diff options
105 files changed, 2275 insertions, 4347 deletions
diff --git a/Interact.hs b/Interact.hs index 80b5a34f5..4d24904c5 100644 --- a/Interact.hs +++ b/Interact.hs @@ -9,6 +9,10 @@ -- You must have first done a 'cabal configure' or 'cabal install' +-- Note: Interact.hs doesn't work with Cabal >= 1.18. I recommend +-- using cabal sandboxes and the new 'cabal repl' command if you are +-- using a recent version. + import System.Process import Distribution.Simple.LocalBuildInfo import Distribution.Package @@ -13,14 +13,15 @@ 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], [Haddock markup], [OPML], [Emacs Org-mode] +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. Pandoc's enhanced version of markdown includes syntax for footnotes, tables, flexible ordered lists, definition lists, fenced code blocks, @@ -108,7 +109,7 @@ to PDF: Production of a PDF requires that a LaTeX engine be installed (see `--latex-engine`, below), and assumes that the following LaTeX packages are available: `amssymb`, `amsmath`, `ifxetex`, `ifluatex`, `listings` (if the -`--listings` option is used), `fancyvrb`, `longtable`, `url`, +`--listings` option is used), `fancyvrb`, `longtable`, `booktabs`, `url`, `graphicx`, `hyperref`, `ulem`, `babel` (if the `lang` variable is set), `fontspec` (if `xelatex` or `lualatex` is used as the LaTeX engine), `xltxtra` and `xunicode` (if `xelatex` is used). @@ -143,14 +144,14 @@ 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), `opml` (OPML), `org` (Emacs Org-mode), + `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` 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 @@ -434,8 +435,8 @@ Options affecting specific writers `--chapters` : Treat top-level headers as chapters in LaTeX, ConTeXt, and DocBook output. When the LaTeX template uses the report, book, or - memoir class, this option is implied. If `--beamer` is used, - top-level headers will become `\part{..}`. + memoir class, this option is implied. If `beamer` is the output + format, top-level headers will become `\part{..}`. `-N`, `--number-sections` : Number section headings in LaTeX, ConTeXt, HTML, or EPUB output. @@ -801,6 +802,8 @@ as `title`, `author`, and `date`) as well as the following: : causes links to be printed as footnotes 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` @@ -894,6 +897,9 @@ If you need a hard line break, put two or more spaces at the end of a line. **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 +to create a hard line break, since trailing spaces in the cells +are ignored. Headers ------- @@ -1277,7 +1283,7 @@ one tab: + pears + peaches * vegetables - + brocolli + + broccoli + chard As noted above, markdown allows you to write list items "lazily," instead of @@ -1843,6 +1849,18 @@ equivalent of the markdown in the `abstract` field: <p>This is the abstract.</p> <p>It consists of two paragraphs.</p> +Note: The `author` variable in the default templates expects a simple list or +string. To use the structured authors in the example, you would need a +custom template. For example: + + $for(author)$ + $if(author.name)$ + $author.name$$if(author.affiliation)$ ($author.affiliation$)$endif$ + $else$ + $author$ + $endif$ + $endfor$ + Backslash escapes ----------------- @@ -2091,7 +2109,7 @@ Raw HTML Markdown allows you to insert raw HTML (or DocBook) anywhere in a document (except verbatim contexts, where `<`, `>`, and `&` are interpreted -literally). (Techncially this is not an extension, since standard +literally). (Technically this is not an extension, since standard markdown allows it, but it has been made an extension so that it can be disabled if desired.) @@ -2456,6 +2474,21 @@ document with an appropriate header: The bibliography will be inserted after this header. +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 --------------------- @@ -2504,10 +2537,9 @@ the document, for example: Comment: This is a sample mmd title block, with a field spanning multiple lines. -See the MultiMarkdown documentation for details. Note that only title, -author, and date are recognized; other fields are simply ignored by -pandoc. If `pandoc_title_block` or `yaml_metadata_block` is enabled, -it will take precedence over `mmd_title_block`. +See the MultiMarkdown documentation for details. If `pandoc_title_block` or +`yaml_metadata_block` is enabled, it will take precedence over +`mmd_title_block`. [MultiMarkdown]: http://fletcherpenney.net/multimarkdown/ @@ -2565,6 +2597,20 @@ variants are supported: `markdown_strict` (Markdown.pl) : `raw_html` +Extensions with formats other than markdown +------------------------------------------- + +Some of the extensions discussed above can be used with formats +other than markdown: + +* `auto_identifiers` can be used with `latex`, `rst`, `mediawiki`, + and `textile` input (and is used by default). + +* `tex_math_dollars`, `tex_math_single_backslash`, and + `tex_math_double_backslash` can be used with `html` input. + (This is handy for reading web pages formatted using MathJax, + for example.) + Producing slide shows with Pandoc ================================= @@ -2822,12 +2868,14 @@ The following fields are recognized: ~ A string value. `cover-image` ~ A string value (path to cover image). +`stylesheet` + ~ A string value (path to CSS stylesheet). Literate Haskell support ======================== If you append `+lhs` (or `+literate_haskell`) to an appropriate input or output -format (`markdown`, `mardkown_strict`, `rst`, or `latex` for input or output; +format (`markdown`, `markdown_strict`, `rst`, or `latex` for input or output; `beamer`, `html` or `html5` for output only), pandoc will treat the document as literate Haskell source. This means that diff --git a/RELEASE-CHECKLIST b/RELEASE-CHECKLIST index d3b1a7fc9..af0102622 100644 --- a/RELEASE-CHECKLIST +++ b/RELEASE-CHECKLIST @@ -16,9 +16,7 @@ _ Upload to Google Code (googlecode-upload.sh) _ Go to Google code and deprecate the old versions -- Add release on github (github-upload.sh + manual) - -_ Add release on sourceforge +- Add release on github (and upload files) _ Upload to HackageDB @@ -1,3 +1,143 @@ +pandoc (1.12.3.3) + + * To changes to source; recompiled tarball with latest alex and + happy, so they will work with GHC 7.8. + +pandoc (1.12.3.2) + + * Bumped version bounds for blaze-html, blaze-markup. + + * ImageSize: Avoid use of lookAhead, which is not in binary >= 0.6 + (#1124). + + * Fixed mediawiki ordered list parsing (#1122). + + * HTML reader: Fixed bug reading inline math with `$$` (#225). + + * Added support for LaTeX style literate Haskell code blocks in rST + (Merijn Verstraaten). + +pandoc (1.12.3.1) + + * Relaxed version constraint on binary, allowing the use of binary 0.5. + +pandoc (1.12.3) + + * The `--bibliography` option now sets the `biblio-files` variable. + So, if you're using `--natbib` or `--biblatex`, you can just use + `--bibliography=foo.bib` instead of `-V bibliofiles=foo`. + + * Don't run pandoc-citeproc filter if `--bibliography` is + used together with `--natbib` or `--biblatex` (Florian Eitel). + + * Template changes: + + + Updated beamer template to include booktabs. + + Added `abstract` variable to LaTeX template. + + Put `header-includes` after `title` in LaTeX template (#908). + + Allow use of `\includegraphics[size]` in beamer. + This just required porting a macro definition from the default + LaTeX template to the default beamer template. + + * `reference.docx`: Include `FootnoteText` style. + Otherwise Word ignores the style, even when specified in the `pPr`. + (#901) + + * `reference.odt`: Tidied `styles.xml`. + + * Relaxed version bounds for dependencies. + + * Added `withSocketsDo` around http conduit code in `openURL`, + so it works on Windows (#1080). + + * 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 + multiline table cells. + + Citation keys may now start with underscores, and may contain + underscores adjacent to internal punctuation. + + * LaTeX reader: + + + Add support for `Verb` macro (jrnold) (#1090). + + Support babel-style quoting: `` "`..."' ``. + + * Properly handle script blocks in strict mode. (That is, + `markdown-markdown_in_html_blocks`.) Previously a spurious + `<p>` tag was being added (#1093). + + * Docbook reader: Avoid failure if `tbody` contains no `tr` or `row` + elements. + + * LaTeX writer: + + + Factored out function for table cell creation. + + Better treatment of footnotes in tables. + Notes now appear in the regular sequence, rather than in the + table cell. (This was a regression in 1.10.) + + * HTML reader: Parse name/content pairs from meta tags as metadata. + Closes #1106. + + * Moved `fixDisplayMath` from Docx writer to `Writer.Shared`. + + * OpenDocument writer: Fixed `RawInline`, `RawBlock` so they don't escape. + + * ODT writer: Use mathml for proper rendering of formulas. + Note: LibreOffice's support for this seems a bit buggy. But + it should be better than what we had before. + + * RST writer: Ensure no blank line after def in definition list (#992). + + * Markdown writer: Don't use tilde code blocks with braced attributes in + `markdown_github` output. A consequence of this change is that the + backtick form will be preferred in general if both are enabled. That + is good, as it is much more widespread than the tilde form. (#1084) + + * Docx writer: Fixed problem with some modified reference docx files. + Include `word/_rels/settings.xml.rels` if it exists, as well as other + `rels` files besides the ones pandoc generates explicitly. + + * HTML writer: + + + With `--toc`, headers no longer link to themselves (#1081). + + Omit footnotes from TOC entries. Otherwise we get doubled + footnotes when headers have notes! + + * EPUB writer: + + + Avoid duplicate notes when headings contain notes. + This arose because the headings are copied into the metadata + "title" field, and the note gets rendered twice. We strip the + note now before putting the heading in "title". + + Strip out footnotes from toc entries. + + Fixed bug with `--epub-stylesheet`. Now the contents of + `writerEpubStylesheet` (set by `--epub-stylesheet`) + 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 + with `//`. + + * `Text.Pandoc.ImageSize`: Parse EXIF format JPEGs. Previously + we could only get size information for JFIF format, which led + 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 + continuation lines containing raw HTML (or even verbatim raw HTML). + pandoc (1.12.2) * Metadata may now be included in YAML blocks in a markdown document. @@ -40,6 +180,8 @@ pandoc (1.12.2) if the spine has `linear="no"`. Apparently this is best practice for other converters as well: <http://www.idpf.org/epub/20/spec/OPF_2.0.1_draft.htm#Section2.6>. + + Allow `stylesheet` in metadata. The value is a path to the stylesheet. + + Allow partial dates: `YYYY`, `YYYY-MM`. * Markdown writer: Fix rendering of tight sublists (#1050). Previously a spurious blank line was included after a tight sublist. @@ -87,6 +229,7 @@ pandoc (1.12.2) This fix puts braces around a term that contains an internal link, to avoid problems with square brackets. + Properly escape pdftitle, pdfauthor (#1059). + + Use booktabs package for tables (thanks to Jose Luis Duran). * Updated beamer template. Now references should work properly (in a slide) when `--biblatex` or `--natbib` is used. @@ -107,31 +250,40 @@ pandoc (1.12.2) + Use pandoc `Div` and `Span` for raw `<div>`, `<span>` when `--parse-raw`. + Recognize `svg` tags as block level content (thanks to MinRK). + + Parse LaTeX math if appropriate options are set. * Markdown reader: + Yaml block must start immediately after `---`. If there's a blank line after `---`, we interpreted it as a horizontal rule. + Correctly handle empty bullet list items. + + Stop parsing "list lines" when we hit a block tag. + This fixes exponential slowdown in certain input, e.g. + a series of lists followed by `</div>`. * 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. + * `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). + + Fixed bug in `openURL` with `data:` URIs. Previously the base-64 + encoded bytestring was returned. We now decode it so it's a proper + image! * 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. + * `Text.Pandoc.Parsing`: - * `Text.Pandoc.Shared`: Fixed bug in `openURL` with `data:` URIs. - Previously the base-64 encoded bytestring was returned. - We now decode it so it's a proper image! + + 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'` @@ -151,11 +303,15 @@ 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". * Don't look for slidy files in data files with `--self-contained`. + * Allow `https:` command line arguments to be downloaded. + * Fixed `make_osx_package.sh` so data files embedded in `pandoc-citeproc`. pandoc (1.12.1) @@ -3700,7 +3856,7 @@ pandoc (1.5.1.1) [ John MacFarlane ] - * Fixed uniqueIdent in Shared so that header identifiers work as + * Fixed uniqueIdent in Shared so that header identifiers work as advertized in the README and are are valid XHTML names. pandoc (1.5.1) diff --git a/data/reference.docx b/data/reference.docx Binary files differindex 42c14a906..a9c268b9f 100644 --- a/data/reference.docx +++ b/data/reference.docx diff --git a/data/reference.odt b/data/reference.odt Binary files differindex 08385dd4c..c01345612 100644 --- a/data/reference.odt +++ b/data/reference.odt diff --git a/data/sample.lua b/data/sample.lua index a7e9d6337..a0c3c29a2 100644 --- a/data/sample.lua +++ b/data/sample.lua @@ -181,6 +181,10 @@ function Span(s, attr) return "<span" .. attributes(attr) .. ">" .. s .. "</span>" end +function Cite(s) + return "<span class=\"cite\">" .. s .. "</span>" +end + function Plain(s) return s end diff --git a/data/templates b/data/templates -Subproject 713a8f63d5589ab9313869e47b03cf7f49e00e9 +Subproject 3a0ed995ca45648029a445302a16a92b8dfe6c8 diff --git a/github-upload.sh b/github-upload.sh index 2a5f6534d..875d51831 100644..100755 --- a/github-upload.sh +++ b/github-upload.sh @@ -1,4 +1,4 @@ -#!/usr/bin/bash +#!/bin/bash VERSION=$1 FULLNAME=pandoc-$VERSION @@ -7,12 +7,12 @@ read -s -p "Token (https://github.com/settings/applications): " TOKEN curl -H "Authorization: token $TOKEN" \ -H "Accept: application/vnd.github.manifold-preview" \ -H "Content-Type: application/x-apple-diskimage" \ - --data-binary @$FULLNAME.dmg \ - "https://uploads.github.com/repos/jgm/pandoc/releases/$FULLNAME/assets?name=$FULLNAME.dmg" + --data-binary @$FULLNAME.pkg.zip \ + "https://uploads.github.com/repos/jgm/pandoc/releases/$VERSION/assets?name=$FULLNAME.pkg.zip" curl -H "Authorization: token $TOKEN" \ -H "Accept: application/vnd.github.manifold-preview" \ -H "Content-Type: application/x-msi" \ --data-binary @$FULLNAME.msi \ - "https://uploads.github.com/repos/jgm/pandoc/releases/$FULLNAME/assets?name=$FULLNAME.msi" + "https://uploads.github.com/repos/jgm/pandoc/releases/$VERSION/assets?name=$FULLNAME.msi" diff --git a/googlecode-upload.sh b/googlecode-upload.sh index 19975ca91..40fba78e2 100755 --- a/googlecode-upload.sh +++ b/googlecode-upload.sh @@ -2,4 +2,4 @@ VERSION=$1 googlecode_upload.py -s "Source tarball" -p pandoc -u fiddlosopher --labels=Featured,Type-Source,OpSys-All dist/pandoc-$VERSION.tar.gz googlecode_upload.py -s "Windows installer" -p pandoc -u fiddlosopher --labels=Featured,Type-Installer,OpSys-Windows pandoc-$VERSION.msi -googlecode_upload.py -s "Mac OS X installer" -p pandoc -u fiddlosopher --labels=Featured,Type-Installer,OpSys-OSX pandoc-$VERSION.dmg +googlecode_upload.py -s "Mac OS X installer" -p pandoc -u fiddlosopher --labels=Featured,Type-Installer,OpSys-OSX pandoc-$VERSION.pkg.zip diff --git a/make_osx_package.sh b/make_osx_package.sh index a4eb404f0..6c943c84a 100755 --- a/make_osx_package.sh +++ b/make_osx_package.sh @@ -1,4 +1,4 @@ -#!/bin/sh -e +#!/bin/bash -e DIST=`pwd`/osx_package SANDBOX=`pwd`/.cabal-sandbox @@ -8,10 +8,13 @@ ROOT=$DIST/pandoc DEST=$ROOT/usr/local SCRIPTS=osx-resources BASE=pandoc-$VERSION -ME=jgm +ME=$(whoami) CODESIGNID="Developer ID Application: John Macfarlane" PACKAGEMAKER=/Applications/PackageMaker.app/Contents/MacOS/PackageMaker -EXES="pandoc pandoc-citeproc biblio2yaml" +EXES="pandoc pandoc-citeproc" + +read -s -p "sudo password: " PASSWORD +echo $PASSWORD | sudo -S echo "Password valid, continuing." echo Removing old files... rm -rf $DIST @@ -50,6 +53,8 @@ codesign --force --sign "$CODESIGNID" $DEST/bin/pandoc 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 $ROOT \ @@ -67,11 +72,13 @@ sudo codesign --force --sign "$CODESIGNID" $BASE.pkg # make sure it's valid... spctl --assess --type install $BASE.pkg -echo Creating disk image... +echo Creating zip... +zip -9 -r $BASE.pkg.zip $BASE.pkg -sudo hdiutil create "$BASE.dmg" \ - -format UDZO -ov \ - -volname "pandoc $VERSION" \ - -srcfolder $BASE.pkg -sudo hdiutil internet-enable "$BASE.dmg" +# echo Creating disk image... +# sudo hdiutil create "$BASE.dmg" \ +# -format UDZO -ov \ +# -volname "pandoc $VERSION" \ +# -srcfolder $BASE.pkg +# sudo hdiutil internet-enable "$BASE.dmg" diff --git a/pandoc.cabal b/pandoc.cabal index e279a2cc9..0570c1072 100644 --- a/pandoc.cabal +++ b/pandoc.cabal @@ -1,5 +1,5 @@ Name: pandoc -Version: 1.12.2 +Version: 1.12.3.3 Cabal-Version: >= 1.10 Build-Type: Custom License: GPL @@ -17,8 +17,8 @@ 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, + markup, OPML, Emacs Org-Mode, 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 @@ -202,46 +202,49 @@ Library syb >= 0.1 && < 0.5, containers >= 0.1 && < 0.6, unordered-containers >= 0.2 && < 0.3, - array >= 0.3 && < 0.5, + array >= 0.3 && < 0.6, parsec >= 3.1 && < 3.2, mtl >= 1.1 && < 2.2, network >= 2 && < 2.5, filepath >= 1.1 && < 1.4, - process >= 1 && < 1.2, + process >= 1 && < 1.3, directory >= 1 && < 1.3, bytestring >= 0.9 && < 0.11, - text >= 0.11 && < 0.12, - zip-archive >= 0.1.3.3 && < 0.2, + text >= 0.11 && < 1.2, + zip-archive >= 0.1.3.3 && < 0.3, old-locale >= 1 && < 1.1, time >= 1.2 && < 1.5, HTTP >= 4000.0.5 && < 4000.3, - texmath >= 0.6.5.2 && < 0.7, + texmath >= 0.6.6 && < 0.7, xml >= 1.3.12 && < 1.4, random >= 1 && < 1.1, extensible-exceptions >= 0.1 && < 0.2, pandoc-types >= 1.12.3 && < 1.13, - aeson >= 0.6 && < 0.7, + aeson >= 0.6 && < 0.8, tagsoup >= 0.12.5 && < 0.14, base64-bytestring >= 0.1 && < 1.1, zlib >= 0.5 && < 0.6, - highlighting-kate >= 0.5.5 && < 0.6, + highlighting-kate >= 0.5.6 && < 0.6, data-default >= 0.4 && < 0.6, - temporary >= 1.1 && < 1.2, - blaze-html >= 0.5 && < 0.7, - blaze-markup >= 0.5.1 && < 0.6, - attoparsec >= 0.10 && < 0.11, + 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, vector >= 0.10 && < 0.11, - hslua >= 0.3 && < 0.4 + hslua >= 0.3 && < 0.4, + binary >= 0.5 && < 0.8 Build-Tools: alex, happy if flag(http-conduit) - Build-Depends: http-conduit >= 1.9 && < 1.10, + Build-Depends: http-conduit >= 1.9 && < 2.1, http-types >= 0.8 && < 0.9 cpp-options: -DHTTP_CONDUIT 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 @@ -260,6 +263,7 @@ Library 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, @@ -317,12 +321,11 @@ Executable pandoc directory >= 1 && < 1.3, filepath >= 1.1 && < 1.4, network >= 2 && < 2.5, - text >= 0.11 && < 0.12, + text >= 0.11 && < 1.2, bytestring >= 0.9 && < 0.11, extensible-exceptions >= 0.1 && < 0.2, - highlighting-kate >= 0.5.5 && < 0.6, - aeson >= 0.6 && < 0.7, - text >= 0.11 && < 0.12, + highlighting-kate >= 0.5.6 && < 0.6, + aeson >= 0.6 && < 0.8, yaml >= 0.8.3 && < 0.9, containers >= 0.1 && < 0.6, HTTP >= 4000.0.5 && < 4000.3 @@ -360,11 +363,11 @@ Test-Suite test-pandoc pandoc, pandoc-types >= 1.12.3 && < 1.13, bytestring >= 0.9 && < 0.11, - text >= 0.11 && < 0.12, + text >= 0.11 && < 1.2, directory >= 1 && < 1.3, filepath >= 1.1 && < 1.4, - process >= 1 && < 1.2, - highlighting-kate >= 0.5.5 && < 0.6, + process >= 1 && < 1.3, + highlighting-kate >= 0.5.6 && < 0.6, Diff >= 0.2 && < 0.4, test-framework >= 0.3 && < 0.9, test-framework-hunit >= 0.2 && < 0.4, @@ -380,6 +383,7 @@ Test-Suite test-pandoc Tests.Walk Tests.Readers.LaTeX Tests.Readers.Markdown + Tests.Readers.Org Tests.Readers.RST Tests.Writers.Native Tests.Writers.ConTeXt @@ -35,7 +35,8 @@ import Text.Pandoc.Builder (setMeta) import Text.Pandoc.PDF (makePDF) import Text.Pandoc.Readers.LaTeX (handleIncludes) import Text.Pandoc.Shared ( tabFilter, readDataFileUTF8, readDataFile, - safeRead, headerShift, normalize, err, warn ) + safeRead, headerShift, normalize, err, warn, + openURL ) import Text.Pandoc.XML ( toEntities ) import Text.Pandoc.SelfContained ( makeSelfContained ) import Text.Pandoc.Process (pipeProcess) @@ -55,7 +56,6 @@ import Control.Exception.Extensible ( throwIO ) import qualified Text.Pandoc.UTF8 as UTF8 import Control.Monad (when, unless, liftM) import Data.Foldable (foldrM) -import Network.HTTP (simpleHTTP, mkRequest, getResponseBody, RequestMethod(..)) import Network.URI (parseURI, isURI, URI(..)) import qualified Data.ByteString.Lazy as B import qualified Data.ByteString as BS @@ -162,6 +162,7 @@ data Opt = Opt , optAscii :: Bool -- ^ Use ascii characters only in html , optTeXLigatures :: Bool -- ^ Use TeX ligatures for quotes/dashes , optDefaultImageExtension :: String -- ^ Default image extension + , optTrace :: Bool -- ^ Print debug information } -- | Defaults for command-line options. @@ -217,6 +218,7 @@ defaultOpts = Opt , optAscii = False , optTeXLigatures = True , optDefaultImageExtension = "" + , optTrace = False } -- | A list of functions, each transforming the options data structure @@ -656,7 +658,7 @@ options = (ReqArg (\arg opt -> do let b = takeBaseName arg - if (b == "pdflatex" || b == "lualatex" || b == "xelatex") + if b `elem` ["pdflatex", "lualatex", "xelatex"] then return opt { optLaTeXEngine = arg } else err 45 "latex-engine must be pdflatex, lualatex, or xelatex.") "PROGRAM") @@ -667,6 +669,9 @@ options = (\arg opt -> return opt{ optMetadata = addMetadata "bibliography" (readMetaValue arg) $ optMetadata opt + , optVariables = + ("biblio-files", dropExtension arg) : + optVariables opt }) "FILE") "" @@ -755,6 +760,11 @@ options = (\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 })) @@ -824,6 +834,7 @@ defaultReaderName fallback (x:xs) = ".latex" -> "latex" ".ltx" -> "latex" ".rst" -> "rst" + ".org" -> "org" ".lhs" -> "markdown+lhs" ".db" -> "docbook" ".opml" -> "opml" @@ -949,6 +960,7 @@ main = do , optAscii = ascii , optTeXLigatures = texLigatures , optDefaultImageExtension = defaultImageExtension + , optTrace = trace } = opts when dumpArgs $ @@ -958,7 +970,9 @@ main = do -- --bibliography implies -F pandoc-citeproc for backwards compatibility: let filters' = case M.lookup "bibliography" metadata of - Just _ | all (\f -> takeBaseName f /= "pandoc-citeproc") + Just _ | optCiteMethod opts /= Natbib && + optCiteMethod opts /= Biblatex && + all (\f -> takeBaseName f /= "pandoc-citeproc") filters -> "pandoc-citeproc" : filters _ -> filters let plugins = map externalFilter filters' @@ -1034,12 +1048,10 @@ main = do variables' <- case mathMethod of LaTeXMathML Nothing -> do - s <- readDataFileUTF8 datadir - ("LaTeXMathML.js") + s <- readDataFileUTF8 datadir "LaTeXMathML.js" return $ ("mathml-script", s) : variables MathML Nothing -> do - s <- readDataFileUTF8 datadir - ("MathMLinHTML.js") + s <- readDataFileUTF8 datadir "MathMLinHTML.js" return $ ("mathml-script", s) : variables _ -> return variables @@ -1071,6 +1083,7 @@ main = do , readerIndentedCodeClasses = codeBlockClasses , readerApplyMacros = not laTeXOutput , readerDefaultImageExtension = defaultImageExtension + , readerTrace = trace } let writerOptions = def { writerStandalone = standalone', @@ -1120,10 +1133,13 @@ main = do readSource "-" = UTF8.getContents readSource src = case parseURI src of Just u | uriScheme u `elem` ["http:","https:"] -> - readURI u + readURI src _ -> UTF8.readFile src - readURI uri = simpleHTTP (mkRequest GET uri) >>= getResponseBody >>= - return . UTF8.toStringLazy -- treat all as UTF8 + 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) diff --git a/src/Text/Pandoc.hs b/src/Text/Pandoc.hs index 2c90fd09b..66b0e49c0 100644 --- a/src/Text/Pandoc.hs +++ b/src/Text/Pandoc.hs @@ -65,6 +65,7 @@ module Text.Pandoc , readMarkdown , readMediaWiki , readRST + , readOrg , readLaTeX , readHtml , readTextile @@ -116,6 +117,7 @@ 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 @@ -203,6 +205,7 @@ readers = [ ("native" , \_ s -> return $ readNative s) ,("mediawiki" , \o s -> return $ readMediaWiki o s) ,("docbook" , \o s -> return $ readDocBook o s) ,("opml" , \o s -> return $ readOPML o s) + ,("org" , \o s -> return $ readOrg 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) @@ -270,7 +273,10 @@ getDefaultExtensions "markdown_strict" = strictExtensions getDefaultExtensions "markdown_phpextra" = phpMarkdownExtraExtensions getDefaultExtensions "markdown_mmd" = multimarkdownExtensions getDefaultExtensions "markdown_github" = githubMarkdownExtensions -getDefaultExtensions _ = pandocExtensions +getDefaultExtensions "markdown" = pandocExtensions +getDefaultExtensions "plain" = pandocExtensions +getDefaultExtensions "textile" = Set.fromList [Ext_auto_identifiers, Ext_raw_tex] +getDefaultExtensions _ = Set.fromList [Ext_auto_identifiers] -- | Retrieve reader based on formatSpec (format+extensions). getReader :: String -> Either String (ReaderOptions -> String -> IO Pandoc) diff --git a/src/Text/Pandoc/ImageSize.hs b/src/Text/Pandoc/ImageSize.hs index 9b0850efb..3c9623b3c 100644 --- a/src/Text/Pandoc/ImageSize.hs +++ b/src/Text/Pandoc/ImageSize.hs @@ -32,9 +32,14 @@ module Text.Pandoc.ImageSize ( ImageType(..), imageType, imageSize, sizeInPixels, sizeInPoints ) where import Data.ByteString (ByteString, unpack) import qualified Data.ByteString.Char8 as B +import qualified Data.ByteString.Lazy as BL +import Control.Applicative import Control.Monad import Data.Bits +import Data.Binary +import Data.Binary.Get import Text.Pandoc.Shared (safeRead) +import qualified Data.Map as M -- quick and dirty functions to get image sizes -- algorithms borrowed from wwwis.pl @@ -53,7 +58,8 @@ imageType :: ByteString -> Maybe ImageType imageType img = case B.take 4 img of "\x89\x50\x4e\x47" -> return Png "\x47\x49\x46\x38" -> return Gif - "\xff\xd8\xff\xe0" -> return Jpeg + "\xff\xd8\xff\xe0" -> return Jpeg -- JFIF + "\xff\xd8\xff\xe1" -> return Jpeg -- Exif "%PDF" -> return Pdf "%!PS" | (B.take 4 $ B.drop 1 $ B.dropWhile (/=' ') img) == "EPSF" @@ -139,8 +145,14 @@ gifSize img = do jpegSize :: ByteString -> Maybe ImageSize jpegSize img = do let (hdr, rest) = B.splitAt 4 img - guard $ hdr == "\xff\xd8\xff\xe0" guard $ B.length rest >= 14 + case hdr of + "\xff\xd8\xff\xe0" -> jfifSize rest + "\xff\xd8\xff\xe1" -> exifSize $ B.takeWhile (/= '\xff') rest + _ -> mzero + +jfifSize :: ByteString -> Maybe ImageSize +jfifSize rest = do let [dpiDensity,dpix1,dpix2,dpiy1,dpiy2] = map fromIntegral $ unpack $ B.take 5 $ B.drop 9 $ rest let factor = case dpiDensity of @@ -149,11 +161,11 @@ jpegSize img = do _ -> const 72 let dpix = factor (shift dpix1 8 + dpix2) let dpiy = factor (shift dpiy1 8 + dpiy2) - (w,h) <- findJpegSize rest + (w,h) <- findJfifSize rest return $ ImageSize { pxX = w, pxY = h, dpiX = dpix, dpiY = dpiy } -findJpegSize :: ByteString -> Maybe (Integer,Integer) -findJpegSize bs = do +findJfifSize :: ByteString -> Maybe (Integer,Integer) +findJfifSize bs = do let bs' = B.dropWhile (=='\xff') $ B.dropWhile (/='\xff') bs case B.uncons bs' of Just (c,bs'') | c >= '\xc0' && c <= '\xc3' -> do @@ -165,8 +177,217 @@ findJpegSize bs = do [c1,c2] -> do let len = shift c1 8 + c2 -- skip variables - findJpegSize $ B.drop len bs'' + findJfifSize $ B.drop len bs'' _ -> fail "JPEG parse error" Nothing -> fail "Did not find length record" +exifSize :: ByteString -> Maybe ImageSize +exifSize bs = runGet (Just <$> exifHeader bl) bl + where bl = BL.fromChunks [bs] +-- NOTE: It would be nicer to do +-- runGet ((Just <$> exifHeader) <|> return Nothing) +-- which would prevent pandoc from raising an error when an exif header can't +-- be parsed. But we only get an Alternative instance for Get in binary 0.6, +-- and binary 0.5 ships with ghc 7.6. + +exifHeader :: BL.ByteString -> Get ImageSize +exifHeader hdr = do + _app1DataSize <- getWord16be + exifHdr <- getWord32be + unless (exifHdr == 0x45786966) $ fail "Did not find exif header" + zeros <- getWord16be + unless (zeros == 0) $ fail "Expected zeros after exif header" + -- beginning of tiff header -- we read whole thing to use + -- in getting data from offsets: + let tiffHeader = BL.drop 8 hdr + byteAlign <- getWord16be + let bigEndian = byteAlign == 0x4d4d + let (getWord16, getWord32, getWord64) = + if bigEndian + then (getWord16be, getWord32be, getWord64be) + else (getWord16le, getWord32le, getWord64le) + let getRational = do + num <- getWord32 + den <- getWord32 + return $ fromIntegral num / fromIntegral den + tagmark <- getWord16 + unless (tagmark == 0x002a) $ fail "Failed alignment sanity check" + ifdOffset <- getWord32 + skip (fromIntegral ifdOffset - 8) -- skip to IDF + numentries <- getWord16 + let ifdEntry = do + tag <- getWord16 >>= \t -> + maybe (fail $ "Unknown tag type " ++ show t) return + (M.lookup t tagTypeTable) + dataFormat <- getWord16 + numComponents <- getWord32 + (fmt, bytesPerComponent) <- + case dataFormat of + 1 -> return (UnsignedByte . runGet getWord8, 1) + 2 -> return (AsciiString, 1) + 3 -> return (UnsignedShort . runGet getWord16, 2) + 4 -> return (UnsignedLong . runGet getWord32, 4) + 5 -> return (UnsignedRational . runGet getRational, 8) + 6 -> return (SignedByte . runGet getWord8, 1) + 7 -> return (Undefined . runGet getWord8, 1) + 8 -> return (SignedShort . runGet getWord16, 2) + 9 -> return (SignedLong . runGet getWord32, 4) + 10 -> return (SignedRational . runGet getRational, 8) + 11 -> return (SingleFloat . runGet getWord32 {- TODO -}, 4) + 12 -> return (DoubleFloat . runGet getWord64 {- TODO -}, 8) + _ -> fail $ "Unknown data format " ++ show dataFormat + let totalBytes = fromIntegral $ numComponents * bytesPerComponent + payload <- if totalBytes <= 4 -- data is right here + then fmt <$> + (getLazyByteString (fromIntegral totalBytes) <* + skip (4 - totalBytes)) + else do -- get data from offset + offs <- getWord32 + return $ fmt $ BL.take (fromIntegral totalBytes) $ + BL.drop (fromIntegral offs) tiffHeader + return (tag, payload) + entries <- sequence $ replicate (fromIntegral numentries) ifdEntry + subentries <- case lookup ExifOffset entries of + Just (UnsignedLong offset) -> do + pos <- bytesRead + skip (fromIntegral offset - (fromIntegral pos - 8)) + numsubentries <- getWord16 + sequence $ + replicate (fromIntegral numsubentries) ifdEntry + _ -> return [] + let allentries = entries ++ subentries + (width, height) <- case (lookup ExifImageWidth allentries, + lookup ExifImageHeight allentries) of + (Just (UnsignedLong w), Just (UnsignedLong h)) -> + return (fromIntegral w, fromIntegral h) + _ -> fail "Could not determine image width, height" + let resfactor = case lookup ResolutionUnit allentries of + Just (UnsignedShort 1) -> (100 / 254) + _ -> 1 + let xres = maybe 72 (\(UnsignedRational x) -> floor $ x * resfactor) + $ lookup XResolution allentries + let yres = maybe 72 (\(UnsignedRational x) -> floor $ x * resfactor) + $ lookup YResolution allentries + return $ ImageSize{ + pxX = width + , pxY = height + , dpiX = xres + , dpiY = yres } + +data DataFormat = UnsignedByte Word8 + | AsciiString BL.ByteString + | UnsignedShort Word16 + | UnsignedLong Word32 + | UnsignedRational Rational + | SignedByte Word8 + | Undefined Word8 + | SignedShort Word16 + | SignedLong Word32 + | SignedRational Rational + | SingleFloat Word32 + | DoubleFloat Word64 + deriving (Show) + +data TagType = ImageDescription + | Make + | Model + | Orientation + | XResolution + | YResolution + | ResolutionUnit + | Software + | DateTime + | WhitePoint + | PrimaryChromaticities + | YCbCrCoefficients + | YCbCrPositioning + | ReferenceBlackWhite + | Copyright + | ExifOffset + | ExposureTime + | FNumber + | ExposureProgram + | ISOSpeedRatings + | ExifVersion + | DateTimeOriginal + | DateTimeDigitized + | ComponentConfiguration + | CompressedBitsPerPixel + | ShutterSpeedValue + | ApertureValue + | BrightnessValue + | ExposureBiasValue + | MaxApertureValue + | SubjectDistance + | MeteringMode + | LightSource + | Flash + | FocalLength + | MakerNote + | UserComment + | FlashPixVersion + | ColorSpace + | ExifImageWidth + | ExifImageHeight + | RelatedSoundFile + | ExifInteroperabilityOffset + | FocalPlaneXResolution + | FocalPlaneYResolution + | FocalPlaneResolutionUnit + | SensingMethod + | FileSource + | SceneType + deriving (Show, Eq, Ord) +tagTypeTable :: M.Map Word16 TagType +tagTypeTable = M.fromList + [ (0x010e, ImageDescription) + , (0x010f, Make) + , (0x0110, Model) + , (0x0112, Orientation) + , (0x011a, XResolution) + , (0x011b, YResolution) + , (0x0128, ResolutionUnit) + , (0x0131, Software) + , (0x0132, DateTime) + , (0x013e, WhitePoint) + , (0x013f, PrimaryChromaticities) + , (0x0211, YCbCrCoefficients) + , (0x0213, YCbCrPositioning) + , (0x0214, ReferenceBlackWhite) + , (0x8298, Copyright) + , (0x8769, ExifOffset) + , (0x829a, ExposureTime) + , (0x829d, FNumber) + , (0x8822, ExposureProgram) + , (0x8827, ISOSpeedRatings) + , (0x9000, ExifVersion) + , (0x9003, DateTimeOriginal) + , (0x9004, DateTimeDigitized) + , (0x9101, ComponentConfiguration) + , (0x9102, CompressedBitsPerPixel) + , (0x9201, ShutterSpeedValue) + , (0x9202, ApertureValue) + , (0x9203, BrightnessValue) + , (0x9204, ExposureBiasValue) + , (0x9205, MaxApertureValue) + , (0x9206, SubjectDistance) + , (0x9207, MeteringMode) + , (0x9208, LightSource) + , (0x9209, Flash) + , (0x920a, FocalLength) + , (0x927c, MakerNote) + , (0x9286, UserComment) + , (0xa000, FlashPixVersion) + , (0xa001, ColorSpace) + , (0xa002, ExifImageWidth) + , (0xa003, ExifImageHeight) + , (0xa004, RelatedSoundFile) + , (0xa005, ExifInteroperabilityOffset) + , (0xa20e, FocalPlaneXResolution) + , (0xa20f, FocalPlaneYResolution) + , (0xa210, FocalPlaneResolutionUnit) + , (0xa217, SensingMethod) + , (0xa300, FileSource) + , (0xa301, SceneType) + ] diff --git a/src/Text/Pandoc/MIME.hs b/src/Text/Pandoc/MIME.hs index f41aa98bb..44989ee94 100644 --- a/src/Text/Pandoc/MIME.hs +++ b/src/Text/Pandoc/MIME.hs @@ -147,6 +147,7 @@ mimeTypesList = -- List borrowed from happstack-server. ,("dxr","application/x-director") ,("emb","chemical/x-embl-dl-nucleotide") ,("embl","chemical/x-embl-dl-nucleotide") + ,("emf","image/x-emf") ,("eml","message/rfc822") ,("ent","chemical/x-ncbi-asn1-ascii") ,("eot","application/vnd.ms-fontobject") @@ -465,6 +466,7 @@ mimeTypesList = -- List borrowed from happstack-server. ,("wm","video/x-ms-wm") ,("wma","audio/x-ms-wma") ,("wmd","application/x-ms-wmd") + ,("wmf","image/x-wmf") ,("wml","text/vnd.wap.wml") ,("wmlc","application/vnd.wap.wmlc") ,("wmls","text/vnd.wap.wmlscript") diff --git a/src/Text/Pandoc/Options.hs b/src/Text/Pandoc/Options.hs index 5f65abdde..38220f542 100644 --- a/src/Text/Pandoc/Options.hs +++ b/src/Text/Pandoc/Options.hs @@ -210,6 +210,7 @@ data ReaderOptions = ReaderOptions{ , readerIndentedCodeClasses :: [String] -- ^ Default classes for -- indented code blocks , readerDefaultImageExtension :: String -- ^ Default extension for images + , readerTrace :: Bool -- ^ Print debugging info } deriving (Show, Read) instance Default ReaderOptions @@ -225,6 +226,7 @@ instance Default ReaderOptions , readerApplyMacros = True , readerIndentedCodeClasses = [] , readerDefaultImageExtension = "" + , readerTrace = False } -- diff --git a/src/Text/Pandoc/PDF.hs b/src/Text/Pandoc/PDF.hs index e8683b98f..39442854d 100644 --- a/src/Text/Pandoc/PDF.hs +++ b/src/Text/Pandoc/PDF.hs @@ -41,6 +41,7 @@ import System.Directory import System.Environment import Control.Monad (unless) 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 @@ -87,7 +88,7 @@ handleImage' baseURL tmpdir (Image ils (src,tit)) = do res <- fetchItem baseURL src case res of Right (contents, Just mime) -> do - let ext = maybe (takeExtension src) id $ + let ext = fromMaybe (takeExtension src) $ extensionFromMimeType mime let basename = UTF8.toString $ B64.encode $ UTF8.fromString src let fname = tmpdir </> basename <.> ext @@ -148,7 +149,12 @@ runTeXProgram program runsLeft tmpDir source = do let programArgs = ["-halt-on-error", "-interaction", "nonstopmode", "-output-directory", tmpDir, file] env' <- getEnvironment - let texinputs = maybe (tmpDir ++ ":") ((tmpDir ++ ":") ++) +#ifdef _WINDOWS + let sep = ";" +#else + let sep = ":" +#endif + let texinputs = maybe (tmpDir ++ sep) ((tmpDir ++ sep) ++) $ lookup "TEXINPUTS" env' let env'' = ("TEXINPUTS", texinputs) : [(k,v) | (k,v) <- env', k /= "TEXINPUTS"] diff --git a/src/Text/Pandoc/Parsing.hs b/src/Text/Pandoc/Parsing.hs index 9687d7712..2bc351db3 100644 --- a/src/Text/Pandoc/Parsing.hs +++ b/src/Text/Pandoc/Parsing.hs @@ -48,6 +48,8 @@ module Text.Pandoc.Parsing ( (>>~), romanNumeral, emailAddress, uri, + mathInline, + mathDisplay, withHorizDisplacement, withRaw, escaped, @@ -269,7 +271,7 @@ spaceChar = satisfy $ \c -> c == ' ' || c == '\t' -- | Parses a nonspace, nonnewline character. nonspaceChar :: Parser [Char] st Char -nonspaceChar = satisfy $ \x -> x /= '\t' && x /= '\n' && x /= ' ' && x /= '\r' +nonspaceChar = satisfy $ flip notElem ['\t', '\n', ' ', '\r'] -- | Skips zero or more spaces or tabs. skipSpaces :: Parser [Char] st () @@ -455,6 +457,39 @@ uri = try $ do let uri' = scheme ++ ":" ++ fromEntities str' return (uri', escapeURI uri') +mathInlineWith :: String -> String -> Parser [Char] st 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) + notFollowedBy digit -- to prevent capture of $5 + return $ concat words' + +mathDisplayWith :: String -> String -> Parser [Char] st String +mathDisplayWith op cl = try $ do + string op + many1Till (noneOf "\n" <|> (newline >>~ notFollowedBy' blankline)) (try $ string cl) + +mathDisplay :: Parser [Char] ParserState String +mathDisplay = + (guardEnabled Ext_tex_math_dollars >> mathDisplayWith "$$" "$$") + <|> (guardEnabled Ext_tex_math_single_backslash >> + mathDisplayWith "\\[" "\\]") + <|> (guardEnabled Ext_tex_math_double_backslash >> + mathDisplayWith "\\\\[" "\\\\]") + +mathInline :: Parser [Char] ParserState String +mathInline = + (guardEnabled Ext_tex_math_dollars >> mathInlineWith "$" "$") + <|> (guardEnabled Ext_tex_math_single_backslash >> + mathInlineWith "\\(" "\\)") + <|> (guardEnabled Ext_tex_math_double_backslash >> + mathInlineWith "\\\\(" "\\\\)") + -- | Applies a parser, returns tuple of its results and its horizontal -- displacement (the difference between the source column at the end -- and the source column at the beginning). Vertical displacement @@ -818,6 +853,11 @@ 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 -> (String, Attr)), -- ^ Current rST custom text roles + -- Triple represents: 1) Base role, 2) Optional format (only for :raw: + -- roles), 3) Source language annotation for code (could be used to + -- annotate role classes too). + stateWarnings :: [String] -- ^ Warnings generated by the parser } @@ -880,6 +920,7 @@ defaultParserState = stateHasChapters = False, stateMacros = [], stateRstDefaultRole = "title-reference", + stateRstCustomRoles = M.empty, stateWarnings = []} getOption :: (ReaderOptions -> a) -> Parser s ParserState a @@ -1027,7 +1068,7 @@ doubleQuoteStart :: Parser [Char] ParserState () doubleQuoteStart = do failIfInQuoteContext InDoubleQuote try $ do charOrRef "\"\8220\147" - notFollowedBy (satisfy (\c -> c == ' ' || c == '\t' || c == '\n')) + notFollowedBy . satisfy $ flip elem [' ', '\t', '\n'] doubleQuoteEnd :: Parser [Char] st () doubleQuoteEnd = do diff --git a/src/Text/Pandoc/Pretty.hs b/src/Text/Pandoc/Pretty.hs index faf2a6797..5331587ce 100644 --- a/src/Text/Pandoc/Pretty.hs +++ b/src/Text/Pandoc/Pretty.hs @@ -60,6 +60,7 @@ module Text.Pandoc.Pretty ( , hsep , vcat , vsep + , nestle , chomp , inside , braces @@ -72,7 +73,7 @@ module Text.Pandoc.Pretty ( ) where -import Data.Sequence (Seq, fromList, (<|), singleton, mapWithIndex) +import Data.Sequence (Seq, fromList, (<|), singleton, mapWithIndex, viewl, ViewL(..)) import Data.Foldable (toList) import Data.List (intercalate) import Data.Monoid @@ -80,8 +81,7 @@ import Data.String import Control.Monad.State import Data.Char (isSpace) -data Monoid a => - RenderState a = RenderState{ +data RenderState a = RenderState{ output :: [a] -- ^ In reverse order , prefix :: String , usePrefix :: Bool @@ -186,6 +186,14 @@ vcat = foldr ($$) empty vsep :: [Doc] -> Doc vsep = foldr ($+$) empty +-- | Removes leading blank lines from a 'Doc'. +nestle :: Doc -> Doc +nestle (Doc d) = Doc $ go d + where go x = case viewl x of + (BlankLine :< rest) -> go rest + (NewLine :< rest) -> go rest + _ -> x + -- | Chomps trailing blank space off of a 'Doc'. chomp :: Doc -> Doc chomp d = Doc (fromList dl') diff --git a/src/Text/Pandoc/Readers/DocBook.hs b/src/Text/Pandoc/Readers/DocBook.hs index fc29988d5..56cb16b20 100644 --- a/src/Text/Pandoc/Readers/DocBook.hs +++ b/src/Text/Pandoc/Readers/DocBook.hs @@ -12,6 +12,7 @@ import Data.Char (isSpace) import Control.Monad.State import Control.Applicative ((<$>)) import Data.List (intersperse) +import Data.Maybe (fromMaybe) {- @@ -683,7 +684,7 @@ parseBlock (Elem e) = "lowerroman" -> LowerRoman "upperroman" -> UpperRoman _ -> Decimal - let start = maybe 1 id $ + let start = fromMaybe 1 $ (attrValue "override" <$> filterElement (named "listitem") e) >>= safeRead orderedListWith (start,listStyle,DefaultDelim) @@ -779,7 +780,7 @@ parseBlock (Elem e) = caption <- case filterChild isCaption e of Just t -> getInlines t Nothing -> return mempty - let e' = maybe e id $ filterChild (named "tgroup") e + let e' = fromMaybe e $ filterChild (named "tgroup") e let isColspec x = named "colspec" x || named "col" x let colspecs = case filterChild (named "colgroup") e' of Just c -> filterChildren isColspec c @@ -801,12 +802,14 @@ parseBlock (Elem e) = Just "center" -> AlignCenter _ -> AlignDefault let toWidth c = case findAttr (unqual "colwidth") c of - Just w -> maybe 0 id + Just w -> fromMaybe 0 $ safeRead $ '0': filter (\x -> (x >= '0' && x <= '9') || x == '.') w Nothing -> 0 :: Double - let numrows = maximum $ map length bodyrows + let numrows = case bodyrows of + [] -> 0 + xs -> maximum $ map length xs let aligns = case colspecs of [] -> replicate numrows AlignDefault cs -> map toAlignment cs diff --git a/src/Text/Pandoc/Readers/HTML.hs b/src/Text/Pandoc/Readers/HTML.hs index d691c9878..d1e4d0024 100644 --- a/src/Text/Pandoc/Readers/HTML.hs +++ b/src/Text/Pandoc/Readers/HTML.hs @@ -76,9 +76,18 @@ pBody :: TagParser [Block] pBody = pInTags "body" block pHead :: TagParser [Block] -pHead = pInTags "head" $ pTitle <|> ([] <$ pAnyTag) +pHead = pInTags "head" $ pTitle <|> pMetaTag <|> ([] <$ pAnyTag) where pTitle = pInTags "title" inline >>= setTitle . normalizeSpaces setTitle t = [] <$ (updateState $ B.setMeta "title" (B.fromList t)) + pMetaTag = do + mt <- pSatisfy (~== TagOpen "meta" []) + let name = fromAttrib "name" mt + if null name + then return [] + else do + let content = fromAttrib "content" mt + updateState $ B.setMeta name (B.text content) + return [] block :: TagParser [Block] block = choice @@ -207,7 +216,7 @@ pHeader = try $ do let bodyTitle = TagOpen tagtype attr ~== TagOpen "h1" [("class","title")] let level = read (drop 1 tagtype) contents <- liftM concat $ manyTill inline (pCloses tagtype <|> eof) - let ident = maybe "" id $ lookup "id" attr + 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 @@ -257,7 +266,7 @@ pCol = try $ do skipMany pBlank return $ case lookup "width" attribs of Just x | not (null x) && last x == '%' -> - maybe 0.0 id $ safeRead ('0':'.':init x) + fromMaybe 0.0 $ safeRead ('0':'.':init x) _ -> 0.0 pColgroup :: TagParser [Double] @@ -467,7 +476,13 @@ pBlank = try $ do pTagContents :: Parser [Char] ParserState Inline pTagContents = - pStr <|> pSpace <|> smartPunctuation pTagContents <|> pSymbol <|> pBad + Math DisplayMath `fmap` mathDisplay + <|> Math InlineMath `fmap` mathInline + <|> pStr + <|> pSpace + <|> smartPunctuation pTagContents + <|> pSymbol + <|> pBad pStr :: Parser [Char] ParserState Inline pStr = do @@ -482,6 +497,7 @@ isSpecial '"' = True isSpecial '\'' = True isSpecial '.' = True isSpecial '-' = True +isSpecial '$' = True isSpecial '\8216' = True isSpecial '\8217' = True isSpecial '\8220' = True diff --git a/src/Text/Pandoc/Readers/LaTeX.hs b/src/Text/Pandoc/Readers/LaTeX.hs index 75e29ebb9..51271edc5 100644 --- a/src/Text/Pandoc/Readers/LaTeX.hs +++ b/src/Text/Pandoc/Readers/LaTeX.hs @@ -38,7 +38,8 @@ import Text.Pandoc.Definition import Text.Pandoc.Walk import Text.Pandoc.Shared import Text.Pandoc.Options -import Text.Pandoc.Parsing hiding ((<|>), many, optional, space) +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 @@ -172,6 +173,8 @@ double_quote :: LP Inlines double_quote = ( quoted' doubleQuoted (try $ string "``") (void $ try $ string "''") <|> quoted' doubleQuoted (string "“") (void $ char '”') + -- the following is used by babel for localized quotes: + <|> quoted' doubleQuoted (try $ string "\"`") (void $ try $ string "\"'") <|> quoted' doubleQuoted (string "\"") (void $ char '"') ) @@ -454,6 +457,7 @@ inlineCommands = M.fromList $ , ("footnote", (note . mconcat) <$> (char '{' *> manyTill block (char '}'))) , ("verb", doverb) , ("lstinline", doverb) + , ("Verb", doverb) , ("texttt", (code . stringify . toList) <$> tok) , ("url", (unescapeURL <$> braced) >>= \url -> pure (link url "" (str url))) @@ -870,9 +874,8 @@ verbatimEnv = do (_,r) <- withRaw $ do controlSeq "begin" name <- braced - guard $ name == "verbatim" || name == "Verbatim" || - name == "lstlisting" || name == "minted" || - name == "alltt" + guard $ name `elem` ["verbatim", "Verbatim", "lstlisting", + "minted", "alltt"] verbEnv name rest <- getInput return (r,rest) diff --git a/src/Text/Pandoc/Readers/Markdown.hs b/src/Text/Pandoc/Readers/Markdown.hs index 33d1a9620..0ea7f9ac5 100644 --- a/src/Text/Pandoc/Readers/Markdown.hs +++ b/src/Text/Pandoc/Readers/Markdown.hs @@ -60,6 +60,8 @@ 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 @@ -215,10 +217,10 @@ pandocTitleBlock = try $ do author' <- author date' <- date return $ - ( if B.isNull title' then id else B.setMeta "title" title' - . if null author' then id else B.setMeta "author" author' - . if B.isNull date' then id else B.setMeta "date" date' ) - nullMeta + (if B.isNull title' then id else B.setMeta "title" title') + . (if null author' then id else B.setMeta "author" author') + . (if B.isNull date' then id else B.setMeta "date" date') + $ nullMeta updateState $ \st -> st{ stateMeta' = stateMeta' st <> meta' } yamlMetaBlock :: MarkdownParser (F Blocks) @@ -354,7 +356,7 @@ referenceKey = try $ do 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 @@ -730,9 +740,14 @@ listStart = bulletListStart <|> (anyOrderedListStart >> return ()) listLine :: MarkdownParser String listLine = try $ do notFollowedBy' (do indentSpaces - many (spaceChar) + many spaceChar listStart) - chunks <- manyTill (liftM snd (htmlTag isCommentTag) <|> count 1 anyChar) newline + notFollowedBy' $ htmlTag (~== TagClose "div") + chunks <- 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 @@ -759,6 +774,7 @@ listContinuationLine :: MarkdownParser String listContinuationLine = try $ do notFollowedBy blankline notFollowedBy' listStart + notFollowedBy' $ htmlTag (~== TagClose "div") optional indentSpaces result <- anyLine return $ result ++ "\n" @@ -783,8 +799,8 @@ listItem start = try $ do orderedList :: MarkdownParser (F Blocks) orderedList = try $ do (start, style, delim) <- lookAhead anyOrderedListStart - unless ((style == DefaultStyle || style == Decimal || style == Example) && - (delim == DefaultDelim || delim == Period)) $ + unless (style `elem` [DefaultStyle, Decimal, Example] && + delim `elem` [DefaultDelim, Period]) $ guardEnabled Ext_fancy_lists when (style == Example) $ guardEnabled Ext_example_lists items <- fmap sequence $ many1 $ listItem @@ -896,7 +912,9 @@ plain = fmap B.plain . trimInlinesF . mconcat <$> many1 inline -- htmlElement :: MarkdownParser String -htmlElement = strictHtmlBlock <|> liftM snd (htmlTag isBlockTag) +htmlElement = rawVerbatimBlock + <|> strictHtmlBlock + <|> liftM snd (htmlTag isBlockTag) htmlBlock :: MarkdownParser (F Blocks) htmlBlock = do @@ -917,8 +935,8 @@ strictHtmlBlock = htmlInBalanced (not . isInlineTag) rawVerbatimBlock :: MarkdownParser String rawVerbatimBlock = try $ do - (TagOpen tag _, open) <- htmlTag (tagOpen (\t -> - t == "pre" || t == "style" || t == "script") + (TagOpen tag _, open) <- htmlTag (tagOpen (flip elem + ["pre", "style", "script"]) (const True)) contents <- manyTill anyChar (htmlTag (~== TagClose tag)) return $ open ++ contents ++ renderTags [TagClose tag] @@ -936,6 +954,8 @@ rawHtmlBlocks = do htmlBlocks <- many1 $ try $ do s <- rawVerbatimBlock <|> try ( do (t,raw) <- htmlTag isBlockTag + guard $ t ~/= TagOpen "div" [] && + t ~/= TagClose "div" exts <- getOption readerExtensions -- if open tag, need markdown="1" if -- markdown_attributes extension is set @@ -1118,12 +1138,12 @@ multilineTableHeader headless = try $ do then liftM (map (:[]) . tail . splitStringByIndices (init indices)) $ lookAhead anyLine else return $ transpose $ map - (\ln -> tail $ splitStringByIndices (init indices) ln) + (tail . splitStringByIndices (init indices)) rawContent let aligns = zipWith alignType rawHeadsList lengths let rawHeads = if headless then replicate (length dashes) "" - else map unwords rawHeadsList + else map (unlines . map trim) rawHeadsList heads <- fmap sequence $ mapM (parseFromString (mconcat <$> many plain)) $ map trim rawHeads @@ -1180,7 +1200,7 @@ gridTableHeader headless = try $ do -- RST does not have a notion of alignments let rawHeads = if headless then replicate (length dashes) "" - else map unwords $ transpose + else map (unlines . map trim) $ transpose $ map (gridTableSplitLine indices) rawContent heads <- fmap sequence $ mapM (parseFromString parseBlocks . trim) rawHeads return (heads, aligns, indices) @@ -1366,7 +1386,7 @@ ltSign :: MarkdownParser (F Inlines) ltSign = do guardDisabled Ext_raw_html <|> guardDisabled Ext_markdown_in_html_blocks - <|> (notFollowedBy' rawHtmlBlocks >> return ()) + <|> (notFollowedBy' (htmlTag isBlockTag) >> return ()) char '<' return $ return $ B.str "<" @@ -1406,39 +1426,6 @@ math :: MarkdownParser (F Inlines) math = (return . B.displayMath <$> (mathDisplay >>= applyMacros')) <|> (return . B.math <$> (mathInline >>= applyMacros')) -mathDisplay :: MarkdownParser String -mathDisplay = - (guardEnabled Ext_tex_math_dollars >> mathDisplayWith "$$" "$$") - <|> (guardEnabled Ext_tex_math_single_backslash >> - mathDisplayWith "\\[" "\\]") - <|> (guardEnabled Ext_tex_math_double_backslash >> - mathDisplayWith "\\\\[" "\\\\]") - -mathDisplayWith :: String -> String -> MarkdownParser String -mathDisplayWith op cl = try $ do - string op - many1Till (noneOf "\n" <|> (newline >>~ notFollowedBy' blankline)) (try $ string cl) - -mathInline :: MarkdownParser String -mathInline = - (guardEnabled Ext_tex_math_dollars >> mathInlineWith "$" "$") - <|> (guardEnabled Ext_tex_math_single_backslash >> - mathInlineWith "\\(" "\\)") - <|> (guardEnabled Ext_tex_math_double_backslash >> - mathInlineWith "\\\\(" "\\\\)") - -mathInlineWith :: String -> String -> MarkdownParser 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) - notFollowedBy digit -- to prevent capture of $5 - return $ concat words' - -- Parses material enclosed in *s, **s, _s, or __s. -- Designed to avoid backtracking. enclosure :: Char @@ -1565,16 +1552,14 @@ endline :: MarkdownParser (F Inlines) endline = try $ do newline notFollowedBy blankline + -- parse potential list-starts differently if in a list: + st <- getState + when (stateParserContext st == ListItemState) $ notFollowedBy 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 >> notFollowedBy (() <$ (lookAhead (char '`') >> codeBlockFenced)) - -- parse potential list-starts differently if in a list: - st <- getState - when (stateParserContext st == ListItemState) $ do - notFollowedBy' bulletListStart - notFollowedBy' anyOrderedListStart (guardEnabled Ext_hard_line_breaks >> return (return B.linebreak)) <|> (guardEnabled Ext_ignore_line_breaks >> return mempty) <|> (return $ return B.space) @@ -1747,7 +1732,7 @@ spanHtml = try $ do guardEnabled Ext_markdown_in_html_blocks (TagOpen _ attrs, _) <- htmlTag (~== TagOpen "span" []) contents <- mconcat <$> manyTill inline (htmlTag (~== TagClose "span")) - let ident = maybe "" id $ lookup "id" attrs + 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 @@ -1755,12 +1740,19 @@ spanHtml = try $ do 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 = maybe "" id $ 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) <$> contents + (TagOpen _ attrs, rawtag) <- htmlTag (~== TagOpen "div" []) + bls <- option "" (blankline >> option "" blanklines) + contents <- mconcat <$> + many (notFollowedBy' (htmlTag (~== TagClose "div")) >> block) + closed <- option False (True <$ htmlTag (~== TagClose "div")) + if closed + then do + 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 @@ -1836,9 +1828,10 @@ citeKey = try $ do guard $ lastStrPos /= Just pos suppress_author <- option False (char '-' >> return True) char '@' - first <- letter - let internal p = try $ p >>~ lookAhead (letter <|> digit) - rest <- many $ letter <|> digit <|> internal (oneOf ":.#$%&-_+?<>~/") + 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) diff --git a/src/Text/Pandoc/Readers/MediaWiki.hs b/src/Text/Pandoc/Readers/MediaWiki.hs index 1c074e3de..794890eb6 100644 --- a/src/Text/Pandoc/Readers/MediaWiki.hs +++ b/src/Text/Pandoc/Readers/MediaWiki.hs @@ -54,6 +54,7 @@ import Data.Sequence (viewl, ViewL(..), (<|)) import qualified Data.Foldable as F import qualified Data.Map as M import Data.Char (isDigit, isSpace) +import Data.Maybe (fromMaybe) -- | Read mediawiki from an input string and return a Pandoc document. readMediaWiki :: ReaderOptions -- ^ Reader options @@ -148,9 +149,16 @@ inlinesInTags tag = try $ do blocksInTags :: String -> MWParser Blocks blocksInTags tag = try $ do (_,raw) <- htmlTag (~== TagOpen tag []) + let closer = if tag == "li" + then htmlTag (~== TagClose "li") + <|> lookAhead ( + htmlTag (~== TagOpen "li" []) + <|> htmlTag (~== TagClose "ol") + <|> htmlTag (~== TagClose "ul")) + else htmlTag (~== TagClose tag) if '/' `elem` raw -- self-closing tag then return mempty - else mconcat <$> manyTill block (htmlTag (~== TagClose tag)) + else mconcat <$> manyTill block closer charsInTags :: String -> MWParser [Char] charsInTags tag = try $ do @@ -204,7 +212,7 @@ table = do tableStart styles <- option [] parseAttrs <* blankline let tableWidth = case lookup "width" styles of - Just w -> maybe 1.0 id $ parseWidth w + Just w -> fromMaybe 1.0 $ parseWidth w Nothing -> 1.0 caption <- option mempty tableCaption optional rowsep @@ -285,7 +293,7 @@ tableCell = try $ do Just "center" -> AlignCenter _ -> AlignDefault let width = case lookup "width" attrs of - Just xs -> maybe 0.0 id $ parseWidth xs + Just xs -> fromMaybe 0.0 $ parseWidth xs Nothing -> 0.0 return ((align, width), bs) @@ -380,15 +388,13 @@ bulletList = B.bulletList <$> orderedList :: MWParser Blocks orderedList = (B.orderedList <$> many1 (listItem '#')) - <|> (B.orderedList <$> (htmlTag (~== TagOpen "ul" []) *> spaces *> - many (listItem '#' <|> li) <* - optional (htmlTag (~== TagClose "ul")))) - <|> do (tag,_) <- htmlTag (~== TagOpen "ol" []) - spaces - items <- many (listItem '#' <|> li) - optional (htmlTag (~== TagClose "ol")) - let start = maybe 1 id $ safeRead $ fromAttrib "start" tag - return $ B.orderedListWith (start, DefaultStyle, DefaultDelim) items + <|> try + (do (tag,_) <- htmlTag (~== TagOpen "ol" []) + spaces + items <- many (listItem '#' <|> li) + optional (htmlTag (~== TagClose "ol")) + let start = fromMaybe 1 $ safeRead $ fromAttrib "start" tag + return $ B.orderedListWith (start, DefaultStyle, DefaultDelim) items) definitionList :: MWParser Blocks definitionList = B.definitionList <$> many1 defListItem diff --git a/src/Text/Pandoc/Readers/Org.hs b/src/Text/Pandoc/Readers/Org.hs new file mode 100644 index 000000000..5dc250f04 --- /dev/null +++ b/src/Text/Pandoc/Readers/Org.hs @@ -0,0 +1,552 @@ +{-# LANGUAGE OverloadedStrings #-} +{- +Copyright (C) 2014 Albert Krewinkel <tarleb@moltkeplatz.de> + +This program is free software; you can redistribute it and/or modify +it under the terms of the GNU General Public License as published by +the Free Software Foundation; either version 2 of the License, or +(at your option) any later version. + +This program is distributed in the hope that it will be useful, +but WITHOUT ANY WARRANTY; without even the implied warranty of +MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the +GNU General Public License for more details. + +You should have received a copy of the GNU General Public License +along with this program; if not, write to the Free Software +Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA +-} + +{- | + Module : Text.Pandoc.Readers.Org + Copyright : Copyright (C) 2014 Albert Krewinkel + License : GNU GPL, version 2 or above + + Maintainer : Albert Krewinkel <tarleb@moltkeplatz.de> + +Conversion of Org-Mode to 'Pandoc' document. +-} +module Text.Pandoc.Readers.Org ( readOrg ) where + +import qualified Text.Pandoc.Builder as B +import Text.Pandoc.Builder (Inlines, Blocks, trimInlines, (<>)) +import Text.Pandoc.Definition +import Text.Pandoc.Options +import Text.Pandoc.Parsing hiding (orderedListMarker) +import Text.Pandoc.Shared (compactify') + +import Control.Applicative (pure, (<$>), (<$), (<*>), (<*), (*>), (<**>)) +import Control.Monad (guard, mzero) +import Data.Char (toLower) +import Data.List (foldl') +import Data.Maybe (listToMaybe, fromMaybe) +import Data.Monoid (mconcat, mempty, mappend) + +-- | Parse org-mode string and return a Pandoc document. +readOrg :: ReaderOptions -- ^ Reader options + -> String -- ^ String to parse (assuming @'\n'@ line endings) + -> Pandoc +readOrg opts s = (readWith parseOrg) def{ stateOptions = opts } (s ++ "\n\n") + +type OrgParser = Parser [Char] ParserState + +parseOrg:: OrgParser Pandoc +parseOrg = do + blocks' <- B.toList <$> parseBlocks + st <- getState + let meta = stateMeta st + return $ Pandoc meta $ filter (/= Null) blocks' + +-- +-- parsing blocks +-- + +parseBlocks :: OrgParser Blocks +parseBlocks = mconcat <$> manyTill block eof + +block :: OrgParser Blocks +block = choice [ mempty <$ blanklines + , orgBlock + , example + , drawer + , specialLine + , header + , hline + , list + , table + , paraOrPlain + ] <?> "block" + +-- +-- Org Blocks (#+BEGIN_... / #+END_...) +-- + +orgBlock :: OrgParser Blocks +orgBlock = try $ do + (indent, blockType, args) <- blockHeader + blockStr <- rawBlockContent indent blockType + let classArgs = [ translateLang . fromMaybe [] $ listToMaybe args ] + case blockType of + "comment" -> return mempty + "src" -> return $ B.codeBlockWith ("", classArgs, []) blockStr + _ -> B.divWith ("", [blockType], []) + <$> (parseFromString parseBlocks blockStr) + +blockHeader :: OrgParser (Int, String, [String]) +blockHeader = (,,) <$> blockIndent + <*> blockType + <*> (skipSpaces *> blockArgs) + where blockIndent = length <$> many spaceChar + blockType = map toLower <$> (stringAnyCase "#+begin_" *> many letter) + blockArgs = manyTill (many nonspaceChar <* skipSpaces) newline + +rawBlockContent :: Int -> String -> OrgParser String +rawBlockContent indent blockType = + unlines . map commaEscaped <$> manyTill indentedLine blockEnder + where + indentedLine = try $ choice [ blankline *> pure "\n" + , indentWith indent *> anyLine + ] + blockEnder = try $ indentWith indent *> stringAnyCase ("#+end_" <> blockType) + +-- 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 ' ')) ] + +translateLang :: String -> String +translateLang "sh" = "bash" +translateLang cs = cs + +commaEscaped :: String -> String +commaEscaped (',':cs@('*':_)) = cs +commaEscaped (',':cs@('#':'+':_)) = cs +commaEscaped cs = cs + +example :: OrgParser Blocks +example = try $ + B.codeBlockWith ("", ["example"], []) . unlines <$> many1 exampleLine + +exampleLine :: OrgParser String +exampleLine = try $ string ": " *> anyLine + +-- Drawers for properties or a logbook +drawer :: OrgParser Blocks +drawer = try $ do + drawerStart + manyTill drawerLine (try drawerEnd) + return mempty + +drawerStart :: OrgParser String +drawerStart = try $ + skipSpaces *> drawerName <* skipSpaces <* 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 <* newline + + +-- Comments, Options and Metadata +specialLine :: OrgParser Blocks +specialLine = try $ metaLine <|> commentLine + +metaLine :: OrgParser Blocks +metaLine = try $ metaLineStart *> 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 Blocks +declarationLine = try $ do + meta' <- B.setMeta <$> metaKey <*> metaValue <*> pure nullMeta + updateState $ \st -> st { stateMeta = stateMeta st <> meta' } + return mempty + +metaValue :: OrgParser MetaValue +metaValue = MetaInlines . B.toList . trimInlines <$> restOfLine + +metaKey :: OrgParser [Char] +metaKey = map toLower <$> many1 (noneOf ": \n\r") + <* char ':' + <* skipSpaces + +-- | Headers +header :: OrgParser Blocks +header = try $ + B.header <$> headerStart + <*> (trimInlines <$> restOfLine) + +headerStart :: OrgParser Int +headerStart = try $ + (length <$> many1 (char '*')) <* many1 (char ' ') + +-- 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 [Blocks] + | OrgAlignRow [Alignment] + | OrgHlineRow + deriving (Eq, Show) + +type OrgTableContent = (Int, [Alignment], [Double], [Blocks], [[Blocks]]) + +table :: OrgParser Blocks +table = try $ do + lookAhead tableStart + (_, aligns, widths, heads, lns) <- normalizeTable . tableContent <$> tableRows + return $ B.table "" (zip aligns widths) heads lns + +tableStart :: OrgParser Char +tableStart = try $ skipSpaces *> char '|' + +tableRows :: OrgParser [OrgTableRow] +tableRows = try $ many (tableAlignRow <|> tableHline <|> tableContentRow) + +tableContentRow :: OrgParser OrgTableRow +tableContentRow = try $ + OrgContentRow <$> (tableStart *> manyTill tableContentCell newline) + +tableContentCell :: OrgParser Blocks +tableContentCell = try $ + B.plain . trimInlines . mconcat <$> many1Till inline (try endOfCell) + +endOfCell :: OrgParser Char +-- endOfCell = char '|' <|> newline +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) + +tableContent :: [OrgTableRow] + -> OrgTableContent +tableContent = foldl' (flip rowToContent) (0, mempty, repeat 0, mempty, mempty) + +normalizeTable :: OrgTableContent + -> OrgTableContent +normalizeTable (cols, aligns, widths, heads, lns) = + let aligns' = fillColumns aligns AlignDefault + widths' = fillColumns widths 0.0 + heads' = if heads == mempty + then heads + else fillColumns heads (B.plain mempty) + lns' = map (flip fillColumns (B.plain mempty)) lns + fillColumns base padding = take cols $ base ++ repeat padding + in (cols, aligns', widths', 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 + -> OrgTableContent + -> OrgTableContent +rowToContent OrgHlineRow = maybeBodyToHeader +rowToContent (OrgContentRow rs) = setLongestRow rs . appendToBody rs +rowToContent (OrgAlignRow as) = setLongestRow as . setAligns as + +setLongestRow :: [a] + -> OrgTableContent + -> OrgTableContent +setLongestRow r (cols, aligns, widths, heads, lns) = + (max cols (length r), aligns, widths, heads, lns) + +maybeBodyToHeader :: OrgTableContent + -> OrgTableContent +maybeBodyToHeader (cols, aligns, widths, [], b:[]) = (cols, aligns, widths, b, []) +maybeBodyToHeader content = content + +appendToBody :: [Blocks] + -> OrgTableContent + -> OrgTableContent +appendToBody r (cols, aligns, widths, heads, lns) = + (cols, aligns, widths, heads, lns ++ [r]) + +setAligns :: [Alignment] + -> OrgTableContent + -> OrgTableContent +setAligns aligns (cols, _, widths, heads, lns) = + (cols, aligns, widths, heads, lns) + +-- Paragraphs or Plain text +paraOrPlain :: OrgParser Blocks +paraOrPlain = try $ + trimInlines . mconcat + <$> many1 inline + <**> option B.plain + (try $ newline *> pure B.para) + +restOfLine :: OrgParser Inlines +restOfLine = mconcat <$> manyTill inline newline + + +-- +-- list blocks +-- + +list :: OrgParser Blocks +list = choice [ bulletList, orderedList ] <?> "list" + +bulletList :: OrgParser Blocks +bulletList = B.bulletList . compactify' <$> many1 (listItem bulletListStart) + +orderedList :: OrgParser Blocks +orderedList = B.orderedList . compactify' <$> many1 (listItem orderedListStart) + +genericListStart :: OrgParser String + -> OrgParser Int +genericListStart listMarker = try $ + (+) <$> (length <$> many spaceChar) + <*> (length <$> listMarker <* many1 spaceChar) + +-- parses bullet list start and returns its length (excl. following whitespace) +bulletListStart :: OrgParser Int +bulletListStart = genericListStart bulletListMarker + where bulletListMarker = pure <$> oneOf "*-+" + +orderedListStart :: OrgParser Int +orderedListStart = genericListStart orderedListMarker + -- Ordered list markers allowed in org-mode + where orderedListMarker = mappend <$> many1 digit <*> (pure <$> oneOf ".)") + +listItem :: OrgParser Int + -> OrgParser Blocks +listItem start = try $ do + (markerLength, first) <- try (start >>= rawListItem) + rest <- many (listContinuation markerLength) + parseFromString parseBlocks $ concat (first:rest) + +-- parse raw text for one list item, excluding start marker and continuations +rawListItem :: Int + -> OrgParser (Int, String) +rawListItem markerLength = try $ do + firstLine <- anyLine + restLines <- many (listLine markerLength) + return (markerLength, (firstLine ++ "\n" ++ (concat restLines))) + +-- 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 $ + mappend <$> many blankline + <*> (concat <$> many1 (listLine markerLength)) + +-- parse a line of a list item +listLine :: Int + -> OrgParser String +listLine markerLength = try $ + indentWith markerLength *> anyLine + <**> pure (++ "\n") + + +-- +-- inline +-- + +inline :: OrgParser Inlines +inline = choice inlineParsers <?> "inline" + where inlineParsers = [ whitespace + , link + , str + , endline + , emph + , strong + , strikeout + , underline + , code + , verbatim + , subscript + , superscript + , symbol + ] + +-- treat these as potentially non-text when parsing inline: +specialChars :: [Char] +specialChars = "\"$'()*+-./:<=>[\\]^_{|}~" + + +whitespace :: OrgParser Inlines +whitespace = B.space <$ skipMany1 spaceChar <?> "whitespace" + +str :: OrgParser Inlines +str = B.str <$> many1 (noneOf $ specialChars ++ "\n\r ") + <* updateLastStrPos + +-- an endline character that can be treated as a space, not a structural break +endline :: OrgParser Inlines +endline = try $ do + newline + notFollowedBy blankline + notFollowedBy' exampleLine + notFollowedBy' hline + notFollowedBy' tableStart + notFollowedBy' drawerStart + notFollowedBy' headerStart + notFollowedBy' metaLineStart + notFollowedBy' commentLineStart + notFollowedBy' bulletListStart + notFollowedBy' orderedListStart + return B.space + +link :: OrgParser Inlines +link = explicitLink <|> selfLink <?> "link" + +explicitLink :: OrgParser Inlines +explicitLink = try $ do + char '[' + src <- enclosedRaw (char '[') (char ']') + title <- enclosedInlines (char '[') (char ']') + char ']' + return $ B.link src "" title + +selfLink :: OrgParser Inlines +selfLink = try $ do + src <- enclosedRaw (string "[[") (string "]]") + return $ B.link src "" (B.str src) + +emph :: OrgParser Inlines +emph = B.emph <$> inlinesEnclosedBy '/' + +strong :: OrgParser Inlines +strong = B.strong <$> inlinesEnclosedBy '*' + +strikeout :: OrgParser Inlines +strikeout = B.strikeout <$> inlinesEnclosedBy '+' + +-- There is no underline, so we use strong instead. +underline :: OrgParser Inlines +underline = B.strong <$> inlinesEnclosedBy '_' + +code :: OrgParser Inlines +code = B.code <$> rawEnclosedBy '=' + +verbatim :: OrgParser Inlines +verbatim = B.rawInline "" <$> rawEnclosedBy '~' + +subscript :: OrgParser Inlines +subscript = B.subscript <$> (try $ char '_' *> maybeGroupedByBraces) + +superscript :: OrgParser Inlines +superscript = B.superscript <$> (try $ char '^' *> maybeGroupedByBraces) + +maybeGroupedByBraces :: OrgParser Inlines +maybeGroupedByBraces = try $ + choice [ try $ enclosedInlines (char '{') (char '}') + , B.str . (:"") <$> anyChar + ] + +symbol :: OrgParser Inlines +symbol = B.str . (: "") <$> oneOf specialChars + +enclosedInlines :: OrgParser a + -> OrgParser b + -> OrgParser Inlines +enclosedInlines start end = try $ + trimInlines . mconcat <$> enclosed start end inline + +-- FIXME: This is a hack +inlinesEnclosedBy :: Char + -> OrgParser Inlines +inlinesEnclosedBy c = enclosedInlines (atStart (char c) <* endsOnThisOrNextLine c) + (atEnd $ char c) + +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 + +rawEnclosedBy :: Char + -> OrgParser String +rawEnclosedBy c = enclosedRaw (atStart $ char c) (atEnd $ char c) + +-- succeeds only if we're not right after a str (ie. in middle of word) +atStart :: OrgParser a -> OrgParser a +atStart p = do + pos <- getPosition + st <- getState + guard $ stateLastStrPos st /= Just pos + p + +-- | succeeds only if we're at the end of a word +atEnd :: OrgParser a -> OrgParser a +atEnd p = try $ p <* lookingAtEndOfWord + where lookingAtEndOfWord = lookAhead . oneOf $ postWordChars + +postWordChars :: [Char] +postWordChars = "\t\n\r !\"'),-.:?}" + +-- FIXME: These functions are hacks and should be replaced +endsOnThisOrNextLine :: Char + -> OrgParser () +endsOnThisOrNextLine c = do + inp <- getInput + let doOtherwise = \rest -> endsOnThisLine rest c (const mzero) + endsOnThisLine inp c doOtherwise + +endsOnThisLine :: [Char] + -> Char + -> ([Char] -> OrgParser ()) + -> OrgParser () +endsOnThisLine input c doOnOtherLines = do + case break (`elem` c:"\n") input of + (_,'\n':rest) -> doOnOtherLines rest + (_,_:rest@(n:_)) -> if n `elem` postWordChars + then return () + else endsOnThisLine rest c doOnOtherLines + _ -> mzero + diff --git a/src/Text/Pandoc/Readers/RST.hs b/src/Text/Pandoc/Readers/RST.hs index 32893128a..127eae167 100644 --- a/src/Text/Pandoc/Readers/RST.hs +++ b/src/Text/Pandoc/Readers/RST.hs @@ -36,12 +36,13 @@ import Text.Pandoc.Builder (setMeta, fromList) import Text.Pandoc.Shared import Text.Pandoc.Parsing import Text.Pandoc.Options -import Control.Monad ( when, liftM, guard, mzero ) +import Control.Monad ( when, liftM, guard, mzero, mplus ) import Data.List ( findIndex, intersperse, intercalate, transpose, sort, deleteFirstsBy, isSuffixOf ) +import Data.Maybe (fromMaybe) import qualified Data.Map as M import Text.Printf ( printf ) -import Control.Applicative ((<$>), (<$), (<*), (*>)) +import Control.Applicative ((<$>), (<$), (<*), (*>), (<*>)) import Text.Pandoc.Builder (Inlines, Blocks, trimInlines, (<>)) import qualified Text.Pandoc.Builder as B import Data.Monoid (mconcat, mempty) @@ -347,14 +348,25 @@ lhsCodeBlock = try $ do getPosition >>= guard . (==1) . sourceColumn guardEnabled Ext_literate_haskell optional codeBlockStart - lns <- many1 birdTrackLine - -- if (as is normal) there is always a space after >, drop it - let lns' = if all (\ln -> null ln || take 1 ln == " ") lns - then map (drop 1) lns - else lns + lns <- latexCodeBlock <|> birdCodeBlock blanklines return $ B.codeBlockWith ("", ["sourceCode", "literate", "haskell"], []) - $ intercalate "\n" lns' + $ intercalate "\n" lns + +latexCodeBlock :: Parser [Char] st [[Char]] +latexCodeBlock = try $ do + try (latexBlockLine "\\begin{code}") + many1Till anyLine (try $ latexBlockLine "\\end{code}") + where + latexBlockLine s = skipMany spaceChar >> string s >> blankline + +birdCodeBlock :: Parser [Char] st [[Char]] +birdCodeBlock = filterSpace <$> many1 birdTrackLine + where filterSpace lns = + -- if (as is normal) there is always a space after >, drop it + if all (\ln -> null ln || take 1 ln == " ") lns + then map (drop 1) lns + else lns birdTrackLine :: Parser [Char] st [Char] birdTrackLine = char '>' >> anyLine @@ -519,7 +531,7 @@ directive' = do 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) @@ -569,7 +581,7 @@ directive' = do "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 @@ -580,7 +592,38 @@ directive' = do Nothing -> B.image src "" alt _ -> return mempty --- Can contain haracter codes as decimal numbers or +-- TODO: +-- - Silently ignores illegal fields +-- - Silently drops classes +-- - 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 + baseRole <- case M.lookup parentRole customRoles of + Just (base, _, _) -> return base + Nothing -> return parentRole + + let fmt = if baseRole == "raw" then lookup "format" fields else Nothing + annotate = maybe id addLanguage $ + if baseRole == "code" + then lookup "language" fields + else Nothing + + updateState $ \s -> s { + stateRstCustomRoles = + M.insert role (baseRole, fmt, (,) parentRole . annotate) customRoles + } + + return $ B.singleton Null + where + addLanguage lang (ident, classes, keyValues) = + (ident, "sourceCode" : lang : classes, keyValues) + inheritedRole = + (,) <$> roleNameEndingIn (char '(') <*> roleNameEndingIn (char ')') + +-- Can contain character codes as decimal numbers or -- hexadecimal numbers, prefixed by 0x, x, \x, U+, u, or \u -- or as XML-style hexadecimal character entities, e.g. ᨫ -- or text, which is used as-is. Comments start with .. @@ -919,17 +962,56 @@ strong = B.strong . trimInlines . mconcat <$> -- 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.str contents + "math" -> return $ B.math contents + "title-reference" -> titleRef contents + "title" -> titleRef contents + "t" -> titleRef contents + "code" -> return $ B.codeWith attr contents + "raw" -> return $ B.rawInline (fromMaybe "" fmt) contents + custom -> do + customRole <- stateRstCustomRoles <$> getState + case M.lookup custom customRole of + Just (_, newFmt, inherit) -> let + fmtStr = fmt `mplus` newFmt + (newRole, newAttr) = inherit attr + in renderRole contents fmtStr newRole newAttr + Nothing -> 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://http://www.python.org/dev/peps/pep-" ++ padNo ++ "/" + +roleNameEndingIn :: RSTParser Char -> RSTParser String +roleNameEndingIn end = many1Till (letter <|> char '-') end roleMarker :: RSTParser String -roleMarker = char ':' *> many1Till (letter <|> char '-') (char ':') +roleMarker = char ':' *> roleNameEndingIn (char ':') roleBefore :: RSTParser (String,String) roleBefore = try $ do diff --git a/src/Text/Pandoc/Readers/Textile.hs b/src/Text/Pandoc/Readers/Textile.hs index 23e07f621..93658cdea 100644 --- a/src/Text/Pandoc/Readers/Textile.hs +++ b/src/Text/Pandoc/Readers/Textile.hs @@ -594,7 +594,7 @@ surrounded border = enclosed (border *> notFollowedBy (oneOf " \t\n\r")) (try bo 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) >>= +simpleInline border construct = surrounded border inlineWithAttribute >>= return . construct . normalizeSpaces where inlineWithAttribute = (try $ optional attributes) >> inline diff --git a/src/Text/Pandoc/Shared.hs b/src/Text/Pandoc/Shared.hs index 7592b7659..714402e42 100644 --- a/src/Text/Pandoc/Shared.hs +++ b/src/Text/Pandoc/Shared.hs @@ -91,7 +91,8 @@ import Data.Char ( toLower, isLower, isUpper, isAlpha, isLetter, isDigit, isSpace ) import Data.List ( find, isPrefixOf, intercalate ) import qualified Data.Map as M -import Network.URI ( escapeURIString, isURI, unEscapeString ) +import Network.URI ( escapeURIString, isURI, nonStrictRelativeTo, + unEscapeString, parseURIReference ) import System.Directory import Text.Pandoc.MIME (getMimeType) import System.FilePath ( (</>), takeExtension, dropExtension ) @@ -121,6 +122,7 @@ import Data.ByteString.Lazy (toChunks) import Network.HTTP.Conduit (httpLbs, parseUrl, withManager, responseBody, responseHeaders) import Network.HTTP.Types.Header ( hContentType) +import Network (withSocketsDo) #else import Network.URI (parseURI) import Network.HTTP (findHeader, rspBody, @@ -531,7 +533,7 @@ headerShift n = walk shift -- | Detect if a list is tight. isTightList :: [[Block]] -> Bool -isTightList = and . map firstIsPlain +isTightList = all firstIsPlain where firstIsPlain (Plain _ : _) = True firstIsPlain _ = False @@ -563,14 +565,10 @@ makeMeta title authors date = -- | Render HTML tags. renderTags' :: [Tag String] -> String renderTags' = renderTagsOptions - renderOptions{ optMinimize = \x -> - let y = map toLower x - in y == "hr" || y == "br" || - y == "img" || y == "meta" || - y == "link" - , optRawTag = \x -> - let y = map toLower x - in y == "script" || y == "style" } + renderOptions{ optMinimize = matchTags ["hr", "br", "img", + "meta", "link"] + , optRawTag = matchTags ["script", "style"] } + where matchTags = \tags -> flip elem tags . map toLower -- -- File handling @@ -626,9 +624,13 @@ fetchItem :: Maybe String -> String -> IO (Either E.SomeException (BS.ByteString, Maybe String)) fetchItem sourceURL s | isURI s = openURL s - | otherwise = case sourceURL of - Just u -> openURL (u ++ "/" ++ s) - Nothing -> E.try readLocalFile + | 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 where readLocalFile = do let mime = case takeExtension s of ".gz" -> getMimeType $ dropExtension s @@ -644,7 +646,7 @@ openURL u contents = B8.pack $ unEscapeString $ drop 1 $ dropWhile (/=',') u in return $ Right (decodeLenient contents, Just mime) #ifdef HTTP_CONDUIT - | otherwise = E.try $ do + | otherwise = withSocketsDo $ E.try $ do req <- parseUrl u resp <- withManager $ httpLbs req return (BS.concat $ toChunks $ responseBody resp, diff --git a/src/Text/Pandoc/Writers/Docx.hs b/src/Text/Pandoc/Writers/Docx.hs index 5c7341b69..2a834c2da 100644 --- a/src/Text/Pandoc/Writers/Docx.hs +++ b/src/Text/Pandoc/Writers/Docx.hs @@ -29,7 +29,8 @@ 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.List ( intercalate, groupBy ) +import Data.Maybe (fromMaybe) +import Data.List ( intercalate, isPrefixOf, isSuffixOf ) import qualified Data.ByteString as B import qualified Data.ByteString.Lazy as BL import qualified Data.ByteString.Lazy.Char8 as BL8 @@ -42,6 +43,7 @@ import Text.Pandoc.Definition import Text.Pandoc.Generic import Text.Pandoc.ImageSize import Text.Pandoc.Shared hiding (Element) +import Text.Pandoc.Writers.Shared (fixDisplayMath) import Text.Pandoc.Options import Text.Pandoc.Readers.TeXMath import Text.Pandoc.Highlighting ( highlight ) @@ -130,7 +132,8 @@ writeDocx opts doc@(Pandoc meta _) = do let mkOverrideNode (part', contentType') = mknode "Override" [("PartName",part'),("ContentType",contentType')] () let mkImageOverride (_, imgpath, mbMimeType, _, _) = - mkOverrideNode ("/word/" ++ imgpath, maybe "application/octet-stream" id mbMimeType) + mkOverrideNode ("/word/" ++ imgpath, + fromMaybe "application/octet-stream" mbMimeType) let overrides = map mkOverrideNode [("/word/webSettings.xml", "application/vnd.openxmlformats-officedocument.wordprocessingml.webSettings+xml") @@ -260,6 +263,12 @@ writeDocx opts doc@(Pandoc meta _) = do 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 -- Create archive let archive = foldr addEntryToArchive emptyArchive $ @@ -267,7 +276,7 @@ writeDocx opts doc@(Pandoc meta _) = do footnoteRelEntry : numEntry : styleEntry : footnotesEntry : docPropsEntry : docPropsAppEntry : themeEntry : fontTableEntry : settingsEntry : webSettingsEntry : - imageEntries + imageEntries ++ miscRelEntries return $ fromArchive archive styleToOpenXml :: Style -> [Element] @@ -322,7 +331,7 @@ mkNum markers marker numid = NumberMarker _ _ start -> map (\lvl -> mknode "w:lvlOverride" [("w:ilvl",show (lvl :: Int))] $ mknode "w:startOverride" [("w:val",show start)] ()) [0..6] - where absnumid = maybe 0 id $ M.lookup marker markers + where absnumid = fromMaybe 0 $ M.lookup marker markers mkAbstractNum :: (ListMarker,Int) -> IO Element mkAbstractNum (marker,numid) = do @@ -807,30 +816,8 @@ br = mknode "w:r" [] [mknode "w:br" [("w:type","textWrapping")] () ] parseXml :: Archive -> String -> IO Element parseXml refArchive relpath = - case (findEntryByPath relpath refArchive >>= parseXMLDoc . UTF8.toStringLazy . fromEntry) of - Just d -> return d + 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" - -isDisplayMath :: Inline -> Bool -isDisplayMath (Math DisplayMath _) = True -isDisplayMath _ = False - -stripLeadingTrailingSpace :: [Inline] -> [Inline] -stripLeadingTrailingSpace = go . reverse . go . reverse - where go (Space:xs) = xs - go xs = xs - -fixDisplayMath :: Block -> Block -fixDisplayMath (Plain lst) - | any isDisplayMath lst && not (all isDisplayMath lst) = - -- chop into several paragraphs so each displaymath is its own - Div ("",["math"],[]) $ map (Plain . stripLeadingTrailingSpace) $ - groupBy (\x y -> (isDisplayMath x && isDisplayMath y) || - not (isDisplayMath x || isDisplayMath y)) lst -fixDisplayMath (Para lst) - | any isDisplayMath lst && not (all isDisplayMath lst) = - -- chop into several paragraphs so each displaymath is its own - Div ("",["math"],[]) $ map (Para . stripLeadingTrailingSpace) $ - groupBy (\x y -> (isDisplayMath x && isDisplayMath y) || - not (isDisplayMath x || isDisplayMath y)) lst -fixDisplayMath x = x diff --git a/src/Text/Pandoc/Writers/EPUB.hs b/src/Text/Pandoc/Writers/EPUB.hs index 59c90b16d..a48300939 100644 --- a/src/Text/Pandoc/Writers/EPUB.hs +++ b/src/Text/Pandoc/Writers/EPUB.hs @@ -38,7 +38,7 @@ import Text.Printf (printf) import System.FilePath ( (</>), takeBaseName, takeExtension, takeFileName ) import qualified Data.ByteString.Lazy as B import qualified Data.ByteString.Lazy.Char8 as B8 -import Text.Pandoc.UTF8 ( fromStringLazy, toString ) +import qualified Text.Pandoc.UTF8 as UTF8 import Text.Pandoc.SelfContained ( makeSelfContained ) import Codec.Archive.Zip import Control.Applicative ((<$>)) @@ -89,8 +89,13 @@ data EPUBMetadata = EPUBMetadata{ , epubCoverage :: Maybe String , epubRights :: Maybe String , epubCoverImage :: Maybe String + , epubStylesheet :: Maybe Stylesheet } deriving Show +data Stylesheet = StylesheetPath FilePath + | StylesheetContents String + deriving Show + data Creator = Creator{ creatorText :: String , creatorRole :: Maybe String @@ -119,7 +124,12 @@ opfName n = QName n Nothing (Just "opf") plainify :: [Inline] -> String plainify t = - trimr $ writePlain def{ writerStandalone = False } $ Pandoc nullMeta [Plain t] + trimr $ writePlain def{ writerStandalone = False } + $ Pandoc nullMeta [Plain $ walk removeNote t] + +removeNote :: Inline -> Inline +removeNote (Note _) = Str "" +removeNote x = x getEPUBMetadata :: WriterOptions -> Meta -> IO EPUBMetadata getEPUBMetadata opts meta = do @@ -171,8 +181,8 @@ addMetadataFromXML e@(Element (QName name _ (Just "dc")) attrs _ _) md , titleFileAs = getAttr "file-as" , titleType = getAttr "type" } : epubTitle md } - | name == "date" = md{ epubDate = maybe "" id $ normalizeDate' - $ strContent e } + | name == "date" = md{ epubDate = fromMaybe "" $ normalizeDate' + $ strContent e } | name == "language" = md{ epubLanguage = strContent e } | name == "creator" = md{ epubCreator = Creator{ creatorText = strContent e @@ -262,10 +272,11 @@ metadataFromMeta opts meta = EPUBMetadata{ , epubCoverage = coverage , epubRights = rights , epubCoverImage = coverImage + , epubStylesheet = stylesheet } where identifiers = getIdentifier meta titles = getTitle meta - date = maybe "" id $ + date = fromMaybe "" $ (metaValueToString <$> lookupMeta "date" meta) >>= normalizeDate' language = maybe "" metaValueToString $ lookupMeta "language" meta `mplus` lookupMeta "lang" meta @@ -282,13 +293,16 @@ metadataFromMeta opts meta = EPUBMetadata{ rights = metaValueToString <$> lookupMeta "rights" meta coverImage = lookup "epub-cover-image" (writerVariables opts) `mplus` (metaValueToString <$> lookupMeta "cover-image" meta) + stylesheet = (StylesheetContents <$> writerEpubStylesheet opts) `mplus` + ((StylesheetPath . metaValueToString) <$> + lookupMeta "stylesheet" meta) -- | Produce an EPUB file from a Pandoc document. writeEPUB :: WriterOptions -- ^ Writer options -> Pandoc -- ^ Document to convert -> IO B.ByteString writeEPUB opts doc@(Pandoc meta _) = do - let version = maybe EPUB2 id (writerEpubVersion opts) + let version = fromMaybe EPUB2 (writerEpubVersion opts) let epub3 = version == EPUB3 epochtime <- floor `fmap` getPOSIXTime let mkEntry path content = toEntry path epochtime content @@ -392,10 +406,12 @@ writeEPUB opts doc@(Pandoc meta _) = do chapToEntry num (Chapter mbnum bs) = mkEntry (showChapter num) $ renderHtml $ writeHtml opts'{ writerNumberOffset = - maybe [] id mbnum } + fromMaybe [] mbnum } $ case bs of (Header _ _ xs : _) -> - Pandoc (setMeta "title" (fromList xs) nullMeta) bs + -- remove notes or we get doubled footnotes + Pandoc (setMeta "title" (walk removeNote $ fromList xs) + nullMeta) bs _ -> Pandoc nullMeta bs @@ -427,7 +443,7 @@ writeEPUB opts doc@(Pandoc meta _) = do let fontNode ent = unode "item" ! [("id", takeBaseName $ eRelativePath ent), ("href", eRelativePath ent), - ("media-type", maybe "" id $ getMimeType $ eRelativePath ent)] $ () + ("media-type", fromMaybe "" $ getMimeType $ eRelativePath ent)] $ () let plainTitle = case docTitle meta of [] -> case epubTitle metadata of [] -> "UNTITLED" @@ -437,7 +453,7 @@ writeEPUB opts doc@(Pandoc meta _) = do (x:_) -> identifierText x -- use first identifier as UUID [] -> error "epubIdentifier is null" -- shouldn't happen currentTime <- getCurrentTime - let contentsData = fromStringLazy $ ppTopElement $ + let contentsData = UTF8.fromStringLazy $ ppTopElement $ unode "package" ! [("version", case version of EPUB2 -> "2.0" EPUB3 -> "3.0") @@ -525,7 +541,7 @@ writeEPUB opts doc@(Pandoc meta _) = do [ unode "navLabel" $ unode "text" (plainify $ docTitle meta) , unode "content" ! [("src","title_page.xhtml")] $ () ] - let tocData = fromStringLazy $ ppTopElement $ + let tocData = UTF8.fromStringLazy $ ppTopElement $ unode "ncx" ! [("version","2005-1") ,("xmlns","http://www.daisy.org/z3986/2005/ncx/")] $ [ unode "head" $ @@ -557,7 +573,7 @@ writeEPUB opts doc@(Pandoc meta _) = do (_:_) -> [unode "ol" ! [("class","toc")] $ subs] let navtag = if epub3 then "nav" else "div" - let navData = fromStringLazy $ ppTopElement $ + let navData = UTF8.fromStringLazy $ ppTopElement $ unode "html" ! [("xmlns","http://www.w3.org/1999/xhtml") ,("xmlns:epub","http://www.idpf.org/2007/ops")] $ [ unode "head" $ @@ -571,10 +587,10 @@ writeEPUB opts doc@(Pandoc meta _) = do let navEntry = mkEntry "nav.xhtml" navData -- mimetype - let mimetypeEntry = mkEntry "mimetype" $ fromStringLazy "application/epub+zip" + let mimetypeEntry = mkEntry "mimetype" $ UTF8.fromStringLazy "application/epub+zip" -- container.xml - let containerData = fromStringLazy $ ppTopElement $ + let containerData = UTF8.fromStringLazy $ ppTopElement $ unode "container" ! [("version","1.0") ,("xmlns","urn:oasis:names:tc:opendocument:xmlns:container")] $ unode "rootfiles" $ @@ -583,18 +599,19 @@ writeEPUB opts doc@(Pandoc meta _) = do let containerEntry = mkEntry "META-INF/container.xml" containerData -- com.apple.ibooks.display-options.xml - let apple = fromStringLazy $ ppTopElement $ + let apple = UTF8.fromStringLazy $ ppTopElement $ unode "display_options" $ unode "platform" ! [("name","*")] $ unode "option" ! [("name","specified-fonts")] $ "true" let appleEntry = mkEntry "META-INF/com.apple.ibooks.display-options.xml" apple -- stylesheet - stylesheet <- case writerEpubStylesheet opts of - Just s -> return s - Nothing -> toString `fmap` + stylesheet <- case epubStylesheet metadata of + Just (StylesheetPath fp) -> UTF8.readFile fp + Just (StylesheetContents s) -> return s + Nothing -> UTF8.toString `fmap` readDataFile (writerUserDataDir opts) "epub.css" - let stylesheetEntry = mkEntry "stylesheet.css" $ fromStringLazy stylesheet + let stylesheetEntry = mkEntry "stylesheet.css" $ UTF8.fromStringLazy stylesheet -- construct archive let archive = foldr addEntryToArchive emptyArchive diff --git a/src/Text/Pandoc/Writers/FB2.hs b/src/Text/Pandoc/Writers/FB2.hs index adbe948be..803617f95 100644 --- a/src/Text/Pandoc/Writers/FB2.hs +++ b/src/Text/Pandoc/Writers/FB2.hs @@ -44,7 +44,7 @@ import qualified Text.XML.Light.Cursor as XC import Text.Pandoc.Definition import Text.Pandoc.Options (WriterOptions(..), HTMLMathMethod(..), def) -import Text.Pandoc.Shared (orderedListMarkers) +import Text.Pandoc.Shared (orderedListMarkers, isHeaderBlock) import Text.Pandoc.Walk -- | Data to be written at the end of the document: @@ -157,9 +157,7 @@ renderSection level (ttl, body) = do else cMapM blockToXml body return $ el "section" (title ++ content) where - hasSubsections = any isHeader - isHeader (Header _ _ _) = True - isHeader _ = False + hasSubsections = any isHeaderBlock -- | Only <p> and <empty-line> are allowed within <title> in FB2. formatTitle :: [Inline] -> [Content] diff --git a/src/Text/Pandoc/Writers/HTML.hs b/src/Text/Pandoc/Writers/HTML.hs index 641652276..3ac2a836f 100644 --- a/src/Text/Pandoc/Writers/HTML.hs +++ b/src/Text/Pandoc/Writers/HTML.hs @@ -45,7 +45,7 @@ import Numeric ( showHex ) import Data.Char ( ord, toLower ) import Data.List ( isPrefixOf, intersperse ) import Data.String ( fromString ) -import Data.Maybe ( catMaybes ) +import Data.Maybe ( catMaybes, fromMaybe ) import Control.Monad.State import Text.Blaze.Html hiding(contents) import Text.Blaze.Internal(preEscapedString) @@ -118,7 +118,7 @@ pandocToHtml opts (Pandoc meta blocks) = do let stringifyHTML = escapeStringForXML . stringify let authsMeta = map stringifyHTML $ docAuthors meta let dateMeta = stringifyHTML $ docDate meta - let slideLevel = maybe (getSlideLevel blocks) id $ writerSlideLevel opts + let slideLevel = fromMaybe (getSlideLevel blocks) $ writerSlideLevel opts let sects = hierarchicalize $ if writerSlideVariant opts == NoSlides then blocks @@ -475,28 +475,22 @@ blockToHtml opts (BlockQuote blocks) = else do contents <- blockListToHtml opts blocks return $ H.blockquote $ nl opts >> contents >> nl opts -blockToHtml opts (Header level (ident,_,_) lst) = do +blockToHtml opts (Header level (_,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 - let revealSlash = ['/' | writerSlideVariant opts == RevealJsSlides] - let contents'' = if writerTableOfContents opts && not (null ident) - then H.a ! A.href (toValue $ - '#' : revealSlash ++ - writerIdentifierPrefix opts ++ - ident) $ contents' - else contents' return $ case level of - 1 -> H.h1 contents'' - 2 -> H.h2 contents'' - 3 -> H.h3 contents'' - 4 -> H.h4 contents'' - 5 -> H.h5 contents'' - 6 -> H.h6 contents'' - _ -> H.p contents'' + 1 -> H.h1 contents' + 2 -> H.h2 contents' + 3 -> H.h3 contents' + 4 -> H.h4 contents' + 5 -> H.h5 contents' + 6 -> H.h6 contents' + _ -> H.p contents' blockToHtml opts (BulletList lst) = do contents <- mapM (blockListToHtml opts) lst return $ unordList opts contents @@ -524,7 +518,7 @@ blockToHtml opts (DefinitionList lst) = do contents <- mapM (\(term, defs) -> do term' <- if null term then return mempty - else liftM (H.dt) $ inlineListToHtml opts term + else liftM H.dt $ inlineListToHtml opts term defs' <- mapM ((liftM (\x -> H.dd $ (x >> nl opts))) . blockListToHtml opts) defs return $ mconcat $ nl opts : term' : nl opts : @@ -756,7 +750,9 @@ inlineToHtml opts inline = else [A.title $ toValue tit]) return $ foldl (!) H5.embed attributes -- note: null title included, as in Markdown.pl - (Note contents) -> do + (Note contents) + | writerIgnoreNotes opts -> return mempty + | otherwise -> do st <- get let notes = stNotes st let number = (length notes) + 1 diff --git a/src/Text/Pandoc/Writers/LaTeX.hs b/src/Text/Pandoc/Writers/LaTeX.hs index f3cbcf19f..b2eff4490 100644 --- a/src/Text/Pandoc/Writers/LaTeX.hs +++ b/src/Text/Pandoc/Writers/LaTeX.hs @@ -40,6 +40,7 @@ import Network.URI ( isURI, unEscapeString ) import Data.List ( (\\), isSuffixOf, isInfixOf, isPrefixOf, intercalate, intersperse ) import Data.Char ( toLower, isPunctuation, isAscii, isLetter, isDigit, ord ) +import Data.Maybe ( fromMaybe ) import Control.Applicative ((<|>)) import Control.Monad.State import Text.Pandoc.Pretty @@ -50,6 +51,8 @@ import Text.Pandoc.Highlighting (highlight, styleToLaTeX, data WriterState = WriterState { stInNote :: Bool -- true if we're in a note + , stInMinipage :: Bool -- true if in minipage + , 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 , stVerbInNote :: Bool -- true if document has verbatim text in note @@ -70,7 +73,7 @@ data WriterState = writeLaTeX :: WriterOptions -> Pandoc -> String writeLaTeX options document = evalState (pandocToLaTeX options document) $ - WriterState { stInNote = False, + WriterState { stInNote = False, stInMinipage = False, stNotes = [], stOLLevel = 1, stOptions = options, stVerbInNote = False, stTable = False, stStrikeout = False, @@ -188,7 +191,7 @@ stringToLaTeX _ [] = return "" stringToLaTeX ctx (x:xs) = do opts <- gets stOptions rest <- stringToLaTeX ctx xs - let ligatures = writerTeXLigatures opts && not (ctx == CodeString) + let ligatures = writerTeXLigatures opts && (ctx /= CodeString) let isUrl = ctx == URLString when (x == '€') $ modify $ \st -> st{ stUsesEuro = True } @@ -203,7 +206,7 @@ stringToLaTeX ctx (x:xs) = do '_' | not isUrl -> "\\_" ++ rest '#' -> "\\#" ++ rest '-' -> case xs of -- prevent adjacent hyphens from forming ligatures - ('-':_) -> "-{}" ++ rest + ('-':_) -> "-\\/" ++ rest _ -> '-' : rest '~' | not isUrl -> "\\textasciitilde{}" ++ rest '^' -> "\\^{}" ++ rest @@ -238,7 +241,7 @@ inCmd cmd contents = char '\\' <> text cmd <> braces contents toSlides :: [Block] -> State WriterState [Block] toSlides bs = do opts <- gets stOptions - let slideLevel = maybe (getSlideLevel bs) id $ writerSlideLevel opts + let slideLevel = fromMaybe (getSlideLevel bs) $ writerSlideLevel opts let bs' = prepSlides slideLevel bs concat `fmap` (mapM (elementToBeamer slideLevel) $ hierarchicalize bs') @@ -441,7 +444,7 @@ blockToLaTeX (DefinitionList lst) = do incremental <- gets stIncremental let inc = if incremental then "[<+->]" else "" items <- mapM defListItemToLaTeX lst - let spacing = if and $ map isTightList (map snd lst) + let spacing = if all isTightList (map snd lst) then text "\\itemsep1pt\\parskip0pt\\parsep0pt" else empty return $ text ("\\begin{description}" ++ inc) $$ spacing $$ vcat items $$ @@ -453,12 +456,12 @@ blockToLaTeX (Header level (id',classes,_) lst) = blockToLaTeX (Table caption aligns widths heads rows) = do headers <- if all null heads then return empty - else ($$ "\\hline\\noalign{\\medskip}") `fmap` + else ($$ "\\midrule\\endhead") `fmap` (tableRowToLaTeX True aligns widths) heads captionText <- inlineListToLaTeX caption let capt = if isEmpty captionText then empty - else text "\\noalign{\\medskip}" + else text "\\addlinespace" $$ text "\\caption" <> braces captionText rows' <- mapM (tableRowToLaTeX False aligns widths) rows let colDescriptors = text $ concat $ map toColDescriptor aligns @@ -466,10 +469,10 @@ blockToLaTeX (Table caption aligns widths heads rows) = do return $ "\\begin{longtable}[c]" <> braces ("@{}" <> colDescriptors <> "@{}") -- the @{} removes extra space at beginning and end - $$ "\\hline\\noalign{\\medskip}" + $$ "\\toprule\\addlinespace" $$ headers $$ vcat rows' - $$ "\\hline" + $$ "\\bottomrule" $$ capt $$ "\\end{longtable}" @@ -490,23 +493,42 @@ tableRowToLaTeX :: Bool -> [[Block]] -> State WriterState Doc tableRowToLaTeX header aligns widths cols = do - renderedCells <- mapM blockListToLaTeX cols - let valign = text $ if header then "[b]" else "[t]" - let halign x = case x of - AlignLeft -> "\\raggedright" - AlignRight -> "\\raggedleft" - AlignCenter -> "\\centering" - AlignDefault -> "\\raggedright" -- scale factor compensates for extra space between columns -- so the whole table isn't larger than columnwidth let scaleFactor = 0.97 ** fromIntegral (length aligns) - let toCell 0 _ c = c - toCell w a c = "\\begin{minipage}" <> valign <> - braces (text (printf "%.2f\\columnwidth" - (w * scaleFactor))) <> - (halign a <> cr <> c <> cr) <> "\\end{minipage}" - let cells = zipWith3 toCell widths aligns renderedCells - return $ hsep (intersperse "&" cells) $$ "\\\\\\noalign{\\medskip}" + let widths' = map (scaleFactor *) widths + cells <- mapM (tableCellToLaTeX header) $ zip3 widths' aligns cols + return $ hsep (intersperse "&" cells) $$ "\\\\\\addlinespace" + +tableCellToLaTeX :: Bool -> (Double, Alignment, [Block]) + -> State WriterState Doc +tableCellToLaTeX _ (0, _, blocks) = blockListToLaTeX blocks +tableCellToLaTeX header (width, align, blocks) = do + modify $ \st -> st{ stInMinipage = True, stNotes = [] } + cellContents <- blockListToLaTeX blocks + notes <- gets stNotes + modify $ \st -> st{ stInMinipage = False, stNotes = [] } + let valign = text $ if header then "[b]" else "[t]" + let halign = case align of + AlignLeft -> "\\raggedright" + AlignRight -> "\\raggedleft" + AlignCenter -> "\\centering" + AlignDefault -> "\\raggedright" + return $ ("\\begin{minipage}" <> valign <> + braces (text (printf "%.2f\\columnwidth" width)) <> + (halign <> cr <> cellContents <> cr) <> "\\end{minipage}") + $$ case notes of + [] -> empty + ns -> (case length ns of + n | n > 1 -> "\\addtocounter" <> + braces "footnote" <> + braces (text $ show $ 1 - n) + | otherwise -> empty) + $$ + vcat (intersperse + ("\\addtocounter" <> braces "footnote" <> braces "1") + $ map (\x -> "\\footnotetext" <> braces x) + $ reverse ns) listItemToLaTeX :: [Block] -> State WriterState Doc listItemToLaTeX lst = blockListToLaTeX lst >>= return . (text "\\item" $$) . @@ -709,14 +731,20 @@ inlineToLaTeX (Image _ (source, _)) = do source'' <- stringToLaTeX URLString source' return $ "\\includegraphics" <> braces (text source'') inlineToLaTeX (Note contents) = do + inMinipage <- gets stInMinipage modify (\s -> s{stInNote = True}) contents' <- blockListToLaTeX contents modify (\s -> s {stInNote = False}) let optnl = case reverse contents of (CodeBlock _ _ : _) -> cr _ -> empty - return $ "\\footnote" <> braces (nest 2 contents' <> optnl) - -- note: a \n before } needed when note ends with a Verbatim environment + let noteContents = nest 2 contents' <> optnl + 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 citationsToNatbib :: [Citation] -> State WriterState Doc citationsToNatbib (one:[]) @@ -737,9 +765,9 @@ citationsToNatbib cits | noPrefix (tail cits) && noSuffix (init cits) && ismode NormalCitation cits = citeCommand "citep" p s ks where - noPrefix = and . map (null . citationPrefix) - noSuffix = and . map (null . citationSuffix) - ismode m = and . map (((==) m) . citationMode) + noPrefix = all (null . citationPrefix) + noSuffix = all (null . citationSuffix) + ismode m = all (((==) m) . citationMode) p = citationPrefix $ head $ cits s = citationSuffix $ last $ cits ks = intercalate ", " $ map citationId cits diff --git a/src/Text/Pandoc/Writers/Markdown.hs b/src/Text/Pandoc/Writers/Markdown.hs index 60d474263..278e5cc9d 100644 --- a/src/Text/Pandoc/Writers/Markdown.hs +++ b/src/Text/Pandoc/Writers/Markdown.hs @@ -338,7 +338,7 @@ blockToMarkdown opts (RawBlock f str) else return $ if isEnabled Ext_markdown_attribute opts then text (addMarkdownAttribute str) <> text "\n" else text str <> text "\n" - | f == "latex" || f == "tex" || f == "markdown" = do + | f `elem` ["latex", "tex", "markdown"] = do st <- get if stPlain st then return empty @@ -381,13 +381,11 @@ blockToMarkdown opts (CodeBlock (_,classes,_) str) isEnabled Ext_literate_haskell opts = return $ prefixed "> " (text str) <> blankline blockToMarkdown opts (CodeBlock attribs str) = return $ - case attribs of - x | x /= nullAttr && isEnabled Ext_fenced_code_blocks opts -> - tildes <> " " <> attrs <> cr <> text str <> - cr <> tildes <> blankline - (_,(cls:_),_) | isEnabled Ext_backtick_code_blocks opts -> - backticks <> " " <> text cls <> cr <> text str <> - cr <> backticks <> blankline + case attribs == nullAttr of + False | isEnabled Ext_backtick_code_blocks opts -> + backticks <> attrs <> cr <> text str <> cr <> backticks <> blankline + | isEnabled Ext_fenced_code_blocks opts -> + tildes <> attrs <> cr <> text str <> cr <> tildes <> blankline _ -> nest (writerTabStop opts) (text str) <> blankline where tildes = text $ case [ln | ln <- lines str, all (=='~') ln] of [] -> "~~~~" @@ -396,8 +394,10 @@ blockToMarkdown opts (CodeBlock attribs str) = return $ | otherwise -> replicate (n+1) '~' backticks = text "```" attrs = if isEnabled Ext_fenced_code_attributes opts - then nowrap $ attrsToMarkdown attribs - else empty + then nowrap $ " " <> attrsToMarkdown attribs + else case attribs of + (_,[cls],_) -> " " <> text cls + _ -> empty blockToMarkdown opts (BlockQuote blocks) = do st <- get -- if we're writing literate haskell, put a space before the bird tracks @@ -628,10 +628,11 @@ getReference label (src, tit) = do Nothing -> do let label' = case find ((== label) . fst) (stRefs st) of Just _ -> -- label is used; generate numerical label - case find (\n -> not (any (== [Str (show n)]) - (map fst (stRefs st)))) [1..(10000 :: Integer)] of - Just x -> [Str (show x)] - Nothing -> error "no unique label" + case find (\n -> notElem [Str (show n)] + (map fst (stRefs st))) + [1..(10000 :: Integer)] of + Just x -> [Str (show x)] + Nothing -> error "no unique label" Nothing -> label modify (\s -> s{ stRefs = (label', (src,tit)) : stRefs st }) return label' diff --git a/src/Text/Pandoc/Writers/MediaWiki.hs b/src/Text/Pandoc/Writers/MediaWiki.hs index 61741a61e..83fefaa29 100644 --- a/src/Text/Pandoc/Writers/MediaWiki.hs +++ b/src/Text/Pandoc/Writers/MediaWiki.hs @@ -51,7 +51,7 @@ data WriterState = WriterState { writeMediaWiki :: WriterOptions -> Pandoc -> String writeMediaWiki opts document = evalState (pandocToMediaWiki opts document) - (WriterState { stNotes = False, stListLevel = [], stUseTags = False }) + WriterState { stNotes = False, stListLevel = [], stUseTags = False } -- | Return MediaWiki representation of document. pandocToMediaWiki :: WriterOptions -> Pandoc -> State WriterState String diff --git a/src/Text/Pandoc/Writers/ODT.hs b/src/Text/Pandoc/Writers/ODT.hs index cc0a06243..c3652d65d 100644 --- a/src/Text/Pandoc/Writers/ODT.hs +++ b/src/Text/Pandoc/Writers/ODT.hs @@ -30,7 +30,10 @@ Conversion of 'Pandoc' documents to ODT. -} module Text.Pandoc.Writers.ODT ( writeODT ) where import Data.IORef -import Data.List ( isPrefixOf ) +import Data.List ( isPrefixOf, isSuffixOf ) +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 @@ -40,13 +43,14 @@ import Text.Pandoc.ImageSize ( imageSize, sizeInPoints ) import Text.Pandoc.MIME ( getMimeType ) import Text.Pandoc.Definition import Text.Pandoc.Walk +import Text.Pandoc.Writers.Shared ( fixDisplayMath ) import Text.Pandoc.Writers.OpenDocument ( writeOpenDocument ) import Control.Monad (liftM) import Text.Pandoc.XML import Text.Pandoc.Pretty import qualified Control.Exception as E import Data.Time.Clock.POSIX ( getPOSIXTime ) -import System.FilePath ( takeExtension ) +import System.FilePath ( takeExtension, takeDirectory ) -- | Produce an ODT file from a Pandoc document. writeODT :: WriterOptions -- ^ Writer options @@ -60,9 +64,9 @@ writeODT opts doc@(Pandoc meta _) = do Just f -> B.readFile f Nothing -> (B.fromChunks . (:[])) `fmap` readDataFile datadir "reference.odt" - -- handle pictures + -- handle formulas and pictures picEntriesRef <- newIORef ([] :: [Entry]) - doc' <- walkM (transformPic opts picEntriesRef) doc + doc' <- walkM (transformPicMath opts picEntriesRef) $ walk fixDisplayMath doc let newContents = writeOpenDocument opts{writerWrapText = False} doc' epochtime <- floor `fmap` getPOSIXTime let contentEntry = toEntry "content.xml" epochtime @@ -72,7 +76,11 @@ writeODT opts doc@(Pandoc meta _) = do $ contentEntry : picEntries -- construct META-INF/manifest.xml based on archive let toFileEntry fp = case getMimeType fp of - Nothing -> empty + 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 Just m -> selfClosingTag "manifest:file-entry" [("manifest:media-type", m) ,("manifest:full-path", fp) @@ -80,6 +88,8 @@ writeODT opts doc@(Pandoc meta _) = do ] let files = [ ent | ent <- filesInArchive archive, not ("META-INF" `isPrefixOf` ent) ] + let formulas = [ takeDirectory ent ++ "/" | ent <- filesInArchive archive, + "Formula-" `isPrefixOf` ent, takeExtension ent == ".xml" ] let manifestEntry = toEntry "META-INF/manifest.xml" epochtime $ fromStringLazy $ render Nothing $ text "<?xml version=\"1.0\" encoding=\"utf-8\"?>" @@ -91,6 +101,7 @@ writeODT opts doc@(Pandoc meta _) = do [("manifest:media-type","application/vnd.oasis.opendocument.text") ,("manifest:full-path","/")] $$ vcat ( map toFileEntry $ files ) + $$ vcat ( map toFileEntry $ formulas ) ) ) let archive' = addEntryToArchive manifestEntry archive @@ -118,8 +129,8 @@ writeODT opts doc@(Pandoc meta _) = do $ addEntryToArchive metaEntry archive' return $ fromArchive archive'' -transformPic :: WriterOptions -> IORef [Entry] -> Inline -> IO Inline -transformPic opts entriesRef (Image lab (src,_)) = do +transformPicMath :: WriterOptions -> IORef [Entry] -> Inline -> IO Inline +transformPicMath opts entriesRef (Image lab (src,_)) = do res <- fetchItem (writerSourceURL opts) src case res of Left (_ :: E.SomeException) -> do @@ -127,7 +138,7 @@ transformPic opts entriesRef (Image lab (src,_)) = do return $ Emph lab Right (img, _) -> do let size = imageSize img - let (w,h) = maybe (0,0) id $ sizeInPoints `fmap` size + 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 @@ -136,5 +147,29 @@ transformPic opts entriesRef (Image lab (src,_)) = do let entry = toEntry newsrc epochtime $ toLazy img modifyIORef entriesRef (entry:) return $ Image lab (newsrc, tit') -transformPic _ _ x = return x +transformPicMath _ entriesRef (Math t math) = do + entries <- readIORef entriesRef + let dt = if t == InlineMath then DisplayInline else DisplayBlock + case texMathToMathML dt math of + Left _ -> return $ Math t math + Right r -> do + let conf = useShortEmptyTags (const False) defaultConfigPP + let mathml = ppcTopElement conf r + epochtime <- floor `fmap` getPOSIXTime + let dirname = "Formula-" ++ show (length entries) ++ "/" + let fname = dirname ++ "content.xml" + let entry = toEntry fname epochtime (fromStringLazy mathml) + modifyIORef entriesRef (entry:) + return $ RawInline (Format "opendocument") $ render Nothing $ + inTags False "draw:frame" [("text:anchor-type", + if t == DisplayMath + then "paragraph" + else "as-char") + ,("style:vertical-pos", "middle") + ,("style:vertical-rel", "text")] $ + selfClosingTag "draw:object" [("xlink:href", dirname) + , ("xlink:type", "simple") + , ("xlink:show", "embed") + , ("xlink:actuate", "onLoad")] +transformPicMath _ _ x = return x diff --git a/src/Text/Pandoc/Writers/OpenDocument.hs b/src/Text/Pandoc/Writers/OpenDocument.hs index 4ddfd7166..0029c3296 100644 --- a/src/Text/Pandoc/Writers/OpenDocument.hs +++ b/src/Text/Pandoc/Writers/OpenDocument.hs @@ -285,8 +285,12 @@ blocksToOpenDocument o b = vcat <$> mapM (blockToOpenDocument o) b -- | Convert a Pandoc block element to OpenDocument. blockToOpenDocument :: WriterOptions -> Block -> State WriterState Doc blockToOpenDocument o bs - | Plain b <- bs = inParagraphTags =<< inlinesToOpenDocument o b - | Para b <- bs = inParagraphTags =<< inlinesToOpenDocument o b + | Plain b <- bs = if null b + then return empty + else inParagraphTags =<< inlinesToOpenDocument o b + | Para b <- bs = if null b + then return empty + else inParagraphTags =<< inlinesToOpenDocument o b | Div _ xs <- bs = blocksToOpenDocument o xs | Header i _ b <- bs = setFirstPara >> (inHeaderTags i =<< inlinesToOpenDocument o b) @@ -298,8 +302,8 @@ blockToOpenDocument o bs | Table c a w h r <- bs = setFirstPara >> table c a w h r | HorizontalRule <- bs = setFirstPara >> return (selfClosingTag "text:p" [ ("text:style-name", "Horizontal_20_Line") ]) - | RawBlock f s <- bs = if f == "opendocument" - then preformatted s + | RawBlock f s <- bs = if f == Format "opendocument" + then return $ text s else return empty | Null <- bs = return empty | otherwise = return empty @@ -378,8 +382,8 @@ inlineToOpenDocument o ils | Code _ s <- ils = withTextStyle Pre $ inTextStyle $ preformatted s | Math t s <- ils = inlinesToOpenDocument o (readTeXMath' t s) | Cite _ l <- ils = inlinesToOpenDocument o l - | RawInline f s <- ils = if f == "opendocument" - then return $ preformatted s + | RawInline f s <- ils = if f == Format "opendocument" + then return $ text s else return empty | Link l (s,t) <- ils = mkLink s t <$> inlinesToOpenDocument o l | Image _ (s,t) <- ils = mkImg s t diff --git a/src/Text/Pandoc/Writers/Org.hs b/src/Text/Pandoc/Writers/Org.hs index 51083f52b..d318c5f6a 100644 --- a/src/Text/Pandoc/Writers/Org.hs +++ b/src/Text/Pandoc/Writers/Org.hs @@ -129,7 +129,7 @@ blockToOrg (Para inlines) = do blockToOrg (RawBlock "html" str) = return $ blankline $$ "#+BEGIN_HTML" $$ nest 2 (text str) $$ "#+END_HTML" $$ blankline -blockToOrg (RawBlock f str) | f == "org" || f == "latex" || f == "tex" = +blockToOrg (RawBlock f str) | f `elem` ["org", "latex", "tex"] = return $ text str blockToOrg (RawBlock _ _) = return empty blockToOrg HorizontalRule = return $ blankline $$ "--------------" $$ blankline diff --git a/src/Text/Pandoc/Writers/RST.hs b/src/Text/Pandoc/Writers/RST.hs index 1a62f7250..37bb66632 100644 --- a/src/Text/Pandoc/Writers/RST.hs +++ b/src/Text/Pandoc/Writers/RST.hs @@ -287,7 +287,7 @@ definitionListItemToRST (label, defs) = do label' <- inlineListToRST label contents <- liftM vcat $ mapM blockListToRST defs tabstop <- get >>= (return . writerTabStop . stOptions) - return $ label' $$ nest tabstop (contents <> cr) + return $ label' $$ nest tabstop (nestle contents <> cr) -- | Convert list of Pandoc block elements to RST. blockListToRST :: [Block] -- ^ List of block elements diff --git a/src/Text/Pandoc/Writers/Shared.hs b/src/Text/Pandoc/Writers/Shared.hs index 9cb08803c..604aac1c9 100644 --- a/src/Text/Pandoc/Writers/Shared.hs +++ b/src/Text/Pandoc/Writers/Shared.hs @@ -34,6 +34,7 @@ module Text.Pandoc.Writers.Shared ( , setField , defField , tagWithAttrs + , fixDisplayMath ) where import Text.Pandoc.Definition @@ -46,6 +47,7 @@ import qualified Data.Map as M import qualified Data.Text as T import Data.Aeson (FromJSON(..), fromJSON, ToJSON (..), Value(Object), Result(..)) import qualified Data.Traversable as Traversable +import Data.List ( groupBy ) -- | Create JSON value for template from a 'Meta' and an association list -- of variables, specified at the command line or in the writer. @@ -65,8 +67,7 @@ metaToJSON opts blockWriter inlineWriter (Meta metamap) renderedMap <- Traversable.mapM (metaValueToJSON blockWriter inlineWriter) metamap - return $ M.foldWithKey (\key val obj -> defField key val obj) - baseContext renderedMap + return $ M.foldWithKey defField baseContext renderedMap | otherwise = return (Object H.empty) metaValueToJSON :: Monad m @@ -137,3 +138,28 @@ tagWithAttrs tag (ident,classes,kvs) = hsep ,hsep (map (\(k,v) -> text k <> "=" <> doubleQuotes (text (escapeStringForXML v))) kvs) ] <> ">" + +isDisplayMath :: Inline -> Bool +isDisplayMath (Math DisplayMath _) = True +isDisplayMath _ = False + +stripLeadingTrailingSpace :: [Inline] -> [Inline] +stripLeadingTrailingSpace = go . reverse . go . reverse + where go (Space:xs) = xs + go xs = xs + +-- Put display math in its own block (for ODT/DOCX). +fixDisplayMath :: Block -> Block +fixDisplayMath (Plain lst) + | any isDisplayMath lst && not (all isDisplayMath lst) = + -- chop into several paragraphs so each displaymath is its own + Div ("",["math"],[]) $ map (Plain . stripLeadingTrailingSpace) $ + groupBy (\x y -> (isDisplayMath x && isDisplayMath y) || + not (isDisplayMath x || isDisplayMath y)) lst +fixDisplayMath (Para lst) + | any isDisplayMath lst && not (all isDisplayMath lst) = + -- chop into several paragraphs so each displaymath is its own + Div ("",["math"],[]) $ map (Para . stripLeadingTrailingSpace) $ + groupBy (\x y -> (isDisplayMath x && isDisplayMath y) || + not (isDisplayMath x || isDisplayMath y)) lst +fixDisplayMath x = x diff --git a/src/Text/Pandoc/Writers/Texinfo.hs b/src/Text/Pandoc/Writers/Texinfo.hs index d62e50880..bf3df8035 100644 --- a/src/Text/Pandoc/Writers/Texinfo.hs +++ b/src/Text/Pandoc/Writers/Texinfo.hs @@ -293,7 +293,7 @@ blockListToTexinfo (x:xs) = do case x of Header level _ _ -> do -- We need need to insert a menu for this node. - let (before, after) = break isHeader xs + let (before, after) = break isHeaderBlock xs before' <- blockListToTexinfo before let menu = if level < 4 then collectNodes (level + 1) after @@ -315,10 +315,6 @@ blockListToTexinfo (x:xs) = do xs' <- blockListToTexinfo xs return $ x' $$ xs' -isHeader :: Block -> Bool -isHeader (Header _ _ _) = True -isHeader _ = False - collectNodes :: Int -> [Block] -> [Block] collectNodes _ [] = [] collectNodes level (x:xs) = diff --git a/src/Text/Pandoc/Writers/Textile.hs b/src/Text/Pandoc/Writers/Textile.hs index 7c102cc86..95aedf780 100644 --- a/src/Text/Pandoc/Writers/Textile.hs +++ b/src/Text/Pandoc/Writers/Textile.hs @@ -51,7 +51,7 @@ data WriterState = WriterState { writeTextile :: WriterOptions -> Pandoc -> String writeTextile opts document = evalState (pandocToTextile opts document) - (WriterState { stNotes = [], stListLevel = [], stUseTags = False }) + WriterState { stNotes = [], stListLevel = [], stUseTags = False } -- | Return Textile representation of document. pandocToTextile :: WriterOptions -> Pandoc -> State WriterState String diff --git a/tests/MarkdownTest_1.0.3/MarkdownTest.pl b/tests/MarkdownTest_1.0.3/MarkdownTest.pl deleted file mode 100755 index 55553d09c..000000000 --- a/tests/MarkdownTest_1.0.3/MarkdownTest.pl +++ /dev/null @@ -1,176 +0,0 @@ -#!/usr/bin/perl - -# -# MarkdownTester -- Run tests for Markdown implementations -# -# Copyright (c) 2004-2005 John Gruber -# <http://daringfireball.net/projects/markdown/> -# - -use strict; -use warnings; -use Getopt::Long; -use Benchmark; - -our $VERSION = '1.0.2'; -# Sat 24 Dec 2005 - -my $time_start = new Benchmark; -my $test_dir = "Tests"; -my $script = "./Markdown.pl"; -my $use_tidy = 0; -my ($flag_version); - -GetOptions ( - "script=s" => \$script, - "testdir=s" => \$test_dir, - "tidy" => \$use_tidy, - "version" => \$flag_version, - ); - -if($flag_version) { - my $progname = $0; - $progname =~ s{.*/}{}; - die "$progname version $VERSION\n"; -} - -unless (-d $test_dir) { die "'$test_dir' is not a directory.\n"; } -unless (-f $script) { die "$script does not exist.\n"; } -unless (-x $script) { die "$script is not executable.\n"; } - -my $tests_passed = 0; -my $tests_failed = 0; - -TEST: -foreach my $testfile (glob "$test_dir/*.text") { - my $testname = $testfile; - $testname =~ s{.*/(.+)\.text$}{$1}i; - print "$testname ... "; - - # Look for a corresponding .html file for each .text file: - my $resultfile = $testfile; - $resultfile =~ s{\.text$}{\.html}i; - unless (-f $resultfile) { - print "'$resultfile' does not exist.\n\n"; - next TEST; - } - - # open(TEST, $testfile) || die("Can't open testfile: $!"); - open(RESULT, $resultfile) || die("Can't open resultfile: $!"); - undef $/; - # my $t_input = <TEST>; - my $t_result = <RESULT>; - - my $t_output = `'$script' '$testfile'`; - - # Normalize the output and expected result strings: - $t_result =~ s/\s+\z//; # trim trailing whitespace - $t_output =~ s/\s+\z//; # trim trailing whitespace - if ($use_tidy) { - # Escape the strings, pass them through to CLI tidy tool for tag-level equivalency - $t_result =~ s{'}{'\\''}g; # escape ' chars for shell - $t_output =~ s{'}{'\\''}g; - $t_result = `echo '$t_result' | tidy --show-body-only 1 --quiet 1 --show-warnings 0`; - $t_output = `echo '$t_output' | tidy --show-body-only 1 --quiet 1 --show-warnings 0`; - } - - if ($t_output eq $t_result) { - print "OK\n"; - $tests_passed++; - } - else { - print "FAILED\n\n"; -# This part added by JM to print diffs - open(OUT, '>tmp1') or die $!; - print OUT $t_output or die $!; - open(RES, '>tmp2') or die $!; - print RES $t_result or die $!; - print `diff tmp1 tmp2`; - close RES; - close OUT; - print "\n"; - `rm tmp?`; -# End of added part - $tests_failed++; - } -} - -print "\n\n"; -print "$tests_passed passed; $tests_failed failed.\n"; - -my $time_end = new Benchmark; -my $time_diff = timediff($time_end, $time_start); -print "Benchmark: ", timestr($time_diff), "\n"; - - -__END__ - -=pod - -=head1 NAME - -B<MarkdownTest> - - -=head1 SYNOPSIS - -B<MarkdownTest.pl> [ B<--options> ] [ I<file> ... ] - - -=head1 DESCRIPTION - - -=head1 OPTIONS - -Use "--" to end switch parsing. For example, to open a file named "-z", use: - - MarkdownTest.pl -- -z - -=over 4 - -=item B<--script> - -Specify the path to the Markdown script to test. Defaults to -"./Markdown.pl". Example: - - ./MarkdownTest.pl --script ./PHP-Markdown/php-markdown - -=item B<--testdir> - -Specify the path to a directory containing test data. Defaults to "Tests". - -=item B<--tidy> - -Flag to turn on using the command line 'tidy' tool to normalize HTML -output before comparing script output to the expected test result. -Assumes that the 'tidy' command is available in your PATH. Defaults to -off. - -=back - - - -=head1 BUGS - - - -=head1 VERSION HISTORY - -1.0 Mon 13 Dec 2004-2005 - -1.0.1 Mon 19 Sep 2005 - - + Better handling of case when foo.text exists, but foo.html doesn't. - It now prints a message and moves on, rather than dying. - - -=head1 COPYRIGHT AND LICENSE - -Copyright (c) 2004-2005 John Gruber -<http://daringfireball.net/> -All rights reserved. - -This is free software; you may redistribute it and/or modify it under -the same terms as Perl itself. - -=cut diff --git a/tests/MarkdownTest_1.0.3/Tests/Amps and angle encoding.html b/tests/MarkdownTest_1.0.3/Tests/Amps and angle encoding.html deleted file mode 100644 index 9606860b6..000000000 --- a/tests/MarkdownTest_1.0.3/Tests/Amps and angle encoding.html +++ /dev/null @@ -1,17 +0,0 @@ -<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>Here's a <a href="http://example.com/?foo=1&bar=2">link</a> with an ampersand in the URL.</p> - -<p>Here's a link with an amersand in the link text: <a href="http://att.com/" title="AT&T">AT&T</a>.</p> - -<p>Here's an inline <a href="/script?foo=1&bar=2">link</a>.</p> - -<p>Here's an inline <a href="/script?foo=1&bar=2">link</a>.</p> diff --git a/tests/MarkdownTest_1.0.3/Tests/Amps and angle encoding.text b/tests/MarkdownTest_1.0.3/Tests/Amps and angle encoding.text deleted file mode 100644 index 0e9527f93..000000000 --- a/tests/MarkdownTest_1.0.3/Tests/Amps and angle encoding.text +++ /dev/null @@ -1,21 +0,0 @@ -AT&T has an ampersand in their name. - -AT&T is another way to write it. - -This & that. - -4 < 5. - -6 > 5. - -Here's a [link] [1] with an ampersand in the URL. - -Here's a link with an amersand in the link text: [AT&T] [2]. - -Here's an inline [link](/script?foo=1&bar=2). - -Here's an inline [link](</script?foo=1&bar=2>). - - -[1]: http://example.com/?foo=1&bar=2 -[2]: http://att.com/ "AT&T"
\ No newline at end of file diff --git a/tests/MarkdownTest_1.0.3/Tests/Auto links.html b/tests/MarkdownTest_1.0.3/Tests/Auto links.html deleted file mode 100644 index f8df9852c..000000000 --- a/tests/MarkdownTest_1.0.3/Tests/Auto links.html +++ /dev/null @@ -1,18 +0,0 @@ -<p>Link: <a href="http://example.com/">http://example.com/</a>.</p> - -<p>With an ampersand: <a href="http://example.com/?foo=1&bar=2">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>It should.</li> -</ul> - -<blockquote> - <p>Blockquoted: <a href="http://example.com/">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/MarkdownTest_1.0.3/Tests/Auto links.text b/tests/MarkdownTest_1.0.3/Tests/Auto links.text deleted file mode 100644 index abbc48869..000000000 --- a/tests/MarkdownTest_1.0.3/Tests/Auto links.text +++ /dev/null @@ -1,13 +0,0 @@ -Link: <http://example.com/>. - -With an ampersand: <http://example.com/?foo=1&bar=2> - -* In a list? -* <http://example.com/> -* It should. - -> Blockquoted: <http://example.com/> - -Auto-links should not occur here: `<http://example.com/>` - - or here: <http://example.com/>
\ No newline at end of file diff --git a/tests/MarkdownTest_1.0.3/Tests/Backslash escapes.html b/tests/MarkdownTest_1.0.3/Tests/Backslash escapes.html deleted file mode 100644 index 29870dac5..000000000 --- a/tests/MarkdownTest_1.0.3/Tests/Backslash escapes.html +++ /dev/null @@ -1,118 +0,0 @@ -<p>These should all get escaped:</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> - -<p>These should not, because they occur within a code block:</p> - -<pre><code>Backslash: \\ - -Backtick: \` - -Asterisk: \* - -Underscore: \_ - -Left brace: \{ - -Right brace: \} - -Left bracket: \[ - -Right bracket: \] - -Left paren: \( - -Right paren: \) - -Greater-than: \> - -Hash: \# - -Period: \. - -Bang: \! - -Plus: \+ - -Minus: \- -</code></pre> - -<p>Nor should these, which occur in code spans:</p> - -<p>Backslash: <code>\\</code></p> - -<p>Backtick: <code>\`</code></p> - -<p>Asterisk: <code>\*</code></p> - -<p>Underscore: <code>\_</code></p> - -<p>Left brace: <code>\{</code></p> - -<p>Right brace: <code>\}</code></p> - -<p>Left bracket: <code>\[</code></p> - -<p>Right bracket: <code>\]</code></p> - -<p>Left paren: <code>\(</code></p> - -<p>Right paren: <code>\)</code></p> - -<p>Greater-than: <code>\></code></p> - -<p>Hash: <code>\#</code></p> - -<p>Period: <code>\.</code></p> - -<p>Bang: <code>\!</code></p> - -<p>Plus: <code>\+</code></p> - -<p>Minus: <code>\-</code></p> - - -<p>These should get escaped, even though they're matching pairs for -other Markdown constructs:</p> - -<p>*asterisks*</p> - -<p>_underscores_</p> - -<p>`backticks`</p> - -<p>This is a code span with a literal backslash-backtick sequence: <code>\`</code></p> - -<p>This is a tag with unescaped backticks <span attr='`ticks`'>bar</span>.</p> - -<p>This is a tag with backslashes <span attr='\\backslashes\\'>bar</span>.</p> diff --git a/tests/MarkdownTest_1.0.3/Tests/Backslash escapes.text b/tests/MarkdownTest_1.0.3/Tests/Backslash escapes.text deleted file mode 100644 index 5b014cb33..000000000 --- a/tests/MarkdownTest_1.0.3/Tests/Backslash escapes.text +++ /dev/null @@ -1,120 +0,0 @@ -These should all get escaped: - -Backslash: \\ - -Backtick: \` - -Asterisk: \* - -Underscore: \_ - -Left brace: \{ - -Right brace: \} - -Left bracket: \[ - -Right bracket: \] - -Left paren: \( - -Right paren: \) - -Greater-than: \> - -Hash: \# - -Period: \. - -Bang: \! - -Plus: \+ - -Minus: \- - - - -These should not, because they occur within a code block: - - Backslash: \\ - - Backtick: \` - - Asterisk: \* - - Underscore: \_ - - Left brace: \{ - - Right brace: \} - - Left bracket: \[ - - Right bracket: \] - - Left paren: \( - - Right paren: \) - - Greater-than: \> - - Hash: \# - - Period: \. - - Bang: \! - - Plus: \+ - - Minus: \- - - -Nor should these, which occur in code spans: - -Backslash: `\\` - -Backtick: `` \` `` - -Asterisk: `\*` - -Underscore: `\_` - -Left brace: `\{` - -Right brace: `\}` - -Left bracket: `\[` - -Right bracket: `\]` - -Left paren: `\(` - -Right paren: `\)` - -Greater-than: `\>` - -Hash: `\#` - -Period: `\.` - -Bang: `\!` - -Plus: `\+` - -Minus: `\-` - - -These should get escaped, even though they're matching pairs for -other Markdown constructs: - -\*asterisks\* - -\_underscores\_ - -\`backticks\` - -This is a code span with a literal backslash-backtick sequence: `` \` `` - -This is a tag with unescaped backticks <span attr='`ticks`'>bar</span>. - -This is a tag with backslashes <span attr='\\backslashes\\'>bar</span>. diff --git a/tests/MarkdownTest_1.0.3/Tests/Blockquotes with code blocks.html b/tests/MarkdownTest_1.0.3/Tests/Blockquotes with code blocks.html deleted file mode 100644 index 990202a1b..000000000 --- a/tests/MarkdownTest_1.0.3/Tests/Blockquotes with code blocks.html +++ /dev/null @@ -1,15 +0,0 @@ -<blockquote> - <p>Example:</p> - -<pre><code>sub status { - print "working"; -} -</code></pre> - - <p>Or:</p> - -<pre><code>sub status { - return "working"; -} -</code></pre> -</blockquote> diff --git a/tests/MarkdownTest_1.0.3/Tests/Blockquotes with code blocks.text b/tests/MarkdownTest_1.0.3/Tests/Blockquotes with code blocks.text deleted file mode 100644 index c31d17104..000000000 --- a/tests/MarkdownTest_1.0.3/Tests/Blockquotes with code blocks.text +++ /dev/null @@ -1,11 +0,0 @@ -> Example: -> -> sub status { -> print "working"; -> } -> -> Or: -> -> sub status { -> return "working"; -> } diff --git a/tests/MarkdownTest_1.0.3/Tests/Code Blocks.html b/tests/MarkdownTest_1.0.3/Tests/Code Blocks.html deleted file mode 100644 index 32703f5cb..000000000 --- a/tests/MarkdownTest_1.0.3/Tests/Code Blocks.html +++ /dev/null @@ -1,18 +0,0 @@ -<pre><code>code block on the first line -</code></pre> - -<p>Regular text.</p> - -<pre><code>code block indented by spaces -</code></pre> - -<p>Regular text.</p> - -<pre><code>the lines in this block -all contain trailing spaces -</code></pre> - -<p>Regular Text.</p> - -<pre><code>code block on the last line -</code></pre> diff --git a/tests/MarkdownTest_1.0.3/Tests/Code Blocks.text b/tests/MarkdownTest_1.0.3/Tests/Code Blocks.text deleted file mode 100644 index b54b09285..000000000 --- a/tests/MarkdownTest_1.0.3/Tests/Code Blocks.text +++ /dev/null @@ -1,14 +0,0 @@ - code block on the first line - -Regular text. - - code block indented by spaces - -Regular text. - - the lines in this block - all contain trailing spaces - -Regular Text. - - code block on the last line
\ No newline at end of file diff --git a/tests/MarkdownTest_1.0.3/Tests/Code Spans.html b/tests/MarkdownTest_1.0.3/Tests/Code Spans.html deleted file mode 100644 index 4b8afbb70..000000000 --- a/tests/MarkdownTest_1.0.3/Tests/Code Spans.html +++ /dev/null @@ -1,6 +0,0 @@ -<p><code><test a="</code> content of attribute <code>"></code></p> - -<p>Fix for backticks within HTML tag: <span attr='`ticks`'>like this</span></p> - -<p>Here's how you put <code>`backticks`</code> in a code span.</p> - diff --git a/tests/MarkdownTest_1.0.3/Tests/Code Spans.text b/tests/MarkdownTest_1.0.3/Tests/Code Spans.text deleted file mode 100644 index 750a1973d..000000000 --- a/tests/MarkdownTest_1.0.3/Tests/Code Spans.text +++ /dev/null @@ -1,6 +0,0 @@ -`<test a="` content of attribute `">` - -Fix for backticks within HTML tag: <span attr='`ticks`'>like this</span> - -Here's how you put `` `backticks` `` in a code span. - diff --git a/tests/MarkdownTest_1.0.3/Tests/Hard-wrapped paragraphs with list-like lines.html b/tests/MarkdownTest_1.0.3/Tests/Hard-wrapped paragraphs with list-like lines.html deleted file mode 100644 index e21ac79a2..000000000 --- a/tests/MarkdownTest_1.0.3/Tests/Hard-wrapped paragraphs with list-like lines.html +++ /dev/null @@ -1,8 +0,0 @@ -<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> diff --git a/tests/MarkdownTest_1.0.3/Tests/Hard-wrapped paragraphs with list-like lines.text b/tests/MarkdownTest_1.0.3/Tests/Hard-wrapped paragraphs with list-like lines.text deleted file mode 100644 index f8a5b27bf..000000000 --- a/tests/MarkdownTest_1.0.3/Tests/Hard-wrapped paragraphs with list-like lines.text +++ /dev/null @@ -1,8 +0,0 @@ -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. diff --git a/tests/MarkdownTest_1.0.3/Tests/Horizontal rules.html b/tests/MarkdownTest_1.0.3/Tests/Horizontal rules.html deleted file mode 100644 index 2dc2ab656..000000000 --- a/tests/MarkdownTest_1.0.3/Tests/Horizontal rules.html +++ /dev/null @@ -1,71 +0,0 @@ -<p>Dashes:</p> - -<hr /> - -<hr /> - -<hr /> - -<hr /> - -<pre><code>--- -</code></pre> - -<hr /> - -<hr /> - -<hr /> - -<hr /> - -<pre><code>- - - -</code></pre> - -<p>Asterisks:</p> - -<hr /> - -<hr /> - -<hr /> - -<hr /> - -<pre><code>*** -</code></pre> - -<hr /> - -<hr /> - -<hr /> - -<hr /> - -<pre><code>* * * -</code></pre> - -<p>Underscores:</p> - -<hr /> - -<hr /> - -<hr /> - -<hr /> - -<pre><code>___ -</code></pre> - -<hr /> - -<hr /> - -<hr /> - -<hr /> - -<pre><code>_ _ _ -</code></pre> diff --git a/tests/MarkdownTest_1.0.3/Tests/Horizontal rules.text b/tests/MarkdownTest_1.0.3/Tests/Horizontal rules.text deleted file mode 100644 index 1594bda27..000000000 --- a/tests/MarkdownTest_1.0.3/Tests/Horizontal rules.text +++ /dev/null @@ -1,67 +0,0 @@ -Dashes: - ---- - - --- - - --- - - --- - - --- - -- - - - - - - - - - - - - - - - - - - - - - - - - -Asterisks: - -*** - - *** - - *** - - *** - - *** - -* * * - - * * * - - * * * - - * * * - - * * * - - -Underscores: - -___ - - ___ - - ___ - - ___ - - ___ - -_ _ _ - - _ _ _ - - _ _ _ - - _ _ _ - - _ _ _ diff --git a/tests/MarkdownTest_1.0.3/Tests/Inline HTML (Advanced).html b/tests/MarkdownTest_1.0.3/Tests/Inline HTML (Advanced).html deleted file mode 100644 index 3af9cafb1..000000000 --- a/tests/MarkdownTest_1.0.3/Tests/Inline HTML (Advanced).html +++ /dev/null @@ -1,15 +0,0 @@ -<p>Simple block on one line:</p> - -<div>foo</div> - -<p>And nested without indentation:</p> - -<div> -<div> -<div> -foo -</div> -<div style=">"/> -</div> -<div>bar</div> -</div> diff --git a/tests/MarkdownTest_1.0.3/Tests/Inline HTML (Advanced).text b/tests/MarkdownTest_1.0.3/Tests/Inline HTML (Advanced).text deleted file mode 100644 index 86b7206d2..000000000 --- a/tests/MarkdownTest_1.0.3/Tests/Inline HTML (Advanced).text +++ /dev/null @@ -1,15 +0,0 @@ -Simple block on one line: - -<div>foo</div> - -And nested without indentation: - -<div> -<div> -<div> -foo -</div> -<div style=">"/> -</div> -<div>bar</div> -</div> diff --git a/tests/MarkdownTest_1.0.3/Tests/Inline HTML (Simple).html b/tests/MarkdownTest_1.0.3/Tests/Inline HTML (Simple).html deleted file mode 100644 index 6bf78f8fc..000000000 --- a/tests/MarkdownTest_1.0.3/Tests/Inline HTML (Simple).html +++ /dev/null @@ -1,72 +0,0 @@ -<p>Here's a simple block:</p> - -<div> - foo -</div> - -<p>This should be a code block, though:</p> - -<pre><code><div> - foo -</div> -</code></pre> - -<p>As should this:</p> - -<pre><code><div>foo</div> -</code></pre> - -<p>Now, nested:</p> - -<div> - <div> - <div> - foo - </div> - </div> -</div> - -<p>This should just be an HTML comment:</p> - -<!-- Comment --> - -<p>Multiline:</p> - -<!-- -Blah -Blah ---> - -<p>Code block:</p> - -<pre><code><!-- Comment --> -</code></pre> - -<p>Just plain comment, with trailing spaces on the line:</p> - -<!-- foo --> - -<p>Code:</p> - -<pre><code><hr /> -</code></pre> - -<p>Hr's:</p> - -<hr> - -<hr/> - -<hr /> - -<hr> - -<hr/> - -<hr /> - -<hr class="foo" id="bar" /> - -<hr class="foo" id="bar"/> - -<hr class="foo" id="bar" > diff --git a/tests/MarkdownTest_1.0.3/Tests/Inline HTML (Simple).text b/tests/MarkdownTest_1.0.3/Tests/Inline HTML (Simple).text deleted file mode 100644 index 14aa2dc27..000000000 --- a/tests/MarkdownTest_1.0.3/Tests/Inline HTML (Simple).text +++ /dev/null @@ -1,69 +0,0 @@ -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 ---> - -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" > - diff --git a/tests/MarkdownTest_1.0.3/Tests/Inline HTML comments.html b/tests/MarkdownTest_1.0.3/Tests/Inline HTML comments.html deleted file mode 100644 index 3f167a161..000000000 --- a/tests/MarkdownTest_1.0.3/Tests/Inline HTML comments.html +++ /dev/null @@ -1,13 +0,0 @@ -<p>Paragraph one.</p> - -<!-- This is a simple comment --> - -<!-- - This is another comment. ---> - -<p>Paragraph two.</p> - -<!-- one comment block -- -- with two comments --> - -<p>The end.</p> diff --git a/tests/MarkdownTest_1.0.3/Tests/Inline HTML comments.text b/tests/MarkdownTest_1.0.3/Tests/Inline HTML comments.text deleted file mode 100644 index 41d830d03..000000000 --- a/tests/MarkdownTest_1.0.3/Tests/Inline HTML comments.text +++ /dev/null @@ -1,13 +0,0 @@ -Paragraph one. - -<!-- This is a simple comment --> - -<!-- - This is another comment. ---> - -Paragraph two. - -<!-- one comment block -- -- with two comments --> - -The end. diff --git a/tests/MarkdownTest_1.0.3/Tests/Links, inline style.html b/tests/MarkdownTest_1.0.3/Tests/Links, inline style.html deleted file mode 100644 index f36607ddd..000000000 --- a/tests/MarkdownTest_1.0.3/Tests/Links, inline style.html +++ /dev/null @@ -1,11 +0,0 @@ -<p>Just a <a href="/url/">URL</a>.</p> - -<p><a href="/url/" title="title">URL and title</a>.</p> - -<p><a href="/url/" title="title preceded by two spaces">URL and title</a>.</p> - -<p><a href="/url/" title="title preceded by a tab">URL and title</a>.</p> - -<p><a href="/url/" title="title has spaces afterward">URL and title</a>.</p> - -<p><a href="">Empty</a>.</p> diff --git a/tests/MarkdownTest_1.0.3/Tests/Links, inline style.text b/tests/MarkdownTest_1.0.3/Tests/Links, inline style.text deleted file mode 100644 index 09017a90c..000000000 --- a/tests/MarkdownTest_1.0.3/Tests/Links, inline style.text +++ /dev/null @@ -1,12 +0,0 @@ -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 has spaces afterward" ). - - -[Empty](). diff --git a/tests/MarkdownTest_1.0.3/Tests/Links, reference style.html b/tests/MarkdownTest_1.0.3/Tests/Links, reference style.html deleted file mode 100644 index 8e70c32f4..000000000 --- a/tests/MarkdownTest_1.0.3/Tests/Links, reference style.html +++ /dev/null @@ -1,52 +0,0 @@ -<p>Foo <a href="/url/" title="Title">bar</a>.</p> - -<p>Foo <a href="/url/" title="Title">bar</a>.</p> - -<p>Foo <a href="/url/" title="Title">bar</a>.</p> - -<p>With <a href="/url/">embedded [brackets]</a>.</p> - -<p>Indented <a href="/url">once</a>.</p> - -<p>Indented <a href="/url">twice</a>.</p> - -<p>Indented <a href="/url">thrice</a>.</p> - -<p>Indented [four][] times.</p> - -<pre><code>[four]: /url -</code></pre> - -<hr /> - -<p><a href="foo">this</a> should work</p> - -<p>So should <a href="foo">this</a>.</p> - -<p>And <a href="foo">this</a>.</p> - -<p>And <a href="foo">this</a>.</p> - -<p>And <a href="foo">this</a>.</p> - -<p>But not [that] [].</p> - -<p>Nor [that][].</p> - -<p>Nor [that].</p> - -<p>[Something in brackets like <a href="foo">this</a> should work]</p> - -<p>[Same with <a href="foo">this</a>.]</p> - -<p>In this case, <a href="/somethingelse/">this</a> points to something else.</p> - -<p>Backslashing should suppress [this] and [this].</p> - -<hr /> - -<p>Here's one where the <a href="/url/">link -breaks</a> across lines.</p> - -<p>Here's another where the <a href="/url/">link -breaks</a> across lines, but with a line-ending space.</p> diff --git a/tests/MarkdownTest_1.0.3/Tests/Links, reference style.text b/tests/MarkdownTest_1.0.3/Tests/Links, reference style.text deleted file mode 100644 index 341ec88e3..000000000 --- a/tests/MarkdownTest_1.0.3/Tests/Links, reference style.text +++ /dev/null @@ -1,71 +0,0 @@ -Foo [bar] [1]. - -Foo [bar][1]. - -Foo [bar] -[1]. - -[1]: /url/ "Title" - - -With [embedded [brackets]] [b]. - - -Indented [once][]. - -Indented [twice][]. - -Indented [thrice][]. - -Indented [four][] times. - - [once]: /url - - [twice]: /url - - [thrice]: /url - - [four]: /url - - -[b]: /url/ - -* * * - -[this] [this] should work - -So should [this][this]. - -And [this] []. - -And [this][]. - -And [this]. - -But not [that] []. - -Nor [that][]. - -Nor [that]. - -[Something in brackets like [this][] should work] - -[Same with [this].] - -In this case, [this](/somethingelse/) points to something else. - -Backslashing should suppress \[this] and [this\]. - -[this]: foo - - -* * * - -Here's one where the [link -breaks] across lines. - -Here's another where the [link -breaks] across lines, but with a line-ending space. - - -[link breaks]: /url/ diff --git a/tests/MarkdownTest_1.0.3/Tests/Links, shortcut references.html b/tests/MarkdownTest_1.0.3/Tests/Links, shortcut references.html deleted file mode 100644 index bf81e939f..000000000 --- a/tests/MarkdownTest_1.0.3/Tests/Links, shortcut references.html +++ /dev/null @@ -1,9 +0,0 @@ -<p>This is the <a href="/simple">simple case</a>.</p> - -<p>This one has a <a href="/foo">line -break</a>.</p> - -<p>This one has a <a href="/foo">line -break</a> with a line-ending space.</p> - -<p><a href="/that">this</a> and the <a href="/other">other</a></p> diff --git a/tests/MarkdownTest_1.0.3/Tests/Links, shortcut references.text b/tests/MarkdownTest_1.0.3/Tests/Links, shortcut references.text deleted file mode 100644 index 8c44c98fe..000000000 --- a/tests/MarkdownTest_1.0.3/Tests/Links, shortcut references.text +++ /dev/null @@ -1,20 +0,0 @@ -This is the [simple case]. - -[simple case]: /simple - - - -This one has a [line -break]. - -This one has a [line -break] with a line-ending space. - -[line break]: /foo - - -[this] [that] and the [other] - -[this]: /this -[that]: /that -[other]: /other diff --git a/tests/MarkdownTest_1.0.3/Tests/Literal quotes in titles.html b/tests/MarkdownTest_1.0.3/Tests/Literal quotes in titles.html deleted file mode 100644 index 611c1ac61..000000000 --- a/tests/MarkdownTest_1.0.3/Tests/Literal quotes in titles.html +++ /dev/null @@ -1,3 +0,0 @@ -<p>Foo <a href="/url/" title="Title with "quotes" inside">bar</a>.</p> - -<p>Foo <a href="/url/" title="Title with "quotes" inside">bar</a>.</p> diff --git a/tests/MarkdownTest_1.0.3/Tests/Literal quotes in titles.text b/tests/MarkdownTest_1.0.3/Tests/Literal quotes in titles.text deleted file mode 100644 index 29d0e4235..000000000 --- a/tests/MarkdownTest_1.0.3/Tests/Literal quotes in titles.text +++ /dev/null @@ -1,7 +0,0 @@ -Foo [bar][]. - -Foo [bar](/url/ "Title with "quotes" inside"). - - - [bar]: /url/ "Title with "quotes" inside" - diff --git a/tests/MarkdownTest_1.0.3/Tests/Markdown Documentation - Basics.html b/tests/MarkdownTest_1.0.3/Tests/Markdown Documentation - Basics.html deleted file mode 100644 index d5bdbb29a..000000000 --- a/tests/MarkdownTest_1.0.3/Tests/Markdown Documentation - Basics.html +++ /dev/null @@ -1,314 +0,0 @@ -<h1>Markdown: Basics</h1> - -<ul id="ProjectSubmenu"> - <li><a href="/projects/markdown/" title="Markdown Project Page">Main</a></li> - <li><a class="selected" title="Markdown Basics">Basics</a></li> - <li><a href="/projects/markdown/syntax" title="Markdown Syntax Documentation">Syntax</a></li> - <li><a href="/projects/markdown/license" title="Pricing and License Information">License</a></li> - <li><a href="/projects/markdown/dingus" title="Online Markdown Web Form">Dingus</a></li> -</ul> - -<h2>Getting the Gist of Markdown's Formatting Syntax</h2> - -<p>This page offers a brief overview of what it's like to use Markdown. -The <a href="/projects/markdown/syntax" title="Markdown Syntax">syntax page</a> provides complete, detailed documentation for -every feature, but Markdown should be very easy to pick up simply by -looking at a few examples of it in action. The examples on this page -are written in a before/after style, showing example syntax and the -HTML output produced by Markdown.</p> - -<p>It's also helpful to simply try Markdown out; the <a href="/projects/markdown/dingus" title="Markdown Dingus">Dingus</a> is a -web application that allows you type your own Markdown-formatted text -and translate it to XHTML.</p> - -<p><strong>Note:</strong> This document is itself written using Markdown; you -can <a href="/projects/markdown/basics.text">see the source for it by adding '.text' to the URL</a>.</p> - -<h2>Paragraphs, Headers, Blockquotes</h2> - -<p>A paragraph is simply one or more consecutive lines of text, separated -by one or more blank lines. (A blank line is any line that looks like a -blank line -- a line containing nothing spaces or tabs is considered -blank.) Normal paragraphs should not be intended with spaces or tabs.</p> - -<p>Markdown offers two styles of headers: <em>Setext</em> and <em>atx</em>. -Setext-style headers for <code><h1></code> and <code><h2></code> are created by -"underlining" with equal signs (<code>=</code>) and hyphens (<code>-</code>), respectively. -To create an atx-style header, you put 1-6 hash marks (<code>#</code>) at the -beginning of the line -- the number of hashes equals the resulting -HTML header level.</p> - -<p>Blockquotes are indicated using email-style '<code>></code>' angle brackets.</p> - -<p>Markdown:</p> - -<pre><code>A First Level Header -==================== - -A Second Level Header ---------------------- - -Now is the time for all good men to come to -the aid of their country. This is just a -regular paragraph. - -The quick brown fox jumped over the lazy -dog's back. - -### Header 3 - -> This is a blockquote. -> -> This is the second paragraph in the blockquote. -> -> ## This is an H2 in a blockquote -</code></pre> - -<p>Output:</p> - -<pre><code><h1>A First Level Header</h1> - -<h2>A Second Level Header</h2> - -<p>Now is the time for all good men to come to -the aid of their country. This is just a -regular paragraph.</p> - -<p>The quick brown fox jumped over the lazy -dog's back.</p> - -<h3>Header 3</h3> - -<blockquote> - <p>This is a blockquote.</p> - - <p>This is the second paragraph in the blockquote.</p> - - <h2>This is an H2 in a blockquote</h2> -</blockquote> -</code></pre> - -<h3>Phrase Emphasis</h3> - -<p>Markdown uses asterisks and underscores to indicate spans of emphasis.</p> - -<p>Markdown:</p> - -<pre><code>Some of these words *are emphasized*. -Some of these words _are emphasized also_. - -Use two asterisks for **strong emphasis**. -Or, if you prefer, __use two underscores instead__. -</code></pre> - -<p>Output:</p> - -<pre><code><p>Some of these words <em>are emphasized</em>. -Some of these words <em>are emphasized also</em>.</p> - -<p>Use two asterisks for <strong>strong emphasis</strong>. -Or, if you prefer, <strong>use two underscores instead</strong>.</p> -</code></pre> - -<h2>Lists</h2> - -<p>Unordered (bulleted) lists use asterisks, pluses, and hyphens (<code>*</code>, -<code>+</code>, and <code>-</code>) as list markers. These three markers are -interchangable; this:</p> - -<pre><code>* Candy. -* Gum. -* Booze. -</code></pre> - -<p>this:</p> - -<pre><code>+ Candy. -+ Gum. -+ Booze. -</code></pre> - -<p>and this:</p> - -<pre><code>- Candy. -- Gum. -- Booze. -</code></pre> - -<p>all produce the same output:</p> - -<pre><code><ul> -<li>Candy.</li> -<li>Gum.</li> -<li>Booze.</li> -</ul> -</code></pre> - -<p>Ordered (numbered) lists use regular numbers, followed by periods, as -list markers:</p> - -<pre><code>1. Red -2. Green -3. Blue -</code></pre> - -<p>Output:</p> - -<pre><code><ol> -<li>Red</li> -<li>Green</li> -<li>Blue</li> -</ol> -</code></pre> - -<p>If you put blank lines between items, you'll get <code><p></code> tags for the -list item text. You can create multi-paragraph list items by indenting -the paragraphs by 4 spaces or 1 tab:</p> - -<pre><code>* A list item. - - With multiple paragraphs. - -* Another item in the list. -</code></pre> - -<p>Output:</p> - -<pre><code><ul> -<li><p>A list item.</p> -<p>With multiple paragraphs.</p></li> -<li><p>Another item in the list.</p></li> -</ul> -</code></pre> - -<h3>Links</h3> - -<p>Markdown supports two styles for creating links: <em>inline</em> and -<em>reference</em>. With both styles, you use square brackets to delimit the -text you want to turn into a link.</p> - -<p>Inline-style links use parentheses immediately after the link text. -For example:</p> - -<pre><code>This is an [example link](http://example.com/). -</code></pre> - -<p>Output:</p> - -<pre><code><p>This is an <a href="http://example.com/"> -example link</a>.</p> -</code></pre> - -<p>Optionally, you may include a title attribute in the parentheses:</p> - -<pre><code>This is an [example link](http://example.com/ "With a Title"). -</code></pre> - -<p>Output:</p> - -<pre><code><p>This is an <a href="http://example.com/" title="With a Title"> -example link</a>.</p> -</code></pre> - -<p>Reference-style links allow you to refer to your links by names, which -you define elsewhere in your document:</p> - -<pre><code>I get 10 times more traffic from [Google][1] than from -[Yahoo][2] or [MSN][3]. - -[1]: http://google.com/ "Google" -[2]: http://search.yahoo.com/ "Yahoo Search" -[3]: http://search.msn.com/ "MSN Search" -</code></pre> - -<p>Output:</p> - -<pre><code><p>I get 10 times more traffic from <a href="http://google.com/" -title="Google">Google</a> than from <a href="http://search.yahoo.com/" -title="Yahoo Search">Yahoo</a> or <a href="http://search.msn.com/" -title="MSN Search">MSN</a>.</p> -</code></pre> - -<p>The title attribute is optional. Link names may contain letters, -numbers and spaces, but are <em>not</em> case sensitive:</p> - -<pre><code>I start my morning with a cup of coffee and -[The New York Times][NY Times]. - -[ny times]: http://www.nytimes.com/ -</code></pre> - -<p>Output:</p> - -<pre><code><p>I start my morning with a cup of coffee and -<a href="http://www.nytimes.com/">The New York Times</a>.</p> -</code></pre> - -<h3>Images</h3> - -<p>Image syntax is very much like link syntax.</p> - -<p>Inline (titles are optional):</p> - -<pre><code> -</code></pre> - -<p>Reference-style:</p> - -<pre><code>![alt text][id] - -[id]: /path/to/img.jpg "Title" -</code></pre> - -<p>Both of the above examples produce the same output:</p> - -<pre><code><img src="/path/to/img.jpg" alt="alt text" title="Title" /> -</code></pre> - -<h3>Code</h3> - -<p>In a regular paragraph, you can create code span by wrapping text in -backtick quotes. Any ampersands (<code>&</code>) and angle brackets (<code><</code> or -<code>></code>) will automatically be translated into HTML entities. This makes -it easy to use Markdown to write about HTML example code:</p> - -<pre><code>I strongly recommend against using any `<blink>` tags. - -I wish SmartyPants used named entities like `&mdash;` -instead of decimal-encoded entites like `&#8212;`. -</code></pre> - -<p>Output:</p> - -<pre><code><p>I strongly recommend against using any -<code>&lt;blink&gt;</code> tags.</p> - -<p>I wish SmartyPants used named entities like -<code>&amp;mdash;</code> instead of decimal-encoded -entites like <code>&amp;#8212;</code>.</p> -</code></pre> - -<p>To specify an entire block of pre-formatted code, indent every line of -the block by 4 spaces or 1 tab. Just like with code spans, <code>&</code>, <code><</code>, -and <code>></code> characters will be escaped automatically.</p> - -<p>Markdown:</p> - -<pre><code>If you want your page to validate under XHTML 1.0 Strict, -you've got to put paragraph tags in your blockquotes: - - <blockquote> - <p>For example.</p> - </blockquote> -</code></pre> - -<p>Output:</p> - -<pre><code><p>If you want your page to validate under XHTML 1.0 Strict, -you've got to put paragraph tags in your blockquotes:</p> - -<pre><code>&lt;blockquote&gt; - &lt;p&gt;For example.&lt;/p&gt; -&lt;/blockquote&gt; -</code></pre> -</code></pre> diff --git a/tests/MarkdownTest_1.0.3/Tests/Markdown Documentation - Basics.text b/tests/MarkdownTest_1.0.3/Tests/Markdown Documentation - Basics.text deleted file mode 100644 index 486055ca7..000000000 --- a/tests/MarkdownTest_1.0.3/Tests/Markdown Documentation - Basics.text +++ /dev/null @@ -1,306 +0,0 @@ -Markdown: Basics -================ - -<ul id="ProjectSubmenu"> - <li><a href="/projects/markdown/" title="Markdown Project Page">Main</a></li> - <li><a class="selected" title="Markdown Basics">Basics</a></li> - <li><a href="/projects/markdown/syntax" title="Markdown Syntax Documentation">Syntax</a></li> - <li><a href="/projects/markdown/license" title="Pricing and License Information">License</a></li> - <li><a href="/projects/markdown/dingus" title="Online Markdown Web Form">Dingus</a></li> -</ul> - - -Getting the Gist of Markdown's Formatting Syntax ------------------------------------------------- - -This page offers a brief overview of what it's like to use Markdown. -The [syntax page] [s] provides complete, detailed documentation for -every feature, but Markdown should be very easy to pick up simply by -looking at a few examples of it in action. The examples on this page -are written in a before/after style, showing example syntax and the -HTML output produced by Markdown. - -It's also helpful to simply try Markdown out; the [Dingus] [d] is a -web application that allows you type your own Markdown-formatted text -and translate it to XHTML. - -**Note:** This document is itself written using Markdown; you -can [see the source for it by adding '.text' to the URL] [src]. - - [s]: /projects/markdown/syntax "Markdown Syntax" - [d]: /projects/markdown/dingus "Markdown Dingus" - [src]: /projects/markdown/basics.text - - -## Paragraphs, Headers, Blockquotes ## - -A paragraph is simply one or more consecutive lines of text, separated -by one or more blank lines. (A blank line is any line that looks like a -blank line -- a line containing nothing spaces or tabs is considered -blank.) Normal paragraphs should not be intended with spaces or tabs. - -Markdown offers two styles of headers: *Setext* and *atx*. -Setext-style headers for `<h1>` and `<h2>` are created by -"underlining" with equal signs (`=`) and hyphens (`-`), respectively. -To create an atx-style header, you put 1-6 hash marks (`#`) at the -beginning of the line -- the number of hashes equals the resulting -HTML header level. - -Blockquotes are indicated using email-style '`>`' angle brackets. - -Markdown: - - A First Level Header - ==================== - - A Second Level Header - --------------------- - - Now is the time for all good men to come to - the aid of their country. This is just a - regular paragraph. - - The quick brown fox jumped over the lazy - dog's back. - - ### Header 3 - - > This is a blockquote. - > - > This is the second paragraph in the blockquote. - > - > ## This is an H2 in a blockquote - - -Output: - - <h1>A First Level Header</h1> - - <h2>A Second Level Header</h2> - - <p>Now is the time for all good men to come to - the aid of their country. This is just a - regular paragraph.</p> - - <p>The quick brown fox jumped over the lazy - dog's back.</p> - - <h3>Header 3</h3> - - <blockquote> - <p>This is a blockquote.</p> - - <p>This is the second paragraph in the blockquote.</p> - - <h2>This is an H2 in a blockquote</h2> - </blockquote> - - - -### Phrase Emphasis ### - -Markdown uses asterisks and underscores to indicate spans of emphasis. - -Markdown: - - Some of these words *are emphasized*. - Some of these words _are emphasized also_. - - Use two asterisks for **strong emphasis**. - Or, if you prefer, __use two underscores instead__. - -Output: - - <p>Some of these words <em>are emphasized</em>. - Some of these words <em>are emphasized also</em>.</p> - - <p>Use two asterisks for <strong>strong emphasis</strong>. - Or, if you prefer, <strong>use two underscores instead</strong>.</p> - - - -## Lists ## - -Unordered (bulleted) lists use asterisks, pluses, and hyphens (`*`, -`+`, and `-`) as list markers. These three markers are -interchangable; this: - - * Candy. - * Gum. - * Booze. - -this: - - + Candy. - + Gum. - + Booze. - -and this: - - - Candy. - - Gum. - - Booze. - -all produce the same output: - - <ul> - <li>Candy.</li> - <li>Gum.</li> - <li>Booze.</li> - </ul> - -Ordered (numbered) lists use regular numbers, followed by periods, as -list markers: - - 1. Red - 2. Green - 3. Blue - -Output: - - <ol> - <li>Red</li> - <li>Green</li> - <li>Blue</li> - </ol> - -If you put blank lines between items, you'll get `<p>` tags for the -list item text. You can create multi-paragraph list items by indenting -the paragraphs by 4 spaces or 1 tab: - - * A list item. - - With multiple paragraphs. - - * Another item in the list. - -Output: - - <ul> - <li><p>A list item.</p> - <p>With multiple paragraphs.</p></li> - <li><p>Another item in the list.</p></li> - </ul> - - - -### Links ### - -Markdown supports two styles for creating links: *inline* and -*reference*. With both styles, you use square brackets to delimit the -text you want to turn into a link. - -Inline-style links use parentheses immediately after the link text. -For example: - - This is an [example link](http://example.com/). - -Output: - - <p>This is an <a href="http://example.com/"> - example link</a>.</p> - -Optionally, you may include a title attribute in the parentheses: - - This is an [example link](http://example.com/ "With a Title"). - -Output: - - <p>This is an <a href="http://example.com/" title="With a Title"> - example link</a>.</p> - -Reference-style links allow you to refer to your links by names, which -you define elsewhere in your document: - - I get 10 times more traffic from [Google][1] than from - [Yahoo][2] or [MSN][3]. - - [1]: http://google.com/ "Google" - [2]: http://search.yahoo.com/ "Yahoo Search" - [3]: http://search.msn.com/ "MSN Search" - -Output: - - <p>I get 10 times more traffic from <a href="http://google.com/" - title="Google">Google</a> than from <a href="http://search.yahoo.com/" - title="Yahoo Search">Yahoo</a> or <a href="http://search.msn.com/" - title="MSN Search">MSN</a>.</p> - -The title attribute is optional. Link names may contain letters, -numbers and spaces, but are *not* case sensitive: - - I start my morning with a cup of coffee and - [The New York Times][NY Times]. - - [ny times]: http://www.nytimes.com/ - -Output: - - <p>I start my morning with a cup of coffee and - <a href="http://www.nytimes.com/">The New York Times</a>.</p> - - -### Images ### - -Image syntax is very much like link syntax. - -Inline (titles are optional): - -  - -Reference-style: - - ![alt text][id] - - [id]: /path/to/img.jpg "Title" - -Both of the above examples produce the same output: - - <img src="/path/to/img.jpg" alt="alt text" title="Title" /> - - - -### Code ### - -In a regular paragraph, you can create code span by wrapping text in -backtick quotes. Any ampersands (`&`) and angle brackets (`<` or -`>`) will automatically be translated into HTML entities. This makes -it easy to use Markdown to write about HTML example code: - - I strongly recommend against using any `<blink>` tags. - - I wish SmartyPants used named entities like `—` - instead of decimal-encoded entites like `—`. - -Output: - - <p>I strongly recommend against using any - <code><blink></code> tags.</p> - - <p>I wish SmartyPants used named entities like - <code>&mdash;</code> instead of decimal-encoded - entites like <code>&#8212;</code>.</p> - - -To specify an entire block of pre-formatted code, indent every line of -the block by 4 spaces or 1 tab. Just like with code spans, `&`, `<`, -and `>` characters will be escaped automatically. - -Markdown: - - If you want your page to validate under XHTML 1.0 Strict, - you've got to put paragraph tags in your blockquotes: - - <blockquote> - <p>For example.</p> - </blockquote> - -Output: - - <p>If you want your page to validate under XHTML 1.0 Strict, - you've got to put paragraph tags in your blockquotes:</p> - - <pre><code><blockquote> - <p>For example.</p> - </blockquote> - </code></pre> diff --git a/tests/MarkdownTest_1.0.3/Tests/Markdown Documentation - Syntax.html b/tests/MarkdownTest_1.0.3/Tests/Markdown Documentation - Syntax.html deleted file mode 100644 index 5c01306cc..000000000 --- a/tests/MarkdownTest_1.0.3/Tests/Markdown Documentation - Syntax.html +++ /dev/null @@ -1,942 +0,0 @@ -<h1>Markdown: Syntax</h1> - -<ul id="ProjectSubmenu"> - <li><a href="/projects/markdown/" title="Markdown Project Page">Main</a></li> - <li><a href="/projects/markdown/basics" title="Markdown Basics">Basics</a></li> - <li><a class="selected" title="Markdown Syntax Documentation">Syntax</a></li> - <li><a href="/projects/markdown/license" title="Pricing and License Information">License</a></li> - <li><a href="/projects/markdown/dingus" title="Online Markdown Web Form">Dingus</a></li> -</ul> - -<ul> -<li><a href="#overview">Overview</a> -<ul> -<li><a href="#philosophy">Philosophy</a></li> -<li><a href="#html">Inline HTML</a></li> -<li><a href="#autoescape">Automatic Escaping for Special Characters</a></li> -</ul></li> -<li><a href="#block">Block Elements</a> -<ul> -<li><a href="#p">Paragraphs and Line Breaks</a></li> -<li><a href="#header">Headers</a></li> -<li><a href="#blockquote">Blockquotes</a></li> -<li><a href="#list">Lists</a></li> -<li><a href="#precode">Code Blocks</a></li> -<li><a href="#hr">Horizontal Rules</a></li> -</ul></li> -<li><a href="#span">Span Elements</a> -<ul> -<li><a href="#link">Links</a></li> -<li><a href="#em">Emphasis</a></li> -<li><a href="#code">Code</a></li> -<li><a href="#img">Images</a></li> -</ul></li> -<li><a href="#misc">Miscellaneous</a> -<ul> -<li><a href="#backslash">Backslash Escapes</a></li> -<li><a href="#autolink">Automatic Links</a></li> -</ul></li> -</ul> - -<p><strong>Note:</strong> This document is itself written using Markdown; you -can <a href="/projects/markdown/syntax.text">see the source for it by adding '.text' to the URL</a>.</p> - -<hr /> - -<h2 id="overview">Overview</h2> - -<h3 id="philosophy">Philosophy</h3> - -<p>Markdown is intended to be as easy-to-read and easy-to-write as is feasible.</p> - -<p>Readability, however, is emphasized above all else. A Markdown-formatted -document should be publishable as-is, as plain text, without looking -like it's been marked up with tags or formatting instructions. While -Markdown's syntax has been influenced by several existing text-to-HTML -filters -- including <a href="http://docutils.sourceforge.net/mirror/setext.html">Setext</a>, <a href="http://www.aaronsw.com/2002/atx/">atx</a>, <a href="http://textism.com/tools/textile/">Textile</a>, <a href="http://docutils.sourceforge.net/rst.html">reStructuredText</a>, -<a href="http://www.triptico.com/software/grutatxt.html">Grutatext</a>, and <a href="http://ettext.taint.org/doc/">EtText</a> -- the single biggest source of -inspiration for Markdown's syntax is the format of plain text email.</p> - -<p>To this end, Markdown's syntax is comprised entirely of punctuation -characters, which punctuation characters have been carefully chosen so -as to look like what they mean. E.g., asterisks around a word actually -look like *emphasis*. Markdown lists look like, well, lists. Even -blockquotes look like quoted passages of text, assuming you've ever -used email.</p> - -<h3 id="html">Inline HTML</h3> - -<p>Markdown's syntax is intended for one purpose: to be used as a -format for <em>writing</em> for the web.</p> - -<p>Markdown is not a replacement for HTML, or even close to it. Its -syntax is very small, corresponding only to a very small subset of -HTML tags. The idea is <em>not</em> to create a syntax that makes it easier -to insert HTML tags. In my opinion, HTML tags are already easy to -insert. The idea for Markdown is to make it easy to read, write, and -edit prose. HTML is a <em>publishing</em> format; Markdown is a <em>writing</em> -format. Thus, Markdown's formatting syntax only addresses issues that -can be conveyed in plain text.</p> - -<p>For any markup that is not covered by Markdown's syntax, you simply -use HTML itself. There's no need to preface it or delimit it to -indicate that you're switching from Markdown to HTML; you just use -the tags.</p> - -<p>The only restrictions are that block-level HTML elements -- e.g. <code><div></code>, -<code><table></code>, <code><pre></code>, <code><p></code>, etc. -- must be separated from surrounding -content by blank lines, and the start and end tags of the block should -not be indented with tabs or spaces. Markdown is smart enough not -to add extra (unwanted) <code><p></code> tags around HTML block-level tags.</p> - -<p>For example, to add an HTML table to a Markdown article:</p> - -<pre><code>This is a regular paragraph. - -<table> - <tr> - <td>Foo</td> - </tr> -</table> - -This is another regular paragraph. -</code></pre> - -<p>Note that Markdown formatting syntax is not processed within block-level -HTML tags. E.g., you can't use Markdown-style <code>*emphasis*</code> inside an -HTML block.</p> - -<p>Span-level HTML tags -- e.g. <code><span></code>, <code><cite></code>, or <code><del></code> -- can be -used anywhere in a Markdown paragraph, list item, or header. If you -want, you can even use HTML tags instead of Markdown formatting; e.g. if -you'd prefer to use HTML <code><a></code> or <code><img></code> tags instead of Markdown's -link or image syntax, go right ahead.</p> - -<p>Unlike block-level HTML tags, Markdown syntax <em>is</em> processed within -span-level tags.</p> - -<h3 id="autoescape">Automatic Escaping for Special Characters</h3> - -<p>In HTML, there are two characters that demand special treatment: <code><</code> -and <code>&</code>. Left angle brackets are used to start tags; ampersands are -used to denote HTML entities. If you want to use them as literal -characters, you must escape them as entities, e.g. <code>&lt;</code>, and -<code>&amp;</code>.</p> - -<p>Ampersands in particular are bedeviling for web writers. If you want to -write about 'AT&T', you need to write '<code>AT&amp;T</code>'. You even need to -escape ampersands within URLs. Thus, if you want to link to:</p> - -<pre><code>http://images.google.com/images?num=30&q=larry+bird -</code></pre> - -<p>you need to encode the URL as:</p> - -<pre><code>http://images.google.com/images?num=30&amp;q=larry+bird -</code></pre> - -<p>in your anchor tag <code>href</code> attribute. Needless to say, this is easy to -forget, and is probably the single most common source of HTML validation -errors in otherwise well-marked-up web sites.</p> - -<p>Markdown allows you to use these characters naturally, taking care of -all the necessary escaping for you. If you use an ampersand as part of -an HTML entity, it remains unchanged; otherwise it will be translated -into <code>&amp;</code>.</p> - -<p>So, if you want to include a copyright symbol in your article, you can write:</p> - -<pre><code>&copy; -</code></pre> - -<p>and Markdown will leave it alone. But if you write:</p> - -<pre><code>AT&T -</code></pre> - -<p>Markdown will translate it to:</p> - -<pre><code>AT&amp;T -</code></pre> - -<p>Similarly, because Markdown supports <a href="#html">inline HTML</a>, if you use -angle brackets as delimiters for HTML tags, Markdown will treat them as -such. But if you write:</p> - -<pre><code>4 < 5 -</code></pre> - -<p>Markdown will translate it to:</p> - -<pre><code>4 &lt; 5 -</code></pre> - -<p>However, inside Markdown code spans and blocks, angle brackets and -ampersands are <em>always</em> encoded automatically. This makes it easy to use -Markdown to write about HTML code. (As opposed to raw HTML, which is a -terrible format for writing about HTML syntax, because every single <code><</code> -and <code>&</code> in your example code needs to be escaped.)</p> - -<hr /> - -<h2 id="block">Block Elements</h2> - -<h3 id="p">Paragraphs and Line Breaks</h3> - -<p>A paragraph is simply one or more consecutive lines of text, separated -by one or more blank lines. (A blank line is any line that looks like a -blank line -- a line containing nothing but spaces or tabs is considered -blank.) Normal paragraphs should not be intended with spaces or tabs.</p> - -<p>The implication of the "one or more consecutive lines of text" rule is -that Markdown supports "hard-wrapped" text paragraphs. This differs -significantly from most other text-to-HTML formatters (including Movable -Type's "Convert Line Breaks" option) which translate every line break -character in a paragraph into a <code><br /></code> tag.</p> - -<p>When you <em>do</em> want to insert a <code><br /></code> break tag using Markdown, you -end a line with two or more spaces, then type return.</p> - -<p>Yes, this takes a tad more effort to create a <code><br /></code>, but a simplistic -"every line break is a <code><br /></code>" rule wouldn't work for Markdown. -Markdown's email-style <a href="#blockquote">blockquoting</a> and multi-paragraph <a href="#list">list items</a> -work best -- and look better -- when you format them with hard breaks.</p> - -<h3 id="header">Headers</h3> - -<p>Markdown supports two styles of headers, <a href="http://docutils.sourceforge.net/mirror/setext.html">Setext</a> and <a href="http://www.aaronsw.com/2002/atx/">atx</a>.</p> - -<p>Setext-style headers are "underlined" using equal signs (for first-level -headers) and dashes (for second-level headers). For example:</p> - -<pre><code>This is an H1 -============= - -This is an H2 -------------- -</code></pre> - -<p>Any number of underlining <code>=</code>'s or <code>-</code>'s will work.</p> - -<p>Atx-style headers use 1-6 hash characters at the start of the line, -corresponding to header levels 1-6. For example:</p> - -<pre><code># This is an H1 - -## This is an H2 - -###### This is an H6 -</code></pre> - -<p>Optionally, you may "close" atx-style headers. This is purely -cosmetic -- you can use this if you think it looks better. The -closing hashes don't even need to match the number of hashes -used to open the header. (The number of opening hashes -determines the header level.) :</p> - -<pre><code># This is an H1 # - -## This is an H2 ## - -### This is an H3 ###### -</code></pre> - -<h3 id="blockquote">Blockquotes</h3> - -<p>Markdown uses email-style <code>></code> characters for blockquoting. If you're -familiar with quoting passages of text in an email message, then you -know how to create a blockquote in Markdown. It looks best if you hard -wrap the text and put a <code>></code> before every line:</p> - -<pre><code>> This is a blockquote with two paragraphs. Lorem ipsum dolor sit amet, -> consectetuer adipiscing elit. Aliquam hendrerit mi posuere lectus. -> Vestibulum enim wisi, viverra nec, fringilla in, laoreet vitae, risus. -> -> Donec sit amet nisl. Aliquam semper ipsum sit amet velit. Suspendisse -> id sem consectetuer libero luctus adipiscing. -</code></pre> - -<p>Markdown allows you to be lazy and only put the <code>></code> before the first -line of a hard-wrapped paragraph:</p> - -<pre><code>> This is a blockquote with two paragraphs. Lorem ipsum dolor sit amet, -consectetuer adipiscing elit. Aliquam hendrerit mi posuere lectus. -Vestibulum enim wisi, viverra nec, fringilla in, laoreet vitae, risus. - -> Donec sit amet nisl. Aliquam semper ipsum sit amet velit. Suspendisse -id sem consectetuer libero luctus adipiscing. -</code></pre> - -<p>Blockquotes can be nested (i.e. a blockquote-in-a-blockquote) by -adding additional levels of <code>></code>:</p> - -<pre><code>> This is the first level of quoting. -> -> > This is nested blockquote. -> -> Back to the first level. -</code></pre> - -<p>Blockquotes can contain other Markdown elements, including headers, lists, -and code blocks:</p> - -<pre><code>> ## This is a header. -> -> 1. This is the first list item. -> 2. This is the second list item. -> -> Here's some example code: -> -> return shell_exec("echo $input | $markdown_script"); -</code></pre> - -<p>Any decent text editor should make email-style quoting easy. For -example, with BBEdit, you can make a selection and choose Increase -Quote Level from the Text menu.</p> - -<h3 id="list">Lists</h3> - -<p>Markdown supports ordered (numbered) and unordered (bulleted) lists.</p> - -<p>Unordered lists use asterisks, pluses, and hyphens -- interchangably --- as list markers:</p> - -<pre><code>* Red -* Green -* Blue -</code></pre> - -<p>is equivalent to:</p> - -<pre><code>+ Red -+ Green -+ Blue -</code></pre> - -<p>and:</p> - -<pre><code>- Red -- Green -- Blue -</code></pre> - -<p>Ordered lists use numbers followed by periods:</p> - -<pre><code>1. Bird -2. McHale -3. Parish -</code></pre> - -<p>It's important to note that the actual numbers you use to mark the -list have no effect on the HTML output Markdown produces. The HTML -Markdown produces from the above list is:</p> - -<pre><code><ol> -<li>Bird</li> -<li>McHale</li> -<li>Parish</li> -</ol> -</code></pre> - -<p>If you instead wrote the list in Markdown like this:</p> - -<pre><code>1. Bird -1. McHale -1. Parish -</code></pre> - -<p>or even:</p> - -<pre><code>3. Bird -1. McHale -8. Parish -</code></pre> - -<p>you'd get the exact same HTML output. The point is, if you want to, -you can use ordinal numbers in your ordered Markdown lists, so that -the numbers in your source match the numbers in your published HTML. -But if you want to be lazy, you don't have to.</p> - -<p>If you do use lazy list numbering, however, you should still start the -list with the number 1. At some point in the future, Markdown may support -starting ordered lists at an arbitrary number.</p> - -<p>List markers typically start at the left margin, but may be indented by -up to three spaces. List markers must be followed by one or more spaces -or a tab.</p> - -<p>To make lists look nice, you can wrap items with hanging indents:</p> - -<pre><code>* Lorem ipsum dolor sit amet, consectetuer adipiscing elit. - Aliquam hendrerit mi posuere lectus. Vestibulum enim wisi, - viverra nec, fringilla in, laoreet vitae, risus. -* Donec sit amet nisl. Aliquam semper ipsum sit amet velit. - Suspendisse id sem consectetuer libero luctus adipiscing. -</code></pre> - -<p>But if you want to be lazy, you don't have to:</p> - -<pre><code>* Lorem ipsum dolor sit amet, consectetuer adipiscing elit. -Aliquam hendrerit mi posuere lectus. Vestibulum enim wisi, -viverra nec, fringilla in, laoreet vitae, risus. -* Donec sit amet nisl. Aliquam semper ipsum sit amet velit. -Suspendisse id sem consectetuer libero luctus adipiscing. -</code></pre> - -<p>If list items are separated by blank lines, Markdown will wrap the -items in <code><p></code> tags in the HTML output. For example, this input:</p> - -<pre><code>* Bird -* Magic -</code></pre> - -<p>will turn into:</p> - -<pre><code><ul> -<li>Bird</li> -<li>Magic</li> -</ul> -</code></pre> - -<p>But this:</p> - -<pre><code>* Bird - -* Magic -</code></pre> - -<p>will turn into:</p> - -<pre><code><ul> -<li><p>Bird</p></li> -<li><p>Magic</p></li> -</ul> -</code></pre> - -<p>List items may consist of multiple paragraphs. Each subsequent -paragraph in a list item must be intended by either 4 spaces -or one tab:</p> - -<pre><code>1. This is a list item with two paragraphs. Lorem ipsum dolor - sit amet, consectetuer adipiscing elit. Aliquam hendrerit - mi posuere lectus. - - Vestibulum enim wisi, viverra nec, fringilla in, laoreet - vitae, risus. Donec sit amet nisl. Aliquam semper ipsum - sit amet velit. - -2. Suspendisse id sem consectetuer libero luctus adipiscing. -</code></pre> - -<p>It looks nice if you indent every line of the subsequent -paragraphs, but here again, Markdown will allow you to be -lazy:</p> - -<pre><code>* This is a list item with two paragraphs. - - This is the second paragraph in the list item. You're -only required to indent the first line. Lorem ipsum dolor -sit amet, consectetuer adipiscing elit. - -* Another item in the same list. -</code></pre> - -<p>To put a blockquote within a list item, the blockquote's <code>></code> -delimiters need to be indented:</p> - -<pre><code>* A list item with a blockquote: - - > This is a blockquote - > inside a list item. -</code></pre> - -<p>To put a code block within a list item, the code block needs -to be indented <em>twice</em> -- 8 spaces or two tabs:</p> - -<pre><code>* A list item with a code block: - - <code goes here> -</code></pre> - -<p>It's worth noting that it's possible to trigger an ordered list by -accident, by writing something like this:</p> - -<pre><code>1986. What a great season. -</code></pre> - -<p>In other words, a <em>number-period-space</em> sequence at the beginning of a -line. To avoid this, you can backslash-escape the period:</p> - -<pre><code>1986\. What a great season. -</code></pre> - -<h3 id="precode">Code Blocks</h3> - -<p>Pre-formatted code blocks are used for writing about programming or -markup source code. Rather than forming normal paragraphs, the lines -of a code block are interpreted literally. Markdown wraps a code block -in both <code><pre></code> and <code><code></code> tags.</p> - -<p>To produce a code block in Markdown, simply indent every line of the -block by at least 4 spaces or 1 tab. For example, given this input:</p> - -<pre><code>This is a normal paragraph: - - This is a code block. -</code></pre> - -<p>Markdown will generate:</p> - -<pre><code><p>This is a normal paragraph:</p> - -<pre><code>This is a code block. -</code></pre> -</code></pre> - -<p>One level of indentation -- 4 spaces or 1 tab -- is removed from each -line of the code block. For example, this:</p> - -<pre><code>Here is an example of AppleScript: - - tell application "Foo" - beep - end tell -</code></pre> - -<p>will turn into:</p> - -<pre><code><p>Here is an example of AppleScript:</p> - -<pre><code>tell application "Foo" - beep -end tell -</code></pre> -</code></pre> - -<p>A code block continues until it reaches a line that is not indented -(or the end of the article).</p> - -<p>Within a code block, ampersands (<code>&</code>) and angle brackets (<code><</code> and <code>></code>) -are automatically converted into HTML entities. This makes it very -easy to include example HTML source code using Markdown -- just paste -it and indent it, and Markdown will handle the hassle of encoding the -ampersands and angle brackets. For example, this:</p> - -<pre><code> <div class="footer"> - &copy; 2004 Foo Corporation - </div> -</code></pre> - -<p>will turn into:</p> - -<pre><code><pre><code>&lt;div class="footer"&gt; - &amp;copy; 2004 Foo Corporation -&lt;/div&gt; -</code></pre> -</code></pre> - -<p>Regular Markdown syntax is not processed within code blocks. E.g., -asterisks are just literal asterisks within a code block. This means -it's also easy to use Markdown to write about Markdown's own syntax.</p> - -<h3 id="hr">Horizontal Rules</h3> - -<p>You can produce a horizontal rule tag (<code><hr /></code>) by placing three or -more hyphens, asterisks, or underscores on a line by themselves. If you -wish, you may use spaces between the hyphens or asterisks. Each of the -following lines will produce a horizontal rule:</p> - -<pre><code>* * * - -*** - -***** - -- - - - ---------------------------------------- - -_ _ _ -</code></pre> - -<hr /> - -<h2 id="span">Span Elements</h2> - -<h3 id="link">Links</h3> - -<p>Markdown supports two style of links: <em>inline</em> and <em>reference</em>.</p> - -<p>In both styles, the link text is delimited by [square brackets].</p> - -<p>To create an inline link, use a set of regular parentheses immediately -after the link text's closing square bracket. Inside the parentheses, -put the URL where you want the link to point, along with an <em>optional</em> -title for the link, surrounded in quotes. For example:</p> - -<pre><code>This is [an example](http://example.com/ "Title") inline link. - -[This link](http://example.net/) has no title attribute. -</code></pre> - -<p>Will produce:</p> - -<pre><code><p>This is <a href="http://example.com/" title="Title"> -an example</a> inline link.</p> - -<p><a href="http://example.net/">This link</a> has no -title attribute.</p> -</code></pre> - -<p>If you're referring to a local resource on the same server, you can -use relative paths:</p> - -<pre><code>See my [About](/about/) page for details. -</code></pre> - -<p>Reference-style links use a second set of square brackets, inside -which you place a label of your choosing to identify the link:</p> - -<pre><code>This is [an example][id] reference-style link. -</code></pre> - -<p>You can optionally use a space to separate the sets of brackets:</p> - -<pre><code>This is [an example] [id] reference-style link. -</code></pre> - -<p>Then, anywhere in the document, you define your link label like this, -on a line by itself:</p> - -<pre><code>[id]: http://example.com/ "Optional Title Here" -</code></pre> - -<p>That is:</p> - -<ul> -<li>Square brackets containing the link identifier (optionally -indented from the left margin using up to three spaces);</li> -<li>followed by a colon;</li> -<li>followed by one or more spaces (or tabs);</li> -<li>followed by the URL for the link;</li> -<li>optionally followed by a title attribute for the link, enclosed -in double or single quotes.</li> -</ul> - -<p>The link URL may, optionally, be surrounded by angle brackets:</p> - -<pre><code>[id]: <http://example.com/> "Optional Title Here" -</code></pre> - -<p>You can put the title attribute on the next line and use extra spaces -or tabs for padding, which tends to look better with longer URLs:</p> - -<pre><code>[id]: http://example.com/longish/path/to/resource/here - "Optional Title Here" -</code></pre> - -<p>Link definitions are only used for creating links during Markdown -processing, and are stripped from your document in the HTML output.</p> - -<p>Link definition names may constist of letters, numbers, spaces, and punctuation -- but they are <em>not</em> case sensitive. E.g. these two links:</p> - -<pre><code>[link text][a] -[link text][A] -</code></pre> - -<p>are equivalent.</p> - -<p>The <em>implicit link name</em> shortcut allows you to omit the name of the -link, in which case the link text itself is used as the name. -Just use an empty set of square brackets -- e.g., to link the word -"Google" to the google.com web site, you could simply write:</p> - -<pre><code>[Google][] -</code></pre> - -<p>And then define the link:</p> - -<pre><code>[Google]: http://google.com/ -</code></pre> - -<p>Because link names may contain spaces, this shortcut even works for -multiple words in the link text:</p> - -<pre><code>Visit [Daring Fireball][] for more information. -</code></pre> - -<p>And then define the link:</p> - -<pre><code>[Daring Fireball]: http://daringfireball.net/ -</code></pre> - -<p>Link definitions can be placed anywhere in your Markdown document. I -tend to put them immediately after each paragraph in which they're -used, but if you want, you can put them all at the end of your -document, sort of like footnotes.</p> - -<p>Here's an example of reference links in action:</p> - -<pre><code>I get 10 times more traffic from [Google] [1] than from -[Yahoo] [2] or [MSN] [3]. - - [1]: http://google.com/ "Google" - [2]: http://search.yahoo.com/ "Yahoo Search" - [3]: http://search.msn.com/ "MSN Search" -</code></pre> - -<p>Using the implicit link name shortcut, you could instead write:</p> - -<pre><code>I get 10 times more traffic from [Google][] than from -[Yahoo][] or [MSN][]. - - [google]: http://google.com/ "Google" - [yahoo]: http://search.yahoo.com/ "Yahoo Search" - [msn]: http://search.msn.com/ "MSN Search" -</code></pre> - -<p>Both of the above examples will produce the following HTML output:</p> - -<pre><code><p>I get 10 times more traffic from <a href="http://google.com/" -title="Google">Google</a> than from -<a href="http://search.yahoo.com/" title="Yahoo Search">Yahoo</a> -or <a href="http://search.msn.com/" title="MSN Search">MSN</a>.</p> -</code></pre> - -<p>For comparison, here is the same paragraph written using -Markdown's inline link style:</p> - -<pre><code>I get 10 times more traffic from [Google](http://google.com/ "Google") -than from [Yahoo](http://search.yahoo.com/ "Yahoo Search") or -[MSN](http://search.msn.com/ "MSN Search"). -</code></pre> - -<p>The point of reference-style links is not that they're easier to -write. The point is that with reference-style links, your document -source is vastly more readable. Compare the above examples: using -reference-style links, the paragraph itself is only 81 characters -long; with inline-style links, it's 176 characters; and as raw HTML, -it's 234 characters. In the raw HTML, there's more markup than there -is text.</p> - -<p>With Markdown's reference-style links, a source document much more -closely resembles the final output, as rendered in a browser. By -allowing you to move the markup-related metadata out of the paragraph, -you can add links without interrupting the narrative flow of your -prose.</p> - -<h3 id="em">Emphasis</h3> - -<p>Markdown treats asterisks (<code>*</code>) and underscores (<code>_</code>) as indicators of -emphasis. Text wrapped with one <code>*</code> or <code>_</code> will be wrapped with an -HTML <code><em></code> tag; double <code>*</code>'s or <code>_</code>'s will be wrapped with an HTML -<code><strong></code> tag. E.g., this input:</p> - -<pre><code>*single asterisks* - -_single underscores_ - -**double asterisks** - -__double underscores__ -</code></pre> - -<p>will produce:</p> - -<pre><code><em>single asterisks</em> - -<em>single underscores</em> - -<strong>double asterisks</strong> - -<strong>double underscores</strong> -</code></pre> - -<p>You can use whichever style you prefer; the lone restriction is that -the same character must be used to open and close an emphasis span.</p> - -<p>Emphasis can be used in the middle of a word:</p> - -<pre><code>un*fucking*believable -</code></pre> - -<p>But if you surround an <code>*</code> or <code>_</code> with spaces, it'll be treated as a -literal asterisk or underscore.</p> - -<p>To produce a literal asterisk or underscore at a position where it -would otherwise be used as an emphasis delimiter, you can backslash -escape it:</p> - -<pre><code>\*this text is surrounded by literal asterisks\* -</code></pre> - -<h3 id="code">Code</h3> - -<p>To indicate a span of code, wrap it with backtick quotes (<code>`</code>). -Unlike a pre-formatted code block, a code span indicates code within a -normal paragraph. For example:</p> - -<pre><code>Use the `printf()` function. -</code></pre> - -<p>will produce:</p> - -<pre><code><p>Use the <code>printf()</code> function.</p> -</code></pre> - -<p>To include a literal backtick character within a code span, you can use -multiple backticks as the opening and closing delimiters:</p> - -<pre><code>``There is a literal backtick (`) here.`` -</code></pre> - -<p>which will produce this:</p> - -<pre><code><p><code>There is a literal backtick (`) here.</code></p> -</code></pre> - -<p>The backtick delimiters surrounding a code span may include spaces -- -one after the opening, one before the closing. This allows you to place -literal backtick characters at the beginning or end of a code span:</p> - -<pre><code>A single backtick in a code span: `` ` `` - -A backtick-delimited string in a code span: `` `foo` `` -</code></pre> - -<p>will produce:</p> - -<pre><code><p>A single backtick in a code span: <code>`</code></p> - -<p>A backtick-delimited string in a code span: <code>`foo`</code></p> -</code></pre> - -<p>With a code span, ampersands and angle brackets are encoded as HTML -entities automatically, which makes it easy to include example HTML -tags. Markdown will turn this:</p> - -<pre><code>Please don't use any `<blink>` tags. -</code></pre> - -<p>into:</p> - -<pre><code><p>Please don't use any <code>&lt;blink&gt;</code> tags.</p> -</code></pre> - -<p>You can write this:</p> - -<pre><code>`&#8212;` is the decimal-encoded equivalent of `&mdash;`. -</code></pre> - -<p>to produce:</p> - -<pre><code><p><code>&amp;#8212;</code> is the decimal-encoded -equivalent of <code>&amp;mdash;</code>.</p> -</code></pre> - -<h3 id="img">Images</h3> - -<p>Admittedly, it's fairly difficult to devise a "natural" syntax for -placing images into a plain text document format.</p> - -<p>Markdown uses an image syntax that is intended to resemble the syntax -for links, allowing for two styles: <em>inline</em> and <em>reference</em>.</p> - -<p>Inline image syntax looks like this:</p> - -<pre><code> - - -</code></pre> - -<p>That is:</p> - -<ul> -<li>An exclamation mark: <code>!</code>;</li> -<li>followed by a set of square brackets, containing the <code>alt</code> -attribute text for the image;</li> -<li>followed by a set of parentheses, containing the URL or path to -the image, and an optional <code>title</code> attribute enclosed in double -or single quotes.</li> -</ul> - -<p>Reference-style image syntax looks like this:</p> - -<pre><code>![Alt text][id] -</code></pre> - -<p>Where "id" is the name of a defined image reference. Image references -are defined using syntax identical to link references:</p> - -<pre><code>[id]: url/to/image "Optional title attribute" -</code></pre> - -<p>As of this writing, Markdown has no syntax for specifying the -dimensions of an image; if this is important to you, you can simply -use regular HTML <code><img></code> tags.</p> - -<hr /> - -<h2 id="misc">Miscellaneous</h2> - -<h3 id="autolink">Automatic Links</h3> - -<p>Markdown supports a shortcut style for creating "automatic" links for URLs and email addresses: simply surround the URL or email address with angle brackets. What this means is that if you want to show the actual text of a URL or email address, and also have it be a clickable link, you can do this:</p> - -<pre><code><http://example.com/> -</code></pre> - -<p>Markdown will turn this into:</p> - -<pre><code><a href="http://example.com/">http://example.com/</a> -</code></pre> - -<p>Automatic links for email addresses work similarly, except that -Markdown will also perform a bit of randomized decimal and hex -entity-encoding to help obscure your address from address-harvesting -spambots. For example, Markdown will turn this:</p> - -<pre><code><address@example.com> -</code></pre> - -<p>into something like this:</p> - -<pre><code><a href="&#x6D;&#x61;i&#x6C;&#x74;&#x6F;:&#x61;&#x64;&#x64;&#x72;&#x65; -&#115;&#115;&#64;&#101;&#120;&#x61;&#109;&#x70;&#x6C;e&#x2E;&#99;&#111; -&#109;">&#x61;&#x64;&#x64;&#x72;&#x65;&#115;&#115;&#64;&#101;&#120;&#x61; -&#109;&#x70;&#x6C;e&#x2E;&#99;&#111;&#109;</a> -</code></pre> - -<p>which will render in a browser as a clickable link to "address@example.com".</p> - -<p>(This sort of entity-encoding trick will indeed fool many, if not -most, address-harvesting bots, but it definitely won't fool all of -them. It's better than nothing, but an address published in this way -will probably eventually start receiving spam.)</p> - -<h3 id="backslash">Backslash Escapes</h3> - -<p>Markdown allows you to use backslash escapes to generate literal -characters which would otherwise have special meaning in Markdown's -formatting syntax. For example, if you wanted to surround a word with -literal asterisks (instead of an HTML <code><em></code> tag), you can backslashes -before the asterisks, like this:</p> - -<pre><code>\*literal asterisks\* -</code></pre> - -<p>Markdown provides backslash escapes for the following characters:</p> - -<pre><code>\ backslash -` backtick -* asterisk -_ underscore -{} curly braces -[] square brackets -() parentheses -# hash mark -+ plus sign -- minus sign (hyphen) -. dot -! exclamation mark -</code></pre> diff --git a/tests/MarkdownTest_1.0.3/Tests/Markdown Documentation - Syntax.text b/tests/MarkdownTest_1.0.3/Tests/Markdown Documentation - Syntax.text deleted file mode 100644 index 57360a16c..000000000 --- a/tests/MarkdownTest_1.0.3/Tests/Markdown Documentation - Syntax.text +++ /dev/null @@ -1,888 +0,0 @@ -Markdown: Syntax -================ - -<ul id="ProjectSubmenu"> - <li><a href="/projects/markdown/" title="Markdown Project Page">Main</a></li> - <li><a href="/projects/markdown/basics" title="Markdown Basics">Basics</a></li> - <li><a class="selected" title="Markdown Syntax Documentation">Syntax</a></li> - <li><a href="/projects/markdown/license" title="Pricing and License Information">License</a></li> - <li><a href="/projects/markdown/dingus" title="Online Markdown Web Form">Dingus</a></li> -</ul> - - -* [Overview](#overview) - * [Philosophy](#philosophy) - * [Inline HTML](#html) - * [Automatic Escaping for Special Characters](#autoescape) -* [Block Elements](#block) - * [Paragraphs and Line Breaks](#p) - * [Headers](#header) - * [Blockquotes](#blockquote) - * [Lists](#list) - * [Code Blocks](#precode) - * [Horizontal Rules](#hr) -* [Span Elements](#span) - * [Links](#link) - * [Emphasis](#em) - * [Code](#code) - * [Images](#img) -* [Miscellaneous](#misc) - * [Backslash Escapes](#backslash) - * [Automatic Links](#autolink) - - -**Note:** This document is itself written using Markdown; you -can [see the source for it by adding '.text' to the URL][src]. - - [src]: /projects/markdown/syntax.text - -* * * - -<h2 id="overview">Overview</h2> - -<h3 id="philosophy">Philosophy</h3> - -Markdown is intended to be as easy-to-read and easy-to-write as is feasible. - -Readability, however, is emphasized above all else. A Markdown-formatted -document should be publishable as-is, as plain text, without looking -like it's been marked up with tags or formatting instructions. While -Markdown's syntax has been influenced by several existing text-to-HTML -filters -- including [Setext] [1], [atx] [2], [Textile] [3], [reStructuredText] [4], -[Grutatext] [5], and [EtText] [6] -- the single biggest source of -inspiration for Markdown's syntax is the format of plain text email. - - [1]: http://docutils.sourceforge.net/mirror/setext.html - [2]: http://www.aaronsw.com/2002/atx/ - [3]: http://textism.com/tools/textile/ - [4]: http://docutils.sourceforge.net/rst.html - [5]: http://www.triptico.com/software/grutatxt.html - [6]: http://ettext.taint.org/doc/ - -To this end, Markdown's syntax is comprised entirely of punctuation -characters, which punctuation characters have been carefully chosen so -as to look like what they mean. E.g., asterisks around a word actually -look like \*emphasis\*. Markdown lists look like, well, lists. Even -blockquotes look like quoted passages of text, assuming you've ever -used email. - - - -<h3 id="html">Inline HTML</h3> - -Markdown's syntax is intended for one purpose: to be used as a -format for *writing* for the web. - -Markdown is not a replacement for HTML, or even close to it. Its -syntax is very small, corresponding only to a very small subset of -HTML tags. The idea is *not* to create a syntax that makes it easier -to insert HTML tags. In my opinion, HTML tags are already easy to -insert. The idea for Markdown is to make it easy to read, write, and -edit prose. HTML is a *publishing* format; Markdown is a *writing* -format. Thus, Markdown's formatting syntax only addresses issues that -can be conveyed in plain text. - -For any markup that is not covered by Markdown's syntax, you simply -use HTML itself. There's no need to preface it or delimit it to -indicate that you're switching from Markdown to HTML; you just use -the tags. - -The only restrictions are that block-level HTML elements -- e.g. `<div>`, -`<table>`, `<pre>`, `<p>`, etc. -- must be separated from surrounding -content by blank lines, and the start and end tags of the block should -not be indented with tabs or spaces. Markdown is smart enough not -to add extra (unwanted) `<p>` tags around HTML block-level tags. - -For example, to add an HTML table to a Markdown article: - - This is a regular paragraph. - - <table> - <tr> - <td>Foo</td> - </tr> - </table> - - This is another regular paragraph. - -Note that Markdown formatting syntax is not processed within block-level -HTML tags. E.g., you can't use Markdown-style `*emphasis*` inside an -HTML block. - -Span-level HTML tags -- e.g. `<span>`, `<cite>`, or `<del>` -- can be -used anywhere in a Markdown paragraph, list item, or header. If you -want, you can even use HTML tags instead of Markdown formatting; e.g. if -you'd prefer to use HTML `<a>` or `<img>` tags instead of Markdown's -link or image syntax, go right ahead. - -Unlike block-level HTML tags, Markdown syntax *is* processed within -span-level tags. - - -<h3 id="autoescape">Automatic Escaping for Special Characters</h3> - -In HTML, there are two characters that demand special treatment: `<` -and `&`. Left angle brackets are used to start tags; ampersands are -used to denote HTML entities. If you want to use them as literal -characters, you must escape them as entities, e.g. `<`, and -`&`. - -Ampersands in particular are bedeviling for web writers. If you want to -write about 'AT&T', you need to write '`AT&T`'. You even need to -escape ampersands within URLs. Thus, if you want to link to: - - http://images.google.com/images?num=30&q=larry+bird - -you need to encode the URL as: - - http://images.google.com/images?num=30&q=larry+bird - -in your anchor tag `href` attribute. Needless to say, this is easy to -forget, and is probably the single most common source of HTML validation -errors in otherwise well-marked-up web sites. - -Markdown allows you to use these characters naturally, taking care of -all the necessary escaping for you. If you use an ampersand as part of -an HTML entity, it remains unchanged; otherwise it will be translated -into `&`. - -So, if you want to include a copyright symbol in your article, you can write: - - © - -and Markdown will leave it alone. But if you write: - - AT&T - -Markdown will translate it to: - - AT&T - -Similarly, because Markdown supports [inline HTML](#html), if you use -angle brackets as delimiters for HTML tags, Markdown will treat them as -such. But if you write: - - 4 < 5 - -Markdown will translate it to: - - 4 < 5 - -However, inside Markdown code spans and blocks, angle brackets and -ampersands are *always* encoded automatically. This makes it easy to use -Markdown to write about HTML code. (As opposed to raw HTML, which is a -terrible format for writing about HTML syntax, because every single `<` -and `&` in your example code needs to be escaped.) - - -* * * - - -<h2 id="block">Block Elements</h2> - - -<h3 id="p">Paragraphs and Line Breaks</h3> - -A paragraph is simply one or more consecutive lines of text, separated -by one or more blank lines. (A blank line is any line that looks like a -blank line -- a line containing nothing but spaces or tabs is considered -blank.) Normal paragraphs should not be intended with spaces or tabs. - -The implication of the "one or more consecutive lines of text" rule is -that Markdown supports "hard-wrapped" text paragraphs. This differs -significantly from most other text-to-HTML formatters (including Movable -Type's "Convert Line Breaks" option) which translate every line break -character in a paragraph into a `<br />` tag. - -When you *do* want to insert a `<br />` break tag using Markdown, you -end a line with two or more spaces, then type return. - -Yes, this takes a tad more effort to create a `<br />`, but a simplistic -"every line break is a `<br />`" rule wouldn't work for Markdown. -Markdown's email-style [blockquoting][bq] and multi-paragraph [list items][l] -work best -- and look better -- when you format them with hard breaks. - - [bq]: #blockquote - [l]: #list - - - -<h3 id="header">Headers</h3> - -Markdown supports two styles of headers, [Setext] [1] and [atx] [2]. - -Setext-style headers are "underlined" using equal signs (for first-level -headers) and dashes (for second-level headers). For example: - - This is an H1 - ============= - - This is an H2 - ------------- - -Any number of underlining `=`'s or `-`'s will work. - -Atx-style headers use 1-6 hash characters at the start of the line, -corresponding to header levels 1-6. For example: - - # This is an H1 - - ## This is an H2 - - ###### This is an H6 - -Optionally, you may "close" atx-style headers. This is purely -cosmetic -- you can use this if you think it looks better. The -closing hashes don't even need to match the number of hashes -used to open the header. (The number of opening hashes -determines the header level.) : - - # This is an H1 # - - ## This is an H2 ## - - ### This is an H3 ###### - - -<h3 id="blockquote">Blockquotes</h3> - -Markdown uses email-style `>` characters for blockquoting. If you're -familiar with quoting passages of text in an email message, then you -know how to create a blockquote in Markdown. It looks best if you hard -wrap the text and put a `>` before every line: - - > This is a blockquote with two paragraphs. Lorem ipsum dolor sit amet, - > consectetuer adipiscing elit. Aliquam hendrerit mi posuere lectus. - > Vestibulum enim wisi, viverra nec, fringilla in, laoreet vitae, risus. - > - > Donec sit amet nisl. Aliquam semper ipsum sit amet velit. Suspendisse - > id sem consectetuer libero luctus adipiscing. - -Markdown allows you to be lazy and only put the `>` before the first -line of a hard-wrapped paragraph: - - > This is a blockquote with two paragraphs. Lorem ipsum dolor sit amet, - consectetuer adipiscing elit. Aliquam hendrerit mi posuere lectus. - Vestibulum enim wisi, viverra nec, fringilla in, laoreet vitae, risus. - - > Donec sit amet nisl. Aliquam semper ipsum sit amet velit. Suspendisse - id sem consectetuer libero luctus adipiscing. - -Blockquotes can be nested (i.e. a blockquote-in-a-blockquote) by -adding additional levels of `>`: - - > This is the first level of quoting. - > - > > This is nested blockquote. - > - > Back to the first level. - -Blockquotes can contain other Markdown elements, including headers, lists, -and code blocks: - - > ## This is a header. - > - > 1. This is the first list item. - > 2. This is the second list item. - > - > Here's some example code: - > - > return shell_exec("echo $input | $markdown_script"); - -Any decent text editor should make email-style quoting easy. For -example, with BBEdit, you can make a selection and choose Increase -Quote Level from the Text menu. - - -<h3 id="list">Lists</h3> - -Markdown supports ordered (numbered) and unordered (bulleted) lists. - -Unordered lists use asterisks, pluses, and hyphens -- interchangably --- as list markers: - - * Red - * Green - * Blue - -is equivalent to: - - + Red - + Green - + Blue - -and: - - - Red - - Green - - Blue - -Ordered lists use numbers followed by periods: - - 1. Bird - 2. McHale - 3. Parish - -It's important to note that the actual numbers you use to mark the -list have no effect on the HTML output Markdown produces. The HTML -Markdown produces from the above list is: - - <ol> - <li>Bird</li> - <li>McHale</li> - <li>Parish</li> - </ol> - -If you instead wrote the list in Markdown like this: - - 1. Bird - 1. McHale - 1. Parish - -or even: - - 3. Bird - 1. McHale - 8. Parish - -you'd get the exact same HTML output. The point is, if you want to, -you can use ordinal numbers in your ordered Markdown lists, so that -the numbers in your source match the numbers in your published HTML. -But if you want to be lazy, you don't have to. - -If you do use lazy list numbering, however, you should still start the -list with the number 1. At some point in the future, Markdown may support -starting ordered lists at an arbitrary number. - -List markers typically start at the left margin, but may be indented by -up to three spaces. List markers must be followed by one or more spaces -or a tab. - -To make lists look nice, you can wrap items with hanging indents: - - * Lorem ipsum dolor sit amet, consectetuer adipiscing elit. - Aliquam hendrerit mi posuere lectus. Vestibulum enim wisi, - viverra nec, fringilla in, laoreet vitae, risus. - * Donec sit amet nisl. Aliquam semper ipsum sit amet velit. - Suspendisse id sem consectetuer libero luctus adipiscing. - -But if you want to be lazy, you don't have to: - - * Lorem ipsum dolor sit amet, consectetuer adipiscing elit. - Aliquam hendrerit mi posuere lectus. Vestibulum enim wisi, - viverra nec, fringilla in, laoreet vitae, risus. - * Donec sit amet nisl. Aliquam semper ipsum sit amet velit. - Suspendisse id sem consectetuer libero luctus adipiscing. - -If list items are separated by blank lines, Markdown will wrap the -items in `<p>` tags in the HTML output. For example, this input: - - * Bird - * Magic - -will turn into: - - <ul> - <li>Bird</li> - <li>Magic</li> - </ul> - -But this: - - * Bird - - * Magic - -will turn into: - - <ul> - <li><p>Bird</p></li> - <li><p>Magic</p></li> - </ul> - -List items may consist of multiple paragraphs. Each subsequent -paragraph in a list item must be intended by either 4 spaces -or one tab: - - 1. This is a list item with two paragraphs. Lorem ipsum dolor - sit amet, consectetuer adipiscing elit. Aliquam hendrerit - mi posuere lectus. - - Vestibulum enim wisi, viverra nec, fringilla in, laoreet - vitae, risus. Donec sit amet nisl. Aliquam semper ipsum - sit amet velit. - - 2. Suspendisse id sem consectetuer libero luctus adipiscing. - -It looks nice if you indent every line of the subsequent -paragraphs, but here again, Markdown will allow you to be -lazy: - - * This is a list item with two paragraphs. - - This is the second paragraph in the list item. You're - only required to indent the first line. Lorem ipsum dolor - sit amet, consectetuer adipiscing elit. - - * Another item in the same list. - -To put a blockquote within a list item, the blockquote's `>` -delimiters need to be indented: - - * A list item with a blockquote: - - > This is a blockquote - > inside a list item. - -To put a code block within a list item, the code block needs -to be indented *twice* -- 8 spaces or two tabs: - - * A list item with a code block: - - <code goes here> - - -It's worth noting that it's possible to trigger an ordered list by -accident, by writing something like this: - - 1986. What a great season. - -In other words, a *number-period-space* sequence at the beginning of a -line. To avoid this, you can backslash-escape the period: - - 1986\. What a great season. - - - -<h3 id="precode">Code Blocks</h3> - -Pre-formatted code blocks are used for writing about programming or -markup source code. Rather than forming normal paragraphs, the lines -of a code block are interpreted literally. Markdown wraps a code block -in both `<pre>` and `<code>` tags. - -To produce a code block in Markdown, simply indent every line of the -block by at least 4 spaces or 1 tab. For example, given this input: - - This is a normal paragraph: - - This is a code block. - -Markdown will generate: - - <p>This is a normal paragraph:</p> - - <pre><code>This is a code block. - </code></pre> - -One level of indentation -- 4 spaces or 1 tab -- is removed from each -line of the code block. For example, this: - - Here is an example of AppleScript: - - tell application "Foo" - beep - end tell - -will turn into: - - <p>Here is an example of AppleScript:</p> - - <pre><code>tell application "Foo" - beep - end tell - </code></pre> - -A code block continues until it reaches a line that is not indented -(or the end of the article). - -Within a code block, ampersands (`&`) and angle brackets (`<` and `>`) -are automatically converted into HTML entities. This makes it very -easy to include example HTML source code using Markdown -- just paste -it and indent it, and Markdown will handle the hassle of encoding the -ampersands and angle brackets. For example, this: - - <div class="footer"> - © 2004 Foo Corporation - </div> - -will turn into: - - <pre><code><div class="footer"> - &copy; 2004 Foo Corporation - </div> - </code></pre> - -Regular Markdown syntax is not processed within code blocks. E.g., -asterisks are just literal asterisks within a code block. This means -it's also easy to use Markdown to write about Markdown's own syntax. - - - -<h3 id="hr">Horizontal Rules</h3> - -You can produce a horizontal rule tag (`<hr />`) by placing three or -more hyphens, asterisks, or underscores on a line by themselves. If you -wish, you may use spaces between the hyphens or asterisks. Each of the -following lines will produce a horizontal rule: - - * * * - - *** - - ***** - - - - - - - --------------------------------------- - - _ _ _ - - -* * * - -<h2 id="span">Span Elements</h2> - -<h3 id="link">Links</h3> - -Markdown supports two style of links: *inline* and *reference*. - -In both styles, the link text is delimited by [square brackets]. - -To create an inline link, use a set of regular parentheses immediately -after the link text's closing square bracket. Inside the parentheses, -put the URL where you want the link to point, along with an *optional* -title for the link, surrounded in quotes. For example: - - This is [an example](http://example.com/ "Title") inline link. - - [This link](http://example.net/) has no title attribute. - -Will produce: - - <p>This is <a href="http://example.com/" title="Title"> - an example</a> inline link.</p> - - <p><a href="http://example.net/">This link</a> has no - title attribute.</p> - -If you're referring to a local resource on the same server, you can -use relative paths: - - See my [About](/about/) page for details. - -Reference-style links use a second set of square brackets, inside -which you place a label of your choosing to identify the link: - - This is [an example][id] reference-style link. - -You can optionally use a space to separate the sets of brackets: - - This is [an example] [id] reference-style link. - -Then, anywhere in the document, you define your link label like this, -on a line by itself: - - [id]: http://example.com/ "Optional Title Here" - -That is: - -* Square brackets containing the link identifier (optionally - indented from the left margin using up to three spaces); -* followed by a colon; -* followed by one or more spaces (or tabs); -* followed by the URL for the link; -* optionally followed by a title attribute for the link, enclosed - in double or single quotes. - -The link URL may, optionally, be surrounded by angle brackets: - - [id]: <http://example.com/> "Optional Title Here" - -You can put the title attribute on the next line and use extra spaces -or tabs for padding, which tends to look better with longer URLs: - - [id]: http://example.com/longish/path/to/resource/here - "Optional Title Here" - -Link definitions are only used for creating links during Markdown -processing, and are stripped from your document in the HTML output. - -Link definition names may constist of letters, numbers, spaces, and punctuation -- but they are *not* case sensitive. E.g. these two links: - - [link text][a] - [link text][A] - -are equivalent. - -The *implicit link name* shortcut allows you to omit the name of the -link, in which case the link text itself is used as the name. -Just use an empty set of square brackets -- e.g., to link the word -"Google" to the google.com web site, you could simply write: - - [Google][] - -And then define the link: - - [Google]: http://google.com/ - -Because link names may contain spaces, this shortcut even works for -multiple words in the link text: - - Visit [Daring Fireball][] for more information. - -And then define the link: - - [Daring Fireball]: http://daringfireball.net/ - -Link definitions can be placed anywhere in your Markdown document. I -tend to put them immediately after each paragraph in which they're -used, but if you want, you can put them all at the end of your -document, sort of like footnotes. - -Here's an example of reference links in action: - - I get 10 times more traffic from [Google] [1] than from - [Yahoo] [2] or [MSN] [3]. - - [1]: http://google.com/ "Google" - [2]: http://search.yahoo.com/ "Yahoo Search" - [3]: http://search.msn.com/ "MSN Search" - -Using the implicit link name shortcut, you could instead write: - - I get 10 times more traffic from [Google][] than from - [Yahoo][] or [MSN][]. - - [google]: http://google.com/ "Google" - [yahoo]: http://search.yahoo.com/ "Yahoo Search" - [msn]: http://search.msn.com/ "MSN Search" - -Both of the above examples will produce the following HTML output: - - <p>I get 10 times more traffic from <a href="http://google.com/" - title="Google">Google</a> than from - <a href="http://search.yahoo.com/" title="Yahoo Search">Yahoo</a> - or <a href="http://search.msn.com/" title="MSN Search">MSN</a>.</p> - -For comparison, here is the same paragraph written using -Markdown's inline link style: - - I get 10 times more traffic from [Google](http://google.com/ "Google") - than from [Yahoo](http://search.yahoo.com/ "Yahoo Search") or - [MSN](http://search.msn.com/ "MSN Search"). - -The point of reference-style links is not that they're easier to -write. The point is that with reference-style links, your document -source is vastly more readable. Compare the above examples: using -reference-style links, the paragraph itself is only 81 characters -long; with inline-style links, it's 176 characters; and as raw HTML, -it's 234 characters. In the raw HTML, there's more markup than there -is text. - -With Markdown's reference-style links, a source document much more -closely resembles the final output, as rendered in a browser. By -allowing you to move the markup-related metadata out of the paragraph, -you can add links without interrupting the narrative flow of your -prose. - - -<h3 id="em">Emphasis</h3> - -Markdown treats asterisks (`*`) and underscores (`_`) as indicators of -emphasis. Text wrapped with one `*` or `_` will be wrapped with an -HTML `<em>` tag; double `*`'s or `_`'s will be wrapped with an HTML -`<strong>` tag. E.g., this input: - - *single asterisks* - - _single underscores_ - - **double asterisks** - - __double underscores__ - -will produce: - - <em>single asterisks</em> - - <em>single underscores</em> - - <strong>double asterisks</strong> - - <strong>double underscores</strong> - -You can use whichever style you prefer; the lone restriction is that -the same character must be used to open and close an emphasis span. - -Emphasis can be used in the middle of a word: - - un*fucking*believable - -But if you surround an `*` or `_` with spaces, it'll be treated as a -literal asterisk or underscore. - -To produce a literal asterisk or underscore at a position where it -would otherwise be used as an emphasis delimiter, you can backslash -escape it: - - \*this text is surrounded by literal asterisks\* - - - -<h3 id="code">Code</h3> - -To indicate a span of code, wrap it with backtick quotes (`` ` ``). -Unlike a pre-formatted code block, a code span indicates code within a -normal paragraph. For example: - - Use the `printf()` function. - -will produce: - - <p>Use the <code>printf()</code> function.</p> - -To include a literal backtick character within a code span, you can use -multiple backticks as the opening and closing delimiters: - - ``There is a literal backtick (`) here.`` - -which will produce this: - - <p><code>There is a literal backtick (`) here.</code></p> - -The backtick delimiters surrounding a code span may include spaces -- -one after the opening, one before the closing. This allows you to place -literal backtick characters at the beginning or end of a code span: - - A single backtick in a code span: `` ` `` - - A backtick-delimited string in a code span: `` `foo` `` - -will produce: - - <p>A single backtick in a code span: <code>`</code></p> - - <p>A backtick-delimited string in a code span: <code>`foo`</code></p> - -With a code span, ampersands and angle brackets are encoded as HTML -entities automatically, which makes it easy to include example HTML -tags. Markdown will turn this: - - Please don't use any `<blink>` tags. - -into: - - <p>Please don't use any <code><blink></code> tags.</p> - -You can write this: - - `—` is the decimal-encoded equivalent of `—`. - -to produce: - - <p><code>&#8212;</code> is the decimal-encoded - equivalent of <code>&mdash;</code>.</p> - - - -<h3 id="img">Images</h3> - -Admittedly, it's fairly difficult to devise a "natural" syntax for -placing images into a plain text document format. - -Markdown uses an image syntax that is intended to resemble the syntax -for links, allowing for two styles: *inline* and *reference*. - -Inline image syntax looks like this: - -  - -  - -That is: - -* An exclamation mark: `!`; -* followed by a set of square brackets, containing the `alt` - attribute text for the image; -* followed by a set of parentheses, containing the URL or path to - the image, and an optional `title` attribute enclosed in double - or single quotes. - -Reference-style image syntax looks like this: - - ![Alt text][id] - -Where "id" is the name of a defined image reference. Image references -are defined using syntax identical to link references: - - [id]: url/to/image "Optional title attribute" - -As of this writing, Markdown has no syntax for specifying the -dimensions of an image; if this is important to you, you can simply -use regular HTML `<img>` tags. - - -* * * - - -<h2 id="misc">Miscellaneous</h2> - -<h3 id="autolink">Automatic Links</h3> - -Markdown supports a shortcut style for creating "automatic" links for URLs and email addresses: simply surround the URL or email address with angle brackets. What this means is that if you want to show the actual text of a URL or email address, and also have it be a clickable link, you can do this: - - <http://example.com/> - -Markdown will turn this into: - - <a href="http://example.com/">http://example.com/</a> - -Automatic links for email addresses work similarly, except that -Markdown will also perform a bit of randomized decimal and hex -entity-encoding to help obscure your address from address-harvesting -spambots. For example, Markdown will turn this: - - <address@example.com> - -into something like this: - - <a href="mailto:addre - ss@example.co - m">address@exa - mple.com</a> - -which will render in a browser as a clickable link to "address@example.com". - -(This sort of entity-encoding trick will indeed fool many, if not -most, address-harvesting bots, but it definitely won't fool all of -them. It's better than nothing, but an address published in this way -will probably eventually start receiving spam.) - - - -<h3 id="backslash">Backslash Escapes</h3> - -Markdown allows you to use backslash escapes to generate literal -characters which would otherwise have special meaning in Markdown's -formatting syntax. For example, if you wanted to surround a word with -literal asterisks (instead of an HTML `<em>` tag), you can backslashes -before the asterisks, like this: - - \*literal asterisks\* - -Markdown provides backslash escapes for the following characters: - - \ backslash - ` backtick - * asterisk - _ underscore - {} curly braces - [] square brackets - () parentheses - # hash mark - + plus sign - - minus sign (hyphen) - . dot - ! exclamation mark - diff --git a/tests/MarkdownTest_1.0.3/Tests/Nested blockquotes.html b/tests/MarkdownTest_1.0.3/Tests/Nested blockquotes.html deleted file mode 100644 index d8ec7f8e0..000000000 --- a/tests/MarkdownTest_1.0.3/Tests/Nested blockquotes.html +++ /dev/null @@ -1,9 +0,0 @@ -<blockquote> - <p>foo</p> - - <blockquote> - <p>bar</p> - </blockquote> - - <p>foo</p> -</blockquote> diff --git a/tests/MarkdownTest_1.0.3/Tests/Nested blockquotes.text b/tests/MarkdownTest_1.0.3/Tests/Nested blockquotes.text deleted file mode 100644 index ed3c624ff..000000000 --- a/tests/MarkdownTest_1.0.3/Tests/Nested blockquotes.text +++ /dev/null @@ -1,5 +0,0 @@ -> foo -> -> > bar -> -> foo diff --git a/tests/MarkdownTest_1.0.3/Tests/Ordered and unordered lists.html b/tests/MarkdownTest_1.0.3/Tests/Ordered and unordered lists.html deleted file mode 100644 index ba71eab39..000000000 --- a/tests/MarkdownTest_1.0.3/Tests/Ordered and unordered lists.html +++ /dev/null @@ -1,148 +0,0 @@ -<h2>Unordered</h2> - -<p>Asterisks tight:</p> - -<ul> -<li>asterisk 1</li> -<li>asterisk 2</li> -<li>asterisk 3</li> -</ul> - -<p>Asterisks loose:</p> - -<ul> -<li><p>asterisk 1</p></li> -<li><p>asterisk 2</p></li> -<li><p>asterisk 3</p></li> -</ul> - -<hr /> - -<p>Pluses tight:</p> - -<ul> -<li>Plus 1</li> -<li>Plus 2</li> -<li>Plus 3</li> -</ul> - -<p>Pluses loose:</p> - -<ul> -<li><p>Plus 1</p></li> -<li><p>Plus 2</p></li> -<li><p>Plus 3</p></li> -</ul> - -<hr /> - -<p>Minuses tight:</p> - -<ul> -<li>Minus 1</li> -<li>Minus 2</li> -<li>Minus 3</li> -</ul> - -<p>Minuses loose:</p> - -<ul> -<li><p>Minus 1</p></li> -<li><p>Minus 2</p></li> -<li><p>Minus 3</p></li> -</ul> - -<h2>Ordered</h2> - -<p>Tight:</p> - -<ol> -<li>First</li> -<li>Second</li> -<li>Third</li> -</ol> - -<p>and:</p> - -<ol> -<li>One</li> -<li>Two</li> -<li>Three</li> -</ol> - -<p>Loose using tabs:</p> - -<ol> -<li><p>First</p></li> -<li><p>Second</p></li> -<li><p>Third</p></li> -</ol> - -<p>and using spaces:</p> - -<ol> -<li><p>One</p></li> -<li><p>Two</p></li> -<li><p>Three</p></li> -</ol> - -<p>Multiple paragraphs:</p> - -<ol> -<li><p>Item 1, graf one.</p> - -<p>Item 2. graf two. The quick brown fox jumped over the lazy dog's -back.</p></li> -<li><p>Item 2.</p></li> -<li><p>Item 3.</p></li> -</ol> - -<h2>Nested</h2> - -<ul> -<li>Tab -<ul> -<li>Tab -<ul> -<li>Tab</li> -</ul></li> -</ul></li> -</ul> - -<p>Here's another:</p> - -<ol> -<li>First</li> -<li>Second: -<ul> -<li>Fee</li> -<li>Fie</li> -<li>Foe</li> -</ul></li> -<li>Third</li> -</ol> - -<p>Same thing but with paragraphs:</p> - -<ol> -<li><p>First</p></li> -<li><p>Second:</p> - -<ul> -<li>Fee</li> -<li>Fie</li> -<li>Foe</li> -</ul></li> -<li><p>Third</p></li> -</ol> - - -<p>This was an error in Markdown 1.0.1:</p> - -<ul> -<li><p>this</p> - -<ul><li>sub</li></ul> - -<p>that</p></li> -</ul> diff --git a/tests/MarkdownTest_1.0.3/Tests/Ordered and unordered lists.text b/tests/MarkdownTest_1.0.3/Tests/Ordered and unordered lists.text deleted file mode 100644 index 7f3b49777..000000000 --- a/tests/MarkdownTest_1.0.3/Tests/Ordered and unordered lists.text +++ /dev/null @@ -1,131 +0,0 @@ -## 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: - -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 2. graf two. The quick brown fox jumped over the lazy dog's - back. - -2. Item 2. - -3. Item 3. - - - -## 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 - - -This was an error in Markdown 1.0.1: - -* this - - * sub - - that diff --git a/tests/MarkdownTest_1.0.3/Tests/Strong and em together.html b/tests/MarkdownTest_1.0.3/Tests/Strong and em together.html deleted file mode 100644 index 71ec78c70..000000000 --- a/tests/MarkdownTest_1.0.3/Tests/Strong and em together.html +++ /dev/null @@ -1,7 +0,0 @@ -<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> diff --git a/tests/MarkdownTest_1.0.3/Tests/Strong and em together.text b/tests/MarkdownTest_1.0.3/Tests/Strong and em together.text deleted file mode 100644 index 95ee690db..000000000 --- a/tests/MarkdownTest_1.0.3/Tests/Strong and em together.text +++ /dev/null @@ -1,7 +0,0 @@ -***This is strong and em.*** - -So is ***this*** word. - -___This is strong and em.___ - -So is ___this___ word. diff --git a/tests/MarkdownTest_1.0.3/Tests/Tabs.html b/tests/MarkdownTest_1.0.3/Tests/Tabs.html deleted file mode 100644 index 3301ba803..000000000 --- a/tests/MarkdownTest_1.0.3/Tests/Tabs.html +++ /dev/null @@ -1,25 +0,0 @@ -<ul> -<li><p>this is a list item -indented with tabs</p></li> -<li><p>this is a list item -indented with spaces</p></li> -</ul> - -<p>Code:</p> - -<pre><code>this code block is indented by one tab -</code></pre> - -<p>And:</p> - -<pre><code> this code block is indented by two tabs -</code></pre> - -<p>And:</p> - -<pre><code>+ this is an example list item - indented with tabs - -+ this is an example list item - indented with spaces -</code></pre> diff --git a/tests/MarkdownTest_1.0.3/Tests/Tabs.text b/tests/MarkdownTest_1.0.3/Tests/Tabs.text deleted file mode 100644 index 589d1136e..000000000 --- a/tests/MarkdownTest_1.0.3/Tests/Tabs.text +++ /dev/null @@ -1,21 +0,0 @@ -+ this is a list item - indented with tabs - -+ this is a list item - indented with spaces - -Code: - - this code block is indented by one tab - -And: - - this code block is indented by two tabs - -And: - - + this is an example list item - indented with tabs - - + this is an example list item - indented with spaces diff --git a/tests/MarkdownTest_1.0.3/Tests/Tidyness.html b/tests/MarkdownTest_1.0.3/Tests/Tidyness.html deleted file mode 100644 index f2a8ce70f..000000000 --- a/tests/MarkdownTest_1.0.3/Tests/Tidyness.html +++ /dev/null @@ -1,8 +0,0 @@ -<blockquote> -<p>A list within a blockquote:</p> -<ul> -<li>asterisk 1</li> -<li>asterisk 2</li> -<li>asterisk 3</li> -</ul> -</blockquote> diff --git a/tests/MarkdownTest_1.0.3/Tests/Tidyness.text b/tests/MarkdownTest_1.0.3/Tests/Tidyness.text deleted file mode 100644 index 5f18b8da2..000000000 --- a/tests/MarkdownTest_1.0.3/Tests/Tidyness.text +++ /dev/null @@ -1,5 +0,0 @@ -> A list within a blockquote: -> -> * asterisk 1 -> * asterisk 2 -> * asterisk 3 diff --git a/tests/Tests/Readers/LaTeX.hs b/tests/Tests/Readers/LaTeX.hs index c1efd1b68..8ff23ebc1 100644 --- a/tests/Tests/Readers/LaTeX.hs +++ b/tests/Tests/Readers/LaTeX.hs @@ -21,7 +21,7 @@ tests = [ testGroup "basic" [ "simple" =: "word" =?> para "word" , "space" =: - "some text" =?> para ("some text") + "some text" =?> para "some text" , "emphasized" =: "\\emph{emphasized}" =?> para (emph "emphasized") ] diff --git a/tests/Tests/Readers/Markdown.hs b/tests/Tests/Readers/Markdown.hs index b04ff9a0d..492680a35 100644 --- a/tests/Tests/Readers/Markdown.hs +++ b/tests/Tests/Readers/Markdown.hs @@ -171,13 +171,13 @@ tests = [ testGroup "inline code" , testGroup "smart punctuation" [ test markdownSmart "quote before ellipses" ("'...hi'" - =?> para (singleQuoted ("…hi"))) + =?> para (singleQuoted "…hi")) , test markdownSmart "apostrophe before emph" ("D'oh! A l'*aide*!" =?> para ("D’oh! A l’" <> emph "aide" <> "!")) , test markdownSmart "apostrophe in French" ("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»")) + =?> para "À l’arrivée de la guerre, le thème de l’«impossibilité du socialisme»") ] , testGroup "mixed emphasis and strong" [ "emph and strong emph alternating" =: diff --git a/tests/Tests/Readers/Org.hs b/tests/Tests/Readers/Org.hs new file mode 100644 index 000000000..8c5982302 --- /dev/null +++ b/tests/Tests/Readers/Org.hs @@ -0,0 +1,533 @@ +{-# LANGUAGE OverloadedStrings #-} +module Tests.Readers.Org (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) + +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") + + , "Strikeout" =: + "+Kill Bill+" =?> + para (strikeout . spcSep $ [ "Kill", "Bill" ]) + + , "Code" =: + "=Robot.rock()=" =?> + para (code "Robot.rock()") + + , "Verbatim" =: + "~word for word~" =?> + para (rawInline "" "word for word") + + , "Symbol" =: + "A * symbol" =?> + para (str "A" <> space <> str "*" <> space <> "symbol") + + , "Superscript single char" =: + "2^n" =?> + para (str "2" <> superscript "n") + + , "Superscript multi char" =: + "2^{n-1}" =?> + para (str "2" <> superscript "n-1") + + , "Subscript single char" =: + "a_n" =?> + para (str "a" <> subscript "n") + + , "Subscript multi char" =: + "a_{n+1}" =?> + para (str "a" <> subscript "n+1") + + , "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" + ]) + + , "Markup may not span more than two lines" =: + unlines [ "/this *is", "not*", "emph/" ] =?> + para (spcSep [ "/this" + , (strong ("is" <> space <> "not")) + , "emph/" ]) + + , "Explicit link" =: + "[[http://zeitlens.com/][pseudo-random nonsense]]" =?> + (para $ link "http://zeitlens.com/" "" + ("pseudo-random" <> space <> "nonsense")) + + , "Self-link" =: + "[[http://zeitlens.com/]]" =?> + (para $ link "http://zeitlens.com/" "" "http://zeitlens.com/") + ] + + , 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:") + ] + + , 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") + ] + + , "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) + + , "Source Block in Text" =: + 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" =: + 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' + ] + + , 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" + ] + + , "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 + [ para "Discovery" + , bulletList [ plain ("One" <> space <> + "More" <> space <> + "Time") + , plain ("Harder," <> space <> + "Better," <> space <> + "Faster," <> space <> + "Stronger") + ] + ] + , mconcat + [ para "Homework" + , bulletList [ plain ("Around" <> space <> + "the" <> space <> + "World") + ] + ] + , mconcat + [ para ("Human" <> space <> "After" <> space <> "All") + , bulletList [ plain "Technologic" + , plain ("Robot" <> space <> "Rock") + ] + ] + ] + + , "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 + [ para "One" + , orderedList [ plain "One-One" + , plain "One-Two" + ] + ] + , mconcat + [ para "Two" + , orderedList [ plain "Two-One" + , plain "Two-Two" + ] + ] + ] + in orderedListWith listStyle listStructure + + , "Ordered List in Bullet List" =: + ("- Emacs\n" ++ + " 1. Org\n") =?> + bulletList [ (para "Emacs") <> + (orderedList [ plain "Org"]) + ] + + , "Bullet List in Ordered List" =: + ("1. GNU\n" ++ + " - Freedom\n") =?> + orderedList [ (para "GNU") <> bulletList [ (plain "Freedom") ] ] + ] + + , 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 ] + ] + ] + ] diff --git a/tests/Tests/Walk.hs b/tests/Tests/Walk.hs index f6aa1beae..34350e28a 100644 --- a/tests/Tests/Walk.hs +++ b/tests/Tests/Walk.hs @@ -21,11 +21,11 @@ tests = [ testGroup "Walk" p_walk :: (Typeable a, Walkable a Pandoc) => (a -> a) -> Pandoc -> Bool -p_walk f = (\(d :: Pandoc) -> everywhere (mkT f) d == walk f d) +p_walk f d = everywhere (mkT f) d == walk f d p_query :: (Eq a, Typeable a1, Monoid a, Walkable a1 Pandoc) => (a1 -> a) -> Pandoc -> Bool -p_query f = (\(d :: Pandoc) -> everything mappend (mempty `mkQ` f) d == query f d) +p_query f d = everything mappend (mempty `mkQ` f) d == query f d inlineTrans :: Inline -> Inline inlineTrans (Str xs) = Str $ map toUpper xs diff --git a/tests/html-reader.native b/tests/html-reader.native index 15937e594..e80905729 100644 --- a/tests/html-reader.native +++ b/tests/html-reader.native @@ -1,4 +1,4 @@ -Pandoc (Meta {unMeta = fromList [("title",MetaInlines [Str "Pandoc",Space,Str "Test",Space,Str "Suite"])]}) +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 "."] ,HorizontalRule ,Header 1 ("",[],[]) [Str "Headers"] @@ -207,18 +207,18 @@ Pandoc (Meta {unMeta = fromList [("title",MetaInlines [Str "Pandoc",Space,Str "T ,BulletList [[Plain [Str "\\cite[22",Str "-",Str "23]{smith",Str ".",Str "1899}"]] ,[Plain [Str "\\doublespacing"]] - ,[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 "$p$",Str "-",Str "Tree"]] - ,[Plain [Str "$\\frac{d}{dx}f(x)=\\lim_{h\\to",Space,Str "0}\\frac{f(x+h)",Str "-",Str "f(x)}{h}$"]] - ,[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 "$\\alpha",Space,Str "+",Space,Str "\\omega",Space,Str "\\times",Space,Str "x^2$",Str "."]]] + ,[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:"] ,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 "$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 "$34,000",Str ".",Space,Str "(It",Space,Str "worked",Space,Str "if",Space,Str "\"",Str "lot",Str "\"",Space,Str "is",Space,Str "emphasized",Str ".",Str ")"]] - ,[Plain [Str "Escaped",Space,Code ("",[],[]) "$",Str ":",Space,Str "$73",Space,Emph [Str "this",Space,Str "should",Space,Str "be",Space,Str "emphasized"],Space,Str "23$",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:"] ,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 diff --git a/tests/lhs-test.latex b/tests/lhs-test.latex index 51c62f98a..78f072600 100644 --- a/tests/lhs-test.latex +++ b/tests/lhs-test.latex @@ -1,5 +1,4 @@ \documentclass[]{article} -\usepackage[T1]{fontenc} \usepackage{lmodern} \usepackage{amssymb,amsmath} \usepackage{ifxetex,ifluatex} @@ -7,6 +6,7 @@ % 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 diff --git a/tests/lhs-test.latex+lhs b/tests/lhs-test.latex+lhs index 606d49a12..50a0e15e1 100644 --- a/tests/lhs-test.latex+lhs +++ b/tests/lhs-test.latex+lhs @@ -1,5 +1,4 @@ \documentclass[]{article} -\usepackage[T1]{fontenc} \usepackage{lmodern} \usepackage{amssymb,amsmath} \usepackage{ifxetex,ifluatex} @@ -7,6 +6,7 @@ % 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 diff --git a/tests/lhs-test.markdown b/tests/lhs-test.markdown index 47ec920d3..75a253bf4 100644 --- a/tests/lhs-test.markdown +++ b/tests/lhs-test.markdown @@ -4,11 +4,11 @@ lhs test `unsplit` is an arrow that takes a pair of values and combines them to return a single value: -~~~~ {.sourceCode .literate .haskell} +``` {.sourceCode .literate .haskell} unsplit :: (Arrow a) => (b -> c -> d) -> a (b, c) d unsplit = arr . uncurry -- arr (\op (x,y) -> x `op` y) -~~~~ +``` `(***)` combines two arrows into a new arrow by running the two arrows on a pair of values (one arrow on the first item of the pair and one arrow on the diff --git a/tests/markdown-reader-more.native b/tests/markdown-reader-more.native index ca588571f..27f09dada 100644 --- a/tests/markdown-reader-more.native +++ b/tests/markdown-reader-more.native @@ -40,7 +40,7 @@ ,OrderedList (3,Example,TwoParens) [[Plain [Str "Third",Space,Str "example."]]] ,Header 2 ("macros",[],[]) [Str "Macros"] -,Para [Math InlineMath "\\langle x,y \\rangle"] +,Para [Math InlineMath "{\\langle x,y \\rangle}"] ,Header 2 ("case-insensitive-references",[],[]) [Str "Case-insensitive",Space,Str "references"] ,Para [Link [Str "Fum"] ("/fum","")] ,Para [Link [Str "FUM"] ("/fum","")] diff --git a/tests/mediawiki-reader.wiki b/tests/mediawiki-reader.wiki index 26f4ef164..c0c22bec6 100644 --- a/tests/mediawiki-reader.wiki +++ b/tests/mediawiki-reader.wiki @@ -232,11 +232,11 @@ ends the list. <li>list item A2</li> </ol> -<ul> +<ol> #abc #def #ghi -</ul> +</ol> <ol start="9"> <li>Amsterdam</li> diff --git a/tests/rst-reader.native b/tests/rst-reader.native index 497810f39..fd48bc60c 100644 --- a/tests/rst-reader.native +++ b/tests/rst-reader.native @@ -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 ("",["sourceCode","haskell"],[]) "fmap id [1,2..10]",Str "."] +,Null +,Null +,Para [Str "Indirect",Space,Str "python",Space,Str "role",Space,Code ("",["sourceCode","python"],[]) "[x*x for x in [1,2,3,4,5]]",Str "."] +,Null +,Null +,Para [Str "Different",Space,Str "indirect",Space,Str "C",Space,Code ("",["sourceCode","c"],[]) "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/tables.latex b/tests/tables.latex index c27e10461..1a87c4f71 100644 --- a/tests/tables.latex +++ b/tests/tables.latex @@ -1,59 +1,59 @@ Simple table with caption: \begin{longtable}[c]{@{}rlcl@{}} -\hline\noalign{\medskip} +\toprule\addlinespace Right & Left & Center & Default -\\\noalign{\medskip} -\hline\noalign{\medskip} +\\\addlinespace +\midrule\endhead 12 & 12 & 12 & 12 -\\\noalign{\medskip} +\\\addlinespace 123 & 123 & 123 & 123 -\\\noalign{\medskip} +\\\addlinespace 1 & 1 & 1 & 1 -\\\noalign{\medskip} -\hline -\noalign{\medskip} +\\\addlinespace +\bottomrule +\addlinespace \caption{Demonstration of simple table syntax.} \end{longtable} Simple table without caption: \begin{longtable}[c]{@{}rlcl@{}} -\hline\noalign{\medskip} +\toprule\addlinespace Right & Left & Center & Default -\\\noalign{\medskip} -\hline\noalign{\medskip} +\\\addlinespace +\midrule\endhead 12 & 12 & 12 & 12 -\\\noalign{\medskip} +\\\addlinespace 123 & 123 & 123 & 123 -\\\noalign{\medskip} +\\\addlinespace 1 & 1 & 1 & 1 -\\\noalign{\medskip} -\hline +\\\addlinespace +\bottomrule \end{longtable} Simple table indented two spaces: \begin{longtable}[c]{@{}rlcl@{}} -\hline\noalign{\medskip} +\toprule\addlinespace Right & Left & Center & Default -\\\noalign{\medskip} -\hline\noalign{\medskip} +\\\addlinespace +\midrule\endhead 12 & 12 & 12 & 12 -\\\noalign{\medskip} +\\\addlinespace 123 & 123 & 123 & 123 -\\\noalign{\medskip} +\\\addlinespace 1 & 1 & 1 & 1 -\\\noalign{\medskip} -\hline -\noalign{\medskip} +\\\addlinespace +\bottomrule +\addlinespace \caption{Demonstration of simple table syntax.} \end{longtable} Multiline table with caption: \begin{longtable}[c]{@{}clrl@{}} -\hline\noalign{\medskip} +\toprule\addlinespace \begin{minipage}[b]{0.13\columnwidth}\centering Centered Header \end{minipage} & \begin{minipage}[b]{0.12\columnwidth}\raggedright @@ -63,8 +63,8 @@ Right Aligned \end{minipage} & \begin{minipage}[b]{0.30\columnwidth}\raggedright Default aligned \end{minipage} -\\\noalign{\medskip} -\hline\noalign{\medskip} +\\\addlinespace +\midrule\endhead \begin{minipage}[t]{0.13\columnwidth}\centering First \end{minipage} & \begin{minipage}[t]{0.12\columnwidth}\raggedright @@ -74,7 +74,7 @@ row \end{minipage} & \begin{minipage}[t]{0.30\columnwidth}\raggedright Example of a row that spans multiple lines. \end{minipage} -\\\noalign{\medskip} +\\\addlinespace \begin{minipage}[t]{0.13\columnwidth}\centering Second \end{minipage} & \begin{minipage}[t]{0.12\columnwidth}\raggedright @@ -84,16 +84,16 @@ row \end{minipage} & \begin{minipage}[t]{0.30\columnwidth}\raggedright Here's another one. Note the blank line between rows. \end{minipage} -\\\noalign{\medskip} -\hline -\noalign{\medskip} +\\\addlinespace +\bottomrule +\addlinespace \caption{Here's the caption. It may span multiple lines.} \end{longtable} Multiline table without caption: \begin{longtable}[c]{@{}clrl@{}} -\hline\noalign{\medskip} +\toprule\addlinespace \begin{minipage}[b]{0.13\columnwidth}\centering Centered Header \end{minipage} & \begin{minipage}[b]{0.12\columnwidth}\raggedright @@ -103,8 +103,8 @@ Right Aligned \end{minipage} & \begin{minipage}[b]{0.30\columnwidth}\raggedright Default aligned \end{minipage} -\\\noalign{\medskip} -\hline\noalign{\medskip} +\\\addlinespace +\midrule\endhead \begin{minipage}[t]{0.13\columnwidth}\centering First \end{minipage} & \begin{minipage}[t]{0.12\columnwidth}\raggedright @@ -114,7 +114,7 @@ row \end{minipage} & \begin{minipage}[t]{0.30\columnwidth}\raggedright Example of a row that spans multiple lines. \end{minipage} -\\\noalign{\medskip} +\\\addlinespace \begin{minipage}[t]{0.13\columnwidth}\centering Second \end{minipage} & \begin{minipage}[t]{0.12\columnwidth}\raggedright @@ -124,27 +124,27 @@ row \end{minipage} & \begin{minipage}[t]{0.30\columnwidth}\raggedright Here's another one. Note the blank line between rows. \end{minipage} -\\\noalign{\medskip} -\hline +\\\addlinespace +\bottomrule \end{longtable} Table without column headers: \begin{longtable}[c]{@{}rlcr@{}} -\hline\noalign{\medskip} +\toprule\addlinespace 12 & 12 & 12 & 12 -\\\noalign{\medskip} +\\\addlinespace 123 & 123 & 123 & 123 -\\\noalign{\medskip} +\\\addlinespace 1 & 1 & 1 & 1 -\\\noalign{\medskip} -\hline +\\\addlinespace +\bottomrule \end{longtable} Multiline table without column headers: \begin{longtable}[c]{@{}clrl@{}} -\hline\noalign{\medskip} +\toprule\addlinespace \begin{minipage}[t]{0.13\columnwidth}\centering First \end{minipage} & \begin{minipage}[t]{0.12\columnwidth}\raggedright @@ -154,7 +154,7 @@ row \end{minipage} & \begin{minipage}[t]{0.30\columnwidth}\raggedright Example of a row that spans multiple lines. \end{minipage} -\\\noalign{\medskip} +\\\addlinespace \begin{minipage}[t]{0.13\columnwidth}\centering Second \end{minipage} & \begin{minipage}[t]{0.12\columnwidth}\raggedright @@ -164,6 +164,6 @@ row \end{minipage} & \begin{minipage}[t]{0.30\columnwidth}\raggedright Here's another one. Note the blank line between rows. \end{minipage} -\\\noalign{\medskip} -\hline +\\\addlinespace +\bottomrule \end{longtable} diff --git a/tests/test-pandoc.hs b/tests/test-pandoc.hs index ae521541a..74f8e5044 100644 --- a/tests/test-pandoc.hs +++ b/tests/test-pandoc.hs @@ -7,6 +7,7 @@ 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.Writers.ConTeXt import qualified Tests.Writers.LaTeX @@ -31,6 +32,7 @@ tests = [ testGroup "Old" Tests.Old.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 ] ] diff --git a/tests/writer.latex b/tests/writer.latex index 9431f43b1..4cb989fba 100644 --- a/tests/writer.latex +++ b/tests/writer.latex @@ -1,5 +1,4 @@ \documentclass[]{article} -\usepackage[T1]{fontenc} \usepackage{lmodern} \usepackage{amssymb,amsmath} \usepackage{ifxetex,ifluatex} @@ -7,6 +6,7 @@ % 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 diff --git a/windows/make-windows-installer.bat b/windows/make-windows-installer.bat index cf20bc98c..d27859057 100644 --- a/windows/make-windows-installer.bat +++ b/windows/make-windows-installer.bat @@ -10,7 +10,6 @@ cabal-dev install -v1 --reinstall --flags="embed_data_files" pandoc-citeproc if %errorlevel% neq 0 exit /b %errorlevel%
strip cabal-dev\bin\pandoc.exe
strip cabal-dev\bin\pandoc-citeproc.exe
-strip cabal-dev\bin\biblio2yaml.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
diff --git a/windows/pandoc.wxs b/windows/pandoc.wxs index 5fe0a022e..7a20effe5 100644 --- a/windows/pandoc.wxs +++ b/windows/pandoc.wxs @@ -57,8 +57,6 @@ Name="Version" Type="string" Value="[ProductVersion]" KeyPath="yes"/>
<File Id="pandoc_citeprocEXE" Name="pandoc-citeproc.exe"
Source="..\cabal-dev\bin\pandoc-citeproc.exe" />
- <File Id="biblio2yamlEXE" Name="biblio2yaml.exe"
- Source="..\cabal-dev\bin\biblio2yaml.exe" />
</Component>
<Component Id="UpdatePathUser"
|