacterStyle="CharacterStyle/Code"> + <Content><http://example.com/></Content> + </CharacterStyleRange><Br /> +</ParagraphStyleRange> +<ParagraphStyleRange AppliedParagraphStyle="ParagraphStyle/CodeBlock"> + <CharacterStyleRange AppliedCharacterStyle="$ID/NormalCharacterStyle"> + <Content>or here: <http://example.com/></Content> + </CharacterStyleRange><Br /> +</ParagraphStyleRange> +<ParagraphStyleRange AppliedParagraphStyle="ParagraphStyle/Header1"> + <CharacterStyleRange AppliedCharacterStyle="$ID/NormalCharacterStyle"> + <Content>Images</Content> + </CharacterStyleRange><Br /> +</ParagraphStyleRange> +<ParagraphStyleRange AppliedParagraphStyle="ParagraphStyle/Paragraph"> + <CharacterStyleRange AppliedCharacterStyle="$ID/NormalCharacterStyle"> + <Content>From </Content> + </CharacterStyleRange> + <CharacterStyleRange AppliedCharacterStyle="$ID/NormalCharacterStyle"> + <Content>“</Content> + </CharacterStyleRange> + <CharacterStyleRange AppliedCharacterStyle="$ID/NormalCharacterStyle"> + <Content>Voyage dans la Lune</Content> + </CharacterStyleRange> + <CharacterStyleRange AppliedCharacterStyle="$ID/NormalCharacterStyle"> + <Content>”</Content> + </CharacterStyleRange> + <CharacterStyleRange AppliedCharacterStyle="$ID/NormalCharacterStyle"> + <Content> by Georges Melies (1902):</Content> + </CharacterStyleRange><Br /> +</ParagraphStyleRange> +<ParagraphStyleRange AppliedParagraphStyle="ParagraphStyle/Paragraph"> + <CharacterStyleRange AppliedCharacterStyle="$ID/NormalCharacterStyle"> + <Rectangle Self="uec" ItemTransform="1 0 0 1 75 -50"> + <Properties> + <PathGeometry> + <GeometryPathType PathOpen="false"> + <PathPointArray> + <PathPointType Anchor="-75 -50" LeftDirection="-75 -50" RightDirection="-75 -50" /> + <PathPointType Anchor="-75 50" LeftDirection="-75 50" RightDirection="-75 50" /> + <PathPointType Anchor="75 50" LeftDirection="75 50" RightDirection="75 50" /> + <PathPointType Anchor="75 -50" LeftDirection="75 -50" RightDirection="75 -50" /> + </PathPointArray> + </GeometryPathType> + </PathGeometry> + </Properties> + <Image Self="ue6" ItemTransform="1.0 0 0 1.0 -75 -50"> + <Properties> + <Profile type="string"> + $ID/Embedded + <GraphicBounds Left="0" Top="0" Right="150" Bottom="100" /> + </Profile> + </Properties> + <Link Self="ueb" LinkResourceURI="lalune.jpg" /> + </Image> + </Rectangle> + </CharacterStyleRange><Br /> +</ParagraphStyleRange> +<ParagraphStyleRange AppliedParagraphStyle="ParagraphStyle/Paragraph"> + <CharacterStyleRange AppliedCharacterStyle="$ID/NormalCharacterStyle"> + <Content>Here is a movie </Content> + </CharacterStyleRange> + <CharacterStyleRange AppliedCharacterStyle="$ID/NormalCharacterStyle"> + <Rectangle Self="uec" ItemTransform="1 0 0 1 75 -50"> + <Properties> + <PathGeometry> + <GeometryPathType PathOpen="false"> + <PathPointArray> + <PathPointType Anchor="-75 -50" LeftDirection="-75 -50" RightDirection="-75 -50" /> + <PathPointType Anchor="-75 50" LeftDirection="-75 50" RightDirection="-75 50" /> + <PathPointType Anchor="75 50" LeftDirection="75 50" RightDirection="75 50" /> + <PathPointType Anchor="75 -50" LeftDirection="75 -50" RightDirection="75 -50" /> + </PathPointArray> + </GeometryPathType> + </PathGeometry> + </Properties> + <Image Self="ue6" ItemTransform="1.0 0 0 1.0 -75 -50"> + <Properties> + <Profile type="string"> + $ID/Embedded + <GraphicBounds Left="0" Top="0" Right="150" Bottom="100" /> + </Profile> + </Properties> + <Link Self="ueb" LinkResourceURI="movie.jpg" /> + </Image> + </Rectangle> + </CharacterStyleRange> + <CharacterStyleRange AppliedCharacterStyle="$ID/NormalCharacterStyle"> + <Content> icon.</Content> + </CharacterStyleRange><Br /> +</ParagraphStyleRange> +<ParagraphStyleRange AppliedParagraphStyle="ParagraphStyle/Header1"> + <CharacterStyleRange AppliedCharacterStyle="$ID/NormalCharacterStyle"> + <Content>Footnotes</Content> + </CharacterStyleRange><Br /> +</ParagraphStyleRange> +<ParagraphStyleRange AppliedParagraphStyle="ParagraphStyle/Paragraph"> + <CharacterStyleRange AppliedCharacterStyle="$ID/NormalCharacterStyle"> + <Content>Here is a footnote reference,</Content> + </CharacterStyleRange> + <CharacterStyleRange AppliedCharacterStyle="$ID/NormalCharacterStyle" Position="Superscript"> + <Footnote> + <ParagraphStyleRange> + <CharacterStyleRange> + <Content><?ACE 4?></Content> + </CharacterStyleRange> + </ParagraphStyleRange> + <ParagraphStyleRange AppliedParagraphStyle="ParagraphStyle/Footnote > Paragraph"> + <CharacterStyleRange AppliedCharacterStyle="$ID/NormalCharacterStyle"> + <Content> </Content> + </CharacterStyleRange> + <CharacterStyleRange AppliedCharacterStyle="$ID/NormalCharacterStyle"> + <Content>Here is the footnote. It can go anywhere after the footnote reference. It need not be placed at the end of the document.</Content> + </CharacterStyleRange><Br /> + </ParagraphStyleRange> + </Footnote> + </CharacterStyleRange> + <CharacterStyleRange AppliedCharacterStyle="$ID/NormalCharacterStyle"> + <Content> and another.</Content> + </CharacterStyleRange> + <CharacterStyleRange AppliedCharacterStyle="$ID/NormalCharacterStyle" Position="Superscript"> + <Footnote> + <ParagraphStyleRange> + <CharacterStyleRange> + <Content><?ACE 4?></Content> + </CharacterStyleRange> + </ParagraphStyleRange> + <ParagraphStyleRange AppliedParagraphStyle="ParagraphStyle/Footnote > Paragraph"> + <CharacterStyleRange AppliedCharacterStyle="$ID/NormalCharacterStyle"> + <Content> </Content> + </CharacterStyleRange> + <CharacterStyleRange AppliedCharacterStyle="$ID/NormalCharacterStyle"> + <Content>Here’s the long note. This one contains multiple blocks.</Content> + </CharacterStyleRange><Br /> + </ParagraphStyleRange> + <ParagraphStyleRange AppliedParagraphStyle="ParagraphStyle/Footnote > Paragraph"> + <CharacterStyleRange AppliedCharacterStyle="$ID/NormalCharacterStyle"> + <Content> </Content> + </CharacterStyleRange> + <CharacterStyleRange AppliedCharacterStyle="$ID/NormalCharacterStyle"> + <Content>Subsequent blocks are indented to show that they belong to the footnote (as with list items).</Content> + </CharacterStyleRange><Br /> + </ParagraphStyleRange> + <ParagraphStyleRange AppliedParagraphStyle="ParagraphStyle/Footnote > CodeBlock"> + <CharacterStyleRange AppliedCharacterStyle="$ID/NormalCharacterStyle"> + <Content> { <code> }</Content> + </CharacterStyleRange><Br /> + </ParagraphStyleRange> + <ParagraphStyleRange AppliedParagraphStyle="ParagraphStyle/Footnote > Paragraph"> + <CharacterStyleRange AppliedCharacterStyle="$ID/NormalCharacterStyle"> + <Content> </Content> + </CharacterStyleRange> + <CharacterStyleRange AppliedCharacterStyle="$ID/NormalCharacterStyle"> + <Content>If you want, you can indent every line, but you can also be lazy and just indent the first line of each block.</Content> + </CharacterStyleRange><Br /> + </ParagraphStyleRange> + </Footnote> + </CharacterStyleRange> + <CharacterStyleRange AppliedCharacterStyle="$ID/NormalCharacterStyle"> + <Content> This should </Content> + </CharacterStyleRange> + <CharacterStyleRange AppliedCharacterStyle="CharacterStyle/Italic"> + <Content>not</Content> + </CharacterStyleRange> + <CharacterStyleRange AppliedCharacterStyle="$ID/NormalCharacterStyle"> + <Content> be a footnote reference, because it contains a space.[^my note] Here is an inline note.</Content> + </CharacterStyleRange> + <CharacterStyleRange AppliedCharacterStyle="$ID/NormalCharacterStyle" Position="Superscript"> + <Footnote> + <ParagraphStyleRange> + <CharacterStyleRange> + <Content><?ACE 4?></Content> + </CharacterStyleRange> + </ParagraphStyleRange> + <ParagraphStyleRange AppliedParagraphStyle="ParagraphStyle/Footnote > Paragraph"> + <CharacterStyleRange AppliedCharacterStyle="$ID/NormalCharacterStyle"> + <Content> </Content> + </CharacterStyleRange> + <CharacterStyleRange AppliedCharacterStyle="$ID/NormalCharacterStyle"> + <Content>This is </Content> + </CharacterStyleRange> + <CharacterStyleRange AppliedCharacterStyle="CharacterStyle/Italic"> + <Content>easier</Content> + </CharacterStyleRange> + <CharacterStyleRange AppliedCharacterStyle="$ID/NormalCharacterStyle"> + <Content> to type. Inline notes may contain </Content> + </CharacterStyleRange> + <HyperlinkTextSource Self="htss-31" Name="" Hidden="false"> + <CharacterStyleRange AppliedCharacterStyle="CharacterStyle/Link"> + <Content>links</Content> + </CharacterStyleRange> + </HyperlinkTextSource> + <CharacterStyleRange AppliedCharacterStyle="$ID/NormalCharacterStyle"> + <Content> and </Content> + </CharacterStyleRange> + <CharacterStyleRange AppliedCharacterStyle="CharacterStyle/Code"> + <Content>]</Content> + </CharacterStyleRange> + <CharacterStyleRange AppliedCharacterStyle="$ID/NormalCharacterStyle"> + <Content> verbatim characters, as well as [bracketed text].</Content> + </CharacterStyleRange><Br /> + </ParagraphStyleRange> + </Footnote> + </CharacterStyleRange><Br /> +</ParagraphStyleRange> +<ParagraphStyleRange AppliedParagraphStyle="ParagraphStyle/Blockquote > Paragraph"> + <CharacterStyleRange AppliedCharacterStyle="$ID/NormalCharacterStyle"> + <Content>Notes can go in quotes.</Content> + </CharacterStyleRange> + <CharacterStyleRange AppliedCharacterStyle="$ID/NormalCharacterStyle" Position="Superscript"> + <Footnote> + <ParagraphStyleRange> + <CharacterStyleRange> + <Content><?ACE 4?></Content> + </CharacterStyleRange> + </ParagraphStyleRange> + <ParagraphStyleRange AppliedParagraphStyle="ParagraphStyle/Footnote > Paragraph"> + <CharacterStyleRange AppliedCharacterStyle="$ID/NormalCharacterStyle"> + <Content> </Content> + </CharacterStyleRange> + <CharacterStyleRange AppliedCharacterStyle="$ID/NormalCharacterStyle"> + <Content>In quote.</Content> + </CharacterStyleRange><Br /> + </ParagraphStyleRange> + </Footnote> + </CharacterStyleRange><Br /> +</ParagraphStyleRange> +<ParagraphStyleRange AppliedParagraphStyle="ParagraphStyle/NumList > first" NumberingContinue="false"> + <CharacterStyleRange AppliedCharacterStyle="$ID/NormalCharacterStyle"> + <Content>And in list items.</Content> + </CharacterStyleRange> + <CharacterStyleRange AppliedCharacterStyle="$ID/NormalCharacterStyle" Position="Superscript"> + <Footnote> + <ParagraphStyleRange> + <CharacterStyleRange> + <Content><?ACE 4?></Content> + </CharacterStyleRange> + </ParagraphStyleRange> + <ParagraphStyleRange AppliedParagraphStyle="ParagraphStyle/Footnote > Paragraph"> + <CharacterStyleRange AppliedCharacterStyle="$ID/NormalCharacterStyle"> + <Content> </Content> + </CharacterStyleRange> + <CharacterStyleRange AppliedCharacterStyle="$ID/NormalCharacterStyle"> + <Content>In list.</Content> + </CharacterStyleRange><Br /> + </ParagraphStyleRange> + </Footnote> + </CharacterStyleRange><Br /> +</ParagraphStyleRange> +<ParagraphStyleRange AppliedParagraphStyle="ParagraphStyle/Paragraph"> + <CharacterStyleRange AppliedCharacterStyle="$ID/NormalCharacterStyle"> + <Content>This paragraph should not be part of the note, as it is not indented.</Content> + </CharacterStyleRange><Br /> +</ParagraphStyleRange> + + </Story> + <HyperlinkURLDestination Self="HyperlinkURLDestination/http://google.com" Name="link" DestinationURL="http://google.com" DestinationUniqueKey="1" /> + <Hyperlink Self="uf-31" Name="http://google.com" Source="htss-31" Visible="true" DestinationUniqueKey="1"> + <Properties> + <BorderColor type="enumeration">Black</BorderColor> + <Destination type="object">HyperlinkURLDestination/http://google.com</Destination> + </Properties> + </Hyperlink> + <HyperlinkURLDestination Self="HyperlinkURLDestination/http://example.com/" Name="link" DestinationURL="http://example.com/" DestinationUniqueKey="1" /> + <Hyperlink Self="uf-30" Name="http://example.com/" Source="htss-30" Visible="true" DestinationUniqueKey="1"> + <Properties> + <BorderColor type="enumeration">Black</BorderColor> + <Destination type="object">HyperlinkURLDestination/http://example.com/</Destination> + </Properties> + </Hyperlink> + <HyperlinkURLDestination Self="HyperlinkURLDestination/mailto:nobody@nowhere.net" Name="link" DestinationURL="mailto:nobody@nowhere.net" DestinationUniqueKey="1" /> + <Hyperlink Self="uf-29" Name="mailto:nobody@nowhere.net" Source="htss-29" Visible="true" DestinationUniqueKey="1"> + <Properties> + <BorderColor type="enumeration">Black</BorderColor> + <Destination type="object">HyperlinkURLDestination/mailto:nobody@nowhere.net</Destination> + </Properties> + </Hyperlink> + <HyperlinkURLDestination Self="HyperlinkURLDestination/http://example.com/" Name="link" DestinationURL="http://example.com/" DestinationUniqueKey="1" /> + <Hyperlink Self="uf-28" Name="http://example.com/" Source="htss-28" Visible="true" DestinationUniqueKey="1"> + <Properties> + <BorderColor type="enumeration">Black</BorderColor> + <Destination type="object">HyperlinkURLDestination/http://example.com/</Destination> + </Properties> + </Hyperlink> + <HyperlinkURLDestination Self="HyperlinkURLDestination/http://example.com/?foo=1&bar=2" Name="link" DestinationURL="http://example.com/?foo=1&bar=2" DestinationUniqueKey="1" /> + <Hyperlink Self="uf-27" Name="http://example.com/?foo=1&bar=2" Source="htss-27" Visible="true" DestinationUniqueKey="1"> + <Properties> + <BorderColor type="enumeration">Black</BorderColor> + <Destination type="object">HyperlinkURLDestination/http://example.com/?foo=1&bar=2</Destination> + </Properties> + </Hyperlink> + <HyperlinkURLDestination Self="HyperlinkURLDestination//script?foo=1&bar=2" Name="link" DestinationURL="/script?foo=1&bar=2" DestinationUniqueKey="1" /> + <Hyperlink Self="uf-26" Name="/script?foo=1&bar=2" Source="htss-26" Visible="true" DestinationUniqueKey="1"> + <Properties> + <BorderColor type="enumeration">Black</BorderColor> + <Destination type="object">HyperlinkURLDestination//script?foo=1&bar=2</Destination> + </Properties> + </Hyperlink> + <HyperlinkURLDestination Self="HyperlinkURLDestination//script?foo=1&bar=2" Name="link" DestinationURL="/script?foo=1&bar=2" DestinationUniqueKey="1" /> + <Hyperlink Self="uf-25" Name="/script?foo=1&bar=2" Source="htss-25" Visible="true" DestinationUniqueKey="1"> + <Properties> + <BorderColor type="enumeration">Black</BorderColor> + <Destination type="object">HyperlinkURLDestination//script?foo=1&bar=2</Destination> + </Properties> + </Hyperlink> + <HyperlinkURLDestination Self="HyperlinkURLDestination/http://att.com/" Name="link" DestinationURL="http://att.com/" DestinationUniqueKey="1" /> + <Hyperlink Self="uf-24" Name="http://att.com/" Source="htss-24" Visible="true" DestinationUniqueKey="1"> + <Properties> + <BorderColor type="enumeration">Black</BorderColor> + <Destination type="object">HyperlinkURLDestination/http://att.com/</Destination> + </Properties> + </Hyperlink> + <HyperlinkURLDestination Self="HyperlinkURLDestination/http://example.com/?foo=1&bar=2" Name="link" DestinationURL="http://example.com/?foo=1&bar=2" DestinationUniqueKey="1" /> + <Hyperlink Self="uf-23" Name="http://example.com/?foo=1&bar=2" Source="htss-23" Visible="true" DestinationUniqueKey="1"> + <Properties> + <BorderColor type="enumeration">Black</BorderColor> + <Destination type="object">HyperlinkURLDestination/http://example.com/?foo=1&bar=2</Destination> + </Properties> + </Hyperlink> + <HyperlinkURLDestination Self="HyperlinkURLDestination//url/" Name="link" DestinationURL="/url/" DestinationUniqueKey="1" /> + <Hyperlink Self="uf-22" Name="/url/" Source="htss-22" Visible="true" DestinationUniqueKey="1"> + <Properties> + <BorderColor type="enumeration">Black</BorderColor> + <Destination type="object">HyperlinkURLDestination//url/</Destination> + </Properties> + </Hyperlink> + <HyperlinkURLDestination Self="HyperlinkURLDestination//url/" Name="link" DestinationURL="/url/" DestinationUniqueKey="1" /> + <Hyperlink Self="uf-21" Name="/url/" Source="htss-21" Visible="true" DestinationUniqueKey="1"> + <Properties> + <BorderColor type="enumeration">Black</BorderColor> + <Destination type="object">HyperlinkURLDestination//url/</Destination> + </Properties> + </Hyperlink> + <HyperlinkURLDestination Self="HyperlinkURLDestination//url" Name="link" DestinationURL="/url" DestinationUniqueKey="1" /> + <Hyperlink Self="uf-20" Name="/url" Source="htss-20" Visible="true" DestinationUniqueKey="1"> + <Properties> + <BorderColor type="enumeration">Black</BorderColor> + <Destination type="object">HyperlinkURLDestination//url</Destination> + </Properties> + </Hyperlink> + <HyperlinkURLDestination Self="HyperlinkURLDestination//url" Name="link" DestinationURL="/url" DestinationUniqueKey="1" /> + <Hyperlink Self="uf-19" Name="/url" Source="htss-19" Visible="true" DestinationUniqueKey="1"> + <Properties> + <BorderColor type="enumeration">Black</BorderColor> + <Destination type="object">HyperlinkURLDestination//url</Destination> + </Properties> + </Hyperlink> + <HyperlinkURLDestination Self="HyperlinkURLDestination//url" Name="link" DestinationURL="/url" DestinationUniqueKey="1" /> + <Hyperlink Self="uf-18" Name="/url" Source="htss-18" Visible="true" DestinationUniqueKey="1"> + <Properties> + <BorderColor type="enumeration">Black</BorderColor> + <Destination type="object">HyperlinkURLDestination//url</Destination> + </Properties> + </Hyperlink> + <HyperlinkURLDestination Self="HyperlinkURLDestination//url/" Name="link" DestinationURL="/url/" DestinationUniqueKey="1" /> + <Hyperlink Self="uf-17" Name="/url/" Source="htss-17" Visible="true" DestinationUniqueKey="1"> + <Properties> + <BorderColor type="enumeration">Black</BorderColor> + <Destination type="object">HyperlinkURLDestination//url/</Destination> + </Properties> + </Hyperlink> + <HyperlinkURLDestination Self="HyperlinkURLDestination//url/" Name="link" DestinationURL="/url/" DestinationUniqueKey="1" /> + <Hyperlink Self="uf-16" Name="/url/" Source="htss-16" Visible="true" DestinationUniqueKey="1"> + <Properties> + <BorderColor type="enumeration">Black</BorderColor> + <Destination type="object">HyperlinkURLDestination//url/</Destination> + </Properties> + </Hyperlink> + <HyperlinkURLDestination Self="HyperlinkURLDestination//url/" Name="link" DestinationURL="/url/" DestinationUniqueKey="1" /> + <Hyperlink Self="uf-15" Name="/url/" Source="htss-15" Visible="true" DestinationUniqueKey="1"> + <Properties> + <BorderColor type="enumeration">Black</BorderColor> + <Destination type="object">HyperlinkURLDestination//url/</Destination> + </Properties> + </Hyperlink> + <HyperlinkURLDestination Self="HyperlinkURLDestination//url/" Name="link" DestinationURL="/url/" DestinationUniqueKey="1" /> + <Hyperlink Self="uf-14" Name="/url/" Source="htss-14" Visible="true" DestinationUniqueKey="1"> + <Properties> + <BorderColor type="enumeration">Black</BorderColor> + <Destination type="object">HyperlinkURLDestination//url/</Destination> + </Properties> + </Hyperlink> + <HyperlinkURLDestination Self="HyperlinkURLDestination//url/" Name="link" DestinationURL="/url/" DestinationUniqueKey="1" /> + <Hyperlink Self="uf-13" Name="/url/" Source="htss-13" Visible="true" DestinationUniqueKey="1"> + <Properties> + <BorderColor type="enumeration">Black</BorderColor> + <Destination type="object">HyperlinkURLDestination//url/</Destination> + </Properties> + </Hyperlink> + <HyperlinkURLDestination Self="HyperlinkURLDestination/" Name="link" DestinationURL="" DestinationUniqueKey="1" /> + <Hyperlink Self="uf-12" Name="" Source="htss-12" Visible="true" DestinationUniqueKey="1"> + <Properties> + <BorderColor type="enumeration">Black</BorderColor> + <Destination type="object">HyperlinkURLDestination/</Destination> + </Properties> + </Hyperlink> + <HyperlinkURLDestination Self="HyperlinkURLDestination/mailto:nobody@nowhere.net" Name="link" DestinationURL="mailto:nobody@nowhere.net" DestinationUniqueKey="1" /> + <Hyperlink Self="uf-11" Name="mailto:nobody@nowhere.net" Source="htss-11" Visible="true" DestinationUniqueKey="1"> + <Properties> + <BorderColor type="enumeration">Black</BorderColor> + <Destination type="object">HyperlinkURLDestination/mailto:nobody@nowhere.net</Destination> + </Properties> + </Hyperlink> + <HyperlinkURLDestination Self="HyperlinkURLDestination//url/with_underscore" Name="link" DestinationURL="/url/with_underscore" DestinationUniqueKey="1" /> + <Hyperlink Self="uf-10" Name="/url/with_underscore" Source="htss-10" Visible="true" DestinationUniqueKey="1"> + <Properties> + <BorderColor type="enumeration">Black</BorderColor> + <Destination type="object">HyperlinkURLDestination//url/with_underscore</Destination> + </Properties> + </Hyperlink> + <HyperlinkURLDestination Self="HyperlinkURLDestination//url/" Name="link" DestinationURL="/url/" DestinationUniqueKey="1" /> + <Hyperlink Self="uf-9" Name="/url/" Source="htss-9" Visible="true" DestinationUniqueKey="1"> + <Properties> + <BorderColor type="enumeration">Black</BorderColor> + <Destination type="object">HyperlinkURLDestination//url/</Destination> + </Properties> + </Hyperlink> + <HyperlinkURLDestination Self="HyperlinkURLDestination//url/" Name="link" DestinationURL="/url/" DestinationUniqueKey="1" /> + <Hyperlink Self="uf-8" Name="/url/" Source="htss-8" Visible="true" DestinationUniqueKey="1"> + <Properties> + <BorderColor type="enumeration">Black</BorderColor> + <Destination type="object">HyperlinkURLDestination//url/</Destination> + </Properties> + </Hyperlink> + <HyperlinkURLDestination Self="HyperlinkURLDestination//url/" Name="link" DestinationURL="/url/" DestinationUniqueKey="1" /> + <Hyperlink Self="uf-7" Name="/url/" Source="htss-7" Visible="true" DestinationUniqueKey="1"> + <Properties> + <BorderColor type="enumeration">Black</BorderColor> + <Destination type="object">HyperlinkURLDestination//url/</Destination> + </Properties> + </Hyperlink> + <HyperlinkURLDestination Self="HyperlinkURLDestination//url/" Name="link" DestinationURL="/url/" DestinationUniqueKey="1" /> + <Hyperlink Self="uf-6" Name="/url/" Source="htss-6" Visible="true" DestinationUniqueKey="1"> + <Properties> + <BorderColor type="enumeration">Black</BorderColor> + <Destination type="object">HyperlinkURLDestination//url/</Destination> + </Properties> + </Hyperlink> + <HyperlinkURLDestination Self="HyperlinkURLDestination//url/" Name="link" DestinationURL="/url/" DestinationUniqueKey="1" /> + <Hyperlink Self="uf-5" Name="/url/" Source="htss-5" Visible="true" DestinationUniqueKey="1"> + <Properties> + <BorderColor type="enumeration">Black</BorderColor> + <Destination type="object">HyperlinkURLDestination//url/</Destination> + </Properties> + </Hyperlink> + <HyperlinkURLDestination Self="HyperlinkURLDestination//url/" Name="link" DestinationURL="/url/" DestinationUniqueKey="1" /> + <Hyperlink Self="uf-4" Name="/url/" Source="htss-4" Visible="true" DestinationUniqueKey="1"> + <Properties> + <BorderColor type="enumeration">Black</BorderColor> + <Destination type="object">HyperlinkURLDestination//url/</Destination> + </Properties> + </Hyperlink> + <HyperlinkURLDestination Self="HyperlinkURLDestination/http://example.com/?foo=1&bar=2" Name="link" DestinationURL="http://example.com/?foo=1&bar=2" DestinationUniqueKey="1" /> + <Hyperlink Self="uf-3" Name="http://example.com/?foo=1&bar=2" Source="htss-3" Visible="true" DestinationUniqueKey="1"> + <Properties> + <BorderColor type="enumeration">Black</BorderColor> + <Destination type="object">HyperlinkURLDestination/http://example.com/?foo=1&bar=2</Destination> + </Properties> + </Hyperlink> + <HyperlinkURLDestination Self="HyperlinkURLDestination//url" Name="link" DestinationURL="/url" DestinationUniqueKey="1" /> + <Hyperlink Self="uf-2" Name="/url" Source="htss-2" Visible="true" DestinationUniqueKey="1"> + <Properties> + <BorderColor type="enumeration">Black</BorderColor> + <Destination type="object">HyperlinkURLDestination//url</Destination> + </Properties> + </Hyperlink> + <HyperlinkURLDestination Self="HyperlinkURLDestination//url" Name="link" DestinationURL="/url" DestinationUniqueKey="1" /> + <Hyperlink Self="uf-1" Name="/url" Source="htss-1" Visible="true" DestinationUniqueKey="1"> + <Properties> + <BorderColor type="enumeration">Black</BorderColor> + <Destination type="object">HyperlinkURLDestination//url</Destination> + </Properties> + </Hyperlink> +</Document> diff --git a/tests/writer.latex b/tests/writer.latex index 641ed420b..ee886e757 100644 --- a/tests/writer.latex +++ b/tests/writer.latex @@ -1,12 +1,10 @@ \documentclass[]{article} -\usepackage[T1]{fontenc} \usepackage{lmodern} \usepackage{amssymb,amsmath} \usepackage{ifxetex,ifluatex} \usepackage{fixltx2e} % provides \textsubscript -% use upquote if available, for straight quotes in verbatim environments -\IfFileExists{upquote.sty}{\usepackage{upquote}}{} \ifnum 0\ifxetex 1\fi\ifluatex 1\fi=0 % if pdftex + \usepackage[T1]{fontenc} \usepackage[utf8]{inputenc} \else % if luatex or xelatex \ifxetex @@ -18,28 +16,24 @@ \defaultfontfeatures{Mapping=tex-text,Scale=MatchLowercase} \newcommand{\euro}{€} \fi +% use upquote if available, for straight quotes in verbatim environments +\IfFileExists{upquote.sty}{\usepackage{upquote}}{} % use microtype if available -\IfFileExists{microtype.sty}{\usepackage{microtype}}{} +\IfFileExists{microtype.sty}{% +\usepackage{microtype} +\UseMicrotypeSet[protrusion]{basicmath} % disable protrusion for tt fonts +}{} \usepackage{fancyvrb} +\VerbatimFootnotes \usepackage{graphicx} -% Redefine \includegraphics so that, unless explicit options are -% given, the image width will not exceed the width of the page. -% Images get their normal width if they fit onto the page, but -% are scaled down if they would overflow the margins. \makeatletter -\def\ScaleIfNeeded{% - \ifdim\Gin@nat@width>\linewidth - \linewidth - \else - \Gin@nat@width - \fi -} +\def\maxwidth{\ifdim\Gin@nat@width>\linewidth\linewidth\else\Gin@nat@width\fi} +\def\maxheight{\ifdim\Gin@nat@height>\textheight\textheight\else\Gin@nat@height\fi} \makeatother -\let\Oldincludegraphics\includegraphics -{% - \catcode`\@=11\relax% - \gdef\includegraphics{\@ifnextchar[{\Oldincludegraphics}{\Oldincludegraphics[width=\ScaleIfNeeded]}}% -}% +% Scale images if necessary, so that they will not overflow the page +% margins by default, and it is still possible to overwrite the defaults +% using explicit options in \includegraphics[width, height, ...]{} +\setkeys{Gin}{width=\maxwidth,height=\maxheight,keepaspectratio} \ifxetex \usepackage[setpagesize=false, % page size defined by xetex unicode=false, % unicode breaks when used with xetex @@ -76,7 +70,7 @@ This is a set of tests for pandoc. Most of them are adapted from John Gruber's markdown test suite. -\begin{center}\rule{3in}{0.4pt}\end{center} +\begin{center}\rule{0.5\linewidth}{\linethickness}\end{center} \section{\texorpdfstring{Headers}{Headers}}\label{headers} @@ -103,7 +97,7 @@ with no blank line with no blank line -\begin{center}\rule{3in}{0.4pt}\end{center} +\begin{center}\rule{0.5\linewidth}{\linethickness}\end{center} \section{\texorpdfstring{Paragraphs}{Paragraphs}}\label{paragraphs} @@ -117,7 +111,7 @@ Here's one with a bullet. * criminey. There should be a hard line break\\here. -\begin{center}\rule{3in}{0.4pt}\end{center} +\begin{center}\rule{0.5\linewidth}{\linethickness}\end{center} \section{\texorpdfstring{Block Quotes}{Block Quotes}}\label{block-quotes} @@ -162,7 +156,7 @@ This should not be a block quote: 2 \textgreater{} 1. And a following paragraph. -\begin{center}\rule{3in}{0.4pt}\end{center} +\begin{center}\rule{0.5\linewidth}{\linethickness}\end{center} \section{\texorpdfstring{Code Blocks}{Code Blocks}}\label{code-blocks} @@ -186,7 +180,7 @@ And: These should not be escaped: \$ \\ \> \[ \{ \end{verbatim} -\begin{center}\rule{3in}{0.4pt}\end{center} +\begin{center}\rule{0.5\linewidth}{\linethickness}\end{center} \section{\texorpdfstring{Lists}{Lists}}\label{lists} @@ -496,7 +490,7 @@ M.A.~2007 B. Williams -\begin{center}\rule{3in}{0.4pt}\end{center} +\begin{center}\rule{0.5\linewidth}{\linethickness}\end{center} \section{\texorpdfstring{Definition Lists}{Definition Lists}}\label{definition-lists} @@ -662,7 +656,7 @@ Code: Hr's: -\begin{center}\rule{3in}{0.4pt}\end{center} +\begin{center}\rule{0.5\linewidth}{\linethickness}\end{center} \section{\texorpdfstring{Inline Markup}{Inline Markup}}\label{inline-markup} @@ -694,7 +688,7 @@ H\textsubscript{many~of~them}O. These should not be superscripts or subscripts, because of the unescaped spaces: a\^{}b c\^{}d, a\textasciitilde{}b c\textasciitilde{}d. -\begin{center}\rule{3in}{0.4pt}\end{center} +\begin{center}\rule{0.5\linewidth}{\linethickness}\end{center} \section{\texorpdfstring{Smart quotes, ellipses, dashes}{Smart quotes, ellipses, dashes}}\label{smart-quotes-ellipses-dashes} @@ -716,7 +710,7 @@ Dashes between numbers: 5--7, 255--66, 1987--1999. Ellipses\ldots{}and\ldots{}and\ldots{}. -\begin{center}\rule{3in}{0.4pt}\end{center} +\begin{center}\rule{0.5\linewidth}{\linethickness}\end{center} \section{\texorpdfstring{LaTeX}{LaTeX}}\label{latex} @@ -725,20 +719,20 @@ Ellipses\ldots{}and\ldots{}and\ldots{}. \item \cite[22-23]{smith.1899} \item - $2+2=4$ + \(2+2=4\) \item - $x \in y$ + \(x \in y\) \item - $\alpha \wedge \omega$ + \(\alpha \wedge \omega\) \item - $223$ + \(223\) \item - $p$-Tree + \(p\)-Tree \item Here's some display math: \[\frac{d}{dx}f(x)=\lim_{h\to 0}\frac{f(x+h)-f(x)}{h}\] \item - Here's one that has a line break in it: $\alpha + \omega \times x^2$. + Here's one that has a line break in it: \(\alpha + \omega \times x^2\). \end{itemize} These shouldn't be math: @@ -746,7 +740,7 @@ These shouldn't be math: \begin{itemize} \itemsep1pt\parskip0pt\parsep0pt \item - To get the famous equation, write \texttt{\$e = mc\^{}2\$}. + To get the famous equation, write \texttt{\$e\ =\ mc\^{}2\$}. \item \$22,000 is a \emph{lot} of money. So is \$34,000. (It worked if ``lot'' is emphasized.) @@ -764,7 +758,7 @@ Dog & 2 \\ Cat & 1 \\ \hline \end{tabular} -\begin{center}\rule{3in}{0.4pt}\end{center} +\begin{center}\rule{0.5\linewidth}{\linethickness}\end{center} \section{\texorpdfstring{Special Characters}{Special Characters}}\label{special-characters} @@ -827,7 +821,7 @@ Plus: + Minus: - -\begin{center}\rule{3in}{0.4pt}\end{center} +\begin{center}\rule{0.5\linewidth}{\linethickness}\end{center} \section{\texorpdfstring{Links}{Links}}\label{links} @@ -906,7 +900,8 @@ With an ampersand: \url{http://example.com/?foo=1\&bar=2} It should. \end{itemize} -An e-mail address: \href{mailto:nobody@nowhere.net}{nobody@nowhere.net} +An e-mail address: +\href{mailto:nobody@nowhere.net}{\nolinkurl{nobody@nowhere.net}} \begin{quote} Blockquoted: \url{http://example.com/} @@ -919,7 +914,7 @@ Auto-links should not occur here: or here: <http://example.com/> \end{verbatim} -\begin{center}\rule{3in}{0.4pt}\end{center} +\begin{center}\rule{0.5\linewidth}{\linethickness}\end{center} \section{\texorpdfstring{Images}{Images}}\label{images} @@ -933,7 +928,7 @@ From ``Voyage dans la Lune'' by Georges Melies (1902): Here is a movie \includegraphics{movie.jpg} icon. -\begin{center}\rule{3in}{0.4pt}\end{center} +\begin{center}\rule{0.5\linewidth}{\linethickness}\end{center} \section{\texorpdfstring{Footnotes}{Footnotes}}\label{footnotes} diff --git a/tests/writer.man b/tests/writer.man index aab588f9c..900dfcdb2 100644 --- a/tests/writer.man +++ b/tests/writer.man @@ -450,6 +450,7 @@ Simple block on one line: foo .PP And nested without indentation: +.PP foo bar .PP @@ -458,6 +459,7 @@ This is \f[I]emphasized\f[] And this is \f[B]strong\f[] .PP Here's a simple block: +.PP foo .PP This should be a code block, though: diff --git a/tests/writer.markdown b/tests/writer.markdown index 9cf153637..ad97b15ef 100644 --- a/tests/writer.markdown +++ b/tests/writer.markdown @@ -9,7 +9,7 @@ title: Pandoc Test Suite This is a set of tests for pandoc. Most of them are adapted from John Gruber’s markdown test suite. -* * * * * +------------------------------------------------------------------------------ Headers ======= @@ -38,7 +38,7 @@ Level 2 with no blank line -* * * * * +------------------------------------------------------------------------------ Paragraphs ========== @@ -54,7 +54,7 @@ Here’s one with a bullet. \* criminey. There should be a hard line break\ here. -* * * * * +------------------------------------------------------------------------------ Block Quotes ============ @@ -84,7 +84,7 @@ This should not be a block quote: 2 \> 1. And a following paragraph. -* * * * * +------------------------------------------------------------------------------ Code Blocks =========== @@ -105,7 +105,7 @@ And: These should not be escaped: \$ \\ \> \[ \{ -* * * * * +------------------------------------------------------------------------------ Lists ===== @@ -268,7 +268,7 @@ M.A. 2007 B. Williams -* * * * * +------------------------------------------------------------------------------ Definition Lists ================ @@ -277,8 +277,10 @@ Tight using spaces: apple : red fruit + orange : orange fruit + banana : yellow fruit @@ -286,30 +288,37 @@ Tight using tabs: apple : red fruit + orange : orange fruit + banana : yellow fruit Loose: apple + : red fruit orange + : orange fruit banana + : yellow fruit Multiple blocks with italics: *apple* + : red fruit contains seeds, crisp, pleasant to taste *orange* + : orange fruit { orange code block } @@ -321,6 +330,7 @@ Multiple definitions, tight: apple : red fruit : computer + orange : orange fruit : bank @@ -328,11 +338,13 @@ orange Multiple definitions, loose: apple + : red fruit : computer orange + : orange fruit : bank @@ -340,11 +352,13 @@ orange Blank line after term, indented marker, alternate markers: apple + : red fruit : computer orange + : orange fruit 1. sublist @@ -395,9 +409,7 @@ And this is **strong** </td> </tr> </table> - <script type="text/javascript">document.write('This *should not* be interpreted as markdown');</script> - Here’s a simple block: <div> @@ -435,26 +447,22 @@ foo This should just be an HTML comment: <!-- Comment --> - Multiline: <!-- Blah Blah --> - <!-- This is another comment. --> - Code block: <!-- Comment --> Just plain comment, with trailing spaces on the line: -<!-- foo --> - +<!-- foo --> Code: <hr /> @@ -462,24 +470,16 @@ Code: Hr’s: <hr> - <hr /> - <hr /> - -<hr> - -<hr /> - -<hr /> - +<hr> +<hr /> +<hr /> <hr class="foo" id="bar" /> - <hr class="foo" id="bar" /> - <hr class="foo" id="bar"> -* * * * * +------------------------------------------------------------------------------ Inline Markup ============= @@ -509,7 +509,7 @@ Subscripts: H~2~O, H~23~O, H~many of them~O. These should not be superscripts or subscripts, because of the unescaped spaces: a\^b c\^d, a\~b c\~d. -* * * * * +------------------------------------------------------------------------------ Smart quotes, ellipses, dashes ============================== @@ -531,7 +531,7 @@ Dashes between numbers: 5–7, 255–66, 1987–1999. Ellipses…and…and…. -* * * * * +------------------------------------------------------------------------------ LaTeX ===== @@ -562,7 +562,7 @@ Dog & 2 \\ Cat & 1 \\ \hline \end{tabular} -* * * * * +------------------------------------------------------------------------------ Special Characters ================== @@ -617,7 +617,7 @@ Plus: + Minus: - -* * * * * +------------------------------------------------------------------------------ Links ===== @@ -699,7 +699,7 @@ Auto-links should not occur here: `<http://example.com/>` or here: <http://example.com/> -* * * * * +------------------------------------------------------------------------------ Images ====== @@ -710,7 +710,7 @@ From “Voyage dans la Lune” by Georges Melies (1902): Here is a movie  icon. -* * * * * +------------------------------------------------------------------------------ Footnotes ========= diff --git a/tests/writer.mediawiki b/tests/writer.mediawiki index 2f3726285..efd43cb04 100644 --- a/tests/writer.mediawiki +++ b/tests/writer.mediawiki @@ -325,6 +325,7 @@ And nested without indentation: foo + </div> </div> @@ -347,15 +348,14 @@ And this is '''strong''' </td> </tr> </table> - <script type="text/javascript">document.write('This *should not* be interpreted as markdown');</script> - Here’s a simple block: <div> foo + </div> This should be a code block, though: @@ -383,49 +383,36 @@ foo This should just be an HTML comment: <!-- Comment --> - Multiline: <!-- Blah Blah --> - <!-- This is another comment. --> - Code block: <pre><!-- Comment --></pre> Just plain comment, with trailing spaces on the line: -<!-- foo --> - +<!-- foo --> Code: <pre><hr /></pre> Hr’s: <hr> - <hr /> - <hr /> - -<hr> - -<hr /> - -<hr /> - +<hr> +<hr /> +<hr /> <hr class="foo" id="bar" /> - <hr class="foo" id="bar" /> - <hr class="foo" id="bar"> - ----- = Inline Markup = diff --git a/tests/writer.native b/tests/writer.native index 678d7595f..93d2939ad 100644 --- a/tests/writer.native +++ b/tests/writer.native @@ -230,15 +230,21 @@ Pandoc (Meta {unMeta = fromList [("author",MetaList [MetaInlines [Str "John",Spa ,Para [Str "Simple",Space,Str "block",Space,Str "on",Space,Str "one",Space,Str "line:"] ,Div ("",[],[]) [Plain [Str "foo"]] ,Para [Str "And",Space,Str "nested",Space,Str "without",Space,Str "indentation:"] -,Div ("",[],[]) [Div ("",[],[]) [Div ("",[],[]) [Plain [Str "foo"]]],Div ("",[],[]) [Plain [Str "bar"]]] +,Div ("",[],[]) [Div ("",[],[]) [Div ("",[],[]) [Para [Str "foo"]]],Div ("",[],[]) [Plain [Str "bar"]]] ,Para [Str "Interpreted",Space,Str "markdown",Space,Str "in",Space,Str "a",Space,Str "table:"] -,RawBlock (Format "html") "<table>\n<tr>\n<td>" +,RawBlock (Format "html") "<table>" +,RawBlock (Format "html") "<tr>" +,RawBlock (Format "html") "<td>" ,Plain [Str "This",Space,Str "is",Space,Emph [Str "emphasized"]] -,RawBlock (Format "html") "</td>\n<td>" +,RawBlock (Format "html") "</td>" +,RawBlock (Format "html") "<td>" ,Plain [Str "And",Space,Str "this",Space,Str "is",Space,Strong [Str "strong"]] -,RawBlock (Format "html") "</td>\n</tr>\n</table>\n\n<script type=\"text/javascript\">document.write('This *should not* be interpreted as markdown');</script>\n" +,RawBlock (Format "html") "</td>" +,RawBlock (Format "html") "</tr>" +,RawBlock (Format "html") "</table>" +,RawBlock (Format "html") "<script type=\"text/javascript\">document.write('This *should not* be interpreted as markdown');</script>" ,Para [Str "Here\8217s",Space,Str "a",Space,Str "simple",Space,Str "block:"] -,Div ("",[],[]) [Plain [Str "foo"]] +,Div ("",[],[]) [Para [Str "foo"]] ,Para [Str "This",Space,Str "should",Space,Str "be",Space,Str "a",Space,Str "code",Space,Str "block,",Space,Str "though:"] ,CodeBlock ("",[],[]) "<div>\n foo\n</div>" ,Para [Str "As",Space,Str "should",Space,Str "this:"] @@ -246,17 +252,26 @@ Pandoc (Meta {unMeta = fromList [("author",MetaList [MetaInlines [Str "John",Spa ,Para [Str "Now,",Space,Str "nested:"] ,Div ("",[],[]) [Div ("",[],[]) [Div ("",[],[]) [Plain [Str "foo"]]]] ,Para [Str "This",Space,Str "should",Space,Str "just",Space,Str "be",Space,Str "an",Space,Str "HTML",Space,Str "comment:"] -,RawBlock (Format "html") "<!-- Comment -->\n" +,RawBlock (Format "html") "<!-- Comment -->" ,Para [Str "Multiline:"] -,RawBlock (Format "html") "<!--\nBlah\nBlah\n-->\n\n<!--\n This is another comment.\n-->\n" +,RawBlock (Format "html") "<!--\nBlah\nBlah\n-->" +,RawBlock (Format "html") "<!--\n This is another comment.\n-->" ,Para [Str "Code",Space,Str "block:"] ,CodeBlock ("",[],[]) "<!-- Comment -->" ,Para [Str "Just",Space,Str "plain",Space,Str "comment,",Space,Str "with",Space,Str "trailing",Space,Str "spaces",Space,Str "on",Space,Str "the",Space,Str "line:"] -,RawBlock (Format "html") "<!-- foo --> \n" +,RawBlock (Format "html") "<!-- foo -->" ,Para [Str "Code:"] ,CodeBlock ("",[],[]) "<hr />" ,Para [Str "Hr\8217s:"] -,RawBlock (Format "html") "<hr>\n\n<hr />\n\n<hr />\n\n<hr> \n\n<hr /> \n\n<hr /> \n\n<hr class=\"foo\" id=\"bar\" />\n\n<hr class=\"foo\" id=\"bar\" />\n\n<hr class=\"foo\" id=\"bar\">\n" +,RawBlock (Format "html") "<hr>" +,RawBlock (Format "html") "<hr />" +,RawBlock (Format "html") "<hr />" +,RawBlock (Format "html") "<hr>" +,RawBlock (Format "html") "<hr />" +,RawBlock (Format "html") "<hr />" +,RawBlock (Format "html") "<hr class=\"foo\" id=\"bar\" />" +,RawBlock (Format "html") "<hr class=\"foo\" id=\"bar\" />" +,RawBlock (Format "html") "<hr class=\"foo\" id=\"bar\">" ,HorizontalRule ,Header 1 ("inline-markup",[],[]) [Str "Inline",Space,Str "Markup"] ,Para [Str "This",Space,Str "is",Space,Emph [Str "emphasized"],Str ",",Space,Str "and",Space,Str "so",Space,Emph [Str "is",Space,Str "this"],Str "."] diff --git a/tests/writer.opml b/tests/writer.opml index 228cad247..840c3c6e1 100644 --- a/tests/writer.opml +++ b/tests/writer.opml @@ -21,14 +21,14 @@ <outline text="Level 3" _note="with no blank line"> </outline> </outline> - <outline text="Level 2" _note="with no blank line * * * * *"> + <outline text="Level 2" _note="with no blank line ------------------------------------------------------------------------"> </outline> </outline> -<outline text="Paragraphs" _note="Here’s a regular paragraph. In Markdown 1.0.0 and earlier. Version 8. This line turns into a list item. Because a hard-wrapped line in the middle of a paragraph looked like a list item. Here’s one with a bullet. \* criminey. There should be a hard line break\ here. * * * * *"> +<outline text="Paragraphs" _note="Here’s a regular paragraph. In Markdown 1.0.0 and earlier. Version 8. This line turns into a list item. Because a hard-wrapped line in the middle of a paragraph looked like a list item. Here’s one with a bullet. \* criminey. There should be a hard line break\ here. ------------------------------------------------------------------------"> </outline> -<outline text="Block Quotes" _note="E-mail style: > This is a block quote. It is pretty short. > Code in a block quote: > > sub status { > print "working"; > } > > A list: > > 1. item one > 2. item two > > Nested block quotes: > > > nested > > > nested This should not be a block quote: 2 \> 1. And a following paragraph. * * * * *"> +<outline text="Block Quotes" _note="E-mail style: > This is a block quote. It is pretty short. > Code in a block quote: > > sub status { > print "working"; > } > > A list: > > 1. item one > 2. item two > > Nested block quotes: > > > nested > > > nested This should not be a block quote: 2 \> 1. And a following paragraph. ------------------------------------------------------------------------"> </outline> -<outline text="Code Blocks" _note="Code: ---- (should be four hyphens) sub status { print "working"; } this code block is indented by one tab And: this code block is indented by two tabs These should not be escaped: \$ \\ \> \[ \{ * * * * *"> +<outline text="Code Blocks" _note="Code: ---- (should be four hyphens) sub status { print "working"; } this code block is indented by one tab And: this code block is indented by two tabs These should not be escaped: \$ \\ \> \[ \{ ------------------------------------------------------------------------"> </outline> <outline text="Lists"> <outline text="Unordered" _note="Asterisks tight: - asterisk 1 - asterisk 2 - asterisk 3 Asterisks loose: - asterisk 1 - asterisk 2 - asterisk 3 Pluses tight: - Plus 1 - Plus 2 - Plus 3 Pluses loose: - Plus 1 - Plus 2 - Plus 3 Minuses tight: - Minus 1 - Minus 2 - Minus 3 Minuses loose: - Minus 1 - Minus 2 - Minus 3 "> @@ -39,20 +39,20 @@ </outline> <outline text="Tabs and spaces" _note="- this is a list item indented with tabs - this is a list item indented with spaces - this is an example list item indented with tabs - this is an example list item indented with spaces "> </outline> - <outline text="Fancy list markers" _note="(2) begins with 2 (3) and now 3 with a continuation iv. sublist with roman numerals, starting with 4 v. more items (A) a subsublist (B) a subsublist Nesting: A. Upper Alpha I. Upper Roman. (6) Decimal start with 6 c) Lower alpha with paren Autonumbering: 1. Autonumber. 2. More. 1. Nested. Should not be a list item: M.A. 2007 B. Williams * * * * *"> + <outline text="Fancy list markers" _note="(2) begins with 2 (3) and now 3 with a continuation iv. sublist with roman numerals, starting with 4 v. more items (A) a subsublist (B) a subsublist Nesting: A. Upper Alpha I. Upper Roman. (6) Decimal start with 6 c) Lower alpha with paren Autonumbering: 1. Autonumber. 2. More. 1. Nested. Should not be a list item: M.A. 2007 B. Williams ------------------------------------------------------------------------"> </outline> </outline> -<outline text="Definition Lists" _note="Tight using spaces: apple : red fruit orange : orange fruit banana : yellow fruit Tight using tabs: apple : red fruit orange : orange fruit banana : yellow fruit Loose: apple : red fruit orange : orange fruit banana : yellow fruit Multiple blocks with italics: *apple* : red fruit contains seeds, crisp, pleasant to taste *orange* : orange fruit { orange code block } > orange block quote Multiple definitions, tight: apple : red fruit : computer orange : orange fruit : bank Multiple definitions, loose: apple : red fruit : computer orange : orange fruit : bank Blank line after term, indented marker, alternate markers: apple : red fruit : computer orange : orange fruit 1. sublist 2. sublist "> +<outline text="Definition Lists" _note="Tight using spaces: apple : red fruit orange : orange fruit banana : yellow fruit Tight using tabs: apple : red fruit orange : orange fruit banana : yellow fruit Loose: apple : red fruit orange : orange fruit banana : yellow fruit Multiple blocks with italics: *apple* : red fruit contains seeds, crisp, pleasant to taste *orange* : orange fruit { orange code block } > orange block quote Multiple definitions, tight: apple : red fruit : computer orange : orange fruit : bank Multiple definitions, loose: apple : red fruit : computer orange : orange fruit : bank Blank line after term, indented marker, alternate markers: apple : red fruit : computer orange : orange fruit 1. sublist 2. sublist "> </outline> -<outline text="HTML Blocks" _note="Simple block on one line: <div> foo </div> And nested without indentation: <div> <div> <div> foo </div> </div> <div> bar </div> </div> Interpreted markdown in a table: <table> <tr> <td> This is *emphasized* </td> <td> And this is **strong** </td> </tr> </table> <script type="text/javascript">document.write('This *should not* be interpreted as markdown');</script> Here’s a simple block: <div> foo </div> This should be a code block, though: <div> foo </div> As should this: <div>foo</div> Now, nested: <div> <div> <div> foo </div> </div> </div> This should just be an HTML comment: <!-- Comment --> Multiline: <!-- Blah Blah --> <!-- This is another comment. --> Code block: <!-- Comment --> Just plain comment, with trailing spaces on the line: <!-- foo --> Code: <hr /> Hr’s: <hr> <hr /> <hr /> <hr> <hr /> <hr /> <hr class="foo" id="bar" /> <hr class="foo" id="bar" /> <hr class="foo" id="bar"> * * * * *"> +<outline text="HTML Blocks" _note="Simple block on one line: <div> foo </div> And nested without indentation: <div> <div> <div> foo </div> </div> <div> bar </div> </div> Interpreted markdown in a table: <table> <tr> <td> This is *emphasized* </td> <td> And this is **strong** </td> </tr> </table> <script type="text/javascript">document.write('This *should not* be interpreted as markdown');</script> Here’s a simple block: <div> foo </div> This should be a code block, though: <div> foo </div> As should this: <div>foo</div> Now, nested: <div> <div> <div> foo </div> </div> </div> This should just be an HTML comment: <!-- Comment --> Multiline: <!-- Blah Blah --> <!-- This is another comment. --> Code block: <!-- Comment --> Just plain comment, with trailing spaces on the line: <!-- foo --> Code: <hr /> Hr’s: <hr> <hr /> <hr /> <hr> <hr /> <hr /> <hr class="foo" id="bar" /> <hr class="foo" id="bar" /> <hr class="foo" id="bar"> ------------------------------------------------------------------------"> </outline> -<outline text="Inline Markup" _note="This is *emphasized*, and so *is this*. This is **strong**, and so **is this**. An *[emphasized link](/url)*. ***This is strong and em.*** So is ***this*** word. ***This is strong and em.*** So is ***this*** word. This is code: `>`, `$`, `\`, `\$`, `<html>`. ~~This is *strikeout*.~~ Superscripts: a^bc^d a^*hello*^ a^hello there^. Subscripts: H~2~O, H~23~O, H~many of them~O. These should not be superscripts or subscripts, because of the unescaped spaces: a\^b c\^d, a\~b c\~d. * * * * *"> +<outline text="Inline Markup" _note="This is *emphasized*, and so *is this*. This is **strong**, and so **is this**. An *[emphasized link](/url)*. ***This is strong and em.*** So is ***this*** word. ***This is strong and em.*** So is ***this*** word. This is code: `>`, `$`, `\`, `\$`, `<html>`. ~~This is *strikeout*.~~ Superscripts: a^bc^d a^*hello*^ a^hello there^. Subscripts: H~2~O, H~23~O, H~many of them~O. These should not be superscripts or subscripts, because of the unescaped spaces: a\^b c\^d, a\~b c\~d. ------------------------------------------------------------------------"> </outline> -<outline text="Smart quotes, ellipses, dashes" _note="“Hello,” said the spider. “‘Shelob’ is my name.” ‘A’, ‘B’, and ‘C’ are letters. ‘Oak,’ ‘elm,’ and ‘beech’ are names of trees. So is ‘pine.’ ‘He said, “I want to go.”’ Were you alive in the 70’s? Here is some quoted ‘`code`’ and a “[quoted link](http://example.com/?foo=1&bar=2)”. Some dashes: one—two — three—four — five. Dashes between numbers: 5–7, 255–66, 1987–1999. Ellipses…and…and…. * * * * *"> +<outline text="Smart quotes, ellipses, dashes" _note="“Hello,” said the spider. “‘Shelob’ is my name.” ‘A’, ‘B’, and ‘C’ are letters. ‘Oak,’ ‘elm,’ and ‘beech’ are names of trees. So is ‘pine.’ ‘He said, “I want to go.”’ Were you alive in the 70’s? Here is some quoted ‘`code`’ and a “[quoted link](http://example.com/?foo=1&bar=2)”. Some dashes: one—two — three—four — five. Dashes between numbers: 5–7, 255–66, 1987–1999. Ellipses…and…and…. ------------------------------------------------------------------------"> </outline> -<outline text="LaTeX" _note="- \cite[22-23]{smith.1899} - $2+2=4$ - $x \in y$ - $\alpha \wedge \omega$ - $223$ - $p$-Tree - Here’s some display math: $$\frac{d}{dx}f(x)=\lim_{h\to 0}\frac{f(x+h)-f(x)}{h}$$ - Here’s one that has a line break in it: $\alpha + \omega \times x^2$. These shouldn’t be math: - To get the famous equation, write `$e = mc^2$`. - \$22,000 is a *lot* of money. So is \$34,000. (It worked if “lot” is emphasized.) - Shoes (\$20) and socks (\$5). - Escaped `$`: \$73 *this should be emphasized* 23\$. Here’s a LaTeX table: \begin{tabular}{|l|l|}\hline Animal & Number \\ \hline Dog & 2 \\ Cat & 1 \\ \hline \end{tabular} * * * * *"> +<outline text="LaTeX" _note="- \cite[22-23]{smith.1899} - $2+2=4$ - $x \in y$ - $\alpha \wedge \omega$ - $223$ - $p$-Tree - Here’s some display math: $$\frac{d}{dx}f(x)=\lim_{h\to 0}\frac{f(x+h)-f(x)}{h}$$ - Here’s one that has a line break in it: $\alpha + \omega \times x^2$. These shouldn’t be math: - To get the famous equation, write `$e = mc^2$`. - \$22,000 is a *lot* of money. So is \$34,000. (It worked if “lot” is emphasized.) - Shoes (\$20) and socks (\$5). - Escaped `$`: \$73 *this should be emphasized* 23\$. Here’s a LaTeX table: \begin{tabular}{|l|l|}\hline Animal & Number \\ \hline Dog & 2 \\ Cat & 1 \\ \hline \end{tabular} ------------------------------------------------------------------------"> </outline> -<outline text="Special Characters" _note="Here is some unicode: - I hat: Î - o umlaut: ö - section: § - set membership: ∈ - copyright: © AT&T has an ampersand in their name. AT&T is another way to write it. This & that. 4 \< 5. 6 \> 5. Backslash: \\ Backtick: \` Asterisk: \* Underscore: \_ Left brace: { Right brace: } Left bracket: [ Right bracket: ] Left paren: ( Right paren: ) Greater-than: \> Hash: \# Period: . Bang: ! Plus: + Minus: - * * * * *"> +<outline text="Special Characters" _note="Here is some unicode: - I hat: Î - o umlaut: ö - section: § - set membership: ∈ - copyright: © AT&T has an ampersand in their name. AT&T is another way to write it. This & that. 4 \< 5. 6 \> 5. Backslash: \\ Backtick: \` Asterisk: \* Underscore: \_ Left brace: { Right brace: } Left bracket: [ Right bracket: ] Left paren: ( Right paren: ) Greater-than: \> Hash: \# Period: . Bang: ! Plus: + Minus: - ------------------------------------------------------------------------"> </outline> <outline text="Links"> <outline text="Explicit" _note="Just a [URL](/url/). [URL and title](/url/ "title"). [URL and title](/url/ "title preceded by two spaces"). [URL and title](/url/ "title preceded by a tab"). [URL and title](/url/ "title with "quotes" in it") [URL and title](/url/ "title with single quotes") [with\_underscore](/url/with_underscore) [Email link](mailto:nobody@nowhere.net) [Empty]()."> @@ -61,10 +61,10 @@ </outline> <outline text="With ampersands" _note="Here’s a [link with an ampersand in the URL](http://example.com/?foo=1&bar=2). Here’s a link with an amersand in the link text: [AT&T](http://att.com/ "AT&T"). Here’s an [inline link](/script?foo=1&bar=2). Here’s an [inline link in pointy braces](/script?foo=1&bar=2)."> </outline> - <outline text="Autolinks" _note="With an ampersand: <http://example.com/?foo=1&bar=2> - In a list? - <http://example.com/> - It should. An e-mail address: <nobody@nowhere.net> > Blockquoted: <http://example.com/> Auto-links should not occur here: `<http://example.com/>` or here: <http://example.com/> * * * * *"> + <outline text="Autolinks" _note="With an ampersand: <http://example.com/?foo=1&bar=2> - In a list? - <http://example.com/> - It should. An e-mail address: <nobody@nowhere.net> > Blockquoted: <http://example.com/> Auto-links should not occur here: `<http://example.com/>` or here: <http://example.com/> ------------------------------------------------------------------------"> </outline> </outline> -<outline text="Images" _note="From “Voyage dans la Lune” by Georges Melies (1902):  Here is a movie  icon. * * * * *"> +<outline text="Images" _note="From “Voyage dans la Lune” by Georges Melies (1902):  Here is a movie  icon. ------------------------------------------------------------------------"> </outline> <outline text="Footnotes" _note="Here is a footnote reference,[^1] and another.[^2] This should *not* be a footnote reference, because it contains a space.[\^my note] Here is an inline note.[^3] > Notes can go in quotes.[^4] 1. And in list items.[^5] This paragraph should not be part of the note, as it is not indented. [^1]: Here is the footnote. It can go anywhere after the footnote reference. It need not be placed at the end of the document. [^2]: Here’s the long note. This one contains multiple blocks. Subsequent blocks are indented to show that they belong to the footnote (as with list items). { <code> } If you want, you can indent every line, but you can also be lazy and just indent the first line of each block. [^3]: This is *easier* to type. Inline notes may contain [links](http://google.com) and `]` verbatim characters, as well as [bracketed text]. [^4]: In quote. [^5]: In list."> </outline> diff --git a/tests/writer.org b/tests/writer.org index 85016f352..13bacdfa6 100644 --- a/tests/writer.org +++ b/tests/writer.org @@ -42,7 +42,7 @@ item. Here's one with a bullet. * criminey. -There should be a hard line break +There should be a hard line break\\ here. -------------- @@ -397,7 +397,13 @@ Interpreted markdown in a table: #+BEGIN_HTML <table> +#+END_HTML + +#+BEGIN_HTML <tr> +#+END_HTML + +#+BEGIN_HTML <td> #+END_HTML @@ -405,6 +411,9 @@ This is /emphasized/ #+BEGIN_HTML </td> +#+END_HTML + +#+BEGIN_HTML <td> #+END_HTML @@ -412,9 +421,17 @@ And this is *strong* #+BEGIN_HTML </td> +#+END_HTML + +#+BEGIN_HTML </tr> +#+END_HTML + +#+BEGIN_HTML </table> +#+END_HTML +#+BEGIN_HTML <script type="text/javascript">document.write('This *should not* be interpreted as markdown');</script> #+END_HTML @@ -485,7 +502,9 @@ Multiline: Blah Blah --> +#+END_HTML +#+BEGIN_HTML <!-- This is another comment. --> @@ -500,7 +519,7 @@ Code block: Just plain comment, with trailing spaces on the line: #+BEGIN_HTML - <!-- foo --> + <!-- foo --> #+END_HTML Code: @@ -513,21 +532,37 @@ Hr's: #+BEGIN_HTML <hr> +#+END_HTML +#+BEGIN_HTML <hr /> +#+END_HTML +#+BEGIN_HTML <hr /> +#+END_HTML - <hr> +#+BEGIN_HTML + <hr> +#+END_HTML - <hr /> +#+BEGIN_HTML + <hr /> +#+END_HTML - <hr /> +#+BEGIN_HTML + <hr /> +#+END_HTML +#+BEGIN_HTML <hr class="foo" id="bar" /> +#+END_HTML +#+BEGIN_HTML <hr class="foo" id="bar" /> +#+END_HTML +#+BEGIN_HTML <hr class="foo" id="bar"> #+END_HTML diff --git a/tests/writer.plain b/tests/writer.plain index 60e7bb329..fab0489ac 100644 --- a/tests/writer.plain +++ b/tests/writer.plain @@ -5,39 +5,43 @@ July 17, 2006 This is a set of tests for pandoc. Most of them are adapted from John Gruber’s markdown test suite. -* * * * * +------------------------------------------------------------------------------ + + + +HEADERS -Headers -======= Level 2 with an embedded link ------------------------------ -Level 3 with emphasis +Level 3 with _emphasis_ Level 4 Level 5 -Level 1 -======= -Level 2 with emphasis ---------------------- + +LEVEL 1 + + +Level 2 with _emphasis_ Level 3 with no blank line + Level 2 -------- with no blank line -* * * * * +------------------------------------------------------------------------------ + + + +PARAGRAPHS -Paragraphs -========== Here’s a regular paragraph. @@ -47,13 +51,15 @@ item. Here’s one with a bullet. * criminey. -There should be a hard line break +There should be a hard line break here. -* * * * * +------------------------------------------------------------------------------ + + + +BLOCK QUOTES -Block Quotes -============ E-mail style: @@ -80,10 +86,12 @@ This should not be a block quote: 2 > 1. And a following paragraph. -* * * * * +------------------------------------------------------------------------------ + + + +CODE BLOCKS -Code Blocks -=========== Code: @@ -101,13 +109,14 @@ And: These should not be escaped: \$ \\ \> \[ \{ -* * * * * +------------------------------------------------------------------------------ + + + +LISTS -Lists -===== Unordered ---------- Asterisks tight: @@ -151,8 +160,8 @@ Minuses loose: - Minus 3 + Ordered -------- Tight: @@ -192,8 +201,8 @@ Multiple paragraphs: 3. Item 3. + Nested ------- - Tab - Tab @@ -221,8 +230,8 @@ Same thing but with paragraphs: 3. Third + Tabs and spaces ---------------- - this is a list item indented with tabs @@ -232,8 +241,8 @@ Tabs and spaces - this is an example list item indented with spaces + Fancy list markers ------------------- (2) begins with 2 (3) and now 3 @@ -264,17 +273,21 @@ M.A. 2007 B. Williams -* * * * * +------------------------------------------------------------------------------ + + + +DEFINITION LISTS -Definition Lists -================ Tight using spaces: apple red fruit + orange orange fruit + banana yellow fruit @@ -282,30 +295,37 @@ Tight using tabs: apple red fruit + orange orange fruit + banana yellow fruit Loose: apple + red fruit orange + orange fruit banana + yellow fruit Multiple blocks with italics: -apple +_apple_ + red fruit contains seeds, crisp, pleasant to taste -orange +_orange_ + orange fruit { orange code block } @@ -317,6 +337,7 @@ Multiple definitions, tight: apple red fruit computer + orange orange fruit bank @@ -324,11 +345,13 @@ orange Multiple definitions, loose: apple + red fruit computer orange + orange fruit bank @@ -336,18 +359,22 @@ orange Blank line after term, indented marker, alternate markers: apple + red fruit computer orange + orange fruit 1. sublist 2. sublist -HTML Blocks -=========== + + +HTML BLOCKS + Simple block on one line: @@ -361,8 +388,8 @@ bar Interpreted markdown in a table: -This is emphasized -And this is strong +This is _emphasized_ +And this is STRONG Here’s a simple block: foo @@ -397,40 +424,44 @@ Code: Hr’s: -* * * * * +------------------------------------------------------------------------------ + + + +INLINE MARKUP -Inline Markup -============= -This is emphasized, and so is this. +This is _emphasized_, and so _is this_. -This is strong, and so is this. +This is STRONG, and so IS THIS. -An emphasized link. +An _emphasized link_. -This is strong and em. +_THIS IS STRONG AND EM._ -So is this word. +So is _THIS_ word. -This is strong and em. +_THIS IS STRONG AND EM._ -So is this word. +So is _THIS_ word. This is code: >, $, \, \$, <html>. -This is strikeout. +~~This is _strikeout_.~~ -Superscripts: abcd ahello ahello there. +Superscripts: a^bc^d a^_hello_^ a^hello there^. -Subscripts: H2O, H23O, Hmany of themO. +Subscripts: H~2~O, H~23~O, H~many of them~O. These should not be superscripts or subscripts, because of the unescaped spaces: a^b c^d, a~b c~d. -* * * * * +------------------------------------------------------------------------------ + + + +SMART QUOTES, ELLIPSES, DASHES -Smart quotes, ellipses, dashes -============================== “Hello,” said the spider. “‘Shelob’ is my name.” @@ -448,35 +479,39 @@ Dashes between numbers: 5–7, 255–66, 1987–1999. Ellipses…and…and…. -* * * * * +------------------------------------------------------------------------------ + + + +LATEX -LaTeX -===== - -- 2+2=4 -- x \in y -- \alpha \wedge \omega +- 2 + 2 = 4 +- x ∈ y +- α ∧ ω - 223 - p-Tree - Here’s some display math: - \frac{d}{dx}f(x)=\lim_{h\to 0}\frac{f(x+h)-f(x)}{h} -- Here’s one that has a line break in it: \alpha + \omega \times x^2. + $$\frac{d}{dx}f(x)=\lim_{h\to 0}\frac{f(x+h)-f(x)}{h}$$ +- Here’s one that has a line break in it: α + ω × x^2^. These shouldn’t be math: - To get the famous equation, write $e = mc^2$. -- $22,000 is a lot of money. So is $34,000. (It worked if “lot” is +- $22,000 is a _lot_ of money. So is $34,000. (It worked if “lot” is emphasized.) - Shoes ($20) and socks ($5). -- Escaped $: $73 this should be emphasized 23$. +- Escaped $: $73 _this should be emphasized_ 23$. Here’s a LaTeX table: -* * * * * +------------------------------------------------------------------------------ + + + +SPECIAL CHARACTERS -Special Characters -================== Here is some unicode: @@ -528,13 +563,14 @@ Plus: + Minus: - -* * * * * +------------------------------------------------------------------------------ + + + +LINKS -Links -===== Explicit --------- Just a URL. @@ -554,8 +590,8 @@ Email link Empty. + Reference ---------- Foo bar. @@ -581,8 +617,8 @@ Foo bar. Foo biz. + With ampersands ---------------- Here’s a link with an ampersand in the URL. @@ -592,8 +628,8 @@ Here’s an inline link. Here’s an inline link in pointy braces. + Autolinks ---------- With an ampersand: http://example.com/?foo=1&bar=2 @@ -609,10 +645,12 @@ Auto-links should not occur here: <http://example.com/> or here: <http://example.com/> -* * * * * +------------------------------------------------------------------------------ + + + +IMAGES -Images -====== From “Voyage dans la Lune” by Georges Melies (1902): @@ -620,37 +658,39 @@ From “Voyage dans la Lune” by Georges Melies (1902): Here is a movie [movie] icon. -* * * * * +------------------------------------------------------------------------------ + + + +FOOTNOTES -Footnotes -========= -Here is a footnote reference,[^1] and another.[^2] This should not be a +Here is a footnote reference,[1] and another.[2] This should _not_ be a footnote reference, because it contains a space.[^my note] Here is an inline -note.[^3] +note.[3] - Notes can go in quotes.[^4] + Notes can go in quotes.[4] -1. And in list items.[^5] +1. And in list items.[5] This paragraph should not be part of the note, as it is not indented. -[^1]: Here is the footnote. It can go anywhere after the footnote reference. - It need not be placed at the end of the document. +[1] Here is the footnote. It can go anywhere after the footnote reference. It +need not be placed at the end of the document. -[^2]: Here’s the long note. This one contains multiple blocks. +[2] Here’s the long note. This one contains multiple blocks. - Subsequent blocks are indented to show that they belong to the footnote - (as with list items). +Subsequent blocks are indented to show that they belong to the footnote (as +with list items). - { <code> } + { <code> } - If you want, you can indent every line, but you can also be lazy and just - indent the first line of each block. +If you want, you can indent every line, but you can also be lazy and just +indent the first line of each block. -[^3]: This is easier to type. Inline notes may contain links and ] verbatim - characters, as well as [bracketed text]. +[3] This is _easier_ to type. Inline notes may contain links and ] verbatim +characters, as well as [bracketed text]. -[^4]: In quote. +[4] In quote. -[^5]: In list. +[5] In list. diff --git a/tests/writer.rst b/tests/writer.rst index 68bc4a06c..f09871a34 100644 --- a/tests/writer.rst +++ b/tests/writer.rst @@ -432,7 +432,13 @@ Interpreted markdown in a table: .. raw:: html <table> + +.. raw:: html + <tr> + +.. raw:: html + <td> This is *emphasized* @@ -440,6 +446,9 @@ This is *emphasized* .. raw:: html </td> + +.. raw:: html + <td> And this is **strong** @@ -447,9 +456,17 @@ And this is **strong** .. raw:: html </td> + +.. raw:: html + </tr> + +.. raw:: html + </table> +.. raw:: html + <script type="text/javascript">document.write('This *should not* be interpreted as markdown');</script> Here’s a simple block: @@ -521,6 +538,8 @@ Multiline: Blah --> +.. raw:: html + <!-- This is another comment. --> @@ -535,7 +554,7 @@ Just plain comment, with trailing spaces on the line: .. raw:: html - <!-- foo --> + <!-- foo --> Code: @@ -549,20 +568,36 @@ Hr’s: <hr> +.. raw:: html + <hr /> +.. raw:: html + <hr /> - <hr> +.. raw:: html + + <hr> - <hr /> +.. raw:: html - <hr /> + <hr /> + +.. raw:: html + + <hr /> + +.. raw:: html <hr class="foo" id="bar" /> +.. raw:: html + <hr class="foo" id="bar" /> +.. raw:: html + <hr class="foo" id="bar"> -------------- @@ -804,6 +839,7 @@ From “Voyage dans la Lune” by Georges Melies (1902): :alt: Voyage dans la Lune lalune + Here is a movie |movie| icon. -------------- diff --git a/tests/writer.rtf b/tests/writer.rtf index 954d95cc4..08d3c1fee 100644 --- a/tests/writer.rtf +++ b/tests/writer.rtf @@ -208,13 +208,13 @@ These should not be escaped: \\$ \\\\ \\> \\[ \\\{\par} {\pard \ql \f0 \sa180 \li0 \fi0 Simple block on one line:\par} {\pard \ql \f0 \sa0 \li0 \fi0 foo\par} {\pard \ql \f0 \sa180 \li0 \fi0 And nested without indentation:\par} -{\pard \ql \f0 \sa0 \li0 \fi0 foo\par} +{\pard \ql \f0 \sa180 \li0 \fi0 foo\par} {\pard \ql \f0 \sa0 \li0 \fi0 bar\par} {\pard \ql \f0 \sa180 \li0 \fi0 Interpreted markdown in a table:\par} {\pard \ql \f0 \sa0 \li0 \fi0 This is {\i emphasized}\par} {\pard \ql \f0 \sa0 \li0 \fi0 And this is {\b strong}\par} {\pard \ql \f0 \sa180 \li0 \fi0 Here\u8217's a simple block:\par} -{\pard \ql \f0 \sa0 \li0 \fi0 foo\par} +{\pard \ql \f0 \sa180 \li0 \fi0 foo\par} {\pard \ql \f0 \sa180 \li0 \fi0 This should be a code block, though:\par} {\pard \ql \f0 \sa180 \li0 \fi0 \f1 <div>\line foo\line @@ -429,8 +429,8 @@ http://example.com/ {\pard \qc \f0 \sa180 \li0 \fi0 \emdash\emdash\emdash\emdash\emdash\par} {\pard \ql \f0 \sa180 \li0 \fi0 \b \fs36 Images\par} {\pard \ql \f0 \sa180 \li0 \fi0 From \u8220"Voyage dans la Lune\u8221" by Georges Melies (1902):\par} -{\pard \ql \f0 \sa180 \li0 \fi0 {\pict\jpegblip ffd8ffe000104a46494600010101007800780000ffdb00430006040506050406060506070706080a100a0a09090a140e0f0c1017141818171416161a1d251f1a1b231c1616202c20232627292a29191f2d302d283025282928ffdb0043010707070a080a130a0a13281a161a2828282828282828282828282828282828282828282828282828282828282828282828282828282828282828282828282828ffc000110800fa00fa03011100021101031101ffc4001c0000000701010000000000000000000000010203040506070008ffc4003e100002010303020404040502050500030001020300041105122106311322415107617181143291a1234252b1c115f016336272d1082443e1f1265382ffc40017010101010100000000000000000000000000010204ffc4001b11010101010003010000000000000000000001110212213141ffda000c03010002110311003f00dadd18a10a704f6a95ccc57e37750782b0d8d9ea0cd32e7c5446e07e9f4ad723119a7b89e61e348f260719278aad613cbb640002938c76a182b264fc87bd13009c0c019c76e3d68a072e1cf6f4cd502d330c28269a61bb39c923923d4fad44c08dccb95cfd28b8280769ee08a263891e1808739e4f1d8d149392172cc714050dbb9fde8960ed8c60b79b1ed44103b05c331dbdb1dc5026ac1946d20ff8140aa631c773ec738a0346a003bf93e9cf02801895e7b9a01886796c923bd0090a06393c76a0142003ce3d86680d8dd9392303f5341ccc1b3cf7a2c812c37e4923d381429757013209fa511c18146c9247a0f6a007900c0c671c6280854e086c673eb45c27c038fd68aedff2fda836ef881f136f25d5e6b7d1262964aa02b03f98fbf153131935edcc97576f35c33349212cc4f39f7ab26186dfce5b200f73451f7600dcb8cf27e7400c0b291914046c9e0718fde81371b8e7273f4ef4007691919240e714097f31f376e7b5008caee27807b0f5a02c8e1b3c6d27d33cd0201d839523144d1a149ae084b78da47638211771fd050d582c3a0faab5119b6d12f8ab1c06788a0fd4e2ac356fd1fe08754ddccaba849696309e598c9e2103fed1dcfdeadc44fea5ff00a7f956366d375e492403ca935bedcf1eea4ff6ac68a55efc1beb3b552574f8e7009ff933a927ec715bc82b3a8f4d6bba5ca1352d22fe061cf9a0383f71dea5119cc6c0baed3eaac0f1fad40897dcc3d81f7a052366c1007df3400f21edefc5008c28f30c9c5170ee4fc37830086395250a7c66770c18e78da31c0c63de8609b41f7c515c5172a30c3b76344a3e377cb2339cf7a242aea89808cce368272b8c1a2e107c672a49f5c1a181c9c7ae7da8a2119e7b1f5068099ffa68258a132062d8f9e0f34059502b61bf2824e681bb297ced2a71efda80f19c47b9c77fdbe74057c13e539cf3c1a0eeeb9c73f33405ddb4f18249c1e28062b79ae242902024465b9214614649e7bd0362a7249eddc513456e5720f38f5a1a98e96e95d6baa6ebc2d1ad1e65521649bb469f563534d6d7d31f04347d2a2fc5f535db6a0e83718906c887cbbe5a9a8bef44dce9f731ca9a2e89169d6d6f2184b1455dc07b11dcfeb4d16f119c649a681285b03d3e5500f87820ff006a0e098191de80ac9b8904647b55d11da9681a56a31f87a869f6970b8ffe4883629a289aefc16e92d441682da5b098f21ed9f033f353914d19b751fc08d66cc16d12fe2bf45ec92ff0df1fdbfb559ec667aff4eeb1a04db359d3ae6d40eccebe53f46ec7f5ab82263da7dcf3eb5174e5181076918c7de869503232491ee4515c1803824f03b51287f30e0e7d803449494832c157278a2e8c71fcb9f9d144639236824d01e142efb1768cfb9c7ef40512a818de78ff00a682518e7cc30ab9e00a02cce9953247bd41e467191ed9a04205ee99da4e4e3d283a524b0427b5026c18a8e082067db8341ce0e39ed409b6502907391edda80f2dfdc496f0c124ac6184b144cf0a4e338fd2894f7a7342d4ba9b568f4fd261f12571966270a8bfd47d8511bae85f02b47b7fc34bac5d5c5dc88a0c90ab6c8d9bedce3ef4d1ad691a6dae976a96d616d15b409f9638d70054a1dbc68ea51d4329f4619a8022b78e04548515117b05000a035c5c4702a995c26e3819f534047bcb68a458cce866719540724d02e41c0f7a012a40f6141cbc8e7bd01719e38e6838af1c0a04ca8206d3cd037bdb082fad9e0bd8a39e0718649141047d0d5d18f759fc0cd3af164b8e9999acae4e4f81236e898f7c0f55fed574615aee83a96817ef67abda3db4ebdb7f66f983d88a061bb8db9e3d45165076db83c1f950a53780d8247c80a2398f182724f1c7ad080c608cfa7a51a0062adc7afbd0130173bb9c5070f071cb37e82826106e8f615e01c9e680d6b35bc534be3c1e3831b2aa962bb188f2b71df1de819ae4b1048c7f57bd01a58268e332642ae0704f7cf6207af6a01b99e17b7b6416e227407c494139909ed9f4c0a04a4e501e0f1eb40d263e53dce7fa682c9d0bd13abf58dd6db18bc2b157c4975270ab8ef8f563f21447a73a03a1f4de8eb031582b497328066b97fcd21ff038edfde88b7e32703bd64188e7e6283864b73400cd804b67ca3268317eacea6d56ff005233592f8b6303f953fa4af7c2fa93417fe98b763e0ea171297bab98558068f695ce0e08fdbd281e5c6a57ba5e9d14d716ef7774f2ec112601da4f27ec2827ada74bab559a20e148fcae36b0f91140283729c77a0e0a7777a01dac68395719e39a029607cb901b19c501480ab9279f4a086ea8d0b48d76c0586b7143224a76c61ce1831fe93e86b43cd1f12fe19ea7d2533dcdbeebcd20b612651e68f9ece3fcf6fa5067cbcf20ff009a051724905411e94032799060723da8406d6c67e7ea68d0e1770fe5cfb5026c37039ef9a02eca098c91e6e01e71c500b1d8a49c12786cf6a06a4e256008e3d050119958007920e2801154e32fb4120927b014017eb1c523ac5209a356215c291b87be28957ef853f0d66eaa99352d515e1d190f947669ce7b0ffa7e74a8f4be996569a5d9c56b6704705b46bb5238d42851f2ac875712bc70b3c30f892019540704d01ad2669a0491936330c95ce7140b2e4939a03638c7e8680ae485e33bbe540d60d3ada162c90a02c7270a39340a4f28b68da4645007a8f6a069a746f73235ddcefc391e12b2e1916824948742c99382473c73404791c617695279dc0640f9502c578c9efeb4095cb4cb0830ba21cf999c6401f4f5a05061d430c8079a02e03b3004311c7d281b5e3cd676c65489ee594e4aafe6c7ae07a9a0a075bbea3a8ea96f047d3935ebc404f04ad29411e08e011d98fed416fd212ee5b05b4d5ad6300c615807f1171eaa49eff5ad418c7c55f8466dd66d57a521f20cbcd66a7247a9283dbe5418a63862479877cf1f6c5008e400bdf1ce684016fe53dfbd1a73794600e08ce3d6800377c8c7d6800a9cf75fd4503d91492460f7ee3d28247a7b459f5fd592d22711c206f9e563858a31f99cfd050583518ba75247b1d134f9aed21396d4669769931dc01c003f7a329c4d17458ac5b55d36c12e040a3f1da75c1cb04ede2447f7f6a94567ad7a66db4fbbb29ba7d65b8b4bd8ccd09c8231eaa07b8ab04a7c2cf87b3f53ea8d77abc72c1a5dabe2452bb5a561fc83e5ee7e541e988218ed2dd22b7855228d76a46a00000ec00a510bd4dd511f4fe84da95cc31f880022da4902b1e7d3e99ac86fd03d631f565b4ee6d4dbbc649009cab2e48c83f514165b8b94b6895c44f279c280839e78ce28178ae6de46748a789e453865570483ec6812d42e85a421fc37918b00a883924d024c6e99b7a2a966c0009e17dc9f9fed40f81c77e28139218e4ff9815b9cf23340a01c907b9140201038ed402fcafd28386464e4fd33c50272bc60032609cf00fbd024f722dc66f24822ddf972f8feff00e280f69b24844919cac9ce7de83a447f30ded823007b50459d6ecacb528349b979127651b1dc795f1f3f7a0990148054823dc5015d491c0a0c3be337c2ff00c489b5ee9c87172016b9b541c49ff5a8f7f71eb560c1fc43e0a47e1aa94277310431f91fa551c1727f29ed409b641c86e31839a3454805739c1f6a026f1fd740f64665fc8c31cfde82db79bb40e9e8f49b62eb7d7e8b717ec832c91ff247fa1dc7df2281bcc9369d671493c422b7911654c1215f92bb8827bf068624ba635392df5eb4b9924558ee5bc19b71cee43c6dc7cf34c657be8db0b0b9d0f51d2afe668934dbf9628ddb8c2b8c0073f3a80da37546a7d25174fd95dc125c69f7313ee5655dfc313bd483cf07b1f6a68d5b48d5ec758b612e9d7293211c8fe653f35ee2a084eb9e8bb1eafb3582fe496278f3e1c919fcb9f97ad03ee8dd017a6741b6d3229dae161057c5750a48249ec3eb4139238568f6a9e7b103b5037934cb3793c610a2cd9277a8da73f5140ee38f6280c4b11c65b934023006d50050030e4647de80c846de3b500fcf9fbd0197273ed4007b91400e580c8e45074a82400e72682b36fd2162b7f25ddc09af2766ceeb872db79cf00f6a0b3229550140e07007a50092db860673de818df473c862686dad6470d9cce3b7b63e740fa1de6252ebb5bd81cd00bee2d800d003a6464004763ce683ce9f1cbe1f1d3a67ea1d1a30b68edffba814708c7f9c63d0fafceaca31e6dc71e1f07daa82608c83819f7a1a11ce149238fd68d0a579ec682cfd27a7c3a86bd10bc38b3b756b8b93c1fe1a8c91f7381f7a034f752ea5aa5c5eb292f732128037619c018f6ec282e5a2cb047abda74d5ce9b6da80f136de4a496219b3e48c92000323ea73467519d3da5bb757dbda410ac90c77c23058f99007ee7ec31416882ee47d23acb5185caf8bab4691b1efe57fff0038a9457ee75a82f6e7429350466b482f2742c0f74241c80c38c64541a9cfa1e89ac0177d33ab3d8de28f2b5bca429f91140e2c7a9b5ae9fb85b6ea9b46b9b3c796fe040768f76ec0fafb1f9505df4ebdb3d4edd6e74db98ee216fe68ce47d280648f75e2485a44da385ddc13f4a025ddbdbea16a633286566ce55f9c8f6c502ad750db2c514f30dec428247e6340bbf04100b73402afb943ed2b9e30683836defe9403bc1e06734020e06280cafe8683a375941d841c77c1a0151b467b50159f00e4127e5402872371040c5046eb5aadbe9b1c02e2f6dad25b89047099c677b7b0140fe3f1010afc803f3018e68160c3041ee2823f5dba92d34db89a1d9e2843b03b6d05bd013560c1748d57aa2797c6b35bab78e6959dc47231580ff336dcfb03c1a58364b5bbb7d7fa7b7427f1f673830c8664285bd1815238fad20f2c7c41e979ba43aa2e2c1cb1b663bede438f3a13c7dc76fb5515e9065b851f7a02950002a09c51a1b83cf14176e90d3645e9ad7752752aac23b3439c066665c827e944d29a6410aea725c4567135bd840d3c88a723728c29c9efe6c50d3ee9545b0bf8ef2e6e3c2fc2c6f72f2920e5f19039ee4938a9a875d03278377acf52ddf867f036ef71923932bfe51fbd3475cdc369df0db4fb389d4ea37970fa9cc0b00511795ce7d4f181eb4cd2451755fc45ac16d637381b14ca36b641dfce723e4053170d6cb52bbb362f6d3cb19241f2b9029862f09f143549ba7e7d2eef6caf2797c66ee17fdfd69862d1a069da7dfdac579d17adcda5ea9e1a992376c4723e39e3b024fd7e94c458ac3e25dee8d31d3bae74e7b79002bf8b8549471db38f5f4ed4c165e943a06a328d4ba605b4b22a1523c420c64fbaf38a82d36f0ce7cf7463790729b53017e940e0b0ceceed8ce0500e1b70daa08f5c9ed41d271cd0132476e7d7ff00aa069797d2411168ed9a41fcc858211f73c5075acb25ca6fb82aa31e58a36c81f561dcd033d42169e158ac64b98151b3981c2966cf639f4a064c7a8ac55e4865b7d493701e1c8e52403ea3cbfda827e390ca3f2c914aa81991bd281cdacc2747215c60e0ee5c67e940cb51b0b2bcbd824bfb08ee1a252d1caea1821cfa67b1fa504982b2283ce08f518a08abb82f6dd0369a5662081e14ce40c7ae1b04fda82275cb0bfd4f4536f7114589a5412461f3e4ce4e0e060f63f6ab2893d3b4b5b5b78e22ed22aae3cc3cc7e64fad3449a22a461500007602a0cd7e3b74c26b5d2ad79147baf34eccca40e4a7f30ff3f6aba3cd0543267eb5427b86f1f4c76ef45d0eca1ad5ef224d13e1cf4fd9b22192fa67bc955f8c8c617fba9fb510d7a6ed3fd43a735e5b54964be658c048fb6cdd9e7eb8a186bac97d174e6d22e23437b7ac26b95e77c68bf950fa7279e2b22dba45b59e97a669fa4ea36aeff89cea9a90451fc355ff0096ad9f4ce3f41570675d4fa8c77da8de5cde5be26bc653171ca47dc1f6c9fed5562b97f70276808da7c24f0c1c63804e33fa8a2928c0e0383c8f7ed41d92a41393f4a2548595c2c37493db4cd04e8a08f139566edfef3445b6e7aeaf65d2df48ea2b11776ae02a93e564c772adef409f4ee8ba9a21d73a36fa579ad9f325afe599171ed9c30a960d5ba0fe2843abb47a6f510fc26a4c36890f9558fcc6783506a1147b510024e30339ce680d2c6ae9861eb9a009178a0205443b989e39cd01d8075e3047ce80563057ca381ed4011c4531e503d85013c91b804a21279c903341131cda8c3abdc8650f6d20c4321232adec3dc504bab2c113c9293bb1963df3408dd4b75e1efb2856463dbc43b4631fad047e9177ad4fe32ea16b1db4b8fe1aa92571f5f5a0916bc8e0895af5c46c17cd8c9ff7da80f6d736f7f6915c59cab35bc837238ed8a072a31c1ef4062870718a06f7702dc5b3c522ee4752ae0fa8230683c75d6ba3b74ef535fe984929149e4278ca9e47edfdab42058003763ed409f88ffd6dfad06b1f12ae612fa0c76e0b471e9916d23f973eb4158d3efeff004a984da5debc1295d8e4018dbf3145d583a2ad96f356bbd7f5d90dc59587f1e79a6392f28fcaa3ee47159444ea3aa5ddfc7acf50dcdc344d7a4dbc317f52641200f6000fdeb41b5ef51d8eab672ffa9e971c97c11638268e431a46000012a3b9a351567db823b11f3ef40948e428048207a8340ab48ae83cb83ee0f3428a982719edf3e68c9cc97d3fe15ad8c9be138f2bf38e7b8f6ef40f7a5f55bdd3f56b46d3649127f1405f08e7249c76f5fa50689d48ba5f545cdcbdb462cba9206411b2b055bb07d4fb1c73528d4fa8f52d62cf47b6b8d2e65fc458c49f8a818795c151939f977a823ba0fe253750eb7fe937b04293f9f6c90be41dbdc7ff006283473c1efc1a06f69776d73bbf0f2aca32572bc80470450284a46dfca19f819f5a04e799614def26c0bdce09cfd85045dc75769d12dc3c3e2491db0dd3c85195235f7c91cfd066ae0cdba9be31f4ec61a386c1ef9d4ee473e45cfb1cf34c101d3ff1ac9d481d46c628ed24751881880833f988e7b0fa5328dfed2f2def2ce2b9b79925b791772ca87208f7a60182ee2b95cc0c48f53823fbd40ac658b30f4f4a086d4ee1d75bb6b78f4e965596366fc5211b23238008fde81f43692da5bc30d97831a0397dc09e3d714087506bf61a2c4cd77324726d2caaec141f9fd2ae0c435bf8c57173ad7876f7a2daca10489121244cdf319ce3dbf5a834fe81f881a6f57bcb6ba7c53c72c11873e28cee1db391dbef4199ff00ea4348116a5a66a8a8a04aad04847a90723f6ad7d18c312ddc02a3815423ba0f63fa541687bd9efe1b533b3c9e0a78473e899e318a09bd0ba6eef543e3b2bd8e9b10064bd9e4da001dc81401aeeb29a984d0ba7d5e1d06d4e6594f06523bc8e7f5c0ac8af752dfc17d7090d9218ec6d9447129ee71fcc4fb9cd6842ab10dc0014f3e5a2c1704b671dfdc734525226dc939e283a362c7f940344a380393df144733e2276e38f5efcd01b4bbbfc3dda4a9298a44395902e4a9c70682660d4265d62de40b1bdc1545054f95c8fe627df141af7c3af8808f3dd68dd5d2a45765884b8908d8c3b6c27b7a77a945d7a5fa474bd2ba8e4d5748b28624955d5d8b13b79ee9e983d8d40a753758c7a46b96f6114725dc92279a2810b3a64f94900763cfafa503fd3b59b79ed84da34713c0cd890f0a158fa1f981de826e1b548959fc4dc5cee24b6467e59ed4101ff19e9f676baa5d6a72c50adb4ad1ac790ccc076200f7ad41e7df881d79a87576a5f87b0f161d381db1c2a36e7e6d8ff3416bf87ff082c6f208ef7a82f22b9761bd6d619785f6dc477fa53705ab57f83bd297ceb1e9caf67708db9c4526723e849e3e94f212dd25d117fd29a8c09a76b534fa39cf8b6b71ced38e36fb73417f52e64548e34007e673e9f21ef590a1c918c90718dc281a69b68f67118d9da5058b798f6fa7fe280daadd1b2d36eae70710c4d263df0a4d583cc7a668fd4bf11b5837d7c93dcd9a3146959822a0e781f4cfa55161e9dd7fa67a4f55b9e9aea3e9f81fc09ca0ba118998fcdb2338c7b528d39f4cd2ba76e2d357d292df4eb391809963420ce1b1b576fa1e7359119f1eb4e17dd033ca172d6b2a4df303383fdeb5c8f2eef3bce4e0e335684cb0c9f354160d36f64b0baf16072b91b5f03391f43c51aab23a5debe91c4fad4d73689e6fc3a290573ff4f03e59f4a3280d67581ce916567f84b58ce0a1fccec3d58fa9a084de08c90464e4d1a8e419059b201f4a05630a176918efc50176293872c17bf14042aa0125b03db14046c60b60123fde6827fa0c68edd5365ff11346ba6292ee64194240c807e59a32b7fc51bfe8bd5ed5db424860beb62b89218422ce09c11c01dbbd0660ae110bf1bf2154838dbebfefeb41a8f4cdac7f117458f4d9ecd2df53b4cf81a822808c47255c0f7c8e7fb54a2ec2cfabba3b4b4b8d3af12eedad40926b0f070a13f9b633649f7a82eba6ea4357d321d4ecad512daf20df26e016507fa4fbfaf3e98f9d067dd2bd2faac9aa4d72d72d1e9510ca46a7631c7a320e18f1dfd7bd059afb7da816d23de4ba5de211346a1e4785f190548e4648c63b64e6b43ce9d5baafe3b539c5b452dbda46c638a167cb281c73ee4ff9340e3a3fa5f5aea4ba58f4bb57dbfcf2b02a8bf7f7a0de3a5fa0b50d2a2d92eb3e048c0a97c867dbedcf6a944e5cf4f6b76d1b3d8ea42795066266c87c81c65b9cfaf15048e83af3cd64abac08edaf01546c38dae4e0657ee6826e5b892de3702292e2545ddb55700fd0fbfca81c4b3bc718716eef9eeaa402280d14ab3c0b2c65c06fe571823ed40df56b217fa6dd5ab9216689a33f2c8c558307e83b8d77a37aaa7d22f2512c28768800c9954671b3d33ebef568d0ef7a7749eb0b5bbbb162d657b32b46d2e1564c8ed9c5644d1b0b9bbd261d2a440af6cb0e2e5b1e7dbc1238e0f7a0375b696daa7496a3a4dac8a92cf078685b271db04d391e40d5ec4586a1716de2a49e0c8c85d3b120f715ba1899173ff305413070abd89cfe9f5a2d3ee9c8639fa874eb6b804c52dc46b20c9f302c3bd11e84d47e1af4d5dc6521d3e3b662c19a58721ff5a9a321f89bd27a374b456d158dccd34d333332c9b4b2afbe47a7cb1f7aa33d2bc0d8c0f1c8f6a2c14b6d501b39cf63450897380c319e3de8065031c038f7ed40d8faf1ce41e4d004876a8dc3cc7e743025c956c818028c904579e7f0e15695c9c0541924f6c00283d0bf07f42d6b48820b8d62d20b2b58d656404959e52f83c8ff00fcfafbd4a35bb06f12391a48dd55cee2b2f3818ed8f6a8158a159890f02242079147623e631c502b0db436d1ecb7458d4738038fb0a087d6eeb508f48bb7d32d95750752b6c26c905b3ddb6f61eb574794f5cb6b9d0fa9678b512b25d24bbe52b8c1638278fbd582c57ff12afaed45b5bc0d0d8a8c08a2731ee3eec5793f40450466a1d59af446293c186cd53ca0c36eab93dc649e49fbd048e89f1675ed35e301e293919dcbf9867b37cbe94a35fe94ea4d33aba6824306dc48015750d86c6e247b0cf63591a40b8dc23fc30f14138dcac3000f9d03687547f12e8dd5af816b13148dddbcd29039c0f6f6f7a0eb5d62caf5636825db70c9bc4328f0dc0271c8a090627d3073ce681acf6505ccf14d35bc2f2c2731bb28254fb8a075144a83ca806792400334049ee6281e2496408656d880ff0031f61fa50446bd76058ea1b9e21025a3bb48afe71df9c7b71de9c8f196a0de23ca7b827d4f7add117e0cbfd4b5059392369663ff004e71c51aa97e8f555eadd258f2bf8a889cff00dc28cbd0bf123a926e96d163bdb74490bca2321c678209ff001591e71eafd7a7d7ef45cde2c20aae144638033fb9ad2e1b5e69d058da431ccf21d4a5c3b4631b62523807feaf5c7a50222f2d648c25f5aeec8c2cd19dae3d3e87e944d3eb7e90d425b49ef2292de38224f1505c3f8724a9eeaa7bd0d57a60406059436306868a7803839c7ad1a158039c13f4a33a716767f8cb9b6b55e1ae2458813e9938cd07a9f42d0b4de99b4b7d1f41b58ff19b03c93ba06607fa8b1f5f619a5b8266d74a65d42da6ba90cce996dcdc8c9fff006a5a2c2635083b05ef83eb5028076341db4b1ed9f7a04651fc41db18ed419d75b744dbea335fcb0db0335f2057901c05da73c8f9d5d18a75174a3f4c47335e35da4ce418a489374254f707d463d33565d1529b569a489a17944b06ec8057d71dcd037b4b6b8bfba31584124b27e62a8a4f1ea68357f83da7ea5a76bfe0912453ccabb49194653cb60f6ce3dfda983d196cd108c2401711f9768e306b2297d73fc6d02773a8b591922693c5004bb9d72542fa2f6efde8314ff867aeeec27500b77bb5670e36ca19b1dff2e7f2fd2837ce8bd5dd348b78b552219022870d9c46e792a4f6c608a0b846c8e03232b29ec41cd0199f1410fd4b24b1e8f712c0a5e4452d851e6c639dbf3238a0afa42ba77475e4ba8470896681da45180b18da76af3c9029c8f26dc1df2b9c606e273e86b743331924f27f4a82c12280e59b008e79f6a2d4d74188ff00e30d203a82ad7519c1ff00b860d11ba7c5e86c9fa3afae6f4091e043e021270b21e01c7dcd6479ab4dd3aeb56be4b7b184cf2b301b57d07bfd2b4bad0fe25e9f6960ba7c7a55ac50cd750335ccaade7723b83b8f6e38a2207a5ba4e7ea3d93780cb616ca53781f99fbff009a0b675a5be9765d43a75a6ad3b25adb4185429b831c70303dfdfd2831eb8954ca48f3827819c71ed406b2b1b9bf9a5fc1c4ce2253238047957dc9345d122b792eee522811a495ce1157b93ed444ff0049f476b1aaf51c761345269d25be269259570c833c6077249e062a68f53e8ef0da69509d4ae225b92a04af232ab16f98cf1f4a5a266d4dbca8af13a329ecca723f51502d14f0cb9f05d1c8ee01c91f6a0393b4edfe63c8a031608859b38f97340d84d04e5846eae50f9829ce3eb400fb24466041f5e3d2823f56d22db57b192d6e61468a41c823ff0035651916bbf04ada7badda5cad6d1b72c09dc33f2a6875d25f0865d06fe2bc6d4c4d3282026cca8cfafcfd29a34cd234a10c768f711a78f1bb392a3001208e3ec69a26a58d640c832091c90706a084ea1d3eeafdadf4f86da3166c0b4b397c18f046140f5ce4d04f4702436e91c28a9122e028ed8a0a9f5a5b6a09a1bc5a135bc72cce048b3c5bc15c638f9d59043fc2db997481aa69dae49e1cb6bb643239211939e467818f97bd305965ebce9a10bc8da9dbaa2679dd9ce3d8530572cfac87566ab05ae9f1490692b9696e1f833738555f96793504df5f25945d2576b7ec16dc46792381c7b7ad5e60f234980e42f6c9c56a82ec3eff00bd4124e49700f1c646e3cd169ce9575f83d52cee324347323f6e3861ff008a23d47d4ba6a75074fdcd8ef317e2e2ff0098bdd4706a60c3f4ae8cd5f44eb8fc3e97248a638cbc73bf90483d463b373e9574685abf42a6b5649fea72bbdeac4a8d3b018cfae31f7a6895b6b29b41d30d8e9f6bbed9213e1b7a994e724fcbb5064bd7835a9752d3af75d8116354778f660788cbd9483dbb0a0cd20b2b8d43528ad2088bdcccf854039cff00e2827a0d34e9da1de896f2182492efc0976f998aa827d3d334113a74aa9a9298628e74570478bc0c7cf1da83724bb8246d3e6416b0384da61b5501c9f5c3704f152c037561a95f5fce61d3ad6db4ab950f34b331dd9f4191db8fdcd406d67a675ab4b6d325d1af248272a43430315ddec7038f6ad4b3f448bf47eb71cb69abddebf21d5e26896203846c30c8603b9c6452d9835901405660376319ac84bf13180779d8bb82827d4fb0a06f777367a75acd7170f1430a9f331200cfceae061a0cf6dac692d7365266191db0578f5edf3a6075a6c9278b3433188a467860d96fbd40fe540471409aa0c1140750001ed8ed4058e15133c983960077edf6a06faade5c5b7822d2d926766cb967da2341dd8f0727d85033d27597d62e2ee3163756915bbf8799d71e2f19dcbf2a092b88dd9a311950a0e5b70ce47fe6ac18af53f5b69da9752dd69da9ca906876e24465d9e69881c6ff005c679c0aa2bfd267a347512c93dbb5d42d90d3c800b68c9ce0ec3cfa528db74ad034db5905ee8be1ac728dc153984f3f980f4fb56453be2de8f647a6aff53796596f0aed46798ec033ce149c0fb0ad71479c9bb9dc3bf3c55a0b95f65a825150b481a407b93c0fda8a29c06671dc93803bd131eafd0af6dffe18d2ee25982a4b04603b7a9c631fad03bbe586381bc5945b96385718c827db3eb5288eb8ba934eb15fc3c535f05427796dcccdec7150637d5bd55d5362b7975aa4d0d919018adec8637807bb60723000e4f7cd58203538aefa8aeb478a7b9beba924547b8774cf8608036a80704639cf1f9855d1a7f4c68b67a03de5e5d59dad8d988c62e1c0f107a1e7fdf7a082ea6d07a6e3e99375a7cb6b3db093c727701e2360f7f53dfb50653d4130d42ee18f48b3f0232a15218936963ebf5fbd06dbf0cfa74855b9d46e04b730c6144691e12307d33ea7de8348ba6b5478a279a004f98c479247b81f5a9438805ac0be2e02e73c9ef8fbd40c2346d43578eefc40da7da1dc8b8eefea4fcb9fef419beabf12a4bcebcb2d2fa7ee0dc58492084b30236bb6467dce383f6a0b87556a67a7f4d95a0bbb5468816f0a69c78b2e072572719ce78357079dfab3af2e7a92c963b88d94abbbf91cedc93edf418aa2c5f0dbe2a6a9a0c90d8de34773a6a8da1186d6403fa48fec682d9adeb7a9b4c9d572dacc9a6c9700456e5ca910e000ecbd8e580352fb1ae7476bd6dd49a325e5a9f3025245fe961dea097523cc0919a032af039a006936c81423104649c703ef40dcce64bc3035a87b6f0c378f9fe7cf2b8fdf340a4b6e25962915d94a67807839f7a043586922b5636ec44c061063f31f6ab079d7fe19b7eb2d4efeef55d5d74f992e9a0fc3a441dcb13927b838c9aa2d4bf042c618e178efee6e18104870172318edf5c1e6945bbe1a748ea7d2315edbea3a99bcb190030c401010e4e783ee0fa56455be3d6b90c1a6268d69e17f1486900ee98ec29ccc183119419e7e55ba11f089f523ef5058363a8059fb8e31e9421b491056c01819e28d3d0ff07eea3d53a1e3b6b8db235aca63c139c0eea68ca47a9fa6ef757b83ff00bf68ad428c2f248c7a8f9fcea518df516adac74e7544f63a2ea172f1800291e6cee19ec78cd5826344e85b6bad25ba8fade5b99dae0ee11efc71e858f7e7d054a2d7d39a75ae8f7b6b00b8917f1516624b78429da327cec493db1db1d8540cf4aea28f58d6aeae2f6dd64b498082d880488d149fcea7d4939ab04175e6850a8d32de3b78e380c8de32c4db4e18e430fef543cf86fd0d691b4fabdf6648b3b2db69ce7dd87be68342d2f4fb9b5b891af1a28a2dc05bc5036d001e0eef7352884b961a2ea9aa7555c885e08d45b5bc52b61b686c120fb939fb541276bd4b61d53624d942e2f6200bc32290633e99f4233416dd3ad3f0d611c0c77b632e71dc9ef41156dd27a45addcb3dbd9c513b1dd941821bdc7b558333b9f873757fd69a85e3f813e9c7723b5d93265d872473c11544a68ff08fa75e290b42ec4e4124e70738fa5048e89f0f745d2aeadd2decedda6525c975121183c77f7a945c754d0e0d563682ed43425369403bff00bcd58308ba7d5fe13f5a05889974a9d8b46aede4914f707d88ff001528ddf4fd7edb54d1a1d56c312dab2e64dbc9418e78f5c541296d70b716d1cd6f8789977230ecc280cb7519b816f212b205de4e0843ce300f6cfcb39a0545c42cee88e0b458ddec33ee680eac92266360debc7b5056fad2d354b9b189745744be121daf27e550548ce3d4d58324d07a725e98ea2b7ff5381f5169a7579d021fe13904ee43ddfbe49038ab46e76cf05cc714f6d309232a4a98ce54fd6b2196bb7f2e9b631b2c427b891b6851db3eff002007341e5bf887aa2ea3d4f77378be381e42fdb711ed5a1554395caf1cd07617dcd04fc85402101da791421b49920331381c60d1a69bf02f56f03a925b12c162b98c955f775e47df19a32d99b518268e4491668704a79d4aeec7b7bd4a30feb7e9144d76e265697c3e2693631674273803e556087d76f35fd49859e9925ccf611141106f2e182e3241f727f5a94681a268f79ad1b1b8b9dd66b1c2b1ce9bb06361c1e7bf3fe6a096b0d3ba57488e485b52b40909c386901607d47bf7a0ae758eb69ac4d15be81a748f0a9c35cc90b2eff4c03c1c638a0b77405c5d5d45f87be5fe359a88b81b401dc1c7d38fb50586fed18ea3015790091591e447c1518c8c7a0a0a5754d8c9d49a8d9f4ee9dba0b3b5224b9692327728f627e7c6682f9a7e996b6b3a8b6b748a348820c7720761412c064e3041ce282b5d4bd73d3bd3f33daea97ac2e540dd0a292dc8cd043c1f15ba2a7923b65bb910371b9a12141f9d02edf13ba2ade56857551e5e77244c54fd0e280746ebfe99bbbd655d56dcdc9ce08465565f4ee3bfca82d53eb3a6dac3e25c5f5ba646402e33fa77a0aff5b74ad8757e9ca972844aa37c520fcca7d3f5ab067bd369a8f467544d626c98e9f7118f0200e4465c903049c8c9e6ad1b24334b6fa6249716cab20037c309dd83db03b5640dddac3764a4f02cb1103863919fa7a1a06d6f600c37162911b7b252b87dc773f1927393f4a079f868edae1ae6328a8b1ed38e30050226e85d5dc1f879011b3c47c2f604719f9d01eff4f4b83e3c6b18bb452b1cac9b8a83de80b16e8208a3b7b58e1407cc061427cc0ff1560ce7a8f592d69a97504cad2dac01a2b53900c3e9e51ea58f727d0551e73bfb86b99a49a46dcf21c96340dc13804f20f6f9501c0e3b8a0963316fcc4607007f57bd084d64dec01200ce483468ff0040d525d1755b4d4206ff0095207c11dc67ff0019a18f56584f6daad9dade4211e39104a8ded9152b235cd8c530613229c8c1c8ef50472e81690ee00322b0c100f0debdbb7ca8111ace856371358cba85aa5cc407891ccf83f2ef4048b4ad2e59bf116769672c72f99dd1437239078e2824a4d3e1b94559234110e781839fa0a0561b38ad532a12319c86c6307e740a9732a3a00cac870cd8e0faf0681be8b6db965bb909df3c85806eeabced5a09523647e6e0fef419a6adf116daf7ac34be9dd1da686e7f1ca2e243b76320ce57df9ff1560cc3e3f470ff00c78255b842b35bc6c4af9b6e323d3e95467b6365f8dbcf062beb68c119595d8aaff6e282422e9899b4f6bb5d46cda2562a76316c1078f4a0859e1b9b762c0bf94f0e84feb4125a57505c58ea70dd5d0174a986d92b1c13f6f5a0de7a5be366877260b5d42dee2d2423124a487507ebdf15289dd3fac7a7bab6feded74d61733473acdb5a162142ff00313d81ed505fa58fc6d809380c1b9f5c502e0e05040ea367a85dea454de2ff00a610375b04c16c7a16ef8340b5f6930dce9375636acf6a278f04c5dd4f1dbf4a084e91d06f3a52dee62bbd4a2b882494ced3c8a448063b63b638fde803ab7ae749b2b3096d792c93c8c109b55dcd18ce3710473ffdd043dc758dc5869044565aa5dda4c3c2b7bc78c1f14e3963db03e7c0ab066bf1327d41ba76ca6bc48ecad24c456f6b0c87cf8e4bbfa138c0fa9aa3297c83dd4e28395811cf2680a5b93c7ed413cd1ff0f3c797b8031406645236b0508406f30e68ba49c051b97d0e0e7d28ad57e19f575c5be8f269515dac772877c11bc464dea7ba8c739ce78f9d3193bb8ebfea2bcbd6b5b6b8b58bb7f13c2f0ce31cf0deb4c0f2dbad6d743d2ee99efae752d6c02a86e0054524f6383c7ff94c0b6af274c75149a46a5a82c46f1e1479fc3190bd8156fbe7f4a960bf74e9d253f1167a3ac09e0856610e3041ec7f6c540f67b892cee7f8d18368232ef2af2508c7047cf340ead5bf130accc9b1186541e723d09ffc5033bbb1b82d74d6b37f1244daa1b38073df3f4a08eeb1d3b50d4fa6a5b4d32f12cef1902ee73e523d476fde8306eb0d3fabfa4ba92c278af67bb7281606472f90bdd58558253a6afb40ea1d62283a8b461a66a6f931cf6a7c2466f7cfb939e7b5515fbed3747b5eb8f06eb78d35080a2ec9719c76f98049a0b4ebdd37d1bad869acbf0b03c5c16b29444adf50ded41995f68564a263a66b31cd02be152505493f51c1a088bab69ad1bc179e320f07c37c8a0692b46c4995f0381db39a0b2fc34e971d57d4705bc8db6c50ef9dd97b81fcbf7381528f5ae97a1d8e996d1db69b0c7648855b10a81b80f43c739c54134147b9a036063279fb5046e957726a0f2cfe04915b06db1788305ffeac7a0a00d72f8d9c491c06337533050ac7185cf2df6a06da2da4293488f34973328c34aea428c9ec3eded40ee7d2ad249448f6b133820ee2833df3fde819ea96897461b05b87815f2ee919e5d47704fa039ab079b3e326b70eafd4ef6d6650d8e9ebf868b69c8247723efebf2aa280eb9193ebedc5002a124e015340018fb8fde82cf32b1603d0678cd02406dce3008e47ce81b499c331383c9c9f5a2e9c69377369f7d6f796a4acf148acb83fb511e91b3b3d0bab745b7d45acedd8e3732b71b1fd73f7a5a19eafd09a56a0a96b1c705b49c48510761ce4fcfbd4d0d752826b2b583476fc3daacb295b79d768de8a32b1e71f989e49f6a7d14dd1af5ba275a45b8b093c054492ea769092373765c1da4679fbd306e36ba9595fe9f0dcdbcc92c33e1579cf27d0d409ea178f68521b6b76926ee8a7853f7ff140bc768d78f6f73748d1cd103b543f0091cf6efc502f7319dac194371d8b6326829f0c501d7ae6fa568d5d4942c806d4db81839f53c8cd59456fae6e628749b5bab8b1865b08e4726588ec11e7f2e49071c93da9a31dd4341d675e9a5bad374f9858162d0b4ac70e18f0573df35a0c759f87bd53a404f174f965dfff00f479b1ef570576e34bd4b4cc0bdb3b9b7258a00e846e3f2a94376475cee4914af7ca9150685f09ba61efb52fc7dd69bf8eb7c158d1d0b47bb38f37efde968d6eeb4eb5e91d6ad25b660aee59974db6881690918e31ce39279e062a5a34bb57b88adedd1e379679065d80036679e6a07e8391bce7e940c659ef5afe1286de3b16f2b8903094b7b2fa7ce81eb380c4260ed193f2a0cd6fa5d4a4ea0fc7bdadcce923158a3039db83c038e3ef41a0e96b2ad8a35e009291b8a939d9f227e43bd590436bbd6fa269202c974b7123602c76e779624e00e29833bf897d493e896525dbcb2a6b5a9c3e1456b91b6d60cf989c7f31f7a60c02490961ebcf3eb541308e39e067b507007b96007a67fb50178f97eb4165ce18165c2927b773fad023202d9c8dbb7818ff003408300b87f2f1c107d0d0c15a4f2e339c90467f6a18bdfc2cea8ff4bd561b4b9ba686d6e64552c4f954e7d7e46a60f4688d240af1b2bc6cbf5047ca960617ba658de1b792f2d94a5ab33461b18524633fa1a81b5c8b5168967369d23c0e0a24622dc981d81c76aba29df0bb48d660d52fceb88d069f04aeb69130037127f37b9c0ed9a8350781240bbc06da72323b1f7a0eb8816e633192ebc8c9472a78fa50349b4c83c068e24f0ddbcc1c13b837be4d055b57e98b996d4db5b4a893dc1e6620b6ccf2c467efc504ce97a38d3f4d874bf09af6d46e2f25cb82724e791db15650a43f878b51fc34f3da8f132b6d6a98c80a39ff007e99aba249631b58b9047239ec3e55368aeeb7d2da6f52c0eb7f16e87f2c6e836ba90724ab7a67b55d115ac7c3e8aed2182def4c56a14096368959a423d77e3229a27b41e9d8343b01069c8a8dc9660aa3713df3c64d4a1c695d3d6b67a8cba94b9b8d4e61869e4e4a8c636a7f4afcaa09a485519caae19b966f7a0435196582c656b74df3e308beec7b50629375775b691ac5bdb6b16d6378779f019b00a31cf391c9c2f1daae0b35ef52f5374de88d77aa45a6cd25ddc0108694ee2188c28007603d6a0d16c92430a4b2ed3230dc401855cfa0a0a07c45d7b5db9d462e9ee960b14b2ee134ef8c850012147ec78ab0670b643a2efae753d72686e6e2da211db42176079c8e768f65e39f7aa332d6f58bbd635096f6fe6692695b24f603d801e82823cb900ee00e68006460051dfd680ed9f0c905b713d8d006d5f5419fa505a18f94e40501b1b81a04186d62402c87be3d6810b81290aea8467201231cd1749dbc437f9f1e201db3de8ba07dc0175c027f28a335b17c26f888d6b6d0e8fabf892a29c453b1e547f49f7a946d6424f08236491c833ee0835073294888894120700f0280813c40a6711bc8843e00fca7d3ef40e41dc081f9a811681c6f7565329185623b7e9de812b3bcf11ff0b74563bd50494cf120071b97e5fda80d7577046c9019d5669dbc340324eec67fb734103d5da96bf67a7cf0e916f6e2765f25ddc4c11107ab1c8c647cce2816d3ec7f0f6564cae6e67da375e6d52cc4af2e4fb13ed4145f899d47b3499f4bb6d46cda49b69b92921565c3648e3dd40c81cd5c0ae89f13ec246d3e379ed2d6da180b5d34849da1780b128e49271c9f4a60ba685d5fa36bc42d95c324ec7090cc9b1d87b81ed50588958977cacaaa3b9341c655f12348d1dcb8dc1946540f99a019e2134454eeda7bed3839cd052fe2136b536b5d3563a1ca53c49da4b9507198940ce7e5c9fbe281c6b7a974cf4ee4ea7242d76dc784a3c595b3e9b464e3f6ad0ac745ccbd4fadcbabea42da56959a382ce7460d6b1a93c01f97272093ebf6a82f1ad6af0e9da5cb3cecf6902216919f82aa3818c7a9f4c530649a9f5269ba7429d472239bc991a1b0d3c3152880f0f23039e7bf3de90635ab6a377aa5ebdcdecef2c9239e59f3827e5ed54302195fcc38cd01245395c1f5f4a05b606538e483c501b6939e3b5077860f3914165754c33e549000dbe87de813b820c27fa7baafb8a04a69c98e281e42618c795338033df1f3a06c03e4e029247007ad010093c35674da71f977640340081a190658e41c820f141b0fc33f8926c218b4ed609366a02249bb2d19ce3ea4528dbece68eead926b7916689c643a9e0d643387521fea2f693c2d6efc786ee46d9bfed3eff2a04669edf5295ff057a60bd865309246d3bbbedc1efef41d63a8dec9ab4fa7dd4510fc3c69234ca186e2d9c003b7a67bd034bad0a5bb96e25d575267889cc1b54446d9bd0a37bfbfbd02925945a72cba8dddc48b3f87b1e58f23c623f292bdb7fa7cf38a0a5750f54ebba56a9a67fc516b6d6fd3970ea9234677c8dc7f38f6e4640ce282d1ac4b16bfa72c1d2bad430cd1ba822061865f5007d3daac19cf547c189357d561bbd3eee683c62cd786e9b73337b8c7bd512bd39f06adedec2de0d5ae639da372e6485363107f97767b505cee755d03a5e58ac228659af123184b7b733322e38c91dbf5a943ab3d52e64b49ee755d2e64950e238e35f10c884e17cbe87dc540e6d7509a4f110e9f7566a471712850abf6ce463e6280bacea36fd33a4497f773cf32c698dcc4beee33938edc7ad05534aea683ae61d64c4d2a69b6b88d16d5ca5c303f3e386cf61db140e27b5e99e96b64bdd562b6b30aa36c6c37cac7dc9eec6b42c1a66a962fa70beb6b516d0cbe76322f86c78f6c66831bf8b5d5d2dfa35a5dce60b1933b6ce3c788769f2b331ec1b8fd2831b79649984b239773c1dc68129725c1c640e73400ec781d8fb1a03c4a85d0c8582640257bd01e51fc42236263c9c67be280429c6037eb405dbf5fd682c2a0bb976cf07d3fc5009279ef8ec4e68193a9902b28e7dc71fb501d95b098e0f6dd9e0d0049131019b047b8390281bb292484e47c8500c4f242c3076bf704704739a0be7c3febfbae9a5daf23cd017c7e19fb107bb67d0f6fd6837cd2757d1fab34f4f05e37dde630b1c3a91edf4f7159103d6eb7da65fdbdf59dadb5e2460ac876ed9e1c8c060f9efe9c8a0a75cfc42d5742d2ee5a7e9dbb494b6d6b9bc930cce4f940e3cd81ed4160e98f88315e689fff0022b57664199cc5196f0c7a164ef8f98cd0589baffa68590985eb15c0db1985839f6c2919340b69d03f5285bdd6f4bf021424db4329cb153fccc3d09c76a090d3340d2f479a7bab3b38e2924e5e451cfd280d7dafe936f6c5e4bd89813b02a36589ce318a0358dc35cc4e17f9bf234cdbb78fa0c607a7340e6cec20b1596610c6934b8323226379edda81da8dcb9ec40a042f50b5bb21645473b58b11dbd7bfca8304f8add5d67a9ea8ba5d8ea72c1a4d8a952f10f2c920e368cf71e99fad5833dd0754d6ed66bdb2e9a91a5babb2a310465a57c1ddc1038e7bd5171d3748b8d46ee1ff005298dc6a764c27d4eeaee7fe1c01795881c9e7804fe940dbe287c4b6d75a1b1d1c986d62277c91bf131f4c0f6fad0663737135d3b497124924871f98e7803007d2811dc5b83903dc0a0333f03be7de8122df2c9a05a11e5f51f7a05ce7071804fca8033e5da0734020b0183bb23e5416269577ed0e5323078ceeefdff6a03dbcd62914c2f629a47c622689800879e4fbd046f9d8a2a03e31385c0e73da8b83ca590947dcaead8208e73da8849b3e19ce704f7c5015586d006431f5cf61f3a04ee586ff002481c8fe6191408f0011eb8e30682774dea9bbb5784492ca6385832e1ca95e3d2834be9df8c312e2db5eb4375080337000f1303d18763591a469baef4d755989ec6f6dae5a23e20b599406dd8e080ddbed41272f4dd8caf1c86d163910f9595882a3d718a035edd695d3b6a926b57d0ac65b10b4e06eedd863bf141077fd7af2782bd3fa26a1a8891d57c630948c0279393dcd04cf5875258f4de9f0cb7b7b6d66d2b81ba752d85f5214724fed41036bd79d2fe319d7a8f4b9c81e58de2f04827b9ce09a07a3acecf54b790685ace8697606009e52c377b7f2e682b097d7d36acf0f55df5edbdc0977412468cb6ce3be10af3c63b9c8a0b0751f505be9690dd5d752436f62a3fe4c6448f3b7b0c64e38f615734651f107e3045ac42b67a7693018633b965bc1bc838ee173807bf7cd33065baaeb1a95f2c11dfcd2bc51fe48880aa3e8a062a8b059f595df4ae9a74de9e9ec499d43c97b1427c6e47e525bb63e4282ad3ea3712893c599dbc4259c1627713c927de81043950df97db1406da8411c92063be280230839627078e79a0390a71b5bb5003a8c1232338e4507025573e9fbd02a0e41dc0e680c3691cf714053bb34160895dc16f291d98d02322aa39f3e14707ffaa06f202a5bb0c7201f4a343aca51090497efdfbfce89840c8db8e46573923ff14410b00490d9f5c1a0425dd8ce4673e873cd0265e4dbe7041ed814009b8cbb8e5863bd07163b7716e0607b6698060b96b7b9478dc8643918247ee39a60b7e97f133a8b4e0c63d4ee597380923970a3ef4c0e13e25dfcfab457ba95bdbddb212016501867b9cfbfda982f907c74b282da34874a9048aa479c83838edc62982b7ac7c42d235cd67f15ac5b40c366418a2cb0c1c81e6f5e31db14c160d035de8cd4a3f18ea96562cc37359dfe9cac887fef039fd6b39446f56ea5d13a9dca4579a922496b1975b8d22dfc3566cf9557230703be715ac1431d4d2275325d7fae6b4f6f182a93ef1e32a9f41938f6a60afeb1a95c5fea53dccf772cf2c8c489240031f627e7565c0d67bbf160487c1801073bc0c31f91f953420f2bc8c7c52cc540032738a809905c0f4fa501940208e73df34028e703938a0577ae013f4a001300db4f03b71407461ce0502dca8c9c7dcf6a003fafcbdcd0070bc1e0fd734070db467b8a04cb9c9e68274b93bcb1daa40200ed4099765249ec476cf340849b8b264823bf34689ee009cb671df1409bc8e8b8e770e3ec68984d9c953cf97be2860b248caaebc107dc67f7a184c31232db88fd451031ce50e76039f5c8045026efb8f93279e0fd680b239504f0483d88ef409ee25bb90c79c0e050151c6e21b39ce783eb40adbcc2cefa17bdb61322387781c950e3dbdf9c8a066f28790b22e013db3dbef54726081e63c6460d34191b1bb0720f634060e7600412c781502409c8e3d7b500ed71dbef8ed40243f181c0a02e5d4e0fad006f644e4819e3b501f7e3049e7b501bc43b4e391da80558003392d40a23305e320d02e64cf998e1bf5a032b0c927b8e68049c8c8e71c6280377043118f4e680bbff00de0504ddbb3128371c1c64668024e59f3cd02521254e4fad1a2107e48fe6a6809ddb9e78a029e1463d05027ffc744a6c3857c7b1a205ff00e637fbf4a02b12b1794e39f4a02024e7249ed409924720906800005173fd7404989698ee39e4f7a04cf723d07a501fff0097ed406ffe36a018ff00281e99a037f4d0731f3bfd28007e53400ff99a810248c0cf140bc60123233cff008a0557f9beb4056eff007a07109243e79a03778b27bfbd02b128c27039a054001b818a06609de793da815006070283ffd9}\par} -{\pard \ql \f0 \sa180 \li0 \fi0 Here is a movie {\pict\jpegblip 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} icon.\par} +{\pard \ql \f0 \sa180 \li0 \fi0 {\pict\jpegblip\picw250\pich250\picwgoal3000\pichgoal3000 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}\par} +{\pard \ql \f0 \sa180 \li0 \fi0 Here is a movie {\pict\jpegblip\picw20\pich22\picwgoal400\pichgoal440 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} icon.\par} {\pard \qc \f0 \sa180 \li0 \fi0 \emdash\emdash\emdash\emdash\emdash\par} {\pard \ql \f0 \sa180 \li0 \fi0 \b \fs36 Footnotes\par} {\pard \ql \f0 \sa180 \li0 \fi0 Here is a footnote reference,{\super\chftn}{\*\footnote\chftn\~\plain\pard {\pard \ql \f0 \sa180 \li0 \fi0 Here is the footnote. It can go anywhere after the footnote reference. It need not be placed at the end of the document.\par} diff --git a/tests/writer.textile b/tests/writer.textile index 5042f79cb..7de677741 100644 --- a/tests/writer.textile +++ b/tests/writer.textile @@ -367,6 +367,7 @@ And nested without indentation: foo + </div> @@ -393,15 +394,14 @@ And this is *strong* </td> </tr> </table> - <script type="text/javascript">document.write('This *should not* be interpreted as markdown');</script> - Here's a simple block: <div> foo + </div> This should be a code block, though: @@ -437,18 +437,15 @@ foo This should just be an HTML comment: <!-- Comment --> - Multiline: <!-- Blah Blah --> - <!-- This is another comment. --> - Code block: bc. <!-- Comment --> @@ -456,8 +453,7 @@ bc. <!-- Comment --> Just plain comment, with trailing spaces on the line: -<!-- foo --> - +<!-- foo --> Code: bc. <hr /> @@ -466,23 +462,14 @@ bc. <hr /> Hr's: <hr> - <hr /> - <hr /> - -<hr> - -<hr /> - -<hr /> - +<hr> +<hr /> +<hr /> <hr class="foo" id="bar" /> - <hr class="foo" id="bar" /> - <hr class="foo" id="bar"> - <hr /> h1(#inline-markup). Inline Markup diff --git a/trypandoc/Makefile b/trypandoc/Makefile new file mode 100644 index 000000000..29942ac00 --- /dev/null +++ b/trypandoc/Makefile @@ -0,0 +1,14 @@ +CGIBIN=/home/website/cgi-bin +TRYPANDOC=/home/website/html/pandoc/try/ +CGI=${CGIBIN}/trypandoc +BIN=../dist/build/trypandoc/trypandoc + +install: ${CGI} ${TRYPANDOC}/index.html + +${TRYPANDOC}/%: % + cp $< $@ && chown website:www-data $@ && chmod a+r $@ + +${CGI}: ${BIN} + cp $< $@ && chown website:www-data $@ && chmod a+rx $@ + +.PHONY: install diff --git a/trypandoc/index.html b/trypandoc/index.html new file mode 100644 index 000000000..2c9c55ef2 --- /dev/null +++ b/trypandoc/index.html @@ -0,0 +1,137 @@ +<!doctype html> +<html lang="en"> +<head> + <meta charset="utf-8"> + <title>Try pandoc!</title> + <script src="//code.jquery.com/jquery-1.11.0.min.js"></script> + <script src="//maxcdn.bootstrapcdn.com/bootstrap/3.1.1/js/bootstrap.min.js"></script> + <link href="//maxcdn.bootstrapcdn.com/bootstrap/3.1.1/css/bootstrap.min.css" rel="stylesheet"> + <script type="text/javascript"> +(function($) { // http://stackoverflow.com/questions/901115/how-can-i-get-query-string-values + $.QueryString = (function(a) { + if (a == "") return {}; + var b = {}; + for (var i = 0; i < a.length; ++i) + { + var p=a[i].split('='); + if (p.length != 2) continue; + b[p[0]] = decodeURIComponent(p[1].replace(/\+/g, " ")); + } + return b; + })(window.location.search.substr(1).split('&')) +})(jQuery); + +function newpage() { + var input = $("#text").val(); + var from = $("#from").val(); + var to = $("#to").val(); + var href = window.location.href; + window.location.href = href.replace(/([?].*)?$/,"?" + $.param({text: input, from: from, to: to})); +}; + +function process(res) { + $("#results").text(res.result); + $("#version").text(res.version); +} + +$(document).ready(function() { + var text = $.QueryString["text"]; + $("#text").val(text); + var from = $.QueryString["from"] || "markdown"; + $("#from").val(from); + var to = $.QueryString["to"] || "html"; + $("#to").val(to); + if (text && text != "") { + $.getJSON("http://johnmacfarlane.net/cgi-bin/trypandoc", { from: from, to: to, text: text }, process); + }; + $("#convert").click(newpage); +}); + </script> + <style type="text/css"> + h1 { margin-bottom: 1em; } + body { margin: auto; } + textarea { height: auto; width: 100%; font-family: monospace; margin-top: 15px; } + div.alert { margin: 1em; } + h3 { margin-top: 0; margin-bottom: 0; padding: 0; font-size: 100%; } + pre#results { width: 100%; margin-top: 15px; } + footer { color: #555; text-align: center; margin: 1em; } + p.version { color: #555; } + button#convert { vertical-align: bottom; } + </style> +</head> +<body> +<div class="container"> + <div class="row"> + <h1>Try <a href="http://johnmacfarlane.net/pandoc/">pandoc</a>!</h1> + </div> + <div class="row"> + <div class="col-md-6"> + <label for="from"> + from + </label> + <select id="from"> + <option value="markdown" selected>Markdown</option> + <option value="markdown_strict">Markdown/strict</option> + <option value="markdown_phpextra">PHP Markdown Extra</option> + <option value="markdown_github">Github Markdown</option> + <option value="markdown_mmd">MultiMarkdown</option> + <option value="rst">reStructuredText</option> + <option value="textile">Textile</option> + <option value="latex">LaTeX</option> + <option value="html">HTML</option> + <option value="docbook">DocBook</option> + <option value="opml">OPML</option> + <option value="org">Emacs Org Mode</option> + <option value="t2t">Txt2Tags</option> + <option value="mediawiki">MediaWiki</option> + <option value="haddock">Haddock markup</option> + </select> + <br/> + <textarea id="text" maxlength="3000" rows="15"></textarea> + </div> + <div class="col-md-6"> + <label for="to"> + to + </label> + <select id="to"> + <option value="html" selected>HTML</option> + <option value="html5">HTML 5</option> + <option value="markdown">Markdown</option> + <option value="markdown_strict">Markdown/strict</option> + <option value="markdown_phpextra">PHP Markdown Extra</option> + <option value="markdown_github">Github Markdown</option> + <option value="markdown_mmd">MultiMarkdown</option> + <option value="rst">reStructuredText</option> + <option value="asciidoc">AsciiDoc</option> + <option value="textile">Textile</option> + <option value="mediawiki">MediaWiki</option> + <option value="dokuwiki">DokuWiki</option> + <option value="org">Emacs Org Mode</option> + <option value="latex">LaTeX</option> + <option value="beamer">LaTeX Beamer</option> + <option value="context">ConTeXt</option> + <option value="man">Groff man</option> + <option value="texinfo">Texinfo</option> + <option value="docbook">DocBook</option> + <option value="opml">OPML</option> + <option value="icml">ICML</option> + <option value="opendocument">OpenDocument</option> + <option value="rtf">RTF</option> + <option value="dzslides">DZSlides</option> + <option value="slidy">Slidy</option> + <option value="S5">S5</option> + <option value="slideous">Slideous</option> + </select> + + <button class="btn btn-primary btn-xs" id="convert">Convert</button> + <br/> + <pre id="results"></pre> + </div> + </div> +</div> +<footer> + <p class="version">pandoc <span id="version"></span></p> + <p>© 2013–2014 <a href="http://johnmacfarlane.net">John MacFarlane</a></p> +</footer> +</body> +</html> diff --git a/trypandoc/trypandoc.hs b/trypandoc/trypandoc.hs new file mode 100644 index 000000000..c530f45f2 --- /dev/null +++ b/trypandoc/trypandoc.hs @@ -0,0 +1,100 @@ +{-# LANGUAGE OverloadedStrings #-} +module Main where +import Network.Wai.Handler.CGI +import Network.Wai +import Control.Applicative ((<$>)) +import Data.Maybe (mapMaybe, fromMaybe) +import Network.HTTP.Types.Status (status200) +import Network.HTTP.Types.Header (hContentType) +import Network.HTTP.Types.URI (queryToQueryText) +import Text.Pandoc +import Text.Pandoc.Shared (tabFilter) +import Text.Highlighting.Kate (pygments) +import Data.Aeson +import qualified Data.Text as T +import Data.Text (Text) + +main :: IO () +main = run app + +app :: Application +app req respond = do + let query = queryToQueryText $ queryString req + let getParam x = maybe (error $ T.unpack x ++ " paramater not set") + return $ lookup x query + text <- getParam "text" >>= checkLength . fromMaybe T.empty + fromFormat <- fromMaybe "" <$> getParam "from" + toFormat <- fromMaybe "" <$> getParam "to" + reader <- maybe (error $ "could not find reader for " ++ T.unpack fromFormat) return + $ lookup fromFormat fromFormats + let writer = maybe (error $ "could not find writer for " ++ T.unpack toFormat) id + $ lookup toFormat toFormats + let result = T.pack $ writer $ reader $ tabFilter 4 $ T.unpack text + let output = encode $ object [ T.pack "result" .= result + , T.pack "name" .= + if fromFormat == "markdown_strict" + then T.pack "pandoc (strict)" + else T.pack "pandoc" + , T.pack "version" .= pandocVersion] + respond $ responseLBS status200 [(hContentType,"text/json; charset=UTF-8")] output + +checkLength :: Text -> IO Text +checkLength t = + if T.length t > 10000 + then error "exceeds length limit of 10,000 characters" + else return t + +writerOpts :: WriterOptions +writerOpts = def { writerReferenceLinks = True, + writerEmailObfuscation = NoObfuscation, + writerHTMLMathMethod = MathJax "http://cdn.mathjax.org/mathjax/latest/MathJax.js?config=TeX-AMS-MML_HTMLorMML", + writerHighlight = True, + writerHighlightStyle = pygments } + +readerOpts :: ReaderOptions +readerOpts = def { readerParseRaw = True, + readerSmart = True } + +fromFormats :: [(Text, String -> Pandoc)] +fromFormats = [ + ("native" , readNative) + ,("json" , Text.Pandoc.readJSON readerOpts) + ,("markdown" , readMarkdown readerOpts) + ,("markdown_strict" , readMarkdown readerOpts{ + readerExtensions = strictExtensions, + readerSmart = False }) + ,("markdown_phpextra" , readMarkdown readerOpts{ + readerExtensions = phpMarkdownExtraExtensions }) + ,("markdown_github" , readMarkdown readerOpts{ + readerExtensions = githubMarkdownExtensions }) + ,("markdown_mmd", readMarkdown readerOpts{ + readerExtensions = multimarkdownExtensions }) + ,("rst" , readRST readerOpts) + ,("mediawiki" , readMediaWiki readerOpts) + ,("docbook" , readDocBook readerOpts) + ,("opml" , readOPML readerOpts) + ,("t2t" , readTxt2TagsNoMacros readerOpts) + ,("org" , readOrg readerOpts) + ,("textile" , readTextile readerOpts) -- TODO : textile+lhs + ,("html" , readHtml readerOpts) + ,("latex" , readLaTeX readerOpts) + ,("haddock" , readHaddock readerOpts) + ] + +toFormats :: [(Text, Pandoc -> String)] +toFormats = mapMaybe (\(x,y) -> + case y of + PureStringWriter w -> Just (T.pack x, w writerOpts{ + writerExtensions = + case x of + "markdown_strict" -> strictExtensions + "markdown_phpextra" -> phpMarkdownExtraExtensions + "markdown_mmd" -> multimarkdownExtensions + "markdown_github" -> githubMarkdownExtensions + _ -> pandocExtensions + }) + _ -> + case x of + "rtf" -> Just (T.pack x, writeRTF writerOpts) + _ -> Nothing) writers + diff --git a/windows/make-windows-installer.bat b/windows/make-windows-installer.bat index d27859057..d4816fa69 100644 --- a/windows/make-windows-installer.bat +++ b/windows/make-windows-installer.bat @@ -1,21 +1,20 @@ @echo off
cd ..
cabal update
-cabal-dev clean
-cabal install hsb2hs cabal-dev
+cabal sandbox init
+cabal clean
+cabal install hsb2hs
if %errorlevel% neq 0 exit /b %errorlevel%
-cabal-dev install -v1 --force --reinstall --flags="embed_data_files"
+cabal install -v1 --force --reinstall --flags="embed_data_files" . pandoc-citeproc
if %errorlevel% neq 0 exit /b %errorlevel%
-cabal-dev install -v1 --reinstall --flags="embed_data_files" pandoc-citeproc
+strip .\.cabal-sandbox\bin\pandoc.exe
+strip .\.cabal-sandbox\bin\pandoc-citeproc.exe
+.\.cabal-sandbox\bin\pandoc.exe -s --template data\templates\default.html -S README -o README.html
if %errorlevel% neq 0 exit /b %errorlevel%
-strip cabal-dev\bin\pandoc.exe
-strip cabal-dev\bin\pandoc-citeproc.exe
-cabal-dev\bin\pandoc.exe -s --template data\templates\default.html -S README -o README.html
-if %errorlevel% neq 0 exit /b %errorlevel%
-cabal-dev\bin\pandoc.exe -s --template data\templates\default.rtf COPYING -t rtf -S -o COPYING.rtf
+.\.cabal-sandbox\bin\pandoc.exe -s --template data\templates\default.rtf COPYING -t rtf -S -o COPYING.rtf
if %errorlevel% neq 0 exit /b %errorlevel%
copy COPYRIGHT COPYRIGHT.txt
-for /f "tokens=1-2 delims= " %%a in ('cabal-dev\bin\pandoc --version') do (
+for /f "tokens=1-2 delims= " %%a in ('.\.cabal-sandbox\bin\pandoc --version') do (
@set VERSION=%%b
goto :next
)
@@ -29,7 +28,7 @@ cd windows echo Creating msi...
candle -dVERSION=%VERSION% pandoc.wxs
if %errorlevel% neq 0 exit /b %errorlevel%
-light -sw1076 -ext WixUIExtension -out pandoc-%VERSION%.msi pandoc.wixobj
+light -sw1076 -ext WixUIExtension -out pandoc-%VERSION%-windows.msi pandoc.wixobj
if %errorlevel% neq 0 exit /b %errorlevel%
echo Starting kSign: sign, then quit kSign to complete the build...
kSign
diff --git a/windows/pandoc.wxs b/windows/pandoc.wxs index 7a20effe5..75c316772 100644 --- a/windows/pandoc.wxs +++ b/windows/pandoc.wxs @@ -44,7 +44,7 @@ Name="Version" Type="string" Value="[ProductVersion]" KeyPath="yes"/>
<RemoveFolder Id="APPLICATIONFOLDER" On="uninstall"/>
<File Id="pandocEXE" Name="pandoc.exe"
- Source="..\cabal-dev\bin\pandoc.exe" />
+ Source="..\.cabal-sandbox\bin\pandoc.exe" />
<File Id="pandocCOPYRIGHT" Name="COPYRIGHT.txt"
Source="..\COPYRIGHT.txt" />
<File Id="pandocCOPYING" Name="COPYING.rtf"
@@ -56,7 +56,7 @@ <RegistryValue Root="HKMU" Key="Software\John MacFarlane\Pandoc"
Name="Version" Type="string" Value="[ProductVersion]" KeyPath="yes"/>
<File Id="pandoc_citeprocEXE" Name="pandoc-citeproc.exe"
- Source="..\cabal-dev\bin\pandoc-citeproc.exe" />
+ Source="..\.cabal-sandbox\bin\pandoc-citeproc.exe" />
</Component>
<Component Id="UpdatePathUser"
|
