diff options
137 files changed, 19996 insertions, 0 deletions
@@ -0,0 +1,3 @@ +# Known Bugs + + diff --git a/ChangeLog b/ChangeLog new file mode 100644 index 000000000..15c08bcc9 --- /dev/null +++ b/ChangeLog @@ -0,0 +1 @@ +Please see changelog.Debian (debian/changelog in source tree). diff --git a/LICENSE b/LICENSE new file mode 100644 index 000000000..eadeab310 --- /dev/null +++ b/LICENSE @@ -0,0 +1,74 @@ +(c) 2006 John MacFarlane (jgm At berkeley.edu). Released under the +[GPL][], version 2 or greater. + +[GPL]: http://www.gnu.org/copyleft/gpl.html + +THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS +"AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT +LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR +A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT +OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, +SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED +TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR +PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF +LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING +NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS +SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE. + +---------------------------------------------------------------------- + +UTF8.hs + +Copyright (c) 2003, OGI School of Science & Engineering, Oregon Health & +Science University, All rights reserved. + +Redistribution and use in source and binary forms, with or without +modification, are permitted provided that the following conditions +are met: + +- Redistributions of source code must retain the above copyright + notice, this list of conditions and the following disclaimer. + +- Redistributions in binary form must reproduce the above + copyright notice, this list of conditions and the following + disclaimer in the documentation and/or other materials provided + with the distribution. + +- Neither the name of OGI or OHSU nor the names of its + contributors may be used to endorse or promote products derived + from this software without specific prior written permission. + +THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS +"AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT +LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR +A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT +OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, +SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED +TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR +PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF +LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING +NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS +SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE. + +modified by Martin Norbäck +modified to pass illegal utf-8 sequences through unchanged + +---------------------------------------------------------------------- + +ASCIIMathML.js + +Copyright 2005, Peter Jipsen, Chapman University +<http://www1.chapman.edu/~jipsen/mathml/asciimath.html> + +Released under the [GPL][]. + +---------------------------------------------------------------------- + +S5 slides.js and css files + +by Eric A. Meyer +<http://meyerweb.com/eric/tools/s5 + +Released under an explicit Public Domain License + + diff --git a/Makefile b/Makefile new file mode 100644 index 000000000..880f3f8e7 --- /dev/null +++ b/Makefile @@ -0,0 +1,146 @@ +# Makefile for Pandoc. + +#------------------------------------------------------------------------------- +# Cabal constants +#------------------------------------------------------------------------------- +CABAL := $(wildcard *.cabal) +NAME := $(shell sed -ne 's/^[Nn]ame:[[:space:]]*//p' $(CABAL)) +THIS := $(shell echo $(NAME) | tr A-Z a-z) +VERSION := $(shell sed -ne 's/^[Vv]ersion:[[:space:]]*//p' $(CABAL)) +EXECUTABLES := $(shell sed -ne 's/^[Ee]xecutable:[[:space:]]*//p' $(CABAL)) + +#------------------------------------------------------------------------------- +# Variables to setup through environment +#------------------------------------------------------------------------------- +PREFIX ?= /usr/local +DESTDIR ?= + +#------------------------------------------------------------------------------- +# Constant names and commands in source tree +#------------------------------------------------------------------------------- +SRCDIR := src +MANDIR := man +BUILDDIR := dist +BUILDCONF := .setup-config +BUILDCMD := runhaskell Setup.hs + +#------------------------------------------------------------------------------- +# Installation paths +#------------------------------------------------------------------------------- +BINPATH := $(DESTDIR)$(PREFIX)/bin +DATAPATH := $(DESTDIR)$(PREFIX)/share +DOCPATH := $(DATAPATH)/doc/$(THIS) +LIBDOCPATH := $(DATAPATH)/doc/$(THIS)-doc +MANPATH := $(DATAPATH)/man +PKGPATH := $(DATAPATH)/$(THIS) + +#------------------------------------------------------------------------------- +# Generic Makefile variables +#------------------------------------------------------------------------------- +INSTALL := install -c +INSTALL_PROGRAM := $(INSTALL) -m 755 +INSTALL_DATA := $(INSTALL) -m 644 + +#------------------------------------------------------------------------------- +# Recipes +#------------------------------------------------------------------------------- + +.PHONY: all +all: build + +.PHONY: templates +templates: $(SRCDIR)/templates +$(SRCDIR)/templates: + $(MAKE) -C $(SRCDIR)/templates + +.PHONY: prep +prep: + # Darcs cannot preserve file permissions. + -for p in configure debian/rules; do chmod +x $$p; done + +.PHONY: configure +cleanup_files+=$(BUILDDIR) $(BUILDCONF) $(CABAL:%.cabal=%).buildinfo +configure: $(BUILDCONF) +$(BUILDCONF): prep + $(BUILDCMD) configure --prefix=$(PREFIX) + +.PHONY: build +build: templates configure + $(BUILDCMD) build + +.PHONY: build-lib-doc +build-lib-doc: html +cleanup_files+=html +html: $(BUILDCONF) + $(BUILDCMD) haddock && mv $(BUILDDIR)/doc/html . + +cleanup_files+=$(EXECUTABLES) +$(EXECUTABLES): build + # Ugly kludge to seperate program and library installations. + # Leave the library installation to Cabal ('install-lib' target). + find $(BUILDDIR) -type f -name "$(EXECUTABLES)" -perm +a=x -exec mv {} . \; + + +# XXX: Note that we don't handle PREFIX correctly at the install-* stages, +# i.e. any PREFIX given at the configuration time is lost, unless it is +# also supplied (via environment) at these stages. +.PHONY: install-exec uninstall-exec +bin_all:=$(EXECUTABLES) html2markdown markdown2latex latex2markdown markdown2pdf +install-exec: $(bin_all) + $(INSTALL) -d $(BINPATH); \ + for p in $(bin_all); do $(INSTALL_PROGRAM) $$p $(BINPATH)/; done +uninstall-exec: + -for p in $(bin_all); do rm -f $(BINPATH)/$$p; done + +.PHONY: install-doc uninstall-doc +doc_all:=README.html README BUGS TODO +cleanup_files+=README.html +install-doc: $(doc_all) + $(INSTALL) -d $(DOCPATH) && $(INSTALL_DATA) $(doc_all) $(DOCPATH)/; \ + $(INSTALL) -d $(MANPATH) && cp -a $(MANDIR)/* $(MANPATH)/ +uninstall-doc: + -for d in $(doc_all); do rm -f $(DOCPATH)/$$d; done + -cd $(MANDIR) && find . -type f -exec rm -f "$(MANPATH)/{}" \; + +# Handle program installation manually (due to the deficiencies in Cabal). +.PHONY: install uninstall +install: install-exec install-doc +# FIXME: incomplete support for uninstallation. +uninstall: uninstall-exec uninstall-doc + +.PHONY: install-lib install-lib-doc +install-lib: + @$(BUILDCMD) install || true # required since we move executable +install-lib-doc: build-lib-doc + $(INSTALL) -d $(LIBDOCPATH) && cp -a html $(LIBDOCPATH)/ + +.PHONY: test test-markdown +test: $(EXECUTABLES) + @cd tests && perl runtests.pl -s $(PWD)/$(THIS) +test-markdown: $(EXECUTABLES) + @cd tests/MarkdownTest_1.0.3 && perl MarkdownTest.pl -s $(PWD)/$(THIS) -tidy +%.html: % + ./$(THIS) -s $^ >$@ || rm -f $@ + +# Stolen and slightly improved from a GPLed Makefile. Credits to John Meacham. +src_all:=$(shell find $(SRCDIR) -type f -name '*hs' | egrep -v '^\./(_darcs|lib|test)/') +cleanup_files+=$(patsubst %,$(SRCDIR)/%,tags tags.sorted) +tags: $(src_all) + cd $(SRCDIR) && hasktags -c $(src_all:$(SRCDIR)/%=%); \ + LC_ALL=C sort tags >tags.sorted; mv tags.sorted tags + +deb: debian prep + if [ -x /usr/bin/debuild ]; then \ + debuild -i_darcs -I_darcs -uc -us; \ + else \ + echo "*** Please install devscripts package. ***"; \ + dpkg-buildpackage -i_darcs -I_darcs -uc -us; \ + fi + +.PHONY: distclean clean +distclean: clean prep + if [ -d debian ]; then fakeroot debian/rules clean; fi +clean: + -if [ -f $(BUILDCONF) ]; then $(BUILDCMD) clean; fi + -rm -rf $(cleanup_files) + diff --git a/Pandoc.buildinfo.in b/Pandoc.buildinfo.in new file mode 100644 index 000000000..6eed3bf16 --- /dev/null +++ b/Pandoc.buildinfo.in @@ -0,0 +1 @@ +Ghc-Options: @HCFLAGS@ diff --git a/Pandoc.cabal b/Pandoc.cabal new file mode 100644 index 000000000..7a34a1e21 --- /dev/null +++ b/Pandoc.cabal @@ -0,0 +1,33 @@ +Name: Pandoc +Version: 0.21 +License: GPL +License-File: LICENSE +Author: John MacFarlane <jgm@berkeley.edu> +Homepage: http://sophos.berkeley.edu/macfarlane/pandoc +Category: Text +Synopsis: Utilities for translating between various markup formats +Description: Haskell utilities for translating between markdown, HTML, + reStructuredText, LaTeX, and RTF +Build-Depends: base, haskell98, parsec +Hs-Source-Dir: src +Exposed-Modules: Text.ParserCombinators.Pandoc, + Text.Pandoc.ASCIIMathML, + Text.Pandoc.Definition, + Text.Pandoc.HtmlEntities, + Text.Pandoc.Shared, + Text.Pandoc.UTF8, + Text.Pandoc.Writers.DefaultHeaders, + Text.Pandoc.Writers.HTML, + Text.Pandoc.Writers.Markdown, + Text.Pandoc.Writers.LaTeX, + Text.Pandoc.Writers.RST, + Text.Pandoc.Writers.S5, + Text.Pandoc.Writers.RTF, + Text.Pandoc.Readers.HTML, + Text.Pandoc.Readers.Markdown, + Text.Pandoc.Readers.RST, + Text.Pandoc.Readers.LaTeX + +Executable: pandoc +Hs-Source-Dir: src +Main-Is: Main.hs @@ -0,0 +1,508 @@ +% pandoc +% John MacFarlane +% August 10, 2006 + +`pandoc` converts files from one markup format to another. It can +read [markdown] and (with some limitations) [reStructuredText], [HTML], and +[LaTeX], and it can write [markdown], [reStructuredText], [HTML], +[LaTeX], [RTF], and [S5] HTML slide shows. It is written in +[Haskell], using the excellent [Parsec] parser combinator library. + +[markdown]: http://daringfireball.net/projects/markdown/ +[reStructuredText]: http://docutils.sourceforge.net/docs/ref/rst/introduction.html +[S5]: http://meyerweb.com/eric/tools/s5/ +[HTML]: http://www.w3.org/TR/html40/ +[LaTeX]: http://www.latex-project.org/ +[RTF]: http://en.wikipedia.org/wiki/Rich_Text_Format +[Haskell]: http://www.haskell.org/ +[Parsec]: http://www.cs.uu.nl/~daan/download/parsec/parsec.html + +(c) 2006 John MacFarlane (jgm At berkeley.edu). Released under the +[GPL], version 2 or greater. This software carries no warranty of +any kind. (See LICENSE for full copyright and warranty notices.) + +[GPL]: http://www.gnu.org/copyleft/gpl.html + +# Installation + +## Installing GHC + +To compile `pandoc`, you'll need [GHC] version 6.4 or greater. + +If you don't have GHC already, you can get it from the +[GHC Download] page. + +[GHC]: http://www.haskell.org/ghc/ +[GHC Download]: http://www.haskell.org/ghc/download.html + +Note: As of this writing, there's no MacOS X installer package for +GHC 6.4.2 (the latest version). There is an installer for +GHC 6.4.1 [here](http://www.haskell.org/ghc/download_ghc_641.html#macosx). +It will work just fine on PPC-based Macs. GHC has not yet been ported +to Intel Macs: see <http://hackage.haskell.org/trac/ghc/wiki/X86OSXGhc>. + +You'll also need standard build tools: GNU Make, sed, bash, and perl. +These are standard on unix systems (including MacOS X). If you're +using Windows, you can install [Cygwin]. + +[Cygwin]: http://www.cygwin.com/ + +Note: I have tested `pandoc` on MacOS X and Linux systems. I have not +tried it on Windows, and I have no idea whether it will work on Windows. + +## Installing `pandoc` + +1. Change to the directory containing the `pandoc` distribution. + +2. Compile: + + make + +3. Optional, but recommended: + + make test + +4. If you want to install the `pandoc` program and the relevant wrappers + and documents (including this file) into `/usr/local` directory, type: + + make install + + If you only want the `pandoc` program and the shell scripts `latex2markdown`, + `markdown2latex`, `markdown2pdf`, `markdown2html`, `html2markdown` installed + into your `~/bin` directory, type (note the **`-exec`** suffix): + + PREFIX=~ make install-exec + +5. If you want to install the Pandoc library modules for use in + other Haskell programs, type (as root): + + make install-lib + +6. To install the library documentation (into `/usr/local/pandoc-doc`), + type: + + make install-lib-doc + +# Using `pandoc` + +You can run `pandoc` like this: + + ./pandoc + +If you copy the `pandoc` executable to a directory in your path +(perhaps using `make install`), you can invoke it without the "./": + + pandoc + +If you run `pandoc` without arguments, it will accept input from +STDIN. If you run it with file names as arguments, it will take input +from those files. It accepts several command-line options. For a +list, type + + pandoc -h + +The most important options specify the format of the source file and +the output. The default reader is markdown; the default writer is +HTML. So if you don't specify a reader or writer, `pandoc` will +convert markdown to HTML. To convert markdown to LaTeX, you could +write: + + pandoc -w latex input.txt + +To convert html to markdown: + + pandoc -r html -w markdown input.txt + +Supported writers include markdown, LaTeX, HTML, RTF, +reStructuredText, and S5 (which produces an HTML file that acts like +powerpoint). Supported readers include markdown, HTML, LaTeX, and +reStructuredText. Note that the rst (reStructuredText) reader only +parses a subset of rst syntax. For example, it doesn't handle tables, +definition lists, option lists, or footnotes. It handles only the +constructs expressible in unextended markdown. But for simple +documents it should be adequate. The LaTeX and HTML readers are also +limited in what they can do. + +`pandoc` writes its output to STDOUT. If you want to write to a file, +use redirection: + + pandoc input.txt > output.html + +Note that you can specify multiple input files on the command line. +`pandoc` will concatenate them all (with blank lines between them) +before parsing: + + pandoc -s chapter1.txt chapter2.txt chapter3.txt references.txt > book.html + +## Character encoding + +Unfortunately, due to limitations in GHC, `pandoc` does not +automatically detect the system's local character encoding. Hence, +all input and output is assumed to be in the UTF-8 encoding. If you +use accented or foreign characters, you should convert the input file +to UTF-8 before processing it with `pandoc`. This can be done by +piping the input through [`iconv`]: for example, + + iconv -t utf-8 source.txt | pandoc > output.html + +will convert `source.txt` from the local encoding to UTF-8, then +convert it to HTML, putting the output in `output.html`. + +[`iconv`]: http://www.gnu.org/software/libiconv/ + +The shell scripts (described below) automatically convert the source +from the local encoding to UTF-8 before running them through `pandoc`. + +## The shell scripts + +For convenience, five shell scripts have been included that make it +easy to run `pandoc` without remembering all the command-line options. +All of the scripts presuppose that `pandoc` is in the path, and +`html2markdown` also presupposes that `curl` and `tidy` are in the +path. + +1. `markdown2html` converts markdown to HTML, running `iconv` first to + convert the file to UTF-8. (This can be used as a replacement for + `Markdown.pl`.) + +2. `html2markdown` can take either a filename or a URL as argument. If + it is given a URL, it uses `curl` to fetch the contents of the + specified URL, then filters this through `tidy` to straighten up the + HTML and convert to UTF-8, and finally passes this HTML to `pandoc` to + produce markdown text: + + html2markdown http://www.fsf.org + + html2markdown www.fsf.org + + html2markdown subdir/mylocalfile.html + +3. `latex2markdown` converts a LaTeX file to markdown. + + latex2markdown mytexfile.tex + +4. `markdown2latex` converts markdown to LaTeX: + + markdown2latex mytextfile.txt + +5. `markdown2pdf` converts markdown to PDF, using LaTeX, but removing + all the intermediate files created by LaTeX. Example: + + markdown2pdf mytextfile.txt + + creates a file `mytextfile.pdf` in the working directory. + +# Command-line options + +Various command-line options can be used to customize the output. +For a complete list, type + + pandoc --help + +`-p` or `--preserve-tabs` causes tabs in the source text to be +preserved, rather than converted to spaces (the default). + +`--tabstop` allows the user to set the tab stop (which defaults to 4). + +`-R` or `--parse-raw` causes the HTML and LaTeX readers to parse HTML +codes and LaTeX environments that it can't translate as raw HTML or +LaTeX. Raw HTML can be printed in markdown, reStructuredText, HTML, +and S5 output; raw LaTeX can be printed in markdown, reStructuredText, +and LaTeX output. The default is for the readers to omit +untranslatable HTML codes and LaTeX environments. (The LaTeX reader +does pass through untranslatable LaTeX commands, even if `-R` is not +specified.) + +`-s` or `--standalone` causes `pandoc` to produce a standalone file, +complete with appropriate document headers. By default, `pandoc` +produces a fragment. + +`--custom-header` can be used to specify a custom document header. To +see the headers used by default, use the `-D` option: for example, +`pandoc -D html` prints the default HTML header. + +`-c` or `--css` allows the user to specify a custom stylesheet that +will be linked to in HTML and S5 output. + +`-H` or `--include-in-header` specifies a file to be included +(verbatim) at the end of the document header. This can be used, for +example, to include special CSS or javascript in HTML documents. + +`-B` or `--include-before-body` specifies a file to be included +(verbatim) at the beginning of the document body (after the `<body>` +tag in HTML, or the `\begin{document}` command in LaTeX). This can be +used to include navigation bars or banners in HTML documents. + +`-A` or `--include-after-body` specifies a file to be included +(verbatim) at the end of the docment body (before the `</body>` tag in +HTML, or the `\end{document}` command in LaTeX). + +`-T` or `--title-prefix` specifies a string to be included as a prefix +at the beginning of the title that appears in the HTML header (but not +in the title as it appears at the beginning of the HTML body). (See +below on Titles.) + +`-S` or `--smartypants` causes `pandoc` to produce typographically +correct HTML output, along the lines of John Gruber's [Smartypants]. +Straight quotes are converted to curly quotes, `---` to dashes, and +`...` to ellipses. + +[Smartypants]: http://daringfireball.net/projects/smartypants/ + +`-m` or `--asciimathml` will cause LaTeX formulas (between $ signs) in +HTML or S5 to display as formulas rather than as code. The trick will +not work in all browsers, but it works in Firefox. Peter Jipsen's +[ASCIIMathML] script is used to do the magic. + +[ASCIIMathML]: http://www1.chapman.edu/~jipsen/mathml/asciimath.html + +`-i` or `--incremental` causes all lists in S5 output to be displayed +incrementally by default (one item at a time). The normal default +is for lists to be displayed all at once. + +`-N` or `--number-sections` causes sections to be numbered in LaTeX +output. By default, sections are not numbered. + +# `pandoc`'s markdown vs. standard markdown + +In parsing markdown, `pandoc` departs from and extends [standard markdown] +in a few respects. (To run `pandoc` on the official +markdown test suite, type `make markdown_tests`.) + +[standard markdown]: http://daringfireball.net/projects/markdown/syntax + +## Lists + +`pandoc` behaves differently from standard markdown on some "edge +cases" involving lists. Consider this source: + + 1. First + 2. Second: + - Fee + - Fie + - Foe + + 3. Third + +`pandoc` transforms this into a "compact list" (with no `<p>` tags +around "First", "Second", or "Third"), while markdown puts `<p>` +tags around "Second" and "Third" (but not "First"), because of +the blank space around "Third". `pandoc` follows a simple rule: +if the text is followed by a blank line, it is treated as a +paragraph. Since "Second" is followed by a list, and not a blank +line, it isn't treated as a paragraph. The fact that the list +is followed by a blank line is irrelevant. + +## Literal quotes in titles + +Standard markdown allows unescaped literal quotes in titles, as +in + + [foo]: "bar "embedded" baz" + +`pandoc` requires all quotes within titles to be escaped: + + [foo]: "bar \"embedded\" baz" + +## Reference links + +`pandoc` allows implicit reference links in either of two styles: + + 1. Here's my [link] + 2. Here's my [link][] + + [link]: linky.com + +If there's no corresponding reference, the implicit reference link +will appear as regular bracketed text. Note: even `[link][]` will +appear as `[link]` if there's no reference for `link`. If you want +`[link][]`, use a backslash escape: `\[link]\[]`. + +## Footnotes + +`pandoc`'s markdown allows footnotes, using the following syntax: + + here is a footnote reference,^(1) and another.^(longnote) + + ^(1) Here is the footnote. It can go anywhere in the document, + except in embedded contexts like block quotes or lists. + + ^(longnote) Here's the other note. This one contains multiple + blocks. + ^ + ^ Caret characters are used to indicate that the blocks all belong + to a single footnote (as with block quotes). + ^ + ^ If you want, you can use a caret at the beginning of every line, + ^ as with blockquotes, but all that you need is a caret at the + ^ beginning of the first line of the block and any preceding + ^ blank lines. + +Footnote references may not contain spaces, tabs, or newlines. + +## Embedded HTML + +`pandoc` treats embedded HTML in markdown a bit differently than +Markdown 1.0. While Markdown 1.0 leaves HTML blocks exactly as they +are, `pandoc` treats text between HTML tags as markdown. Thus, for +example, `pandoc` will turn + + <table> + <tr> + <td>*one*</td> + <td>[a link](http://google.com)</td> + </tr> + </table> + +into + + <table> + <tr> + <td><em>one</em></td> + <td><a href="http://google.com">a link</a></td> + </tr> + </table> + +whereas Markdown 1.0 will preserve it as is. + +There is one exception to this rule: text between `<script>` and +`</script>` tags is not interpreted as markdown. + +This departure from standard markdown should make it easier to mix +markdown with HTML block elements. For example, one can surround +a block of markdown text with `<div>` tags without preventing it +from being interpreted as markdown. + +## Title blocks + +If the file begins with a title block + + % title + % author(s) (separated by commas) + % date + +it will be parsed as bibliographic information, not regular text. (It +will be used, for example, in the title of standalone LaTeX or HTML +output.) The block may contain just a title, a title and an author, +or all three lines. Each must begin with a % and fit on one line. +The title may contain standard inline formatting. If you want to +include an author but no title, or a title and a date but no author, +you need a blank line: + + % My title + % + % June 15, 2006 + +Titles will be written only when the `--standalone` (`-s`) option is +chosen. In HTML output, titles will appear twice: once in the +document head -- this is the title that will appear at the top of the +window in a browser -- and once at the beginning of the document body. +The title in the document head can have an optional prefix attached +(`--title-prefix` or `-T` option). The title in the body appears as +an H1 element with class "title", so it can be suppressed or +reformatted with CSS. + +If a title prefix is specified with `-T` and no title block appears +in the document, the title prefix will be used by itself as the +HTML title. + +## Box-style blockquotes + +`pandoc` supports emacs-style boxquote block quotes, in addition to +standard markdown (email-style) boxquotes: + + ,---- + | They look like this. + `---- + +## Inline LaTeX + +Anything between two $ characters will be parsed as LaTeX math. The +opening $ must have a character immediately to its right, while the +closing $ must have a character immediately to its left. Thus, +`$20,000 and $30,000` won't parse as math. The $ character can be +escaped with a backslash if needed. + +If you pass the `-m` (`--asciimathml`) option to `pandoc`, it will +include the [ASCIIMathML] script in the resulting HTML. This will +cause LaTeX math to be displayed as formulas in better browsers. + +[ASCIIMathML]: http://www1.chapman.edu/~jipsen/asciimath.html + +Inline LaTeX commands will also be preserved and passed unchanged +to the LaTeX writer. Thus, for example, you can use LaTeX to +include BibTeX citations: + + This result was proved in \cite{jones.1967}. + +You can also use LaTeX environments. For example, + + \begin{tabular}{|l|l|}\hline + Age & Frequency \\ \hline + 18--25 & 15 \\ + 26--35 & 33 \\ + 36--45 & 22 \\ \hline + \end{tabular} + +Note, however, that material between the begin and end tags will +be interpreted as raw LaTeX, not as markdown. + +## Custom headers + +When run with the "standalone" option (`-s`), `pandoc` creates a +standalone file, complete with an appropriate header. To see the +default headers used for html and latex, use the following commands: + + pandoc -D html + + pandoc -D latex + +If you want to use a different header, just create a file containing +it and specify it on the command line as follows: + + pandoc --header=MyHeaderFile + +# Producing S5 with `pandoc` + +Producing an [S5] slide show with `pandoc` is easy. A title page is +constructed automatically from the document's title block (see above). +Each section (with a level-one header) produces a single slide. (Note +that if the section is too big, the slide will not fit on the page; S5 +is not smart enough to produce multiple pages.) + +Here's the markdown source for a simple slide show, `eating.txt`: + + % Eating Habits + % John Doe + % March 22, 2005 + + # In the morning + + - Eat eggs + - Drink coffee + + # In the evening + + - Eat spaghetti + - Drink wine + +To produce the slide show, simply type + + pandoc -w s5 -s eating.txt > eating.html + +and open up `eating.html` in a browser. The HTML file embeds +all the required javascript and CSS, so no other files are necessary. + +Note that by default, the S5 writer produces lists that display +"all at once." If you want your lists to display incrementally +(one item at a time), use the `-i` option. If you want a +particular list to depart from the default (that is, to display +incrementally without the `-i` option and all at once with the +`-i` option), put it in a block quote: + + > - Eat spaghetti + > - Drink wine + +In this way incremental and nonincremental lists can be mixed in +a single document. + diff --git a/Setup.hs b/Setup.hs new file mode 100644 index 000000000..362b40cf4 --- /dev/null +++ b/Setup.hs @@ -0,0 +1,2 @@ +import Distribution.Simple +main = defaultMainWithHooks defaultUserHooks @@ -0,0 +1,2 @@ +# TODO + diff --git a/configure b/configure new file mode 100644 index 000000000..064cd719a --- /dev/null +++ b/configure @@ -0,0 +1,20 @@ +#!/bin/sh + +# GHC does not recognize any environment variable, unlike with GCC which honors +# CFLAGS. This hook is a workaround for this flaw and introduces an HCFLAGS +# variable. + +CABAL=Pandoc.cabal +BUILDINFO=${CABAL%%.cabal}.buildinfo + +[ -f $BUILDINFO.in ] || { + echo >&2 "==> No $BUILDINFO.in exists; skipping $BUILDINFO creation." + exit 0 +} + +if [ "${HCFLAGS-UNDEFINED}" = "UNDEFINED" ]; then + echo >&2 "==> No HCFLAGS defined; skipping $BUILDINFO creation." + exit 0 +fi + +sed -e "s#@HCFLAGS@#$HCFLAGS#g" $BUILDINFO.in >$BUILDINFO diff --git a/debian/changelog b/debian/changelog new file mode 100644 index 000000000..7a71dfd06 --- /dev/null +++ b/debian/changelog @@ -0,0 +1,19 @@ +pandoc (0.21) unstable; urgency=low + + * Revamp and split Debian package. Closes: #391666. + * Revamped build system. + * Various fixes in wrapper scripts. + + -- Recai Oktaş <roktas@debian.org> Sun, 3 Sep 2006 13:25:18 +0300 + +pandoc (0.2) unstable; urgency=low + + * Fixed unicode/utf-8 translation + + -- John MacFarlane <clemens@kclee.de> Mon, 14 Aug 2006 00:00:00 -0400 + +pandoc (0.1) unstable; urgency=low + + * Initial creation of debian package + + -- John MacFarlane <clemens@kclee.de> Mon, 14 Aug 2006 00:00:00 -0400 diff --git a/debian/compat b/debian/compat new file mode 100644 index 000000000..b8626c4cf --- /dev/null +++ b/debian/compat @@ -0,0 +1 @@ +4 diff --git a/debian/control b/debian/control new file mode 100644 index 000000000..99f70c269 --- /dev/null +++ b/debian/control @@ -0,0 +1,42 @@ +Source: pandoc +Section: text +Priority: optional +Maintainer: Recai Oktaş <roktas@debian.org> +Build-Depends: debhelper (>= 4.0.0), haskell-devscripts (>=0.5.11), ghc6 (>=6.4), perl +Build-Depends-Indep: haddock +Standards-Version: 3.7.2.0 + +Package: pandoc +Section: text +Architecture: any +Depends: ${shlibs:Depends} +Suggests: tetex-bin, tidy, wget | w3m +Description: General markup converter + Pandoc is an implementation of Markdown (and much more) in Haskell. It + can convert Markdown formatted text to HTML, LaTeX, rich text format, + reStructuredText, or an S5 HTML slide show. It can also convert HTML, + LaTeX, and reStructuredText to Markdown. + +Package: libghc6-pandoc-dev +Section: libdevel +Architecture: any +Depends: ${haskell:Depends} +Suggests: pandoc-doc +Description: General markup converter + Pandoc is an implementation of Markdown (and much more) in Haskell. It + can convert Markdown formatted text to HTML, LaTeX, rich text format, + reStructuredText, or an S5 HTML slide show. It can also convert HTML, + LaTeX, and reStructuredText to Markdown. + . + This package contains the libraries compiled for GHC 6. + +Package: pandoc-doc +Section: doc +Architecture: all +Description: General markup converter + Pandoc is an implementation of Markdown (and much more) in Haskell. It + can convert Markdown formatted text to HTML, LaTeX, rich text format, + reStructuredText, or an S5 HTML slide show. It can also convert HTML, + LaTeX, and reStructuredText to Markdown. + . + This package contains the library documentation for Pandoc. diff --git a/debian/copyright b/debian/copyright new file mode 100644 index 000000000..6ed3ec2ca --- /dev/null +++ b/debian/copyright @@ -0,0 +1,62 @@ +Pandoc is copyright 2006 by John MacFarlane <jgm@berkeley.edu>. It is licensed +under the terms of the GPL version 2 or later. On Debian systems, the complete +text of the GPL can be found in /usr/share/common-licenses/GPL. + +This package was debianized by Recai Oktaş <roktas@debian.org>. It was +downloaded from http://sophos.berkeley.edu/macfarlane/ + +---------------------------------------------------------------------- + +UTF8.hs + +Copyright (c) 2003, OGI School of Science & Engineering, Oregon Health & +Science University, All rights reserved. + +Redistribution and use in source and binary forms, with or without +modification, are permitted provided that the following conditions +are met: + +- Redistributions of source code must retain the above copyright + notice, this list of conditions and the following disclaimer. + +- Redistributions in binary form must reproduce the above + copyright notice, this list of conditions and the following + disclaimer in the documentation and/or other materials provided + with the distribution. + +- Neither the name of OGI or OHSU nor the names of its + contributors may be used to endorse or promote products derived + from this software without specific prior written permission. + +THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS +"AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT +LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR +A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT +OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, +SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED +TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR +PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF +LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING +NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS +SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE. + +modified by Martin Norbäck +modified to pass illegal utf-8 sequences through unchanged + +---------------------------------------------------------------------- + +ASCIIMathML.js + +Copyright 2005, Peter Jipsen, Chapman University +<http://www1.chapman.edu/~jipsen/mathml/asciimath.html> + +Released under the GPL. + +---------------------------------------------------------------------- + +S5 slides.js and css files + +by Eric A. Meyer +<http://meyerweb.com/eric/tools/s5 + +Released under an explicit Public Domain License diff --git a/debian/pandoc-doc.doc-base b/debian/pandoc-doc.doc-base new file mode 100644 index 000000000..3fd80e7d9 --- /dev/null +++ b/debian/pandoc-doc.doc-base @@ -0,0 +1,11 @@ +Document: pandoc-doc +Title: Pandoc documentation +Author: John MacFarlane +Abstract: This is the documentation of Pandoc, which includes the API + documentation of the Pandoc library and documentation for the Pandoc + tools. +Section: Apps/Programming + +Format: html +Index: /usr/share/doc/pandoc-doc/index.html +Files: /usr/share/doc/pandoc-doc/*.html /usr/share/doc/pandoc-doc/pandoc/*.html diff --git a/debian/pandoc-doc.docs b/debian/pandoc-doc.docs new file mode 100644 index 000000000..cf7cb60ed --- /dev/null +++ b/debian/pandoc-doc.docs @@ -0,0 +1 @@ +html/* diff --git a/debian/pandoc.dirs b/debian/pandoc.dirs new file mode 100644 index 000000000..e77248175 --- /dev/null +++ b/debian/pandoc.dirs @@ -0,0 +1 @@ +usr/bin diff --git a/debian/rules b/debian/rules new file mode 100644 index 000000000..45a999435 --- /dev/null +++ b/debian/rules @@ -0,0 +1,113 @@ +#!/usr/bin/make -f +# +# debian/rules for pandoc. +# Copyright © 2006 Recai Oktaş <roktasATdebian.org> +# +# This file is based on John Goerzen's Cabal Debian template. +# See http://www.n-heptane.com/nhlab/repos/cabalDebianTemplate/ +# +# Licensed under the GNU General Public License, version 2. +# See the file 'http://www.gnu.org/copyleft/gpl.txt'. + +THIS := pandoc + +# Uncomment this to turn on verbose mode. +#export DH_VERBOSE=1 + +# Handle noopt in DEB_BUILD_OPTIONS. Emulate CFLAGS (as HCFLAGS). +ifneq (,$(findstring noopt,$(DEB_BUILD_OPTIONS))) +MAKE_ENVVARS := HCFLAGS=-O0 +else +MAKE_ENVVARS := HCFLAGS=-O2 +endif +MAKE_ENVVARS += PREFIX=/usr + +configure: configure-stamp +configure-stamp: + dh_testdir + $(MAKE_ENVVARS) $(MAKE) configure + + touch configure-stamp + +build: build-stamp +build-stamp: configure-stamp + dh_testdir + + touch build-stamp + +clean: + dh_testdir + dh_testroot + $(MAKE) clean + rm -rf setup Setup.hi Setup.ho Setup.o .*config* dist html + rm -f build-stamp configure-stamp + + dh_clean + +install: build + dh_testdir + dh_testroot + dh_clean -k + dh_installdirs -a + + dh_haskell -a + + # Hack! Cabal builds executables while building libraries. Move these + # files to top dir where the Makefile install target expects to find. + # See "BUGS" section at the following document: + # http://www.n-heptane.com/nhlab/repos/cabalDebianTemplate/INSTRUCTIONS.txt + find debian/libghc6-$(THIS)-dev -type d -name 'bin' -true | \ + while read bin; do mv $$bin/* .; rm -rf $$bin; done + DESTDIR=debian/$(THIS) $(MAKE_ENVVARS) $(MAKE) install + +build-indep: build-indep-stamp +build-indep-stamp: + dh_testdir + $(MAKE) build-lib-doc + +install-indep: build-indep + dh_testdir + dh_testroot + dh_clean -k + dh_installdirs -i + + dh_haskell -i + +# Build architecture-independent files here. +binary-indep: build-indep install-indep + dh_testdir + dh_testroot + dh_installchangelogs -i + dh_installdocs -i + dh_installexamples -i + dh_installman -i + dh_link -i + dh_strip -i + dh_compress -i + dh_fixperms -i + dh_installdeb -i + dh_shlibdeps -i + dh_gencontrol -i + dh_md5sums -i + dh_builddeb -i + +# Build architecture-dependent files here. +binary-arch: build install + dh_testdir + dh_testroot + dh_installchangelogs -a + dh_installdocs -a + dh_installexamples -a + dh_installman -a + dh_link -a + dh_strip -a -Xhtml2 -Xmarkdown2 -Xlatex2 + dh_compress -a + dh_fixperms -a + dh_installdeb -a + dh_shlibdeps -a + dh_gencontrol -a + dh_md5sums -a + dh_builddeb -a + +binary: binary-indep binary-arch +.PHONY: build clean binary-indep binary-arch binary install build-indep install-indep diff --git a/html2markdown b/html2markdown new file mode 100644 index 000000000..3f9a4857e --- /dev/null +++ b/html2markdown @@ -0,0 +1,39 @@ +#!/bin/sh -e +# converts html to markdown +# uses an available program to fetch URL and tidy to normalize it first + +[ -n "$(which pandoc)" ] || { + echo >&2 "You need 'pandoc' to use this program!" + exit 1 +} +[ -n "$(which tidy)" ] || { + echo >&2 "You need 'tidy' to use this program!" + exit 1 +} + +if [ -z "$1" ] || [ -f $1 ]; then + tidy -utf8 $1 2>/dev/null | pandoc -r html -w markdown -s +else + # Treat given argument as an URL. Locate a + # sensible text based browser (note the order). + for p in wget lynx w3m curl links w3c; do + if which $p >/dev/null; then + DUMPER=$p + break + fi + done + # Setup proper options. + case "$DUMPER" in + wget) OPT="-O-" ;; + lynx) OPT="-source" ;; + w3m) OPT="-dump_source" ;; + curl) OPT="" ;; + links) OPT="-source" ;; + w3c) OPT="-n -get" ;; + "") echo -n >&2 "Needs a program to fetch the URL " + echo -n >&2 "(e.g. wget, w3m, lynx, w3m or curl)." + exit 1 ;; + esac + # Fetch and feed to pandoc. + $DUMPER $OPT $1 2>/dev/null | tidy -utf8 2>/dev/null | pandoc -r html -w markdown -s +fi diff --git a/latex2markdown b/latex2markdown new file mode 100644 index 000000000..ce75ac117 --- /dev/null +++ b/latex2markdown @@ -0,0 +1,7 @@ +#!/bin/sh -e +# runs pandoc to convert latex to markdown +[ -n "$(which pandoc)" ] || { + echo >&2 "You need 'pandoc' to use this program!" + exit 1 +} +iconv -t utf-8 $* | pandoc -r latex -w markdown -s diff --git a/man/man1/html2markdown.1 b/man/man1/html2markdown.1 new file mode 100644 index 000000000..bb084e36e --- /dev/null +++ b/man/man1/html2markdown.1 @@ -0,0 +1,15 @@ +.TH PANDOC 1 "AUGUST 2006" Linux "User Manuals" +.SH NAME +html2markdown \- converts HTML to markdown-formatted text +.SH SYNOPSIS +.B html2markdown [input-file or URL] +.SH DESCRIPTION +.B html2markdown +converts input-file (or text from STDIN) or URL from HTML to +markdown-formatted plain text. Uses an available program +(e.g. wget, w3m, lynx or curl) to fetch the URL. +.SH AUTHOR +John MacFarlane <jgm at berkeley.edu> +.SH "SEE ALSO" +pandoc (1), markdown2html (1), markdown2latex (1), latex2markdown (1), markdown2pdf (1) + diff --git a/man/man1/latex2markdown.1 b/man/man1/latex2markdown.1 new file mode 100644 index 000000000..abc140a0f --- /dev/null +++ b/man/man1/latex2markdown.1 @@ -0,0 +1,13 @@ +.TH PANDOC 1 "AUGUST 2006" Linux "User Manuals" +.SH NAME +latex2markdown \- converts LaTeX to markdown-formatted text +.SH SYNOPSIS +.B latex2markdown [input-file] +.SH DESCRIPTION +.B latex2markdown +converts input-file from LaTeX to markdown-formatted plain text. +.SH AUTHOR +John MacFarlane <jgm at berkeley.edu> +.SH "SEE ALSO" +pandoc (1), markdown2html (1), html2markdown (1), markdown2latex (1), markdown2pdf (1) + diff --git a/man/man1/markdown2html.1 b/man/man1/markdown2html.1 new file mode 100644 index 000000000..cc91a9a6a --- /dev/null +++ b/man/man1/markdown2html.1 @@ -0,0 +1,15 @@ +.TH PANDOC 1 "AUGUST 2006" Linux "User Manuals" +.SH NAME +markdown2html \- converts markdown-formatted text to HTML +.SH SYNOPSIS +.B markdown2html [input-files] +.SH DESCRIPTION +.B markdown2html +converts input-files (or text from STDIN) from markdown-formatted +plain text to HTML. +.SH AUTHOR +John MacFarlane <jgm at berkeley.edu> +.SH "SEE ALSO" +pandoc (1), html2markdown (1), markdown2latex (1), latex2markdown (1), +markdown2pdf (1) + diff --git a/man/man1/markdown2latex.1 b/man/man1/markdown2latex.1 new file mode 100644 index 000000000..ee34dd112 --- /dev/null +++ b/man/man1/markdown2latex.1 @@ -0,0 +1,15 @@ +.TH PANDOC 1 "AUGUST 2006" Linux "User Manuals" +.SH NAME +markdown2latex \- converts markdown-formatted text to LaTeX +.SH SYNOPSIS +.B markdown2latex [input-files] +.SH DESCRIPTION +.B markdown2latex +converts input-files (or text from STDIN) from markdown-formatted +plain text to LaTeX. +.SH AUTHOR +John MacFarlane <jgm at berkeley.edu> +.SH "SEE ALSO" +pandoc (1), markdown2html (1), html2markdown (1), latex2markdown (1), +markdown2pdf (1) + diff --git a/man/man1/markdown2pdf.1 b/man/man1/markdown2pdf.1 new file mode 100644 index 000000000..f49d0e3d3 --- /dev/null +++ b/man/man1/markdown2pdf.1 @@ -0,0 +1,16 @@ +.TH PANDOC 1 "AUGUST 2006" Linux "User Manuals" +.SH NAME +markdown2pdf \- converts markdown-formatted text to PDF, using pdflatex +.SH SYNOPSIS +.B markdown2pdf [input-file] +.SH DESCRIPTION +.B markdown2pdf +converts input-file (or text from STDIN, which in this case, the +resulting PDF file is named as 'stdin.pdf') from markdown-formatted +plain text to PDF, using LaTeX. Cleans up intermediate LaTeX files. +.SH AUTHOR +John MacFarlane <jgm at berkeley.edu> +.SH "SEE ALSO" +pandoc (1), markdown2html (1), html2markdown (1), markdown2latex (1), +latex2markdown (1) + diff --git a/man/man1/pandoc.1 b/man/man1/pandoc.1 new file mode 100644 index 000000000..8fb4afe5e --- /dev/null +++ b/man/man1/pandoc.1 @@ -0,0 +1,20 @@ +.TH PANDOC 1 "AUGUST 2006" Linux "User Manuals" +.SH NAME +pandoc \- general markup converter +.SH SYNOPSIS +.B pandoc [options] [input-files] +.SH DESCRIPTION +.B pandoc +converts files from one markup format to another. It can read markdown +and (with some limitations) reStructuredText, HTML, and LaTeX, and it +can write markdown, reStructuredText, HTML, LaTeX, RTF, and S5 HTML +slide shows. +.SH OPTIONS +For full usage information, including command-line options, +type +.B pandoc -h +.SH AUTHOR +John MacFarlane <jgm at berkeley.edu> +.SH "SEE ALSO" +markdown2html (1), html2markdown (1), markdown2latex (1), latex2markdown (1), markdown2pdf (1) + diff --git a/markdown2html b/markdown2html new file mode 100644 index 000000000..50d7a7e2a --- /dev/null +++ b/markdown2html @@ -0,0 +1,7 @@ +#!/bin/sh -e +# converts markdown to HTML +[ -n "$(which pandoc)" ] || { + echo >&2 "You need 'pandoc' to use this program!" + exit 1 +} +iconv -t utf-8 $* | pandoc diff --git a/markdown2latex b/markdown2latex new file mode 100644 index 000000000..76d24dc10 --- /dev/null +++ b/markdown2latex @@ -0,0 +1,7 @@ +#!/bin/sh -e +# converts markdown to latex +[ -n "$(which pandoc)" ] || { + echo >&2 "You need 'pandoc' to use this program!" + exit 1 +} +iconv -t utf-8 $* | pandoc -w latex -s diff --git a/markdown2pdf b/markdown2pdf new file mode 100644 index 000000000..6a76aab7d --- /dev/null +++ b/markdown2pdf @@ -0,0 +1,44 @@ +#!/bin/sh -e +# converts markdown to latex, then uses latex to make a PDF + +[ -n "$(which pandoc)" ] || { + echo >&2 "You need 'pandoc' to use this program!" + exit 1 +} +[ -n "$(which pdflatex)" ] || { + echo >&2 "You need 'pdflatex' to use this program!" + exit 1 +} + +TEMP=${TMPDIR-/tmp}/markdown2pdf.$$ +trap "status=$?; rm -rf $TEMP; exit $status" 0 INT + +if [ -z "$1" ]; then + BASE='stdin' # input is STDIN, since no argument given +else + filename=${1##*/} + BASE=${filename%\.*} +fi + +mkdir -p $TEMP && iconv -t utf-8 $* | pandoc -w latex -s > $TEMP/$BASE.tex +( + cd $TEMP + if ! pdflatex -interaction=batchmode $BASE.tex >/dev/null 2>&1; then + echo >&2 "LaTeX errors:" + cat >&2 $BASE.log + exit 1 + fi +) || exit $? + +is_target_exists= +if [ -f $BASE.pdf ]; then + is_target_exists=1 +fi + +cp --suffix=~ --backup $TEMP/$BASE.pdf . + +echo -n >&2 "Created $BASE.pdf" +[ -z "$is_target_exists" ] || { + echo -n >&2 " (previous file has been backed up as '$BASE.pdf~')" +} +echo >&2 . diff --git a/src/ASCIIMathML.js b/src/ASCIIMathML.js new file mode 100644 index 000000000..216b04b3e --- /dev/null +++ b/src/ASCIIMathML.js @@ -0,0 +1,945 @@ +/* +ASCIIMathML.js +============== +This file contains JavaScript functions to convert ASCII math notation +to Presentation MathML. The conversion is done while the (X)HTML page +loads, and should work with Firefox/Mozilla/Netscape 7+ and Internet +Explorer 6+MathPlayer (http://www.dessci.com/en/products/mathplayer/). +Just add the next line to your (X)HTML page with this file in the same folder: +<script type="text/javascript" src="ASCIIMathML.js"></script> +This is a convenient and inexpensive solution for authoring MathML. + +Version 1.4.7 Dec 15, 2005, (c) Peter Jipsen http://www.chapman.edu/~jipsen +Latest version at http://www.chapman.edu/~jipsen/mathml/ASCIIMathML.js +For changes see http://www.chapman.edu/~jipsen/mathml/asciimathchanges.txt +If you use it on a webpage, please send the URL to jipsen@chapman.edu + +Modified July 2006 by John MacFarlane (added CODE to list of contexts +in which replacement does not occur, modified AMisMathMLAvailable +to better identify Safari browser). + +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 (at http://www.gnu.org/copyleft/gpl.html) +for more details. +*/ + +var checkForMathML = true; // check if browser can display MathML +var notifyIfNoMathML = true; // display note if no MathML capability +var alertIfNoMathML = false; // show alert box if no MathML capability +var mathcolor = "red"; // change it to "" (to inherit) or any other color +var mathfontfamily = "serif"; // change to "" to inherit (works in IE) + // or another family (e.g. "arial") +var displaystyle = true; // puts limits above and below large operators +var showasciiformulaonhover = true; // helps students learn ASCIIMath +var decimalsign = "."; // change to "," if you like, beware of `(1,2)`! +var AMdelimiter1 = "`", AMescape1 = "\\\\`"; // can use other characters +var AMdelimiter2 = "$", AMescape2 = "\\\\\\$", AMdelimiter2regexp = "\\$"; +var doubleblankmathdelimiter = false; // if true, x+1 is equal to `x+1` + // for IE this works only in <!-- --> +//var separatetokens;// has been removed (email me if this is a problem) +var isIE = document.createElementNS==null; + +if (document.getElementById==null) + alert("This webpage requires a recent browser such as\ +\nMozilla/Netscape 7+ or Internet Explorer 6+MathPlayer") + +// all further global variables start with "AM" + +function AMcreateElementXHTML(t) { + if (isIE) return document.createElement(t); + else return document.createElementNS("http://www.w3.org/1999/xhtml",t); +} + +function AMnoMathMLNote() { + var nd = AMcreateElementXHTML("h3"); + nd.setAttribute("align","center") + nd.appendChild(AMcreateElementXHTML("p")); + nd.appendChild(document.createTextNode("To view the ")); + var an = AMcreateElementXHTML("a"); + an.appendChild(document.createTextNode("ASCIIMathML")); + an.setAttribute("href","http://www.chapman.edu/~jipsen/asciimath.html"); + nd.appendChild(an); + nd.appendChild(document.createTextNode(" notation use Internet Explorer 6+")); + an = AMcreateElementXHTML("a"); + an.appendChild(document.createTextNode("MathPlayer")); + an.setAttribute("href","http://www.dessci.com/en/products/mathplayer/download.htm"); + nd.appendChild(an); + nd.appendChild(document.createTextNode(" or Netscape/Mozilla/Firefox")); + nd.appendChild(AMcreateElementXHTML("p")); + return nd; +} + +function AMisMathMLavailable() { + var regex = /KHTML/; /* This line and the next two modified by JM for better Safari detection */ + if (navigator.appName.slice(0,8)=="Netscape") + if (navigator.appVersion.slice(0,1)>="5" && !regex.test(navigator.userAgent)) return null; + else return AMnoMathMLNote(); + else if (navigator.appName.slice(0,9)=="Microsoft") + try { + var ActiveX = new ActiveXObject("MathPlayer.Factory.1"); + return null; + } catch (e) { + return AMnoMathMLNote(); + } + else return AMnoMathMLNote(); +} + +// character lists for Mozilla/Netscape fonts +var AMcal = [0xEF35,0x212C,0xEF36,0xEF37,0x2130,0x2131,0xEF38,0x210B,0x2110,0xEF39,0xEF3A,0x2112,0x2133,0xEF3B,0xEF3C,0xEF3D,0xEF3E,0x211B,0xEF3F,0xEF40,0xEF41,0xEF42,0xEF43,0xEF44,0xEF45,0xEF46]; +var AMfrk = [0xEF5D,0xEF5E,0x212D,0xEF5F,0xEF60,0xEF61,0xEF62,0x210C,0x2111,0xEF63,0xEF64,0xEF65,0xEF66,0xEF67,0xEF68,0xEF69,0xEF6A,0x211C,0xEF6B,0xEF6C,0xEF6D,0xEF6E,0xEF6F,0xEF70,0xEF71,0x2128]; +var AMbbb = [0xEF8C,0xEF8D,0x2102,0xEF8E,0xEF8F,0xEF90,0xEF91,0x210D,0xEF92,0xEF93,0xEF94,0xEF95,0xEF96,0x2115,0xEF97,0x2119,0x211A,0x211D,0xEF98,0xEF99,0xEF9A,0xEF9B,0xEF9C,0xEF9D,0xEF9E,0x2124]; + +var CONST = 0, UNARY = 1, BINARY = 2, INFIX = 3, LEFTBRACKET = 4, + RIGHTBRACKET = 5, SPACE = 6, UNDEROVER = 7, DEFINITION = 8, + LEFTRIGHT = 9, TEXT = 10; // token types + +var AMsqrt = {input:"sqrt", tag:"msqrt", output:"sqrt", tex:null, ttype:UNARY}, + AMroot = {input:"root", tag:"mroot", output:"root", tex:null, ttype:BINARY}, + AMfrac = {input:"frac", tag:"mfrac", output:"/", tex:null, ttype:BINARY}, + AMdiv = {input:"/", tag:"mfrac", output:"/", tex:null, ttype:INFIX}, + AMover = {input:"stackrel", tag:"mover", output:"stackrel", tex:null, ttype:BINARY}, + AMsub = {input:"_", tag:"msub", output:"_", tex:null, ttype:INFIX}, + AMsup = {input:"^", tag:"msup", output:"^", tex:null, ttype:INFIX}, + AMtext = {input:"text", tag:"mtext", output:"text", tex:null, ttype:TEXT}, + AMmbox = {input:"mbox", tag:"mtext", output:"mbox", tex:null, ttype:TEXT}, + AMquote = {input:"\"", tag:"mtext", output:"mbox", tex:null, ttype:TEXT}; + +var AMsymbols = [ +//some greek symbols +{input:"alpha", tag:"mi", output:"\u03B1", tex:null, ttype:CONST}, +{input:"beta", tag:"mi", output:"\u03B2", tex:null, ttype:CONST}, +{input:"chi", tag:"mi", output:"\u03C7", tex:null, ttype:CONST}, +{input:"delta", tag:"mi", output:"\u03B4", tex:null, ttype:CONST}, +{input:"Delta", tag:"mo", output:"\u0394", tex:null, ttype:CONST}, +{input:"epsi", tag:"mi", output:"\u03B5", tex:"epsilon", ttype:CONST}, +{input:"varepsilon", tag:"mi", output:"\u025B", tex:null, ttype:CONST}, +{input:"eta", tag:"mi", output:"\u03B7", tex:null, ttype:CONST}, +{input:"gamma", tag:"mi", output:"\u03B3", tex:null, ttype:CONST}, +{input:"Gamma", tag:"mo", output:"\u0393", tex:null, ttype:CONST}, +{input:"iota", tag:"mi", output:"\u03B9", tex:null, ttype:CONST}, +{input:"kappa", tag:"mi", output:"\u03BA", tex:null, ttype:CONST}, +{input:"lambda", tag:"mi", output:"\u03BB", tex:null, ttype:CONST}, +{input:"Lambda", tag:"mo", output:"\u039B", tex:null, ttype:CONST}, +{input:"mu", tag:"mi", output:"\u03BC", tex:null, ttype:CONST}, +{input:"nu", tag:"mi", output:"\u03BD", tex:null, ttype:CONST}, +{input:"omega", tag:"mi", output:"\u03C9", tex:null, ttype:CONST}, +{input:"Omega", tag:"mo", output:"\u03A9", tex:null, ttype:CONST}, +{input:"phi", tag:"mi", output:"\u03C6", tex:null, ttype:CONST}, +{input:"varphi", tag:"mi", output:"\u03D5", tex:null, ttype:CONST}, +{input:"Phi", tag:"mo", output:"\u03A6", tex:null, ttype:CONST}, +{input:"pi", tag:"mi", output:"\u03C0", tex:null, ttype:CONST}, +{input:"Pi", tag:"mo", output:"\u03A0", tex:null, ttype:CONST}, +{input:"psi", tag:"mi", output:"\u03C8", tex:null, ttype:CONST}, +{input:"Psi", tag:"mi", output:"\u03A8", tex:null, ttype:CONST}, +{input:"rho", tag:"mi", output:"\u03C1", tex:null, ttype:CONST}, +{input:"sigma", tag:"mi", output:"\u03C3", tex:null, ttype:CONST}, +{input:"Sigma", tag:"mo", output:"\u03A3", tex:null, ttype:CONST}, +{input:"tau", tag:"mi", output:"\u03C4", tex:null, ttype:CONST}, +{input:"theta", tag:"mi", output:"\u03B8", tex:null, ttype:CONST}, +{input:"vartheta", tag:"mi", output:"\u03D1", tex:null, ttype:CONST}, +{input:"Theta", tag:"mo", output:"\u0398", tex:null, ttype:CONST}, +{input:"upsilon", tag:"mi", output:"\u03C5", tex:null, ttype:CONST}, +{input:"xi", tag:"mi", output:"\u03BE", tex:null, ttype:CONST}, +{input:"Xi", tag:"mo", output:"\u039E", tex:null, ttype:CONST}, +{input:"zeta", tag:"mi", output:"\u03B6", tex:null, ttype:CONST}, + +//binary operation symbols +{input:"*", tag:"mo", output:"\u22C5", tex:"cdot", ttype:CONST}, +{input:"**", tag:"mo", output:"\u22C6", tex:"star", ttype:CONST}, +{input:"//", tag:"mo", output:"/", tex:null, ttype:CONST}, +{input:"\\\\", tag:"mo", output:"\\", tex:"backslash", ttype:CONST}, +{input:"setminus", tag:"mo", output:"\\", tex:null, ttype:CONST}, +{input:"xx", tag:"mo", output:"\u00D7", tex:"times", ttype:CONST}, +{input:"-:", tag:"mo", output:"\u00F7", tex:"divide", ttype:CONST}, +{input:"@", tag:"mo", output:"\u2218", tex:"circ", ttype:CONST}, +{input:"o+", tag:"mo", output:"\u2295", tex:"oplus", ttype:CONST}, +{input:"ox", tag:"mo", output:"\u2297", tex:"otimes", ttype:CONST}, +{input:"o.", tag:"mo", output:"\u2299", tex:"odot", ttype:CONST}, +{input:"sum", tag:"mo", output:"\u2211", tex:null, ttype:UNDEROVER}, +{input:"prod", tag:"mo", output:"\u220F", tex:null, ttype:UNDEROVER}, +{input:"^^", tag:"mo", output:"\u2227", tex:"wedge", ttype:CONST}, +{input:"^^^", tag:"mo", output:"\u22C0", tex:"bigwedge", ttype:UNDEROVER}, +{input:"vv", tag:"mo", output:"\u2228", tex:"vee", ttype:CONST}, +{input:"vvv", tag:"mo", output:"\u22C1", tex:"bigvee", ttype:UNDEROVER}, +{input:"nn", tag:"mo", output:"\u2229", tex:"cap", ttype:CONST}, +{input:"nnn", tag:"mo", output:"\u22C2", tex:"bigcap", ttype:UNDEROVER}, +{input:"uu", tag:"mo", output:"\u222A", tex:"cup", ttype:CONST}, +{input:"uuu", tag:"mo", output:"\u22C3", tex:"bigcup", ttype:UNDEROVER}, + +//binary relation symbols +{input:"!=", tag:"mo", output:"\u2260", tex:"ne", ttype:CONST}, +{input:":=", tag:"mo", output:":=", tex:null, ttype:CONST}, +{input:"lt", tag:"mo", output:"<", tex:null, ttype:CONST}, +{input:"<=", tag:"mo", output:"\u2264", tex:"le", ttype:CONST}, +{input:"lt=", tag:"mo", output:"\u2264", tex:"leq", ttype:CONST}, +{input:">=", tag:"mo", output:"\u2265", tex:"ge", ttype:CONST}, +{input:"geq", tag:"mo", output:"\u2265", tex:null, ttype:CONST}, +{input:"-<", tag:"mo", output:"\u227A", tex:"prec", ttype:CONST}, +{input:"-lt", tag:"mo", output:"\u227A", tex:null, ttype:CONST}, +{input:">-", tag:"mo", output:"\u227B", tex:"succ", ttype:CONST}, +{input:"-<=", tag:"mo", output:"\u2AAF", tex:"preceq", ttype:CONST}, +{input:">-=", tag:"mo", output:"\u2AB0", tex:"succeq", ttype:CONST}, +{input:"in", tag:"mo", output:"\u2208", tex:null, ttype:CONST}, +{input:"!in", tag:"mo", output:"\u2209", tex:"notin", ttype:CONST}, +{input:"sub", tag:"mo", output:"\u2282", tex:"subset", ttype:CONST}, +{input:"sup", tag:"mo", output:"\u2283", tex:"supset", ttype:CONST}, +{input:"sube", tag:"mo", output:"\u2286", tex:"subseteq", ttype:CONST}, +{input:"supe", tag:"mo", output:"\u2287", tex:"supseteq", ttype:CONST}, +{input:"-=", tag:"mo", output:"\u2261", tex:"equiv", ttype:CONST}, +{input:"~=", tag:"mo", output:"\u2245", tex:"cong", ttype:CONST}, +{input:"~~", tag:"mo", output:"\u2248", tex:"approx", ttype:CONST}, +{input:"prop", tag:"mo", output:"\u221D", tex:"propto", ttype:CONST}, + +//logical symbols +{input:"and", tag:"mtext", output:"and", tex:null, ttype:SPACE}, +{input:"or", tag:"mtext", output:"or", tex:null, ttype:SPACE}, +{input:"not", tag:"mo", output:"\u00AC", tex:"neg", ttype:CONST}, +{input:"=>", tag:"mo", output:"\u21D2", tex:"implies", ttype:CONST}, +{input:"if", tag:"mo", output:"if", tex:null, ttype:SPACE}, +{input:"<=>", tag:"mo", output:"\u21D4", tex:"iff", ttype:CONST}, +{input:"AA", tag:"mo", output:"\u2200", tex:"forall", ttype:CONST}, +{input:"EE", tag:"mo", output:"\u2203", tex:"exists", ttype:CONST}, +{input:"_|_", tag:"mo", output:"\u22A5", tex:"bot", ttype:CONST}, +{input:"TT", tag:"mo", output:"\u22A4", tex:"top", ttype:CONST}, +{input:"|--", tag:"mo", output:"\u22A2", tex:"vdash", ttype:CONST}, +{input:"|==", tag:"mo", output:"\u22A8", tex:"models", ttype:CONST}, + +//grouping brackets +{input:"(", tag:"mo", output:"(", tex:null, ttype:LEFTBRACKET}, +{input:")", tag:"mo", output:")", tex:null, ttype:RIGHTBRACKET}, +{input:"[", tag:"mo", output:"[", tex:null, ttype:LEFTBRACKET}, +{input:"]", tag:"mo", output:"]", tex:null, ttype:RIGHTBRACKET}, +{input:"{", tag:"mo", output:"{", tex:null, ttype:LEFTBRACKET}, +{input:"}", tag:"mo", output:"}", tex:null, ttype:RIGHTBRACKET}, +{input:"|", tag:"mo", output:"|", tex:null, ttype:LEFTRIGHT}, +//{input:"||", tag:"mo", output:"||", tex:null, ttype:LEFTRIGHT}, +{input:"(:", tag:"mo", output:"\u2329", tex:"langle", ttype:LEFTBRACKET}, +{input:":)", tag:"mo", output:"\u232A", tex:"rangle", ttype:RIGHTBRACKET}, +{input:"<<", tag:"mo", output:"\u2329", tex:null, ttype:LEFTBRACKET}, +{input:">>", tag:"mo", output:"\u232A", tex:null, ttype:RIGHTBRACKET}, +{input:"{:", tag:"mo", output:"{:", tex:null, ttype:LEFTBRACKET, invisible:true}, +{input:":}", tag:"mo", output:":}", tex:null, ttype:RIGHTBRACKET, invisible:true}, + +//miscellaneous symbols +{input:"int", tag:"mo", output:"\u222B", tex:null, ttype:CONST}, +{input:"dx", tag:"mi", output:"{:d x:}", tex:null, ttype:DEFINITION}, +{input:"dy", tag:"mi", output:"{:d y:}", tex:null, ttype:DEFINITION}, +{input:"dz", tag:"mi", output:"{:d z:}", tex:null, ttype:DEFINITION}, +{input:"dt", tag:"mi", output:"{:d t:}", tex:null, ttype:DEFINITION}, +{input:"oint", tag:"mo", output:"\u222E", tex:null, ttype:CONST}, +{input:"del", tag:"mo", output:"\u2202", tex:"partial", ttype:CONST}, +{input:"grad", tag:"mo", output:"\u2207", tex:"nabla", ttype:CONST}, +{input:"+-", tag:"mo", output:"\u00B1", tex:"pm", ttype:CONST}, +{input:"O/", tag:"mo", output:"\u2205", tex:"emptyset", ttype:CONST}, +{input:"oo", tag:"mo", output:"\u221E", tex:"infty", ttype:CONST}, +{input:"aleph", tag:"mo", output:"\u2135", tex:null, ttype:CONST}, +{input:"...", tag:"mo", output:"...", tex:"ldots", ttype:CONST}, +{input:":.", tag:"mo", output:"\u2234", tex:"therefore", ttype:CONST}, +{input:"/_", tag:"mo", output:"\u2220", tex:"angle", ttype:CONST}, +{input:"\\ ", tag:"mo", output:"\u00A0", tex:null, ttype:CONST}, +{input:"quad", tag:"mo", output:"\u00A0\u00A0", tex:null, ttype:CONST}, +{input:"qquad", tag:"mo", output:"\u00A0\u00A0\u00A0\u00A0", tex:null, ttype:CONST}, +{input:"cdots", tag:"mo", output:"\u22EF", tex:null, ttype:CONST}, +{input:"vdots", tag:"mo", output:"\u22EE", tex:null, ttype:CONST}, +{input:"ddots", tag:"mo", output:"\u22F1", tex:null, ttype:CONST}, +{input:"diamond", tag:"mo", output:"\u22C4", tex:null, ttype:CONST}, +{input:"square", tag:"mo", output:"\u25A1", tex:null, ttype:CONST}, +{input:"|__", tag:"mo", output:"\u230A", tex:"lfloor", ttype:CONST}, +{input:"__|", tag:"mo", output:"\u230B", tex:"rfloor", ttype:CONST}, +{input:"|~", tag:"mo", output:"\u2308", tex:"lceiling", ttype:CONST}, +{input:"~|", tag:"mo", output:"\u2309", tex:"rceiling", ttype:CONST}, +{input:"CC", tag:"mo", output:"\u2102", tex:null, ttype:CONST}, +{input:"NN", tag:"mo", output:"\u2115", tex:null, ttype:CONST}, +{input:"QQ", tag:"mo", output:"\u211A", tex:null, ttype:CONST}, +{input:"RR", tag:"mo", output:"\u211D", tex:null, ttype:CONST}, +{input:"ZZ", tag:"mo", output:"\u2124", tex:null, ttype:CONST}, +{input:"f", tag:"mi", output:"f", tex:null, ttype:UNARY, func:true}, +{input:"g", tag:"mi", output:"g", tex:null, ttype:UNARY, func:true}, + +//standard functions +{input:"lim", tag:"mo", output:"lim", tex:null, ttype:UNDEROVER}, +{input:"Lim", tag:"mo", output:"Lim", tex:null, ttype:UNDEROVER}, +{input:"sin", tag:"mo", output:"sin", tex:null, ttype:UNARY, func:true}, +{input:"cos", tag:"mo", output:"cos", tex:null, ttype:UNARY, func:true}, +{input:"tan", tag:"mo", output:"tan", tex:null, ttype:UNARY, func:true}, +{input:"sinh", tag:"mo", output:"sinh", tex:null, ttype:UNARY, func:true}, +{input:"cosh", tag:"mo", output:"cosh", tex:null, ttype:UNARY, func:true}, +{input:"tanh", tag:"mo", output:"tanh", tex:null, ttype:UNARY, func:true}, +{input:"cot", tag:"mo", output:"cot", tex:null, ttype:UNARY, func:true}, +{input:"sec", tag:"mo", output:"sec", tex:null, ttype:UNARY, func:true}, +{input:"csc", tag:"mo", output:"csc", tex:null, ttype:UNARY, func:true}, +{input:"log", tag:"mo", output:"log", tex:null, ttype:UNARY, func:true}, +{input:"ln", tag:"mo", output:"ln", tex:null, ttype:UNARY, func:true}, +{input:"det", tag:"mo", output:"det", tex:null, ttype:UNARY, func:true}, +{input:"dim", tag:"mo", output:"dim", tex:null, ttype:CONST}, +{input:"mod", tag:"mo", output:"mod", tex:null, ttype:CONST}, +{input:"gcd", tag:"mo", output:"gcd", tex:null, ttype:UNARY, func:true}, +{input:"lcm", tag:"mo", output:"lcm", tex:null, ttype:UNARY, func:true}, +{input:"lub", tag:"mo", output:"lub", tex:null, ttype:CONST}, +{input:"glb", tag:"mo", output:"glb", tex:null, ttype:CONST}, +{input:"min", tag:"mo", output:"min", tex:null, ttype:UNDEROVER}, +{input:"max", tag:"mo", output:"max", tex:null, ttype:UNDEROVER}, + +//arrows +{input:"uarr", tag:"mo", output:"\u2191", tex:"uparrow", ttype:CONST}, +{input:"darr", tag:"mo", output:"\u2193", tex:"downarrow", ttype:CONST}, +{input:"rarr", tag:"mo", output:"\u2192", tex:"rightarrow", ttype:CONST}, +{input:"->", tag:"mo", output:"\u2192", tex:"to", ttype:CONST}, +{input:"|->", tag:"mo", output:"\u21A6", tex:"mapsto", ttype:CONST}, +{input:"larr", tag:"mo", output:"\u2190", tex:"leftarrow", ttype:CONST}, +{input:"harr", tag:"mo", output:"\u2194", tex:"leftrightarrow", ttype:CONST}, +{input:"rArr", tag:"mo", output:"\u21D2", tex:"Rightarrow", ttype:CONST}, +{input:"lArr", tag:"mo", output:"\u21D0", tex:"Leftarrow", ttype:CONST}, +{input:"hArr", tag:"mo", output:"\u21D4", tex:"Leftrightarrow", ttype:CONST}, + +//commands with argument +AMsqrt, AMroot, AMfrac, AMdiv, AMover, AMsub, AMsup, +{input:"hat", tag:"mover", output:"\u005E", tex:null, ttype:UNARY, acc:true}, +{input:"bar", tag:"mover", output:"\u00AF", tex:"overline", ttype:UNARY, acc:true}, +{input:"vec", tag:"mover", output:"\u2192", tex:null, ttype:UNARY, acc:true}, +{input:"dot", tag:"mover", output:".", tex:null, ttype:UNARY, acc:true}, +{input:"ddot", tag:"mover", output:"..", tex:null, ttype:UNARY, acc:true}, +{input:"ul", tag:"munder", output:"\u0332", tex:"underline", ttype:UNARY, acc:true}, +AMtext, AMmbox, AMquote, +{input:"bb", tag:"mstyle", atname:"fontweight", atval:"bold", output:"bb", tex:null, ttype:UNARY}, +{input:"mathbf", tag:"mstyle", atname:"fontweight", atval:"bold", output:"mathbf", tex:null, ttype:UNARY}, +{input:"sf", tag:"mstyle", atname:"fontfamily", atval:"sans-serif", output:"sf", tex:null, ttype:UNARY}, +{input:"mathsf", tag:"mstyle", atname:"fontfamily", atval:"sans-serif", output:"mathsf", tex:null, ttype:UNARY}, +{input:"bbb", tag:"mstyle", atname:"mathvariant", atval:"double-struck", output:"bbb", tex:null, ttype:UNARY, codes:AMbbb}, +{input:"mathbb", tag:"mstyle", atname:"mathvariant", atval:"double-struck", output:"mathbb", tex:null, ttype:UNARY, codes:AMbbb}, +{input:"cc", tag:"mstyle", atname:"mathvariant", atval:"script", output:"cc", tex:null, ttype:UNARY, codes:AMcal}, +{input:"mathcal", tag:"mstyle", atname:"mathvariant", atval:"script", output:"mathcal", tex:null, ttype:UNARY, codes:AMcal}, +{input:"tt", tag:"mstyle", atname:"fontfamily", atval:"monospace", output:"tt", tex:null, ttype:UNARY}, +{input:"mathtt", tag:"mstyle", atname:"fontfamily", atval:"monospace", output:"mathtt", tex:null, ttype:UNARY}, +{input:"fr", tag:"mstyle", atname:"mathvariant", atval:"fraktur", output:"fr", tex:null, ttype:UNARY, codes:AMfrk}, +{input:"mathfrak", tag:"mstyle", atname:"mathvariant", atval:"fraktur", output:"mathfrak", tex:null, ttype:UNARY, codes:AMfrk} +]; + +function compareNames(s1,s2) { + if (s1.input > s2.input) return 1 + else return -1; +} + +var AMnames = []; //list of input symbols + +function AMinitSymbols() { + var texsymbols = [], i; + for (i=0; i<AMsymbols.length; i++) + if (AMsymbols[i].tex) + texsymbols[texsymbols.length] = {input:AMsymbols[i].tex, + tag:AMsymbols[i].tag, output:AMsymbols[i].output, ttype:AMsymbols[i].ttype}; + AMsymbols = AMsymbols.concat(texsymbols); + AMsymbols.sort(compareNames); + for (i=0; i<AMsymbols.length; i++) AMnames[i] = AMsymbols[i].input; +} + +var AMmathml = "http://www.w3.org/1998/Math/MathML"; + +function AMcreateElementMathML(t) { + if (isIE) return document.createElement("m:"+t); + else return document.createElementNS(AMmathml,t); +} + +function AMcreateMmlNode(t,frag) { +// var node = AMcreateElementMathML(name); + if (isIE) var node = document.createElement("m:"+t); + else var node = document.createElementNS(AMmathml,t); + node.appendChild(frag); + return node; +} + +function newcommand(oldstr,newstr) { + AMsymbols = AMsymbols.concat([{input:oldstr, tag:"mo", output:newstr, + tex:null, ttype:DEFINITION}]); +} + +function AMremoveCharsAndBlanks(str,n) { +//remove n characters and any following blanks + var st; + if (str.charAt(n)=="\\" && str.charAt(n+1)!="\\" && str.charAt(n+1)!=" ") + st = str.slice(n+1); + else st = str.slice(n); + for (var i=0; i<st.length && st.charCodeAt(i)<=32; i=i+1); + return st.slice(i); +} + +function AMposition(arr, str, n) { +// return position >=n where str appears or would be inserted +// assumes arr is sorted + if (n==0) { + var h,m; + n = -1; + h = arr.length; + while (n+1<h) { + m = (n+h) >> 1; + if (arr[m]<str) n = m; else h = m; + } + return h; + } else + for (var i=n; i<arr.length && arr[i]<str; i++); + return i; // i=arr.length || arr[i]>=str +} + +function AMgetSymbol(str) { +//return maximal initial substring of str that appears in names +//return null if there is none + var k = 0; //new pos + var j = 0; //old pos + var mk; //match pos + var st; + var tagst; + var match = ""; + var more = true; + for (var i=1; i<=str.length && more; i++) { + st = str.slice(0,i); //initial substring of length i + j = k; + k = AMposition(AMnames, st, j); + if (k<AMnames.length && str.slice(0,AMnames[k].length)==AMnames[k]){ + match = AMnames[k]; + mk = k; + i = match.length; + } + more = k<AMnames.length && str.slice(0,AMnames[k].length)>=AMnames[k]; + } + AMpreviousSymbol=AMcurrentSymbol; + if (match!=""){ + AMcurrentSymbol=AMsymbols[mk].ttype; + return AMsymbols[mk]; + } +// if str[0] is a digit or - return maxsubstring of digits.digits + AMcurrentSymbol=CONST; + k = 1; + st = str.slice(0,1); + var integ = true; + while ("0"<=st && st<="9" && k<=str.length) { + st = str.slice(k,k+1); + k++; + } + if (st == decimalsign) { + st = str.slice(k,k+1); + if ("0"<=st && st<="9") { + integ = false; + k++; + while ("0"<=st && st<="9" && k<=str.length) { + st = str.slice(k,k+1); + k++; + } + } + } + if ((integ && k>1) || k>2) { + st = str.slice(0,k-1); + tagst = "mn"; + } else { + k = 2; + st = str.slice(0,1); //take 1 character + tagst = (("A">st || st>"Z") && ("a">st || st>"z")?"mo":"mi"); + } + if (st=="-" && AMpreviousSymbol==INFIX) { + AMcurrentSymbol = INFIX; //trick "/" into recognizing "-" on second parse + return {input:st, tag:tagst, output:st, ttype:UNARY, func:true}; + } + return {input:st, tag:tagst, output:st, ttype:CONST}; +} + +function AMremoveBrackets(node) { + var st; + if (node.nodeName=="mrow") { + st = node.firstChild.firstChild.nodeValue; + if (st=="(" || st=="[" || st=="{") node.removeChild(node.firstChild); + } + if (node.nodeName=="mrow") { + st = node.lastChild.firstChild.nodeValue; + if (st==")" || st=="]" || st=="}") node.removeChild(node.lastChild); + } +} + +/*Parsing ASCII math expressions with the following grammar +v ::= [A-Za-z] | greek letters | numbers | other constant symbols +u ::= sqrt | text | bb | other unary symbols for font commands +b ::= frac | root | stackrel binary symbols +l ::= ( | [ | { | (: | {: left brackets +r ::= ) | ] | } | :) | :} right brackets +S ::= v | lEr | uS | bSS Simple expression +I ::= S_S | S^S | S_S^S | S Intermediate expression +E ::= IE | I/I Expression +Each terminal symbol is translated into a corresponding mathml node.*/ + +var AMnestingDepth,AMpreviousSymbol,AMcurrentSymbol; + +function AMparseSexpr(str) { //parses str and returns [node,tailstr] + var symbol, node, result, i, st,// rightvert = false, + newFrag = document.createDocumentFragment(); + str = AMremoveCharsAndBlanks(str,0); + symbol = AMgetSymbol(str); //either a token or a bracket or empty + if (symbol == null || symbol.ttype == RIGHTBRACKET && AMnestingDepth > 0) { + return [null,str]; + } + if (symbol.ttype == DEFINITION) { + str = symbol.output+AMremoveCharsAndBlanks(str,symbol.input.length); + symbol = AMgetSymbol(str); + } + switch (symbol.ttype) { + case UNDEROVER: + case CONST: + str = AMremoveCharsAndBlanks(str,symbol.input.length); + return [AMcreateMmlNode(symbol.tag, //its a constant + document.createTextNode(symbol.output)),str]; + case LEFTBRACKET: //read (expr+) + AMnestingDepth++; + str = AMremoveCharsAndBlanks(str,symbol.input.length); + result = AMparseExpr(str,true); + AMnestingDepth--; + if (typeof symbol.invisible == "boolean" && symbol.invisible) + node = AMcreateMmlNode("mrow",result[0]); + else { + node = AMcreateMmlNode("mo",document.createTextNode(symbol.output)); + node = AMcreateMmlNode("mrow",node); + node.appendChild(result[0]); + } + return [node,result[1]]; + case TEXT: + if (symbol!=AMquote) str = AMremoveCharsAndBlanks(str,symbol.input.length); + if (str.charAt(0)=="{") i=str.indexOf("}"); + else if (str.charAt(0)=="(") i=str.indexOf(")"); + else if (str.charAt(0)=="[") i=str.indexOf("]"); + else if (symbol==AMquote) i=str.slice(1).indexOf("\"")+1; + else i = 0; + if (i==-1) i = str.length; + st = str.slice(1,i); + if (st.charAt(0) == " ") { + node = AMcreateElementMathML("mspace"); + node.setAttribute("width","1ex"); + newFrag.appendChild(node); + } + newFrag.appendChild( + AMcreateMmlNode(symbol.tag,document.createTextNode(st))); + if (st.charAt(st.length-1) == " ") { + node = AMcreateElementMathML("mspace"); + node.setAttribute("width","1ex"); + newFrag.appendChild(node); + } + str = AMremoveCharsAndBlanks(str,i+1); + return [AMcreateMmlNode("mrow",newFrag),str]; + case UNARY: + str = AMremoveCharsAndBlanks(str,symbol.input.length); + result = AMparseSexpr(str); + if (result[0]==null) return [AMcreateMmlNode(symbol.tag, + document.createTextNode(symbol.output)),str]; + if (typeof symbol.func == "boolean" && symbol.func) { // functions hack + st = str.charAt(0); + if (st=="^" || st=="_" || st=="/" || st=="|" || st==",") { + return [AMcreateMmlNode(symbol.tag, + document.createTextNode(symbol.output)),str]; + } else { + node = AMcreateMmlNode("mrow", + AMcreateMmlNode(symbol.tag,document.createTextNode(symbol.output))); + node.appendChild(result[0]); + return [node,result[1]]; + } + } + AMremoveBrackets(result[0]); + if (symbol.input == "sqrt") { // sqrt + return [AMcreateMmlNode(symbol.tag,result[0]),result[1]]; + } else if (typeof symbol.acc == "boolean" && symbol.acc) { // accent + node = AMcreateMmlNode(symbol.tag,result[0]); + node.appendChild(AMcreateMmlNode("mo",document.createTextNode(symbol.output))); + return [node,result[1]]; + } else { // font change command + if (!isIE && typeof symbol.codes != "undefined") { + for (i=0; i<result[0].childNodes.length; i++) + if (result[0].childNodes[i].nodeName=="mi" || result[0].nodeName=="mi") { + st = (result[0].nodeName=="mi"?result[0].firstChild.nodeValue: + result[0].childNodes[i].firstChild.nodeValue); + var newst = []; + for (var j=0; j<st.length; j++) + if (st.charCodeAt(j)>64 && st.charCodeAt(j)<91) newst = newst + + String.fromCharCode(symbol.codes[st.charCodeAt(j)-65]); + else newst = newst + st.charAt(j); + if (result[0].nodeName=="mi") + result[0]=AMcreateElementMathML("mo"). + appendChild(document.createTextNode(newst)); + else result[0].replaceChild(AMcreateElementMathML("mo"). + appendChild(document.createTextNode(newst)),result[0].childNodes[i]); + } + } + node = AMcreateMmlNode(symbol.tag,result[0]); + node.setAttribute(symbol.atname,symbol.atval); + return [node,result[1]]; + } + case BINARY: + str = AMremoveCharsAndBlanks(str,symbol.input.length); + result = AMparseSexpr(str); + if (result[0]==null) return [AMcreateMmlNode("mo", + document.createTextNode(symbol.input)),str]; + AMremoveBrackets(result[0]); + var result2 = AMparseSexpr(result[1]); + if (result2[0]==null) return [AMcreateMmlNode("mo", + document.createTextNode(symbol.input)),str]; + AMremoveBrackets(result2[0]); + if (symbol.input=="root" || symbol.input=="stackrel") + newFrag.appendChild(result2[0]); + newFrag.appendChild(result[0]); + if (symbol.input=="frac") newFrag.appendChild(result2[0]); + return [AMcreateMmlNode(symbol.tag,newFrag),result2[1]]; + case INFIX: + str = AMremoveCharsAndBlanks(str,symbol.input.length); + return [AMcreateMmlNode("mo",document.createTextNode(symbol.output)),str]; + case SPACE: + str = AMremoveCharsAndBlanks(str,symbol.input.length); + node = AMcreateElementMathML("mspace"); + node.setAttribute("width","1ex"); + newFrag.appendChild(node); + newFrag.appendChild( + AMcreateMmlNode(symbol.tag,document.createTextNode(symbol.output))); + node = AMcreateElementMathML("mspace"); + node.setAttribute("width","1ex"); + newFrag.appendChild(node); + return [AMcreateMmlNode("mrow",newFrag),str]; + case LEFTRIGHT: +// if (rightvert) return [null,str]; else rightvert = true; + AMnestingDepth++; + str = AMremoveCharsAndBlanks(str,symbol.input.length); + result = AMparseExpr(str,false); + AMnestingDepth--; + var st = ""; + if (result[0].lastChild!=null) + st = result[0].lastChild.firstChild.nodeValue; + if (st == "|") { // its an absolute value subterm + node = AMcreateMmlNode("mo",document.createTextNode(symbol.output)); + node = AMcreateMmlNode("mrow",node); + node.appendChild(result[0]); + return [node,result[1]]; + } else { // the "|" is a \mid + node = AMcreateMmlNode("mo",document.createTextNode(symbol.output)); + node = AMcreateMmlNode("mrow",node); + return [node,str]; + } + default: +//alert("default"); + str = AMremoveCharsAndBlanks(str,symbol.input.length); + return [AMcreateMmlNode(symbol.tag, //its a constant + document.createTextNode(symbol.output)),str]; + } +} + +function AMparseIexpr(str) { + var symbol, sym1, sym2, node, result, underover; + str = AMremoveCharsAndBlanks(str,0); + sym1 = AMgetSymbol(str); + result = AMparseSexpr(str); + node = result[0]; + str = result[1]; + symbol = AMgetSymbol(str); + if (symbol.ttype == INFIX && symbol.input != "/") { + str = AMremoveCharsAndBlanks(str,symbol.input.length); +// if (symbol.input == "/") result = AMparseIexpr(str); else ... + result = AMparseSexpr(str); + if (result[0] == null) // show box in place of missing argument + result[0] = AMcreateMmlNode("mo",document.createTextNode("\u25A1")); + else AMremoveBrackets(result[0]); + str = result[1]; +// if (symbol.input == "/") AMremoveBrackets(node); + if (symbol.input == "_") { + sym2 = AMgetSymbol(str); + underover = (sym1.ttype == UNDEROVER); + if (sym2.input == "^") { + str = AMremoveCharsAndBlanks(str,sym2.input.length); + var res2 = AMparseSexpr(str); + AMremoveBrackets(res2[0]); + str = res2[1]; + node = AMcreateMmlNode((underover?"munderover":"msubsup"),node); + node.appendChild(result[0]); + node.appendChild(res2[0]); + node = AMcreateMmlNode("mrow",node); // so sum does not stretch + } else { + node = AMcreateMmlNode((underover?"munder":"msub"),node); + node.appendChild(result[0]); + } + } else { + node = AMcreateMmlNode(symbol.tag,node); + node.appendChild(result[0]); + } + } + return [node,str]; +} + +function AMparseExpr(str,rightbracket) { + var symbol, node, result, i, nodeList = [], + newFrag = document.createDocumentFragment(); + do { + str = AMremoveCharsAndBlanks(str,0); + result = AMparseIexpr(str); + node = result[0]; + str = result[1]; + symbol = AMgetSymbol(str); + if (symbol.ttype == INFIX && symbol.input == "/") { + str = AMremoveCharsAndBlanks(str,symbol.input.length); + result = AMparseIexpr(str); + if (result[0] == null) // show box in place of missing argument + result[0] = AMcreateMmlNode("mo",document.createTextNode("\u25A1")); + else AMremoveBrackets(result[0]); + str = result[1]; + AMremoveBrackets(node); + node = AMcreateMmlNode(symbol.tag,node); + node.appendChild(result[0]); + newFrag.appendChild(node); + symbol = AMgetSymbol(str); + } + else if (node!=undefined) newFrag.appendChild(node); + } while ((symbol.ttype != RIGHTBRACKET && + (symbol.ttype != LEFTRIGHT || rightbracket) + || AMnestingDepth == 0) && symbol!=null && symbol.output!=""); + if (symbol.ttype == RIGHTBRACKET || symbol.ttype == LEFTRIGHT) { +// if (AMnestingDepth > 0) AMnestingDepth--; + var len = newFrag.childNodes.length; + if (len>0 && newFrag.childNodes[len-1].nodeName == "mrow" && len>1 && + newFrag.childNodes[len-2].nodeName == "mo" && + newFrag.childNodes[len-2].firstChild.nodeValue == ",") { //matrix + var right = newFrag.childNodes[len-1].lastChild.firstChild.nodeValue; + if (right==")" || right=="]") { + var left = newFrag.childNodes[len-1].firstChild.firstChild.nodeValue; + if (left=="(" && right==")" && symbol.output != "}" || + left=="[" && right=="]") { + var pos = []; // positions of commas + var matrix = true; + var m = newFrag.childNodes.length; + for (i=0; matrix && i<m; i=i+2) { + pos[i] = []; + node = newFrag.childNodes[i]; + if (matrix) matrix = node.nodeName=="mrow" && + (i==m-1 || node.nextSibling.nodeName=="mo" && + node.nextSibling.firstChild.nodeValue==",")&& + node.firstChild.firstChild.nodeValue==left && + node.lastChild.firstChild.nodeValue==right; + if (matrix) + for (var j=0; j<node.childNodes.length; j++) + if (node.childNodes[j].firstChild.nodeValue==",") + pos[i][pos[i].length]=j; + if (matrix && i>1) matrix = pos[i].length == pos[i-2].length; + } + if (matrix) { + var row, frag, n, k, table = document.createDocumentFragment(); + for (i=0; i<m; i=i+2) { + row = document.createDocumentFragment(); + frag = document.createDocumentFragment(); + node = newFrag.firstChild; // <mrow>(-,-,...,-,-)</mrow> + n = node.childNodes.length; + k = 0; + node.removeChild(node.firstChild); //remove ( + for (j=1; j<n-1; j++) { + if (typeof pos[i][k] != "undefined" && j==pos[i][k]){ + node.removeChild(node.firstChild); //remove , + row.appendChild(AMcreateMmlNode("mtd",frag)); + k++; + } else frag.appendChild(node.firstChild); + } + row.appendChild(AMcreateMmlNode("mtd",frag)); + if (newFrag.childNodes.length>2) { + newFrag.removeChild(newFrag.firstChild); //remove <mrow>)</mrow> + newFrag.removeChild(newFrag.firstChild); //remove <mo>,</mo> + } + table.appendChild(AMcreateMmlNode("mtr",row)); + } + node = AMcreateMmlNode("mtable",table); + if (typeof symbol.invisible == "boolean" && symbol.invisible) node.setAttribute("columnalign","left"); + newFrag.replaceChild(node,newFrag.firstChild); + } + } + } + } + str = AMremoveCharsAndBlanks(str,symbol.input.length); + if (typeof symbol.invisible != "boolean" || !symbol.invisible) { + node = AMcreateMmlNode("mo",document.createTextNode(symbol.output)); + newFrag.appendChild(node); + } + } + return [newFrag,str]; +} + +function AMparseMath(str) { + var result, node = AMcreateElementMathML("mstyle"); + if (mathcolor != "") node.setAttribute("mathcolor",mathcolor); + if (displaystyle) node.setAttribute("displaystyle","true"); + if (mathfontfamily != "") node.setAttribute("fontfamily",mathfontfamily); + AMnestingDepth = 0; + node.appendChild(AMparseExpr(str.replace(/^\s+/g,""),false)[0]); + node = AMcreateMmlNode("math",node); + if (showasciiformulaonhover) //fixed by djhsu so newline + node.setAttribute("title",str.replace(/\s+/g," "));//does not show in Gecko + if (mathfontfamily != "" && (isIE || mathfontfamily != "serif")) { + var fnode = AMcreateElementXHTML("font"); + fnode.setAttribute("face",mathfontfamily); + fnode.appendChild(node); + return fnode; + } + return node; +} + +function AMstrarr2docFrag(arr, linebreaks) { + var newFrag=document.createDocumentFragment(); + var expr = false; + for (var i=0; i<arr.length; i++) { + if (expr) newFrag.appendChild(AMparseMath(arr[i])); + else { + var arri = (linebreaks ? arr[i].split("\n\n") : [arr[i]]); + newFrag.appendChild(AMcreateElementXHTML("span"). + appendChild(document.createTextNode(arri[0]))); + for (var j=1; j<arri.length; j++) { + newFrag.appendChild(AMcreateElementXHTML("p")); + newFrag.appendChild(AMcreateElementXHTML("span"). + appendChild(document.createTextNode(arri[j]))); + } + } + expr = !expr; + } + return newFrag; +} + +function AMprocessNodeR(n, linebreaks) { + var mtch, str, arr, frg, i; + if (n.childNodes.length == 0) { + if ((n.nodeType!=8 || linebreaks) && + n.parentNode.nodeName!="form" && n.parentNode.nodeName!="FORM" && + n.parentNode.nodeName!="textarea" && n.parentNode.nodeName!="TEXTAREA" && + n.parentNode.nodeName!="code" && n.parentNode.nodeName!="CODE" && /* added by JM */ + n.parentNode.nodeName!="pre" && n.parentNode.nodeName!="PRE") { + str = n.nodeValue; + if (!(str == null)) { + str = str.replace(/\r\n\r\n/g,"\n\n"); + if (doubleblankmathdelimiter) { + str = str.replace(/\x20\x20\./g," "+AMdelimiter1+"."); + str = str.replace(/\x20\x20,/g," "+AMdelimiter1+","); + str = str.replace(/\x20\x20/g," "+AMdelimiter1+" "); + } + str = str.replace(/\x20+/g," "); + str = str.replace(/\s*\r\n/g," "); + mtch = false; + str = str.replace(new RegExp(AMescape2, "g"), + function(st){mtch=true;return "AMescape2"}); + str = str.replace(new RegExp(AMescape1, "g"), + function(st){mtch=true;return "AMescape1"}); + str = str.replace(new RegExp(AMdelimiter2regexp, "g"),AMdelimiter1); + arr = str.split(AMdelimiter1); + for (i=0; i<arr.length; i++) + arr[i]=arr[i].replace(/AMescape2/g,AMdelimiter2). + replace(/AMescape1/g,AMdelimiter1); + if (arr.length>1 || mtch) { + if (checkForMathML) { + checkForMathML = false; + var nd = AMisMathMLavailable(); + AMnoMathML = nd != null; + if (AMnoMathML && notifyIfNoMathML) + if (alertIfNoMathML) + alert("To view the ASCIIMathML notation use Internet Explorer 6 +\nMathPlayer (free from www.dessci.com)\n\ + or Firefox/Mozilla/Netscape"); + else AMbody.insertBefore(nd,AMbody.childNodes[0]); + } + if (!AMnoMathML) { + frg = AMstrarr2docFrag(arr,n.nodeType==8); + var len = frg.childNodes.length; + n.parentNode.replaceChild(frg,n); + return len-1; + } else return 0; + } + } + } else return 0; + } else if (n.nodeName!="math") { + for (i=0; i<n.childNodes.length; i++) + i += AMprocessNodeR(n.childNodes[i], linebreaks); + } + return 0; +} + +function AMprocessNode(n, linebreaks, spanclassAM) { + var frag,st; + if (spanclassAM!=null) { + frag = document.getElementsByTagName("span") + for (var i=0;i<frag.length;i++) + if (frag[i].className == "AM") + AMprocessNodeR(frag[i],linebreaks); + } else { + try { + st = n.innerHTML; + } catch(err) {} + if (st==null || + st.indexOf(AMdelimiter1)!=-1 || st.indexOf(AMdelimiter2)!=-1) + AMprocessNodeR(n,linebreaks); + } + if (isIE) { //needed to match size and font of formula to surrounding text + frag = document.getElementsByTagName('math'); + for (var i=0;i<frag.length;i++) frag[i].update() + } +} + +var AMbody; +var AMnoMathML = false, AMtranslated = false; + +function translate(spanclassAM) { + if (!AMtranslated) { // run this only once + AMtranslated = true; + AMinitSymbols(); + AMbody = document.getElementsByTagName("body")[0]; + AMprocessNode(AMbody, false, spanclassAM); + } +} + +if (isIE) { // avoid adding MathPlayer info explicitly to each webpage + document.write("<object id=\"mathplayer\"\ + classid=\"clsid:32F66A20-7614-11D4-BD11-00104BD3F987\"></object>"); + document.write("<?import namespace=\"m\" implementation=\"#mathplayer\"?>"); +} + +// GO1.1 Generic onload by Brothercake +// http://www.brothercake.com/ +//onload function (replaces the onload="translate()" in the <body> tag) +function generic() +{ + translate(); +}; +//setup onload function +if(typeof window.addEventListener != 'undefined') +{ + //.. gecko, safari, konqueror and standard + window.addEventListener('load', generic, false); +} +else if(typeof document.addEventListener != 'undefined') +{ + //.. opera 7 + document.addEventListener('load', generic, false); +} +else if(typeof window.attachEvent != 'undefined') +{ + //.. win/ie + window.attachEvent('onload', generic); +} +//** remove this condition to degrade older browsers +else +{ + //.. mac/ie5 and anything else that gets this far + //if there's an existing onload function + if(typeof window.onload == 'function') + { + //store it + var existing = onload; + //add new onload handler + window.onload = function() + { + //call existing onload function + existing(); + //call generic onload function + generic(); + }; + } + else + { + //setup onload function + window.onload = generic; + } +} diff --git a/src/Main.hs b/src/Main.hs new file mode 100644 index 000000000..ff42be094 --- /dev/null +++ b/src/Main.hs @@ -0,0 +1,298 @@ +-- | Main Pandoc program. Parses command-line options and calls the +-- appropriate readers and writers. +module Main where +import Text.Pandoc.UTF8 ( decodeUTF8, encodeUTF8 ) +import Text.Pandoc.Readers.Markdown ( readMarkdown ) +import Text.Pandoc.Readers.HTML ( readHtml ) +import Text.Pandoc.Writers.S5 ( s5CSS, s5Javascript, writeS5 ) +import Text.Pandoc.Writers.RST ( writeRST ) +import Text.Pandoc.Readers.RST ( readRST ) +import Text.Pandoc.ASCIIMathML ( asciiMathMLScript ) +import Text.Pandoc.Writers.HTML ( writeHtml ) +import Text.Pandoc.Writers.LaTeX ( writeLaTeX ) +import Text.Pandoc.Readers.LaTeX ( readLaTeX ) +import Text.Pandoc.Writers.RTF ( writeRTF ) +import Text.Pandoc.Writers.Markdown ( writeMarkdown ) +import Text.Pandoc.Writers.DefaultHeaders ( defaultHtmlHeader, defaultRTFHeader, defaultS5Header, defaultLaTeXHeader ) +import Text.Pandoc.Definition +import Text.Pandoc.Shared +import System ( exitWith, getArgs, getProgName ) +import System.Exit +import System.Console.GetOpt +import IO ( stdout, stderr, hPutStrLn ) +import Data.Maybe ( fromMaybe ) +import Data.List ( isPrefixOf ) +import Char ( toLower ) +import Control.Monad ( (>>=) ) + +version :: String +version = "0.2" + +-- | Association list of formats and readers. +readers :: [(String, ParserState -> String -> Pandoc)] +readers = [("native" , readPandoc) + ,("markdown" , readMarkdown) + ,("rst" , readRST) + ,("html" , readHtml) + ,("latex" , readLaTeX) + ] + +-- | Reader for native Pandoc format. +readPandoc :: ParserState -> String -> Pandoc +readPandoc state input = read input + +-- | Association list of formats and pairs of writers and default headers. +writers :: [ ( String, ( WriterOptions -> Pandoc -> String, String ) ) ] +writers = [("native" , (writeDoc, "")) + ,("html" , (writeHtml, defaultHtmlHeader)) + ,("s5" , (writeS5, defaultS5Header)) + ,("latex" , (writeLaTeX, defaultLaTeXHeader)) + ,("markdown" , (writeMarkdown, "")) + ,("rst" , (writeRST, "")) + ,("rtf" , (writeRTF, defaultRTFHeader)) + ] + +-- | Writer for Pandoc native format. +writeDoc :: WriterOptions -> Pandoc -> String +writeDoc options = prettyPandoc + +-- | Data structure for command line options. +data Opt = Opt + { optPreserveTabs :: Bool -- ^ If @False@, convert tabs to spaces + , optTabStop :: Int -- ^ Number of spaces per tab + , optStandalone :: Bool -- ^ If @True@, include header and footer + , optReader :: ParserState -> String -> Pandoc -- ^ Reader to use + , optWriter :: WriterOptions -> Pandoc -> String -- ^ Writer to use + , optParseRaw :: Bool -- ^ If @True@, parse unconvertable HTML and TeX + , optCSS :: String -- ^ CSS file to link to + , optIncludeInHeader :: String -- ^ File to include in header + , optIncludeBeforeBody :: String -- ^ File to include at beginning of body + , optIncludeAfterBody :: String -- ^ File to include at end of body + , optCustomHeader :: String -- ^ Custom header to use, or "DEFAULT" + , optDefaultHeader :: String -- ^ Default header + , optTitlePrefix :: String -- ^ Optional prefix for HTML title + , optNumberSections :: Bool -- ^ If @True@, number sections in LaTeX + , optIncremental :: Bool -- ^ If @True@, show lists incrementally in S5 + , optSmartypants :: Bool -- ^ If @True@, use smart quotes, dashes, ... + , optASCIIMathML :: Bool -- ^ If @True@, use ASCIIMathML in HTML or S5 + } + +-- | Defaults for command-line options. +startOpt :: Opt +startOpt = Opt + { optPreserveTabs = False + , optTabStop = 4 + , optStandalone = False + , optReader = readMarkdown + , optWriter = writeHtml + , optParseRaw = False + , optCSS = "" + , optIncludeInHeader = "" + , optIncludeBeforeBody = "" + , optIncludeAfterBody = "" + , optCustomHeader = "DEFAULT" + , optDefaultHeader = defaultHtmlHeader + , optTitlePrefix = "" + , optNumberSections = False + , optIncremental = False + , optSmartypants = False + , optASCIIMathML = False + } + +-- | A list of functions, each transforming the options data structure in response +-- to a command-line option. +options :: [OptDescr (Opt -> IO Opt)] +options = + [ Option "v" ["version"] + (NoArg + (\_ -> do + hPutStrLn stderr ("Version " ++ version) + exitWith ExitSuccess)) + "Print version" + + , Option "h" ["help"] + (NoArg + (\_ -> do + prg <- getProgName + hPutStrLn stderr (usageInfo (prg ++ " [OPTIONS] [FILES] - convert FILES from one markup format to another\nIf no OPTIONS specified, converts from markdown to html.\nIf no FILES specified, input is read from STDIN.\nOptions:") options) + exitWith ExitSuccess)) + "Show help" + + , Option "fr" ["from","read"] + (ReqArg + (\arg opt -> case (lookup (map toLower arg) readers) of + Just reader -> return opt { optReader = reader } + Nothing -> error ("Unknown reader: " ++ arg) ) + "FORMAT") + ("Source format (" ++ (concatMap (\(name, fn) -> " " ++ name) readers) ++ " )") + + , Option "tw" ["to","write"] + (ReqArg + (\arg opt -> case (lookup (map toLower arg) writers) of + Just (writer, defaultHeader) -> + return opt { optWriter = writer, + optDefaultHeader = defaultHeader } + Nothing -> error ("Unknown writer: " ++ arg) ) + "FORMAT") + ("Output format (" ++ (concatMap (\(name, fn) -> " " ++ name) writers) ++ " )") + + , Option "s" ["standalone"] + (NoArg + (\opt -> return opt { optStandalone = True })) + "Include needed header and footer on output" + + , Option "p" ["preserve-tabs"] + (NoArg + (\opt -> return opt { optPreserveTabs = True })) + "Preserve tabs instead of converting to spaces" + + , Option "" ["tab-stop"] + (ReqArg + (\arg opt -> return opt { optTabStop = (read arg) } ) + "TABSTOP") + "Tab stop (default 4)" + + , Option "R" ["parse-raw"] + (NoArg + (\opt -> return opt { optParseRaw = True })) + "Parse untranslatable HTML codes and LaTeX environments as raw" + + , Option "S" ["smartypants"] + (NoArg + (\opt -> return opt { optSmartypants = True })) + "Use smartypants for html output" + + , Option "m" ["asciimathml"] + (NoArg + (\opt -> return opt { optASCIIMathML = True, optStandalone = True })) + "Use ASCIIMathML script in html output" + + , Option "i" ["incremental"] + (NoArg + (\opt -> return opt { optIncremental = True })) + "Make list items display incrementally in S5" + + , Option "N" ["number-sections"] + (NoArg + (\opt -> return opt { optNumberSections = True })) + "Number sections in LaTeX" + + , Option "c" ["css"] + (ReqArg + (\arg opt -> return opt { optCSS = arg, optStandalone = True }) + "CSS") + "Link to CSS style sheet" + + , Option "H" ["include-in-header"] + (ReqArg + (\arg opt -> do + text <- readFile arg + return opt { optIncludeInHeader = text, optStandalone = True }) + "FILENAME") + "File to include at end of header (implies -s)" + + , Option "B" ["include-before-body"] + (ReqArg + (\arg opt -> do + text <- readFile arg + return opt { optIncludeBeforeBody = text }) + "FILENAME") + "File to include before document body" + + , Option "A" ["include-after-body"] + (ReqArg + (\arg opt -> do + text <- readFile arg + return opt { optIncludeAfterBody = text }) + "FILENAME") + "File to include after document body" + + , Option "" ["custom-header"] + (ReqArg + (\arg opt -> do + text <- readFile arg + return opt { optCustomHeader = text, optStandalone = True }) + "FILENAME") + "File to use for custom header (implies -s)" + + , Option "T" ["title-prefix"] + (ReqArg + (\arg opt -> return opt { optTitlePrefix = arg, optStandalone = True }) + "STRING") + "String to prefix to HTML window title" + + , Option "D" ["print-default-header"] + (ReqArg + (\arg opt -> do + let header = case (lookup arg writers) of + Just (writer, head) -> head + Nothing -> error ("Unknown reader: " ++ arg) + hPutStrLn stdout header + exitWith ExitSuccess) + "FORMAT") + "Print default header for FORMAT" + ] +main = do + + args <- getArgs + let (actions, sources, errors) = getOpt RequireOrder options args + + -- thread option data structure through all supplied option actions + opts <- foldl (>>=) (return startOpt) actions + + let Opt { optPreserveTabs = preserveTabs + , optTabStop = tabStop + , optStandalone = standalone + , optReader = reader + , optWriter = writer + , optParseRaw = parseRaw + , optCSS = css + , optIncludeInHeader = includeHeader + , optIncludeBeforeBody = includeBefore + , optIncludeAfterBody = includeAfter + , optCustomHeader = customHeader + , optDefaultHeader = defaultHeader + , optTitlePrefix = titlePrefix + , optNumberSections = numberSections + , optIncremental = incremental + , optSmartypants = smartypants + , optASCIIMathML = asciiMathML + } = opts + + let writingS5 = (defaultHeader == defaultS5Header) + let tabFilter = if preserveTabs then id else (tabsToSpaces tabStop) + let addBlank str = str ++ "\n\n" + let removeCRs str = filter (/= '\r') str -- remove DOS-style line endings + let filter = tabFilter . addBlank . removeCRs + let startParserState = defaultParserState { stateParseRaw = parseRaw, + stateTabStop = tabStop, + stateStandalone = standalone } + let csslink = if (css == "") then + "" + else + "<link rel=\"stylesheet\" href=\"" ++ css ++ + "\" type=\"text/css\" media=\"all\" />\n" + let asciiMathMLLink = if asciiMathML then asciiMathMLScript else "" + let header = (if (customHeader == "DEFAULT") then defaultHeader else customHeader) ++ + csslink ++ asciiMathMLLink ++ includeHeader + let writerOptions = WriterOptions { writerStandalone = standalone, + writerHeader = header, + writerTitlePrefix = titlePrefix, + writerSmartypants = smartypants, + writerTabStop = tabStop, + writerS5 = writingS5, + writerIncremental = incremental, + writerNumberSections = numberSections, + writerIncludeBefore = includeBefore, + writerIncludeAfter = includeAfter } + + (readSources sources) >>= (putStrLn . encodeUTF8 . (writer writerOptions) . + (reader startParserState) . filter . + decodeUTF8 . (joinWithSep "\n")) + + where + readSources [] = mapM readSource ["-"] + readSources sources = mapM readSource sources + readSource "-" = getContents + readSource source = readFile source + diff --git a/src/Text/Pandoc/ASCIIMathML.hs b/src/Text/Pandoc/ASCIIMathML.hs new file mode 100644 index 000000000..85d7c46b9 --- /dev/null +++ b/src/Text/Pandoc/ASCIIMathML.hs @@ -0,0 +1,14 @@ +---------------------------------------------------- +-- Do not edit this file by hand. Edit +-- 'templates/ASCIIMathML.hs' +-- and run ./fillTemplates.pl Text/Pandoc/ASCIIMathML.hs +---------------------------------------------------- + +-- | Definitions for use of Pandoc.ASCIIMathML in HTML. +-- (See <http://www1.chapman.edu/~jipsen/mathml/asciimath.html>.) +module Text.Pandoc.ASCIIMathML ( asciiMathMLScript ) where + +-- | String containing Pandoc.ASCIIMathML javascript. +asciiMathMLScript :: String +asciiMathMLScript = "<script type=\"text/javascript\">\n/* ASCIIMathML.js - copyright Peter Jipsen, released under the GPL\nSee http://www1.chapman.edu/~jipsen/mathml/asciimath.html/ */\n\nvar checkForMathML = true; // check if browser can display MathML\nvar notifyIfNoMathML = true; // display note if no MathML capability\nvar alertIfNoMathML = false; // show alert box if no MathML capability\nvar mathcolor = \"red\"; // change it to \"\" (to inherit) or any other color\nvar mathfontfamily = \"serif\"; // change to \"\" to inherit (works in IE) \n // or another family (e.g. \"arial\")\nvar displaystyle = true; // puts limits above and below large operators\nvar showasciiformulaonhover = true; // helps students learn ASCIIMath\nvar decimalsign = \".\"; // change to \",\" if you like, beware of `(1,2)`!\nvar AMdelimiter1 = \"`\", AMescape1 = \"\\\\\\\\`\"; // can use other characters\nvar AMdelimiter2 = \"$\", AMescape2 = \"\\\\\\\\\\\\$\", AMdelimiter2regexp = \"\\\\$\";\nvar doubleblankmathdelimiter = false; // if true, x+1 is equal to `x+1`\n // for IE this works only in <!-- -->\n//var separatetokens;// has been removed (email me if this is a problem)\nvar isIE = document.createElementNS==null;\n\nif (document.getElementById==null) \n alert(\"This webpage requires a recent browser such as\\\n\\nMozilla/Netscape 7+ or Internet Explorer 6+MathPlayer\")\n\n// all further global variables start with \"AM\"\n\nfunction AMcreateElementXHTML(t) {\n if (isIE) return document.createElement(t);\n else return document.createElementNS(\"http://www.w3.org/1999/xhtml\",t);\n}\n\nfunction AMnoMathMLNote() {\n var nd = AMcreateElementXHTML(\"h3\");\n nd.setAttribute(\"align\",\"center\")\n nd.appendChild(AMcreateElementXHTML(\"p\"));\n nd.appendChild(document.createTextNode(\"To view the \"));\n var an = AMcreateElementXHTML(\"a\");\n an.appendChild(document.createTextNode(\"ASCIIMathML\"));\n an.setAttribute(\"href\",\"http://www.chapman.edu/~jipsen/asciimath.html\");\n nd.appendChild(an);\n nd.appendChild(document.createTextNode(\" notation use Internet Explorer 6+\")); \n an = AMcreateElementXHTML(\"a\");\n an.appendChild(document.createTextNode(\"MathPlayer\"));\n an.setAttribute(\"href\",\"http://www.dessci.com/en/products/mathplayer/download.htm\");\n nd.appendChild(an);\n nd.appendChild(document.createTextNode(\" or Netscape/Mozilla/Firefox\"));\n nd.appendChild(AMcreateElementXHTML(\"p\"));\n return nd;\n}\n\nfunction AMisMathMLavailable() {\n var regex = /KHTML/; /* ASCIIMathML.js - copyright Peter Jipsen, released under the GPL\nSee http://www1.chapman.edu/~jipsen/mathml/asciimath.html/ */\n if (navigator.appName.slice(0,8)==\"Netscape\")\n if (navigator.appVersion.slice(0,1)>=\"5\" && !regex.test(navigator.userAgent)) return null;\n else return AMnoMathMLNote();\n else if (navigator.appName.slice(0,9)==\"Microsoft\")\n try {\n var ActiveX = new ActiveXObject(\"MathPlayer.Factory.1\");\n return null;\n } catch (e) {\n return AMnoMathMLNote();\n }\n else return AMnoMathMLNote();\n}\n\n// character lists for Mozilla/Netscape fonts\nvar AMcal = [0xEF35,0x212C,0xEF36,0xEF37,0x2130,0x2131,0xEF38,0x210B,0x2110,0xEF39,0xEF3A,0x2112,0x2133,0xEF3B,0xEF3C,0xEF3D,0xEF3E,0x211B,0xEF3F,0xEF40,0xEF41,0xEF42,0xEF43,0xEF44,0xEF45,0xEF46];\nvar AMfrk = [0xEF5D,0xEF5E,0x212D,0xEF5F,0xEF60,0xEF61,0xEF62,0x210C,0x2111,0xEF63,0xEF64,0xEF65,0xEF66,0xEF67,0xEF68,0xEF69,0xEF6A,0x211C,0xEF6B,0xEF6C,0xEF6D,0xEF6E,0xEF6F,0xEF70,0xEF71,0x2128];\nvar AMbbb = [0xEF8C,0xEF8D,0x2102,0xEF8E,0xEF8F,0xEF90,0xEF91,0x210D,0xEF92,0xEF93,0xEF94,0xEF95,0xEF96,0x2115,0xEF97,0x2119,0x211A,0x211D,0xEF98,0xEF99,0xEF9A,0xEF9B,0xEF9C,0xEF9D,0xEF9E,0x2124];\n\nvar CONST = 0, UNARY = 1, BINARY = 2, INFIX = 3, LEFTBRACKET = 4, \n RIGHTBRACKET = 5, SPACE = 6, UNDEROVER = 7, DEFINITION = 8,\n LEFTRIGHT = 9, TEXT = 10; // token types\n\nvar AMsqrt = {input:\"sqrt\", tag:\"msqrt\", output:\"sqrt\", tex:null, ttype:UNARY},\n AMroot = {input:\"root\", tag:\"mroot\", output:\"root\", tex:null, ttype:BINARY},\n AMfrac = {input:\"frac\", tag:\"mfrac\", output:\"/\", tex:null, ttype:BINARY},\n AMdiv = {input:\"/\", tag:\"mfrac\", output:\"/\", tex:null, ttype:INFIX},\n AMover = {input:\"stackrel\", tag:\"mover\", output:\"stackrel\", tex:null, ttype:BINARY},\n AMsub = {input:\"_\", tag:\"msub\", output:\"_\", tex:null, ttype:INFIX},\n AMsup = {input:\"^\", tag:\"msup\", output:\"^\", tex:null, ttype:INFIX},\n AMtext = {input:\"text\", tag:\"mtext\", output:\"text\", tex:null, ttype:TEXT},\n AMmbox = {input:\"mbox\", tag:\"mtext\", output:\"mbox\", tex:null, ttype:TEXT},\n AMquote = {input:\"\\\"\", tag:\"mtext\", output:\"mbox\", tex:null, ttype:TEXT};\n\nvar AMsymbols = [\n//some greek symbols\n{input:\"alpha\", tag:\"mi\", output:\"\\u03B1\", tex:null, ttype:CONST},\n{input:\"beta\", tag:\"mi\", output:\"\\u03B2\", tex:null, ttype:CONST},\n{input:\"chi\", tag:\"mi\", output:\"\\u03C7\", tex:null, ttype:CONST},\n{input:\"delta\", tag:\"mi\", output:\"\\u03B4\", tex:null, ttype:CONST},\n{input:\"Delta\", tag:\"mo\", output:\"\\u0394\", tex:null, ttype:CONST},\n{input:\"epsi\", tag:\"mi\", output:\"\\u03B5\", tex:\"epsilon\", ttype:CONST},\n{input:\"varepsilon\", tag:\"mi\", output:\"\\u025B\", tex:null, ttype:CONST},\n{input:\"eta\", tag:\"mi\", output:\"\\u03B7\", tex:null, ttype:CONST},\n{input:\"gamma\", tag:\"mi\", output:\"\\u03B3\", tex:null, ttype:CONST},\n{input:\"Gamma\", tag:\"mo\", output:\"\\u0393\", tex:null, ttype:CONST},\n{input:\"iota\", tag:\"mi\", output:\"\\u03B9\", tex:null, ttype:CONST},\n{input:\"kappa\", tag:\"mi\", output:\"\\u03BA\", tex:null, ttype:CONST},\n{input:\"lambda\", tag:\"mi\", output:\"\\u03BB\", tex:null, ttype:CONST},\n{input:\"Lambda\", tag:\"mo\", output:\"\\u039B\", tex:null, ttype:CONST},\n{input:\"mu\", tag:\"mi\", output:\"\\u03BC\", tex:null, ttype:CONST},\n{input:\"nu\", tag:\"mi\", output:\"\\u03BD\", tex:null, ttype:CONST},\n{input:\"omega\", tag:\"mi\", output:\"\\u03C9\", tex:null, ttype:CONST},\n{input:\"Omega\", tag:\"mo\", output:\"\\u03A9\", tex:null, ttype:CONST},\n{input:\"phi\", tag:\"mi\", output:\"\\u03C6\", tex:null, ttype:CONST},\n{input:\"varphi\", tag:\"mi\", output:\"\\u03D5\", tex:null, ttype:CONST},\n{input:\"Phi\", tag:\"mo\", output:\"\\u03A6\", tex:null, ttype:CONST},\n{input:\"pi\", tag:\"mi\", output:\"\\u03C0\", tex:null, ttype:CONST},\n{input:\"Pi\", tag:\"mo\", output:\"\\u03A0\", tex:null, ttype:CONST},\n{input:\"psi\", tag:\"mi\", output:\"\\u03C8\", tex:null, ttype:CONST},\n{input:\"Psi\", tag:\"mi\", output:\"\\u03A8\", tex:null, ttype:CONST},\n{input:\"rho\", tag:\"mi\", output:\"\\u03C1\", tex:null, ttype:CONST},\n{input:\"sigma\", tag:\"mi\", output:\"\\u03C3\", tex:null, ttype:CONST},\n{input:\"Sigma\", tag:\"mo\", output:\"\\u03A3\", tex:null, ttype:CONST},\n{input:\"tau\", tag:\"mi\", output:\"\\u03C4\", tex:null, ttype:CONST},\n{input:\"theta\", tag:\"mi\", output:\"\\u03B8\", tex:null, ttype:CONST},\n{input:\"vartheta\", tag:\"mi\", output:\"\\u03D1\", tex:null, ttype:CONST},\n{input:\"Theta\", tag:\"mo\", output:\"\\u0398\", tex:null, ttype:CONST},\n{input:\"upsilon\", tag:\"mi\", output:\"\\u03C5\", tex:null, ttype:CONST},\n{input:\"xi\", tag:\"mi\", output:\"\\u03BE\", tex:null, ttype:CONST},\n{input:\"Xi\", tag:\"mo\", output:\"\\u039E\", tex:null, ttype:CONST},\n{input:\"zeta\", tag:\"mi\", output:\"\\u03B6\", tex:null, ttype:CONST},\n\n//binary operation symbols\n{input:\"*\", tag:\"mo\", output:\"\\u22C5\", tex:\"cdot\", ttype:CONST},\n{input:\"**\", tag:\"mo\", output:\"\\u22C6\", tex:\"star\", ttype:CONST},\n{input:\"//\", tag:\"mo\", output:\"/\", tex:null, ttype:CONST},\n{input:\"\\\\\\\\\", tag:\"mo\", output:\"\\\\\", tex:\"backslash\", ttype:CONST},\n{input:\"setminus\", tag:\"mo\", output:\"\\\\\", tex:null, ttype:CONST},\n{input:\"xx\", tag:\"mo\", output:\"\\u00D7\", tex:\"times\", ttype:CONST},\n{input:\"-:\", tag:\"mo\", output:\"\\u00F7\", tex:\"divide\", ttype:CONST},\n{input:\"@\", tag:\"mo\", output:\"\\u2218\", tex:\"circ\", ttype:CONST},\n{input:\"o+\", tag:\"mo\", output:\"\\u2295\", tex:\"oplus\", ttype:CONST},\n{input:\"ox\", tag:\"mo\", output:\"\\u2297\", tex:\"otimes\", ttype:CONST},\n{input:\"o.\", tag:\"mo\", output:\"\\u2299\", tex:\"odot\", ttype:CONST},\n{input:\"sum\", tag:\"mo\", output:\"\\u2211\", tex:null, ttype:UNDEROVER},\n{input:\"prod\", tag:\"mo\", output:\"\\u220F\", tex:null, ttype:UNDEROVER},\n{input:\"^^\", tag:\"mo\", output:\"\\u2227\", tex:\"wedge\", ttype:CONST},\n{input:\"^^^\", tag:\"mo\", output:\"\\u22C0\", tex:\"bigwedge\", ttype:UNDEROVER},\n{input:\"vv\", tag:\"mo\", output:\"\\u2228\", tex:\"vee\", ttype:CONST},\n{input:\"vvv\", tag:\"mo\", output:\"\\u22C1\", tex:\"bigvee\", ttype:UNDEROVER},\n{input:\"nn\", tag:\"mo\", output:\"\\u2229\", tex:\"cap\", ttype:CONST},\n{input:\"nnn\", tag:\"mo\", output:\"\\u22C2\", tex:\"bigcap\", ttype:UNDEROVER},\n{input:\"uu\", tag:\"mo\", output:\"\\u222A\", tex:\"cup\", ttype:CONST},\n{input:\"uuu\", tag:\"mo\", output:\"\\u22C3\", tex:\"bigcup\", ttype:UNDEROVER},\n\n//binary relation symbols\n{input:\"!=\", tag:\"mo\", output:\"\\u2260\", tex:\"ne\", ttype:CONST},\n{input:\":=\", tag:\"mo\", output:\":=\", tex:null, ttype:CONST},\n{input:\"lt\", tag:\"mo\", output:\"<\", tex:null, ttype:CONST},\n{input:\"<=\", tag:\"mo\", output:\"\\u2264\", tex:\"le\", ttype:CONST},\n{input:\"lt=\", tag:\"mo\", output:\"\\u2264\", tex:\"leq\", ttype:CONST},\n{input:\">=\", tag:\"mo\", output:\"\\u2265\", tex:\"ge\", ttype:CONST},\n{input:\"geq\", tag:\"mo\", output:\"\\u2265\", tex:null, ttype:CONST},\n{input:\"-<\", tag:\"mo\", output:\"\\u227A\", tex:\"prec\", ttype:CONST},\n{input:\"-lt\", tag:\"mo\", output:\"\\u227A\", tex:null, ttype:CONST},\n{input:\">-\", tag:\"mo\", output:\"\\u227B\", tex:\"succ\", ttype:CONST},\n{input:\"-<=\", tag:\"mo\", output:\"\\u2AAF\", tex:\"preceq\", ttype:CONST},\n{input:\">-=\", tag:\"mo\", output:\"\\u2AB0\", tex:\"succeq\", ttype:CONST},\n{input:\"in\", tag:\"mo\", output:\"\\u2208\", tex:null, ttype:CONST},\n{input:\"!in\", tag:\"mo\", output:\"\\u2209\", tex:\"notin\", ttype:CONST},\n{input:\"sub\", tag:\"mo\", output:\"\\u2282\", tex:\"subset\", ttype:CONST},\n{input:\"sup\", tag:\"mo\", output:\"\\u2283\", tex:\"supset\", ttype:CONST},\n{input:\"sube\", tag:\"mo\", output:\"\\u2286\", tex:\"subseteq\", ttype:CONST},\n{input:\"supe\", tag:\"mo\", output:\"\\u2287\", tex:\"supseteq\", ttype:CONST},\n{input:\"-=\", tag:\"mo\", output:\"\\u2261\", tex:\"equiv\", ttype:CONST},\n{input:\"~=\", tag:\"mo\", output:\"\\u2245\", tex:\"cong\", ttype:CONST},\n{input:\"~~\", tag:\"mo\", output:\"\\u2248\", tex:\"approx\", ttype:CONST},\n{input:\"prop\", tag:\"mo\", output:\"\\u221D\", tex:\"propto\", ttype:CONST},\n\n//logical symbols\n{input:\"and\", tag:\"mtext\", output:\"and\", tex:null, ttype:SPACE},\n{input:\"or\", tag:\"mtext\", output:\"or\", tex:null, ttype:SPACE},\n{input:\"not\", tag:\"mo\", output:\"\\u00AC\", tex:\"neg\", ttype:CONST},\n{input:\"=>\", tag:\"mo\", output:\"\\u21D2\", tex:\"implies\", ttype:CONST},\n{input:\"if\", tag:\"mo\", output:\"if\", tex:null, ttype:SPACE},\n{input:\"<=>\", tag:\"mo\", output:\"\\u21D4\", tex:\"iff\", ttype:CONST},\n{input:\"AA\", tag:\"mo\", output:\"\\u2200\", tex:\"forall\", ttype:CONST},\n{input:\"EE\", tag:\"mo\", output:\"\\u2203\", tex:\"exists\", ttype:CONST},\n{input:\"_|_\", tag:\"mo\", output:\"\\u22A5\", tex:\"bot\", ttype:CONST},\n{input:\"TT\", tag:\"mo\", output:\"\\u22A4\", tex:\"top\", ttype:CONST},\n{input:\"|--\", tag:\"mo\", output:\"\\u22A2\", tex:\"vdash\", ttype:CONST},\n{input:\"|==\", tag:\"mo\", output:\"\\u22A8\", tex:\"models\", ttype:CONST},\n\n//grouping brackets\n{input:\"(\", tag:\"mo\", output:\"(\", tex:null, ttype:LEFTBRACKET},\n{input:\")\", tag:\"mo\", output:\")\", tex:null, ttype:RIGHTBRACKET},\n{input:\"[\", tag:\"mo\", output:\"[\", tex:null, ttype:LEFTBRACKET},\n{input:\"]\", tag:\"mo\", output:\"]\", tex:null, ttype:RIGHTBRACKET},\n{input:\"{\", tag:\"mo\", output:\"{\", tex:null, ttype:LEFTBRACKET},\n{input:\"}\", tag:\"mo\", output:\"}\", tex:null, ttype:RIGHTBRACKET},\n{input:\"|\", tag:\"mo\", output:\"|\", tex:null, ttype:LEFTRIGHT},\n//{input:\"||\", tag:\"mo\", output:\"||\", tex:null, ttype:LEFTRIGHT},\n{input:\"(:\", tag:\"mo\", output:\"\\u2329\", tex:\"langle\", ttype:LEFTBRACKET},\n{input:\":)\", tag:\"mo\", output:\"\\u232A\", tex:\"rangle\", ttype:RIGHTBRACKET},\n{input:\"<<\", tag:\"mo\", output:\"\\u2329\", tex:null, ttype:LEFTBRACKET},\n{input:\">>\", tag:\"mo\", output:\"\\u232A\", tex:null, ttype:RIGHTBRACKET},\n{input:\"{:\", tag:\"mo\", output:\"{:\", tex:null, ttype:LEFTBRACKET, invisible:true},\n{input:\":}\", tag:\"mo\", output:\":}\", tex:null, ttype:RIGHTBRACKET, invisible:true},\n\n//miscellaneous symbols\n{input:\"int\", tag:\"mo\", output:\"\\u222B\", tex:null, ttype:CONST},\n{input:\"dx\", tag:\"mi\", output:\"{:d x:}\", tex:null, ttype:DEFINITION},\n{input:\"dy\", tag:\"mi\", output:\"{:d y:}\", tex:null, ttype:DEFINITION},\n{input:\"dz\", tag:\"mi\", output:\"{:d z:}\", tex:null, ttype:DEFINITION},\n{input:\"dt\", tag:\"mi\", output:\"{:d t:}\", tex:null, ttype:DEFINITION},\n{input:\"oint\", tag:\"mo\", output:\"\\u222E\", tex:null, ttype:CONST},\n{input:\"del\", tag:\"mo\", output:\"\\u2202\", tex:\"partial\", ttype:CONST},\n{input:\"grad\", tag:\"mo\", output:\"\\u2207\", tex:\"nabla\", ttype:CONST},\n{input:\"+-\", tag:\"mo\", output:\"\\u00B1\", tex:\"pm\", ttype:CONST},\n{input:\"O/\", tag:\"mo\", output:\"\\u2205\", tex:\"emptyset\", ttype:CONST},\n{input:\"oo\", tag:\"mo\", output:\"\\u221E\", tex:\"infty\", ttype:CONST},\n{input:\"aleph\", tag:\"mo\", output:\"\\u2135\", tex:null, ttype:CONST},\n{input:\"...\", tag:\"mo\", output:\"...\", tex:\"ldots\", ttype:CONST},\n{input:\":.\", tag:\"mo\", output:\"\\u2234\", tex:\"therefore\", ttype:CONST},\n{input:\"/_\", tag:\"mo\", output:\"\\u2220\", tex:\"angle\", ttype:CONST},\n{input:\"\\\\ \", tag:\"mo\", output:\"\\u00A0\", tex:null, ttype:CONST},\n{input:\"quad\", tag:\"mo\", output:\"\\u00A0\\u00A0\", tex:null, ttype:CONST},\n{input:\"qquad\", tag:\"mo\", output:\"\\u00A0\\u00A0\\u00A0\\u00A0\", tex:null, ttype:CONST},\n{input:\"cdots\", tag:\"mo\", output:\"\\u22EF\", tex:null, ttype:CONST},\n{input:\"vdots\", tag:\"mo\", output:\"\\u22EE\", tex:null, ttype:CONST},\n{input:\"ddots\", tag:\"mo\", output:\"\\u22F1\", tex:null, ttype:CONST},\n{input:\"diamond\", tag:\"mo\", output:\"\\u22C4\", tex:null, ttype:CONST},\n{input:\"square\", tag:\"mo\", output:\"\\u25A1\", tex:null, ttype:CONST},\n{input:\"|__\", tag:\"mo\", output:\"\\u230A\", tex:\"lfloor\", ttype:CONST},\n{input:\"__|\", tag:\"mo\", output:\"\\u230B\", tex:\"rfloor\", ttype:CONST},\n{input:\"|~\", tag:\"mo\", output:\"\\u2308\", tex:\"lceiling\", ttype:CONST},\n{input:\"~|\", tag:\"mo\", output:\"\\u2309\", tex:\"rceiling\", ttype:CONST},\n{input:\"CC\", tag:\"mo\", output:\"\\u2102\", tex:null, ttype:CONST},\n{input:\"NN\", tag:\"mo\", output:\"\\u2115\", tex:null, ttype:CONST},\n{input:\"QQ\", tag:\"mo\", output:\"\\u211A\", tex:null, ttype:CONST},\n{input:\"RR\", tag:\"mo\", output:\"\\u211D\", tex:null, ttype:CONST},\n{input:\"ZZ\", tag:\"mo\", output:\"\\u2124\", tex:null, ttype:CONST},\n{input:\"f\", tag:\"mi\", output:\"f\", tex:null, ttype:UNARY, func:true},\n{input:\"g\", tag:\"mi\", output:\"g\", tex:null, ttype:UNARY, func:true},\n\n//standard functions\n{input:\"lim\", tag:\"mo\", output:\"lim\", tex:null, ttype:UNDEROVER},\n{input:\"Lim\", tag:\"mo\", output:\"Lim\", tex:null, ttype:UNDEROVER},\n{input:\"sin\", tag:\"mo\", output:\"sin\", tex:null, ttype:UNARY, func:true},\n{input:\"cos\", tag:\"mo\", output:\"cos\", tex:null, ttype:UNARY, func:true},\n{input:\"tan\", tag:\"mo\", output:\"tan\", tex:null, ttype:UNARY, func:true},\n{input:\"sinh\", tag:\"mo\", output:\"sinh\", tex:null, ttype:UNARY, func:true},\n{input:\"cosh\", tag:\"mo\", output:\"cosh\", tex:null, ttype:UNARY, func:true},\n{input:\"tanh\", tag:\"mo\", output:\"tanh\", tex:null, ttype:UNARY, func:true},\n{input:\"cot\", tag:\"mo\", output:\"cot\", tex:null, ttype:UNARY, func:true},\n{input:\"sec\", tag:\"mo\", output:\"sec\", tex:null, ttype:UNARY, func:true},\n{input:\"csc\", tag:\"mo\", output:\"csc\", tex:null, ttype:UNARY, func:true},\n{input:\"log\", tag:\"mo\", output:\"log\", tex:null, ttype:UNARY, func:true},\n{input:\"ln\", tag:\"mo\", output:\"ln\", tex:null, ttype:UNARY, func:true},\n{input:\"det\", tag:\"mo\", output:\"det\", tex:null, ttype:UNARY, func:true},\n{input:\"dim\", tag:\"mo\", output:\"dim\", tex:null, ttype:CONST},\n{input:\"mod\", tag:\"mo\", output:\"mod\", tex:null, ttype:CONST},\n{input:\"gcd\", tag:\"mo\", output:\"gcd\", tex:null, ttype:UNARY, func:true},\n{input:\"lcm\", tag:\"mo\", output:\"lcm\", tex:null, ttype:UNARY, func:true},\n{input:\"lub\", tag:\"mo\", output:\"lub\", tex:null, ttype:CONST},\n{input:\"glb\", tag:\"mo\", output:\"glb\", tex:null, ttype:CONST},\n{input:\"min\", tag:\"mo\", output:\"min\", tex:null, ttype:UNDEROVER},\n{input:\"max\", tag:\"mo\", output:\"max\", tex:null, ttype:UNDEROVER},\n\n//arrows\n{input:\"uarr\", tag:\"mo\", output:\"\\u2191\", tex:\"uparrow\", ttype:CONST},\n{input:\"darr\", tag:\"mo\", output:\"\\u2193\", tex:\"downarrow\", ttype:CONST},\n{input:\"rarr\", tag:\"mo\", output:\"\\u2192\", tex:\"rightarrow\", ttype:CONST},\n{input:\"->\", tag:\"mo\", output:\"\\u2192\", tex:\"to\", ttype:CONST},\n{input:\"|->\", tag:\"mo\", output:\"\\u21A6\", tex:\"mapsto\", ttype:CONST},\n{input:\"larr\", tag:\"mo\", output:\"\\u2190\", tex:\"leftarrow\", ttype:CONST},\n{input:\"harr\", tag:\"mo\", output:\"\\u2194\", tex:\"leftrightarrow\", ttype:CONST},\n{input:\"rArr\", tag:\"mo\", output:\"\\u21D2\", tex:\"Rightarrow\", ttype:CONST},\n{input:\"lArr\", tag:\"mo\", output:\"\\u21D0\", tex:\"Leftarrow\", ttype:CONST},\n{input:\"hArr\", tag:\"mo\", output:\"\\u21D4\", tex:\"Leftrightarrow\", ttype:CONST},\n\n//commands with argument\nAMsqrt, AMroot, AMfrac, AMdiv, AMover, AMsub, AMsup,\n{input:\"hat\", tag:\"mover\", output:\"\\u005E\", tex:null, ttype:UNARY, acc:true},\n{input:\"bar\", tag:\"mover\", output:\"\\u00AF\", tex:\"overline\", ttype:UNARY, acc:true},\n{input:\"vec\", tag:\"mover\", output:\"\\u2192\", tex:null, ttype:UNARY, acc:true},\n{input:\"dot\", tag:\"mover\", output:\".\", tex:null, ttype:UNARY, acc:true},\n{input:\"ddot\", tag:\"mover\", output:\"..\", tex:null, ttype:UNARY, acc:true},\n{input:\"ul\", tag:\"munder\", output:\"\\u0332\", tex:\"underline\", ttype:UNARY, acc:true},\nAMtext, AMmbox, AMquote,\n{input:\"bb\", tag:\"mstyle\", atname:\"fontweight\", atval:\"bold\", output:\"bb\", tex:null, ttype:UNARY},\n{input:\"mathbf\", tag:\"mstyle\", atname:\"fontweight\", atval:\"bold\", output:\"mathbf\", tex:null, ttype:UNARY},\n{input:\"sf\", tag:\"mstyle\", atname:\"fontfamily\", atval:\"sans-serif\", output:\"sf\", tex:null, ttype:UNARY},\n{input:\"mathsf\", tag:\"mstyle\", atname:\"fontfamily\", atval:\"sans-serif\", output:\"mathsf\", tex:null, ttype:UNARY},\n{input:\"bbb\", tag:\"mstyle\", atname:\"mathvariant\", atval:\"double-struck\", output:\"bbb\", tex:null, ttype:UNARY, codes:AMbbb},\n{input:\"mathbb\", tag:\"mstyle\", atname:\"mathvariant\", atval:\"double-struck\", output:\"mathbb\", tex:null, ttype:UNARY, codes:AMbbb},\n{input:\"cc\", tag:\"mstyle\", atname:\"mathvariant\", atval:\"script\", output:\"cc\", tex:null, ttype:UNARY, codes:AMcal},\n{input:\"mathcal\", tag:\"mstyle\", atname:\"mathvariant\", atval:\"script\", output:\"mathcal\", tex:null, ttype:UNARY, codes:AMcal},\n{input:\"tt\", tag:\"mstyle\", atname:\"fontfamily\", atval:\"monospace\", output:\"tt\", tex:null, ttype:UNARY},\n{input:\"mathtt\", tag:\"mstyle\", atname:\"fontfamily\", atval:\"monospace\", output:\"mathtt\", tex:null, ttype:UNARY},\n{input:\"fr\", tag:\"mstyle\", atname:\"mathvariant\", atval:\"fraktur\", output:\"fr\", tex:null, ttype:UNARY, codes:AMfrk},\n{input:\"mathfrak\", tag:\"mstyle\", atname:\"mathvariant\", atval:\"fraktur\", output:\"mathfrak\", tex:null, ttype:UNARY, codes:AMfrk}\n];\n\nfunction compareNames(s1,s2) {\n if (s1.input > s2.input) return 1\n else return -1;\n}\n\nvar AMnames = []; //list of input symbols\n\nfunction AMinitSymbols() {\n var texsymbols = [], i;\n for (i=0; i<AMsymbols.length; i++)\n if (AMsymbols[i].tex) \n texsymbols[texsymbols.length] = {input:AMsymbols[i].tex, \n tag:AMsymbols[i].tag, output:AMsymbols[i].output, ttype:AMsymbols[i].ttype};\n AMsymbols = AMsymbols.concat(texsymbols);\n AMsymbols.sort(compareNames);\n for (i=0; i<AMsymbols.length; i++) AMnames[i] = AMsymbols[i].input;\n}\n\nvar AMmathml = \"http://www.w3.org/1998/Math/MathML\";\n\nfunction AMcreateElementMathML(t) {\n if (isIE) return document.createElement(\"m:\"+t);\n else return document.createElementNS(AMmathml,t);\n}\n\nfunction AMcreateMmlNode(t,frag) {\n// var node = AMcreateElementMathML(name);\n if (isIE) var node = document.createElement(\"m:\"+t);\n else var node = document.createElementNS(AMmathml,t);\n node.appendChild(frag);\n return node;\n}\n\nfunction newcommand(oldstr,newstr) {\n AMsymbols = AMsymbols.concat([{input:oldstr, tag:\"mo\", output:newstr, \n tex:null, ttype:DEFINITION}]);\n}\n\nfunction AMremoveCharsAndBlanks(str,n) {\n//remove n characters and any following blanks\n var st;\n if (str.charAt(n)==\"\\\\\" && str.charAt(n+1)!=\"\\\\\" && str.charAt(n+1)!=\" \") \n st = str.slice(n+1);\n else st = str.slice(n);\n for (var i=0; i<st.length && st.charCodeAt(i)<=32; i=i+1);\n return st.slice(i);\n}\n\nfunction AMposition(arr, str, n) { \n// return position >=n where str appears or would be inserted\n// assumes arr is sorted\n if (n==0) {\n var h,m;\n n = -1;\n h = arr.length;\n while (n+1<h) {\n m = (n+h) >> 1;\n if (arr[m]<str) n = m; else h = m;\n }\n return h;\n } else\n for (var i=n; i<arr.length && arr[i]<str; i++);\n return i; // i=arr.length || arr[i]>=str\n}\n\nfunction AMgetSymbol(str) {\n//return maximal initial substring of str that appears in names\n//return null if there is none\n var k = 0; //new pos\n var j = 0; //old pos\n var mk; //match pos\n var st;\n var tagst;\n var match = \"\";\n var more = true;\n for (var i=1; i<=str.length && more; i++) {\n st = str.slice(0,i); //initial substring of length i\n j = k;\n k = AMposition(AMnames, st, j);\n if (k<AMnames.length && str.slice(0,AMnames[k].length)==AMnames[k]){\n match = AMnames[k];\n mk = k;\n i = match.length;\n }\n more = k<AMnames.length && str.slice(0,AMnames[k].length)>=AMnames[k];\n }\n AMpreviousSymbol=AMcurrentSymbol;\n if (match!=\"\"){\n AMcurrentSymbol=AMsymbols[mk].ttype;\n return AMsymbols[mk]; \n }\n// if str[0] is a digit or - return maxsubstring of digits.digits\n AMcurrentSymbol=CONST;\n k = 1;\n st = str.slice(0,1);\n var integ = true;\n while (\"0\"<=st && st<=\"9\" && k<=str.length) {\n st = str.slice(k,k+1);\n k++;\n }\n if (st == decimalsign) {\n st = str.slice(k,k+1);\n if (\"0\"<=st && st<=\"9\") {\n integ = false;\n k++;\n while (\"0\"<=st && st<=\"9\" && k<=str.length) {\n st = str.slice(k,k+1);\n k++;\n }\n }\n }\n if ((integ && k>1) || k>2) {\n st = str.slice(0,k-1);\n tagst = \"mn\";\n } else {\n k = 2;\n st = str.slice(0,1); //take 1 character\n tagst = ((\"A\">st || st>\"Z\") && (\"a\">st || st>\"z\")?\"mo\":\"mi\");\n }\n if (st==\"-\" && AMpreviousSymbol==INFIX) {\n AMcurrentSymbol = INFIX; //trick \"/\" into recognizing \"-\" on second parse\n return {input:st, tag:tagst, output:st, ttype:UNARY, func:true};\n }\n return {input:st, tag:tagst, output:st, ttype:CONST};\n}\n\nfunction AMremoveBrackets(node) {\n var st;\n if (node.nodeName==\"mrow\") {\n st = node.firstChild.firstChild.nodeValue;\n if (st==\"(\" || st==\"[\" || st==\"{\") node.removeChild(node.firstChild);\n }\n if (node.nodeName==\"mrow\") {\n st = node.lastChild.firstChild.nodeValue;\n if (st==\")\" || st==\"]\" || st==\"}\") node.removeChild(node.lastChild);\n }\n}\n\n/* ASCIIMathML.js - copyright Peter Jipsen, released under the GPL\nSee http://www1.chapman.edu/~jipsen/mathml/asciimath.html/ */\n\nvar AMnestingDepth,AMpreviousSymbol,AMcurrentSymbol;\n\nfunction AMparseSexpr(str) { //parses str and returns [node,tailstr]\n var symbol, node, result, i, st,// rightvert = false,\n newFrag = document.createDocumentFragment();\n str = AMremoveCharsAndBlanks(str,0);\n symbol = AMgetSymbol(str); //either a token or a bracket or empty\n if (symbol == null || symbol.ttype == RIGHTBRACKET && AMnestingDepth > 0) {\n return [null,str];\n }\n if (symbol.ttype == DEFINITION) {\n str = symbol.output+AMremoveCharsAndBlanks(str,symbol.input.length); \n symbol = AMgetSymbol(str);\n }\n switch (symbol.ttype) {\n case UNDEROVER:\n case CONST:\n str = AMremoveCharsAndBlanks(str,symbol.input.length); \n return [AMcreateMmlNode(symbol.tag, //its a constant\n document.createTextNode(symbol.output)),str];\n case LEFTBRACKET: //read (expr+)\n AMnestingDepth++;\n str = AMremoveCharsAndBlanks(str,symbol.input.length); \n result = AMparseExpr(str,true);\n AMnestingDepth--;\n if (typeof symbol.invisible == \"boolean\" && symbol.invisible) \n node = AMcreateMmlNode(\"mrow\",result[0]);\n else {\n node = AMcreateMmlNode(\"mo\",document.createTextNode(symbol.output));\n node = AMcreateMmlNode(\"mrow\",node);\n node.appendChild(result[0]);\n }\n return [node,result[1]];\n case TEXT:\n if (symbol!=AMquote) str = AMremoveCharsAndBlanks(str,symbol.input.length);\n if (str.charAt(0)==\"{\") i=str.indexOf(\"}\");\n else if (str.charAt(0)==\"(\") i=str.indexOf(\")\");\n else if (str.charAt(0)==\"[\") i=str.indexOf(\"]\");\n else if (symbol==AMquote) i=str.slice(1).indexOf(\"\\\"\")+1;\n else i = 0;\n if (i==-1) i = str.length;\n st = str.slice(1,i);\n if (st.charAt(0) == \" \") {\n node = AMcreateElementMathML(\"mspace\");\n node.setAttribute(\"width\",\"1ex\");\n newFrag.appendChild(node);\n }\n newFrag.appendChild(\n AMcreateMmlNode(symbol.tag,document.createTextNode(st)));\n if (st.charAt(st.length-1) == \" \") {\n node = AMcreateElementMathML(\"mspace\");\n node.setAttribute(\"width\",\"1ex\");\n newFrag.appendChild(node);\n }\n str = AMremoveCharsAndBlanks(str,i+1);\n return [AMcreateMmlNode(\"mrow\",newFrag),str];\n case UNARY:\n str = AMremoveCharsAndBlanks(str,symbol.input.length); \n result = AMparseSexpr(str);\n if (result[0]==null) return [AMcreateMmlNode(symbol.tag,\n document.createTextNode(symbol.output)),str];\n if (typeof symbol.func == \"boolean\" && symbol.func) { // functions hack\n st = str.charAt(0);\n if (st==\"^\" || st==\"_\" || st==\"/\" || st==\"|\" || st==\",\") {\n return [AMcreateMmlNode(symbol.tag,\n document.createTextNode(symbol.output)),str];\n } else {\n node = AMcreateMmlNode(\"mrow\",\n AMcreateMmlNode(symbol.tag,document.createTextNode(symbol.output)));\n node.appendChild(result[0]);\n return [node,result[1]];\n }\n }\n AMremoveBrackets(result[0]);\n if (symbol.input == \"sqrt\") { // sqrt\n return [AMcreateMmlNode(symbol.tag,result[0]),result[1]];\n } else if (typeof symbol.acc == \"boolean\" && symbol.acc) { // accent\n node = AMcreateMmlNode(symbol.tag,result[0]);\n node.appendChild(AMcreateMmlNode(\"mo\",document.createTextNode(symbol.output)));\n return [node,result[1]];\n } else { // font change command\n if (!isIE && typeof symbol.codes != \"undefined\") {\n for (i=0; i<result[0].childNodes.length; i++)\n if (result[0].childNodes[i].nodeName==\"mi\" || result[0].nodeName==\"mi\") {\n st = (result[0].nodeName==\"mi\"?result[0].firstChild.nodeValue:\n result[0].childNodes[i].firstChild.nodeValue);\n var newst = [];\n for (var j=0; j<st.length; j++)\n if (st.charCodeAt(j)>64 && st.charCodeAt(j)<91) newst = newst +\n String.fromCharCode(symbol.codes[st.charCodeAt(j)-65]);\n else newst = newst + st.charAt(j);\n if (result[0].nodeName==\"mi\")\n result[0]=AMcreateElementMathML(\"mo\").\n appendChild(document.createTextNode(newst));\n else result[0].replaceChild(AMcreateElementMathML(\"mo\").\n appendChild(document.createTextNode(newst)),result[0].childNodes[i]);\n }\n }\n node = AMcreateMmlNode(symbol.tag,result[0]);\n node.setAttribute(symbol.atname,symbol.atval);\n return [node,result[1]];\n }\n case BINARY:\n str = AMremoveCharsAndBlanks(str,symbol.input.length); \n result = AMparseSexpr(str);\n if (result[0]==null) return [AMcreateMmlNode(\"mo\",\n document.createTextNode(symbol.input)),str];\n AMremoveBrackets(result[0]);\n var result2 = AMparseSexpr(result[1]);\n if (result2[0]==null) return [AMcreateMmlNode(\"mo\",\n document.createTextNode(symbol.input)),str];\n AMremoveBrackets(result2[0]);\n if (symbol.input==\"root\" || symbol.input==\"stackrel\") \n newFrag.appendChild(result2[0]);\n newFrag.appendChild(result[0]);\n if (symbol.input==\"frac\") newFrag.appendChild(result2[0]);\n return [AMcreateMmlNode(symbol.tag,newFrag),result2[1]];\n case INFIX:\n str = AMremoveCharsAndBlanks(str,symbol.input.length); \n return [AMcreateMmlNode(\"mo\",document.createTextNode(symbol.output)),str];\n case SPACE:\n str = AMremoveCharsAndBlanks(str,symbol.input.length); \n node = AMcreateElementMathML(\"mspace\");\n node.setAttribute(\"width\",\"1ex\");\n newFrag.appendChild(node);\n newFrag.appendChild(\n AMcreateMmlNode(symbol.tag,document.createTextNode(symbol.output)));\n node = AMcreateElementMathML(\"mspace\");\n node.setAttribute(\"width\",\"1ex\");\n newFrag.appendChild(node);\n return [AMcreateMmlNode(\"mrow\",newFrag),str];\n case LEFTRIGHT:\n// if (rightvert) return [null,str]; else rightvert = true;\n AMnestingDepth++;\n str = AMremoveCharsAndBlanks(str,symbol.input.length); \n result = AMparseExpr(str,false);\n AMnestingDepth--;\n var st = \"\";\n if (result[0].lastChild!=null)\n st = result[0].lastChild.firstChild.nodeValue;\n if (st == \"|\") { // its an absolute value subterm\n node = AMcreateMmlNode(\"mo\",document.createTextNode(symbol.output));\n node = AMcreateMmlNode(\"mrow\",node);\n node.appendChild(result[0]);\n return [node,result[1]];\n } else { // the \"|\" is a \\mid\n node = AMcreateMmlNode(\"mo\",document.createTextNode(symbol.output));\n node = AMcreateMmlNode(\"mrow\",node);\n return [node,str];\n }\n default:\n//alert(\"default\");\n str = AMremoveCharsAndBlanks(str,symbol.input.length); \n return [AMcreateMmlNode(symbol.tag, //its a constant\n document.createTextNode(symbol.output)),str];\n }\n}\n\nfunction AMparseIexpr(str) {\n var symbol, sym1, sym2, node, result, underover;\n str = AMremoveCharsAndBlanks(str,0);\n sym1 = AMgetSymbol(str);\n result = AMparseSexpr(str);\n node = result[0];\n str = result[1];\n symbol = AMgetSymbol(str);\n if (symbol.ttype == INFIX && symbol.input != \"/\") {\n str = AMremoveCharsAndBlanks(str,symbol.input.length);\n// if (symbol.input == \"/\") result = AMparseIexpr(str); else ...\n result = AMparseSexpr(str);\n if (result[0] == null) // show box in place of missing argument\n result[0] = AMcreateMmlNode(\"mo\",document.createTextNode(\"\\u25A1\"));\n else AMremoveBrackets(result[0]);\n str = result[1];\n// if (symbol.input == \"/\") AMremoveBrackets(node);\n if (symbol.input == \"_\") {\n sym2 = AMgetSymbol(str);\n underover = (sym1.ttype == UNDEROVER);\n if (sym2.input == \"^\") {\n str = AMremoveCharsAndBlanks(str,sym2.input.length);\n var res2 = AMparseSexpr(str);\n AMremoveBrackets(res2[0]);\n str = res2[1];\n node = AMcreateMmlNode((underover?\"munderover\":\"msubsup\"),node);\n node.appendChild(result[0]);\n node.appendChild(res2[0]);\n node = AMcreateMmlNode(\"mrow\",node); // so sum does not stretch\n } else {\n node = AMcreateMmlNode((underover?\"munder\":\"msub\"),node);\n node.appendChild(result[0]);\n }\n } else {\n node = AMcreateMmlNode(symbol.tag,node);\n node.appendChild(result[0]);\n }\n }\n return [node,str];\n}\n\nfunction AMparseExpr(str,rightbracket) {\n var symbol, node, result, i, nodeList = [],\n newFrag = document.createDocumentFragment();\n do {\n str = AMremoveCharsAndBlanks(str,0);\n result = AMparseIexpr(str);\n node = result[0];\n str = result[1];\n symbol = AMgetSymbol(str);\n if (symbol.ttype == INFIX && symbol.input == \"/\") {\n str = AMremoveCharsAndBlanks(str,symbol.input.length);\n result = AMparseIexpr(str);\n if (result[0] == null) // show box in place of missing argument\n result[0] = AMcreateMmlNode(\"mo\",document.createTextNode(\"\\u25A1\"));\n else AMremoveBrackets(result[0]);\n str = result[1];\n AMremoveBrackets(node);\n node = AMcreateMmlNode(symbol.tag,node);\n node.appendChild(result[0]);\n newFrag.appendChild(node);\n symbol = AMgetSymbol(str);\n } \n else if (node!=undefined) newFrag.appendChild(node);\n } while ((symbol.ttype != RIGHTBRACKET && \n (symbol.ttype != LEFTRIGHT || rightbracket)\n || AMnestingDepth == 0) && symbol!=null && symbol.output!=\"\");\n if (symbol.ttype == RIGHTBRACKET || symbol.ttype == LEFTRIGHT) {\n// if (AMnestingDepth > 0) AMnestingDepth--;\n var len = newFrag.childNodes.length;\n if (len>0 && newFrag.childNodes[len-1].nodeName == \"mrow\" && len>1 &&\n newFrag.childNodes[len-2].nodeName == \"mo\" &&\n newFrag.childNodes[len-2].firstChild.nodeValue == \",\") { //matrix\n var right = newFrag.childNodes[len-1].lastChild.firstChild.nodeValue;\n if (right==\")\" || right==\"]\") {\n var left = newFrag.childNodes[len-1].firstChild.firstChild.nodeValue;\n if (left==\"(\" && right==\")\" && symbol.output != \"}\" || \n left==\"[\" && right==\"]\") {\n var pos = []; // positions of commas\n var matrix = true;\n var m = newFrag.childNodes.length;\n for (i=0; matrix && i<m; i=i+2) {\n pos[i] = [];\n node = newFrag.childNodes[i];\n if (matrix) matrix = node.nodeName==\"mrow\" && \n (i==m-1 || node.nextSibling.nodeName==\"mo\" && \n node.nextSibling.firstChild.nodeValue==\",\")&&\n node.firstChild.firstChild.nodeValue==left &&\n node.lastChild.firstChild.nodeValue==right;\n if (matrix) \n for (var j=0; j<node.childNodes.length; j++)\n if (node.childNodes[j].firstChild.nodeValue==\",\")\n pos[i][pos[i].length]=j;\n if (matrix && i>1) matrix = pos[i].length == pos[i-2].length;\n }\n if (matrix) {\n var row, frag, n, k, table = document.createDocumentFragment();\n for (i=0; i<m; i=i+2) {\n row = document.createDocumentFragment();\n frag = document.createDocumentFragment();\n node = newFrag.firstChild; // <mrow>(-,-,...,-,-)</mrow>\n n = node.childNodes.length;\n k = 0;\n node.removeChild(node.firstChild); //remove (\n for (j=1; j<n-1; j++) {\n if (typeof pos[i][k] != \"undefined\" && j==pos[i][k]){\n node.removeChild(node.firstChild); //remove ,\n row.appendChild(AMcreateMmlNode(\"mtd\",frag));\n k++;\n } else frag.appendChild(node.firstChild);\n }\n row.appendChild(AMcreateMmlNode(\"mtd\",frag));\n if (newFrag.childNodes.length>2) {\n newFrag.removeChild(newFrag.firstChild); //remove <mrow>)</mrow>\n newFrag.removeChild(newFrag.firstChild); //remove <mo>,</mo>\n }\n table.appendChild(AMcreateMmlNode(\"mtr\",row));\n }\n node = AMcreateMmlNode(\"mtable\",table);\n if (typeof symbol.invisible == \"boolean\" && symbol.invisible) node.setAttribute(\"columnalign\",\"left\");\n newFrag.replaceChild(node,newFrag.firstChild);\n }\n }\n }\n }\n str = AMremoveCharsAndBlanks(str,symbol.input.length);\n if (typeof symbol.invisible != \"boolean\" || !symbol.invisible) {\n node = AMcreateMmlNode(\"mo\",document.createTextNode(symbol.output));\n newFrag.appendChild(node);\n }\n }\n return [newFrag,str];\n}\n\nfunction AMparseMath(str) {\n var result, node = AMcreateElementMathML(\"mstyle\");\n if (mathcolor != \"\") node.setAttribute(\"mathcolor\",mathcolor);\n if (displaystyle) node.setAttribute(\"displaystyle\",\"true\");\n if (mathfontfamily != \"\") node.setAttribute(\"fontfamily\",mathfontfamily);\n AMnestingDepth = 0;\n node.appendChild(AMparseExpr(str.replace(/^\\s+/g,\"\"),false)[0]);\n node = AMcreateMmlNode(\"math\",node);\n if (showasciiformulaonhover) //fixed by djhsu so newline\n node.setAttribute(\"title\",str.replace(/\\s+/g,\" \"));//does not show in Gecko\n if (mathfontfamily != \"\" && (isIE || mathfontfamily != \"serif\")) {\n var fnode = AMcreateElementXHTML(\"font\");\n fnode.setAttribute(\"face\",mathfontfamily);\n fnode.appendChild(node);\n return fnode;\n }\n return node;\n}\n\nfunction AMstrarr2docFrag(arr, linebreaks) {\n var newFrag=document.createDocumentFragment();\n var expr = false;\n for (var i=0; i<arr.length; i++) {\n if (expr) newFrag.appendChild(AMparseMath(arr[i]));\n else {\n var arri = (linebreaks ? arr[i].split(\"\\n\\n\") : [arr[i]]);\n newFrag.appendChild(AMcreateElementXHTML(\"span\").\n appendChild(document.createTextNode(arri[0])));\n for (var j=1; j<arri.length; j++) {\n newFrag.appendChild(AMcreateElementXHTML(\"p\"));\n newFrag.appendChild(AMcreateElementXHTML(\"span\").\n appendChild(document.createTextNode(arri[j])));\n }\n }\n expr = !expr;\n }\n return newFrag;\n}\n\nfunction AMprocessNodeR(n, linebreaks) {\n var mtch, str, arr, frg, i;\n if (n.childNodes.length == 0) {\n if ((n.nodeType!=8 || linebreaks) &&\n n.parentNode.nodeName!=\"form\" && n.parentNode.nodeName!=\"FORM\" &&\n n.parentNode.nodeName!=\"textarea\" && n.parentNode.nodeName!=\"TEXTAREA\" &&\n n.parentNode.nodeName!=\"code\" && n.parentNode.nodeName!=\"CODE\" && /* ASCIIMathML.js - copyright Peter Jipsen, released under the GPL\nSee http://www1.chapman.edu/~jipsen/mathml/asciimath.html/ */\n n.parentNode.nodeName!=\"pre\" && n.parentNode.nodeName!=\"PRE\") {\n str = n.nodeValue;\n if (!(str == null)) {\n str = str.replace(/\\r\\n\\r\\n/g,\"\\n\\n\");\n if (doubleblankmathdelimiter) {\n str = str.replace(/\\x20\\x20\\./g,\" \"+AMdelimiter1+\".\");\n str = str.replace(/\\x20\\x20,/g,\" \"+AMdelimiter1+\",\");\n str = str.replace(/\\x20\\x20/g,\" \"+AMdelimiter1+\" \");\n }\n str = str.replace(/\\x20+/g,\" \");\n str = str.replace(/\\s*\\r\\n/g,\" \");\n mtch = false;\n str = str.replace(new RegExp(AMescape2, \"g\"),\n function(st){mtch=true;return \"AMescape2\"});\n str = str.replace(new RegExp(AMescape1, \"g\"),\n function(st){mtch=true;return \"AMescape1\"});\n str = str.replace(new RegExp(AMdelimiter2regexp, \"g\"),AMdelimiter1);\n arr = str.split(AMdelimiter1);\n for (i=0; i<arr.length; i++)\n arr[i]=arr[i].replace(/AMescape2/g,AMdelimiter2).\n replace(/AMescape1/g,AMdelimiter1);\n if (arr.length>1 || mtch) {\n if (checkForMathML) {\n checkForMathML = false;\n var nd = AMisMathMLavailable();\n AMnoMathML = nd != null;\n if (AMnoMathML && notifyIfNoMathML) \n if (alertIfNoMathML)\n alert(\"To view the ASCIIMathML notation use Internet Explorer 6 +\\nMathPlayer (free from www.dessci.com)\\n\\\n or Firefox/Mozilla/Netscape\");\n else AMbody.insertBefore(nd,AMbody.childNodes[0]);\n }\n if (!AMnoMathML) {\n frg = AMstrarr2docFrag(arr,n.nodeType==8);\n var len = frg.childNodes.length;\n n.parentNode.replaceChild(frg,n);\n return len-1;\n } else return 0;\n }\n }\n } else return 0;\n } else if (n.nodeName!=\"math\") {\n for (i=0; i<n.childNodes.length; i++)\n i += AMprocessNodeR(n.childNodes[i], linebreaks);\n }\n return 0;\n}\n\nfunction AMprocessNode(n, linebreaks, spanclassAM) {\n var frag,st;\n if (spanclassAM!=null) {\n frag = document.getElementsByTagName(\"span\")\n for (var i=0;i<frag.length;i++)\n if (frag[i].className == \"AM\")\n AMprocessNodeR(frag[i],linebreaks);\n } else {\n try {\n st = n.innerHTML;\n } catch(err) {}\n if (st==null || \n st.indexOf(AMdelimiter1)!=-1 || st.indexOf(AMdelimiter2)!=-1) \n AMprocessNodeR(n,linebreaks);\n }\n if (isIE) { //needed to match size and font of formula to surrounding text\n frag = document.getElementsByTagName('math');\n for (var i=0;i<frag.length;i++) frag[i].update()\n }\n}\n\nvar AMbody;\nvar AMnoMathML = false, AMtranslated = false;\n\nfunction translate(spanclassAM) {\n if (!AMtranslated) { // run this only once\n AMtranslated = true;\n AMinitSymbols();\n AMbody = document.getElementsByTagName(\"body\")[0];\n AMprocessNode(AMbody, false, spanclassAM);\n }\n}\n\nif (isIE) { // avoid adding MathPlayer info explicitly to each webpage\n document.write(\"<object id=\\\"mathplayer\\\"\\\n classid=\\\"clsid:32F66A20-7614-11D4-BD11-00104BD3F987\\\"></object>\");\n document.write(\"<?import namespace=\\\"m\\\" implementation=\\\"#mathplayer\\\"?>\");\n}\n\n// GO1.1 Generic onload by Brothercake \n// http://www.brothercake.com/\n//onload function (replaces the onload=\"translate()\" in the <body> tag)\nfunction generic()\n{\n translate();\n};\n//setup onload function\nif(typeof window.addEventListener != 'undefined')\n{\n //.. gecko, safari, konqueror and standard\n window.addEventListener('load', generic, false);\n}\nelse if(typeof document.addEventListener != 'undefined')\n{\n //.. opera 7\n document.addEventListener('load', generic, false);\n}\nelse if(typeof window.attachEvent != 'undefined')\n{\n //.. win/ie\n window.attachEvent('onload', generic);\n}\n//** remove this condition to degrade older browsers\nelse\n{\n //.. mac/ie5 and anything else that gets this far\n //if there's an existing onload function\n if(typeof window.onload == 'function')\n {\n //store it\n var existing = onload;\n //add new onload handler\n window.onload = function()\n {\n //call existing onload function\n existing();\n //call generic onload function\n generic();\n };\n }\n else\n {\n //setup onload function\n window.onload = generic;\n }\n}\n</script>\n" + diff --git a/src/Text/Pandoc/Definition.hs b/src/Text/Pandoc/Definition.hs new file mode 100644 index 000000000..08ff3905e --- /dev/null +++ b/src/Text/Pandoc/Definition.hs @@ -0,0 +1,50 @@ +-- | Definition of 'Pandoc' data structure for format-neutral representation +-- of documents. +module Text.Pandoc.Definition where + +data Pandoc = Pandoc Meta [Block] deriving (Eq, Read, Show) + +-- | Bibliographic information for the document: title (list of 'Inline'), +-- authors (list of strings), date (string). +data Meta = Meta [Inline] -- title + [String] -- authors + String -- date + deriving (Eq, Show, Read) + +-- | Block element. +data Block + = Plain [Inline] -- ^ Plain text, not a paragraph + | Blank -- ^ A blank line + | Null -- ^ Nothing + | Para [Inline] -- ^ Paragraph + | Key [Inline] Target -- ^ Reference key: name (list of inlines) and 'Target' + | CodeBlock String -- ^ Code block (literal) + | RawHtml String -- ^ Raw HTML block (literal) + | BlockQuote [Block] -- ^ Block quote (list of blocks) + | OrderedList [[Block]] -- ^ Ordered list (list of items, each a list of blocks) + | BulletList [[Block]] -- ^ Bullet list (list of items, each a list of blocks) + | Header Int [Inline] -- ^ Header - level (integer) and text (list of inlines) + | HorizontalRule -- ^ Horizontal rule + | Note String [Block] -- ^ Footnote or endnote - reference (string), text (list of blocks) + deriving (Eq, Read, Show) + +-- | Target for a link: either a URL or an indirect (labeled) reference. +data Target + = Src String String -- ^ First string is URL, second is title + | Ref [Inline] -- ^ Label (list of inlines) for an indirect reference + deriving (Show, Eq, Read) + +-- | Inline elements. +data Inline + = Str String -- ^ Text (string) + | Emph [Inline] -- ^ Emphasized text (list of inlines) + | Strong [Inline] -- ^ Strongly emphasized text (list of inlines) + | Code String -- ^ Inline code (literal) + | Space -- ^ Inter-word space + | LineBreak -- ^ Hard line break + | TeX String -- ^ LaTeX code (literal) + | HtmlInline String -- ^ HTML code (literal) + | Link [Inline] Target -- ^ Hyperlink: text (list of inlines) and target + | Image [Inline] Target -- ^ Image: alternative text (list of inlines) and target + | NoteRef String -- ^ Footnote or endnote reference + deriving (Show, Eq, Read) diff --git a/src/Text/Pandoc/HtmlEntities.hs b/src/Text/Pandoc/HtmlEntities.hs new file mode 100644 index 000000000..bbb438ef5 --- /dev/null +++ b/src/Text/Pandoc/HtmlEntities.hs @@ -0,0 +1,306 @@ +-- | Functions for encoding unicode characters as HTML entity +-- references, and vice versa. +module Text.Pandoc.HtmlEntities ( + htmlEntityToChar, + charToHtmlEntity, + decodeEntities, + encodeEntities + ) where +import Char ( chr, ord ) +import Text.Regex ( mkRegex, matchRegexAll ) +import Maybe ( fromMaybe ) + +-- regexs for entities +decimalCodedEntity = mkRegex "&#([0-9]+);" +characterEntity = mkRegex "&#[0-9]+;|&[A-Za-z0-9]+;" + +-- | Return a string with all entity references decoded to unicode characters +-- where possible. +decodeEntities :: String -> String +decodeEntities str = + case (matchRegexAll characterEntity str) of + Nothing -> str + Just (before, match, rest, _) -> before ++ replacement ++ (decodeEntities rest) + where replacement = case (htmlEntityToChar match) of + Just ch -> [ch] + Nothing -> match + +-- | Returns a string with characters replaced with entity references where possible. +encodeEntities :: String -> String +encodeEntities = concatMap (\c -> fromMaybe [c] (charToHtmlEntity c)) + +-- | If the string is a valid entity reference, returns @Just@ the character, +-- otherwise @Nothing@. +htmlEntityToChar :: String -> Maybe Char +htmlEntityToChar entity = + case (lookup entity htmlEntityTable) of + Just ch -> Just ch + Nothing -> case (matchRegexAll decimalCodedEntity entity) of + Just (_, _, _, [sub]) -> Just (chr (read sub)) + Nothing -> Nothing + +-- | If there is an entity reference corresponding to the character, returns +-- @Just@ the entity reference, otherwise @Nothing@. +charToHtmlEntity :: Char -> Maybe String +charToHtmlEntity char = + let matches = filter (\(entity, character) -> (character == char)) htmlEntityTable in + if (length matches) == 0 then + Nothing + else + Just (fst (head matches)) + +htmlEntityTable :: [(String, Char)] +htmlEntityTable = [ + (""", chr 34), + ("&", chr 38), + ("<", chr 60), + (">", chr 62), + (" ", chr 160), + ("¡", chr 161), + ("¢", chr 162), + ("£", chr 163), + ("¤", chr 164), + ("¥", chr 165), + ("¦", chr 166), + ("§", chr 167), + ("¨", chr 168), + ("©", chr 169), + ("ª", chr 170), + ("«", chr 171), + ("¬", chr 172), + ("­", chr 173), + ("®", chr 174), + ("¯", chr 175), + ("°", chr 176), + ("±", chr 177), + ("²", chr 178), + ("³", chr 179), + ("´", chr 180), + ("µ", chr 181), + ("¶", chr 182), + ("·", chr 183), + ("¸", chr 184), + ("¹", chr 185), + ("º", chr 186), + ("»", chr 187), + ("¼", chr 188), + ("½", chr 189), + ("¾", chr 190), + ("¿", chr 191), + ("À", chr 192), + ("Á", chr 193), + ("Â", chr 194), + ("Ã", chr 195), + ("Ä", chr 196), + ("Å", chr 197), + ("Æ", chr 198), + ("Ç", chr 199), + ("È", chr 200), + ("É", chr 201), + ("Ê", chr 202), + ("Ë", chr 203), + ("Ì", chr 204), + ("Í", chr 205), + ("Î", chr 206), + ("Ï", chr 207), + ("Ð", chr 208), + ("Ñ", chr 209), + ("Ò", chr 210), + ("Ó", chr 211), + ("Ô", chr 212), + ("Õ", chr 213), + ("Ö", chr 214), + ("×", chr 215), + ("Ø", chr 216), + ("Ù", chr 217), + ("Ú", chr 218), + ("Û", chr 219), + ("Ü", chr 220), + ("Ý", chr 221), + ("Þ", chr 222), + ("ß", chr 223), + ("à", chr 224), + ("á", chr 225), + ("â", chr 226), + ("ã", chr 227), + ("ä", chr 228), + ("å", chr 229), + ("æ", chr 230), + ("ç", chr 231), + ("è", chr 232), + ("é", chr 233), + ("ê", chr 234), + ("ë", chr 235), + ("ì", chr 236), + ("í", chr 237), + ("î", chr 238), + ("ï", chr 239), + ("ð", chr 240), + ("ñ", chr 241), + ("ò", chr 242), + ("ó", chr 243), + ("ô", chr 244), + ("õ", chr 245), + ("ö", chr 246), + ("÷", chr 247), + ("ø", chr 248), + ("ù", chr 249), + ("ú", chr 250), + ("û", chr 251), + ("ü", chr 252), + ("ý", chr 253), + ("þ", chr 254), + ("ÿ", chr 255), + ("Œ", chr 338), + ("œ", chr 339), + ("Š", chr 352), + ("š", chr 353), + ("Ÿ", chr 376), + ("ƒ", chr 402), + ("ˆ", chr 710), + ("˜", chr 732), + ("Α", chr 913), + ("Β", chr 914), + ("Γ", chr 915), + ("Δ", chr 916), + ("Ε", chr 917), + ("Ζ", chr 918), + ("Η", chr 919), + ("Θ", chr 920), + ("Ι", chr 921), + ("Κ", chr 922), + ("Λ", chr 923), + ("Μ", chr 924), + ("Ν", chr 925), + ("Ξ", chr 926), + ("Ο", chr 927), + ("Π", chr 928), + ("Ρ", chr 929), + ("Σ", chr 931), + ("Τ", chr 932), + ("Υ", chr 933), + ("Φ", chr 934), + ("Χ", chr 935), + ("Ψ", chr 936), + ("Ω", chr 937), + ("α", chr 945), + ("β", chr 946), + ("γ", chr 947), + ("δ", chr 948), + ("ε", chr 949), + ("ζ", chr 950), + ("η", chr 951), + ("θ", chr 952), + ("ι", chr 953), + ("κ", chr 954), + ("λ", chr 955), + ("μ", chr 956), + ("ν", chr 957), + ("ξ", chr 958), + ("ο", chr 959), + ("π", chr 960), + ("ρ", chr 961), + ("ς", chr 962), + ("σ", chr 963), + ("τ", chr 964), + ("υ", chr 965), + ("φ", chr 966), + ("χ", chr 967), + ("ψ", chr 968), + ("ω", chr 969), + ("ϑ", chr 977), + ("ϒ", chr 978), + ("ϖ", chr 982), + (" ", chr 8194), + (" ", chr 8195), + (" ", chr 8201), + ("‌", chr 8204), + ("‍", chr 8205), + ("‎", chr 8206), + ("‏", chr 8207), + ("–", chr 8211), + ("—", chr 8212), + ("‘", chr 8216), + ("’", chr 8217), + ("‚", chr 8218), + ("“", chr 8220), + ("”", chr 8221), + ("„", chr 8222), + ("†", chr 8224), + ("‡", chr 8225), + ("•", chr 8226), + ("…", chr 8230), + ("‰", chr 8240), + ("′", chr 8242), + ("″", chr 8243), + ("‹", chr 8249), + ("›", chr 8250), + ("‾", chr 8254), + ("⁄", chr 8260), + ("€", chr 8364), + ("ℑ", chr 8465), + ("℘", chr 8472), + ("ℜ", chr 8476), + ("™", chr 8482), + ("ℵ", chr 8501), + ("←", chr 8592), + ("↑", chr 8593), + ("→", chr 8594), + ("↓", chr 8595), + ("↔", chr 8596), + ("↵", chr 8629), + ("⇐", chr 8656), + ("⇑", chr 8657), + ("⇒", chr 8658), + ("⇓", chr 8659), + ("⇔", chr 8660), + ("∀", chr 8704), + ("∂", chr 8706), + ("∃", chr 8707), + ("∅", chr 8709), + ("∇", chr 8711), + ("∈", chr 8712), + ("∉", chr 8713), + ("∋", chr 8715), + ("∏", chr 8719), + ("∑", chr 8721), + ("−", chr 8722), + ("∗", chr 8727), + ("√", chr 8730), + ("∝", chr 8733), + ("∞", chr 8734), + ("∠", chr 8736), + ("∧", chr 8743), + ("∨", chr 8744), + ("∩", chr 8745), + ("∪", chr 8746), + ("∫", chr 8747), + ("∴", chr 8756), + ("∼", chr 8764), + ("≅", chr 8773), + ("≈", chr 8776), + ("≠", chr 8800), + ("≡", chr 8801), + ("≤", chr 8804), + ("≥", chr 8805), + ("⊂", chr 8834), + ("⊃", chr 8835), + ("⊄", chr 8836), + ("⊆", chr 8838), + ("⊇", chr 8839), + ("⊕", chr 8853), + ("⊗", chr 8855), + ("⊥", chr 8869), + ("⋅", chr 8901), + ("⌈", chr 8968), + ("⌉", chr 8969), + ("⌊", chr 8970), + ("⌋", chr 8971), + ("⟨", chr 9001), + ("⟩", chr 9002), + ("◊", chr 9674), + ("♠", chr 9824), + ("♣", chr 9827), + ("♥", chr 9829), + ("♦", chr 9830) + ] diff --git a/src/Text/Pandoc/Readers/HTML.hs b/src/Text/Pandoc/Readers/HTML.hs new file mode 100644 index 000000000..054d9eb72 --- /dev/null +++ b/src/Text/Pandoc/Readers/HTML.hs @@ -0,0 +1,434 @@ +-- | Converts HTML to 'Pandoc' document. +module Text.Pandoc.Readers.HTML ( + readHtml, + rawHtmlInline, + rawHtmlBlock, + anyHtmlBlockTag, + anyHtmlInlineTag + ) where + +import Text.Regex ( matchRegex, mkRegex ) +import Text.ParserCombinators.Parsec +import Text.ParserCombinators.Pandoc +import Text.Pandoc.Definition +import Text.Pandoc.Shared +import Text.Pandoc.HtmlEntities ( decodeEntities, htmlEntityToChar ) +import Maybe ( fromMaybe ) +import Char ( toUpper, toLower ) + +-- | Convert HTML-formatted string to 'Pandoc' document. +readHtml :: ParserState -- ^ Parser state + -> String -- ^ String to parse + -> Pandoc +readHtml = readWith parseHtml + +-- for testing +testString :: String -> IO () +testString = testStringWith parseHtml + +-- +-- Constants +-- + +inlineHtmlTags = ["a", "abbr", "acronym", "b", "basefont", "bdo", "big", "br", "cite", + "code", "dfn", "em", "font", "i", "img", "input", "kbd", "label", "q", + "s", "samp", "select", "small", "span", "strike", "strong", "sub", + "sup", "textarea", "tt", "u", "var"] + +-- +-- HTML utility functions +-- + +-- | Read blocks until end tag. +blocksTilEnd tag = try (do + blocks <- manyTill (do {b <- block; spaces; return b}) (htmlEndTag tag) + return blocks) + +-- | Read inlines until end tag. +inlinesTilEnd tag = try (do + inlines <- manyTill inline (htmlEndTag tag) + return inlines) + +-- extract type from a tag: e.g. br from <br>, < br >, </br>, etc. +extractTagType tag = case (matchRegex (mkRegex "<[[:space:]]*/?([A-Za-z0-9]+)") tag) of + Just [match] -> (map toLower match) + Nothing -> "" + +anyHtmlTag = try (do + char '<' + spaces + tag <- many1 alphaNum + attribs <- htmlAttributes + spaces + ender <- option "" (string "/") + let ender' = if (null ender) then "" else " /" + spaces + char '>' + return ("<" ++ tag ++ attribs ++ ender' ++ ">")) + +anyHtmlEndTag = try (do + char '<' + spaces + char '/' + spaces + tagType <- many1 alphaNum + spaces + char '>' + return ("</" ++ tagType ++ ">")) + +htmlTag :: String -> GenParser Char st (String, [(String, String)]) +htmlTag tag = try (do + char '<' + spaces + stringAnyCase tag + attribs <- many htmlAttribute + spaces + option "" (string "/") + spaces + char '>' + return (tag, (map (\(name, content, raw) -> (name, content)) attribs))) + +-- parses a quoted html attribute value +quoted quoteChar = do + result <- between (char quoteChar) (char quoteChar) (many (noneOf [quoteChar])) + return (result, [quoteChar]) + +htmlAttributes = do + attrList <- many htmlAttribute + return (concatMap (\(name, content, raw) -> raw) attrList) + +htmlAttribute = htmlRegularAttribute <|> htmlMinimizedAttribute + +-- minimized boolean attribute (no = and value) +htmlMinimizedAttribute = try (do + spaces + name <- many1 (choice [letter, oneOf ".-_:"]) + spaces + notFollowedBy (char '=') + let content = name + return (name, content, (" " ++ name))) + +htmlRegularAttribute = try (do + spaces + name <- many1 (choice [letter, oneOf ".-_:"]) + spaces + char '=' + spaces + (content, quoteStr) <- choice [ (quoted '\''), + (quoted '"'), + (do{ a <- (many (alphaNum <|> (oneOf "-._:"))); + return (a,"")} ) ] + return (name, content, (" " ++ name ++ "=" ++ quoteStr ++ content ++ quoteStr))) + +htmlEndTag tag = try (do + char '<' + spaces + char '/' + spaces + stringAnyCase tag + spaces + char '>' + return ("</" ++ tag ++ ">")) + +-- | Returns @True@ if the tag is an inline tag. +isInline tag = (extractTagType tag) `elem` inlineHtmlTags + +anyHtmlBlockTag = try (do + tag <- choice [anyHtmlTag, anyHtmlEndTag] + if isInline tag then + fail "inline tag" + else + return tag) + +anyHtmlInlineTag = try (do + tag <- choice [ anyHtmlTag, anyHtmlEndTag ] + if isInline tag then + return tag + else + fail "not an inline tag") + +-- scripts must be treated differently, because they can contain <> etc. +htmlScript = try (do + open <- string "<script" + rest <- manyTill anyChar (htmlEndTag "script") + return (open ++ rest ++ "</script>")) + +rawHtmlBlock = do + notFollowedBy (do {choice [htmlTag "/body", htmlTag "/html"]; return ' '}) + body <- choice [htmlScript, anyHtmlBlockTag, htmlComment, xmlDec, definition] + sp <- (many space) + state <- getState + if stateParseRaw state then + return (RawHtml (body ++ sp)) + else + return Null + +htmlComment = try (do + string "<!--" + comment <- manyTill anyChar (try (string "-->")) + return ("<!--" ++ comment ++ "-->")) + +-- +-- parsing documents +-- + +xmlDec = try (do + string "<?" + rest <- manyTill anyChar (char '>') + return ("<?" ++ rest ++ ">")) + +definition = try (do + string "<!" + rest <- manyTill anyChar (char '>') + return ("<!" ++ rest ++ ">")) + +nonTitleNonHead = try (do + notFollowedBy' (htmlTag "title") + notFollowedBy' (htmlTag "/head") + result <- choice [do {rawHtmlBlock; return ' '}, anyChar] + return result) + +parseTitle = try (do + (tag, attribs) <- htmlTag "title" + contents <- inlinesTilEnd tag + spaces + return contents) + +-- parse header and return meta-information (for now, just title) +parseHead = try (do + htmlTag "head" + spaces + skipMany nonTitleNonHead + contents <- option [] parseTitle + skipMany nonTitleNonHead + htmlTag "/head" + return (contents, [], "")) + +skipHtmlTag tag = option ("",[]) (htmlTag tag) + +-- h1 class="title" representation of title in body +bodyTitle = try (do + (tag, attribs) <- htmlTag "h1" + cl <- case (extractAttribute "class" attribs) of + Just "title" -> do {return ""} + otherwise -> fail "not title" + inlinesTilEnd "h1" + return "") + +parseHtml = do + sepEndBy (choice [xmlDec, definition, htmlComment]) spaces + skipHtmlTag "html" + spaces + (title, authors, date) <- option ([], [], "") parseHead + spaces + skipHtmlTag "body" + spaces + option "" bodyTitle -- skip title in body, because it's represented in meta + blocks <- parseBlocks + spaces + option "" (htmlEndTag "body") + spaces + option "" (htmlEndTag "html") + many anyChar -- ignore anything after </html> + eof + state <- getState + let keyBlocks = stateKeyBlocks state + return (Pandoc (Meta title authors date) (blocks ++ (reverse keyBlocks))) + +-- +-- parsing blocks +-- + +parseBlocks = do + spaces + result <- sepEndBy block spaces + return result + +block = choice [ codeBlock, header, hrule, list, blockQuote, para, plain, + rawHtmlBlock ] <?> "block" + +-- +-- header blocks +-- + +header = choice (map headerLevel (enumFromTo 1 5)) <?> "header" + +headerLevel n = try (do + let level = "h" ++ show n + (tag, attribs) <- htmlTag level + contents <- inlinesTilEnd level + return (Header n (normalizeSpaces contents))) + +-- +-- hrule block +-- + +hrule = try (do + (tag, attribs) <- htmlTag "hr" + state <- getState + if (not (null attribs)) && (stateParseRaw state) then + unexpected "attributes in hr" -- in this case we want to parse it as raw html + else + return HorizontalRule) + +-- +-- code blocks +-- + +codeBlock = choice [ preCodeBlock, bareCodeBlock ] <?> "code block" + +preCodeBlock = try (do + htmlTag "pre" + spaces + htmlTag "code" + result <- manyTill anyChar (htmlEndTag "code") + spaces + htmlEndTag "pre" + return (CodeBlock (decodeEntities result))) + +bareCodeBlock = try (do + htmlTag "code" + result <- manyTill anyChar (htmlEndTag "code") + return (CodeBlock (decodeEntities result))) + +-- +-- block quotes +-- + +blockQuote = try (do + tag <- htmlTag "blockquote" + spaces + blocks <- blocksTilEnd "blockquote" + return (BlockQuote blocks)) + +-- +-- list blocks +-- + +list = choice [ bulletList, orderedList ] <?> "list" + +orderedList = try (do + tag <- htmlTag "ol" + spaces + items <- sepEndBy1 listItem spaces + htmlEndTag "ol" + return (OrderedList items)) + +bulletList = try (do + tag <- htmlTag "ul" + spaces + items <- sepEndBy1 listItem spaces + htmlEndTag "ul" + return (BulletList items)) + +listItem = try (do + tag <- htmlTag "li" + spaces + blocks <- blocksTilEnd "li" + return blocks) + +-- +-- paragraph block +-- + +para = try (do + tag <- htmlTag "p" + result <- inlinesTilEnd "p" + return (Para (normalizeSpaces result))) + +-- +-- plain block +-- + +plain = do + result <- many1 inline + return (Plain (normalizeSpaces result)) + +-- +-- inline +-- + +inline = choice [ text, special ] <?> "inline" + +text = choice [ entity, strong, emph, code, str, linebreak, whitespace ] <?> "text" + +special = choice [ link, image, rawHtmlInline ] <?> "link, inline html, or image" + +entity = try (do + char '&' + body <- choice [(many1 letter), + (try (do{ char '#'; num <- many1 digit; return ("#" ++ num)}))] + char ';' + return (Str [fromMaybe '?' (htmlEntityToChar ("&" ++ body ++ ";"))])) + +code = try (do + htmlTag "code" + result <- manyTill anyChar (htmlEndTag "code") + -- remove internal line breaks, leading and trailing space, and decode entities + let result' = decodeEntities $ removeLeadingTrailingSpace $ joinWithSep " " $ lines result + return (Code result')) + +rawHtmlInline = do + result <- choice [htmlScript, anyHtmlInlineTag] + state <- getState + if stateParseRaw state then + return (HtmlInline result) + else + return (Str "") + +betweenTags tag = try (do + htmlTag tag + result <- inlinesTilEnd tag + return (normalizeSpaces result)) + +emph = try (do + result <- choice [betweenTags "em", betweenTags "it"] + return (Emph result)) + +strong = try (do + result <- choice [betweenTags "b", betweenTags "strong"] + return (Strong result)) + +whitespace = do + many1 space + return Space + +-- hard line break +linebreak = do + htmlTag "br" + return LineBreak + +str = do + result <- many1 (noneOf "<& \t\n") + return (Str (decodeEntities result)) + +-- +-- links and images +-- + +-- extract contents of attribute (attribute names are case-insensitive) +extractAttribute name [] = Nothing +extractAttribute name ((attrName, contents):rest) = + let name' = map toLower name + attrName' = map toLower attrName in + if (attrName' == name') then Just contents else extractAttribute name rest + +link = try (do + (tag, attributes) <- htmlTag "a" + url <- case (extractAttribute "href" attributes) of + Just url -> do {return url} + Nothing -> fail "no href" + let title = fromMaybe "" (extractAttribute "title" attributes) + label <- inlinesTilEnd "a" + ref <- generateReference url title + return (Link (normalizeSpaces label) ref)) + +image = try (do + (tag, attributes) <- htmlTag "img" + url <- case (extractAttribute "src" attributes) of + Just url -> do {return url} + Nothing -> fail "no src" + let title = fromMaybe "" (extractAttribute "title" attributes) + let alt = fromMaybe "" (extractAttribute "alt" attributes) + ref <- generateReference url title + return (Image [Str alt] ref)) diff --git a/src/Text/Pandoc/Readers/LaTeX.hs b/src/Text/Pandoc/Readers/LaTeX.hs new file mode 100644 index 000000000..3bf3dfd23 --- /dev/null +++ b/src/Text/Pandoc/Readers/LaTeX.hs @@ -0,0 +1,585 @@ +-- | Converts LaTeX to 'Pandoc' document. +module Text.Pandoc.Readers.LaTeX ( + readLaTeX, + rawLaTeXInline, + rawLaTeXEnvironment + ) where + +import Text.ParserCombinators.Parsec +import Text.ParserCombinators.Pandoc +import Text.Pandoc.Definition +import Text.Pandoc.Shared +import Maybe ( fromMaybe ) +import Char ( chr ) + +-- | Parse LaTeX from string and return 'Pandoc' document. +readLaTeX :: ParserState -- ^ Parser state, including options for parser + -> String -- ^ String to parse + -> Pandoc +readLaTeX = readWith parseLaTeX + +-- for testing +testString = testStringWith parseLaTeX + +-- characters with special meaning +specialChars = "\\$%&^&_~#{}\n \t|<>" + +-- +-- utility functions +-- + +-- | Change quotation marks in a string back to "basic" quotes. +normalizeQuotes :: String -> String +normalizeQuotes = gsub "''" "\"" . gsub "`" "'" + +-- | Change LaTeX En dashes between digits to hyphens. +normalizeDashes :: String -> String +normalizeDashes = gsub "([0-9])--([0-9])" "\\1-\\2" + +normalizePunctuation :: String -> String +normalizePunctuation = normalizeDashes . normalizeQuotes + +-- | Returns command option (between []) if any, or empty string. +commandOpt = option "" (between (char '[') (char ']') (many1 (noneOf "]"))) + +-- | Returns text between brackets and its matching pair. +bracketedText = try (do + char '{' + result <- many (choice [ try (do{ char '\\'; + b <- oneOf "{}"; + return (['\\', b])}), -- escaped bracket + count 1 (noneOf "{}"), + do {text <- bracketedText; return ("{" ++ text ++ "}")} ]) + char '}' + return (concat result)) + +-- | Parses list of arguments of LaTeX command. +commandArgs = many bracketedText + +-- | Parses LaTeX command, returns (name, star, option, list of arguments). +command = try (do + char '\\' + name <- many1 alphaNum + star <- option "" (string "*") -- some commands have starred versions + opt <- commandOpt + args <- commandArgs + return (name, star, opt, args)) + +begin name = try (do + string "\\begin{" + string name + char '}' + option "" commandOpt + option [] commandArgs + spaces + return name) + +end name = try (do + string "\\end{" + string name + char '}' + spaces + return name) + +-- | Returns a list of block elements containing the contents of an environment. +environment name = try (do + begin name + spaces + contents <- manyTill block (end name) + return contents) + +anyEnvironment = try (do + string "\\begin{" + name <- many alphaNum + star <- option "" (string "*") -- some environments have starred variants + char '}' + option "" commandOpt + option [] commandArgs + spaces + contents <- manyTill block (end (name ++ star)) + return (BlockQuote contents)) + +-- +-- parsing documents +-- + +-- | Skip everything up through \begin{document} +skipLaTeXHeader = try (do + manyTill anyChar (begin "document") + spaces + return "") + +-- | Parse LaTeX and return 'Pandoc'. +parseLaTeX = do + option "" skipLaTeXHeader -- if parsing a fragment, this might not be present + blocks <- parseBlocks + spaces + option "" (string "\\end{document}") -- if parsing a fragment, this might not be present + spaces + eof + state <- getState + let keyBlocks = stateKeyBlocks state + let noteBlocks = stateNoteBlocks state + let blocks' = filter (/= Null) blocks + return (Pandoc (Meta [] [] "") (blocks' ++ (reverse noteBlocks) ++ (reverse keyBlocks))) + +-- +-- parsing blocks +-- + +parseBlocks = do + spaces + result <- many block + return result + +block = choice [ hrule, codeBlock, header, list, blockQuote, mathBlock, comment, + bibliographic, para, specialEnvironment, itemBlock, unknownEnvironment, + unknownCommand ] <?> "block" + +-- +-- header blocks +-- + +header = choice (map headerLevel (enumFromTo 1 5)) <?> "header" + +headerLevel n = try (do + let subs = concat $ replicate (n - 1) "sub" + string ("\\" ++ subs ++ "section") + option ' ' (char '*') + char '{' + title <- manyTill inline (char '}') + spaces + return (Header n (normalizeSpaces title))) + +-- +-- hrule block +-- + +hrule = try (do + oneOfStrings [ "\\begin{center}\\rule{3in}{0.4pt}\\end{center}\n\n", "\\newpage" ] + spaces + return HorizontalRule) + +-- +-- code blocks +-- + +codeBlock = try (do + string "\\begin{verbatim}" -- don't use begin function because it gobbles whitespace + option "" blanklines -- we want to gobble blank lines, but not leading space + contents <- manyTill anyChar (try (string "\\end{verbatim}")) + spaces + return (CodeBlock (stripTrailingNewlines contents))) + +-- +-- block quotes +-- + +blockQuote = choice [ blockQuote1, blockQuote2 ] <?> "blockquote" + +blockQuote1 = try (do + blocks <- environment "quote" + spaces + return (BlockQuote blocks)) + +blockQuote2 = try (do + blocks <- environment "quotation" + spaces + return (BlockQuote blocks)) + +-- +-- math block +-- + +mathBlock = mathBlockWith (begin "equation") (end "equation") <|> + mathBlockWith (begin "displaymath") (end "displaymath") <|> + mathBlockWith (string "\\[") (string "\\]") <?> "math block" + +mathBlockWith start end = try (do + start + spaces + result <- manyTill anyChar end + spaces + return (BlockQuote [Para [TeX ("$" ++ result ++ "$")]])) + +-- +-- list blocks +-- + +list = bulletList <|> orderedList <?> "list" + +listItem = try (do + ("item", _, _, _) <- command + spaces + state <- getState + let oldParserContext = stateParserContext state + updateState (\state -> state {stateParserContext = ListItemState}) + blocks <- many block + updateState (\state -> state {stateParserContext = oldParserContext}) + return blocks) + +orderedList = try (do + begin "enumerate" + spaces + items <- many listItem + end "enumerate" + spaces + return (OrderedList items)) + +bulletList = try (do + begin "itemize" + spaces + items <- many listItem + end "itemize" + spaces + return (BulletList items)) + +-- +-- paragraph block +-- + +para = try (do + result <- many1 inline + spaces + return (Para (normalizeSpaces result))) + +-- +-- title authors date +-- + +bibliographic = choice [ maketitle, title, authors, date ] + +maketitle = try (do + string "\\maketitle" + spaces + return Null) + +title = try (do + string "\\title{" + tit <- manyTill inline (char '}') + spaces + updateState (\state -> state { stateTitle = tit }) + return Null) + +authors = try (do + string "\\author{" + authors <- manyTill anyChar (char '}') + spaces + let authors' = map removeLeadingTrailingSpace $ lines $ gsub "\\\\" "\n" authors + updateState (\state -> state { stateAuthors = authors' }) + return Null) + +date = try (do + string "\\date{" + date' <- manyTill anyChar (char '}') + spaces + updateState (\state -> state { stateDate = date' }) + return Null) + +-- +-- item block +-- for use in unknown environments that aren't being parsed as raw latex +-- + +-- this forces items to be parsed in different blocks +itemBlock = try (do + ("item", _, opt, _) <- command + state <- getState + if (stateParserContext state == ListItemState) then + fail "item should be handled by list block" + else + if null opt then + return Null + else + return (Plain [Str opt])) + +-- +-- raw LaTeX +-- + +specialEnvironment = do -- these are always parsed as raw + followedBy' (choice (map (\name -> begin name) ["tabular", "figure", "tabbing", "eqnarry", + "picture", "table", "verse", "theorem"])) + rawLaTeXEnvironment + +-- | Parse any LaTeX environment and return a Para block containing +-- the whole literal environment as raw TeX. +rawLaTeXEnvironment :: GenParser Char st Block +rawLaTeXEnvironment = try (do + string "\\begin" + char '{' + name <- many1 alphaNum + star <- option "" (string "*") -- for starred variants + let name' = name ++ star + char '}' + opt <- option "" commandOpt + args <- option [] commandArgs + let optStr = if (null opt) then "" else "[" ++ opt ++ "]" + let argStr = concatMap (\arg -> ("{" ++ arg ++ "}")) args + contents <- manyTill (choice [(many1 (noneOf "\\")), + (do{ (Para [TeX str]) <- rawLaTeXEnvironment; return str }), + string "\\"]) (end name') + spaces + return (Para [TeX ("\\begin{" ++ name' ++ "}" ++ optStr ++ argStr ++ + (concat contents) ++ "\\end{" ++ name' ++ "}")])) + +unknownEnvironment = try (do + state <- getState + result <- if stateParseRaw state then -- check to see whether we should include raw TeX + rawLaTeXEnvironment -- if so, get the whole raw environment + else + anyEnvironment -- otherwise just the contents + return result) + +unknownCommand = try (do + notFollowedBy' (string "\\end{itemize}") + notFollowedBy' (string "\\end{enumerate}") + notFollowedBy' (string "\\end{document}") + (name, star, opt, args) <- command + spaces + let optStr = if null opt then "" else "[" ++ opt ++ "]" + let argStr = concatMap (\arg -> ("{" ++ arg ++ "}")) args + state <- getState + if (name == "item") && ((stateParserContext state) == ListItemState) then + fail "should not be parsed as raw" + else + string "" + if stateParseRaw state then + return (Plain [TeX ("\\" ++ name ++ star ++ optStr ++ argStr)]) + else + return (Plain [Str (joinWithSep " " args)])) + +-- latex comment +comment = try (do + char '%' + result <- manyTill anyChar newline + spaces + return Null) + +-- +-- inline +-- + +inline = choice [ strong, emph, ref, lab, code, linebreak, math, ldots, accentedChar, + specialChar, specialInline, escapedChar, unescapedChar, str, + endline, whitespace ] <?> "inline" + +specialInline = choice [ link, image, footnote, rawLaTeXInline ] <?> + "link, raw TeX, note, or image" + +ldots = try (do + string "\\ldots" + return (Str "...")) + +accentedChar = normalAccentedChar <|> specialAccentedChar + +normalAccentedChar = try (do + char '\\' + accent <- oneOf "'`^\"~" + character <- choice [ between (char '{') (char '}') anyChar, anyChar ] + let table = fromMaybe [] $ lookup character accentTable + let result = case lookup accent table of + Just num -> chr num + Nothing -> '?' + return (Str [result])) + +-- an association list of letters and association list of accents +-- and decimal character numbers. +accentTable = + [ ('A', [('`', 192), ('\'', 193), ('^', 194), ('~', 195), ('"', 196)]), + ('E', [('`', 200), ('\'', 201), ('^', 202), ('"', 203)]), + ('I', [('`', 204), ('\'', 205), ('^', 206), ('"', 207)]), + ('N', [('~', 209)]), + ('O', [('`', 210), ('\'', 211), ('^', 212), ('~', 213), ('"', 214)]), + ('U', [('`', 217), ('\'', 218), ('^', 219), ('"', 220)]), + ('a', [('`', 224), ('\'', 225), ('^', 227), ('"', 228)]), + ('e', [('`', 232), ('\'', 233), ('^', 234), ('"', 235)]), + ('i', [('`', 236), ('\'', 237), ('^', 238), ('"', 239)]), + ('n', [('~', 241)]), + ('o', [('`', 242), ('\'', 243), ('^', 244), ('~', 245), ('"', 246)]), + ('u', [('`', 249), ('\'', 250), ('^', 251), ('"', 252)]) ] + +specialAccentedChar = choice [ ccedil, aring, iuml, szlig, aelig, oslash, pound, + euro, copyright, sect ] + +ccedil = try (do + char '\\' + letter <- choice [try (string "cc"), try (string "cC")] + let num = if letter == "cc" then 231 else 199 + return (Str [chr num])) + +aring = try (do + char '\\' + letter <- choice [try (string "aa"), try (string "AA")] + let num = if letter == "aa" then 229 else 197 + return (Str [chr num])) + +iuml = try (do + string "\\\"" + choice [try (string "\\i"), try (string "{\\i}")] + return (Str [chr 239])) + +icirc = try (do + string "\\^" + choice [try (string "\\i"), try (string "{\\i}")] + return (Str [chr 238])) + +szlig = try (do + string "\\ss" + return (Str [chr 223])) + +oslash = try (do + char '\\' + letter <- choice [char 'o', char 'O'] + let num = if letter == 'o' then 248 else 216 + return (Str [chr num])) + +aelig = try (do + char '\\' + letter <- choice [try (string "ae"), try (string "AE")] + let num = if letter == "ae" then 230 else 198 + return (Str [chr num])) + +pound = try (do + string "\\pounds" + return (Str [chr 163])) + +euro = try (do + string "\\euro" + return (Str [chr 8364])) + +copyright = try (do + string "\\copyright" + return (Str [chr 169])) + +sect = try (do + string "\\S" + return (Str [chr 167])) + +escapedChar = escaped (oneOf " $%^&_#{}") + +unescapedChar = do -- ignore standalone, nonescaped special characters + oneOf "$^&_#{}|<>" + return (Str "") + +specialChar = choice [ backslash, bar, lt, gt ] + +backslash = try (do + string "\\textbackslash" + return (Str "\\")) + +bar = try (do + string "\\textbar" + return (Str "\\")) + +lt = try (do + string "\\textless" + return (Str "<")) + +gt = try (do + string "\\textgreater" + return (Str ">")) + +code = try (do + string "\\verb" + marker <- anyChar + result <- manyTill anyChar (char marker) + let result' = removeLeadingTrailingSpace result + return (Code result')) + +emph = try (do + oneOfStrings [ "\\emph{", "\\textit{" ] + result <- manyTill inline (char '}') + return (Emph result)) + +lab = try (do + string "\\label{" + result <- manyTill anyChar (char '}') + return (Str ("(" ++ result ++ ")"))) + +ref = try (do + string "\\ref{" + result <- manyTill anyChar (char '}') + return (Str (result))) + +strong = try (do + string "\\textbf{" + result <- manyTill inline (char '}') + return (Strong result)) + +whitespace = do + many1 (oneOf "~ \t") + return Space + +-- hard line break +linebreak = try (do + string "\\\\" + return LineBreak) + +str = do + result <- many1 (noneOf specialChars) + return (Str (normalizePunctuation result)) + +-- endline internal to paragraph +endline = try (do + newline + notFollowedBy blankline + return Space) + +-- math +math = math1 <|> math2 <?> "math" + +math1 = try (do + char '$' + result <- many (noneOf "$") + char '$' + return (TeX ("$" ++ result ++ "$"))) + +math2 = try (do + string "\\(" + result <- many (noneOf "$") + string "\\)" + return (TeX ("$" ++ result ++ "$"))) + +-- +-- links and images +-- + +link = try (do + string "\\href{" + url <- manyTill anyChar (char '}') + char '{' + label <- manyTill inline (char '}') + ref <- generateReference url "" + return (Link (normalizeSpaces label) ref)) + +image = try (do + ("includegraphics", _, _, (src:lst)) <- command + return (Image [Str "image"] (Src src ""))) + +footnote = try (do + ("footnote", _, _, (contents:[])) <- command + let blocks = case runParser parseBlocks defaultParserState "footnote" contents of + Left err -> error $ "Input:\n" ++ show contents ++ + "\nError:\n" ++ show err + Right result -> result + state <- getState + let notes = stateNoteBlocks state + let nextRef = case notes of + [] -> "1" + (Note ref body):rest -> (show ((read ref) + 1)) + setState (state { stateNoteBlocks = (Note nextRef blocks):notes }) + return (NoteRef nextRef)) + +-- | Parse any LaTeX command and return it in a raw TeX inline element. +rawLaTeXInline :: GenParser Char ParserState Inline +rawLaTeXInline = try (do + (name, star, opt, args) <- command + let optStr = if (null opt) then "" else "[" ++ opt ++ "]" + let argStr = concatMap (\arg -> "{" ++ arg ++ "}") args + state <- getState + if ((name == "begin") || (name == "end") || (name == "item")) then + fail "not an inline command" + else + string "" + return (TeX ("\\" ++ name ++ star ++ optStr ++ argStr))) diff --git a/src/Text/Pandoc/Readers/Markdown.hs b/src/Text/Pandoc/Readers/Markdown.hs new file mode 100644 index 000000000..60ac40fd7 --- /dev/null +++ b/src/Text/Pandoc/Readers/Markdown.hs @@ -0,0 +1,582 @@ +-- | Convert markdown to Pandoc document. +module Text.Pandoc.Readers.Markdown ( + readMarkdown + ) where + +import Text.ParserCombinators.Pandoc +import Text.Pandoc.Definition +import Text.Pandoc.Readers.LaTeX ( rawLaTeXInline, rawLaTeXEnvironment ) +import Text.Pandoc.Shared +import Text.Pandoc.Readers.HTML ( rawHtmlInline, rawHtmlBlock, anyHtmlBlockTag, + anyHtmlInlineTag ) +import Text.Pandoc.HtmlEntities ( decodeEntities ) +import Text.Regex ( matchRegex, mkRegex ) +import Text.ParserCombinators.Parsec + +-- | Read markdown from an input string and return a Pandoc document. +readMarkdown :: ParserState -> String -> Pandoc +readMarkdown = readWith parseMarkdown + +-- | Parse markdown string with default options and print result (for testing). +testString :: String -> IO () +testString = testStringWith parseMarkdown + +-- +-- Constants and data structure definitions +-- + +spaceChars = " \t" +endLineChars = "\n" +labelStart = '[' +labelEnd = ']' +labelSep = ':' +srcStart = '(' +srcEnd = ')' +imageStart = '!' +noteStart = '^' +codeStart = '`' +codeEnd = '`' +emphStart = '*' +emphEnd = '*' +emphStartAlt = '_' +emphEndAlt = '_' +autoLinkStart = '<' +autoLinkEnd = '>' +mathStart = '$' +mathEnd = '$' +bulletListMarkers = "*+-" +orderedListDelimiters = "." +escapeChar = '\\' +hruleChars = "*-_" +quoteChars = "'\"" +atxHChar = '#' +titleOpeners = "\"'(" +setextHChars = ['=','-'] +blockQuoteChar = '>' +hyphenChar = '-' + +-- treat these as potentially non-text when parsing inline: +specialChars = [escapeChar, labelStart, labelEnd, emphStart, emphEnd, emphStartAlt, + emphEndAlt, codeStart, codeEnd, autoLinkEnd, autoLinkStart, mathStart, + mathEnd, imageStart, noteStart, hyphenChar] + +-- +-- auxiliary functions +-- + +-- | Skip a single endline if there is one. +skipEndline = option Space endline + +indentSpaces = do + state <- getState + let tabStop = stateTabStop state + oneOfStrings [ "\t", (replicate tabStop ' ') ] <?> "indentation" + +skipNonindentSpaces = do + state <- getState + let tabStop = stateTabStop state + choice (map (\n -> (try (count n (char ' ')))) (reverse [0..(tabStop - 1)])) + +-- +-- document structure +-- + +titleLine = try (do + char '%' + skipSpaces + line <- manyTill inline newline + return line) + +authorsLine = try (do + char '%' + skipSpaces + authors <- sepEndBy (many1 (noneOf ",;\n")) (oneOf ",;") + newline + return (map removeLeadingTrailingSpace authors)) + +dateLine = try (do + char '%' + skipSpaces + date <- many (noneOf "\n") + newline + return (removeTrailingSpace date)) + +titleBlock = try (do + title <- option [] titleLine + author <- option [] authorsLine + date <- option "" dateLine + option "" blanklines + return (title, author, date)) + +parseMarkdown = do + updateState (\state -> state { stateParseRaw = True }) -- need to parse raw HTML + (title, author, date) <- option ([],[],"") titleBlock + blocks <- parseBlocks + state <- getState + let keys = reverse $ stateKeyBlocks state + return (Pandoc (Meta title author date) (blocks ++ keys)) + +-- +-- parsing blocks +-- + +parseBlocks = do + result <- manyTill block eof + return result + +block = choice [ codeBlock, referenceKey, note, header, hrule, list, blockQuote, rawHtmlBlocks, + rawLaTeXEnvironment, para, plain, blankBlock, nullBlock ] <?> "block" + +-- +-- header blocks +-- + +header = choice [ setextHeader, atxHeader ] <?> "header" + +atxHeader = try (do + lead <- many1 (char atxHChar) + skipSpaces + txt <- many1 (do {notFollowedBy' atxClosing; inline}) + atxClosing + return (Header (length lead) (normalizeSpaces txt))) + +atxClosing = try (do + skipMany (char atxHChar) + skipSpaces + newline + option "" blanklines) + +setextHeader = choice (map (\x -> setextH x) (enumFromTo 1 (length setextHChars))) + +setextH n = try (do + txt <- many1 (do {notFollowedBy newline; inline}) + endline + many1 (char (setextHChars !! (n-1))) + skipSpaces + newline + option "" blanklines + return (Header n (normalizeSpaces txt))) + +-- +-- hrule block +-- + +hruleWith chr = + try (do + skipSpaces + char chr + skipSpaces + char chr + skipSpaces + char chr + skipMany (oneOf (chr:spaceChars)) + newline + option "" blanklines + return HorizontalRule) + +hrule = choice (map hruleWith hruleChars) <?> "hrule" + +-- +-- code blocks +-- + +indentedLine = try (do + indentSpaces + result <- manyTill anyChar newline + return (result ++ "\n")) + +-- two or more indented lines, possibly separated by blank lines +indentedBlock = try (do + res1 <- indentedLine + blanks <- many blankline + res2 <- choice [indentedBlock, indentedLine] + return (res1 ++ blanks ++ res2)) + +codeBlock = do + result <- choice [indentedBlock, indentedLine] + option "" blanklines + return (CodeBlock result) + +-- +-- note block +-- + +note = try (do + (NoteRef ref) <- noteRef + skipSpaces + raw <- sepBy (many (choice [nonEndline, + (try (do {endline; notFollowedBy (char noteStart); return '\n'})) + ])) (try (do {newline; char noteStart; option ' ' (char ' ')})) + newline + blanklines + -- parse the extracted block, which may contain various block elements: + state <- getState + let parsed = case runParser parseBlocks (state {stateParserContext = BlockQuoteState}) "block" ((joinWithSep "\n" raw) ++ "\n\n") of + Left err -> error $ "Raw block:\n" ++ show raw ++ "\nError:\n" ++ show err + Right result -> result + return (Note ref parsed)) + +-- +-- block quotes +-- + +emacsBoxQuote = try (do + string ",----" + manyTill anyChar newline + raw <- manyTill (try (do{ char '|'; + option ' ' (char ' '); + result <- manyTill anyChar newline; + return result})) + (string "`----") + manyTill anyChar newline + option "" blanklines + return raw) + +emailBlockQuoteStart = try (do + skipNonindentSpaces + char blockQuoteChar + option ' ' (char ' ') + return "> ") + +emailBlockQuote = try (do + emailBlockQuoteStart + raw <- sepBy (many (choice [nonEndline, + (try (do{ endline; + notFollowedBy' emailBlockQuoteStart; + return '\n'}))])) + (try (do {newline; emailBlockQuoteStart})) + newline <|> (do{ eof; return '\n'}) + option "" blanklines + return raw) + +blockQuote = do + raw <- choice [ emailBlockQuote, emacsBoxQuote ] + -- parse the extracted block, which may contain various block elements: + state <- getState + let parsed = case runParser parseBlocks (state {stateParserContext = BlockQuoteState}) "block" ((joinWithSep "\n" raw) ++ "\n\n") of + Left err -> error $ "Raw block:\n" ++ show raw ++ "\nError:\n" ++ show err + Right result -> result + return (BlockQuote parsed) + +-- +-- list blocks +-- + +list = choice [ bulletList, orderedList ] <?> "list" + +bulletListStart = + try (do + option ' ' newline -- if preceded by a Plain block in a list context + skipNonindentSpaces + notFollowedBy' hrule -- because hrules start out just like lists + oneOf bulletListMarkers + spaceChar + skipSpaces) + +orderedListStart = + try (do + option ' ' newline -- if preceded by a Plain block in a list context + skipNonindentSpaces + many1 digit + oneOf orderedListDelimiters + oneOf spaceChars + skipSpaces) + +-- parse a line of a list item (start = parser for beginning of list item) +listLine start = try (do + notFollowedBy' start + notFollowedBy blankline + notFollowedBy' (try (do{ indentSpaces; + many (spaceChar); + choice [bulletListStart, orderedListStart]})) + line <- manyTill anyChar newline + return (line ++ "\n")) + +-- parse raw text for one list item, excluding start marker and continuations +rawListItem start = + try (do + start + result <- many1 (listLine start) + blanks <- many blankline + return ((concat result) ++ blanks)) + +-- continuation of a list item - indented and separated by blankline +-- or (in compact lists) endline. +-- note: nested lists are parsed as continuations +listContinuation start = + try (do + followedBy' indentSpaces + result <- many1 (listContinuationLine start) + blanks <- many blankline + return ((concat result) ++ blanks)) + +listContinuationLine start = try (do + notFollowedBy blankline + notFollowedBy' start + option "" indentSpaces + result <- manyTill anyChar newline + return (result ++ "\n")) + +listItem start = + try (do + first <- rawListItem start + rest <- many (listContinuation start) + -- parsing with ListItemState forces markers at beginning of lines to + -- count as list item markers, even if not separated by blank space. + -- see definition of "endline" + state <- getState + let parsed = case runParser parseBlocks (state {stateParserContext = ListItemState}) + "block" raw of + Left err -> error $ "Raw block:\n" ++ raw ++ "\nError:\n" ++ show err + Right result -> result + where raw = concat (first:rest) + return parsed) + +orderedList = + try (do + items <- many1 (listItem orderedListStart) + let items' = compactify items + return (OrderedList items')) + +bulletList = + try (do + items <- many1 (listItem bulletListStart) + let items' = compactify items + return (BulletList items')) + +-- +-- paragraph block +-- + +para = try (do + result <- many1 inline + newline + choice [ (do{ followedBy' (oneOfStrings [">", ",----"]); return "" }), blanklines ] + let result' = normalizeSpaces result + return (Para result')) + +plain = do + result <- many1 inline + let result' = normalizeSpaces result + return (Plain result') + +-- +-- raw html +-- + +rawHtmlBlocks = try (do + htmlBlocks <- many1 rawHtmlBlock + let combined = concatMap (\(RawHtml str) -> str) htmlBlocks + let combined' = if (last combined == '\n') then + init combined -- strip extra newline + else + combined + return (RawHtml combined')) + +-- +-- reference key +-- + +referenceKey = + try (do + skipSpaces + label <- reference + char labelSep + skipSpaces + option ' ' (char autoLinkStart) + src <- many (noneOf (titleOpeners ++ [autoLinkEnd] ++ endLineChars)) + option ' ' (char autoLinkEnd) + tit <- option "" title + blanklines + return (Key label (Src (removeTrailingSpace src) tit))) + +-- +-- inline +-- + +text = choice [ math, strong, emph, code2, code1, str, linebreak, tabchar, + whitespace, endline ] <?> "text" + +inline = choice [ rawLaTeXInline, escapedChar, special, hyphens, text, ltSign, symbol ] <?> "inline" + +special = choice [ link, referenceLink, rawHtmlInline, autoLink, + image, noteRef ] <?> "link, inline html, note, or image" + +escapedChar = escaped anyChar + +ltSign = do + notFollowedBy' rawHtmlBlocks -- don't return < if it starts html + char '<' + return (Str ['<']) + +specialCharsMinusLt = filter (/= '<') specialChars + +symbol = do + result <- oneOf specialCharsMinusLt + return (Str [result]) + +hyphens = try (do + result <- many1 (char '-') + if (length result) == 1 then + skipEndline -- don't want to treat endline after hyphen as a space + else + do{ string ""; return Space } + return (Str result)) + +-- parses inline code, between codeStart and codeEnd +code1 = + try (do + char codeStart + result <- many (noneOf [codeEnd]) + char codeEnd + let result' = removeLeadingTrailingSpace $ joinWithSep " " $ lines result -- get rid of any internal newlines + return (Code result')) + +-- parses inline code, between 2 codeStarts and 2 codeEnds +code2 = + try (do + string [codeStart, codeStart] + result <- manyTill anyChar (try (string [codeEnd, codeEnd])) + let result' = removeLeadingTrailingSpace $ joinWithSep " " $ lines result -- get rid of any internal newlines + return (Code result')) + +mathWord = many1 (choice [(noneOf (" \t\n\\" ++ [mathEnd])), (try (do {c <- char '\\'; notFollowedBy (char mathEnd); return c}))]) + +math = try (do + char mathStart + notFollowedBy space + words <- sepBy1 mathWord (many1 space) + char mathEnd + return (TeX ("$" ++ (joinWithSep " " words) ++ "$"))) + +emph = do + result <- choice [ (enclosed (char emphStart) (char emphEnd) inline), + (enclosed (char emphStartAlt) (char emphEndAlt) inline) ] + return (Emph (normalizeSpaces result)) + +strong = do + result <- choice [ (enclosed (count 2 (char emphStart)) (count 2 (char emphEnd)) inline), + (enclosed (count 2 (char emphStartAlt)) (count 2 (char emphEndAlt)) inline)] + return (Strong (normalizeSpaces result)) + +whitespace = do + many1 (oneOf spaceChars) <?> "whitespace" + return Space + +tabchar = do + tab + return (Str "\t") + +-- hard line break +linebreak = try (do + oneOf spaceChars + many1 (oneOf spaceChars) + endline + return LineBreak ) + +nonEndline = noneOf endLineChars + +str = do + result <- many1 ((noneOf (specialChars ++ spaceChars ++ endLineChars))) + return (Str (decodeEntities result)) + +-- an endline character that can be treated as a space, not a structural break +endline = + try (do + newline + -- next line would allow block quotes without preceding blank line + -- Markdown.pl does allow this, but there's a chance of a wrapped + -- greater-than sign triggering a block quote by accident... +-- notFollowedBy (try (do { choice [emailBlockQuoteStart, string ",----"]; return ' ' })) + notFollowedBy blankline + -- parse potential list starts at beginning of line differently if in a list: + st <- getState + if (stateParserContext st) == ListItemState then + do + notFollowedBy' orderedListStart + notFollowedBy' bulletListStart + else + option () pzero + return Space) + +-- +-- links +-- + +-- a reference label for a link +reference = do + char labelStart + label <- manyTill inline (char labelEnd) + return (normalizeSpaces label) + +-- source for a link, with optional title +source = + try (do + char srcStart + option ' ' (char autoLinkStart) + src <- many (noneOf ([srcEnd, autoLinkEnd] ++ titleOpeners)) + option ' ' (char autoLinkEnd) + tit <- option "" title + skipSpaces + char srcEnd + return (Src (removeTrailingSpace src) tit)) + +titleWith startChar endChar = + try (do + skipSpaces + skipEndline -- a title can be on the next line from the source + skipSpaces + char startChar + tit <- manyTill (choice [ try (do {char '\\'; char endChar}), + (noneOf (endChar:endLineChars)) ]) (char endChar) + let tit' = gsub "\"" """ tit + return tit') + +title = choice [titleWith '(' ')', titleWith '"' '"', titleWith '\'' '\''] <?> "title" + +link = choice [explicitLink, referenceLink] <?> "link" + +explicitLink = + try (do + label <- reference + src <- source + return (Link label src)) + +referenceLink = choice [referenceLinkDouble, referenceLinkSingle] + +referenceLinkDouble = -- a link like [this][/url/] + try (do + label <- reference + skipSpaces + skipEndline + skipSpaces + ref <- reference + return (Link label (Ref ref))) + +referenceLinkSingle = -- a link like [this] + try (do + label <- reference + return (Link label (Ref []))) + +autoLink = -- a link <like.this.com> + try (do + notFollowedBy (do {anyHtmlBlockTag; return ' '}) + src <- between (char autoLinkStart) (char autoLinkEnd) + (many (noneOf (spaceChars ++ endLineChars ++ [autoLinkEnd]))) + case (matchRegex emailAddress src) of + Just _ -> return (Link [Str src] (Src ("mailto:" ++ src) "")) + Nothing -> return (Link [Str src] (Src src ""))) + +emailAddress = mkRegex "([^@:/]+)@(([^.]+[.]?)*([^.]+))" -- presupposes no whitespace + +image = + try (do + char imageStart + (Link label src) <- link + return (Image label src)) + +noteRef = try (do + char noteStart + ref <- between (char '(') (char ')') (many1 (noneOf " \t\n)")) + return (NoteRef ref)) + diff --git a/src/Text/Pandoc/Readers/RST.hs b/src/Text/Pandoc/Readers/RST.hs new file mode 100644 index 000000000..82e5ea303 --- /dev/null +++ b/src/Text/Pandoc/Readers/RST.hs @@ -0,0 +1,644 @@ +-- | Parse reStructuredText and return Pandoc document. +module Text.Pandoc.Readers.RST ( + readRST + ) where +import Text.Pandoc.Definition +import Text.ParserCombinators.Pandoc +import Text.Pandoc.Shared +import Text.Pandoc.Readers.HTML ( anyHtmlBlockTag, anyHtmlInlineTag ) +import Text.Regex ( matchRegex, mkRegex ) +import Text.ParserCombinators.Parsec +import Data.Maybe ( fromMaybe ) +import List ( findIndex ) +import Char ( toUpper ) + +-- | Parse reStructuredText string and return Pandoc document. +readRST :: ParserState -> String -> Pandoc +readRST = readWith parseRST + +-- | Parse a string and print result (for testing). +testString :: String -> IO () +testString = testStringWith parseRST + +-- +-- Constants and data structure definitions +--- + +bulletListMarkers = "*+-" +underlineChars = "!\"#$&'()*+,-./:;<=>?@[\\]^_`{|}~" + +-- treat these as potentially non-text when parsing inline: +specialChars = "\\`|*_<>$:[-" + +-- +-- parsing documents +-- + +isAnonKeyBlock block = case block of + (Key [Str "_"] str) -> True + otherwise -> False + +isNotAnonKeyBlock block = not (isAnonKeyBlock block) + +isHeader1 :: Block -> Bool +isHeader1 (Header 1 _) = True +isHeader1 _ = False + +isHeader2 :: Block -> Bool +isHeader2 (Header 2 _) = True +isHeader2 _ = False + +-- | Promote all headers in a list of blocks. (Part of +-- title transformation for RST.) +promoteHeaders :: Int -> [Block] -> [Block] +promoteHeaders num ((Header level text):rest) = + (Header (level - num) text):(promoteHeaders num rest) +promoteHeaders num (other:rest) = other:(promoteHeaders num rest) +promoteHeaders num [] = [] + +-- | If list of blocks starts with a header (or a header and subheader) +-- of level that are not found elsewhere, return it as a title and +-- promote all the other headers. +titleTransform :: [Block] -- ^ list of blocks + -> ([Block], [Inline]) -- ^ modified list of blocks, title +titleTransform ((Header 1 head1):(Header 2 head2):rest) = -- title and subtitle + if (any isHeader1 rest) || (any isHeader2 rest) then + ((Header 1 head1):(Header 2 head2):rest, []) + else + ((promoteHeaders 2 rest), head1 ++ [Str ":", Space] ++ head2) +titleTransform ((Header 1 head1):rest) = -- title, no subtitle + if (any isHeader1 rest) then + ((Header 1 head1):rest, []) + else + ((promoteHeaders 1 rest), head1) +titleTransform blocks = (blocks, []) + +parseRST = do + state <- getState + input <- getInput + blocks <- parseBlocks -- first pass + let anonymousKeys = filter isAnonKeyBlock blocks + let blocks' = if (null anonymousKeys) then + blocks + else -- run parser again to fill in anonymous links... + case runParser parseBlocks (state { stateKeyBlocks = anonymousKeys }) + "RST source, second pass" input of + Left err -> error $ "\nError:\n" ++ show err + Right result -> (filter isNotAnonKeyBlock result) + let (blocks'', title) = if stateStandalone state then + titleTransform blocks' + else + (blocks', []) + state <- getState + let authors = stateAuthors state + let date = stateDate state + let title' = if (null title) then (stateTitle state) else title + return (Pandoc (Meta title' authors date) blocks'') + +-- +-- parsing blocks +-- + +parseBlocks = do + result <- manyTill block eof + return result + +block = choice [ codeBlock, rawHtmlBlock, rawLaTeXBlock, blockQuote, referenceKey, + imageBlock, unknownDirective, header, hrule, list, fieldList, lineBlock, + para, plain, blankBlock, nullBlock ] <?> "block" + +-- +-- field list +-- + +fieldListItem = try (do + char ':' + name <- many1 alphaNum + string ": " + skipSpaces + first <- manyTill anyChar newline + rest <- many (do{ notFollowedBy (char ':'); + notFollowedBy blankline; + skipSpaces; + manyTill anyChar newline }) + return (name, (joinWithSep " " (first:rest)))) + +fieldList = try (do + items <- many1 fieldListItem + blanklines + let authors = case (lookup "Authors" items) of + Just auth -> [auth] + Nothing -> map snd (filter (\(x,y) -> x == "Author") items) + let date = case (lookup "Date" items) of + Just dat -> dat + Nothing -> "" + let title = case (lookup "Title" items) of + Just tit -> [Str tit] + Nothing -> [] + let remaining = filter (\(x,y) -> (x /= "Authors") && (x /= "Author") && (x /= "Date") && + (x /= "Title")) items + let result = map (\(x,y) -> Para [Strong [Str x], Str ":", Space, Str y]) remaining + updateState (\st -> st { stateAuthors = authors, stateDate = date, stateTitle = title }) + return (BlockQuote result)) + +-- +-- line block +-- + +lineBlockLine = try (do + string "| " + white <- many (oneOf " \t") + line <- manyTill inline newline + let line' = (if null white then [] else [Str white]) ++ line ++ [LineBreak] + return line') + +lineBlock = try (do + lines <- many1 lineBlockLine + blanklines + return $ Para (concat lines)) + +-- +-- paragraph block +-- + +para = choice [ paraBeforeCodeBlock, paraNormal ] <?> "paragraph" + +codeBlockStart = try (do + string "::" + blankline + blankline) + +-- paragraph that ends in a :: starting a code block +paraBeforeCodeBlock = try (do + result <- many1 (do {notFollowedBy' codeBlockStart; inline}) + followedBy' (string "::") + return (Para (if (last result == Space) then + normalizeSpaces result + else + (normalizeSpaces result) ++ [Str ":"]))) + +-- regular paragraph +paraNormal = try (do + result <- many1 inline + newline + blanklines + let result' = normalizeSpaces result + return (Para result')) + +plain = do + result <- many1 inline + let result' = normalizeSpaces result + return (Plain result') + +-- +-- image block +-- + +imageBlock = try (do + string ".. image:: " + src <- manyTill anyChar newline + return (Plain [Image [Str "image"] (Src src "")])) + +-- +-- header blocks +-- + +header = choice [ doubleHeader, singleHeader ] <?> "header" + +-- a header with lines on top and bottom +doubleHeader = try (do + c <- oneOf underlineChars + rest <- many (char c) -- the top line + let lenTop = length (c:rest) + skipSpaces + newline + txt <- many1 (do {notFollowedBy blankline; inline}) + pos <- getPosition + let len = (sourceColumn pos) - 1 + if (len > lenTop) then fail "title longer than border" else (do {return ()}) + blankline -- spaces and newline + count lenTop (char c) -- the bottom line + blanklines + -- check to see if we've had this kind of header before. + -- if so, get appropriate level. if not, add to list. + state <- getState + let headerTable = stateHeaderTable state + let (headerTable', level) = case findIndex (== DoubleHeader c) headerTable of + Just ind -> (headerTable, ind + 1) + Nothing -> (headerTable ++ [DoubleHeader c], (length headerTable) + 1) + setState (state { stateHeaderTable = headerTable' }) + return (Header level (normalizeSpaces txt))) + +-- a header with line on the bottom only +singleHeader = try (do + notFollowedBy' whitespace + txt <- many1 (do {notFollowedBy blankline; inline}) + pos <- getPosition + let len = (sourceColumn pos) - 1 + blankline + c <- oneOf underlineChars + rest <- count (len - 1) (char c) + many (char c) + blanklines + state <- getState + let headerTable = stateHeaderTable state + let (headerTable', level) = case findIndex (== SingleHeader c) headerTable of + Just ind -> (headerTable, ind + 1) + Nothing -> (headerTable ++ [SingleHeader c], (length headerTable) + 1) + setState (state { stateHeaderTable = headerTable' }) + return (Header level (normalizeSpaces txt))) + +-- +-- hrule block +-- + +hruleWith chr = + try (do + count 4 (char chr) + skipMany (char chr) + skipSpaces + newline + blanklines + return HorizontalRule) + +hrule = choice (map hruleWith underlineChars) <?> "hrule" + +-- +-- code blocks +-- + +-- read a line indented by a given string +indentedLine indents = try (do + string indents + result <- manyTill anyChar newline + return (result ++ "\n")) + +-- two or more indented lines, possibly separated by blank lines +-- if variable = True, then any indent will work, but it must be consistent through the block +-- if variable = False, indent should be one tab or equivalent in spaces +indentedBlock variable = try (do + state <- getState + let tabStop = stateTabStop state + indents <- if variable then + many1 (oneOf " \t") + else + oneOfStrings ["\t", (replicate tabStop ' ')] + firstline <- manyTill anyChar newline + rest <- many (choice [ indentedLine indents, + try (do {b <- blanklines; l <- indentedLine indents; return (b ++ l)})]) + option "" blanklines + return (firstline ++ "\n" ++ (concat rest))) + +codeBlock = try (do + codeBlockStart + result <- indentedBlock False -- the False means we want one tab stop indent on each line + return (CodeBlock result)) + +-- +-- raw html +-- + +rawHtmlBlock = try (do + string ".. raw:: html" + blanklines + result <- indentedBlock True + return (RawHtml result)) + +-- +-- raw latex +-- + +rawLaTeXBlock = try (do + string ".. raw:: latex" + blanklines + result <- indentedBlock True + return (Para [(TeX result)])) + +-- +-- block quotes +-- + +blockQuote = try (do + block <- indentedBlock True + -- parse the extracted block, which may contain various block elements: + state <- getState + let parsed = case runParser parseBlocks (state {stateParserContext = BlockQuoteState}) + "block" (block ++ "\n\n") of + Left err -> error $ "Raw block:\n" ++ show block ++ "\nError:\n" ++ show err + Right result -> result + return (BlockQuote parsed)) + +-- +-- list blocks +-- + +list = choice [ bulletList, orderedList ] <?> "list" + +-- parses bullet list start and returns its length (inc. following whitespace) +bulletListStart = + try (do + notFollowedBy' hrule -- because hrules start out just like lists + marker <- oneOf bulletListMarkers + white <- many1 spaceChar + let len = length (marker:white) + return len) + +withPeriodSuffix parser = try (do + a <- parser + b <- char '.' + return (a ++ [b])) + +withParentheses parser = try (do + a <- char '(' + b <- parser + c <- char ')' + return ([a] ++ b ++ [c])) + +withRightParen parser = try (do + a <- parser + b <- char ')' + return (a ++ [b])) + +upcaseWord = map toUpper + +romanNumeral = do + let lowerNumerals = ["i", "ii", "iii", "iiii", "iv", "v", "vi", "vii", "viii", "ix", "x", "xi", "xii", "xiii", "xiv", "xv", "xvi", "xvii", "xviii", "xix", "xx", "xxi", "xxii", "xxiii", "xxiv" ] + let upperNumerals = map upcaseWord lowerNumerals + result <- choice $ map string (lowerNumerals ++ upperNumerals) + return result + +orderedListEnumerator = choice [ many1 digit, + string "#", + count 1 letter, + romanNumeral ] + +-- parses ordered list start and returns its length (inc. following whitespace) +orderedListStart = + try (do + marker <- choice [ withPeriodSuffix orderedListEnumerator, + withParentheses orderedListEnumerator, + withRightParen orderedListEnumerator ] + white <- many1 spaceChar + let len = length (marker ++ white) + return len) + +-- parse a line of a list item +listLine markerLength = try (do + notFollowedBy blankline + indentWith markerLength + line <- manyTill anyChar newline + return (line ++ "\n")) + +-- indent by specified number of spaces (or equiv. tabs) +indentWith num = do + state <- getState + let tabStop = stateTabStop state + if (num < tabStop) then + count num (char ' ') + else + choice [ try (count num (char ' ')), + (try (do {char '\t'; count (num - tabStop) (char ' ')})) ] + +-- parse raw text for one list item, excluding start marker and continuations +rawListItem start = + try (do + markerLength <- start + firstLine <- manyTill anyChar newline + restLines <- many (listLine markerLength) + return (markerLength, (firstLine ++ "\n" ++ (concat restLines)))) + +-- continuation of a list item - indented and separated by blankline or (in compact lists) +-- endline. Note: nested lists are parsed as continuations. +listContinuation markerLength = + try (do + blanks <- many1 blankline + result <- many1 (listLine markerLength) + return (blanks ++ (concat result))) + +listItem start = + try (do + (markerLength, first) <- rawListItem start + rest <- many (listContinuation markerLength) + blanks <- choice [ try (do {b <- many blankline; followedBy' start; return b}), + many1 blankline ] -- whole list must end with blank + -- parsing with ListItemState forces markers at beginning of lines to + -- count as list item markers, even if not separated by blank space. + -- see definition of "endline" + state <- getState + let parsed = case runParser parseBlocks (state {stateParserContext = ListItemState}) + "list item" raw of + Left err -> error $ "Raw:\n" ++ raw ++ "\nError:\n" ++ show err + Right result -> result + where raw = concat (first:rest) ++ blanks + return parsed) + +orderedList = + try (do + items <- many1 (listItem orderedListStart) + let items' = compactify items + return (OrderedList items')) + +bulletList = + try (do + items <- many1 (listItem bulletListStart) + let items' = compactify items + return (BulletList items')) + +-- +-- unknown directive (e.g. comment) +-- + +unknownDirective = try (do + string ".. " + manyTill anyChar newline + many (do {string " "; + char ':'; + many1 (noneOf "\n:"); + char ':'; + many1 (noneOf "\n"); + newline}) + option "" blanklines + return Null) + +-- +-- reference key +-- + +referenceKey = choice [imageKey, anonymousKey, regularKeyQuoted, regularKey] + +imageKey = try (do + string ".. |" + ref <- manyTill inline (char '|') + skipSpaces + string "image::" + src <- manyTill anyChar newline + return (Key (normalizeSpaces ref) (Src (removeLeadingTrailingSpace src) ""))) + +anonymousKey = try (do + choice [string ".. __:", string "__"] + skipSpaces + src <- manyTill anyChar newline + state <- getState + return (Key [Str "_"] (Src (removeLeadingTrailingSpace src) ""))) + +regularKeyQuoted = try (do + string ".. _`" + ref <- manyTill inline (string "`:") + skipSpaces + src <- manyTill anyChar newline + return (Key (normalizeSpaces ref) (Src (removeLeadingTrailingSpace src) ""))) + +regularKey = try (do + string ".. _" + ref <- manyTill inline (char ':') + skipSpaces + src <- manyTill anyChar newline + return (Key (normalizeSpaces ref) (Src (removeLeadingTrailingSpace src) ""))) + + -- + -- inline + -- + +text = choice [ strong, emph, code, str, tabchar, whitespace, endline ] <?> "text" + +inline = choice [ escapedChar, special, hyphens, text, symbol ] <?> "inline" + +special = choice [ link, image ] <?> "link, inline html, or image" + +hyphens = try (do + result <- many1 (char '-') + option Space endline -- don't want to treat endline after hyphen or dash as a space + return (Str result)) + +escapedChar = escaped anyChar + +symbol = do + result <- oneOf specialChars + return (Str [result]) + +-- parses inline code, between codeStart and codeEnd +code = + try (do + string "``" + result <- manyTill anyChar (string "``") + let result' = removeLeadingTrailingSpace $ joinWithSep " " $ lines result + return (Code result')) + +emph = do + result <- enclosed (char '*') (char '*') inline + return (Emph (normalizeSpaces result)) + +strong = do + result <- enclosed (string "**") (string "**") inline + return (Strong (normalizeSpaces result)) + +whitespace = do + many1 spaceChar <?> "whitespace" + return Space + +tabchar = do + tab + return (Str "\t") + +str = do + notFollowedBy' oneWordReferenceLink + result <- many1 (noneOf (specialChars ++ "\t\n ")) + return (Str result) + +-- an endline character that can be treated as a space, not a structural break +endline = + try (do + newline + notFollowedBy blankline + -- parse potential list starts at beginning of line differently if in a list: + st <- getState + if ((stateParserContext st) == ListItemState) then + notFollowedBy' (choice [orderedListStart, bulletListStart]) + else + option () pzero + return Space) + +-- +-- links +-- + +link = choice [explicitLink, referenceLink, autoLink, oneWordReferenceLink] <?> "link" + +explicitLink = + try (do + char '`' + label <- manyTill inline (try (do {spaces; char '<'})) + src <- manyTill (noneOf ">\n ") (char '>') + skipSpaces + string "`_" + return (Link (normalizeSpaces label) (Src (removeLeadingTrailingSpace src) ""))) + +anonymousLinkEnding = + try (do + char '_' + state <- getState + let anonKeys = stateKeyBlocks state + -- if there's a list of anon key refs (from previous pass), pop one off. + -- otherwise return an anon key ref for the next pass to take care of... + case anonKeys of + (Key [Str "_"] src):rest -> + do{ setState (state { stateKeyBlocks = rest }); + return src } + otherwise -> return (Ref [Str "_"])) + +referenceLink = + try (do + char '`' + label <- manyTill inline (string "`_") + src <- option (Ref []) anonymousLinkEnding + return (Link (normalizeSpaces label) src)) + +oneWordReferenceLink = + try (do + label <- many1 alphaNum + char '_' + src <- option (Ref []) anonymousLinkEnding + notFollowedBy alphaNum -- because this_is_not a link + return (Link [Str label] src)) + +uriScheme = oneOfStrings [ "http://", "https://", "ftp://", "file://", "mailto:", + "news:", "telnet:" ] + +uri = try (do + scheme <- uriScheme + identifier <- many1 (noneOf " \t\n") + return (scheme ++ identifier)) + +autoURI = try (do + src <- uri + return (Link [Str src] (Src src ""))) + +emailChar = alphaNum <|> oneOf "-+_." + +emailAddress = try (do + firstLetter <- alphaNum + restAddr <- many emailChar + let addr = firstLetter:restAddr + char '@' + dom <- domain + return (addr ++ '@':dom)) + +domainChar = alphaNum <|> char '-' + +domain = try (do + first <- many1 domainChar + dom <- many1 (try (do{ char '.'; many1 domainChar })) + return (joinWithSep "." (first:dom))) + +autoEmail = try (do + src <- emailAddress + return (Link [Str src] (Src ("mailto:" ++ src) ""))) + +autoLink = autoURI <|> autoEmail + +-- For now, we assume that all substitution references are for images. +image = + try (do + char '|' + ref <- manyTill inline (char '|') + return (Image (normalizeSpaces ref) (Ref ref))) diff --git a/src/Text/Pandoc/Shared.hs b/src/Text/Pandoc/Shared.hs new file mode 100644 index 000000000..dc58dd6b4 --- /dev/null +++ b/src/Text/Pandoc/Shared.hs @@ -0,0 +1,417 @@ +-- | Utility functions and definitions used by the various Pandoc modules. +module Text.Pandoc.Shared ( + -- * Text processing + gsub, + joinWithSep, + tabsToSpaces, + backslashEscape, + escapePreservingRegex, + endsWith, + stripTrailingNewlines, + removeLeadingTrailingSpace, + removeLeadingSpace, + removeTrailingSpace, + -- * Parsing + readWith, + testStringWith, + HeaderType (..), + ParserContext (..), + ParserState (..), + defaultParserState, + -- * Native format prettyprinting + prettyPandoc, + -- * Pandoc block list processing + consolidateList, + isNoteBlock, + splitBySpace, + normalizeSpaces, + compactify, + generateReference, + WriterOptions (..), + KeyTable, + keyTable, + lookupKeySrc, + refsMatch, + replaceReferenceLinks, + replaceRefLinksBlockList + ) where +import Text.Pandoc.Definition +import Text.ParserCombinators.Parsec +import Text.Pandoc.HtmlEntities ( decodeEntities ) +import Text.Regex ( matchRegexAll, mkRegex, subRegex, Regex ) +import Char ( toLower ) +import List ( find, groupBy ) + +-- | Parse a string with a given parser and state. +readWith :: GenParser Char ParserState a -- ^ parser + -> ParserState -- ^ initial state + -> String -- ^ input string + -> a +readWith parser state input = + case runParser parser state "source" input of + Left err -> error $ "\nError:\n" ++ show err + Right result -> result + +-- | Parse a string with @parser@ (for testing). +testStringWith :: (Show a) => + GenParser Char ParserState a + -> String + -> IO () +testStringWith parser str = putStrLn $ show $ readWith parser defaultParserState str + +-- | Parser state + +data HeaderType + = SingleHeader Char -- ^ Single line of characters underneath + | DoubleHeader Char -- ^ Lines of characters above and below + deriving (Eq, Show) + +data ParserContext + = BlockQuoteState -- ^ Used when running parser on contents of blockquote + | ListItemState -- ^ Used when running parser on list item contents + | NullState -- ^ Default state + deriving (Eq, Show) + +data ParserState = ParserState + { stateParseRaw :: Bool, -- ^ Parse untranslatable HTML and LaTeX? + stateParserContext :: ParserContext, -- ^ What are we parsing? + stateKeyBlocks :: [Block], -- ^ List of reference key blocks + stateKeysUsed :: [[Inline]], -- ^ List of references used so far + stateNoteBlocks :: [Block], -- ^ List of note blocks + stateTabStop :: Int, -- ^ Tab stop + stateStandalone :: Bool, -- ^ If @True@, parse bibliographic info + stateTitle :: [Inline], -- ^ Title of document + stateAuthors :: [String], -- ^ Authors of document + stateDate :: String, -- ^ Date of document + stateHeaderTable :: [HeaderType] } -- ^ List of header types used, in what order (for reStructuredText only) + deriving Show + +defaultParserState :: ParserState +defaultParserState = + ParserState { stateParseRaw = False, + stateParserContext = NullState, + stateKeyBlocks = [], + stateKeysUsed = [], + stateNoteBlocks = [], + stateTabStop = 4, + stateStandalone = False, + stateTitle = [], + stateAuthors = [], + stateDate = [], + stateHeaderTable = [] } + +-- | Consolidate @Str@s and @Space@s in an inline list into one big @Str@. +-- Collapse adjacent @Space@s. +consolidateList :: [Inline] -> [Inline] +consolidateList ((Str a):(Str b):rest) = consolidateList ((Str (a ++ b)):rest) +consolidateList ((Str a):Space:rest) = consolidateList ((Str (a ++ " ")):rest) +consolidateList (Space:(Str a):rest) = consolidateList ((Str (" " ++ a)):rest) +consolidateList (Space:Space:rest) = consolidateList ((Str " "):rest) +consolidateList (inline:rest) = inline:(consolidateList rest) +consolidateList [] = [] + +-- | Indent string as a block. +indentBy :: Int -- ^ Number of spaces to indent the block + -> Int -- ^ Number of spaces to indent first line, relative to block + -> String -- ^ Contents of block to indent + -> String +indentBy num first [] = "" +indentBy num first str = + let (firstLine:restLines) = lines str + firstLineIndent = num + first in + (replicate firstLineIndent ' ') ++ firstLine ++ "\n" ++ (joinWithSep "\n" $ map (\line -> (replicate num ' ') ++ line) restLines) + +-- | Prettyprint list of Pandoc blocks elements. +prettyBlockList :: Int -- ^ Number of spaces to indent list of blocks + -> [Block] -- ^ List of blocks + -> String +prettyBlockList indent [] = indentBy indent 0 "[]" +prettyBlockList indent blocks = indentBy indent (-2) $ "[ " ++ (joinWithSep "\n, " (map prettyBlock blocks)) ++ " ]" + +-- | Prettyprint Pandoc block element. +prettyBlock :: Block -> String +prettyBlock (BlockQuote blocks) = "BlockQuote\n " ++ (prettyBlockList 2 blocks) +prettyBlock (Note ref blocks) = "Note " ++ (show ref) ++ "\n " ++ (prettyBlockList 2 blocks) +prettyBlock (OrderedList blockLists) = "OrderedList\n" ++ indentBy 2 0 ("[ " ++ (joinWithSep ", " (map (\blocks -> prettyBlockList 2 blocks) blockLists))) ++ " ]" +prettyBlock (BulletList blockLists) = "BulletList\n" ++ indentBy 2 0 ("[ " ++ (joinWithSep ", " (map (\blocks -> prettyBlockList 2 blocks) blockLists))) ++ " ]" +prettyBlock block = show block + +-- | Prettyprint Pandoc document. +prettyPandoc :: Pandoc -> String +prettyPandoc (Pandoc meta blocks) = "Pandoc " ++ "(" ++ (show meta) ++ ")\n" ++ (prettyBlockList 0 blocks) + +-- | Convert tabs to spaces (with adjustable tab stop). +tabsToSpaces :: Int -- ^ Tabstop + -> String -- ^ String to convert + -> String +tabsToSpaces tabstop str = + unlines (map (tabsInLine tabstop tabstop) (lines str)) + +-- | Convert tabs to spaces in one line. +tabsInLine :: Int -- ^ Number of spaces to next tab stop + -> Int -- ^ Tabstop + -> String -- ^ Line to convert + -> String +tabsInLine num tabstop "" = "" +tabsInLine num tabstop (c:cs) = + let replacement = (if (c == '\t') then (replicate num ' ') else [c]) in + let nextnumraw = (num - (length replacement)) in + let nextnum = if (nextnumraw < 1) then (nextnumraw + tabstop) else nextnumraw in + replacement ++ (tabsInLine nextnum tabstop cs) + +-- | Substitute string for every occurrence of regular expression. +gsub :: String -- ^ Regular expression (as string) to substitute for + -> String -- ^ String to substitute for the regex + -> String -- ^ String to be substituted in + -> String +gsub regex replacement str = subRegex (mkRegex regex) str replacement + +-- | Escape designated characters with backslash. +backslashEscape :: [Char] -- ^ list of special characters to escape + -> String -- ^ string input + -> String +backslashEscape special [] = [] +backslashEscape special (x:xs) = if x `elem` special then + '\\':x:(backslashEscape special xs) + else + x:(backslashEscape special xs) + +-- | Escape string by applying a function, but don't touch anything that matches regex. +escapePreservingRegex :: (String -> String) -- ^ Escaping function + -> Regex -- ^ Regular expression + -> String -- ^ String to be escaped + -> String +escapePreservingRegex escapeFunction regex str = + case (matchRegexAll regex str) of + Nothing -> escapeFunction str + Just (before, matched, after, _) -> + (escapeFunction before) ++ matched ++ + (escapePreservingRegex escapeFunction regex after) + +-- | Returns @True@ if string ends with given character. +endsWith :: Char -> [Char] -> Bool +endsWith char [] = False +endsWith char str = (char == last str) + +-- | Returns @True@ if block is a @Note@ block +isNoteBlock :: Block -> Bool +isNoteBlock (Note ref blocks) = True +isNoteBlock _ = False + +-- | Joins a list of lists, separated by another list. +joinWithSep :: [a] -- ^ List to use as separator + -> [[a]] -- ^ Lists to join + -> [a] +joinWithSep sep [] = [] +joinWithSep sep lst = foldr1 (\a b -> a ++ sep ++ b) lst + +-- | Strip trailing newlines from string. +stripTrailingNewlines :: String -> String +stripTrailingNewlines "" = "" +stripTrailingNewlines str = + if (last str) == '\n' then + stripTrailingNewlines (init str) + else + str + +-- | Remove leading and trailing space (including newlines) from string. +removeLeadingTrailingSpace :: String -> String +removeLeadingTrailingSpace = removeLeadingSpace . removeTrailingSpace + +-- | Remove leading space (including newlines) from string. +removeLeadingSpace :: String -> String +removeLeadingSpace = dropWhile (\x -> (x == ' ') || (x == '\n') || (x == '\t')) + +-- | Remove trailing space (including newlines) from string. +removeTrailingSpace :: String -> String +removeTrailingSpace = reverse . removeLeadingSpace . reverse + +-- | Split list of inlines into groups separated by a space. +splitBySpace :: [Inline] -> [[Inline]] +splitBySpace lst = filter (\a -> (/= Space) (head a)) + (groupBy (\a b -> (/= Space) a && (/= Space) b) lst) + +-- | Normalize a list of inline elements: remove leading and trailing +-- @Space@ elements, and collapse double @Space@s into singles. +normalizeSpaces :: [Inline] -> [Inline] +normalizeSpaces [] = [] +normalizeSpaces list = + let removeDoubles [] = [] + removeDoubles (Space:Space:rest) = removeDoubles (Space:rest) + removeDoubles (x:rest) = x:(removeDoubles rest) in + let removeLeading [] = [] + removeLeading lst = if ((head lst) == Space) then tail lst else lst in + let removeTrailing [] = [] + removeTrailing lst = if ((last lst) == Space) then init lst else lst in + removeLeading $ removeTrailing $ removeDoubles list + +-- | Change final list item from @Para@ to @Plain@ if the list should be compact. +compactify :: [[Block]] -- ^ List of list items (each a list of blocks) + -> [[Block]] +compactify [] = [] +compactify items = + let final = last items + others = init items in + case final of + [Para a] -> if any containsPara others then items else others ++ [[Plain a]] + otherwise -> items + +containsPara :: [Block] -> Bool +containsPara [] = False +containsPara ((Para a):rest) = True +containsPara ((BulletList items):rest) = (any containsPara items) || (containsPara rest) +containsPara ((OrderedList items):rest) = (any containsPara items) || (containsPara rest) +containsPara (x:rest) = containsPara rest + +-- | Options for writers +data WriterOptions = WriterOptions + { writerStandalone :: Bool -- ^ If @True@, writer header and footer + , writerTitlePrefix :: String -- ^ Prefix for HTML titles + , writerHeader :: String -- ^ Header for the document + , writerIncludeBefore :: String -- ^ String to include before the document body + , writerIncludeAfter :: String -- ^ String to include after the document body + , writerSmartypants :: Bool -- ^ If @True@, use smart quotes, dashes, and ellipses + , writerS5 :: Bool -- ^ @True@ if we're writing S5 instead of normal HTML + , writerIncremental :: Bool -- ^ If @True@, display S5 lists incrementally + , writerNumberSections :: Bool -- ^ If @True@, number sections in LaTeX + , writerTabStop :: Int } -- ^ Tabstop for conversion between spaces and tabs + deriving Show + +-- +-- Functions for constructing lists of reference keys +-- + +-- | Returns @Just@ numerical key reference if there's already a key +-- for the specified target in the list of blocks, otherwise @Nothing@. +keyFoundIn :: [Block] -- ^ List of key blocks to search + -> Target -- ^ Target to search for + -> Maybe String +keyFoundIn [] src = Nothing +keyFoundIn ((Key [Str num] src1):rest) src = if (src1 == src) then + Just num + else + keyFoundIn rest src +keyFoundIn (_:rest) src = keyFoundIn rest src + +-- | Return next unique numerical key, given keyList +nextUniqueKey :: [[Inline]] -> String +nextUniqueKey keys = + let nums = [1..10000] + notAKey n = not (any (== [Str (show n)]) keys) in + case (find notAKey nums) of + Just x -> show x + Nothing -> error "Could not find unique key for reference link" + +-- | Generate a reference for a URL (either an existing reference, if +-- there is one, or a new one, if there isn't) and update parser state. +generateReference :: String -- ^ URL + -> String -- ^ Title + -> GenParser tok ParserState Target +generateReference url title = do + let src = Src (decodeEntities url) (decodeEntities title) + state <- getState + let keyBlocks = stateKeyBlocks state + let keysUsed = stateKeysUsed state + case (keyFoundIn keyBlocks src) of + Just num -> return (Ref [Str num]) + Nothing -> do + let nextNum = nextUniqueKey keysUsed + updateState (\st -> st {stateKeyBlocks = (Key [Str nextNum] src):keyBlocks, + stateKeysUsed = [Str nextNum]:keysUsed}) + return (Ref [Str nextNum]) + +-- +-- code to replace reference links with real links and remove unneeded key blocks +-- + +type KeyTable = [([Inline], Target)] + +-- | Returns @True@ if block is a Key block +isRefBlock :: Block -> Bool +isRefBlock (Key _ _) = True +isRefBlock _ = False + +-- | Returns a pair of a list of pairs of keys and associated sources, and a new +-- list of blocks with the included key blocks deleted. +keyTable :: [Block] -> (KeyTable, [Block]) +keyTable [] = ([],[]) +keyTable ((Key ref target):lst) = (((ref, target):table), rest) + where (table, rest) = keyTable lst +keyTable (Null:lst) = keyTable lst -- get rid of Nulls +keyTable (Blank:lst) = keyTable lst -- get rid of Blanks +keyTable ((BlockQuote blocks):lst) = ((table1 ++ table2), ((BlockQuote rest1):rest2)) + where (table1, rest1) = keyTable blocks + (table2, rest2) = keyTable lst +keyTable ((Note ref blocks):lst) = ((table1 ++ table2), ((Note ref rest1):rest2)) + where (table1, rest1) = keyTable blocks + (table2, rest2) = keyTable lst +keyTable ((OrderedList blockLists):lst) = ((table1 ++ table2), ((OrderedList rest1):rest2)) + where results = map keyTable blockLists + rest1 = map snd results + table1 = concatMap fst results + (table2, rest2) = keyTable lst +keyTable ((BulletList blockLists):lst) = ((table1 ++ table2), ((BulletList rest1):rest2)) + where results = map keyTable blockLists + rest1 = map snd results + table1 = concatMap fst results + (table2, rest2) = keyTable lst +keyTable (other:lst) = (table, (other:rest)) + where (table, rest) = keyTable lst + +-- | Look up key in key table and return target object. +lookupKeySrc :: KeyTable -- ^ Key table + -> [Inline] -- ^ Key + -> Maybe Target +lookupKeySrc table key = case table of + [] -> Nothing + (k, src):rest -> if (refsMatch k key) then Just src else lookupKeySrc rest key + +-- | Returns @True@ if keys match (case insensitive). +refsMatch :: [Inline] -> [Inline] -> Bool +refsMatch ((Str x):restx) ((Str y):resty) = ((map toLower x) == (map toLower y)) && refsMatch restx resty +refsMatch ((Code x):restx) ((Code y):resty) = ((map toLower x) == (map toLower y)) && refsMatch restx resty +refsMatch ((TeX x):restx) ((TeX y):resty) = ((map toLower x) == (map toLower y)) && refsMatch restx resty +refsMatch ((HtmlInline x):restx) ((HtmlInline y):resty) = ((map toLower x) == (map toLower y)) && refsMatch restx resty +refsMatch ((NoteRef x):restx) ((NoteRef y):resty) = ((map toLower x) == (map toLower y)) && refsMatch restx resty +refsMatch ((Emph x):restx) ((Emph y):resty) = refsMatch x y && refsMatch restx resty +refsMatch ((Strong x):restx) ((Strong y):resty) = refsMatch x y && refsMatch restx resty +refsMatch (x:restx) (y:resty) = (x == y) && refsMatch restx resty +refsMatch [] x = null x +refsMatch x [] = null x + +-- | Replace reference links with explicit links in list of blocks, removing key blocks. +replaceReferenceLinks :: [Block] -> [Block] +replaceReferenceLinks blocks = + let (keytable, purged) = keyTable blocks in + replaceRefLinksBlockList keytable purged + +-- | Use key table to replace reference links with explicit links in a list of blocks +replaceRefLinksBlockList :: KeyTable -> [Block] -> [Block] +replaceRefLinksBlockList keytable lst = map (replaceRefLinksBlock keytable) lst + +-- | Use key table to replace reference links with explicit links in a block +replaceRefLinksBlock :: KeyTable -> Block -> Block +replaceRefLinksBlock keytable (Plain lst) = Plain (map (replaceRefLinksInline keytable) lst) +replaceRefLinksBlock keytable (Para lst) = Para (map (replaceRefLinksInline keytable) lst) +replaceRefLinksBlock keytable (Header lvl lst) = Header lvl (map (replaceRefLinksInline keytable) lst) +replaceRefLinksBlock keytable (BlockQuote lst) = BlockQuote (map (replaceRefLinksBlock keytable) lst) +replaceRefLinksBlock keytable (Note ref lst) = Note ref (map (replaceRefLinksBlock keytable) lst) +replaceRefLinksBlock keytable (OrderedList lst) = OrderedList (map (replaceRefLinksBlockList keytable) lst) +replaceRefLinksBlock keytable (BulletList lst) = BulletList (map (replaceRefLinksBlockList keytable) lst) +replaceRefLinksBlock keytable other = other + +-- | Use key table to replace reference links with explicit links in an inline element. +replaceRefLinksInline :: KeyTable -> Inline -> Inline +replaceRefLinksInline keytable (Link text (Ref ref)) = (Link newText newRef) + where newRef = case lookupKeySrc keytable (if (null ref) then text else ref) of + Nothing -> (Ref ref) + Just src -> src + newText = map (replaceRefLinksInline keytable) text +replaceRefLinksInline keytable (Image text (Ref ref)) = (Image newText newRef) + where newRef = case lookupKeySrc keytable (if (null ref) then text else ref) of + Nothing -> (Ref ref) + Just src -> src + newText = map (replaceRefLinksInline keytable) text +replaceRefLinksInline keytable (Emph lst) = Emph (map (replaceRefLinksInline keytable) lst) +replaceRefLinksInline keytable (Strong lst) = Strong (map (replaceRefLinksInline keytable) lst) +replaceRefLinksInline keytable other = other diff --git a/src/Text/Pandoc/UTF8.hs b/src/Text/Pandoc/UTF8.hs new file mode 100644 index 000000000..66590809f --- /dev/null +++ b/src/Text/Pandoc/UTF8.hs @@ -0,0 +1,43 @@ +-- | Functions for converting Unicode strings to UTF-8 and vice versa. +-- +-- Taken from <http://www.cse.ogi.edu/~hallgren/Talks/LHiH/base/lib/UTF8.hs>. +-- (c) 2003, OGI School of Science & Engineering, Oregon Health and +-- Science University. +-- +-- Modified by Martin Norbaeck to pass illegal UTF-8 sequences through unchanged. +module Text.Pandoc.UTF8 ( + decodeUTF8, + encodeUTF8 + ) where + +-- From the Char module supplied with HBC. + +-- | Take a UTF-8 string and decode it into a Unicode string. +decodeUTF8 :: String -> String +decodeUTF8 "" = "" +decodeUTF8 (c:c':cs) | '\xc0' <= c && c <= '\xdf' && + '\x80' <= c' && c' <= '\xbf' = + toEnum ((fromEnum c `mod` 0x20) * 0x40 + fromEnum c' `mod` 0x40) : decodeUTF8 cs +decodeUTF8 (c:c':c'':cs) | '\xe0' <= c && c <= '\xef' && + '\x80' <= c' && c' <= '\xbf' && + '\x80' <= c'' && c'' <= '\xbf' = + toEnum ((fromEnum c `mod` 0x10 * 0x1000) + (fromEnum c' `mod` 0x40) * 0x40 + fromEnum c'' `mod` 0x40) : decodeUTF8 cs +decodeUTF8 (c:cs) = c : decodeUTF8 cs + +-- | Take a Unicode string and encode it as a UTF-8 string. +encodeUTF8 :: String -> String +encodeUTF8 "" = "" +encodeUTF8 (c:cs) = + if c > '\x0000' && c < '\x0080' then + c : encodeUTF8 cs + else if c < toEnum 0x0800 then + let i = fromEnum c + in toEnum (0xc0 + i `div` 0x40) : + toEnum (0x80 + i `mod` 0x40) : + encodeUTF8 cs + else + let i = fromEnum c + in toEnum (0xe0 + i `div` 0x1000) : + toEnum (0x80 + (i `mod` 0x1000) `div` 0x40) : + toEnum (0x80 + i `mod` 0x40) : + encodeUTF8 cs diff --git a/src/Text/Pandoc/Writers/DefaultHeaders.hs b/src/Text/Pandoc/Writers/DefaultHeaders.hs new file mode 100644 index 000000000..87dd7d8ff --- /dev/null +++ b/src/Text/Pandoc/Writers/DefaultHeaders.hs @@ -0,0 +1,27 @@ +---------------------------------------------------- +-- Do not edit this file by hand. Edit +-- 'templates/DefaultHeaders.hs' +-- and run ./fillTemplates.pl Text/Pandoc/Writers/DefaultHeaders.hs +---------------------------------------------------- + +-- | Default headers for Pandoc writers. +module Text.Pandoc.Writers.DefaultHeaders ( + defaultLaTeXHeader, + defaultHtmlHeader, + defaultS5Header, + defaultRTFHeader + ) where +import Text.Pandoc.Writers.S5 + +defaultLaTeXHeader :: String +defaultLaTeXHeader = "\\documentclass{article}\n\\usepackage{hyperref}\n\\usepackage{ucs}\n\\usepackage[utf8x]{inputenc}\n\\usepackage{graphicx}\n\\setlength{\\parindent}{0pt}\n\\setlength{\\parskip}{6pt plus 2pt minus 1pt}\n% This is needed for code blocks in footnotes:\n\\usepackage{fancyvrb}\n\\VerbatimFootnotes\n" + +defaultHtmlHeader :: String +defaultHtmlHeader = "<!DOCTYPE HTML PUBLIC \"-//W3C//DTD HTML 4.01 Transitional//EN\"\n \"http://www.w3.org/TR/html4/loose.dtd\">\n<html>\n<head>\n<meta http-equiv=\"Content-Type\" content=\"text/html; charset=UTF-8\" />\n<meta name=\"generator\" content=\"pandoc\" />\n<style type=\"text/css\">\ndiv.pandocNote { border-left: 1px solid grey; padding-left: 1em; }\nspan.pandocNoteRef { vertical-align: super; font-size: 80%; }\nspan.pandocNoteMarker { }\n</style>\n" + +defaultS5Header :: String +defaultS5Header = "<!DOCTYPE html PUBLIC \"-//W3C//DTD XHTML 1.0 Strict//EN\" \"http://www.w3.org/TR/xhtml1/DTD/xhtml1-strict.dtd\">\n<html xmlns=\"http://www.w3.org/1999/xhtml\">\n<head>\n<!-- configuration parameters -->\n<meta name=\"defaultView\" content=\"slideshow\" />\n<meta name=\"controlVis\" content=\"hidden\" />\n<meta http-equiv=\"Content-Type\" content=\"text/html; charset=UTF-8\" />\n<meta name=\"generator\" content=\"pandoc\" />\n" ++ s5CSS ++ s5Javascript + +defaultRTFHeader :: String +defaultRTFHeader = "{\\rtf1\\ansi\\deff0{\\fonttbl{\\f0 Times New Roman;}{\\f1 Courier;}}\n{\\colortbl;\\red255\\green0\\blue0;\\red0\\green0\\blue255;}\n\\widowctrl\\hyphauto\n\n" + diff --git a/src/Text/Pandoc/Writers/HTML.hs b/src/Text/Pandoc/Writers/HTML.hs new file mode 100644 index 000000000..9eecf2761 --- /dev/null +++ b/src/Text/Pandoc/Writers/HTML.hs @@ -0,0 +1,197 @@ +-- | Converts Pandoc to HTML. +module Text.Pandoc.Writers.HTML ( + writeHtml + ) where +import Text.Pandoc.Definition +import Text.Pandoc.Shared +import Text.Html ( stringToHtmlString ) +import Text.Regex ( mkRegex ) +import Numeric ( showHex ) +import Char ( ord ) +import List ( isPrefixOf ) + +-- | Convert Pandoc document to string in HTML format. +writeHtml :: WriterOptions -> Pandoc -> String +writeHtml options (Pandoc (Meta title authors date) blocks) = + let titlePrefix = writerTitlePrefix options in + let topTitle = if not (null titlePrefix) then + [Str titlePrefix] ++ (if not (null title) then [Str " - "] ++ title else []) + else + title in + let head = if (writerStandalone options) then + htmlHeader options (Meta topTitle authors date) + else + "" + titleBlocks = if (writerStandalone options) && (not (null title)) && + (not (writerS5 options)) then + [RawHtml "<h1 class=\"title\">", Plain title, RawHtml "</h1>\n"] + else + [] + foot = if (writerStandalone options) then "</body>\n</html>\n" else "" + body = (writerIncludeBefore options) ++ + concatMap (blockToHtml options) (replaceReferenceLinks (titleBlocks ++ blocks)) ++ + (writerIncludeAfter options) in + head ++ body ++ foot + +-- | Obfuscate a "mailto:" link using Javascript. +obfuscateLink :: WriterOptions -> [Inline] -> String -> String +obfuscateLink options text src = + let text' = inlineListToHtml options text in + let linkText = if src == ("mailto:" ++ text') then "e" else "'" ++ text' ++ "'" + altText = if src == ("mailto:" ++ text') then "\\1 [at] \\2" else text' ++ " (\\1 [at] \\2)" in + gsub "mailto:([^@]*)@(.*)" ("<script type=\"text/javascript\">h='\\2';n='\\1';e=n+'@'+h;document.write('<a href=\"mailto:'+e+'\">'+" ++ linkText ++ "+'<\\/a>');</script><noscript>" ++ altText ++ "</noscript>") src + +-- | Obfuscate character as entity. +obfuscateChar :: Char -> String +obfuscateChar char = let num = ord char in + let numstr = if even num then (show num) else ("x" ++ (showHex num "")) in + "&#" ++ numstr ++ ";" + +-- | Escape string, preserving character entities and quote. +stringToHtml :: String -> String +stringToHtml str = escapePreservingRegex stringToHtmlString (mkRegex "\"|(&[[:alnum:]]*;)") str + +-- | Escape string as in 'stringToHtml' but add smartypants filter. +stringToSmartHtml :: String -> String +stringToSmartHtml = + let escapeDoubleQuotes = + gsub "(\"|"|'')" "”" . -- rest are right quotes + gsub "([[:space:]])(\"|")" "\\1“" . -- never right quo after space + gsub "(\"|"|``)('|`|‘)([^[:punct:][:space:]])" "“‘\\3" . -- "'word left + gsub "(\"|"|``)([^[:punct:][:space:]])" "“\\2" -- "word left + escapeSingleQuotes = + gsub "'" "’" . -- otherwise right + gsub "([[:space:]])'" "\\1‘" . -- never right quo after space + gsub "`" "‘" . -- ` is left + gsub "([^[:punct:][:space:]])'" "\\1’" . -- word' right + gsub "('|`)(\"|"|“|``)" "‘“" . -- '"word left + gsub "^('|`)([^[:punct:][:space:]])" "‘\\2" . -- 'word left + gsub "([^[:punct:][:space:]])'(s|S)" "\\1’\\2" . -- possessive + gsub "([[:space:]])'([^[:punct:][:space:]])" "\\1‘\\2" . -- 'word left + gsub "'([0-9][0-9](s|S))" "’\\1" -- '80s - decade abbrevs. + escapeDashes = gsub " ?-- ?" "—" . + gsub " ?--- ?" "—" . + gsub "([0-9])--?([0-9])" "\\1–\\2" + escapeEllipses = gsub "\\.\\.\\.|\\. \\. \\." "…" in + escapeSingleQuotes . escapeDoubleQuotes . escapeDashes . escapeEllipses . stringToHtml + +-- | Escape code string as needed for HTML. +codeStringToHtml :: String -> String +codeStringToHtml [] = [] +codeStringToHtml (x:xs) = case x of + '&' -> "&" ++ codeStringToHtml xs + '<' -> "<" ++ codeStringToHtml xs + _ -> x:(codeStringToHtml xs) + +-- | Escape string to HTML appropriate for attributes +attributeStringToHtml :: String -> String +attributeStringToHtml = gsub "\"" """ + +-- | Returns an HTML header with appropriate bibliographic information. +htmlHeader :: WriterOptions -> Meta -> String +htmlHeader options (Meta title authors date) = + let titletext = if (null title) then + "" + else + "<title>" ++ (inlineListToHtml options title) ++ "</title>\n" + authortext = if (null authors) then + "" + else + "<meta name=\"author\" content=\"" ++ + (joinWithSep ", " (map stringToHtml authors)) ++ "\" />\n" + datetext = if (date == "") then + "" + else + "<meta name=\"date\" content=\"" ++ (stringToHtml date) ++ "\" />\n" in + (writerHeader options) ++ authortext ++ datetext ++ titletext ++ "</head>\n<body>\n" + +-- | Convert Pandoc block element to HTML. +blockToHtml :: WriterOptions -> Block -> String +blockToHtml options Blank = "\n" +blockToHtml options Null = "" +blockToHtml options (Plain lst) = inlineListToHtml options lst +blockToHtml options (Para lst) = "<p>" ++ (inlineListToHtml options lst) ++ "</p>\n" +blockToHtml options (BlockQuote blocks) = + if (writerS5 options) then -- in S5, treat list in blockquote specially + -- if default is incremental, make it nonincremental; otherwise incremental + let inc = not (writerIncremental options) in + case blocks of + [BulletList lst] -> blockToHtml (options {writerIncremental = inc}) (BulletList lst) + [OrderedList lst] -> blockToHtml (options {writerIncremental = inc}) (OrderedList lst) + otherwise -> "<blockquote>\n" ++ (concatMap (blockToHtml options) blocks) ++ + "</blockquote>\n" + else + "<blockquote>\n" ++ (concatMap (blockToHtml options) blocks) ++ "</blockquote>\n" +blockToHtml options (Note ref lst) = + let marker = "<span class=\"pandocNoteMarker\"><a name=\"note_" ++ ref ++ + "\" href=\"#ref_" ++ ref ++ "\">(" ++ ref ++ ")</a></span> " in + let contents = (concatMap (blockToHtml options) lst) in + let contents' = case contents of + ('<':'p':'>':rest) -> "<p class=\"first\">" ++ marker ++ rest ++ "\n" + otherwise -> marker ++ contents ++ "\n" in + "<div class=\"pandocNote\">\n" ++ contents' ++ "</div>\n" +blockToHtml options (Key _ _) = "" +blockToHtml options (CodeBlock str) = "<pre><code>" ++ (codeStringToHtml str) ++ + "</code></pre>\n" +blockToHtml options (RawHtml str) = str +blockToHtml options (BulletList lst) = + let attribs = if (writerIncremental options) then " class=\"incremental\"" else "" in + "<ul" ++ attribs ++ ">\n" ++ (concatMap (listItemToHtml options) lst) ++ "</ul>\n" +blockToHtml options (OrderedList lst) = + let attribs = if (writerIncremental options) then " class=\"incremental\"" else "" in + "<ol" ++ attribs ++ ">\n" ++ (concatMap (listItemToHtml options) lst) ++ "</ol>\n" +blockToHtml options HorizontalRule = "<hr />\n" +blockToHtml options (Header level lst) = if ((level > 0) && (level <= 6)) then + "<h" ++ (show level) ++ ">" ++ + (inlineListToHtml options lst) ++ + "</h" ++ (show level) ++ ">\n" + else + "<p>" ++ (inlineListToHtml options lst) ++ "</p>\n" +listItemToHtml options list = "<li>" ++ (concatMap (blockToHtml options) list) ++ "</li>\n" + +-- | Convert list of Pandoc inline elements to HTML. +inlineListToHtml :: WriterOptions -> [Inline] -> String +inlineListToHtml options lst = + -- consolidate adjacent Str and Space elements for more intelligent + -- smartypants filtering + let lst' = consolidateList lst in + concatMap (inlineToHtml options) lst' + +-- | Convert Pandoc inline element to HTML. +inlineToHtml :: WriterOptions -> Inline -> String +inlineToHtml options (Emph lst) = "<em>" ++ (inlineListToHtml options lst) ++ "</em>" +inlineToHtml options (Strong lst) = "<strong>" ++ (inlineListToHtml options lst) ++ "</strong>" +inlineToHtml options (Code str) = "<code>" ++ (codeStringToHtml str) ++ "</code>" +inlineToHtml options (Str str) = if (writerSmartypants options) then + stringToSmartHtml str + else + stringToHtml str +inlineToHtml options (TeX str) = (codeStringToHtml str) +inlineToHtml options (HtmlInline str) = str +inlineToHtml options (LineBreak) = "<br />\n" +inlineToHtml options Space = " " +inlineToHtml options (Link text (Src src tit)) = + let title = attributeStringToHtml tit in + if (isPrefixOf "mailto:" src) then + obfuscateLink options text src + else + "<a href=\"" ++ (codeStringToHtml src) ++ "\"" ++ + (if tit /= "" then " title=\"" ++ title ++ "\">" else ">") ++ + (inlineListToHtml options text) ++ "</a>" +inlineToHtml options (Link text (Ref [])) = "[" ++ (inlineListToHtml options text) ++ "]" +inlineToHtml options (Link text (Ref ref)) = "[" ++ (inlineListToHtml options text) ++ "][" ++ + (inlineListToHtml options ref) ++ "]" -- this is what markdown does, for better or worse +inlineToHtml options (Image alt (Src source tit)) = + let title = attributeStringToHtml tit + alternate = inlineListToHtml options alt in + "<img src=\"" ++ source ++ "\"" ++ + (if tit /= "" then " title=\"" ++ title ++ "\"" else "") ++ + (if alternate /= "" then " alt=\"" ++ alternate ++ "\"" else "") ++ ">" +inlineToHtml options (Image alternate (Ref [])) = + "![" ++ (inlineListToHtml options alternate) ++ "]" +inlineToHtml options (Image alternate (Ref ref)) = + "![" ++ (inlineListToHtml options alternate) ++ "][" ++ (inlineListToHtml options ref) ++ "]" +inlineToHtml options (NoteRef ref) = + "<span class=\"pandocNoteRef\"><a name=\"ref_" ++ ref ++ "\" href=\"#note_" ++ ref ++ + "\">(" ++ ref ++ ")</a></span>" + diff --git a/src/Text/Pandoc/Writers/LaTeX.hs b/src/Text/Pandoc/Writers/LaTeX.hs new file mode 100644 index 000000000..b77789e90 --- /dev/null +++ b/src/Text/Pandoc/Writers/LaTeX.hs @@ -0,0 +1,164 @@ +-- | Convert Pandoc to LaTeX. +module Text.Pandoc.Writers.LaTeX ( + writeLaTeX + ) where +import Text.Pandoc.Definition +import Text.Pandoc.Shared +import List ( (\\) ) + +-- | Convert Pandoc to LaTeX. +writeLaTeX :: WriterOptions -> Pandoc -> String +writeLaTeX options (Pandoc meta blocks) = + let notes = filter isNoteBlock blocks in -- assumes all notes are at outer level + let body = (writerIncludeBefore options) ++ + (concatMap (blockToLaTeX notes) (replaceReferenceLinks blocks)) ++ + (writerIncludeAfter options) in + let head = if writerStandalone options then + latexHeader notes options meta + else + "" in + let foot = if writerStandalone options then "\n\\end{document}\n" else "" in + head ++ body ++ foot + +-- | Insert bibliographic information into LaTeX header. +latexHeader :: [Block] -- ^ List of note blocks to use in resolving note refs + -> WriterOptions -- ^ Options, including LaTeX header + -> Meta -- ^ Meta with bibliographic information + -> String +latexHeader notes options (Meta title authors date) = + let titletext = if null title then + "" + else + "\\title{" ++ inlineListToLaTeX notes title ++ "}\n" + authorstext = if null authors then + "" + else + "\\author{" ++ (joinWithSep "\\\\" (map stringToLaTeX authors)) ++ "}\n" + datetext = if date == "" then + "" + else + "\\date{" ++ stringToLaTeX date ++ "}\n" + maketitle = if null title then + "" + else + "\\maketitle\n" + secnumline = if (writerNumberSections options) then + "" + else + "\\setcounter{secnumdepth}{0}\n" + header = writerHeader options in + header ++ secnumline ++ titletext ++ authorstext ++ datetext ++ "\\begin{document}\n" ++ maketitle + + +-- escape things as needed for LaTeX (also ldots, dashes, quotes, etc.) + +escapeBrackets = backslashEscape "{}" +escapeSpecial = backslashEscape "$%&~_#" + +escapeBackslash = gsub "\\\\" "\\\\textbackslash{}" +fixBackslash = gsub "\\\\textbackslash\\\\\\{\\\\\\}" "\\\\textbackslash{}" +escapeHat = gsub "\\^" "\\\\^{}" +escapeBar = gsub "\\|" "\\\\textbar{}" +escapeLt = gsub "<" "\\\\textless{}" +escapeGt = gsub ">" "\\\\textgreater{}" + +escapeDoubleQuotes = + gsub "\"" "''" . -- rest are right quotes + gsub "([[:space:]])\"" "\\1``" . -- never right quote after space + gsub "\"('|`)([^[:punct:][:space:]])" "``{}`\\2" . -- "'word left + gsub "\"([^[:punct:][:space:]])" "``\\1" -- "word left + +escapeSingleQuotes = + gsub "('|`)(\"|``)" "`{}``" . -- '"word left + gsub "([^[:punct:][:space:]])`(s|S)" "\\1'\\2" . -- catch possessives + gsub "^'([^[:punct:][:space:]])" "`\\1" . -- 'word left + gsub "([[:space:]])'" "\\1`" . -- never right quote after space + gsub "([[:space:]])'([^[:punct:][:space:]])" "\\1`\\2" -- 'word left (leave possessives) + +escapeEllipses = gsub "\\.\\.\\.|\\. \\. \\." "\\ldots{}" + +escapeDashes = gsub "([0-9])-([0-9])" "\\1--\\2" . + gsub " -- " "---" . + gsub "([^[:punct:][:space:]])--([^[:punct:][:space:]])" "\\1---\\2" + +escapeSmart = escapeSingleQuotes . escapeDoubleQuotes . escapeDashes . escapeEllipses + +-- | Escape string for LaTeX (including smart quotes, dashes, ellipses) +stringToLaTeX :: String -> String +stringToLaTeX = escapeSmart . escapeGt . escapeLt . escapeBar . escapeHat . + escapeSpecial . fixBackslash . escapeBrackets . escapeBackslash + +-- | Remove all code elements from list of inline elements +-- (because it's illegal to have a \\verb inside a command argument) +deVerb :: [Inline] -> [Inline] +deVerb [] = [] +deVerb ((Code str):rest) = (Str str):(deVerb rest) +deVerb (other:rest) = other:(deVerb rest) + +-- | Convert Pandoc block element to LaTeX. +blockToLaTeX :: [Block] -- ^ List of note blocks to use in resolving note refs + -> Block -- ^ Block to convert + -> String +blockToLaTeX notes Blank = "\n" +blockToLaTeX notes Null = "" +blockToLaTeX notes (Plain lst) = inlineListToLaTeX notes lst ++ "\n" +blockToLaTeX notes (Para lst) = (inlineListToLaTeX notes lst) ++ "\n\n" +blockToLaTeX notes (BlockQuote lst) = + "\\begin{quote}\n" ++ (concatMap (blockToLaTeX notes) lst) ++ "\\end{quote}\n" +blockToLaTeX notes (Note ref lst) = "" +blockToLaTeX notes (Key _ _) = "" +blockToLaTeX notes (CodeBlock str) = "\\begin{verbatim}\n" ++ str ++ "\\end{verbatim}\n" +blockToLaTeX notes (RawHtml str) = "" +blockToLaTeX notes (BulletList lst) = + "\\begin{itemize}\n" ++ (concatMap (listItemToLaTeX notes) lst) ++ "\\end{itemize}\n" +blockToLaTeX notes (OrderedList lst) = + "\\begin{enumerate}\n" ++ (concatMap (listItemToLaTeX notes) lst) ++ "\\end{enumerate}\n" +blockToLaTeX notes HorizontalRule = "\\begin{center}\\rule{3in}{0.4pt}\\end{center}\n\n" +blockToLaTeX notes (Header level lst) = + if (level > 0) && (level <= 3) then + "\\" ++ (concat (replicate (level - 1) "sub")) ++ "section{" ++ + (inlineListToLaTeX notes (deVerb lst)) ++ "}\n\n" + else + (inlineListToLaTeX notes lst) ++ "\n\n" +listItemToLaTeX notes list = "\\item " ++ (concatMap (blockToLaTeX notes) list) + +-- | Convert list of inline elements to LaTeX. +inlineListToLaTeX :: [Block] -- ^ List of note blocks to use in resolving note refs + -> [Inline] -- ^ Inlines to convert + -> String +inlineListToLaTeX notes lst = + -- first, consolidate Str and Space for more effective smartquotes: + let lst' = consolidateList lst in + concatMap (inlineToLaTeX notes) lst' + +-- | Convert inline element to LaTeX +inlineToLaTeX :: [Block] -- ^ List of note blocks to use in resolving note refs + -> Inline -- ^ Inline to convert + -> String +inlineToLaTeX notes (Emph lst) = "\\emph{" ++ (inlineListToLaTeX notes (deVerb lst)) ++ "}" +inlineToLaTeX notes (Strong lst) = "\\textbf{" ++ (inlineListToLaTeX notes (deVerb lst)) ++ "}" +inlineToLaTeX notes (Code str) = "\\verb" ++ [chr] ++ stuffing ++ [chr] + where stuffing = str + chr = ((enumFromTo '!' '~') \\ stuffing) !! 0 +inlineToLaTeX notes (Str str) = stringToLaTeX str +inlineToLaTeX notes (TeX str) = str +inlineToLaTeX notes (HtmlInline str) = "" +inlineToLaTeX notes (LineBreak) = "\\\\\n" +inlineToLaTeX notes Space = " " +inlineToLaTeX notes (Link text (Src src tit)) = + "\\href{" ++ src ++ "}{" ++ (inlineListToLaTeX notes (deVerb text)) ++ "}" +inlineToLaTeX notes (Link text (Ref [])) = "[" ++ (inlineListToLaTeX notes text) ++ "]" +inlineToLaTeX notes (Link text (Ref ref)) = "[" ++ (inlineListToLaTeX notes text) ++ "][" ++ + (inlineListToLaTeX notes ref) ++ "]" -- this is what markdown does, for better or worse +inlineToLaTeX notes (Image alternate (Src source tit)) = "\\includegraphics{" ++ source ++ "}" +inlineToLaTeX notes (Image alternate (Ref [])) = + "![" ++ (inlineListToLaTeX notes alternate) ++ "]" +inlineToLaTeX notes (Image alternate (Ref ref)) = + "![" ++ (inlineListToLaTeX notes alternate) ++ "][" ++ (inlineListToLaTeX notes ref) ++ "]" +inlineToLaTeX [] (NoteRef ref) = "" +inlineToLaTeX ((Note firstref firstblocks):rest) (NoteRef ref) = + if (firstref == ref) then + "\\footnote{" ++ (stripTrailingNewlines (concatMap (blockToLaTeX rest) firstblocks)) ++ "}" + else + inlineToLaTeX rest (NoteRef ref) + diff --git a/src/Text/Pandoc/Writers/Markdown.hs b/src/Text/Pandoc/Writers/Markdown.hs new file mode 100644 index 000000000..b73090f62 --- /dev/null +++ b/src/Text/Pandoc/Writers/Markdown.hs @@ -0,0 +1,149 @@ +-- | Converts Pandoc to Markdown. +module Text.Pandoc.Writers.Markdown ( + writeMarkdown + ) where +import Text.Regex ( matchRegex, mkRegex ) +import Text.Pandoc.Definition +import Text.Pandoc.Shared +import Text.PrettyPrint.HughesPJ hiding ( Str ) + +-- | Convert Pandoc to Markdown. +writeMarkdown :: WriterOptions -> Pandoc -> String +writeMarkdown options (Pandoc meta blocks) = + let body = text (writerIncludeBefore options) <> + vcat (map (blockToMarkdown (writerTabStop options)) (formatKeys blocks)) $$ + text (writerIncludeAfter options) in + let head = if (writerStandalone options) then + ((metaToMarkdown meta) $$ text (writerHeader options)) + else + empty in + render $ head <> body + +-- | Escape special characters for Markdown. +escapeString :: String -> String +escapeString = backslashEscape "`<\\*_^" + +-- | Escape embedded \" in link title. +escapeLinkTitle :: String -> String +escapeLinkTitle = gsub "\"" "\\\\\"" + +-- | Take list of inline elements and return wrapped doc. +wrappedMarkdown :: [Inline] -> Doc +wrappedMarkdown lst = fsep $ map (fcat . (map inlineToMarkdown)) (splitBySpace lst) + +-- | Insert Blank block between key and non-key +formatKeys :: [Block] -> [Block] +formatKeys [] = [] +formatKeys [x] = [x] +formatKeys ((Key x1 y1):(Key x2 y2):rest) = (Key x1 y1):(formatKeys ((Key x2 y2):rest)) +formatKeys ((Key x1 y1):rest) = (Key x1 y1):Blank:(formatKeys rest) +formatKeys (x:(Key x1 y1):rest) = x:Blank:(formatKeys ((Key x1 y1):rest)) +formatKeys (x:rest) = x:(formatKeys rest) + +-- | Convert bibliographic information into Markdown header. +metaToMarkdown :: Meta -> Doc +metaToMarkdown (Meta [] [] "") = empty +metaToMarkdown (Meta title [] "") = (titleToMarkdown title) <> (text "\n") +metaToMarkdown (Meta title authors "") = + (titleToMarkdown title) <> (text "\n") <> (authorsToMarkdown authors) <> (text "\n") +metaToMarkdown (Meta title authors date) = + (titleToMarkdown title) <> (text "\n") <> (authorsToMarkdown authors) <> + (text "\n") <> (dateToMarkdown date) <> (text "\n") + +titleToMarkdown :: [Inline] -> Doc +titleToMarkdown lst = text "% " <> (inlineListToMarkdown lst) + +authorsToMarkdown :: [String] -> Doc +authorsToMarkdown lst = text "% " <> text (joinWithSep ", " (map escapeString lst)) + +dateToMarkdown :: String -> Doc +dateToMarkdown str = text "% " <> text (escapeString str) + +-- | Convert Pandoc block element to markdown. +blockToMarkdown :: Int -- ^ Tab stop + -> Block -- ^ Block element + -> Doc +blockToMarkdown tabStop Blank = text "" +blockToMarkdown tabStop Null = empty +blockToMarkdown tabStop (Plain lst) = wrappedMarkdown lst +blockToMarkdown tabStop (Para lst) = (wrappedMarkdown lst) <> (text "\n") +blockToMarkdown tabStop (BlockQuote lst) = + (vcat $ map (\line -> (text "> ") <> (text line)) $ lines $ render $ vcat $ + map (blockToMarkdown tabStop) lst) <> (text "\n") +blockToMarkdown tabStop (Note ref lst) = + let lns = lines $ render $ vcat $ map (blockToMarkdown tabStop) lst in + if null lns then + empty + else + let first = head lns + rest = tail lns in + text ("^(" ++ (escapeString ref) ++ ") ") <> (text first) $$ (vcat $ + map (\line -> (text "^ ") <> (text line)) rest) <> (text "\n") +blockToMarkdown tabStop (Key txt (Src src tit)) = + text " " <> char '[' <> inlineListToMarkdown txt <> char ']' <> text ": " <> text src <> + (if tit /= "" then (text (" \"" ++ (escapeLinkTitle tit) ++ "\"")) else empty) +blockToMarkdown tabStop (CodeBlock str) = (nest tabStop $ vcat $ map text (lines str)) <> + (if (endsWith '\n' str) then empty else text "\n") <> text "\n" +blockToMarkdown tabStop (RawHtml str) = text str +blockToMarkdown tabStop (BulletList lst) = + vcat (map (bulletListItemToMarkdown tabStop) lst) <> text "\n" +blockToMarkdown tabStop (OrderedList lst) = + vcat (zipWith (orderedListItemToMarkdown tabStop) (enumFromTo 1 (length lst)) lst) <> + text "\n" +blockToMarkdown tabStop HorizontalRule = text "\n* * * * *\n" +blockToMarkdown tabStop (Header level lst) = + text ((replicate level '#') ++ " ") <> (inlineListToMarkdown lst) <> (text "\n") +bulletListItemToMarkdown tabStop list = + hang (text "- ") tabStop (vcat (map (blockToMarkdown tabStop) list)) + +-- | Convert ordered list item (a list of blocks) to markdown. +orderedListItemToMarkdown :: Int -- ^ tab stop + -> Int -- ^ ordinal number of list item + -> [Block] -- ^ list item (list of blocks) + -> Doc +orderedListItemToMarkdown tabStop num list = + hang (text ((show num) ++ "." ++ spacer)) tabStop (vcat (map (blockToMarkdown tabStop) list)) + where spacer = if (num < 10) then " " else "" + +-- | Convert list of Pandoc inline elements to markdown. +inlineListToMarkdown :: [Inline] -> Doc +inlineListToMarkdown lst = hcat $ map inlineToMarkdown lst + +-- | Convert Pandoc inline element to markdown. +inlineToMarkdown :: Inline -> Doc +inlineToMarkdown (Emph lst) = text "*" <> (inlineListToMarkdown lst) <> text "*" +inlineToMarkdown (Strong lst) = text "**" <> (inlineListToMarkdown lst) <> text "**" +inlineToMarkdown (Code str) = + case (matchRegex (mkRegex "``") str) of + Just match -> text ("` " ++ str ++ " `") + Nothing -> case (matchRegex (mkRegex "`") str) of + Just match -> text ("`` " ++ str ++ " ``") + Nothing -> text ("`" ++ str ++ "`") +inlineToMarkdown (Str str) = text $ escapeString str +inlineToMarkdown (TeX str) = text str +inlineToMarkdown (HtmlInline str) = text str +inlineToMarkdown (LineBreak) = text " \n" +inlineToMarkdown Space = char ' ' +inlineToMarkdown (Link txt (Src src tit)) = + let linktext = if (null txt) || (txt == [Str ""]) then + text "link" + else + inlineListToMarkdown txt in + char '[' <> linktext <> char ']' <> char '(' <> text src <> + (if tit /= "" then (text (" \"" ++ (escapeLinkTitle tit) ++ "\"")) else empty) <> char ')' +inlineToMarkdown (Link txt (Ref [])) = char '[' <> inlineListToMarkdown txt <> text "][]" +inlineToMarkdown (Link txt (Ref ref)) = char '[' <> inlineListToMarkdown txt <> char ']' <> + char '[' <> inlineListToMarkdown ref <> char ']' +inlineToMarkdown (Image alternate (Src source tit)) = + let alt = if (null alternate) || (alternate == [Str ""]) then + text "image" + else + inlineListToMarkdown alternate in + char '!' <> char '[' <> alt <> char ']' <> char '(' <> text source <> + (if tit /= "" then (text (" \"" ++ (escapeLinkTitle tit) ++ "\"")) else empty) <> char ')' +inlineToMarkdown (Image alternate (Ref [])) = + char '!' <> char '[' <> inlineListToMarkdown alternate <> char ']' +inlineToMarkdown (Image alternate (Ref ref)) = + char '!' <> char '[' <> inlineListToMarkdown alternate <> char ']' <> + char '[' <> inlineListToMarkdown ref <> char ']' +inlineToMarkdown (NoteRef ref) = char '^' <> char '(' <> text (escapeString ref) <> char ')' diff --git a/src/Text/Pandoc/Writers/RST.hs b/src/Text/Pandoc/Writers/RST.hs new file mode 100644 index 000000000..37d895336 --- /dev/null +++ b/src/Text/Pandoc/Writers/RST.hs @@ -0,0 +1,188 @@ +-- | Converts Pandoc to reStructuredText. +module Text.Pandoc.Writers.RST ( + writeRST + ) where +import Text.Pandoc.Definition +import Text.Pandoc.Shared +import List ( nubBy ) +import Text.PrettyPrint.HughesPJ hiding ( Str ) + +-- | Convert Pandoc to reStructuredText. +writeRST :: WriterOptions -> Pandoc -> String +writeRST options (Pandoc meta blocks) = + let (main, refs) = unzip $ map (blockToRST (writerTabStop options)) + (reformatBlocks $ replaceReferenceLinks blocks) + top = if (writerStandalone options) then + (metaToRST meta) $$ text (writerHeader options) + else + empty in + let refs' = nubBy (\x y -> (render x) == (render y)) refs in -- remove duplicate keys + let body = text (writerIncludeBefore options) <> + vcat main $$ text (writerIncludeAfter options) in + render $ top <> body $$ vcat refs' + +-- | Escape special RST characters. +escapeString :: String -> String +escapeString = backslashEscape "`\\|*_" + +-- | Convert list of inline elements into one 'Doc' of wrapped text and another +-- containing references. +wrappedRST :: [Inline] -> (Doc, Doc) +wrappedRST lst = + let words = splitBySpace lst in + (fsep $ map (fcat . (map (fst . inlineToRST))) words, vcat (map (snd . inlineToRST) lst)) + +-- | Remove reference keys, and make sure there are blanks before each list. +reformatBlocks :: [Block] -> [Block] +reformatBlocks [] = [] +reformatBlocks ((Plain x):(OrderedList y):rest) = + (Para x):(reformatBlocks ((OrderedList y):rest)) +reformatBlocks ((Plain x):(BulletList y):rest) = (Para x):(reformatBlocks ((BulletList y):rest)) +reformatBlocks ((OrderedList x):rest) = + (OrderedList (map reformatBlocks x)):(reformatBlocks rest) +reformatBlocks ((BulletList x):rest) = (BulletList (map reformatBlocks x)):(reformatBlocks rest) +reformatBlocks ((BlockQuote x):rest) = (BlockQuote (reformatBlocks x)):(reformatBlocks rest) +reformatBlocks ((Note ref x):rest) = (Note ref (reformatBlocks x)):(reformatBlocks rest) +reformatBlocks ((Key x1 y1):rest) = reformatBlocks rest +reformatBlocks (x:rest) = x:(reformatBlocks rest) + +-- | Convert bibliographic information to 'Doc'. +metaToRST :: Meta -> Doc +metaToRST (Meta title authors date) = + (titleToRST title) <> (authorsToRST authors) <> (dateToRST date) + +-- | Convert title to 'Doc'. +titleToRST :: [Inline] -> Doc +titleToRST [] = empty +titleToRST lst = + let title = fst $ inlineListToRST lst in + let titleLength = length $ render title in + let border = text (replicate titleLength '=') in + border <> char '\n' <> title <> char '\n' <> border <> text "\n\n" + +-- | Convert author list to 'Doc'. +authorsToRST :: [String] -> Doc +authorsToRST [] = empty +authorsToRST (first:rest) = text ":Author: " <> text first <> char '\n' <> (authorsToRST rest) + +-- | Convert date to 'Doc'. +dateToRST :: String -> Doc +dateToRST [] = empty +dateToRST str = text ":Date: " <> text (escapeString str) <> char '\n' + +-- | Convert Pandoc block element to a 'Doc' containing the main text and +-- another one containing any references. +blockToRST :: Int -- ^ tab stop + -> Block -- ^ block element to convert + -> (Doc, Doc) -- ^ first element is text, second is references for end of file +blockToRST tabStop Blank = (text "\n", empty) +blockToRST tabStop Null = (empty, empty) +blockToRST tabStop (Plain lst) = wrappedRST lst +blockToRST tabStop (Para [TeX str]) = -- raw latex block + let str' = if (endsWith '\n' str) then (str ++ "\n") else (str ++ "\n\n") in + (hang (text "\n.. raw:: latex\n") 3 (vcat $ map text (lines str')), empty) +blockToRST tabStop (Para lst) = ((fst $ wrappedRST lst) <> (text "\n"), snd $ wrappedRST lst) +blockToRST tabStop (BlockQuote lst) = + let (main, refs) = unzip $ map (blockToRST tabStop) lst in + ((nest tabStop $ vcat $ main) <> text "\n", vcat refs) +blockToRST tabStop (Note ref blocks) = + let (main, refs) = unzip $ map (blockToRST tabStop) blocks in + ((hang (text ".. [" <> text (escapeString ref) <> text "] ") 3 (vcat main)), vcat refs) +blockToRST tabStop (Key txt (Src src tit)) = + (text "ERROR - KEY FOUND", empty) -- shouldn't have a key here +blockToRST tabStop (CodeBlock str) = + (hang (text "::\n") tabStop (vcat $ map text (lines ('\n':(str ++ "\n")))), empty) +blockToRST tabStop (RawHtml str) = + let str' = if (endsWith '\n' str) then (str ++ "\n") else (str ++ "\n\n") in + (hang (text "\n.. raw:: html\n") 3 (vcat $ map text (lines str')), empty) +blockToRST tabStop (BulletList lst) = + let (main, refs) = unzip $ map (bulletListItemToRST tabStop) lst in + (vcat main <> text "\n", vcat refs) +blockToRST tabStop (OrderedList lst) = + let (main, refs) = + unzip $ zipWith (orderedListItemToRST tabStop) (enumFromTo 1 (length lst)) lst in + (vcat main <> text "\n", vcat refs) +blockToRST tabStop HorizontalRule = (text "--------------\n", empty) +blockToRST tabStop (Header level lst) = + let (headerText, refs) = inlineListToRST lst in + let headerLength = length $ render headerText in + let headerChar = if (level > 5) then ' ' else "=-~^'" !! (level - 1) in + let border = text $ replicate headerLength headerChar in + (headerText <> char '\n' <> border <> char '\n', refs) + +-- | Convert bullet list item (list of blocks) to reStructuredText. +-- Returns a pair of 'Doc', the first the main text, the second references +bulletListItemToRST :: Int -- ^ tab stop + -> [Block] -- ^ list item (list of blocks) + -> (Doc, Doc) +bulletListItemToRST tabStop list = + let (main, refs) = unzip $ map (blockToRST tabStop) list in + (hang (text "- ") tabStop (vcat main), (vcat refs)) + +-- | Convert an ordered list item (list of blocks) to reStructuredText. +-- Returns a pair of 'Doc', the first the main text, the second references +orderedListItemToRST :: Int -- ^ tab stop + -> Int -- ^ ordinal number of list item + -> [Block] -- ^ list item (list of blocks) + -> (Doc, Doc) +orderedListItemToRST tabStop num list = + let (main, refs) = unzip $ map (blockToRST tabStop) list + spacer = if (length (show num) < 2) then " " else "" in + (hang (text ((show num) ++ "." ++ spacer)) tabStop (vcat main), (vcat refs)) + +-- | Convert a list of inline elements to reStructuredText. +-- Returns a pair of 'Doc', the first the main text, the second references. +inlineListToRST :: [Inline] -> (Doc, Doc) +inlineListToRST lst = let (main, refs) = unzip $ map inlineToRST lst in + (hcat main, hcat refs) + +-- | Convert an inline element to reStructuredText. +-- Returns a pair of 'Doc', the first the main text, the second references. +inlineToRST :: Inline -> (Doc, Doc) -- second Doc is list of refs for end of file +inlineToRST (Emph lst) = let (main, refs) = inlineListToRST lst in + (text "*" <> main <> text "*", refs) +inlineToRST (Strong lst) = let (main, refs) = inlineListToRST lst in + (text "**" <> main <> text "**", refs) +inlineToRST (Code str) = (text $ "``" ++ str ++ "``", empty) +inlineToRST (Str str) = (text $ escapeString str, empty) +inlineToRST (TeX str) = (text str, empty) +inlineToRST (HtmlInline str) = (empty, empty) +inlineToRST (LineBreak) = inlineToRST Space -- RST doesn't have line breaks +inlineToRST Space = (char ' ', empty) +-- +-- Note: can assume reference links have been replaced where possible with explicit links. +-- +inlineToRST (Link txt (Src src tit)) = + let (linktext, ref') = if (null txt) || (txt == [Str ""]) then + (text "link", empty) + else + inlineListToRST $ normalizeSpaces txt in + let link = char '`' <> linktext <> text "`_" + linktext' = render linktext in + let linktext'' = if (':' `elem` linktext') then "`" ++ linktext' ++ "`" else linktext' in + let ref = text ".. _" <> text linktext'' <> text ": " <> text src in + (link, ref' $$ ref) +inlineToRST (Link txt (Ref [])) = + let (linktext, refs) = inlineListToRST txt in + (char '[' <> linktext <> char ']', refs) +inlineToRST (Link txt (Ref ref)) = + let (linktext, refs1) = inlineListToRST txt + (reftext, refs2) = inlineListToRST ref in + (char '[' <> linktext <> text "][" <> reftext <> char ']', refs1 $$ refs2) +inlineToRST (Image alternate (Src source tit)) = + let (alt, ref') = if (null alternate) || (alternate == [Str ""]) then + (text "image", empty) + else + inlineListToRST $ normalizeSpaces alternate in + let link = char '|' <> alt <> char '|' in + let ref = text ".. " <> link <> text " image:: " <> text source in + (link, ref' $$ ref) +inlineToRST (Image alternate (Ref [])) = + let (alttext, refs) = inlineListToRST alternate in + (char '|' <> alttext <> char '|', refs) +-- The following case won't normally occur... +inlineToRST (Image alternate (Ref ref)) = + let (alttext, refs1) = inlineListToRST alternate + (reftext, refs2) = inlineListToRST ref in + (char '|' <> alttext <> char '|', refs1 $$ refs2) +inlineToRST (NoteRef ref) = (text " [" <> text (escapeString ref) <> char ']' <> char '_', empty) diff --git a/src/Text/Pandoc/Writers/RTF.hs b/src/Text/Pandoc/Writers/RTF.hs new file mode 100644 index 000000000..64f17cc74 --- /dev/null +++ b/src/Text/Pandoc/Writers/RTF.hs @@ -0,0 +1,194 @@ +-- | Convert Pandoc to rich text format. +module Text.Pandoc.Writers.RTF ( + writeRTF + ) where +import Text.Pandoc.Definition +import Text.Pandoc.Shared +import List ( isSuffixOf ) +import Char ( ord, chr ) + +-- | Convert Pandoc to a string in rich text format. +writeRTF :: WriterOptions -> Pandoc -> String +writeRTF options (Pandoc meta blocks) = + let notes = filter isNoteBlock blocks in -- assumes all notes are at outer level + let head = if writerStandalone options then + rtfHeader notes (writerHeader options) meta + else + "" + foot = if writerStandalone options then "\n}\n" else "" + body = (writerIncludeBefore options) ++ + (concatMap (blockToRTF notes 0) (replaceReferenceLinks blocks)) ++ + (writerIncludeAfter options) in + head ++ body ++ foot + +-- | Convert unicode characters (> 127) into rich text format representation. +handleUnicode :: String -> String +handleUnicode [] = [] +handleUnicode (c:cs) = if (ord c) > 127 then + '\\':'u':(show (ord c)) ++ "?" ++ (handleUnicode cs) + else + c:(handleUnicode cs) + +escapeSpecial = backslashEscape "{\\}" +escapeTab = gsub "\\\\t" "\\\\tab " + +-- | Escape strings as needed for rich text format. +stringToRTF :: String -> String +stringToRTF = handleUnicode . escapeSpecial . escapeTab + +-- | Escape raw LaTeX strings for RTF. Don't escape \t; it might +-- be the first letter of a command! +latexStringToRTF :: String -> String +latexStringToRTF = handleUnicode . escapeSpecial + +-- | Escape things as needed for code block in RTF. +codeStringToRTF :: String -> String +codeStringToRTF str = joinWithSep "\\line\n" (lines (stringToRTF str)) + +-- | Deal with raw LaTeX. +latexToRTF :: String -> String +latexToRTF str = "{\\cf1 " ++ (latexStringToRTF str) ++ "\\cf0 } " + +-- | Make a paragraph with first-line indent, block indent, and space after. +rtfParSpaced :: Int -- ^ space after (in twips) + -> Int -- ^ block indent (in twips) + -> Int -- ^ first line indent (relative to block) (in twips) + -> String -- ^ string with content + -> String +rtfParSpaced spaceAfter indent firstLineIndent content = + "{\\pard \\sa" ++ (show spaceAfter) ++ " \\li" ++ (show indent) ++ + " \\fi" ++ (show firstLineIndent) ++ " " ++ content ++ "\\par}\n" + +-- | Default paragraph. +rtfPar :: Int -- ^ block indent (in twips) + -> Int -- ^ first line indent (relative to block) (in twips) + -> String -- ^ string with content + -> String +rtfPar = rtfParSpaced 180 + +-- | Compact paragraph (e.g. for compact list items). +rtfCompact :: Int -- ^ block indent (in twips) + -> Int -- ^ first line indent (relative to block) (in twips) + -> String -- ^ string with content + -> String +rtfCompact = rtfParSpaced 0 + +-- number of twips to indent +indentIncrement = 720 +listIncrement = 360 + +-- | Returns appropriate bullet list marker for indent level. +bulletMarker :: Int -> String +bulletMarker indent = case (indent `mod` 720) of + 0 -> "\\bullet " + otherwise -> "\\endash " + +-- | Returns appropriate (list of) ordered list markers for indent level. +orderedMarkers :: Int -> [String] +orderedMarkers indent = case (indent `mod` 720) of + 0 -> map (\x -> show x ++ ".") [1..] + otherwise -> map (\x -> show x ++ ".") $ cycle ['a'..'z'] + +-- | Returns RTF header. +rtfHeader :: [Block] -- ^ list of note blocks + -> String -- ^ header text + -> Meta -- ^ bibliographic information + -> String +rtfHeader notes headerText (Meta title authors date) = + let titletext = if null title then + "" + else + rtfPar 0 0 ("\\qc \\b \\fs36 " ++ inlineListToRTF notes title) + authorstext = if null authors then + "" + else + rtfPar 0 0 ("\\qc " ++ (joinWithSep "\\" (map stringToRTF authors))) + datetext = if date == "" then "" else rtfPar 0 0 ("\\qc " ++ stringToRTF date) in + let spacer = if null (titletext ++ authorstext ++ datetext) then "" else rtfPar 0 0 "" in + headerText ++ titletext ++ authorstext ++ datetext ++ spacer + +-- | Convert Pandoc block element to RTF. +blockToRTF :: [Block] -- ^ list of note blocks + -> Int -- ^ indent level + -> Block -- ^ block to convert + -> String +blockToRTF notes indent Blank = rtfPar indent 0 "" +blockToRTF notes indent Null = "" +blockToRTF notes indent (Plain lst) = rtfCompact indent 0 (inlineListToRTF notes lst) +blockToRTF notes indent (Para lst) = rtfPar indent 0 (inlineListToRTF notes lst) +blockToRTF notes indent (BlockQuote lst) = + concatMap (blockToRTF notes (indent + indentIncrement)) lst +blockToRTF notes indent (Note ref lst) = "" -- there shouldn't be any after filtering +blockToRTF notes indent (Key _ _) = "" +blockToRTF notes indent (CodeBlock str) = rtfPar indent 0 ("\\f1 " ++ (codeStringToRTF str)) +blockToRTF notes indent (RawHtml str) = "" +blockToRTF notes indent (BulletList lst) = + spaceAtEnd $ concatMap (listItemToRTF notes indent (bulletMarker indent)) lst +blockToRTF notes indent (OrderedList lst) = + spaceAtEnd $ concat $ zipWith (listItemToRTF notes indent) (orderedMarkers indent) lst +blockToRTF notes indent HorizontalRule = + rtfPar indent 0 "\\qc \\emdash\\emdash\\emdash\\emdash\\emdash" +blockToRTF notes indent (Header level lst) = + rtfPar indent 0 ("\\b \\fs" ++ (show (40 - (level * 4))) ++ " " ++ + (inlineListToRTF notes lst)) + +-- | Ensure that there's the same amount of space after compact +-- lists as after regular lists. +spaceAtEnd :: String -> String +spaceAtEnd str = + if isSuffixOf "\\par}\n" str then + (take ((length str) - 6) str) ++ "\\sa180\\par}\n" + else + str + +-- | Convert list item (list of blocks) to RTF. +listItemToRTF :: [Block] -- ^ list of note blocks + -> Int -- ^ indent level + -> String -- ^ list start marker + -> [Block] -- ^ list item (list of blocks) + -> [Char] +listItemToRTF notes indent marker [] = + rtfCompact (indent + listIncrement) (0 - listIncrement) + (marker ++ "\\tx" ++ (show listIncrement) ++ "\\tab ") +listItemToRTF notes indent marker list = + let (first:rest) = map (blockToRTF notes (indent + listIncrement)) list in + let modFirst = gsub "\\\\fi-?[0-9]+" ("\\\\fi" ++ (show (0 - listIncrement)) ++ + " " ++ marker ++ "\\\\tx" ++ (show listIncrement) ++ "\\\\tab") first in + modFirst ++ (concat rest) + +-- | Convert list of inline items to RTF. +inlineListToRTF :: [Block] -- ^ list of note blocks + -> [Inline] -- ^ list of inlines to convert + -> String +inlineListToRTF notes lst = concatMap (inlineToRTF notes) lst + +-- | Convert inline item to RTF. +inlineToRTF :: [Block] -- ^ list of note blocks + -> Inline -- ^ inline to convert + -> String +inlineToRTF notes (Emph lst) = "{\\i " ++ (inlineListToRTF notes lst) ++ "} " +inlineToRTF notes (Strong lst) = "{\\b " ++ (inlineListToRTF notes lst) ++ "} " +inlineToRTF notes (Code str) = "{\\f1 " ++ (codeStringToRTF str) ++ "} " +inlineToRTF notes (Str str) = stringToRTF str +inlineToRTF notes (TeX str) = latexToRTF str +inlineToRTF notes (HtmlInline str) = "" +inlineToRTF notes (LineBreak) = "\\line " +inlineToRTF notes Space = " " +inlineToRTF notes (Link text (Src src tit)) = + "{\\field{\\*\\fldinst{HYPERLINK \"" ++ (codeStringToRTF src) ++ "\"}}{\\fldrslt{\\ul\n" + ++ (inlineListToRTF notes text) ++ "\n}}}\n" +inlineToRTF notes (Link text (Ref [])) = "[" ++ (inlineListToRTF notes text) ++ "]" +inlineToRTF notes (Link text (Ref ref)) = "[" ++ (inlineListToRTF notes text) ++ "][" ++ + (inlineListToRTF notes ref) ++ "]" -- this is what markdown does, for better or worse +inlineToRTF notes (Image alternate (Src source tit)) = "{\\cf1 [image: " ++ source ++ "]\\cf0}" +inlineToRTF notes (Image alternate (Ref [])) = "![" ++ (inlineListToRTF notes alternate) ++ "]" +inlineToRTF notes (Image alternate (Ref ref)) = "![" ++ (inlineListToRTF notes alternate) ++ + "][" ++ (inlineListToRTF notes ref) ++ "]" +inlineToRTF [] (NoteRef ref) = "" +inlineToRTF ((Note firstref firstblocks):rest) (NoteRef ref) = + if firstref == ref then + "{\\super\\chftn}{\\*\\footnote\\chftn\\~\\plain\\pard " ++ + (concatMap (blockToRTF rest 0) firstblocks) ++ "}" + else + inlineToRTF rest (NoteRef ref) + diff --git a/src/Text/Pandoc/Writers/S5.hs b/src/Text/Pandoc/Writers/S5.hs new file mode 100644 index 000000000..2d0b913a3 --- /dev/null +++ b/src/Text/Pandoc/Writers/S5.hs @@ -0,0 +1,95 @@ +---------------------------------------------------- +-- Do not edit this file by hand. Edit +-- 'templates/S5.hs' +-- and run ./fillTemplates.pl Text/Pandoc/Writers/S5.hs +---------------------------------------------------- + +-- | Definitions for creation of S5 powerpoint-like HTML. +-- (See <http://meyerweb.com/eric/tools/s5/>.) +module Text.Pandoc.Writers.S5 ( + -- * Strings + s5Javascript, + s5CSS, + s5Links, + -- * Functions + writeS5, + insertS5Structure + ) where +import Text.Pandoc.Shared ( joinWithSep, WriterOptions ) +import Text.Pandoc.Writers.HTML ( writeHtml ) +import Text.Pandoc.Definition + +s5Javascript :: String +s5Javascript = "<script type=\"text/javascript\">\n// S5 v1.1 slides.js -- released into the Public Domain\n//\n// Please see http://www.meyerweb.com/eric/tools/s5/credits.html for information \n// about all the wonderful and talented contributors to this code!\n\nvar undef;\nvar slideCSS = '';\nvar snum = 0;\nvar smax = 1;\nvar incpos = 0;\nvar number = undef;\nvar s5mode = true;\nvar defaultView = 'slideshow';\nvar controlVis = 'visible';\n\nvar isIE = navigator.appName == 'Microsoft Internet Explorer' && navigator.userAgent.indexOf('Opera') < 1 ? 1 : 0;\nvar isOp = navigator.userAgent.indexOf('Opera') > -1 ? 1 : 0;\nvar isGe = navigator.userAgent.indexOf('Gecko') > -1 && navigator.userAgent.indexOf('Safari') < 1 ? 1 : 0;\n\nfunction hasClass(object, className) {\n\tif (!object.className) return false;\n\treturn (object.className.search('(^|\\\\s)' + className + '(\\\\s|$)') != -1);\n}\n\nfunction hasValue(object, value) {\n\tif (!object) return false;\n\treturn (object.search('(^|\\\\s)' + value + '(\\\\s|$)') != -1);\n}\n\nfunction removeClass(object,className) {\n\tif (!object) return;\n\tobject.className = object.className.replace(new RegExp('(^|\\\\s)'+className+'(\\\\s|$)'), RegExp.$1+RegExp.$2);\n}\n\nfunction addClass(object,className) {\n\tif (!object || hasClass(object, className)) return;\n\tif (object.className) {\n\t\tobject.className += ' '+className;\n\t} else {\n\t\tobject.className = className;\n\t}\n}\n\nfunction GetElementsWithClassName(elementName,className) {\n\tvar allElements = document.getElementsByTagName(elementName);\n\tvar elemColl = new Array();\n\tfor (var i = 0; i< allElements.length; i++) {\n\t\tif (hasClass(allElements[i], className)) {\n\t\t\telemColl[elemColl.length] = allElements[i];\n\t\t}\n\t}\n\treturn elemColl;\n}\n\nfunction isParentOrSelf(element, id) {\n\tif (element == null || element.nodeName=='BODY') return false;\n\telse if (element.id == id) return true;\n\telse return isParentOrSelf(element.parentNode, id);\n}\n\nfunction nodeValue(node) {\n\tvar result = \"\";\n\tif (node.nodeType == 1) {\n\t\tvar children = node.childNodes;\n\t\tfor (var i = 0; i < children.length; ++i) {\n\t\t\tresult += nodeValue(children[i]);\n\t\t}\t\t\n\t}\n\telse if (node.nodeType == 3) {\n\t\tresult = node.nodeValue;\n\t}\n\treturn(result);\n}\n\nfunction slideLabel() {\n\tvar slideColl = GetElementsWithClassName('*','slide');\n\tvar list = document.getElementById('jumplist');\n\tsmax = slideColl.length;\n\tfor (var n = 0; n < smax; n++) {\n\t\tvar obj = slideColl[n];\n\n\t\tvar did = 'slide' + n.toString();\n\t\tobj.setAttribute('id',did);\n\t\tif (isOp) continue;\n\n\t\tvar otext = '';\n\t\tvar menu = obj.firstChild;\n\t\tif (!menu) continue; // to cope with empty slides\n\t\twhile (menu && menu.nodeType == 3) {\n\t\t\tmenu = menu.nextSibling;\n\t\t}\n\t \tif (!menu) continue; // to cope with slides with only text nodes\n\n\t\tvar menunodes = menu.childNodes;\n\t\tfor (var o = 0; o < menunodes.length; o++) {\n\t\t\totext += nodeValue(menunodes[o]);\n\t\t}\n\t\tlist.options[list.length] = new Option(n + ' : ' + otext, n);\n\t}\n}\n\nfunction currentSlide() {\n\tvar cs;\n\tif (document.getElementById) {\n\t\tcs = document.getElementById('currentSlide');\n\t} else {\n\t\tcs = document.currentSlide;\n\t}\n\tcs.innerHTML = '<span id=\"csHere\">' + snum + '<\\/span> ' + \n\t\t'<span id=\"csSep\">\\/<\\/span> ' + \n\t\t'<span id=\"csTotal\">' + (smax-1) + '<\\/span>';\n\tif (snum == 0) {\n\t\tcs.style.visibility = 'hidden';\n\t} else {\n\t\tcs.style.visibility = 'visible';\n\t}\n}\n\nfunction go(step) {\n\tif (document.getElementById('slideProj').disabled || step == 0) return;\n\tvar jl = document.getElementById('jumplist');\n\tvar cid = 'slide' + snum;\n\tvar ce = document.getElementById(cid);\n\tif (incrementals[snum].length > 0) {\n\t\tfor (var i = 0; i < incrementals[snum].length; i++) {\n\t\t\tremoveClass(incrementals[snum][i], 'current');\n\t\t\tremoveClass(incrementals[snum][i], 'incremental');\n\t\t}\n\t}\n\tif (step != 'j') {\n\t\tsnum += step;\n\t\tlmax = smax - 1;\n\t\tif (snum > lmax) snum = lmax;\n\t\tif (snum < 0) snum = 0;\n\t} else\n\t\tsnum = parseInt(jl.value);\n\tvar nid = 'slide' + snum;\n\tvar ne = document.getElementById(nid);\n\tif (!ne) {\n\t\tne = document.getElementById('slide0');\n\t\tsnum = 0;\n\t}\n\tif (step < 0) {incpos = incrementals[snum].length} else {incpos = 0;}\n\tif (incrementals[snum].length > 0 && incpos == 0) {\n\t\tfor (var i = 0; i < incrementals[snum].length; i++) {\n\t\t\tif (hasClass(incrementals[snum][i], 'current'))\n\t\t\t\tincpos = i + 1;\n\t\t\telse\n\t\t\t\taddClass(incrementals[snum][i], 'incremental');\n\t\t}\n\t}\n\tif (incrementals[snum].length > 0 && incpos > 0)\n\t\taddClass(incrementals[snum][incpos - 1], 'current');\n\tce.style.visibility = 'hidden';\n\tne.style.visibility = 'visible';\n\tjl.selectedIndex = snum;\n\tcurrentSlide();\n\tnumber = 0;\n}\n\nfunction goTo(target) {\n\tif (target >= smax || target == snum) return;\n\tgo(target - snum);\n}\n\nfunction subgo(step) {\n\tif (step > 0) {\n\t\tremoveClass(incrementals[snum][incpos - 1],'current');\n\t\tremoveClass(incrementals[snum][incpos], 'incremental');\n\t\taddClass(incrementals[snum][incpos],'current');\n\t\tincpos++;\n\t} else {\n\t\tincpos--;\n\t\tremoveClass(incrementals[snum][incpos],'current');\n\t\taddClass(incrementals[snum][incpos], 'incremental');\n\t\taddClass(incrementals[snum][incpos - 1],'current');\n\t}\n}\n\nfunction toggle() {\n\tvar slideColl = GetElementsWithClassName('*','slide');\n\tvar slides = document.getElementById('slideProj');\n\tvar outline = document.getElementById('outlineStyle');\n\tif (!slides.disabled) {\n\t\tslides.disabled = true;\n\t\toutline.disabled = false;\n\t\ts5mode = false;\n\t\tfontSize('1em');\n\t\tfor (var n = 0; n < smax; n++) {\n\t\t\tvar slide = slideColl[n];\n\t\t\tslide.style.visibility = 'visible';\n\t\t}\n\t} else {\n\t\tslides.disabled = false;\n\t\toutline.disabled = true;\n\t\ts5mode = true;\n\t\tfontScale();\n\t\tfor (var n = 0; n < smax; n++) {\n\t\t\tvar slide = slideColl[n];\n\t\t\tslide.style.visibility = 'hidden';\n\t\t}\n\t\tslideColl[snum].style.visibility = 'visible';\n\t}\n}\n\nfunction showHide(action) {\n\tvar obj = GetElementsWithClassName('*','hideme')[0];\n\tswitch (action) {\n\tcase 's': obj.style.visibility = 'visible'; break;\n\tcase 'h': obj.style.visibility = 'hidden'; break;\n\tcase 'k':\n\t\tif (obj.style.visibility != 'visible') {\n\t\t\tobj.style.visibility = 'visible';\n\t\t} else {\n\t\t\tobj.style.visibility = 'hidden';\n\t\t}\n\tbreak;\n\t}\n}\n\n// 'keys' code adapted from MozPoint (http://mozpoint.mozdev.org/)\nfunction keys(key) {\n\tif (!key) {\n\t\tkey = event;\n\t\tkey.which = key.keyCode;\n\t}\n\tif (key.which == 84) {\n\t\ttoggle();\n\t\treturn;\n\t}\n\tif (s5mode) {\n\t\tswitch (key.which) {\n\t\t\tcase 10: // return\n\t\t\tcase 13: // enter\n\t\t\t\tif (window.event && isParentOrSelf(window.event.srcElement, 'controls')) return;\n\t\t\t\tif (key.target && isParentOrSelf(key.target, 'controls')) return;\n\t\t\t\tif(number != undef) {\n\t\t\t\t\tgoTo(number);\n\t\t\t\t\tbreak;\n\t\t\t\t}\n\t\t\tcase 32: // spacebar\n\t\t\tcase 34: // page down\n\t\t\tcase 39: // rightkey\n\t\t\tcase 40: // downkey\n\t\t\t\tif(number != undef) {\n\t\t\t\t\tgo(number);\n\t\t\t\t} else if (!incrementals[snum] || incpos >= incrementals[snum].length) {\n\t\t\t\t\tgo(1);\n\t\t\t\t} else {\n\t\t\t\t\tsubgo(1);\n\t\t\t\t}\n\t\t\t\tbreak;\n\t\t\tcase 33: // page up\n\t\t\tcase 37: // leftkey\n\t\t\tcase 38: // upkey\n\t\t\t\tif(number != undef) {\n\t\t\t\t\tgo(-1 * number);\n\t\t\t\t} else if (!incrementals[snum] || incpos <= 0) {\n\t\t\t\t\tgo(-1);\n\t\t\t\t} else {\n\t\t\t\t\tsubgo(-1);\n\t\t\t\t}\n\t\t\t\tbreak;\n\t\t\tcase 36: // home\n\t\t\t\tgoTo(0);\n\t\t\t\tbreak;\n\t\t\tcase 35: // end\n\t\t\t\tgoTo(smax-1);\n\t\t\t\tbreak;\n\t\t\tcase 67: // c\n\t\t\t\tshowHide('k');\n\t\t\t\tbreak;\n\t\t}\n\t\tif (key.which < 48 || key.which > 57) {\n\t\t\tnumber = undef;\n\t\t} else {\n\t\t\tif (window.event && isParentOrSelf(window.event.srcElement, 'controls')) return;\n\t\t\tif (key.target && isParentOrSelf(key.target, 'controls')) return;\n\t\t\tnumber = (((number != undef) ? number : 0) * 10) + (key.which - 48);\n\t\t}\n\t}\n\treturn false;\n}\n\nfunction clicker(e) {\n\tnumber = undef;\n\tvar target;\n\tif (window.event) {\n\t\ttarget = window.event.srcElement;\n\t\te = window.event;\n\t} else target = e.target;\n\tif (target.getAttribute('href') != null || hasValue(target.rel, 'external') || isParentOrSelf(target, 'controls') || isParentOrSelf(target,'embed') || isParentOrSelf(target,'object')) return true;\n\tif (!e.which || e.which == 1) {\n\t\tif (!incrementals[snum] || incpos >= incrementals[snum].length) {\n\t\t\tgo(1);\n\t\t} else {\n\t\t\tsubgo(1);\n\t\t}\n\t}\n}\n\nfunction findSlide(hash) {\n\tvar target = null;\n\tvar slides = GetElementsWithClassName('*','slide');\n\tfor (var i = 0; i < slides.length; i++) {\n\t\tvar targetSlide = slides[i];\n\t\tif ( (targetSlide.name && targetSlide.name == hash)\n\t\t || (targetSlide.id && targetSlide.id == hash) ) {\n\t\t\ttarget = targetSlide;\n\t\t\tbreak;\n\t\t}\n\t}\n\twhile(target != null && target.nodeName != 'BODY') {\n\t\tif (hasClass(target, 'slide')) {\n\t\t\treturn parseInt(target.id.slice(5));\n\t\t}\n\t\ttarget = target.parentNode;\n\t}\n\treturn null;\n}\n\nfunction slideJump() {\n\tif (window.location.hash == null) return;\n\tvar sregex = /^#slide(\\d+)$/;\n\tvar matches = sregex.exec(window.location.hash);\n\tvar dest = null;\n\tif (matches != null) {\n\t\tdest = parseInt(matches[1]);\n\t} else {\n\t\tdest = findSlide(window.location.hash.slice(1));\n\t}\n\tif (dest != null)\n\t\tgo(dest - snum);\n}\n\nfunction fixLinks() {\n\tvar thisUri = window.location.href;\n\tthisUri = thisUri.slice(0, thisUri.length - window.location.hash.length);\n\tvar aelements = document.getElementsByTagName('A');\n\tfor (var i = 0; i < aelements.length; i++) {\n\t\tvar a = aelements[i].href;\n\t\tvar slideID = a.match('\\#slide[0-9]{1,2}');\n\t\tif ((slideID) && (slideID[0].slice(0,1) == '#')) {\n\t\t\tvar dest = findSlide(slideID[0].slice(1));\n\t\t\tif (dest != null) {\n\t\t\t\tif (aelements[i].addEventListener) {\n\t\t\t\t\taelements[i].addEventListener(\"click\", new Function(\"e\",\n\t\t\t\t\t\t\"if (document.getElementById('slideProj').disabled) return;\" +\n\t\t\t\t\t\t\"go(\"+dest+\" - snum); \" +\n\t\t\t\t\t\t\"if (e.preventDefault) e.preventDefault();\"), true);\n\t\t\t\t} else if (aelements[i].attachEvent) {\n\t\t\t\t\taelements[i].attachEvent(\"onclick\", new Function(\"\",\n\t\t\t\t\t\t\"if (document.getElementById('slideProj').disabled) return;\" +\n\t\t\t\t\t\t\"go(\"+dest+\" - snum); \" +\n\t\t\t\t\t\t\"event.returnValue = false;\"));\n\t\t\t\t}\n\t\t\t}\n\t\t}\n\t}\n}\n\nfunction externalLinks() {\n\tif (!document.getElementsByTagName) return;\n\tvar anchors = document.getElementsByTagName('a');\n\tfor (var i=0; i<anchors.length; i++) {\n\t\tvar anchor = anchors[i];\n\t\tif (anchor.getAttribute('href') && hasValue(anchor.rel, 'external')) {\n\t\t\tanchor.target = '_blank';\n\t\t\taddClass(anchor,'external');\n\t\t}\n\t}\n}\n\nfunction createControls() {\n\tvar controlsDiv = document.getElementById(\"controls\");\n\tif (!controlsDiv) return;\n\tvar hider = ' onmouseover=\"showHide(\\'s\\');\" onmouseout=\"showHide(\\'h\\');\"';\n\tvar hideDiv, hideList = '';\n\tif (controlVis == 'hidden') {\n\t\thideDiv = hider;\n\t} else {\n\t\thideList = hider;\n\t}\n\tcontrolsDiv.innerHTML = '<form action=\"#\" id=\"controlForm\"' + hideDiv + '>' +\n\t'<div id=\"navLinks\">' +\n\t'<a accesskey=\"t\" id=\"toggle\" href=\"javascript:toggle();\">Ø<\\/a>' +\n\t'<a accesskey=\"z\" id=\"prev\" href=\"javascript:go(-1);\">«<\\/a>' +\n\t'<a accesskey=\"x\" id=\"next\" href=\"javascript:go(1);\">»<\\/a>' +\n\t'<div id=\"navList\"' + hideList + '><select id=\"jumplist\" onchange=\"go(\\'j\\');\"><\\/select><\\/div>' +\n\t'<\\/div><\\/form>';\n\tif (controlVis == 'hidden') {\n\t\tvar hidden = document.getElementById('navLinks');\n\t} else {\n\t\tvar hidden = document.getElementById('jumplist');\n\t}\n\taddClass(hidden,'hideme');\n}\n\nfunction fontScale() { // causes layout problems in FireFox that get fixed if browser's Reload is used; same may be true of other Gecko-based browsers\n\tif (!s5mode) return false;\n\tvar vScale = 22; // both yield 32 (after rounding) at 1024x768\n\tvar hScale = 32; // perhaps should auto-calculate based on theme's declared value?\n\tif (window.innerHeight) {\n\t\tvar vSize = window.innerHeight;\n\t\tvar hSize = window.innerWidth;\n\t} else if (document.documentElement.clientHeight) {\n\t\tvar vSize = document.documentElement.clientHeight;\n\t\tvar hSize = document.documentElement.clientWidth;\n\t} else if (document.body.clientHeight) {\n\t\tvar vSize = document.body.clientHeight;\n\t\tvar hSize = document.body.clientWidth;\n\t} else {\n\t\tvar vSize = 700; // assuming 1024x768, minus chrome and such\n\t\tvar hSize = 1024; // these do not account for kiosk mode or Opera Show\n\t}\n\tvar newSize = Math.min(Math.round(vSize/vScale),Math.round(hSize/hScale));\n\tfontSize(newSize + 'px');\n\tif (isGe) { // hack to counter incremental reflow bugs\n\t\tvar obj = document.getElementsByTagName('body')[0];\n\t\tobj.style.display = 'none';\n\t\tobj.style.display = 'block';\n\t}\n}\n\nfunction fontSize(value) {\n\tif (!(s5ss = document.getElementById('s5ss'))) {\n\t\tif (!isIE) {\n\t\t\tdocument.getElementsByTagName('head')[0].appendChild(s5ss = document.createElement('style'));\n\t\t\ts5ss.setAttribute('media','screen, projection');\n\t\t\ts5ss.setAttribute('id','s5ss');\n\t\t} else {\n\t\t\tdocument.createStyleSheet();\n\t\t\tdocument.s5ss = document.styleSheets[document.styleSheets.length - 1];\n\t\t}\n\t}\n\tif (!isIE) {\n\t\twhile (s5ss.lastChild) s5ss.removeChild(s5ss.lastChild);\n\t\ts5ss.appendChild(document.createTextNode('body {font-size: ' + value + ' !important;}'));\n\t} else {\n\t\tdocument.s5ss.addRule('body','font-size: ' + value + ' !important;');\n\t}\n}\n\nfunction notOperaFix() {\n\tslideCSS = document.getElementById('slideProj').href;\n\tvar slides = document.getElementById('slideProj');\n\tvar outline = document.getElementById('outlineStyle');\n\tslides.setAttribute('media','screen');\n\toutline.disabled = true;\n\tif (isGe) {\n\t\tslides.setAttribute('href','null'); // Gecko fix\n\t\tslides.setAttribute('href',slideCSS); // Gecko fix\n\t}\n\tif (isIE && document.styleSheets && document.styleSheets[0]) {\n\t\tdocument.styleSheets[0].addRule('img', 'behavior: url(ui/default/iepngfix.htc)');\n\t\tdocument.styleSheets[0].addRule('div', 'behavior: url(ui/default/iepngfix.htc)');\n\t\tdocument.styleSheets[0].addRule('.slide', 'behavior: url(ui/default/iepngfix.htc)');\n\t}\n}\n\nfunction getIncrementals(obj) {\n\tvar incrementals = new Array();\n\tif (!obj) \n\t\treturn incrementals;\n\tvar children = obj.childNodes;\n\tfor (var i = 0; i < children.length; i++) {\n\t\tvar child = children[i];\n\t\tif (hasClass(child, 'incremental')) {\n\t\t\tif (child.nodeName == 'OL' || child.nodeName == 'UL') {\n\t\t\t\tremoveClass(child, 'incremental');\n\t\t\t\tfor (var j = 0; j < child.childNodes.length; j++) {\n\t\t\t\t\tif (child.childNodes[j].nodeType == 1) {\n\t\t\t\t\t\taddClass(child.childNodes[j], 'incremental');\n\t\t\t\t\t}\n\t\t\t\t}\n\t\t\t} else {\n\t\t\t\tincrementals[incrementals.length] = child;\n\t\t\t\tremoveClass(child,'incremental');\n\t\t\t}\n\t\t}\n\t\tif (hasClass(child, 'show-first')) {\n\t\t\tif (child.nodeName == 'OL' || child.nodeName == 'UL') {\n\t\t\t\tremoveClass(child, 'show-first');\n\t\t\t\tif (child.childNodes[isGe].nodeType == 1) {\n\t\t\t\t\tremoveClass(child.childNodes[isGe], 'incremental');\n\t\t\t\t}\n\t\t\t} else {\n\t\t\t\tincrementals[incrementals.length] = child;\n\t\t\t}\n\t\t}\n\t\tincrementals = incrementals.concat(getIncrementals(child));\n\t}\n\treturn incrementals;\n}\n\nfunction createIncrementals() {\n\tvar incrementals = new Array();\n\tfor (var i = 0; i < smax; i++) {\n\t\tincrementals[i] = getIncrementals(document.getElementById('slide'+i));\n\t}\n\treturn incrementals;\n}\n\nfunction defaultCheck() {\n\tvar allMetas = document.getElementsByTagName('meta');\n\tfor (var i = 0; i< allMetas.length; i++) {\n\t\tif (allMetas[i].name == 'defaultView') {\n\t\t\tdefaultView = allMetas[i].content;\n\t\t}\n\t\tif (allMetas[i].name == 'controlVis') {\n\t\t\tcontrolVis = allMetas[i].content;\n\t\t}\n\t}\n}\n\n// Key trap fix, new function body for trap()\nfunction trap(e) {\n\tif (!e) {\n\t\te = event;\n\t\te.which = e.keyCode;\n\t}\n\ttry {\n\t\tmodifierKey = e.ctrlKey || e.altKey || e.metaKey;\n\t}\n\tcatch(e) {\n\t\tmodifierKey = false;\n\t}\n\treturn modifierKey || e.which == 0;\n}\n\nfunction startup() {\n\tdefaultCheck();\n\tif (!isOp) \n\t\tcreateControls();\n\tslideLabel();\n\tfixLinks();\n\texternalLinks();\n\tfontScale();\n\tif (!isOp) {\n\t\tnotOperaFix();\n\t\tincrementals = createIncrementals();\n\t\tslideJump();\n\t\tif (defaultView == 'outline') {\n\t\t\ttoggle();\n\t\t}\n\t\tdocument.onkeyup = keys;\n\t\tdocument.onkeypress = trap;\n\t\tdocument.onclick = clicker;\n\t}\n}\n\nwindow.onload = startup;\nwindow.onresize = function(){setTimeout('fontScale()', 50);}</script>\n" + +s5CoreCSS :: String +s5CoreCSS = "/* Do not edit or override these styles! The system will likely break if you do. */\n\ndiv#header, div#footer, div#controls, .slide {position: absolute;}\nhtml>body div#header, html>body div#footer, \n html>body div#controls, html>body .slide {position: fixed;}\n.handout {display: none;}\n.layout {display: block;}\n.slide, .hideme, .incremental {visibility: hidden;}\n#slide0 {visibility: visible;}\n" + +s5FramingCSS :: String +s5FramingCSS = "/* The following styles size, place, and layer the slide components.\n Edit these if you want to change the overall slide layout.\n The commented lines can be uncommented (and modified, if necessary) \n to help you with the rearrangement process. */\n\n/* target = 1024x768 */\n\ndiv#header, div#footer, .slide {width: 100%; top: 0; left: 0;}\ndiv#header {top: 0; height: 3em; z-index: 1;}\ndiv#footer {top: auto; bottom: 0; height: 2.5em; z-index: 5;}\n.slide {top: 0; width: 92%; padding: 3.5em 4% 4%; z-index: 2; list-style: none;}\ndiv#controls {left: 50%; bottom: 0; width: 50%; z-index: 100;}\ndiv#controls form {position: absolute; bottom: 0; right: 0; width: 100%;\n margin: 0;}\n#currentSlide {position: absolute; width: 10%; left: 45%; bottom: 1em; z-index: 10;}\nhtml>body #currentSlide {position: fixed;}\n\n/*\ndiv#header {background: #FCC;}\ndiv#footer {background: #CCF;}\ndiv#controls {background: #BBD;}\ndiv#currentSlide {background: #FFC;}\n*/\n" + +s5PrettyCSS :: String +s5PrettyCSS = "/* Following are the presentation styles -- edit away! */\n\nbody {background: #FFF url(bodybg.gif) -16px 0 no-repeat; color: #000; font-size: 2em;}\n:link, :visited {text-decoration: none; color: #00C;}\n#controls :active {color: #88A !important;}\n#controls :focus {outline: 1px dotted #227;}\nh1, h2, h3, h4 {font-size: 100%; margin: 0; padding: 0; font-weight: inherit;}\nul, pre {margin: 0; line-height: 1em;}\nhtml, body {margin: 0; padding: 0;}\n\nblockquote, q {font-style: italic;}\nblockquote {padding: 0 2em 0.5em; margin: 0 1.5em 0.5em; text-align: center; font-size: 1em;}\nblockquote p {margin: 0;}\nblockquote i {font-style: normal;}\nblockquote b {display: block; margin-top: 0.5em; font-weight: normal; font-size: smaller; font-style: normal;}\nblockquote b i {font-style: italic;}\n\nkbd {font-weight: bold; font-size: 1em;}\nsup {font-size: smaller; line-height: 1px;}\n\n.slide code {padding: 2px 0.25em; font-weight: bold; color: #533;}\n.slide code.bad, code del {color: red;}\n.slide code.old {color: silver;}\n.slide pre {padding: 0; margin: 0.25em 0 0.5em 0.5em; color: #533; font-size: 90%;}\n.slide pre code {display: block;}\n.slide ul {margin-left: 5%; margin-right: 7%; list-style: disc;}\n.slide li {margin-top: 0.75em; margin-right: 0;}\n.slide ul ul {line-height: 1;}\n.slide ul ul li {margin: .2em; font-size: 85%; list-style: square;}\n.slide img.leader {display: block; margin: 0 auto;}\n\ndiv#header, div#footer {background: #005; color: #AAB;\n font-family: Verdana, Helvetica, sans-serif;}\ndiv#header {background: #005 url(bodybg.gif) -16px 0 no-repeat;\n line-height: 1px;}\ndiv#footer {font-size: 0.5em; font-weight: bold; padding: 1em 0;}\n#footer h1, #footer h2 {display: block; padding: 0 1em;}\n#footer h2 {font-style: italic;}\n\ndiv.long {font-size: 0.75em;}\n.slide h1 {position: absolute; top: 0.7em; left: 87px; z-index: 1;\n margin: 0; padding: 0.3em 0 0 50px; white-space: nowrap;\n font: bold 150%/1em Helvetica, sans-serif; text-transform: capitalize;\n color: #DDE; background: #005;}\n.slide h3 {font-size: 130%;}\nh1 abbr {font-variant: small-caps;}\n\ndiv#controls {position: absolute; left: 50%; bottom: 0;\n width: 50%;\n text-align: right; font: bold 0.9em Verdana, Helvetica, sans-serif;}\nhtml>body div#controls {position: fixed; padding: 0 0 1em 0;\n top: auto;}\ndiv#controls form {position: absolute; bottom: 0; right: 0; width: 100%;\n margin: 0; padding: 0;}\n#controls #navLinks a {padding: 0; margin: 0 0.5em; \n background: #005; border: none; color: #779; \n cursor: pointer;}\n#controls #navList {height: 1em;}\n#controls #navList #jumplist {position: absolute; bottom: 0; right: 0; background: #DDD; color: #227;}\n\n#currentSlide {text-align: center; font-size: 0.5em; color: #449;}\n\n#slide0 {padding-top: 3.5em; font-size: 90%;}\n#slide0 h1 {position: static; margin: 1em 0 0; padding: 0;\n font: bold 2em Helvetica, sans-serif; white-space: normal;\n color: #000; background: transparent;}\n#slide0 h2 {font: bold italic 1em Helvetica, sans-serif; margin: 0.25em;}\n#slide0 h3 {margin-top: 1.5em; font-size: 1.5em;}\n#slide0 h4 {margin-top: 0; font-size: 1em;}\n\nul.urls {list-style: none; display: inline; margin: 0;}\n.urls li {display: inline; margin: 0;}\n.note {display: none;}\n.external {border-bottom: 1px dotted gray;}\nhtml>body .external {border-bottom: none;}\n.external:after {content: \" \\274F\"; font-size: smaller; color: #77B;}\n\n.incremental, .incremental *, .incremental *:after {color: #DDE; visibility: visible;}\nimg.incremental {visibility: hidden;}\n.slide .current {color: #B02;}\n\n\n/* diagnostics\n\nli:after {content: \" [\" attr(class) \"]\"; color: #F88;}\n */" + +s5OperaCSS :: String +s5OperaCSS = "/* DO NOT CHANGE THESE unless you really want to break Opera Show */\n.slide {\n\tvisibility: visible !important;\n\tposition: static !important;\n\tpage-break-before: always;\n}\n#slide0 {page-break-before: avoid;}\n" + +s5OutlineCSS :: String +s5OutlineCSS = "/* don't change this unless you want the layout stuff to show up in the outline view! */\n\n.layout div, #footer *, #controlForm * {display: none;}\n#footer, #controls, #controlForm, #navLinks, #toggle {\n display: block; visibility: visible; margin: 0; padding: 0;}\n#toggle {float: right; padding: 0.5em;}\nhtml>body #toggle {position: fixed; top: 0; right: 0;}\n\n/* making the outline look pretty-ish */\n\n#slide0 h1, #slide0 h2, #slide0 h3, #slide0 h4 {border: none; margin: 0;}\n#slide0 h1 {padding-top: 1.5em;}\n.slide h1 {margin: 1.5em 0 0; padding-top: 0.25em;\n border-top: 1px solid #888; border-bottom: 1px solid #AAA;}\n#toggle {border: 1px solid; border-width: 0 0 1px 1px; background: #FFF;}\n" + +s5PrintCSS :: String +s5PrintCSS = "/* The following rule is necessary to have all slides appear in print! DO NOT REMOVE IT! */
.slide, ul {page-break-inside: avoid; visibility: visible !important;}
h1 {page-break-after: avoid;}
body {font-size: 12pt; background: white;}
* {color: black;}
#slide0 h1 {font-size: 200%; border: none; margin: 0.5em 0 0.25em;}
#slide0 h3 {margin: 0; padding: 0;}
#slide0 h4 {margin: 0 0 0.5em; padding: 0;}
#slide0 {margin-bottom: 3em;}
h1 {border-top: 2pt solid gray; border-bottom: 1px dotted silver;}
.extra {background: transparent !important;}
div.extra, pre.extra, .example {font-size: 10pt; color: #333;}
ul.extra a {font-weight: bold;}
p.example {display: none;}
#header {display: none;}
#footer h1 {margin: 0; border-bottom: 1px solid; color: gray; font-style: italic;}
#footer h2, #controls {display: none;}
/* The following rule keeps the layout stuff out of print. Remove at your own risk! */
.layout, .layout * {display: none !important;}
" + +s5CSS :: String +s5CSS = "<style type=\"text/css\" media=\"projection\" id=\"slideProj\">\n" ++ s5CoreCSS ++ "\n" ++ s5FramingCSS ++ "\n" ++ s5PrettyCSS ++ "\n</style>\n<style type=\"text/css\" media=\"projection\" id=\"operaFix\">\n" ++ s5OperaCSS ++ "\n</style>\n<style type=\"text/css\" media=\"screen\" id=\"outlineStyle\">\n" ++ s5OutlineCSS ++ "\n</style>\n<style type=\"text/css\" media=\"print\" id=\"slidePrint\">\n" ++ s5PrintCSS ++ "\n</style>\n" + +s5Links :: String +s5Links = "<!-- style sheet links -->\n<link rel=\"stylesheet\" href=\"ui/default/slides.css\" type=\"text/css\" media=\"projection\" id=\"slideProj\" />\n<link rel=\"stylesheet\" href=\"ui/default/outline.css\" type=\"text/css\" media=\"screen\" id=\"outlineStyle\" />\n<link rel=\"stylesheet\" href=\"ui/default/print.css\" type=\"text/css\" media=\"print\" id=\"slidePrint\" />\n<link rel=\"stylesheet\" href=\"ui/default/opera.css\" type=\"text/css\" media=\"projection\" id=\"operaFix\" />\n<!-- S5 JS -->\n<script src=\"ui/default/slides.js\" type=\"text/javascript\"></script>\n" + +-- | Converts 'Pandoc' to an S5 HTML presentation. +writeS5 :: WriterOptions -> Pandoc -> String +writeS5 options = writeHtml options . insertS5Structure + +-- | Inserts HTML needed for an S5 presentation (e.g. around slides). +layoutDiv :: [Inline] -- ^ Title of document (for header or footer) + -> String -- ^ Date of document (for header or footer) + -> [Block] -- ^ List of block elements returned +layoutDiv title date = [(RawHtml "<div class=\"layout\">\n<div id=\"controls\"></div>\n<div id=\"currentSlide\"></div>\n<div id=\"header\"></div>\n<div id=\"footer\">\n"), (Header 1 [Str date]), (Header 2 title), (RawHtml "</div>\n</div>\n")] + +presentationStart = (RawHtml "<div class=\"presentation\">\n\n") + +presentationEnd = (RawHtml "</div>\n") + +slideStart = (RawHtml "<div class=\"slide\">\n") + +slideEnd = (RawHtml "</div>\n") + +-- | Returns 'True' if block is a Header 1. +isH1 :: Block -> Bool +isH1 (Header 1 _) = True +isH1 _ = False + +-- | Insert HTML around sections to make individual slides. +insertSlides :: Bool -> [Block] -> [Block] +insertSlides beginning blocks = + let (beforeHead, rest) = break isH1 blocks in + if (null rest) then + if beginning then + beforeHead + else + beforeHead ++ [slideEnd] + else + if beginning then + beforeHead ++ slideStart:(head rest):(insertSlides False (tail rest)) + else + beforeHead ++ slideEnd:slideStart:(head rest):(insertSlides False (tail rest)) + +-- | Insert blocks into 'Pandoc' for slide structure. +insertS5Structure :: Pandoc -> Pandoc +insertS5Structure (Pandoc meta []) = Pandoc meta [] +insertS5Structure (Pandoc (Meta title authors date) blocks) = + let slides = insertSlides True blocks + firstSlide = if (not (null title)) then [slideStart, (Header 1 title), (Header 3 [Str (joinWithSep ", " authors)]), (Header 4 [Str date]), slideEnd] else [] in + let newBlocks = (layoutDiv title date) ++ presentationStart:firstSlide ++ slides ++ [presentationEnd] in + Pandoc (Meta title authors date) newBlocks + diff --git a/src/Text/ParserCombinators/Pandoc.hs b/src/Text/ParserCombinators/Pandoc.hs new file mode 100644 index 000000000..9bf0a76f7 --- /dev/null +++ b/src/Text/ParserCombinators/Pandoc.hs @@ -0,0 +1,109 @@ +-- | Special parser combinators for Pandoc readers. +module Text.ParserCombinators.Pandoc ( + many1Till, + followedBy', + notFollowedBy', + oneOfStrings, + spaceChar, + skipSpaces, + blankline, + blanklines, + escaped, + enclosed, + blankBlock, + nullBlock, + stringAnyCase + ) where +import Text.ParserCombinators.Parsec +import Text.Pandoc.Definition +import Text.Pandoc.Shared +import Char ( toUpper, toLower ) + +-- | Parses a character and returns 'Null' (so that the parser can move on +-- if it gets stuck). +nullBlock :: GenParser Char st Block +nullBlock = do + anyChar + return Null + +-- | Parses one or more blank lines; returns 'Blank'. +blankBlock :: GenParser Char st Block +blankBlock = do + blanklines + return Blank + +-- | Parses a space or tab. +spaceChar :: CharParser st Char +spaceChar = oneOf " \t" + +-- | Skips zero or more spaces or tabs. +skipSpaces :: GenParser Char st () +skipSpaces = skipMany spaceChar + +-- | Skips zero or more spaces or tabs, then reads a newline. +blankline :: GenParser Char st Char +blankline = try (do + skipSpaces + newline) + +-- | Parses one or more blank lines and returns a string of newlines. +blanklines :: GenParser Char st [Char] +blanklines = try (do + many1 blankline) + +-- | Parses backslash, then applies character parser. +escaped :: GenParser Char st Char -- ^ Parser for character to escape + -> GenParser Char st Inline +escaped parser = try (do + char '\\' + result <- parser + return (Str [result])) + +-- | Parses material enclosed between start and end parsers. +enclosed :: GenParser Char st t -- ^ start parser + -> GenParser Char st end -- ^ end parser + -> GenParser Char st a -- ^ content parser (to be used repeatedly) + -> GenParser Char st [a] +enclosed start end parser = try (do + start + notFollowedBy space + result <- many1Till parser (try end) + return result) + +-- | Like @manyTill@, but reads at least one item. +many1Till :: GenParser tok st a + -> GenParser tok st end + -> GenParser tok st [a] +many1Till p end = try (do + first <- p + rest <- manyTill p end + return (first:rest)) + +-- | A more general form of @notFollowedBy@. This one allows any type of parser to +-- be specified, and succeeds only if that parser fails. It does not consume any input. +notFollowedBy' :: Show b => GenParser a st b -> GenParser a st () +notFollowedBy' parser = try (do{ c <- parser; unexpected (show c) } + <|> return () + ) + +-- | The inverse of @notFollowedBy'@. Fails if parser will fail, otherwise +-- returns @()@ (but does not consume any input). +followedBy' :: (Show b) => GenParser a st b -> GenParser a st () +followedBy' parser = do + isNotFollowed <- option False (do{ notFollowedBy' parser; return True}) + if isNotFollowed then + fail "not followed by parser" + else + return () + +-- | Parses one of a list of strings (tried in order). +oneOfStrings :: [String] -> GenParser Char st String +oneOfStrings listOfStrings = choice $ map (try . string) listOfStrings + +-- | Parse string, case insensitive. +stringAnyCase :: [Char] -> CharParser st String +stringAnyCase [] = string "" +stringAnyCase (x:xs) = try (do + firstChar <- choice [ char (toUpper x), char (toLower x) ] + rest <- stringAnyCase xs + return (firstChar:rest)) diff --git a/src/headers/HtmlHeader b/src/headers/HtmlHeader new file mode 100644 index 000000000..ac1be8d3a --- /dev/null +++ b/src/headers/HtmlHeader @@ -0,0 +1,11 @@ +<!DOCTYPE HTML PUBLIC "-//W3C//DTD HTML 4.01 Transitional//EN" + "http://www.w3.org/TR/html4/loose.dtd"> +<html> +<head> +<meta http-equiv="Content-Type" content="text/html; charset=UTF-8" /> +<meta name="generator" content="pandoc" /> +<style type="text/css"> +div.pandocNote { border-left: 1px solid grey; padding-left: 1em; } +span.pandocNoteRef { vertical-align: super; font-size: 80%; } +span.pandocNoteMarker { } +</style> diff --git a/src/headers/LaTeXHeader b/src/headers/LaTeXHeader new file mode 100644 index 000000000..b69e2426f --- /dev/null +++ b/src/headers/LaTeXHeader @@ -0,0 +1,10 @@ +\documentclass{article} +\usepackage{hyperref} +\usepackage{ucs} +\usepackage[utf8x]{inputenc} +\usepackage{graphicx} +\setlength{\parindent}{0pt} +\setlength{\parskip}{6pt plus 2pt minus 1pt} +% This is needed for code blocks in footnotes: +\usepackage{fancyvrb} +\VerbatimFootnotes diff --git a/src/headers/RTFHeader b/src/headers/RTFHeader new file mode 100644 index 000000000..62923c1d6 --- /dev/null +++ b/src/headers/RTFHeader @@ -0,0 +1,4 @@ +{\rtf1\ansi\deff0{\fonttbl{\f0 Times New Roman;}{\f1 Courier;}} +{\colortbl;\red255\green0\blue0;\red0\green0\blue255;} +\widowctrl\hyphauto + diff --git a/src/headers/S5Header b/src/headers/S5Header new file mode 100644 index 000000000..0cec6c8f3 --- /dev/null +++ b/src/headers/S5Header @@ -0,0 +1,8 @@ +<!DOCTYPE html PUBLIC "-//W3C//DTD XHTML 1.0 Strict//EN" "http://www.w3.org/TR/xhtml1/DTD/xhtml1-strict.dtd"> +<html xmlns="http://www.w3.org/1999/xhtml"> +<head> +<!-- configuration parameters --> +<meta name="defaultView" content="slideshow" /> +<meta name="controlVis" content="hidden" /> +<meta http-equiv="Content-Type" content="text/html; charset=UTF-8" /> +<meta name="generator" content="pandoc" /> diff --git a/src/templates/ASCIIMathML.hs b/src/templates/ASCIIMathML.hs new file mode 100644 index 000000000..fabc7fba2 --- /dev/null +++ b/src/templates/ASCIIMathML.hs @@ -0,0 +1,7 @@ +-- | Definitions for use of Pandoc.ASCIIMathML in HTML. +-- (See <http://www1.chapman.edu/~jipsen/mathml/asciimath.html>.) +module Text.Pandoc.ASCIIMathML ( asciiMathMLScript ) where + +-- | String containing Pandoc.ASCIIMathML javascript. +asciiMathMLScript :: String +asciiMathMLScript = "<script type=\"text/javascript\">\n<ASCIIMathML.js></script>\n" diff --git a/src/templates/DefaultHeaders.hs b/src/templates/DefaultHeaders.hs new file mode 100644 index 000000000..22d17d6a7 --- /dev/null +++ b/src/templates/DefaultHeaders.hs @@ -0,0 +1,20 @@ +-- | Default headers for Pandoc writers. +module Text.Pandoc.Writers.DefaultHeaders ( + defaultLaTeXHeader, + defaultHtmlHeader, + defaultS5Header, + defaultRTFHeader + ) where +import Text.Pandoc.Writers.S5 + +defaultLaTeXHeader :: String +defaultLaTeXHeader = "<LaTeXHeader>" + +defaultHtmlHeader :: String +defaultHtmlHeader = "<HtmlHeader>" + +defaultS5Header :: String +defaultS5Header = "<S5Header>" ++ s5CSS ++ s5Javascript + +defaultRTFHeader :: String +defaultRTFHeader = "<RTFHeader>" diff --git a/src/templates/Makefile b/src/templates/Makefile new file mode 100644 index 000000000..ccd7b7076 --- /dev/null +++ b/src/templates/Makefile @@ -0,0 +1,16 @@ +VPATH := .. +PROCESSOR := ./fillTemplates.pl +TARGETS := Text/Pandoc/ASCIIMathML.hs \ + Text/Pandoc/Writers/S5.hs \ + Text/Pandoc/Writers/DefaultHeaders.hs + +all: $(TARGETS) + +Text/Pandoc/ASCIIMathML.hs: ASCIIMathML.hs $(PROCESSOR) $(VPATH)/ASCIIMathML.js + perl $(PROCESSOR) $@ $(VPATH) + +Text/Pandoc/Writers/S5.hs: S5.hs $(PROCESSOR) $(VPATH)/headers/* + perl $(PROCESSOR) $@ $(VPATH) + +Text/Pandoc/Writers/DefaultHeaders.hs: DefaultHeaders.hs $(PROCESSOR) $(VPATH)/ui/default/* + perl $(PROCESSOR) $@ $(VPATH) diff --git a/src/templates/S5.hs b/src/templates/S5.hs new file mode 100644 index 000000000..1417e7d7d --- /dev/null +++ b/src/templates/S5.hs @@ -0,0 +1,88 @@ +-- | Definitions for creation of S5 powerpoint-like HTML. +-- (See <http://meyerweb.com/eric/tools/s5/>.) +module Text.Pandoc.Writers.S5 ( + -- * Strings + s5Javascript, + s5CSS, + s5Links, + -- * Functions + writeS5, + insertS5Structure + ) where +import Text.Pandoc.Shared ( joinWithSep, WriterOptions ) +import Text.Pandoc.Writers.HTML ( writeHtml ) +import Text.Pandoc.Definition + +s5Javascript :: String +s5Javascript = "<script type=\"text/javascript\">\n<slides.js></script>\n" + +s5CoreCSS :: String +s5CoreCSS = "<s5-core.css>" + +s5FramingCSS :: String +s5FramingCSS = "<framing.css>" + +s5PrettyCSS :: String +s5PrettyCSS = "<pretty.css>" + +s5OperaCSS :: String +s5OperaCSS = "<opera.css>" + +s5OutlineCSS :: String +s5OutlineCSS = "<outline.css>" + +s5PrintCSS :: String +s5PrintCSS = "<print.css>" + +s5CSS :: String +s5CSS = "<style type=\"text/css\" media=\"projection\" id=\"slideProj\">\n" ++ s5CoreCSS ++ "\n" ++ s5FramingCSS ++ "\n" ++ s5PrettyCSS ++ "\n</style>\n<style type=\"text/css\" media=\"projection\" id=\"operaFix\">\n" ++ s5OperaCSS ++ "\n</style>\n<style type=\"text/css\" media=\"screen\" id=\"outlineStyle\">\n" ++ s5OutlineCSS ++ "\n</style>\n<style type=\"text/css\" media=\"print\" id=\"slidePrint\">\n" ++ s5PrintCSS ++ "\n</style>\n" + +s5Links :: String +s5Links = "<!-- style sheet links -->\n<link rel=\"stylesheet\" href=\"ui/default/slides.css\" type=\"text/css\" media=\"projection\" id=\"slideProj\" />\n<link rel=\"stylesheet\" href=\"ui/default/outline.css\" type=\"text/css\" media=\"screen\" id=\"outlineStyle\" />\n<link rel=\"stylesheet\" href=\"ui/default/print.css\" type=\"text/css\" media=\"print\" id=\"slidePrint\" />\n<link rel=\"stylesheet\" href=\"ui/default/opera.css\" type=\"text/css\" media=\"projection\" id=\"operaFix\" />\n<!-- S5 JS -->\n<script src=\"ui/default/slides.js\" type=\"text/javascript\"></script>\n" + +-- | Converts 'Pandoc' to an S5 HTML presentation. +writeS5 :: WriterOptions -> Pandoc -> String +writeS5 options = writeHtml options . insertS5Structure + +-- | Inserts HTML needed for an S5 presentation (e.g. around slides). +layoutDiv :: [Inline] -- ^ Title of document (for header or footer) + -> String -- ^ Date of document (for header or footer) + -> [Block] -- ^ List of block elements returned +layoutDiv title date = [(RawHtml "<div class=\"layout\">\n<div id=\"controls\"></div>\n<div id=\"currentSlide\"></div>\n<div id=\"header\"></div>\n<div id=\"footer\">\n"), (Header 1 [Str date]), (Header 2 title), (RawHtml "</div>\n</div>\n")] + +presentationStart = (RawHtml "<div class=\"presentation\">\n\n") + +presentationEnd = (RawHtml "</div>\n") + +slideStart = (RawHtml "<div class=\"slide\">\n") + +slideEnd = (RawHtml "</div>\n") + +-- | Returns 'True' if block is a Header 1. +isH1 :: Block -> Bool +isH1 (Header 1 _) = True +isH1 _ = False + +-- | Insert HTML around sections to make individual slides. +insertSlides :: Bool -> [Block] -> [Block] +insertSlides beginning blocks = + let (beforeHead, rest) = break isH1 blocks in + if (null rest) then + if beginning then + beforeHead + else + beforeHead ++ [slideEnd] + else + if beginning then + beforeHead ++ slideStart:(head rest):(insertSlides False (tail rest)) + else + beforeHead ++ slideEnd:slideStart:(head rest):(insertSlides False (tail rest)) + +-- | Insert blocks into 'Pandoc' for slide structure. +insertS5Structure :: Pandoc -> Pandoc +insertS5Structure (Pandoc meta []) = Pandoc meta [] +insertS5Structure (Pandoc (Meta title authors date) blocks) = + let slides = insertSlides True blocks + firstSlide = if (not (null title)) then [slideStart, (Header 1 title), (Header 3 [Str (joinWithSep ", " authors)]), (Header 4 [Str date]), slideEnd] else [] in + let newBlocks = (layoutDiv title date) ++ presentationStart:firstSlide ++ slides ++ [presentationEnd] in + Pandoc (Meta title authors date) newBlocks diff --git a/src/templates/fillTemplates.pl b/src/templates/fillTemplates.pl new file mode 100644 index 000000000..381db13d5 --- /dev/null +++ b/src/templates/fillTemplates.pl @@ -0,0 +1,138 @@ +#!/usr/bin/env perl +# fills templates in templates directory with haskell-escaped strings +# slurped from input files + +use strict; +use warnings; + +# Utility routines: + +sub slurp { + open FILE, $_[0] or die "couldn't open file '$_[0]': $!"; + my $contents = do { local $/; <FILE>;}; + close FILE; + return $contents; +} + +sub escape_for_haskell { + my ($contents) = @_; + + $contents =~ s/\\/\\\\/g; + $contents =~ s/\t/\\t/g; + $contents =~ s/"/\\"/g; + $contents =~ s/\n/\\n/g; + return $contents; +} + +# Template processors. + +my %processor = ( + # -------------------------------------------------------------------------- + 'Text/Pandoc/Writers/S5.hs' => { + # -------------------------------------------------------------------------- + proc => sub { + my ($template) = @_; + + my $slides = escape_for_haskell(slurp "ui/default/slides.js"); + my $s5core = escape_for_haskell(slurp "ui/default/s5-core.css"); + my $framing = escape_for_haskell(slurp "ui/default/framing.css"); + my $pretty = escape_for_haskell(slurp "ui/default/pretty.css"); + my $opera = escape_for_haskell(slurp "ui/default/opera.css"); + my $outline = escape_for_haskell(slurp "ui/default/outline.css"); + my $print = escape_for_haskell(slurp "ui/default/print.css"); + + $template =~ s/<slides\.js>/$slides/; + $template =~ s/<s5-core\.css>/$s5core/; + $template =~ s/<framing\.css>/$framing/; + $template =~ s/<pretty\.css>/$pretty/; + $template =~ s/<opera\.css>/$opera/; + $template =~ s/<outline\.css>/$outline/; + $template =~ s/<print\.css>/$print/; + + return $template; + }, + }, + # -------------------------------------------------------------------------- + 'Text/Pandoc/ASCIIMathML.hs' => { + # -------------------------------------------------------------------------- + proc => sub { + my ($template) = @_; + + my $script = escape_for_haskell(slurp "ASCIIMathML.js"); + my $acknowledgements = + " ASCIIMathML.js - copyright Peter Jipsen,". + " released under the GPL\\nSee ". + "http://www1.chapman.edu/~jipsen/mathml/asciimath.html/ "; + $script =~ s/\/\*.*?\*\//\/\*$acknowledgements\*\//g; # strip comments + $template =~ s/<ASCIIMathML\.js>/$script/; + + return $template; + }, + }, + # -------------------------------------------------------------------------- + 'Text/Pandoc/Writers/DefaultHeaders.hs' => { + # -------------------------------------------------------------------------- + proc => sub { + my ($template) = @_; + + my $html = escape_for_haskell(slurp "headers/HtmlHeader"); + my $latex = escape_for_haskell(slurp "headers/LaTeXHeader"); + my $rtf = escape_for_haskell(slurp "headers/RTFHeader"); + my $s5 = escape_for_haskell(slurp "headers/S5Header"); + + $template =~ s/<HtmlHeader>/$html/; + $template =~ s/<LaTeXHeader>/$latex/; + $template =~ s/<RTFHeader>/$rtf/; + $template =~ s/<S5Header>/$s5/; + + return $template; + }, + }, + # -------------------------------------------------------------------------- + # 'foo/bar/baz' => { + # -------------------------------------------------------------------------- + # template => 'optional-template-filename-defaults-to-baz' + # proc => sub { + # my ($template) = @_; + # # Process. + # return $template; + # }, + #}, +); + +# Main. + +my $target = shift @ARGV; +if (!defined $target || !length $target) { + print STDERR "Available targets:\n\n" . join "\n", keys %processor; + die "\n\nYou must supply a target!\n"; +} + +die "No processor exists for '$target'!\n" if ! exists $processor{$target}; + +my $rootdir = shift @ARGV || '..'; +chdir $rootdir or die "Couldn't chdir to '$rootdir': $!"; + +my $template; +if (exists $processor{$target}->{template}) { + $template = $processor{$target}->{template}; +} +else { + ($template = $target) =~ s!.*/+!!; +} +$template = "templates/$template"; +die "No template exists for '$target'!\n" if ! -f "$template"; + +open OUTFILE, ">$target" or die "couldn't open file '$target': $!"; +print OUTFILE <<END; +---------------------------------------------------- +-- Do not edit this file by hand. Edit +-- '$template' +-- and run $0 $target +---------------------------------------------------- + +END + +print OUTFILE $processor{$target}->{proc}->(slurp($template)); +print OUTFILE "\n"; +close OUTFILE; diff --git a/src/ui/default/blank.gif b/src/ui/default/blank.gif Binary files differnew file mode 100644 index 000000000..75b945d25 --- /dev/null +++ b/src/ui/default/blank.gif diff --git a/src/ui/default/bodybg.gif b/src/ui/default/bodybg.gif Binary files differnew file mode 100644 index 000000000..5f448a16f --- /dev/null +++ b/src/ui/default/bodybg.gif diff --git a/src/ui/default/framing.css b/src/ui/default/framing.css new file mode 100644 index 000000000..14d8509e9 --- /dev/null +++ b/src/ui/default/framing.css @@ -0,0 +1,23 @@ +/* The following styles size, place, and layer the slide components. + Edit these if you want to change the overall slide layout. + The commented lines can be uncommented (and modified, if necessary) + to help you with the rearrangement process. */ + +/* target = 1024x768 */ + +div#header, div#footer, .slide {width: 100%; top: 0; left: 0;} +div#header {top: 0; height: 3em; z-index: 1;} +div#footer {top: auto; bottom: 0; height: 2.5em; z-index: 5;} +.slide {top: 0; width: 92%; padding: 3.5em 4% 4%; z-index: 2; list-style: none;} +div#controls {left: 50%; bottom: 0; width: 50%; z-index: 100;} +div#controls form {position: absolute; bottom: 0; right: 0; width: 100%; + margin: 0;} +#currentSlide {position: absolute; width: 10%; left: 45%; bottom: 1em; z-index: 10;} +html>body #currentSlide {position: fixed;} + +/* +div#header {background: #FCC;} +div#footer {background: #CCF;} +div#controls {background: #BBD;} +div#currentSlide {background: #FFC;} +*/ diff --git a/src/ui/default/iepngfix.htc b/src/ui/default/iepngfix.htc new file mode 100644 index 000000000..bba2db756 --- /dev/null +++ b/src/ui/default/iepngfix.htc @@ -0,0 +1,42 @@ +<public:component>
+<public:attach event="onpropertychange" onevent="doFix()" />
+
+<script>
+
+// IE5.5+ PNG Alpha Fix v1.0 by Angus Turnbull http://www.twinhelix.com
+// Free usage permitted as long as this notice remains intact.
+
+// This must be a path to a blank image. That's all the configuration you need here.
+var blankImg = 'ui/default/blank.gif';
+
+var f = 'DXImageTransform.Microsoft.AlphaImageLoader';
+
+function filt(s, m) {
+ if (filters[f]) {
+ filters[f].enabled = s ? true : false;
+ if (s) with (filters[f]) { src = s; sizingMethod = m }
+ } else if (s) style.filter = 'progid:'+f+'(src="'+s+'",sizingMethod="'+m+'")';
+}
+
+function doFix() {
+ if ((parseFloat(navigator.userAgent.match(/MSIE (\S+)/)[1]) < 5.5) ||
+ (event && !/(background|src)/.test(event.propertyName))) return;
+
+ if (tagName == 'IMG') {
+ if ((/\.png$/i).test(src)) {
+ filt(src, 'image'); // was 'scale'
+ src = blankImg;
+ } else if (src.indexOf(blankImg) < 0) filt();
+ } else if (style.backgroundImage) {
+ if (style.backgroundImage.match(/^url[("']+(.*\.png)[)"']+$/i)) {
+ var s = RegExp.$1;
+ style.backgroundImage = '';
+ filt(s, 'crop');
+ } else filt();
+ }
+}
+
+doFix();
+
+</script>
+</public:component>
\ No newline at end of file diff --git a/src/ui/default/opera.css b/src/ui/default/opera.css new file mode 100644 index 000000000..9e9d2a3c5 --- /dev/null +++ b/src/ui/default/opera.css @@ -0,0 +1,7 @@ +/* DO NOT CHANGE THESE unless you really want to break Opera Show */ +.slide { + visibility: visible !important; + position: static !important; + page-break-before: always; +} +#slide0 {page-break-before: avoid;} diff --git a/src/ui/default/outline.css b/src/ui/default/outline.css new file mode 100644 index 000000000..62db519ed --- /dev/null +++ b/src/ui/default/outline.css @@ -0,0 +1,15 @@ +/* don't change this unless you want the layout stuff to show up in the outline view! */ + +.layout div, #footer *, #controlForm * {display: none;} +#footer, #controls, #controlForm, #navLinks, #toggle { + display: block; visibility: visible; margin: 0; padding: 0;} +#toggle {float: right; padding: 0.5em;} +html>body #toggle {position: fixed; top: 0; right: 0;} + +/* making the outline look pretty-ish */ + +#slide0 h1, #slide0 h2, #slide0 h3, #slide0 h4 {border: none; margin: 0;} +#slide0 h1 {padding-top: 1.5em;} +.slide h1 {margin: 1.5em 0 0; padding-top: 0.25em; + border-top: 1px solid #888; border-bottom: 1px solid #AAA;} +#toggle {border: 1px solid; border-width: 0 0 1px 1px; background: #FFF;} diff --git a/src/ui/default/pretty.css b/src/ui/default/pretty.css new file mode 100644 index 000000000..3d3acefff --- /dev/null +++ b/src/ui/default/pretty.css @@ -0,0 +1,86 @@ +/* Following are the presentation styles -- edit away! */ + +body {background: #FFF url(bodybg.gif) -16px 0 no-repeat; color: #000; font-size: 2em;} +:link, :visited {text-decoration: none; color: #00C;} +#controls :active {color: #88A !important;} +#controls :focus {outline: 1px dotted #227;} +h1, h2, h3, h4 {font-size: 100%; margin: 0; padding: 0; font-weight: inherit;} +ul, pre {margin: 0; line-height: 1em;} +html, body {margin: 0; padding: 0;} + +blockquote, q {font-style: italic;} +blockquote {padding: 0 2em 0.5em; margin: 0 1.5em 0.5em; text-align: center; font-size: 1em;} +blockquote p {margin: 0;} +blockquote i {font-style: normal;} +blockquote b {display: block; margin-top: 0.5em; font-weight: normal; font-size: smaller; font-style: normal;} +blockquote b i {font-style: italic;} + +kbd {font-weight: bold; font-size: 1em;} +sup {font-size: smaller; line-height: 1px;} + +.slide code {padding: 2px 0.25em; font-weight: bold; color: #533;} +.slide code.bad, code del {color: red;} +.slide code.old {color: silver;} +.slide pre {padding: 0; margin: 0.25em 0 0.5em 0.5em; color: #533; font-size: 90%;} +.slide pre code {display: block;} +.slide ul {margin-left: 5%; margin-right: 7%; list-style: disc;} +.slide li {margin-top: 0.75em; margin-right: 0;} +.slide ul ul {line-height: 1;} +.slide ul ul li {margin: .2em; font-size: 85%; list-style: square;} +.slide img.leader {display: block; margin: 0 auto;} + +div#header, div#footer {background: #005; color: #AAB; + font-family: Verdana, Helvetica, sans-serif;} +div#header {background: #005 url(bodybg.gif) -16px 0 no-repeat; + line-height: 1px;} +div#footer {font-size: 0.5em; font-weight: bold; padding: 1em 0;} +#footer h1, #footer h2 {display: block; padding: 0 1em;} +#footer h2 {font-style: italic;} + +div.long {font-size: 0.75em;} +.slide h1 {position: absolute; top: 0.7em; left: 87px; z-index: 1; + margin: 0; padding: 0.3em 0 0 50px; white-space: nowrap; + font: bold 150%/1em Helvetica, sans-serif; text-transform: capitalize; + color: #DDE; background: #005;} +.slide h3 {font-size: 130%;} +h1 abbr {font-variant: small-caps;} + +div#controls {position: absolute; left: 50%; bottom: 0; + width: 50%; + text-align: right; font: bold 0.9em Verdana, Helvetica, sans-serif;} +html>body div#controls {position: fixed; padding: 0 0 1em 0; + top: auto;} +div#controls form {position: absolute; bottom: 0; right: 0; width: 100%; + margin: 0; padding: 0;} +#controls #navLinks a {padding: 0; margin: 0 0.5em; + background: #005; border: none; color: #779; + cursor: pointer;} +#controls #navList {height: 1em;} +#controls #navList #jumplist {position: absolute; bottom: 0; right: 0; background: #DDD; color: #227;} + +#currentSlide {text-align: center; font-size: 0.5em; color: #449;} + +#slide0 {padding-top: 3.5em; font-size: 90%;} +#slide0 h1 {position: static; margin: 1em 0 0; padding: 0; + font: bold 2em Helvetica, sans-serif; white-space: normal; + color: #000; background: transparent;} +#slide0 h2 {font: bold italic 1em Helvetica, sans-serif; margin: 0.25em;} +#slide0 h3 {margin-top: 1.5em; font-size: 1.5em;} +#slide0 h4 {margin-top: 0; font-size: 1em;} + +ul.urls {list-style: none; display: inline; margin: 0;} +.urls li {display: inline; margin: 0;} +.note {display: none;} +.external {border-bottom: 1px dotted gray;} +html>body .external {border-bottom: none;} +.external:after {content: " \274F"; font-size: smaller; color: #77B;} + +.incremental, .incremental *, .incremental *:after {color: #DDE; visibility: visible;} +img.incremental {visibility: hidden;} +.slide .current {color: #B02;} + + +/* diagnostics + +li:after {content: " [" attr(class) "]"; color: #F88;} + */
\ No newline at end of file diff --git a/src/ui/default/print.css b/src/ui/default/print.css new file mode 100644 index 000000000..e7a71d145 --- /dev/null +++ b/src/ui/default/print.css @@ -0,0 +1 @@ +/* The following rule is necessary to have all slides appear in print! DO NOT REMOVE IT! */
.slide, ul {page-break-inside: avoid; visibility: visible !important;}
h1 {page-break-after: avoid;}
body {font-size: 12pt; background: white;}
* {color: black;}
#slide0 h1 {font-size: 200%; border: none; margin: 0.5em 0 0.25em;}
#slide0 h3 {margin: 0; padding: 0;}
#slide0 h4 {margin: 0 0 0.5em; padding: 0;}
#slide0 {margin-bottom: 3em;}
h1 {border-top: 2pt solid gray; border-bottom: 1px dotted silver;}
.extra {background: transparent !important;}
div.extra, pre.extra, .example {font-size: 10pt; color: #333;}
ul.extra a {font-weight: bold;}
p.example {display: none;}
#header {display: none;}
#footer h1 {margin: 0; border-bottom: 1px solid; color: gray; font-style: italic;}
#footer h2, #controls {display: none;}
/* The following rule keeps the layout stuff out of print. Remove at your own risk! */
.layout, .layout * {display: none !important;}
\ No newline at end of file diff --git a/src/ui/default/s5-core.css b/src/ui/default/s5-core.css new file mode 100644 index 000000000..86444e041 --- /dev/null +++ b/src/ui/default/s5-core.css @@ -0,0 +1,9 @@ +/* Do not edit or override these styles! The system will likely break if you do. */ + +div#header, div#footer, div#controls, .slide {position: absolute;} +html>body div#header, html>body div#footer, + html>body div#controls, html>body .slide {position: fixed;} +.handout {display: none;} +.layout {display: block;} +.slide, .hideme, .incremental {visibility: hidden;} +#slide0 {visibility: visible;} diff --git a/src/ui/default/slides.css b/src/ui/default/slides.css new file mode 100644 index 000000000..0786d7dbd --- /dev/null +++ b/src/ui/default/slides.css @@ -0,0 +1,3 @@ +@import url(s5-core.css); /* required to make the slide show run at all */ +@import url(framing.css); /* sets basic placement and size of slide components */ +@import url(pretty.css); /* stuff that makes the slides look better than blah */
\ No newline at end of file diff --git a/src/ui/default/slides.js b/src/ui/default/slides.js new file mode 100644 index 000000000..38fe8531c --- /dev/null +++ b/src/ui/default/slides.js @@ -0,0 +1,553 @@ +// S5 v1.1 slides.js -- released into the Public Domain +// +// Please see http://www.meyerweb.com/eric/tools/s5/credits.html for information +// about all the wonderful and talented contributors to this code! + +var undef; +var slideCSS = ''; +var snum = 0; +var smax = 1; +var incpos = 0; +var number = undef; +var s5mode = true; +var defaultView = 'slideshow'; +var controlVis = 'visible'; + +var isIE = navigator.appName == 'Microsoft Internet Explorer' && navigator.userAgent.indexOf('Opera') < 1 ? 1 : 0; +var isOp = navigator.userAgent.indexOf('Opera') > -1 ? 1 : 0; +var isGe = navigator.userAgent.indexOf('Gecko') > -1 && navigator.userAgent.indexOf('Safari') < 1 ? 1 : 0; + +function hasClass(object, className) { + if (!object.className) return false; + return (object.className.search('(^|\\s)' + className + '(\\s|$)') != -1); +} + +function hasValue(object, value) { + if (!object) return false; + return (object.search('(^|\\s)' + value + '(\\s|$)') != -1); +} + +function removeClass(object,className) { + if (!object) return; + object.className = object.className.replace(new RegExp('(^|\\s)'+className+'(\\s|$)'), RegExp.$1+RegExp.$2); +} + +function addClass(object,className) { + if (!object || hasClass(object, className)) return; + if (object.className) { + object.className += ' '+className; + } else { + object.className = className; + } +} + +function GetElementsWithClassName(elementName,className) { + var allElements = document.getElementsByTagName(elementName); + var elemColl = new Array(); + for (var i = 0; i< allElements.length; i++) { + if (hasClass(allElements[i], className)) { + elemColl[elemColl.length] = allElements[i]; + } + } + return elemColl; +} + +function isParentOrSelf(element, id) { + if (element == null || element.nodeName=='BODY') return false; + else if (element.id == id) return true; + else return isParentOrSelf(element.parentNode, id); +} + +function nodeValue(node) { + var result = ""; + if (node.nodeType == 1) { + var children = node.childNodes; + for (var i = 0; i < children.length; ++i) { + result += nodeValue(children[i]); + } + } + else if (node.nodeType == 3) { + result = node.nodeValue; + } + return(result); +} + +function slideLabel() { + var slideColl = GetElementsWithClassName('*','slide'); + var list = document.getElementById('jumplist'); + smax = slideColl.length; + for (var n = 0; n < smax; n++) { + var obj = slideColl[n]; + + var did = 'slide' + n.toString(); + obj.setAttribute('id',did); + if (isOp) continue; + + var otext = ''; + var menu = obj.firstChild; + if (!menu) continue; // to cope with empty slides + while (menu && menu.nodeType == 3) { + menu = menu.nextSibling; + } + if (!menu) continue; // to cope with slides with only text nodes + + var menunodes = menu.childNodes; + for (var o = 0; o < menunodes.length; o++) { + otext += nodeValue(menunodes[o]); + } + list.options[list.length] = new Option(n + ' : ' + otext, n); + } +} + +function currentSlide() { + var cs; + if (document.getElementById) { + cs = document.getElementById('currentSlide'); + } else { + cs = document.currentSlide; + } + cs.innerHTML = '<span id="csHere">' + snum + '<\/span> ' + + '<span id="csSep">\/<\/span> ' + + '<span id="csTotal">' + (smax-1) + '<\/span>'; + if (snum == 0) { + cs.style.visibility = 'hidden'; + } else { + cs.style.visibility = 'visible'; + } +} + +function go(step) { + if (document.getElementById('slideProj').disabled || step == 0) return; + var jl = document.getElementById('jumplist'); + var cid = 'slide' + snum; + var ce = document.getElementById(cid); + if (incrementals[snum].length > 0) { + for (var i = 0; i < incrementals[snum].length; i++) { + removeClass(incrementals[snum][i], 'current'); + removeClass(incrementals[snum][i], 'incremental'); + } + } + if (step != 'j') { + snum += step; + lmax = smax - 1; + if (snum > lmax) snum = lmax; + if (snum < 0) snum = 0; + } else + snum = parseInt(jl.value); + var nid = 'slide' + snum; + var ne = document.getElementById(nid); + if (!ne) { + ne = document.getElementById('slide0'); + snum = 0; + } + if (step < 0) {incpos = incrementals[snum].length} else {incpos = 0;} + if (incrementals[snum].length > 0 && incpos == 0) { + for (var i = 0; i < incrementals[snum].length; i++) { + if (hasClass(incrementals[snum][i], 'current')) + incpos = i + 1; + else + addClass(incrementals[snum][i], 'incremental'); + } + } + if (incrementals[snum].length > 0 && incpos > 0) + addClass(incrementals[snum][incpos - 1], 'current'); + ce.style.visibility = 'hidden'; + ne.style.visibility = 'visible'; + jl.selectedIndex = snum; + currentSlide(); + number = 0; +} + +function goTo(target) { + if (target >= smax || target == snum) return; + go(target - snum); +} + +function subgo(step) { + if (step > 0) { + removeClass(incrementals[snum][incpos - 1],'current'); + removeClass(incrementals[snum][incpos], 'incremental'); + addClass(incrementals[snum][incpos],'current'); + incpos++; + } else { + incpos--; + removeClass(incrementals[snum][incpos],'current'); + addClass(incrementals[snum][incpos], 'incremental'); + addClass(incrementals[snum][incpos - 1],'current'); + } +} + +function toggle() { + var slideColl = GetElementsWithClassName('*','slide'); + var slides = document.getElementById('slideProj'); + var outline = document.getElementById('outlineStyle'); + if (!slides.disabled) { + slides.disabled = true; + outline.disabled = false; + s5mode = false; + fontSize('1em'); + for (var n = 0; n < smax; n++) { + var slide = slideColl[n]; + slide.style.visibility = 'visible'; + } + } else { + slides.disabled = false; + outline.disabled = true; + s5mode = true; + fontScale(); + for (var n = 0; n < smax; n++) { + var slide = slideColl[n]; + slide.style.visibility = 'hidden'; + } + slideColl[snum].style.visibility = 'visible'; + } +} + +function showHide(action) { + var obj = GetElementsWithClassName('*','hideme')[0]; + switch (action) { + case 's': obj.style.visibility = 'visible'; break; + case 'h': obj.style.visibility = 'hidden'; break; + case 'k': + if (obj.style.visibility != 'visible') { + obj.style.visibility = 'visible'; + } else { + obj.style.visibility = 'hidden'; + } + break; + } +} + +// 'keys' code adapted from MozPoint (http://mozpoint.mozdev.org/) +function keys(key) { + if (!key) { + key = event; + key.which = key.keyCode; + } + if (key.which == 84) { + toggle(); + return; + } + if (s5mode) { + switch (key.which) { + case 10: // return + case 13: // enter + if (window.event && isParentOrSelf(window.event.srcElement, 'controls')) return; + if (key.target && isParentOrSelf(key.target, 'controls')) return; + if(number != undef) { + goTo(number); + break; + } + case 32: // spacebar + case 34: // page down + case 39: // rightkey + case 40: // downkey + if(number != undef) { + go(number); + } else if (!incrementals[snum] || incpos >= incrementals[snum].length) { + go(1); + } else { + subgo(1); + } + break; + case 33: // page up + case 37: // leftkey + case 38: // upkey + if(number != undef) { + go(-1 * number); + } else if (!incrementals[snum] || incpos <= 0) { + go(-1); + } else { + subgo(-1); + } + break; + case 36: // home + goTo(0); + break; + case 35: // end + goTo(smax-1); + break; + case 67: // c + showHide('k'); + break; + } + if (key.which < 48 || key.which > 57) { + number = undef; + } else { + if (window.event && isParentOrSelf(window.event.srcElement, 'controls')) return; + if (key.target && isParentOrSelf(key.target, 'controls')) return; + number = (((number != undef) ? number : 0) * 10) + (key.which - 48); + } + } + return false; +} + +function clicker(e) { + number = undef; + var target; + if (window.event) { + target = window.event.srcElement; + e = window.event; + } else target = e.target; + if (target.getAttribute('href') != null || hasValue(target.rel, 'external') || isParentOrSelf(target, 'controls') || isParentOrSelf(target,'embed') || isParentOrSelf(target,'object')) return true; + if (!e.which || e.which == 1) { + if (!incrementals[snum] || incpos >= incrementals[snum].length) { + go(1); + } else { + subgo(1); + } + } +} + +function findSlide(hash) { + var target = null; + var slides = GetElementsWithClassName('*','slide'); + for (var i = 0; i < slides.length; i++) { + var targetSlide = slides[i]; + if ( (targetSlide.name && targetSlide.name == hash) + || (targetSlide.id && targetSlide.id == hash) ) { + target = targetSlide; + break; + } + } + while(target != null && target.nodeName != 'BODY') { + if (hasClass(target, 'slide')) { + return parseInt(target.id.slice(5)); + } + target = target.parentNode; + } + return null; +} + +function slideJump() { + if (window.location.hash == null) return; + var sregex = /^#slide(\d+)$/; + var matches = sregex.exec(window.location.hash); + var dest = null; + if (matches != null) { + dest = parseInt(matches[1]); + } else { + dest = findSlide(window.location.hash.slice(1)); + } + if (dest != null) + go(dest - snum); +} + +function fixLinks() { + var thisUri = window.location.href; + thisUri = thisUri.slice(0, thisUri.length - window.location.hash.length); + var aelements = document.getElementsByTagName('A'); + for (var i = 0; i < aelements.length; i++) { + var a = aelements[i].href; + var slideID = a.match('\#slide[0-9]{1,2}'); + if ((slideID) && (slideID[0].slice(0,1) == '#')) { + var dest = findSlide(slideID[0].slice(1)); + if (dest != null) { + if (aelements[i].addEventListener) { + aelements[i].addEventListener("click", new Function("e", + "if (document.getElementById('slideProj').disabled) return;" + + "go("+dest+" - snum); " + + "if (e.preventDefault) e.preventDefault();"), true); + } else if (aelements[i].attachEvent) { + aelements[i].attachEvent("onclick", new Function("", + "if (document.getElementById('slideProj').disabled) return;" + + "go("+dest+" - snum); " + + "event.returnValue = false;")); + } + } + } + } +} + +function externalLinks() { + if (!document.getElementsByTagName) return; + var anchors = document.getElementsByTagName('a'); + for (var i=0; i<anchors.length; i++) { + var anchor = anchors[i]; + if (anchor.getAttribute('href') && hasValue(anchor.rel, 'external')) { + anchor.target = '_blank'; + addClass(anchor,'external'); + } + } +} + +function createControls() { + var controlsDiv = document.getElementById("controls"); + if (!controlsDiv) return; + var hider = ' onmouseover="showHide(\'s\');" onmouseout="showHide(\'h\');"'; + var hideDiv, hideList = ''; + if (controlVis == 'hidden') { + hideDiv = hider; + } else { + hideList = hider; + } + controlsDiv.innerHTML = '<form action="#" id="controlForm"' + hideDiv + '>' + + '<div id="navLinks">' + + '<a accesskey="t" id="toggle" href="javascript:toggle();">Ø<\/a>' + + '<a accesskey="z" id="prev" href="javascript:go(-1);">«<\/a>' + + '<a accesskey="x" id="next" href="javascript:go(1);">»<\/a>' + + '<div id="navList"' + hideList + '><select id="jumplist" onchange="go(\'j\');"><\/select><\/div>' + + '<\/div><\/form>'; + if (controlVis == 'hidden') { + var hidden = document.getElementById('navLinks'); + } else { + var hidden = document.getElementById('jumplist'); + } + addClass(hidden,'hideme'); +} + +function fontScale() { // causes layout problems in FireFox that get fixed if browser's Reload is used; same may be true of other Gecko-based browsers + if (!s5mode) return false; + var vScale = 22; // both yield 32 (after rounding) at 1024x768 + var hScale = 32; // perhaps should auto-calculate based on theme's declared value? + if (window.innerHeight) { + var vSize = window.innerHeight; + var hSize = window.innerWidth; + } else if (document.documentElement.clientHeight) { + var vSize = document.documentElement.clientHeight; + var hSize = document.documentElement.clientWidth; + } else if (document.body.clientHeight) { + var vSize = document.body.clientHeight; + var hSize = document.body.clientWidth; + } else { + var vSize = 700; // assuming 1024x768, minus chrome and such + var hSize = 1024; // these do not account for kiosk mode or Opera Show + } + var newSize = Math.min(Math.round(vSize/vScale),Math.round(hSize/hScale)); + fontSize(newSize + 'px'); + if (isGe) { // hack to counter incremental reflow bugs + var obj = document.getElementsByTagName('body')[0]; + obj.style.display = 'none'; + obj.style.display = 'block'; + } +} + +function fontSize(value) { + if (!(s5ss = document.getElementById('s5ss'))) { + if (!isIE) { + document.getElementsByTagName('head')[0].appendChild(s5ss = document.createElement('style')); + s5ss.setAttribute('media','screen, projection'); + s5ss.setAttribute('id','s5ss'); + } else { + document.createStyleSheet(); + document.s5ss = document.styleSheets[document.styleSheets.length - 1]; + } + } + if (!isIE) { + while (s5ss.lastChild) s5ss.removeChild(s5ss.lastChild); + s5ss.appendChild(document.createTextNode('body {font-size: ' + value + ' !important;}')); + } else { + document.s5ss.addRule('body','font-size: ' + value + ' !important;'); + } +} + +function notOperaFix() { + slideCSS = document.getElementById('slideProj').href; + var slides = document.getElementById('slideProj'); + var outline = document.getElementById('outlineStyle'); + slides.setAttribute('media','screen'); + outline.disabled = true; + if (isGe) { + slides.setAttribute('href','null'); // Gecko fix + slides.setAttribute('href',slideCSS); // Gecko fix + } + if (isIE && document.styleSheets && document.styleSheets[0]) { + document.styleSheets[0].addRule('img', 'behavior: url(ui/default/iepngfix.htc)'); + document.styleSheets[0].addRule('div', 'behavior: url(ui/default/iepngfix.htc)'); + document.styleSheets[0].addRule('.slide', 'behavior: url(ui/default/iepngfix.htc)'); + } +} + +function getIncrementals(obj) { + var incrementals = new Array(); + if (!obj) + return incrementals; + var children = obj.childNodes; + for (var i = 0; i < children.length; i++) { + var child = children[i]; + if (hasClass(child, 'incremental')) { + if (child.nodeName == 'OL' || child.nodeName == 'UL') { + removeClass(child, 'incremental'); + for (var j = 0; j < child.childNodes.length; j++) { + if (child.childNodes[j].nodeType == 1) { + addClass(child.childNodes[j], 'incremental'); + } + } + } else { + incrementals[incrementals.length] = child; + removeClass(child,'incremental'); + } + } + if (hasClass(child, 'show-first')) { + if (child.nodeName == 'OL' || child.nodeName == 'UL') { + removeClass(child, 'show-first'); + if (child.childNodes[isGe].nodeType == 1) { + removeClass(child.childNodes[isGe], 'incremental'); + } + } else { + incrementals[incrementals.length] = child; + } + } + incrementals = incrementals.concat(getIncrementals(child)); + } + return incrementals; +} + +function createIncrementals() { + var incrementals = new Array(); + for (var i = 0; i < smax; i++) { + incrementals[i] = getIncrementals(document.getElementById('slide'+i)); + } + return incrementals; +} + +function defaultCheck() { + var allMetas = document.getElementsByTagName('meta'); + for (var i = 0; i< allMetas.length; i++) { + if (allMetas[i].name == 'defaultView') { + defaultView = allMetas[i].content; + } + if (allMetas[i].name == 'controlVis') { + controlVis = allMetas[i].content; + } + } +} + +// Key trap fix, new function body for trap() +function trap(e) { + if (!e) { + e = event; + e.which = e.keyCode; + } + try { + modifierKey = e.ctrlKey || e.altKey || e.metaKey; + } + catch(e) { + modifierKey = false; + } + return modifierKey || e.which == 0; +} + +function startup() { + defaultCheck(); + if (!isOp) + createControls(); + slideLabel(); + fixLinks(); + externalLinks(); + fontScale(); + if (!isOp) { + notOperaFix(); + incrementals = createIncrementals(); + slideJump(); + if (defaultView == 'outline') { + toggle(); + } + document.onkeyup = keys; + document.onkeypress = trap; + document.onclick = clicker; + } +} + +window.onload = startup; +window.onresize = function(){setTimeout('fontScale()', 50);}
\ No newline at end of file diff --git a/tests/MarkdownTest_1.0.3/MarkdownTest.pl b/tests/MarkdownTest_1.0.3/MarkdownTest.pl new file mode 100644 index 000000000..55553d09c --- /dev/null +++ b/tests/MarkdownTest_1.0.3/MarkdownTest.pl @@ -0,0 +1,176 @@ +#!/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 new file mode 100644 index 000000000..9606860b6 --- /dev/null +++ b/tests/MarkdownTest_1.0.3/Tests/Amps and angle encoding.html @@ -0,0 +1,17 @@ +<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 new file mode 100644 index 000000000..0e9527f93 --- /dev/null +++ b/tests/MarkdownTest_1.0.3/Tests/Amps and angle encoding.text @@ -0,0 +1,21 @@ +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 new file mode 100644 index 000000000..f8df9852c --- /dev/null +++ b/tests/MarkdownTest_1.0.3/Tests/Auto links.html @@ -0,0 +1,18 @@ +<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 new file mode 100644 index 000000000..abbc48869 --- /dev/null +++ b/tests/MarkdownTest_1.0.3/Tests/Auto links.text @@ -0,0 +1,13 @@ +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 new file mode 100644 index 000000000..29870dac5 --- /dev/null +++ b/tests/MarkdownTest_1.0.3/Tests/Backslash escapes.html @@ -0,0 +1,118 @@ +<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 new file mode 100644 index 000000000..5b014cb33 --- /dev/null +++ b/tests/MarkdownTest_1.0.3/Tests/Backslash escapes.text @@ -0,0 +1,120 @@ +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 new file mode 100644 index 000000000..990202a1b --- /dev/null +++ b/tests/MarkdownTest_1.0.3/Tests/Blockquotes with code blocks.html @@ -0,0 +1,15 @@ +<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 new file mode 100644 index 000000000..c31d17104 --- /dev/null +++ b/tests/MarkdownTest_1.0.3/Tests/Blockquotes with code blocks.text @@ -0,0 +1,11 @@ +> 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 new file mode 100644 index 000000000..32703f5cb --- /dev/null +++ b/tests/MarkdownTest_1.0.3/Tests/Code Blocks.html @@ -0,0 +1,18 @@ +<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 new file mode 100644 index 000000000..b54b09285 --- /dev/null +++ b/tests/MarkdownTest_1.0.3/Tests/Code Blocks.text @@ -0,0 +1,14 @@ + 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 new file mode 100644 index 000000000..4b8afbb70 --- /dev/null +++ b/tests/MarkdownTest_1.0.3/Tests/Code Spans.html @@ -0,0 +1,6 @@ +<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 new file mode 100644 index 000000000..750a1973d --- /dev/null +++ b/tests/MarkdownTest_1.0.3/Tests/Code Spans.text @@ -0,0 +1,6 @@ +`<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 new file mode 100644 index 000000000..e21ac79a2 --- /dev/null +++ b/tests/MarkdownTest_1.0.3/Tests/Hard-wrapped paragraphs with list-like lines.html @@ -0,0 +1,8 @@ +<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 new file mode 100644 index 000000000..f8a5b27bf --- /dev/null +++ b/tests/MarkdownTest_1.0.3/Tests/Hard-wrapped paragraphs with list-like lines.text @@ -0,0 +1,8 @@ +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 new file mode 100644 index 000000000..2dc2ab656 --- /dev/null +++ b/tests/MarkdownTest_1.0.3/Tests/Horizontal rules.html @@ -0,0 +1,71 @@ +<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 new file mode 100644 index 000000000..1594bda27 --- /dev/null +++ b/tests/MarkdownTest_1.0.3/Tests/Horizontal rules.text @@ -0,0 +1,67 @@ +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 new file mode 100644 index 000000000..3af9cafb1 --- /dev/null +++ b/tests/MarkdownTest_1.0.3/Tests/Inline HTML (Advanced).html @@ -0,0 +1,15 @@ +<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 new file mode 100644 index 000000000..86b7206d2 --- /dev/null +++ b/tests/MarkdownTest_1.0.3/Tests/Inline HTML (Advanced).text @@ -0,0 +1,15 @@ +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 new file mode 100644 index 000000000..6bf78f8fc --- /dev/null +++ b/tests/MarkdownTest_1.0.3/Tests/Inline HTML (Simple).html @@ -0,0 +1,72 @@ +<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 new file mode 100644 index 000000000..14aa2dc27 --- /dev/null +++ b/tests/MarkdownTest_1.0.3/Tests/Inline HTML (Simple).text @@ -0,0 +1,69 @@ +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 new file mode 100644 index 000000000..3f167a161 --- /dev/null +++ b/tests/MarkdownTest_1.0.3/Tests/Inline HTML comments.html @@ -0,0 +1,13 @@ +<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 new file mode 100644 index 000000000..41d830d03 --- /dev/null +++ b/tests/MarkdownTest_1.0.3/Tests/Inline HTML comments.text @@ -0,0 +1,13 @@ +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 new file mode 100644 index 000000000..f36607ddd --- /dev/null +++ b/tests/MarkdownTest_1.0.3/Tests/Links, inline style.html @@ -0,0 +1,11 @@ +<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 new file mode 100644 index 000000000..09017a90c --- /dev/null +++ b/tests/MarkdownTest_1.0.3/Tests/Links, inline style.text @@ -0,0 +1,12 @@ +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 new file mode 100644 index 000000000..8e70c32f4 --- /dev/null +++ b/tests/MarkdownTest_1.0.3/Tests/Links, reference style.html @@ -0,0 +1,52 @@ +<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 new file mode 100644 index 000000000..341ec88e3 --- /dev/null +++ b/tests/MarkdownTest_1.0.3/Tests/Links, reference style.text @@ -0,0 +1,71 @@ +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 new file mode 100644 index 000000000..bf81e939f --- /dev/null +++ b/tests/MarkdownTest_1.0.3/Tests/Links, shortcut references.html @@ -0,0 +1,9 @@ +<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 new file mode 100644 index 000000000..8c44c98fe --- /dev/null +++ b/tests/MarkdownTest_1.0.3/Tests/Links, shortcut references.text @@ -0,0 +1,20 @@ +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 new file mode 100644 index 000000000..611c1ac61 --- /dev/null +++ b/tests/MarkdownTest_1.0.3/Tests/Literal quotes in titles.html @@ -0,0 +1,3 @@ +<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 new file mode 100644 index 000000000..29d0e4235 --- /dev/null +++ b/tests/MarkdownTest_1.0.3/Tests/Literal quotes in titles.text @@ -0,0 +1,7 @@ +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 new file mode 100644 index 000000000..d5bdbb29a --- /dev/null +++ b/tests/MarkdownTest_1.0.3/Tests/Markdown Documentation - Basics.html @@ -0,0 +1,314 @@ +<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 new file mode 100644 index 000000000..486055ca7 --- /dev/null +++ b/tests/MarkdownTest_1.0.3/Tests/Markdown Documentation - Basics.text @@ -0,0 +1,306 @@ +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 new file mode 100644 index 000000000..5c01306cc --- /dev/null +++ b/tests/MarkdownTest_1.0.3/Tests/Markdown Documentation - Syntax.html @@ -0,0 +1,942 @@ +<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 new file mode 100644 index 000000000..57360a16c --- /dev/null +++ b/tests/MarkdownTest_1.0.3/Tests/Markdown Documentation - Syntax.text @@ -0,0 +1,888 @@ +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 new file mode 100644 index 000000000..d8ec7f8e0 --- /dev/null +++ b/tests/MarkdownTest_1.0.3/Tests/Nested blockquotes.html @@ -0,0 +1,9 @@ +<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 new file mode 100644 index 000000000..ed3c624ff --- /dev/null +++ b/tests/MarkdownTest_1.0.3/Tests/Nested blockquotes.text @@ -0,0 +1,5 @@ +> 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 new file mode 100644 index 000000000..ba71eab39 --- /dev/null +++ b/tests/MarkdownTest_1.0.3/Tests/Ordered and unordered lists.html @@ -0,0 +1,148 @@ +<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 new file mode 100644 index 000000000..7f3b49777 --- /dev/null +++ b/tests/MarkdownTest_1.0.3/Tests/Ordered and unordered lists.text @@ -0,0 +1,131 @@ +## 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 new file mode 100644 index 000000000..71ec78c70 --- /dev/null +++ b/tests/MarkdownTest_1.0.3/Tests/Strong and em together.html @@ -0,0 +1,7 @@ +<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 new file mode 100644 index 000000000..95ee690db --- /dev/null +++ b/tests/MarkdownTest_1.0.3/Tests/Strong and em together.text @@ -0,0 +1,7 @@ +***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 new file mode 100644 index 000000000..3301ba803 --- /dev/null +++ b/tests/MarkdownTest_1.0.3/Tests/Tabs.html @@ -0,0 +1,25 @@ +<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 new file mode 100644 index 000000000..589d1136e --- /dev/null +++ b/tests/MarkdownTest_1.0.3/Tests/Tabs.text @@ -0,0 +1,21 @@ ++ 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 new file mode 100644 index 000000000..f2a8ce70f --- /dev/null +++ b/tests/MarkdownTest_1.0.3/Tests/Tidyness.html @@ -0,0 +1,8 @@ +<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 new file mode 100644 index 000000000..5f18b8da2 --- /dev/null +++ b/tests/MarkdownTest_1.0.3/Tests/Tidyness.text @@ -0,0 +1,5 @@ +> A list within a blockquote: +> +> * asterisk 1 +> * asterisk 2 +> * asterisk 3 diff --git a/tests/bodybg.gif b/tests/bodybg.gif Binary files differnew file mode 100644 index 000000000..5f448a16f --- /dev/null +++ b/tests/bodybg.gif diff --git a/tests/generate.sh b/tests/generate.sh new file mode 100644 index 000000000..75b3bb9ee --- /dev/null +++ b/tests/generate.sh @@ -0,0 +1,10 @@ +#!/bin/sh + +../pandoc -r native -s -w native testsuite.native > writer.native +../pandoc -r native -s -w markdown testsuite.native > writer.markdown +../pandoc -r native -s -w rst testsuite.native > writer.rst +../pandoc -r native -s -w html testsuite.native > writer.html +../pandoc -r native -s -w html -S testsuite.native > writer.smart.html +../pandoc -r native -s -w latex testsuite.native > writer.latex +../pandoc -r native -s -w rtf testsuite.native > writer.rtf + diff --git a/tests/html-reader.html b/tests/html-reader.html new file mode 100644 index 000000000..0df91b335 --- /dev/null +++ b/tests/html-reader.html @@ -0,0 +1,399 @@ +<html> +<head> +<meta http-equiv="Content-Type" content="text/html; charset=UTF-8" /> +<meta name="generator" content="pandoc" /> +<style type="text/css"> +div.pandocNote { border-left: 1px solid grey; padding-left: 1em; } +span.pandocNoteRef { vertical-align: super; font-size: 80%; } +span.pandocNoteMarker { } +</style> +<title>Pandoc Test Suite</title> +</head> +<body> +<h1 class="title">Pandoc Test Suite</h1> +<p>This is a set of tests for pandoc. Most of them are adapted from John Gruber's markdown test suite.</p> +<hr /> +<h1>Headers</h1> +<h2>Level 2 with an <a href="/url">embedded link</a></h2> +<h3>Level 3 with <em>emphasis</em></h3> +<h4>Level 4</h4> +<h5>Level 5</h5> +<h1>Level 1</h1> +<h2>Level 2 with <em>emphasis</em></h2> +<h3>Level 3</h3> +<p>with no blank line</p> +<h2>Level 2</h2> +<p>with no blank line</p> +<hr /> +<h1>Paragraphs</h1> +<p>Here's a regular paragraph.</p> +<p>In Markdown 1.0.0 and earlier. Version 8. This line turns into a list item. Because a hard-wrapped line in the middle of a paragraph looked like a list item.</p> +<p>Here's one with a bullet. * criminey.</p> +<p>There should be a hard line break<br /> + here.</p> +<hr /> +<h1>Block Quotes</h1> +<p>E-mail style:</p> +<blockquote> +<p>This is a block quote. It is pretty short.</p> +</blockquote> +<blockquote> +<p>Code in a block quote:</p> +<pre><code>sub status { + print "working"; +} +</code></pre> +<p>A list:</p> +<ol> +<li>item one</li> +<li>item two</li> +</ol> +<p>Nested block quotes:</p> +<blockquote> +<p>nested</p> +</blockquote> +<blockquote> +<p>nested</p> +</blockquote> +</blockquote> +<p>This should not be a block quote: 2 > 1.</p> +<p>Box-style:</p> +<blockquote> +<p>Example:</p> +<pre><code>sub status { + print "working"; +} +</code></pre> +</blockquote> +<blockquote> +<ol> +<li>do laundry</li> +<li>take out the trash</li> +</ol> +</blockquote> +<p>Here's a nested one:</p> +<blockquote> +<p>Joe said:</p> +<blockquote> +<p>Don't quote me.</p> +</blockquote> +</blockquote> +<p>And a following paragraph.</p> +<hr /> +<h1>Code Blocks</h1> +<p>Code:</p> +<pre><code>---- (should be four hyphens) + +sub status { + print "working"; +} + +this code block is indented by one tab +</code></pre> +<p>And:</p> +<pre><code> this code block is indented by two tabs + +These should not be escaped: \$ \\ \> \[ \{ +</code></pre> +<hr /> +<h1>Lists</h1> +<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> +<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> +<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 1. 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> +<h2>Tabs and spaces</h2> +<ul> +<li><p>this is a list item indented with tabs</p> +</li> +<li><p>this is a list item indented with spaces</p> +<ul> +<li><p>this is an example list item indented with tabs</p> +</li> +<li><p>this is an example list item indented with spaces</p> +</li> +</ul> +</li> +</ul> +<hr /> +<h1>HTML Blocks</h1> +<p>Simple block on one line:</p> +foo<p>And nested without indentation:</p> +foobar<p>Interpreted markdown in a table:</p> +This is <em>emphasized</em>. And this is <strong>strong</strong><p>Here's a simple block:</p> +foo<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> +foo<p>This should just be an HTML comment:</p> +<p>Multiline:</p> +<p>Code block:</p> +<pre><code><!-- Comment --> +</code></pre> +<p>Just plain comment, with trailing spaces on the line:</p> +<p>Code:</p> +<pre><code><hr /> +</code></pre> +<p>Hr's:</p> +<hr /> +<hr /> +<hr /> +<hr /> +<hr /> +<hr /> +<hr /> +<hr /> +<hr /> +<hr /> +<h1>Inline Markup</h1> +<p>This is <em>emphasized</em>, and so <em>is this</em>.</p> +<p>This is <strong>strong</strong>, and so <strong>is this</strong>.</p> +<p>An <em><a href="/url">emphasized link</a></em>.</p> +<p><strong><em>This is strong and em.</em></strong></p> +<p>So is <strong><em>this</em></strong> word.</p> +<p><strong><em>This is strong and em.</em></strong></p> +<p>So is <strong><em>this</em></strong> word.</p> +<p>This is code: <code>></code>, <code>$</code>, <code>\</code>, <code>\$</code>, <code><html></code>.</p> +<hr /> +<h1>Smart quotes, ellipses, dashes</h1> +<p>"Hello," said the spider. "'Shelob' is my name."</p> +<p>'A', 'B', and 'C' are letters.</p> +<p>'Oak,' 'elm,' and 'beech' are names of trees. So is 'pine.'</p> +<p>'He said, "I want to go."' Were you alive in the 70's?</p> +<p>Here is some quoted '<code>code</code>' and a "<a href="http://example.com/?foo=1&bar=2">quoted link</a>".</p> +<p>Some dashes: one---two --- three--four -- five.</p> +<p>Dashes between numbers: 5-7, 255-66, 1987-1999.</p> +<p>Ellipses...and. . .and . . . .</p> +<hr /> +<h1>LaTeX</h1> +<ul> +<li>\cite[22-23]{smith.1899}</li> +<li>\doublespacing</li> +<li>$2+2=4$</li> +<li>$x \in y$</li> +<li>$\alpha \wedge \omega$</li> +<li>$223$</li> +<li>$p$-Tree</li> +<li>$\frac{d}{dx}f(x)=\lim_{h\to 0}\frac{f(x+h)-f(x)}{h}$</li> +<li>Here's one that has a line break in it: $\alpha + \omega \times x^2$.</li> +</ul> +<p>These shouldn't be math:</p> +<ul> +<li>To get the famous equation, write <code>$e = mc^2$</code>.</li> +<li>$22,000 is a <em>lot</em> of money. So is $34,000. (It worked if "lot" is emphasized.)</li> +<li>Escaped <code>$</code>: $73 <em>this should be emphasized</em> 23$.</li> +</ul> +<p>Here's a LaTeX table:</p> +<p>\begin{tabular}{|l|l|}\hline Animal & Number \\ \hline Dog & 2 \\ Cat & 1 \\ \hline \end{tabular}</p> +<hr /> +<h1>Special Characters</h1> +<p>Here is some unicode:</p> +<ul> +<li>I hat: Î</li> +<li>o umlaut: ö</li> +<li>section: §</li> +<li>set membership: ∈</li> +<li>copyright: ©</li> +</ul> +<p>AT&T has an ampersand in their name.</p> +<p>AT&T is another way to write it.</p> +<p>This & that.</p> +<p>4 < 5.</p> +<p>6 > 5.</p> +<p>Backslash: \</p> +<p>Backtick: `</p> +<p>Asterisk: *</p> +<p>Underscore: _</p> +<p>Left brace: {</p> +<p>Right brace: }</p> +<p>Left bracket: [</p> +<p>Right bracket: ]</p> +<p>Left paren: (</p> +<p>Right paren: )</p> +<p>Greater-than: ></p> +<p>Hash: #</p> +<p>Period: .</p> +<p>Bang: !</p> +<p>Plus: +</p> +<p>Minus: -</p> +<hr /> +<h1>Links</h1> +<h2>Explicit</h2> +<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 with "quotes" in it">URL and title</a></p> +<p><a href="/url/" title="title with single quotes">URL and title</a></p> +Email link (nobody [at] nowhere.net)<p><a href="">Empty</a>.</p> +<h2>Reference</h2> +<p>Foo <a href="/url/">bar</a>.</p> +<p>Foo <a href="/url/">bar</a>.</p> +<p>Foo <a href="/url/">bar</a>.</p> +<p>With <a href="/url/">embedded [brackets]</a>.</p> +<p><a href="/url/">b</a> by itself should be a link.</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>This should [not] be a link.</p> +<pre><code>[not]: /url +</code></pre> +<p>Foo <a href="/url/" title="Title with "quotes" inside">bar</a>.</p> +<p>Foo <a href="/url/" title="Title with "quote" inside">biz</a>.</p> +<h2>With ampersands</h2> +<p>Here's a <a href="http://example.com/?foo=1&bar=2">link with an ampersand in the URL</a>.</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 <a href="/script?foo=1&bar=2">inline link</a>.</p> +<p>Here's an <a href="/script?foo=1&bar=2">inline link in pointy braces</a>.</p> +<h2>Autolinks</h2> +<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> +An e-mail address: nobody [at] nowhere.net<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> +<hr /> +<h1>Images</h1> +<p>From "Voyage dans la Lune" by Georges Melies (1902):</p> +<p><img src="lalune.jpg" title="Voyage dans la Lune" alt="lalune"></p> +<p>Here is a movie <img src="movie.jpg" alt="movie"> icon.</p> +<hr /> +<h1>Footnotes</h1> +<p>Here is a footnote reference<a href="#note_1">(1)</a>, and another<a href="#note_longnote">(longnote)</a>. This should <em>not</em> be a footnote reference, because it contains a space^(my note).</p> +<p><a href="#ref_1">(1)</a> Here is the footnote. It can go anywhere in the document, not just at the end.</p> +<p><a href="#ref_longnote">(longnote)</a> Here's the other note. This one contains multiple blocks.</p> +<p>Caret characters are used to indicate that the blocks all belong to a single footnote (as with block quotes).</p> +<pre><code> { <code> } +</code></pre> +<p>If you want, you can use a caret at the beginning of every line, as with blockquotes, but all that you need is a caret at the beginning of the first line of the block and any preceding blank lines.</p> +</body> +</html> + diff --git a/tests/html-reader.native b/tests/html-reader.native new file mode 100644 index 000000000..e018f6c7b --- /dev/null +++ b/tests/html-reader.native @@ -0,0 +1,328 @@ +Pandoc (Meta [Str "Pandoc",Space,Str "Test",Space,Str "Suite"] [] "") +[ Para [Str "This",Space,Str "is",Space,Str "a",Space,Str "set",Space,Str "of",Space,Str "tests",Space,Str "for",Space,Str "pandoc.",Space,Str "Most",Space,Str "of",Space,Str "them",Space,Str "are",Space,Str "adapted",Space,Str "from",Space,Str "John",Space,Str "Gruber's",Space,Str "markdown",Space,Str "test",Space,Str "suite."] +, HorizontalRule +, Header 1 [Str "Headers"] +, Header 2 [Str "Level",Space,Str "2",Space,Str "with",Space,Str "an",Space,Link [Str "embedded",Space,Str "link"] (Ref [Str "1"])] +, Header 3 [Str "Level",Space,Str "3",Space,Str "with",Space,Emph [Str "emphasis"]] +, Header 4 [Str "Level",Space,Str "4"] +, Header 5 [Str "Level",Space,Str "5"] +, Header 1 [Str "Level",Space,Str "1"] +, Header 2 [Str "Level",Space,Str "2",Space,Str "with",Space,Emph [Str "emphasis"]] +, Header 3 [Str "Level",Space,Str "3"] +, Para [Str "with",Space,Str "no",Space,Str "blank",Space,Str "line"] +, Header 2 [Str "Level",Space,Str "2"] +, Para [Str "with",Space,Str "no",Space,Str "blank",Space,Str "line"] +, HorizontalRule +, Header 1 [Str "Paragraphs"] +, Para [Str "Here's",Space,Str "a",Space,Str "regular",Space,Str "paragraph."] +, Para [Str "In",Space,Str "Markdown",Space,Str "1.0.0",Space,Str "and",Space,Str "earlier.",Space,Str "Version",Space,Str "8.",Space,Str "This",Space,Str "line",Space,Str "turns",Space,Str "into",Space,Str "a",Space,Str "list",Space,Str "item.",Space,Str "Because",Space,Str "a",Space,Str "hard-wrapped",Space,Str "line",Space,Str "in",Space,Str "the",Space,Str "middle",Space,Str "of",Space,Str "a",Space,Str "paragraph",Space,Str "looked",Space,Str "like",Space,Str "a",Space,Str "list",Space,Str "item."] +, Para [Str "Here's",Space,Str "one",Space,Str "with",Space,Str "a",Space,Str "bullet.",Space,Str "*",Space,Str "criminey."] +, Para [Str "There",Space,Str "should",Space,Str "be",Space,Str "a",Space,Str "hard",Space,Str "line",Space,Str "break",LineBreak,Space,Str "here."] +, HorizontalRule +, Header 1 [Str "Block",Space,Str "Quotes"] +, Para [Str "E-mail",Space,Str "style:"] +, BlockQuote + [ Para [Str "This",Space,Str "is",Space,Str "a",Space,Str "block",Space,Str "quote.",Space,Str "It",Space,Str "is",Space,Str "pretty",Space,Str "short."] ] + +, BlockQuote + [ Para [Str "Code",Space,Str "in",Space,Str "a",Space,Str "block",Space,Str "quote:"] + , CodeBlock "sub status {\n print \"working\";\n}\n" + , Para [Str "A",Space,Str "list:"] + , OrderedList + [ [ Plain [Str "item",Space,Str "one"] ] + , [ Plain [Str "item",Space,Str "two"] ] ] + , Para [Str "Nested",Space,Str "block",Space,Str "quotes:"] + , BlockQuote + [ Para [Str "nested"] ] + + , BlockQuote + [ Para [Str "nested"] ] + ] +, Para [Str "This",Space,Str "should",Space,Str "not",Space,Str "be",Space,Str "a",Space,Str "block",Space,Str "quote:",Space,Str "2",Space,Str ">",Space,Str "1."] +, Para [Str "Box-style:"] +, BlockQuote + [ Para [Str "Example:"] + , CodeBlock "sub status {\n print \"working\";\n}\n" ] +, BlockQuote + [ OrderedList + [ [ Plain [Str "do",Space,Str "laundry"] ] + , [ Plain [Str "take",Space,Str "out",Space,Str "the",Space,Str "trash"] ] ] ] +, Para [Str "Here's",Space,Str "a",Space,Str "nested",Space,Str "one:"] +, BlockQuote + [ Para [Str "Joe",Space,Str "said:"] + , BlockQuote + [ Para [Str "Don't",Space,Str "quote",Space,Str "me."] ] + ] +, Para [Str "And",Space,Str "a",Space,Str "following",Space,Str "paragraph."] +, HorizontalRule +, Header 1 [Str "Code",Space,Str "Blocks"] +, Para [Str "Code:"] +, CodeBlock "---- (should be four hyphens)\n\nsub status {\n print \"working\";\n}\n\nthis code block is indented by one tab\n" +, Para [Str "And:"] +, CodeBlock " this code block is indented by two tabs\n\nThese should not be escaped: \\$ \\\\ \\> \\[ \\{\n" +, HorizontalRule +, Header 1 [Str "Lists"] +, Header 2 [Str "Unordered"] +, Para [Str "Asterisks",Space,Str "tight:"] +, BulletList + [ [ Plain [Str "asterisk",Space,Str "1"] ] + , [ Plain [Str "asterisk",Space,Str "2"] ] + , [ Plain [Str "asterisk",Space,Str "3"] ] ] +, Para [Str "Asterisks",Space,Str "loose:"] +, BulletList + [ [ Para [Str "asterisk",Space,Str "1"] ] + , [ Para [Str "asterisk",Space,Str "2"] ] + , [ Para [Str "asterisk",Space,Str "3"] ] ] +, Para [Str "Pluses",Space,Str "tight:"] +, BulletList + [ [ Plain [Str "Plus",Space,Str "1"] ] + , [ Plain [Str "Plus",Space,Str "2"] ] + , [ Plain [Str "Plus",Space,Str "3"] ] ] +, Para [Str "Pluses",Space,Str "loose:"] +, BulletList + [ [ Para [Str "Plus",Space,Str "1"] ] + , [ Para [Str "Plus",Space,Str "2"] ] + , [ Para [Str "Plus",Space,Str "3"] ] ] +, Para [Str "Minuses",Space,Str "tight:"] +, BulletList + [ [ Plain [Str "Minus",Space,Str "1"] ] + , [ Plain [Str "Minus",Space,Str "2"] ] + , [ Plain [Str "Minus",Space,Str "3"] ] ] +, Para [Str "Minuses",Space,Str "loose:"] +, BulletList + [ [ Para [Str "Minus",Space,Str "1"] ] + , [ Para [Str "Minus",Space,Str "2"] ] + , [ Para [Str "Minus",Space,Str "3"] ] ] +, Header 2 [Str "Ordered"] +, Para [Str "Tight:"] +, OrderedList + [ [ Plain [Str "First"] ] + , [ Plain [Str "Second"] ] + , [ Plain [Str "Third"] ] ] +, Para [Str "and:"] +, OrderedList + [ [ Plain [Str "One"] ] + , [ Plain [Str "Two"] ] + , [ Plain [Str "Three"] ] ] +, Para [Str "Loose",Space,Str "using",Space,Str "tabs:"] +, OrderedList + [ [ Para [Str "First"] ] + , [ Para [Str "Second"] ] + , [ Para [Str "Third"] ] ] +, Para [Str "and",Space,Str "using",Space,Str "spaces:"] +, OrderedList + [ [ Para [Str "One"] ] + , [ Para [Str "Two"] ] + , [ Para [Str "Three"] ] ] +, Para [Str "Multiple",Space,Str "paragraphs:"] +, OrderedList + [ [ Para [Str "Item",Space,Str "1,",Space,Str "graf",Space,Str "one."] + , Para [Str "Item",Space,Str "1.",Space,Str "graf",Space,Str "two.",Space,Str "The",Space,Str "quick",Space,Str "brown",Space,Str "fox",Space,Str "jumped",Space,Str "over",Space,Str "the",Space,Str "lazy",Space,Str "dog's",Space,Str "back."] ], [ Para [Str "Item",Space,Str "2."] ] + , [ Para [Str "Item",Space,Str "3."] ] ] +, Header 2 [Str "Nested"] +, BulletList + [ [ Plain [Str "Tab"] + , BulletList + [ [ Plain [Str "Tab"] + , BulletList + [ [ Plain [Str "Tab"] ] + ] ] ] ] ] +, Para [Str "Here's",Space,Str "another:"] +, OrderedList + [ [ Plain [Str "First"] ] + , [ Plain [Str "Second:"] + , BulletList + [ [ Plain [Str "Fee"] ] + , [ Plain [Str "Fie"] ] + , [ Plain [Str "Foe"] ] ] ], [ Plain [Str "Third"] ] ] +, Para [Str "Same",Space,Str "thing",Space,Str "but",Space,Str "with",Space,Str "paragraphs:"] +, OrderedList + [ [ Para [Str "First"] ] + , [ Para [Str "Second:"] + , BulletList + [ [ Plain [Str "Fee"] ] + , [ Plain [Str "Fie"] ] + , [ Plain [Str "Foe"] ] ] ], [ Para [Str "Third"] ] ] +, Header 2 [Str "Tabs",Space,Str "and",Space,Str "spaces"] +, BulletList + [ [ Para [Str "this",Space,Str "is",Space,Str "a",Space,Str "list",Space,Str "item",Space,Str "indented",Space,Str "with",Space,Str "tabs"] ] + , [ Para [Str "this",Space,Str "is",Space,Str "a",Space,Str "list",Space,Str "item",Space,Str "indented",Space,Str "with",Space,Str "spaces"] + , BulletList + [ [ Para [Str "this",Space,Str "is",Space,Str "an",Space,Str "example",Space,Str "list",Space,Str "item",Space,Str "indented",Space,Str "with",Space,Str "tabs"] ] + , [ Para [Str "this",Space,Str "is",Space,Str "an",Space,Str "example",Space,Str "list",Space,Str "item",Space,Str "indented",Space,Str "with",Space,Str "spaces"] ] ] ] ] +, HorizontalRule +, Header 1 [Str "HTML",Space,Str "Blocks"] +, Para [Str "Simple",Space,Str "block",Space,Str "on",Space,Str "one",Space,Str "line:"] +, Plain [Str "foo"] +, Para [Str "And",Space,Str "nested",Space,Str "without",Space,Str "indentation:"] +, Plain [Str "foobar"] +, Para [Str "Interpreted",Space,Str "markdown",Space,Str "in",Space,Str "a",Space,Str "table:"] +, Plain [Str "This",Space,Str "is",Space,Emph [Str "emphasized"],Str ".",Space,Str "And",Space,Str "this",Space,Str "is",Space,Strong [Str "strong"]] +, Para [Str "Here's",Space,Str "a",Space,Str "simple",Space,Str "block:"] +, Plain [Str "foo"] +, Para [Str "This",Space,Str "should",Space,Str "be",Space,Str "a",Space,Str "code",Space,Str "block,",Space,Str "though:"] +, CodeBlock "<div>\n foo\n</div>\n" +, Para [Str "As",Space,Str "should",Space,Str "this:"] +, CodeBlock "<div>foo</div>\n" +, Para [Str "Now,",Space,Str "nested:"] +, Plain [Str "foo"] +, Para [Str "This",Space,Str "should",Space,Str "just",Space,Str "be",Space,Str "an",Space,Str "HTML",Space,Str "comment:"] +, Para [Str "Multiline:"] +, Para [Str "Code",Space,Str "block:"] +, CodeBlock "<!-- Comment -->\n" +, Para [Str "Just",Space,Str "plain",Space,Str "comment,",Space,Str "with",Space,Str "trailing",Space,Str "spaces",Space,Str "on",Space,Str "the",Space,Str "line:"] +, Para [Str "Code:"] +, CodeBlock "<hr />\n" +, Para [Str "Hr's:"] +, HorizontalRule +, HorizontalRule +, HorizontalRule +, HorizontalRule +, HorizontalRule +, HorizontalRule +, HorizontalRule +, HorizontalRule +, HorizontalRule +, HorizontalRule +, Header 1 [Str "Inline",Space,Str "Markup"] +, Para [Str "This",Space,Str "is",Space,Emph [Str "emphasized"],Str ",",Space,Str "and",Space,Str "so",Space,Emph [Str "is",Space,Str "this"],Str "."] +, Para [Str "This",Space,Str "is",Space,Strong [Str "strong"],Str ",",Space,Str "and",Space,Str "so",Space,Strong [Str "is",Space,Str "this"],Str "."] +, Para [Str "An",Space,Emph [Link [Str "emphasized",Space,Str "link"] (Ref [Str "1"])],Str "."] +, Para [Strong [Emph [Str "This",Space,Str "is",Space,Str "strong",Space,Str "and",Space,Str "em."]]] +, Para [Str "So",Space,Str "is",Space,Strong [Emph [Str "this"]],Space,Str "word."] +, Para [Strong [Emph [Str "This",Space,Str "is",Space,Str "strong",Space,Str "and",Space,Str "em."]]] +, Para [Str "So",Space,Str "is",Space,Strong [Emph [Str "this"]],Space,Str "word."] +, Para [Str "This",Space,Str "is",Space,Str "code:",Space,Code ">",Str ",",Space,Code "$",Str ",",Space,Code "\\",Str ",",Space,Code "\\$",Str ",",Space,Code "<html>",Str "."] +, HorizontalRule +, Header 1 [Str "Smart",Space,Str "quotes,",Space,Str "ellipses,",Space,Str "dashes"] +, Para [Str "\"Hello,\"",Space,Str "said",Space,Str "the",Space,Str "spider.",Space,Str "\"'Shelob'",Space,Str "is",Space,Str "my",Space,Str "name.\""] +, Para [Str "'A',",Space,Str "'B',",Space,Str "and",Space,Str "'C'",Space,Str "are",Space,Str "letters."] +, Para [Str "'Oak,'",Space,Str "'elm,'",Space,Str "and",Space,Str "'beech'",Space,Str "are",Space,Str "names",Space,Str "of",Space,Str "trees.",Space,Str "So",Space,Str "is",Space,Str "'pine.'"] +, Para [Str "'He",Space,Str "said,",Space,Str "\"I",Space,Str "want",Space,Str "to",Space,Str "go.\"'",Space,Str "Were",Space,Str "you",Space,Str "alive",Space,Str "in",Space,Str "the",Space,Str "70's?"] +, Para [Str "Here",Space,Str "is",Space,Str "some",Space,Str "quoted",Space,Str "'",Code "code",Str "'",Space,Str "and",Space,Str "a",Space,Str "\"",Link [Str "quoted",Space,Str "link"] (Ref [Str "2"]),Str "\"."] +, Para [Str "Some",Space,Str "dashes:",Space,Str "one---two",Space,Str "---",Space,Str "three--four",Space,Str "--",Space,Str "five."] +, Para [Str "Dashes",Space,Str "between",Space,Str "numbers:",Space,Str "5-7,",Space,Str "255-66,",Space,Str "1987-1999."] +, Para [Str "Ellipses...and.",Space,Str ".",Space,Str ".and",Space,Str ".",Space,Str ".",Space,Str ".",Space,Str "."] +, HorizontalRule +, Header 1 [Str "LaTeX"] +, BulletList + [ [ Plain [Str "\\cite[22-23]{smith.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 "$p$-Tree"] ] + , [ Plain [Str "$\\frac{d}{dx}f(x)=\\lim_{h\\to",Space,Str "0}\\frac{f(x+h)-f(x)}{h}$"] ] + , [ Plain [Str "Here's",Space,Str "one",Space,Str "that",Space,Str "has",Space,Str "a",Space,Str "line",Space,Str "break",Space,Str "in",Space,Str "it:",Space,Str "$\\alpha",Space,Str "+",Space,Str "\\omega",Space,Str "\\times",Space,Str "x^2$."] ] ] +, Para [Str "These",Space,Str "shouldn't",Space,Str "be",Space,Str "math:"] +, BulletList + [ [ Plain [Str "To",Space,Str "get",Space,Str "the",Space,Str "famous",Space,Str "equation,",Space,Str "write",Space,Code "$e = mc^2$",Str "."] ] + , [ Plain [Str "$22,000",Space,Str "is",Space,Str "a",Space,Emph [Str "lot"],Space,Str "of",Space,Str "money.",Space,Str "So",Space,Str "is",Space,Str "$34,000.",Space,Str "(It",Space,Str "worked",Space,Str "if",Space,Str "\"lot\"",Space,Str "is",Space,Str "emphasized.)"] ] + , [ Plain [Str "Escaped",Space,Code "$",Str ":",Space,Str "$73",Space,Emph [Str "this",Space,Str "should",Space,Str "be",Space,Str "emphasized"],Space,Str "23$."] ] ] +, Para [Str "Here's",Space,Str "a",Space,Str "LaTeX",Space,Str "table:"] +, Para [Str "\\begin{tabular}{|l|l|}\\hline",Space,Str "Animal",Space,Str "&",Space,Str "Number",Space,Str "\\\\",Space,Str "\\hline",Space,Str "Dog",Space,Str "&",Space,Str "2",Space,Str "\\\\",Space,Str "Cat",Space,Str "&",Space,Str "1",Space,Str "\\\\",Space,Str "\\hline",Space,Str "\\end{tabular}"] +, HorizontalRule +, Header 1 [Str "Special",Space,Str "Characters"] +, Para [Str "Here",Space,Str "is",Space,Str "some",Space,Str "unicode:"] +, BulletList + [ [ Plain [Str "I",Space,Str "hat:",Space,Str "\206"] ] + , [ Plain [Str "o",Space,Str "umlaut:",Space,Str "\246"] ] + , [ Plain [Str "section:",Space,Str "\167"] ] + , [ Plain [Str "set",Space,Str "membership:",Space,Str "\8712"] ] + , [ Plain [Str "copyright:",Space,Str "\169"] ] ] +, Para [Str "AT",Str "&",Str "T",Space,Str "has",Space,Str "an",Space,Str "ampersand",Space,Str "in",Space,Str "their",Space,Str "name."] +, Para [Str "AT",Str "&",Str "T",Space,Str "is",Space,Str "another",Space,Str "way",Space,Str "to",Space,Str "write",Space,Str "it."] +, Para [Str "This",Space,Str "&",Space,Str "that."] +, Para [Str "4",Space,Str "<",Space,Str "5."] +, Para [Str "6",Space,Str ">",Space,Str "5."] +, Para [Str "Backslash:",Space,Str "\\"] +, Para [Str "Backtick:",Space,Str "`"] +, Para [Str "Asterisk:",Space,Str "*"] +, Para [Str "Underscore:",Space,Str "_"] +, Para [Str "Left",Space,Str "brace:",Space,Str "{"] +, Para [Str "Right",Space,Str "brace:",Space,Str "}"] +, Para [Str "Left",Space,Str "bracket:",Space,Str "["] +, Para [Str "Right",Space,Str "bracket:",Space,Str "]"] +, Para [Str "Left",Space,Str "paren:",Space,Str "("] +, Para [Str "Right",Space,Str "paren:",Space,Str ")"] +, Para [Str "Greater-than:",Space,Str ">"] +, Para [Str "Hash:",Space,Str "#"] +, Para [Str "Period:",Space,Str "."] +, Para [Str "Bang:",Space,Str "!"] +, Para [Str "Plus:",Space,Str "+"] +, Para [Str "Minus:",Space,Str "-"] +, HorizontalRule +, Header 1 [Str "Links"] +, Header 2 [Str "Explicit"] +, Para [Str "Just",Space,Str "a",Space,Link [Str "URL"] (Ref [Str "3"]),Str "."] +, Para [Link [Str "URL",Space,Str "and",Space,Str "title"] (Ref [Str "4"]),Str "."] +, Para [Link [Str "URL",Space,Str "and",Space,Str "title"] (Ref [Str "5"]),Str "."] +, Para [Link [Str "URL",Space,Str "and",Space,Str "title"] (Ref [Str "6"]),Str "."] +, Para [Link [Str "URL",Space,Str "and",Space,Str "title"] (Ref [Str "7"])] +, Para [Link [Str "URL",Space,Str "and",Space,Str "title"] (Ref [Str "8"])] +, Plain [Str "Email",Space,Str "link",Space,Str "(nobody",Space,Str "[at]",Space,Str "nowhere.net)"] +, Para [Link [Str "Empty"] (Ref [Str "9"]),Str "."] +, Header 2 [Str "Reference"] +, Para [Str "Foo",Space,Link [Str "bar"] (Ref [Str "3"]),Str "."] +, Para [Str "Foo",Space,Link [Str "bar"] (Ref [Str "3"]),Str "."] +, Para [Str "Foo",Space,Link [Str "bar"] (Ref [Str "3"]),Str "."] +, Para [Str "With",Space,Link [Str "embedded",Space,Str "[brackets]"] (Ref [Str "3"]),Str "."] +, Para [Link [Str "b"] (Ref [Str "3"]),Space,Str "by",Space,Str "itself",Space,Str "should",Space,Str "be",Space,Str "a",Space,Str "link."] +, Para [Str "Indented",Space,Link [Str "once"] (Ref [Str "1"]),Str "."] +, Para [Str "Indented",Space,Link [Str "twice"] (Ref [Str "1"]),Str "."] +, Para [Str "Indented",Space,Link [Str "thrice"] (Ref [Str "1"]),Str "."] +, Para [Str "This",Space,Str "should",Space,Str "[not]",Space,Str "be",Space,Str "a",Space,Str "link."] +, CodeBlock "[not]: /url\n" +, Para [Str "Foo",Space,Link [Str "bar"] (Ref [Str "10"]),Str "."] +, Para [Str "Foo",Space,Link [Str "biz"] (Ref [Str "11"]),Str "."] +, Header 2 [Str "With",Space,Str "ampersands"] +, Para [Str "Here's",Space,Str "a",Space,Link [Str "link",Space,Str "with",Space,Str "an",Space,Str "ampersand",Space,Str "in",Space,Str "the",Space,Str "URL"] (Ref [Str "2"]),Str "."] +, Para [Str "Here's",Space,Str "a",Space,Str "link",Space,Str "with",Space,Str "an",Space,Str "amersand",Space,Str "in",Space,Str "the",Space,Str "link",Space,Str "text:",Space,Link [Str "AT",Str "&",Str "T"] (Ref [Str "12"]),Str "."] +, Para [Str "Here's",Space,Str "an",Space,Link [Str "inline",Space,Str "link"] (Ref [Str "13"]),Str "."] +, Para [Str "Here's",Space,Str "an",Space,Link [Str "inline",Space,Str "link",Space,Str "in",Space,Str "pointy",Space,Str "braces"] (Ref [Str "13"]),Str "."] +, Header 2 [Str "Autolinks"] +, Para [Str "With",Space,Str "an",Space,Str "ampersand:",Space,Link [Str "http://example.com/?foo=1",Str "&",Str "bar=2"] (Ref [Str "2"])] +, BulletList + [ [ Plain [Str "In",Space,Str "a",Space,Str "list?"] ] + , [ Plain [Link [Str "http://example.com/"] (Ref [Str "14"])] ] + , [ Plain [Str "It",Space,Str "should."] ] ] +, Plain [Str "An",Space,Str "e-mail",Space,Str "address:",Space,Str "nobody",Space,Str "[at]",Space,Str "nowhere.net"] +, BlockQuote + [ Para [Str "Blockquoted:",Space,Link [Str "http://example.com/"] (Ref [Str "14"])] ] + +, Para [Str "Auto-links",Space,Str "should",Space,Str "not",Space,Str "occur",Space,Str "here:",Space,Code "<http://example.com/>"] +, CodeBlock "or here: <http://example.com/>\n" +, HorizontalRule +, Header 1 [Str "Images"] +, Para [Str "From",Space,Str "\"Voyage",Space,Str "dans",Space,Str "la",Space,Str "Lune\"",Space,Str "by",Space,Str "Georges",Space,Str "Melies",Space,Str "(1902):"] +, Para [Image [Str "lalune"] (Ref [Str "15"])] +, Para [Str "Here",Space,Str "is",Space,Str "a",Space,Str "movie",Space,Image [Str "movie"] (Ref [Str "16"]),Space,Str "icon."] +, HorizontalRule +, Header 1 [Str "Footnotes"] +, Para [Str "Here",Space,Str "is",Space,Str "a",Space,Str "footnote",Space,Str "reference",Link [Str "(1)"] (Ref [Str "17"]),Str ",",Space,Str "and",Space,Str "another",Link [Str "(longnote)"] (Ref [Str "18"]),Str ".",Space,Str "This",Space,Str "should",Space,Emph [Str "not"],Space,Str "be",Space,Str "a",Space,Str "footnote",Space,Str "reference,",Space,Str "because",Space,Str "it",Space,Str "contains",Space,Str "a",Space,Str "space^(my",Space,Str "note)."] +, Para [Link [Str "(1)"] (Ref [Str "19"]),Space,Str "Here",Space,Str "is",Space,Str "the",Space,Str "footnote.",Space,Str "It",Space,Str "can",Space,Str "go",Space,Str "anywhere",Space,Str "in",Space,Str "the",Space,Str "document,",Space,Str "not",Space,Str "just",Space,Str "at",Space,Str "the",Space,Str "end."] +, Para [Link [Str "(longnote)"] (Ref [Str "20"]),Space,Str "Here's",Space,Str "the",Space,Str "other",Space,Str "note.",Space,Str "This",Space,Str "one",Space,Str "contains",Space,Str "multiple",Space,Str "blocks."] +, Para [Str "Caret",Space,Str "characters",Space,Str "are",Space,Str "used",Space,Str "to",Space,Str "indicate",Space,Str "that",Space,Str "the",Space,Str "blocks",Space,Str "all",Space,Str "belong",Space,Str "to",Space,Str "a",Space,Str "single",Space,Str "footnote",Space,Str "(as",Space,Str "with",Space,Str "block",Space,Str "quotes)."] +, CodeBlock " { <code> }\n" +, Para [Str "If",Space,Str "you",Space,Str "want,",Space,Str "you",Space,Str "can",Space,Str "use",Space,Str "a",Space,Str "caret",Space,Str "at",Space,Str "the",Space,Str "beginning",Space,Str "of",Space,Str "every",Space,Str "line,",Space,Str "as",Space,Str "with",Space,Str "blockquotes,",Space,Str "but",Space,Str "all",Space,Str "that",Space,Str "you",Space,Str "need",Space,Str "is",Space,Str "a",Space,Str "caret",Space,Str "at",Space,Str "the",Space,Str "beginning",Space,Str "of",Space,Str "the",Space,Str "first",Space,Str "line",Space,Str "of",Space,Str "the",Space,Str "block",Space,Str "and",Space,Str "any",Space,Str "preceding",Space,Str "blank",Space,Str "lines."] +, Key [Str "1"] (Src "/url" "") +, Key [Str "2"] (Src "http://example.com/?foo=1&bar=2" "") +, Key [Str "3"] (Src "/url/" "") +, Key [Str "4"] (Src "/url/" "title") +, Key [Str "5"] (Src "/url/" "title preceded by two spaces") +, Key [Str "6"] (Src "/url/" "title preceded by a tab") +, Key [Str "7"] (Src "/url/" "title with \"quotes\" in it") +, Key [Str "8"] (Src "/url/" "title with single quotes") +, Key [Str "9"] (Src "" "") +, Key [Str "10"] (Src "/url/" "Title with \"quotes\" inside") +, Key [Str "11"] (Src "/url/" "Title with \"quote\" inside") +, Key [Str "12"] (Src "http://att.com/" "AT&T") +, Key [Str "13"] (Src "/script?foo=1&bar=2" "") +, Key [Str "14"] (Src "http://example.com/" "") +, Key [Str "15"] (Src "lalune.jpg" "Voyage dans la Lune") +, Key [Str "16"] (Src "movie.jpg" "") +, Key [Str "17"] (Src "#note_1" "") +, Key [Str "18"] (Src "#note_longnote" "") +, Key [Str "19"] (Src "#ref_1" "") +, Key [Str "20"] (Src "#ref_longnote" "") ] diff --git a/tests/insert b/tests/insert new file mode 100644 index 000000000..f06069ede --- /dev/null +++ b/tests/insert @@ -0,0 +1 @@ +STUFF INSERTED diff --git a/tests/lalune.jpg b/tests/lalune.jpg Binary files differnew file mode 100644 index 000000000..5a50fc088 --- /dev/null +++ b/tests/lalune.jpg diff --git a/tests/movie.jpg b/tests/movie.jpg Binary files differnew file mode 100644 index 000000000..7240efa3b --- /dev/null +++ b/tests/movie.jpg diff --git a/tests/rst-reader.native b/tests/rst-reader.native new file mode 100644 index 000000000..fb63e5e60 --- /dev/null +++ b/tests/rst-reader.native @@ -0,0 +1,175 @@ +Pandoc (Meta [Str "Pandoc",Space,Str "Test",Space,Str "Suite",Str ":",Space,Str "Subtitle"] ["John MacFarlane","Anonymous"] "July 17, 2006") +[ BlockQuote + [ Para [Strong [Str "Revision"],Str ":",Space,Str "3"] ] + +, Header 1 [Str "Level",Space,Str "one",Space,Str "header"] +, Para [Str "This",Space,Str "is",Space,Str "a",Space,Str "set",Space,Str "of",Space,Str "tests",Space,Str "for",Space,Str "pandoc.",Space,Str "Most",Space,Str "of",Space,Str "them",Space,Str "are",Space,Str "adapted",Space,Str "from",Space,Str "John",Space,Str "Gruber's",Space,Str "markdown",Space,Str "test",Space,Str "suite."] +, Header 2 [Str "Level",Space,Str "two",Space,Str "header"] +, Header 3 [Str "Level",Space,Str "three"] +, Header 4 [Str "Level",Space,Str "four",Space,Str "with",Space,Emph [Str "emphasis"]] +, Header 5 [Str "Level",Space,Str "five"] +, Header 1 [Str "Paragraphs"] +, Para [Str "Here's",Space,Str "a",Space,Str "regular",Space,Str "paragraph."] +, Para [Str "In",Space,Str "Markdown",Space,Str "1.0.0",Space,Str "and",Space,Str "earlier.",Space,Str "Version",Space,Str "8.",Space,Str "This",Space,Str "line",Space,Str "turns",Space,Str "into",Space,Str "a",Space,Str "list",Space,Str "item.",Space,Str "Because",Space,Str "a",Space,Str "hard",Str "-",Str "wrapped",Space,Str "line",Space,Str "in",Space,Str "the",Space,Str "middle",Space,Str "of",Space,Str "a",Space,Str "paragraph",Space,Str "looked",Space,Str "like",Space,Str "a",Space,Str "list",Space,Str "item."] +, Para [Str "Here's",Space,Str "one",Space,Str "with",Space,Str "a",Space,Str "bullet.",Space,Str "*",Space,Str "criminey."] +, Para [Str "Horizontal",Space,Str "rule",Str ":"] +, HorizontalRule +, Para [Str "Another",Str ":"] +, HorizontalRule +, Header 1 [Str "Block",Space,Str "Quotes"] +, Para [Str "Here's",Space,Str "a",Space,Str "block",Space,Str "quote",Str ":"] +, BlockQuote + [ Para [Str "This",Space,Str "is",Space,Str "a",Space,Str "block",Space,Str "quote.",Space,Str "It",Space,Str "is",Space,Str "pretty",Space,Str "short."] ] + +, Para [Str "Here's",Space,Str "another,",Space,Str "differently",Space,Str "indented",Str ":"] +, BlockQuote + [ Para [Str "This",Space,Str "is",Space,Str "a",Space,Str "block",Space,Str "quote.",Space,Str "It's",Space,Str "indented",Space,Str "with",Space,Str "a",Space,Str "tab."] + , Para [Str "Code",Space,Str "in",Space,Str "a",Space,Str "block",Space,Str "quote",Str ":"] + , CodeBlock "sub status {\n print \"working\";\n}\n" + , Para [Str "List",Space,Str "in",Space,Str "a",Space,Str "block",Space,Str "quote",Str ":"] + , OrderedList + [ [ Plain [Str "item",Space,Str "one"] ] + , [ Plain [Str "item",Space,Str "two"] ] ] + , Para [Str "Nested",Space,Str "block",Space,Str "quotes",Str ":"] + , BlockQuote + [ Para [Str "nested"] + , BlockQuote + [ Para [Str "nested"] ] + ] ] +, Header 1 [Str "Code",Space,Str "Blocks"] +, Para [Str "Code",Str ":"] +, CodeBlock "---- (should be four hyphens)\n\nsub status {\n print \"working\";\n}\n" +, CodeBlock "this code block is indented by one tab\n" +, Para [Str "And",Str ":"] +, CodeBlock " this block is indented by two tabs\n\n These should not be escaped: \\$ \\\\ \\> \\[ \\{\n" +, Header 1 [Str "Lists"] +, Header 2 [Str "Unordered"] +, Para [Str "Asterisks",Space,Str "tight",Str ":"] +, BulletList + [ [ Plain [Str "asterisk",Space,Str "1"] ] + , [ Plain [Str "asterisk",Space,Str "2"] ] + , [ Plain [Str "asterisk",Space,Str "3"] ] ] +, Para [Str "Asterisks",Space,Str "loose",Str ":"] +, BulletList + [ [ Para [Str "asterisk",Space,Str "1"] ] + , [ Para [Str "asterisk",Space,Str "2"] ] + , [ Para [Str "asterisk",Space,Str "3"] ] ] +, Para [Str "Pluses",Space,Str "tight",Str ":"] +, BulletList + [ [ Plain [Str "Plus",Space,Str "1"] ] + , [ Plain [Str "Plus",Space,Str "2"] ] + , [ Plain [Str "Plus",Space,Str "3"] ] ] +, Para [Str "Pluses",Space,Str "loose",Str ":"] +, BulletList + [ [ Para [Str "Plus",Space,Str "1"] ] + , [ Para [Str "Plus",Space,Str "2"] ] + , [ Para [Str "Plus",Space,Str "3"] ] ] +, Para [Str "Minuses",Space,Str "tight",Str ":"] +, BulletList + [ [ Plain [Str "Minus",Space,Str "1"] ] + , [ Plain [Str "Minus",Space,Str "2"] ] + , [ Plain [Str "Minus",Space,Str "3"] ] ] +, Para [Str "Minuses",Space,Str "loose",Str ":"] +, BulletList + [ [ Para [Str "Minus",Space,Str "1"] ] + , [ Para [Str "Minus",Space,Str "2"] ] + , [ Para [Str "Minus",Space,Str "3"] ] ] +, Header 2 [Str "Ordered"] +, Para [Str "Tight",Str ":"] +, OrderedList + [ [ Plain [Str "First"] ] + , [ Plain [Str "Second"] ] + , [ Plain [Str "Third"] ] ] +, Para [Str "and",Str ":"] +, OrderedList + [ [ Plain [Str "One"] ] + , [ Plain [Str "Two"] ] + , [ Plain [Str "Three"] ] ] +, Para [Str "Loose",Space,Str "using",Space,Str "tabs",Str ":"] +, OrderedList + [ [ Para [Str "First"] ] + , [ Para [Str "Second"] ] + , [ Para [Str "Third"] ] ] +, Para [Str "and",Space,Str "using",Space,Str "spaces",Str ":"] +, OrderedList + [ [ Para [Str "One"] ] + , [ Para [Str "Two"] ] + , [ Para [Str "Three"] ] ] +, Para [Str "Multiple",Space,Str "paragraphs",Str ":"] +, OrderedList + [ [ Para [Str "Item",Space,Str "1,",Space,Str "graf",Space,Str "one."] + , Para [Str "Item",Space,Str "1.",Space,Str "graf",Space,Str "two.",Space,Str "The",Space,Str "quick",Space,Str "brown",Space,Str "fox",Space,Str "jumped",Space,Str "over",Space,Str "the",Space,Str "lazy",Space,Str "dog's",Space,Str "back."] ], [ Para [Str "Item",Space,Str "2."] ] + , [ Para [Str "Item",Space,Str "3."] ] ] +, Para [Str "Nested",Str ":"] +, BulletList + [ [ Para [Str "Tab"] + , BulletList + [ [ Para [Str "Tab"] + , BulletList + [ [ Plain [Str "Tab"] ] + ] ] ] ] ] +, Para [Str "Here's",Space,Str "another",Str ":"] +, OrderedList + [ [ Para [Str "First"] ] + , [ Para [Str "Second",Str ":"] + , BlockQuote + [ BulletList + [ [ Plain [Str "Fee"] ] + , [ Plain [Str "Fie"] ] + , [ Plain [Str "Foe"] ] ] ] ], [ Para [Str "Third"] ] ] +, Header 1 [Str "HTML",Space,Str "Blocks"] +, Para [Str "Simple",Space,Str "block",Space,Str "on",Space,Str "one",Space,Str "line",Str ":"] +, RawHtml "<div>foo</div>\n" +, Para [Str "Now,",Space,Str "nested",Str ":"] +, RawHtml "<div>\n <div>\n <div>\n foo\n </div>\n </div>\n</div>\n" +, Header 1 [Str "LaTeX",Space,Str "Block"] +, Para [TeX "\\begin{tabular}{|l|l|}\\hline\nAnimal & Number \\\\ \\hline\nDog & 2 \\\\\nCat & 1 \\\\ \\hline\n\\end{tabular}\n"] +, Header 1 [Str "Inline",Space,Str "Markup"] +, Para [Str "This",Space,Str "is",Space,Emph [Str "emphasized"],Str ".",Space,Str "This",Space,Str "is",Space,Strong [Str "strong"],Str "."] +, Para [Str "This",Space,Str "is",Space,Str "code",Str ":",Space,Code ">",Str ",",Space,Code "$",Str ",",Space,Code "\\",Str ",",Space,Code "\\$",Str ",",Space,Code "<html>",Str "."] +, Header 1 [Str "Special",Space,Str "Characters"] +, Para [Str "Here",Space,Str "is",Space,Str "some",Space,Str "unicode",Str ":"] +, BulletList + [ [ Plain [Str "I",Space,Str "hat",Str ":",Space,Str "\206"] ] + , [ Plain [Str "o",Space,Str "umlaut",Str ":",Space,Str "\246"] ] + , [ Plain [Str "section",Str ":",Space,Str "\167"] ] + , [ Plain [Str "set",Space,Str "membership",Str ":",Space,Str "\8712"] ] + , [ Plain [Str "copyright",Str ":",Space,Str "\169"] ] ] +, Para [Str "AT&T",Space,Str "has",Space,Str "an",Space,Str "ampersand",Space,Str "in",Space,Str "their",Space,Str "name."] +, Para [Str "This",Space,Str "&",Space,Str "that."] +, Para [Str "4",Space,Str "<",Space,Str "5."] +, Para [Str "6",Space,Str ">",Space,Str "5."] +, Para [Str "Backslash",Str ":",Space,Str "\\"] +, Para [Str "Backtick",Str ":",Space,Str "`"] +, Para [Str "Asterisk",Str ":",Space,Str "*"] +, Para [Str "Underscore",Str ":",Space,Str "_"] +, Para [Str "Left",Space,Str "brace",Str ":",Space,Str "{"] +, Para [Str "Right",Space,Str "brace",Str ":",Space,Str "}"] +, Para [Str "Left",Space,Str "bracket",Str ":",Space,Str "["] +, Para [Str "Right",Space,Str "bracket",Str ":",Space,Str "]"] +, Para [Str "Left",Space,Str "paren",Str ":",Space,Str "("] +, Para [Str "Right",Space,Str "paren",Str ":",Space,Str ")"] +, Para [Str "Greater",Str "-",Str "than",Str ":",Space,Str ">"] +, Para [Str "Hash",Str ":",Space,Str "#"] +, Para [Str "Period",Str ":",Space,Str "."] +, Para [Str "Bang",Str ":",Space,Str "!"] +, Para [Str "Plus",Str ":",Space,Str "+"] +, Para [Str "Minus",Str ":",Space,Str "-"] +, Header 1 [Str "Links"] +, Para [Str "Explicit",Str ":",Space,Str "a",Space,Link [Str "URL"] (Src "/url/" ""),Str "."] +, Para [Str "Two",Space,Str "anonymous",Space,Str "links",Str ":",Space,Link [Str "the",Space,Str "first"] (Src "/url1/" ""),Space,Str "and",Space,Link [Str "the",Space,Str "second"] (Src "/url2/" "")] +, Para [Str "Reference",Space,Str "links",Str ":",Space,Link [Str "link1"] (Ref []),Space,Str "and",Space,Link [Str "link2"] (Ref []),Space,Str "and",Space,Link [Str "link1"] (Ref []),Space,Str "again."] +, Key [Str "link1"] (Src "/url1/" "") +, Key [Str "link2"] (Src "/url2/" "") +, Para [Str "Here's",Space,Str "a",Space,Link [Str "link",Space,Str "with",Space,Str "an",Space,Str "ampersand",Space,Str "in",Space,Str "the",Space,Str "URL"] (Ref []),Str "."] +, Para [Str "Here's",Space,Str "a",Space,Str "link",Space,Str "with",Space,Str "an",Space,Str "amersand",Space,Str "in",Space,Str "the",Space,Str "link",Space,Str "text",Str ":",Space,Link [Str "AT&T"] (Src "/url/" ""),Str "."] +, Key [Str "link",Space,Str "with",Space,Str "an",Space,Str "ampersand",Space,Str "in",Space,Str "the",Space,Str "URL"] (Src "http://example.com/?foo=1&bar=2" "") +, Para [Str "Autolinks",Str ":",Space,Link [Str "http://example.com/?foo=1&bar=2"] (Src "http://example.com/?foo=1&bar=2" ""),Space,Str "and",Space,Link [Str "nobody@nowhere.net"] (Src "mailto:nobody@nowhere.net" ""),Str "."] +, Para [Str "But",Space,Str "not",Space,Str "here",Str ":"] +, CodeBlock "http://example.com/\n" +, Header 1 [Str "Images"] +, Para [Str "From",Space,Str "\"Voyage",Space,Str "dans",Space,Str "la",Space,Str "Lune\"",Space,Str "by",Space,Str "Georges",Space,Str "Melies",Space,Str "(1902)",Str ":"] +, Plain [Image [Str "image"] (Src "lalune.jpg" "")] +, Para [Str "Here",Space,Str "is",Space,Str "a",Space,Str "movie",Space,Image [Str "movie"] (Ref [Str "movie"]),Space,Str "icon."] +, Key [Str "movie"] (Src "movie.jpg" "") +, Blank ] diff --git a/tests/rst-reader.rst b/tests/rst-reader.rst new file mode 100644 index 000000000..75716f7b4 --- /dev/null +++ b/tests/rst-reader.rst @@ -0,0 +1,341 @@ +Pandoc Test Suite +################# +Subtitle +^^^^^^^^ + +:Author: John MacFarlane +:Author: Anonymous +:Date: July 17, 2006 +:Revision: 3 + +Level one header +================ + +This is a set of tests for pandoc. Most of them are adapted from +John Gruber's markdown test suite. + +Level two header +---------------- + +Level three ++++++++++++ + +Level four with *emphasis* +~~~~~~~~~~~~~~~~~~~~~~~~~~ + +Level five +'''''''''' + +Paragraphs +========== + +Here's a regular paragraph. + +In Markdown 1.0.0 and earlier. Version +8. This line turns into a list item. +Because a hard-wrapped line in the +middle of a paragraph looked like a +list item. + +Here's one with a bullet. +* criminey. + +Horizontal rule: + +----- + +Another: + +**** + +Block Quotes +============ + +Here's a block quote: + + This is a block quote. + It is pretty short. + +Here's another, differently indented: + + This is a block quote. + It's indented with a tab. + + Code in a block quote:: + + sub status { + print "working"; + } + + List in a block quote: + + 1. item one + 2. item two + + Nested block quotes: + + nested + + nested + +Code Blocks +=========== + +Code: + +:: + + ---- (should be four hyphens) + + sub status { + print "working"; + } + +:: + + this code block is indented by one tab + +And:: + + this block is indented by two tabs + + These should not be escaped: \$ \\ \> \[ \{ + +Lists +===== + +Unordered +--------- + +Asterisks tight: + +* asterisk 1 +* asterisk 2 +* asterisk 3 + +Asterisks loose: + +* asterisk 1 + +* asterisk 2 + +* asterisk 3 + +Pluses tight: + ++ Plus 1 ++ Plus 2 ++ Plus 3 + +Pluses loose: + ++ Plus 1 + ++ Plus 2 + ++ Plus 3 + +Minuses tight: + +- Minus 1 +- Minus 2 +- Minus 3 + +Minuses loose: + +- Minus 1 + +- Minus 2 + +- Minus 3 + +Ordered +------- + +Tight: + +1. First +2. Second +3. Third + +and: + +1. One +2. Two +3. Three + +Loose using tabs: + +1. First + +2. Second + +3. Third + +and using spaces: + +1. One + +2. Two + +3. Three + +Multiple paragraphs: + +1. Item 1, graf one. + + Item 1. graf two. The quick brown fox jumped over the lazy dog's + back. + +2. Item 2. + +3. Item 3. + +Nested: + +* Tab + + * Tab + + * Tab + +Here's another: + +1. First + +2. Second: + + * Fee + * Fie + * Foe + +3. Third + +HTML Blocks +=========== + +Simple block on one line: + +.. raw:: html + + <div>foo</div> + +Now, nested: + +.. raw:: html + + <div> + <div> + <div> + foo + </div> + </div> + </div> + +LaTeX Block +=========== + +.. raw:: latex + + \begin{tabular}{|l|l|}\hline + Animal & Number \\ \hline + Dog & 2 \\ + Cat & 1 \\ \hline + \end{tabular} + +Inline Markup +============= + +This is *emphasized*. This is **strong**. + +This is code: ``>``, ``$``, ``\``, ``\$``, ``<html>``. + +Special Characters +================== + +Here is some unicode: + +- I hat: Î +- o umlaut: ö +- section: § +- set membership: ∈ +- copyright: © + +AT&T has an ampersand in their name. + +This & that. + +4 < 5. + +6 > 5. + +Backslash: \\ + +Backtick: \` + +Asterisk: \* + +Underscore: \_ + +Left brace: \{ + +Right brace: \} + +Left bracket: \[ + +Right bracket: \] + +Left paren: \( + +Right paren: \) + +Greater-than: \> + +Hash: \# + +Period: \. + +Bang: \! + +Plus: \+ + +Minus: \- + +Links +===== + +Explicit: a `URL </url/>`_. + +Two anonymous links: `the first`__ and `the second`__ + +__ /url1/ +__ /url2/ + +Reference links: `link1`_ and `link2`_ and link1_ again. + +.. _link1: /url1/ +.. _`link2`: /url2/ + +Here's a `link with an ampersand in the URL`_. + +Here's a link with an amersand in the link text: `AT&T </url/>`_. + +.. _link with an ampersand in the URL: http://example.com/?foo=1&bar=2 + +Autolinks: http://example.com/?foo=1&bar=2 and nobody@nowhere.net. + +But not here:: + + http://example.com/ + +Images +====== + +From "Voyage dans la Lune" by Georges Melies (1902): + +.. image:: lalune.jpg + +Here is a movie |movie| icon. + +.. |movie| image:: movie.jpg + diff --git a/tests/runtests.pl b/tests/runtests.pl new file mode 100644 index 000000000..662862e44 --- /dev/null +++ b/tests/runtests.pl @@ -0,0 +1,97 @@ +#!/bin/perl -w + +$verbose = 1; +my $diffexists = `which diff`; +if ($diffexists eq "") { die "diff not found in path.\n"; } + +my $script = "./pandoc"; + +use Getopt::Long; +GetOptions("script=s" => \$script); + +unless (-f $script) { die "$script does not exist.\n"; } +unless (-x $script) { die "$script is not executable.\n"; } + +print "Writer tests:\n"; + +my @writeformats = ("html", "smart.html", "latex", "rst", "rtf", "markdown", "native"); # s5 separately +my @readformats = ("latex", "native"); # handle html,markdown & rst separately +my $source = "testsuite.native"; + +sub test_results +{ + my $testname = $_[0]; + my $output = $_[1]; + my $norm = $_[2]; + my $diffoutput = `diff $output $norm`; + if ($diffoutput eq "") + { + print "PASSED\n"; + } + else + { + print "FAILED\n"; + if ($verbose) { print $diffoutput; } + } +} + +foreach my $format (@writeformats) +{ + $options = ""; + if ($format =~ /smart\./) + { + $options = "-S "; + } + + my $extension = $format; + $extension =~ s/smart\.//g; + + print "Testing $format writer..."; + `$script -r native -w $extension $options -s $source > tmp.$extension`; + + test_results("$format writer", "tmp.$extension", "writer.$format"); +} + +print "Testing s5 writer (basic)..."; +`$script -r native -w s5 -s s5.native > tmp.html`; +test_results("s5 writer (basic)", "tmp.html", "s5.basic.html"); + +print "Testing s5 writer (fancy)..."; +`$script -r native -w s5 -s -S -m -i s5.native > tmp.html`; +test_results("s5 writer (fancy)", "tmp.html", "s5.fancy.html"); + +print "Testing html fragment..."; +`$script -r native -w html s5.native > tmp.html`; +test_results("html fragment", "tmp.html", "s5.fragment.html"); + +print "Testing -H -B -A -c options..."; +`$script -r native -s -w html -H insert -B insert -A insert -c main.css s5.native > tmp.html`; +test_results("-B, -A, -H, -c options", "tmp.html", "s5.inserts.html"); + +print "\nReader tests:\n"; + +print "Testing markdown reader..."; +`$script -r markdown -w native -s testsuite.txt > tmp.native`; +test_results("markdown reader", "tmp.native", "testsuite.native"); + +print "Testing rst reader..."; +`$script -r rst -w native -s rst-reader.rst > tmp.native`; +test_results("rst reader", "tmp.native", "rst-reader.native"); + +print "Testing html reader..."; +`$script -r html -w native -s html-reader.html > tmp.native`; +test_results("html reader", "tmp.native", "html-reader.native"); + +print "\nReader tests (roundtrip: X -> native -> X -> native):\n"; + +foreach my $format (@readformats) +{ + print "testing $format reader..."; + `$script -r $format -w native -s -R writer.$format > tmp1.native`; + `$script -r native -w $format -s -R tmp1.native | $script -r $format -w native -s -R - > tmp2.native`; + test_results("$format reader", "tmp1.native", "tmp2.native"); +} + +`rm tmp?.*`; +`rm tmp.*`; + diff --git a/tests/s5.basic.html b/tests/s5.basic.html new file mode 100644 index 000000000..ddb4d8079 --- /dev/null +++ b/tests/s5.basic.html @@ -0,0 +1,761 @@ +<!DOCTYPE html PUBLIC "-//W3C//DTD XHTML 1.0 Strict//EN" "http://www.w3.org/TR/xhtml1/DTD/xhtml1-strict.dtd"> +<html xmlns="http://www.w3.org/1999/xhtml"> +<head> +<!-- configuration parameters --> +<meta name="defaultView" content="slideshow" /> +<meta name="controlVis" content="hidden" /> +<meta http-equiv="Content-Type" content="text/html; charset=UTF-8" /> +<meta name="generator" content="pandoc" /> +<style type="text/css" media="projection" id="slideProj"> +/* Do not edit or override these styles! The system will likely break if you do. */ + +div#header, div#footer, div#controls, .slide {position: absolute;} +html>body div#header, html>body div#footer, + html>body div#controls, html>body .slide {position: fixed;} +.handout {display: none;} +.layout {display: block;} +.slide, .hideme, .incremental {visibility: hidden;} +#slide0 {visibility: visible;} + +/* The following styles size, place, and layer the slide components. + Edit these if you want to change the overall slide layout. + The commented lines can be uncommented (and modified, if necessary) + to help you with the rearrangement process. */ + +/* target = 1024x768 */ + +div#header, div#footer, .slide {width: 100%; top: 0; left: 0;} +div#header {top: 0; height: 3em; z-index: 1;} +div#footer {top: auto; bottom: 0; height: 2.5em; z-index: 5;} +.slide {top: 0; width: 92%; padding: 3.5em 4% 4%; z-index: 2; list-style: none;} +div#controls {left: 50%; bottom: 0; width: 50%; z-index: 100;} +div#controls form {position: absolute; bottom: 0; right: 0; width: 100%; + margin: 0;} +#currentSlide {position: absolute; width: 10%; left: 45%; bottom: 1em; z-index: 10;} +html>body #currentSlide {position: fixed;} + +/* +div#header {background: #FCC;} +div#footer {background: #CCF;} +div#controls {background: #BBD;} +div#currentSlide {background: #FFC;} +*/ + +/* Following are the presentation styles -- edit away! */ + +body {background: #FFF url(bodybg.gif) -16px 0 no-repeat; color: #000; font-size: 2em;} +:link, :visited {text-decoration: none; color: #00C;} +#controls :active {color: #88A !important;} +#controls :focus {outline: 1px dotted #227;} +h1, h2, h3, h4 {font-size: 100%; margin: 0; padding: 0; font-weight: inherit;} +ul, pre {margin: 0; line-height: 1em;} +html, body {margin: 0; padding: 0;} + +blockquote, q {font-style: italic;} +blockquote {padding: 0 2em 0.5em; margin: 0 1.5em 0.5em; text-align: center; font-size: 1em;} +blockquote p {margin: 0;} +blockquote i {font-style: normal;} +blockquote b {display: block; margin-top: 0.5em; font-weight: normal; font-size: smaller; font-style: normal;} +blockquote b i {font-style: italic;} + +kbd {font-weight: bold; font-size: 1em;} +sup {font-size: smaller; line-height: 1px;} + +.slide code {padding: 2px 0.25em; font-weight: bold; color: #533;} +.slide code.bad, code del {color: red;} +.slide code.old {color: silver;} +.slide pre {padding: 0; margin: 0.25em 0 0.5em 0.5em; color: #533; font-size: 90%;} +.slide pre code {display: block;} +.slide ul {margin-left: 5%; margin-right: 7%; list-style: disc;} +.slide li {margin-top: 0.75em; margin-right: 0;} +.slide ul ul {line-height: 1;} +.slide ul ul li {margin: .2em; font-size: 85%; list-style: square;} +.slide img.leader {display: block; margin: 0 auto;} + +div#header, div#footer {background: #005; color: #AAB; + font-family: Verdana, Helvetica, sans-serif;} +div#header {background: #005 url(bodybg.gif) -16px 0 no-repeat; + line-height: 1px;} +div#footer {font-size: 0.5em; font-weight: bold; padding: 1em 0;} +#footer h1, #footer h2 {display: block; padding: 0 1em;} +#footer h2 {font-style: italic;} + +div.long {font-size: 0.75em;} +.slide h1 {position: absolute; top: 0.7em; left: 87px; z-index: 1; + margin: 0; padding: 0.3em 0 0 50px; white-space: nowrap; + font: bold 150%/1em Helvetica, sans-serif; text-transform: capitalize; + color: #DDE; background: #005;} +.slide h3 {font-size: 130%;} +h1 abbr {font-variant: small-caps;} + +div#controls {position: absolute; left: 50%; bottom: 0; + width: 50%; + text-align: right; font: bold 0.9em Verdana, Helvetica, sans-serif;} +html>body div#controls {position: fixed; padding: 0 0 1em 0; + top: auto;} +div#controls form {position: absolute; bottom: 0; right: 0; width: 100%; + margin: 0; padding: 0;} +#controls #navLinks a {padding: 0; margin: 0 0.5em; + background: #005; border: none; color: #779; + cursor: pointer;} +#controls #navList {height: 1em;} +#controls #navList #jumplist {position: absolute; bottom: 0; right: 0; background: #DDD; color: #227;} + +#currentSlide {text-align: center; font-size: 0.5em; color: #449;} + +#slide0 {padding-top: 3.5em; font-size: 90%;} +#slide0 h1 {position: static; margin: 1em 0 0; padding: 0; + font: bold 2em Helvetica, sans-serif; white-space: normal; + color: #000; background: transparent;} +#slide0 h2 {font: bold italic 1em Helvetica, sans-serif; margin: 0.25em;} +#slide0 h3 {margin-top: 1.5em; font-size: 1.5em;} +#slide0 h4 {margin-top: 0; font-size: 1em;} + +ul.urls {list-style: none; display: inline; margin: 0;} +.urls li {display: inline; margin: 0;} +.note {display: none;} +.external {border-bottom: 1px dotted gray;} +html>body .external {border-bottom: none;} +.external:after {content: " \274F"; font-size: smaller; color: #77B;} + +.incremental, .incremental *, .incremental *:after {color: #DDE; visibility: visible;} +img.incremental {visibility: hidden;} +.slide .current {color: #B02;} + + +/* diagnostics + +li:after {content: " [" attr(class) "]"; color: #F88;} + */ +</style> +<style type="text/css" media="projection" id="operaFix"> +/* DO NOT CHANGE THESE unless you really want to break Opera Show */ +.slide { + visibility: visible !important; + position: static !important; + page-break-before: always; +} +#slide0 {page-break-before: avoid;} + +</style> +<style type="text/css" media="screen" id="outlineStyle"> +/* don't change this unless you want the layout stuff to show up in the outline view! */ + +.layout div, #footer *, #controlForm * {display: none;} +#footer, #controls, #controlForm, #navLinks, #toggle { + display: block; visibility: visible; margin: 0; padding: 0;} +#toggle {float: right; padding: 0.5em;} +html>body #toggle {position: fixed; top: 0; right: 0;} + +/* making the outline look pretty-ish */ + +#slide0 h1, #slide0 h2, #slide0 h3, #slide0 h4 {border: none; margin: 0;} +#slide0 h1 {padding-top: 1.5em;} +.slide h1 {margin: 1.5em 0 0; padding-top: 0.25em; + border-top: 1px solid #888; border-bottom: 1px solid #AAA;} +#toggle {border: 1px solid; border-width: 0 0 1px 1px; background: #FFF;} + +</style> +<style type="text/css" media="print" id="slidePrint"> +/* The following rule is necessary to have all slides appear in print! DO NOT REMOVE IT! */
.slide, ul {page-break-inside: avoid; visibility: visible !important;}
h1 {page-break-after: avoid;}
body {font-size: 12pt; background: white;}
* {color: black;}
#slide0 h1 {font-size: 200%; border: none; margin: 0.5em 0 0.25em;}
#slide0 h3 {margin: 0; padding: 0;}
#slide0 h4 {margin: 0 0 0.5em; padding: 0;}
#slide0 {margin-bottom: 3em;}
h1 {border-top: 2pt solid gray; border-bottom: 1px dotted silver;}
.extra {background: transparent !important;}
div.extra, pre.extra, .example {font-size: 10pt; color: #333;}
ul.extra a {font-weight: bold;}
p.example {display: none;}
#header {display: none;}
#footer h1 {margin: 0; border-bottom: 1px solid; color: gray; font-style: italic;}
#footer h2, #controls {display: none;}
/* The following rule keeps the layout stuff out of print. Remove at your own risk! */
.layout, .layout * {display: none !important;}
+</style> +<script type="text/javascript"> +// S5 v1.1 slides.js -- released into the Public Domain +// +// Please see http://www.meyerweb.com/eric/tools/s5/credits.html for information +// about all the wonderful and talented contributors to this code! + +var undef; +var slideCSS = ''; +var snum = 0; +var smax = 1; +var incpos = 0; +var number = undef; +var s5mode = true; +var defaultView = 'slideshow'; +var controlVis = 'visible'; + +var isIE = navigator.appName == 'Microsoft Internet Explorer' && navigator.userAgent.indexOf('Opera') < 1 ? 1 : 0; +var isOp = navigator.userAgent.indexOf('Opera') > -1 ? 1 : 0; +var isGe = navigator.userAgent.indexOf('Gecko') > -1 && navigator.userAgent.indexOf('Safari') < 1 ? 1 : 0; + +function hasClass(object, className) { + if (!object.className) return false; + return (object.className.search('(^|\\s)' + className + '(\\s|$)') != -1); +} + +function hasValue(object, value) { + if (!object) return false; + return (object.search('(^|\\s)' + value + '(\\s|$)') != -1); +} + +function removeClass(object,className) { + if (!object) return; + object.className = object.className.replace(new RegExp('(^|\\s)'+className+'(\\s|$)'), RegExp.$1+RegExp.$2); +} + +function addClass(object,className) { + if (!object || hasClass(object, className)) return; + if (object.className) { + object.className += ' '+className; + } else { + object.className = className; + } +} + +function GetElementsWithClassName(elementName,className) { + var allElements = document.getElementsByTagName(elementName); + var elemColl = new Array(); + for (var i = 0; i< allElements.length; i++) { + if (hasClass(allElements[i], className)) { + elemColl[elemColl.length] = allElements[i]; + } + } + return elemColl; +} + +function isParentOrSelf(element, id) { + if (element == null || element.nodeName=='BODY') return false; + else if (element.id == id) return true; + else return isParentOrSelf(element.parentNode, id); +} + +function nodeValue(node) { + var result = ""; + if (node.nodeType == 1) { + var children = node.childNodes; + for (var i = 0; i < children.length; ++i) { + result += nodeValue(children[i]); + } + } + else if (node.nodeType == 3) { + result = node.nodeValue; + } + return(result); +} + +function slideLabel() { + var slideColl = GetElementsWithClassName('*','slide'); + var list = document.getElementById('jumplist'); + smax = slideColl.length; + for (var n = 0; n < smax; n++) { + var obj = slideColl[n]; + + var did = 'slide' + n.toString(); + obj.setAttribute('id',did); + if (isOp) continue; + + var otext = ''; + var menu = obj.firstChild; + if (!menu) continue; // to cope with empty slides + while (menu && menu.nodeType == 3) { + menu = menu.nextSibling; + } + if (!menu) continue; // to cope with slides with only text nodes + + var menunodes = menu.childNodes; + for (var o = 0; o < menunodes.length; o++) { + otext += nodeValue(menunodes[o]); + } + list.options[list.length] = new Option(n + ' : ' + otext, n); + } +} + +function currentSlide() { + var cs; + if (document.getElementById) { + cs = document.getElementById('currentSlide'); + } else { + cs = document.currentSlide; + } + cs.innerHTML = '<span id="csHere">' + snum + '<\/span> ' + + '<span id="csSep">\/<\/span> ' + + '<span id="csTotal">' + (smax-1) + '<\/span>'; + if (snum == 0) { + cs.style.visibility = 'hidden'; + } else { + cs.style.visibility = 'visible'; + } +} + +function go(step) { + if (document.getElementById('slideProj').disabled || step == 0) return; + var jl = document.getElementById('jumplist'); + var cid = 'slide' + snum; + var ce = document.getElementById(cid); + if (incrementals[snum].length > 0) { + for (var i = 0; i < incrementals[snum].length; i++) { + removeClass(incrementals[snum][i], 'current'); + removeClass(incrementals[snum][i], 'incremental'); + } + } + if (step != 'j') { + snum += step; + lmax = smax - 1; + if (snum > lmax) snum = lmax; + if (snum < 0) snum = 0; + } else + snum = parseInt(jl.value); + var nid = 'slide' + snum; + var ne = document.getElementById(nid); + if (!ne) { + ne = document.getElementById('slide0'); + snum = 0; + } + if (step < 0) {incpos = incrementals[snum].length} else {incpos = 0;} + if (incrementals[snum].length > 0 && incpos == 0) { + for (var i = 0; i < incrementals[snum].length; i++) { + if (hasClass(incrementals[snum][i], 'current')) + incpos = i + 1; + else + addClass(incrementals[snum][i], 'incremental'); + } + } + if (incrementals[snum].length > 0 && incpos > 0) + addClass(incrementals[snum][incpos - 1], 'current'); + ce.style.visibility = 'hidden'; + ne.style.visibility = 'visible'; + jl.selectedIndex = snum; + currentSlide(); + number = 0; +} + +function goTo(target) { + if (target >= smax || target == snum) return; + go(target - snum); +} + +function subgo(step) { + if (step > 0) { + removeClass(incrementals[snum][incpos - 1],'current'); + removeClass(incrementals[snum][incpos], 'incremental'); + addClass(incrementals[snum][incpos],'current'); + incpos++; + } else { + incpos--; + removeClass(incrementals[snum][incpos],'current'); + addClass(incrementals[snum][incpos], 'incremental'); + addClass(incrementals[snum][incpos - 1],'current'); + } +} + +function toggle() { + var slideColl = GetElementsWithClassName('*','slide'); + var slides = document.getElementById('slideProj'); + var outline = document.getElementById('outlineStyle'); + if (!slides.disabled) { + slides.disabled = true; + outline.disabled = false; + s5mode = false; + fontSize('1em'); + for (var n = 0; n < smax; n++) { + var slide = slideColl[n]; + slide.style.visibility = 'visible'; + } + } else { + slides.disabled = false; + outline.disabled = true; + s5mode = true; + fontScale(); + for (var n = 0; n < smax; n++) { + var slide = slideColl[n]; + slide.style.visibility = 'hidden'; + } + slideColl[snum].style.visibility = 'visible'; + } +} + +function showHide(action) { + var obj = GetElementsWithClassName('*','hideme')[0]; + switch (action) { + case 's': obj.style.visibility = 'visible'; break; + case 'h': obj.style.visibility = 'hidden'; break; + case 'k': + if (obj.style.visibility != 'visible') { + obj.style.visibility = 'visible'; + } else { + obj.style.visibility = 'hidden'; + } + break; + } +} + +// 'keys' code adapted from MozPoint (http://mozpoint.mozdev.org/) +function keys(key) { + if (!key) { + key = event; + key.which = key.keyCode; + } + if (key.which == 84) { + toggle(); + return; + } + if (s5mode) { + switch (key.which) { + case 10: // return + case 13: // enter + if (window.event && isParentOrSelf(window.event.srcElement, 'controls')) return; + if (key.target && isParentOrSelf(key.target, 'controls')) return; + if(number != undef) { + goTo(number); + break; + } + case 32: // spacebar + case 34: // page down + case 39: // rightkey + case 40: // downkey + if(number != undef) { + go(number); + } else if (!incrementals[snum] || incpos >= incrementals[snum].length) { + go(1); + } else { + subgo(1); + } + break; + case 33: // page up + case 37: // leftkey + case 38: // upkey + if(number != undef) { + go(-1 * number); + } else if (!incrementals[snum] || incpos <= 0) { + go(-1); + } else { + subgo(-1); + } + break; + case 36: // home + goTo(0); + break; + case 35: // end + goTo(smax-1); + break; + case 67: // c + showHide('k'); + break; + } + if (key.which < 48 || key.which > 57) { + number = undef; + } else { + if (window.event && isParentOrSelf(window.event.srcElement, 'controls')) return; + if (key.target && isParentOrSelf(key.target, 'controls')) return; + number = (((number != undef) ? number : 0) * 10) + (key.which - 48); + } + } + return false; +} + +function clicker(e) { + number = undef; + var target; + if (window.event) { + target = window.event.srcElement; + e = window.event; + } else target = e.target; + if (target.getAttribute('href') != null || hasValue(target.rel, 'external') || isParentOrSelf(target, 'controls') || isParentOrSelf(target,'embed') || isParentOrSelf(target,'object')) return true; + if (!e.which || e.which == 1) { + if (!incrementals[snum] || incpos >= incrementals[snum].length) { + go(1); + } else { + subgo(1); + } + } +} + +function findSlide(hash) { + var target = null; + var slides = GetElementsWithClassName('*','slide'); + for (var i = 0; i < slides.length; i++) { + var targetSlide = slides[i]; + if ( (targetSlide.name && targetSlide.name == hash) + || (targetSlide.id && targetSlide.id == hash) ) { + target = targetSlide; + break; + } + } + while(target != null && target.nodeName != 'BODY') { + if (hasClass(target, 'slide')) { + return parseInt(target.id.slice(5)); + } + target = target.parentNode; + } + return null; +} + +function slideJump() { + if (window.location.hash == null) return; + var sregex = /^#slide(\d+)$/; + var matches = sregex.exec(window.location.hash); + var dest = null; + if (matches != null) { + dest = parseInt(matches[1]); + } else { + dest = findSlide(window.location.hash.slice(1)); + } + if (dest != null) + go(dest - snum); +} + +function fixLinks() { + var thisUri = window.location.href; + thisUri = thisUri.slice(0, thisUri.length - window.location.hash.length); + var aelements = document.getElementsByTagName('A'); + for (var i = 0; i < aelements.length; i++) { + var a = aelements[i].href; + var slideID = a.match('\#slide[0-9]{1,2}'); + if ((slideID) && (slideID[0].slice(0,1) == '#')) { + var dest = findSlide(slideID[0].slice(1)); + if (dest != null) { + if (aelements[i].addEventListener) { + aelements[i].addEventListener("click", new Function("e", + "if (document.getElementById('slideProj').disabled) return;" + + "go("+dest+" - snum); " + + "if (e.preventDefault) e.preventDefault();"), true); + } else if (aelements[i].attachEvent) { + aelements[i].attachEvent("onclick", new Function("", + "if (document.getElementById('slideProj').disabled) return;" + + "go("+dest+" - snum); " + + "event.returnValue = false;")); + } + } + } + } +} + +function externalLinks() { + if (!document.getElementsByTagName) return; + var anchors = document.getElementsByTagName('a'); + for (var i=0; i<anchors.length; i++) { + var anchor = anchors[i]; + if (anchor.getAttribute('href') && hasValue(anchor.rel, 'external')) { + anchor.target = '_blank'; + addClass(anchor,'external'); + } + } +} + +function createControls() { + var controlsDiv = document.getElementById("controls"); + if (!controlsDiv) return; + var hider = ' onmouseover="showHide(\'s\');" onmouseout="showHide(\'h\');"'; + var hideDiv, hideList = ''; + if (controlVis == 'hidden') { + hideDiv = hider; + } else { + hideList = hider; + } + controlsDiv.innerHTML = '<form action="#" id="controlForm"' + hideDiv + '>' + + '<div id="navLinks">' + + '<a accesskey="t" id="toggle" href="javascript:toggle();">Ø<\/a>' + + '<a accesskey="z" id="prev" href="javascript:go(-1);">«<\/a>' + + '<a accesskey="x" id="next" href="javascript:go(1);">»<\/a>' + + '<div id="navList"' + hideList + '><select id="jumplist" onchange="go(\'j\');"><\/select><\/div>' + + '<\/div><\/form>'; + if (controlVis == 'hidden') { + var hidden = document.getElementById('navLinks'); + } else { + var hidden = document.getElementById('jumplist'); + } + addClass(hidden,'hideme'); +} + +function fontScale() { // causes layout problems in FireFox that get fixed if browser's Reload is used; same may be true of other Gecko-based browsers + if (!s5mode) return false; + var vScale = 22; // both yield 32 (after rounding) at 1024x768 + var hScale = 32; // perhaps should auto-calculate based on theme's declared value? + if (window.innerHeight) { + var vSize = window.innerHeight; + var hSize = window.innerWidth; + } else if (document.documentElement.clientHeight) { + var vSize = document.documentElement.clientHeight; + var hSize = document.documentElement.clientWidth; + } else if (document.body.clientHeight) { + var vSize = document.body.clientHeight; + var hSize = document.body.clientWidth; + } else { + var vSize = 700; // assuming 1024x768, minus chrome and such + var hSize = 1024; // these do not account for kiosk mode or Opera Show + } + var newSize = Math.min(Math.round(vSize/vScale),Math.round(hSize/hScale)); + fontSize(newSize + 'px'); + if (isGe) { // hack to counter incremental reflow bugs + var obj = document.getElementsByTagName('body')[0]; + obj.style.display = 'none'; + obj.style.display = 'block'; + } +} + +function fontSize(value) { + if (!(s5ss = document.getElementById('s5ss'))) { + if (!isIE) { + document.getElementsByTagName('head')[0].appendChild(s5ss = document.createElement('style')); + s5ss.setAttribute('media','screen, projection'); + s5ss.setAttribute('id','s5ss'); + } else { + document.createStyleSheet(); + document.s5ss = document.styleSheets[document.styleSheets.length - 1]; + } + } + if (!isIE) { + while (s5ss.lastChild) s5ss.removeChild(s5ss.lastChild); + s5ss.appendChild(document.createTextNode('body {font-size: ' + value + ' !important;}')); + } else { + document.s5ss.addRule('body','font-size: ' + value + ' !important;'); + } +} + +function notOperaFix() { + slideCSS = document.getElementById('slideProj').href; + var slides = document.getElementById('slideProj'); + var outline = document.getElementById('outlineStyle'); + slides.setAttribute('media','screen'); + outline.disabled = true; + if (isGe) { + slides.setAttribute('href','null'); // Gecko fix + slides.setAttribute('href',slideCSS); // Gecko fix + } + if (isIE && document.styleSheets && document.styleSheets[0]) { + document.styleSheets[0].addRule('img', 'behavior: url(ui/default/iepngfix.htc)'); + document.styleSheets[0].addRule('div', 'behavior: url(ui/default/iepngfix.htc)'); + document.styleSheets[0].addRule('.slide', 'behavior: url(ui/default/iepngfix.htc)'); + } +} + +function getIncrementals(obj) { + var incrementals = new Array(); + if (!obj) + return incrementals; + var children = obj.childNodes; + for (var i = 0; i < children.length; i++) { + var child = children[i]; + if (hasClass(child, 'incremental')) { + if (child.nodeName == 'OL' || child.nodeName == 'UL') { + removeClass(child, 'incremental'); + for (var j = 0; j < child.childNodes.length; j++) { + if (child.childNodes[j].nodeType == 1) { + addClass(child.childNodes[j], 'incremental'); + } + } + } else { + incrementals[incrementals.length] = child; + removeClass(child,'incremental'); + } + } + if (hasClass(child, 'show-first')) { + if (child.nodeName == 'OL' || child.nodeName == 'UL') { + removeClass(child, 'show-first'); + if (child.childNodes[isGe].nodeType == 1) { + removeClass(child.childNodes[isGe], 'incremental'); + } + } else { + incrementals[incrementals.length] = child; + } + } + incrementals = incrementals.concat(getIncrementals(child)); + } + return incrementals; +} + +function createIncrementals() { + var incrementals = new Array(); + for (var i = 0; i < smax; i++) { + incrementals[i] = getIncrementals(document.getElementById('slide'+i)); + } + return incrementals; +} + +function defaultCheck() { + var allMetas = document.getElementsByTagName('meta'); + for (var i = 0; i< allMetas.length; i++) { + if (allMetas[i].name == 'defaultView') { + defaultView = allMetas[i].content; + } + if (allMetas[i].name == 'controlVis') { + controlVis = allMetas[i].content; + } + } +} + +// Key trap fix, new function body for trap() +function trap(e) { + if (!e) { + e = event; + e.which = e.keyCode; + } + try { + modifierKey = e.ctrlKey || e.altKey || e.metaKey; + } + catch(e) { + modifierKey = false; + } + return modifierKey || e.which == 0; +} + +function startup() { + defaultCheck(); + if (!isOp) + createControls(); + slideLabel(); + fixLinks(); + externalLinks(); + fontScale(); + if (!isOp) { + notOperaFix(); + incrementals = createIncrementals(); + slideJump(); + if (defaultView == 'outline') { + toggle(); + } + document.onkeyup = keys; + document.onkeypress = trap; + document.onclick = clicker; + } +} + +window.onload = startup; +window.onresize = function(){setTimeout('fontScale()', 50);}</script> +<meta name="author" content="Sam Smith, Jen Jones" /> +<meta name="date" content="July 15, 2006" /> +<title>My S5 Document</title> +</head> +<body> +<div class="layout"> +<div id="controls"></div> +<div id="currentSlide"></div> +<div id="header"></div> +<div id="footer"> +<h1>July 15, 2006</h1> +<h2>My S5 Document</h2> +</div> +</div> +<div class="presentation"> + +<div class="slide"> +<h1>My S5 Document</h1> +<h3>Sam Smith, Jen Jones</h3> +<h4>July 15, 2006</h4> +</div> +<div class="slide"> +<h1>First slide</h1> +<ul> +<li>first bullet</li> +<li>second bullet</li> +</ul> +</div> +<div class="slide"> +<h1>Smarty</h1> +<ul class="incremental"> +<li>"Hello there"</li> +<li>Here's a -- dash</li> +<li>And 'ellipses'...</li> +</ul> +</div> +<div class="slide"> +<h1>Math</h1> +<ul> +<li>$\frac{d}{dx}f(x)=\lim_{h\to 0}\frac{f(x+h)-f(x)}{h}$</li> +</ul> +</div> +</div> +</body> +</html> + diff --git a/tests/s5.fancy.html b/tests/s5.fancy.html new file mode 100644 index 000000000..875bbfbaf --- /dev/null +++ b/tests/s5.fancy.html @@ -0,0 +1,1673 @@ +<!DOCTYPE html PUBLIC "-//W3C//DTD XHTML 1.0 Strict//EN" "http://www.w3.org/TR/xhtml1/DTD/xhtml1-strict.dtd"> +<html xmlns="http://www.w3.org/1999/xhtml"> +<head> +<!-- configuration parameters --> +<meta name="defaultView" content="slideshow" /> +<meta name="controlVis" content="hidden" /> +<meta http-equiv="Content-Type" content="text/html; charset=UTF-8" /> +<meta name="generator" content="pandoc" /> +<style type="text/css" media="projection" id="slideProj"> +/* Do not edit or override these styles! The system will likely break if you do. */ + +div#header, div#footer, div#controls, .slide {position: absolute;} +html>body div#header, html>body div#footer, + html>body div#controls, html>body .slide {position: fixed;} +.handout {display: none;} +.layout {display: block;} +.slide, .hideme, .incremental {visibility: hidden;} +#slide0 {visibility: visible;} + +/* The following styles size, place, and layer the slide components. + Edit these if you want to change the overall slide layout. + The commented lines can be uncommented (and modified, if necessary) + to help you with the rearrangement process. */ + +/* target = 1024x768 */ + +div#header, div#footer, .slide {width: 100%; top: 0; left: 0;} +div#header {top: 0; height: 3em; z-index: 1;} +div#footer {top: auto; bottom: 0; height: 2.5em; z-index: 5;} +.slide {top: 0; width: 92%; padding: 3.5em 4% 4%; z-index: 2; list-style: none;} +div#controls {left: 50%; bottom: 0; width: 50%; z-index: 100;} +div#controls form {position: absolute; bottom: 0; right: 0; width: 100%; + margin: 0;} +#currentSlide {position: absolute; width: 10%; left: 45%; bottom: 1em; z-index: 10;} +html>body #currentSlide {position: fixed;} + +/* +div#header {background: #FCC;} +div#footer {background: #CCF;} +div#controls {background: #BBD;} +div#currentSlide {background: #FFC;} +*/ + +/* Following are the presentation styles -- edit away! */ + +body {background: #FFF url(bodybg.gif) -16px 0 no-repeat; color: #000; font-size: 2em;} +:link, :visited {text-decoration: none; color: #00C;} +#controls :active {color: #88A !important;} +#controls :focus {outline: 1px dotted #227;} +h1, h2, h3, h4 {font-size: 100%; margin: 0; padding: 0; font-weight: inherit;} +ul, pre {margin: 0; line-height: 1em;} +html, body {margin: 0; padding: 0;} + +blockquote, q {font-style: italic;} +blockquote {padding: 0 2em 0.5em; margin: 0 1.5em 0.5em; text-align: center; font-size: 1em;} +blockquote p {margin: 0;} +blockquote i {font-style: normal;} +blockquote b {display: block; margin-top: 0.5em; font-weight: normal; font-size: smaller; font-style: normal;} +blockquote b i {font-style: italic;} + +kbd {font-weight: bold; font-size: 1em;} +sup {font-size: smaller; line-height: 1px;} + +.slide code {padding: 2px 0.25em; font-weight: bold; color: #533;} +.slide code.bad, code del {color: red;} +.slide code.old {color: silver;} +.slide pre {padding: 0; margin: 0.25em 0 0.5em 0.5em; color: #533; font-size: 90%;} +.slide pre code {display: block;} +.slide ul {margin-left: 5%; margin-right: 7%; list-style: disc;} +.slide li {margin-top: 0.75em; margin-right: 0;} +.slide ul ul {line-height: 1;} +.slide ul ul li {margin: .2em; font-size: 85%; list-style: square;} +.slide img.leader {display: block; margin: 0 auto;} + +div#header, div#footer {background: #005; color: #AAB; + font-family: Verdana, Helvetica, sans-serif;} +div#header {background: #005 url(bodybg.gif) -16px 0 no-repeat; + line-height: 1px;} +div#footer {font-size: 0.5em; font-weight: bold; padding: 1em 0;} +#footer h1, #footer h2 {display: block; padding: 0 1em;} +#footer h2 {font-style: italic;} + +div.long {font-size: 0.75em;} +.slide h1 {position: absolute; top: 0.7em; left: 87px; z-index: 1; + margin: 0; padding: 0.3em 0 0 50px; white-space: nowrap; + font: bold 150%/1em Helvetica, sans-serif; text-transform: capitalize; + color: #DDE; background: #005;} +.slide h3 {font-size: 130%;} +h1 abbr {font-variant: small-caps;} + +div#controls {position: absolute; left: 50%; bottom: 0; + width: 50%; + text-align: right; font: bold 0.9em Verdana, Helvetica, sans-serif;} +html>body div#controls {position: fixed; padding: 0 0 1em 0; + top: auto;} +div#controls form {position: absolute; bottom: 0; right: 0; width: 100%; + margin: 0; padding: 0;} +#controls #navLinks a {padding: 0; margin: 0 0.5em; + background: #005; border: none; color: #779; + cursor: pointer;} +#controls #navList {height: 1em;} +#controls #navList #jumplist {position: absolute; bottom: 0; right: 0; background: #DDD; color: #227;} + +#currentSlide {text-align: center; font-size: 0.5em; color: #449;} + +#slide0 {padding-top: 3.5em; font-size: 90%;} +#slide0 h1 {position: static; margin: 1em 0 0; padding: 0; + font: bold 2em Helvetica, sans-serif; white-space: normal; + color: #000; background: transparent;} +#slide0 h2 {font: bold italic 1em Helvetica, sans-serif; margin: 0.25em;} +#slide0 h3 {margin-top: 1.5em; font-size: 1.5em;} +#slide0 h4 {margin-top: 0; font-size: 1em;} + +ul.urls {list-style: none; display: inline; margin: 0;} +.urls li {display: inline; margin: 0;} +.note {display: none;} +.external {border-bottom: 1px dotted gray;} +html>body .external {border-bottom: none;} +.external:after {content: " \274F"; font-size: smaller; color: #77B;} + +.incremental, .incremental *, .incremental *:after {color: #DDE; visibility: visible;} +img.incremental {visibility: hidden;} +.slide .current {color: #B02;} + + +/* diagnostics + +li:after {content: " [" attr(class) "]"; color: #F88;} + */ +</style> +<style type="text/css" media="projection" id="operaFix"> +/* DO NOT CHANGE THESE unless you really want to break Opera Show */ +.slide { + visibility: visible !important; + position: static !important; + page-break-before: always; +} +#slide0 {page-break-before: avoid;} + +</style> +<style type="text/css" media="screen" id="outlineStyle"> +/* don't change this unless you want the layout stuff to show up in the outline view! */ + +.layout div, #footer *, #controlForm * {display: none;} +#footer, #controls, #controlForm, #navLinks, #toggle { + display: block; visibility: visible; margin: 0; padding: 0;} +#toggle {float: right; padding: 0.5em;} +html>body #toggle {position: fixed; top: 0; right: 0;} + +/* making the outline look pretty-ish */ + +#slide0 h1, #slide0 h2, #slide0 h3, #slide0 h4 {border: none; margin: 0;} +#slide0 h1 {padding-top: 1.5em;} +.slide h1 {margin: 1.5em 0 0; padding-top: 0.25em; + border-top: 1px solid #888; border-bottom: 1px solid #AAA;} +#toggle {border: 1px solid; border-width: 0 0 1px 1px; background: #FFF;} + +</style> +<style type="text/css" media="print" id="slidePrint"> +/* The following rule is necessary to have all slides appear in print! DO NOT REMOVE IT! */
.slide, ul {page-break-inside: avoid; visibility: visible !important;}
h1 {page-break-after: avoid;}
body {font-size: 12pt; background: white;}
* {color: black;}
#slide0 h1 {font-size: 200%; border: none; margin: 0.5em 0 0.25em;}
#slide0 h3 {margin: 0; padding: 0;}
#slide0 h4 {margin: 0 0 0.5em; padding: 0;}
#slide0 {margin-bottom: 3em;}
h1 {border-top: 2pt solid gray; border-bottom: 1px dotted silver;}
.extra {background: transparent !important;}
div.extra, pre.extra, .example {font-size: 10pt; color: #333;}
ul.extra a {font-weight: bold;}
p.example {display: none;}
#header {display: none;}
#footer h1 {margin: 0; border-bottom: 1px solid; color: gray; font-style: italic;}
#footer h2, #controls {display: none;}
/* The following rule keeps the layout stuff out of print. Remove at your own risk! */
.layout, .layout * {display: none !important;}
+</style> +<script type="text/javascript"> +// S5 v1.1 slides.js -- released into the Public Domain +// +// Please see http://www.meyerweb.com/eric/tools/s5/credits.html for information +// about all the wonderful and talented contributors to this code! + +var undef; +var slideCSS = ''; +var snum = 0; +var smax = 1; +var incpos = 0; +var number = undef; +var s5mode = true; +var defaultView = 'slideshow'; +var controlVis = 'visible'; + +var isIE = navigator.appName == 'Microsoft Internet Explorer' && navigator.userAgent.indexOf('Opera') < 1 ? 1 : 0; +var isOp = navigator.userAgent.indexOf('Opera') > -1 ? 1 : 0; +var isGe = navigator.userAgent.indexOf('Gecko') > -1 && navigator.userAgent.indexOf('Safari') < 1 ? 1 : 0; + +function hasClass(object, className) { + if (!object.className) return false; + return (object.className.search('(^|\\s)' + className + '(\\s|$)') != -1); +} + +function hasValue(object, value) { + if (!object) return false; + return (object.search('(^|\\s)' + value + '(\\s|$)') != -1); +} + +function removeClass(object,className) { + if (!object) return; + object.className = object.className.replace(new RegExp('(^|\\s)'+className+'(\\s|$)'), RegExp.$1+RegExp.$2); +} + +function addClass(object,className) { + if (!object || hasClass(object, className)) return; + if (object.className) { + object.className += ' '+className; + } else { + object.className = className; + } +} + +function GetElementsWithClassName(elementName,className) { + var allElements = document.getElementsByTagName(elementName); + var elemColl = new Array(); + for (var i = 0; i< allElements.length; i++) { + if (hasClass(allElements[i], className)) { + elemColl[elemColl.length] = allElements[i]; + } + } + return elemColl; +} + +function isParentOrSelf(element, id) { + if (element == null || element.nodeName=='BODY') return false; + else if (element.id == id) return true; + else return isParentOrSelf(element.parentNode, id); +} + +function nodeValue(node) { + var result = ""; + if (node.nodeType == 1) { + var children = node.childNodes; + for (var i = 0; i < children.length; ++i) { + result += nodeValue(children[i]); + } + } + else if (node.nodeType == 3) { + result = node.nodeValue; + } + return(result); +} + +function slideLabel() { + var slideColl = GetElementsWithClassName('*','slide'); + var list = document.getElementById('jumplist'); + smax = slideColl.length; + for (var n = 0; n < smax; n++) { + var obj = slideColl[n]; + + var did = 'slide' + n.toString(); + obj.setAttribute('id',did); + if (isOp) continue; + + var otext = ''; + var menu = obj.firstChild; + if (!menu) continue; // to cope with empty slides + while (menu && menu.nodeType == 3) { + menu = menu.nextSibling; + } + if (!menu) continue; // to cope with slides with only text nodes + + var menunodes = menu.childNodes; + for (var o = 0; o < menunodes.length; o++) { + otext += nodeValue(menunodes[o]); + } + list.options[list.length] = new Option(n + ' : ' + otext, n); + } +} + +function currentSlide() { + var cs; + if (document.getElementById) { + cs = document.getElementById('currentSlide'); + } else { + cs = document.currentSlide; + } + cs.innerHTML = '<span id="csHere">' + snum + '<\/span> ' + + '<span id="csSep">\/<\/span> ' + + '<span id="csTotal">' + (smax-1) + '<\/span>'; + if (snum == 0) { + cs.style.visibility = 'hidden'; + } else { + cs.style.visibility = 'visible'; + } +} + +function go(step) { + if (document.getElementById('slideProj').disabled || step == 0) return; + var jl = document.getElementById('jumplist'); + var cid = 'slide' + snum; + var ce = document.getElementById(cid); + if (incrementals[snum].length > 0) { + for (var i = 0; i < incrementals[snum].length; i++) { + removeClass(incrementals[snum][i], 'current'); + removeClass(incrementals[snum][i], 'incremental'); + } + } + if (step != 'j') { + snum += step; + lmax = smax - 1; + if (snum > lmax) snum = lmax; + if (snum < 0) snum = 0; + } else + snum = parseInt(jl.value); + var nid = 'slide' + snum; + var ne = document.getElementById(nid); + if (!ne) { + ne = document.getElementById('slide0'); + snum = 0; + } + if (step < 0) {incpos = incrementals[snum].length} else {incpos = 0;} + if (incrementals[snum].length > 0 && incpos == 0) { + for (var i = 0; i < incrementals[snum].length; i++) { + if (hasClass(incrementals[snum][i], 'current')) + incpos = i + 1; + else + addClass(incrementals[snum][i], 'incremental'); + } + } + if (incrementals[snum].length > 0 && incpos > 0) + addClass(incrementals[snum][incpos - 1], 'current'); + ce.style.visibility = 'hidden'; + ne.style.visibility = 'visible'; + jl.selectedIndex = snum; + currentSlide(); + number = 0; +} + +function goTo(target) { + if (target >= smax || target == snum) return; + go(target - snum); +} + +function subgo(step) { + if (step > 0) { + removeClass(incrementals[snum][incpos - 1],'current'); + removeClass(incrementals[snum][incpos], 'incremental'); + addClass(incrementals[snum][incpos],'current'); + incpos++; + } else { + incpos--; + removeClass(incrementals[snum][incpos],'current'); + addClass(incrementals[snum][incpos], 'incremental'); + addClass(incrementals[snum][incpos - 1],'current'); + } +} + +function toggle() { + var slideColl = GetElementsWithClassName('*','slide'); + var slides = document.getElementById('slideProj'); + var outline = document.getElementById('outlineStyle'); + if (!slides.disabled) { + slides.disabled = true; + outline.disabled = false; + s5mode = false; + fontSize('1em'); + for (var n = 0; n < smax; n++) { + var slide = slideColl[n]; + slide.style.visibility = 'visible'; + } + } else { + slides.disabled = false; + outline.disabled = true; + s5mode = true; + fontScale(); + for (var n = 0; n < smax; n++) { + var slide = slideColl[n]; + slide.style.visibility = 'hidden'; + } + slideColl[snum].style.visibility = 'visible'; + } +} + +function showHide(action) { + var obj = GetElementsWithClassName('*','hideme')[0]; + switch (action) { + case 's': obj.style.visibility = 'visible'; break; + case 'h': obj.style.visibility = 'hidden'; break; + case 'k': + if (obj.style.visibility != 'visible') { + obj.style.visibility = 'visible'; + } else { + obj.style.visibility = 'hidden'; + } + break; + } +} + +// 'keys' code adapted from MozPoint (http://mozpoint.mozdev.org/) +function keys(key) { + if (!key) { + key = event; + key.which = key.keyCode; + } + if (key.which == 84) { + toggle(); + return; + } + if (s5mode) { + switch (key.which) { + case 10: // return + case 13: // enter + if (window.event && isParentOrSelf(window.event.srcElement, 'controls')) return; + if (key.target && isParentOrSelf(key.target, 'controls')) return; + if(number != undef) { + goTo(number); + break; + } + case 32: // spacebar + case 34: // page down + case 39: // rightkey + case 40: // downkey + if(number != undef) { + go(number); + } else if (!incrementals[snum] || incpos >= incrementals[snum].length) { + go(1); + } else { + subgo(1); + } + break; + case 33: // page up + case 37: // leftkey + case 38: // upkey + if(number != undef) { + go(-1 * number); + } else if (!incrementals[snum] || incpos <= 0) { + go(-1); + } else { + subgo(-1); + } + break; + case 36: // home + goTo(0); + break; + case 35: // end + goTo(smax-1); + break; + case 67: // c + showHide('k'); + break; + } + if (key.which < 48 || key.which > 57) { + number = undef; + } else { + if (window.event && isParentOrSelf(window.event.srcElement, 'controls')) return; + if (key.target && isParentOrSelf(key.target, 'controls')) return; + number = (((number != undef) ? number : 0) * 10) + (key.which - 48); + } + } + return false; +} + +function clicker(e) { + number = undef; + var target; + if (window.event) { + target = window.event.srcElement; + e = window.event; + } else target = e.target; + if (target.getAttribute('href') != null || hasValue(target.rel, 'external') || isParentOrSelf(target, 'controls') || isParentOrSelf(target,'embed') || isParentOrSelf(target,'object')) return true; + if (!e.which || e.which == 1) { + if (!incrementals[snum] || incpos >= incrementals[snum].length) { + go(1); + } else { + subgo(1); + } + } +} + +function findSlide(hash) { + var target = null; + var slides = GetElementsWithClassName('*','slide'); + for (var i = 0; i < slides.length; i++) { + var targetSlide = slides[i]; + if ( (targetSlide.name && targetSlide.name == hash) + || (targetSlide.id && targetSlide.id == hash) ) { + target = targetSlide; + break; + } + } + while(target != null && target.nodeName != 'BODY') { + if (hasClass(target, 'slide')) { + return parseInt(target.id.slice(5)); + } + target = target.parentNode; + } + return null; +} + +function slideJump() { + if (window.location.hash == null) return; + var sregex = /^#slide(\d+)$/; + var matches = sregex.exec(window.location.hash); + var dest = null; + if (matches != null) { + dest = parseInt(matches[1]); + } else { + dest = findSlide(window.location.hash.slice(1)); + } + if (dest != null) + go(dest - snum); +} + +function fixLinks() { + var thisUri = window.location.href; + thisUri = thisUri.slice(0, thisUri.length - window.location.hash.length); + var aelements = document.getElementsByTagName('A'); + for (var i = 0; i < aelements.length; i++) { + var a = aelements[i].href; + var slideID = a.match('\#slide[0-9]{1,2}'); + if ((slideID) && (slideID[0].slice(0,1) == '#')) { + var dest = findSlide(slideID[0].slice(1)); + if (dest != null) { + if (aelements[i].addEventListener) { + aelements[i].addEventListener("click", new Function("e", + "if (document.getElementById('slideProj').disabled) return;" + + "go("+dest+" - snum); " + + "if (e.preventDefault) e.preventDefault();"), true); + } else if (aelements[i].attachEvent) { + aelements[i].attachEvent("onclick", new Function("", + "if (document.getElementById('slideProj').disabled) return;" + + "go("+dest+" - snum); " + + "event.returnValue = false;")); + } + } + } + } +} + +function externalLinks() { + if (!document.getElementsByTagName) return; + var anchors = document.getElementsByTagName('a'); + for (var i=0; i<anchors.length; i++) { + var anchor = anchors[i]; + if (anchor.getAttribute('href') && hasValue(anchor.rel, 'external')) { + anchor.target = '_blank'; + addClass(anchor,'external'); + } + } +} + +function createControls() { + var controlsDiv = document.getElementById("controls"); + if (!controlsDiv) return; + var hider = ' onmouseover="showHide(\'s\');" onmouseout="showHide(\'h\');"'; + var hideDiv, hideList = ''; + if (controlVis == 'hidden') { + hideDiv = hider; + } else { + hideList = hider; + } + controlsDiv.innerHTML = '<form action="#" id="controlForm"' + hideDiv + '>' + + '<div id="navLinks">' + + '<a accesskey="t" id="toggle" href="javascript:toggle();">Ø<\/a>' + + '<a accesskey="z" id="prev" href="javascript:go(-1);">«<\/a>' + + '<a accesskey="x" id="next" href="javascript:go(1);">»<\/a>' + + '<div id="navList"' + hideList + '><select id="jumplist" onchange="go(\'j\');"><\/select><\/div>' + + '<\/div><\/form>'; + if (controlVis == 'hidden') { + var hidden = document.getElementById('navLinks'); + } else { + var hidden = document.getElementById('jumplist'); + } + addClass(hidden,'hideme'); +} + +function fontScale() { // causes layout problems in FireFox that get fixed if browser's Reload is used; same may be true of other Gecko-based browsers + if (!s5mode) return false; + var vScale = 22; // both yield 32 (after rounding) at 1024x768 + var hScale = 32; // perhaps should auto-calculate based on theme's declared value? + if (window.innerHeight) { + var vSize = window.innerHeight; + var hSize = window.innerWidth; + } else if (document.documentElement.clientHeight) { + var vSize = document.documentElement.clientHeight; + var hSize = document.documentElement.clientWidth; + } else if (document.body.clientHeight) { + var vSize = document.body.clientHeight; + var hSize = document.body.clientWidth; + } else { + var vSize = 700; // assuming 1024x768, minus chrome and such + var hSize = 1024; // these do not account for kiosk mode or Opera Show + } + var newSize = Math.min(Math.round(vSize/vScale),Math.round(hSize/hScale)); + fontSize(newSize + 'px'); + if (isGe) { // hack to counter incremental reflow bugs + var obj = document.getElementsByTagName('body')[0]; + obj.style.display = 'none'; + obj.style.display = 'block'; + } +} + +function fontSize(value) { + if (!(s5ss = document.getElementById('s5ss'))) { + if (!isIE) { + document.getElementsByTagName('head')[0].appendChild(s5ss = document.createElement('style')); + s5ss.setAttribute('media','screen, projection'); + s5ss.setAttribute('id','s5ss'); + } else { + document.createStyleSheet(); + document.s5ss = document.styleSheets[document.styleSheets.length - 1]; + } + } + if (!isIE) { + while (s5ss.lastChild) s5ss.removeChild(s5ss.lastChild); + s5ss.appendChild(document.createTextNode('body {font-size: ' + value + ' !important;}')); + } else { + document.s5ss.addRule('body','font-size: ' + value + ' !important;'); + } +} + +function notOperaFix() { + slideCSS = document.getElementById('slideProj').href; + var slides = document.getElementById('slideProj'); + var outline = document.getElementById('outlineStyle'); + slides.setAttribute('media','screen'); + outline.disabled = true; + if (isGe) { + slides.setAttribute('href','null'); // Gecko fix + slides.setAttribute('href',slideCSS); // Gecko fix + } + if (isIE && document.styleSheets && document.styleSheets[0]) { + document.styleSheets[0].addRule('img', 'behavior: url(ui/default/iepngfix.htc)'); + document.styleSheets[0].addRule('div', 'behavior: url(ui/default/iepngfix.htc)'); + document.styleSheets[0].addRule('.slide', 'behavior: url(ui/default/iepngfix.htc)'); + } +} + +function getIncrementals(obj) { + var incrementals = new Array(); + if (!obj) + return incrementals; + var children = obj.childNodes; + for (var i = 0; i < children.length; i++) { + var child = children[i]; + if (hasClass(child, 'incremental')) { + if (child.nodeName == 'OL' || child.nodeName == 'UL') { + removeClass(child, 'incremental'); + for (var j = 0; j < child.childNodes.length; j++) { + if (child.childNodes[j].nodeType == 1) { + addClass(child.childNodes[j], 'incremental'); + } + } + } else { + incrementals[incrementals.length] = child; + removeClass(child,'incremental'); + } + } + if (hasClass(child, 'show-first')) { + if (child.nodeName == 'OL' || child.nodeName == 'UL') { + removeClass(child, 'show-first'); + if (child.childNodes[isGe].nodeType == 1) { + removeClass(child.childNodes[isGe], 'incremental'); + } + } else { + incrementals[incrementals.length] = child; + } + } + incrementals = incrementals.concat(getIncrementals(child)); + } + return incrementals; +} + +function createIncrementals() { + var incrementals = new Array(); + for (var i = 0; i < smax; i++) { + incrementals[i] = getIncrementals(document.getElementById('slide'+i)); + } + return incrementals; +} + +function defaultCheck() { + var allMetas = document.getElementsByTagName('meta'); + for (var i = 0; i< allMetas.length; i++) { + if (allMetas[i].name == 'defaultView') { + defaultView = allMetas[i].content; + } + if (allMetas[i].name == 'controlVis') { + controlVis = allMetas[i].content; + } + } +} + +// Key trap fix, new function body for trap() +function trap(e) { + if (!e) { + e = event; + e.which = e.keyCode; + } + try { + modifierKey = e.ctrlKey || e.altKey || e.metaKey; + } + catch(e) { + modifierKey = false; + } + return modifierKey || e.which == 0; +} + +function startup() { + defaultCheck(); + if (!isOp) + createControls(); + slideLabel(); + fixLinks(); + externalLinks(); + fontScale(); + if (!isOp) { + notOperaFix(); + incrementals = createIncrementals(); + slideJump(); + if (defaultView == 'outline') { + toggle(); + } + document.onkeyup = keys; + document.onkeypress = trap; + document.onclick = clicker; + } +} + +window.onload = startup; +window.onresize = function(){setTimeout('fontScale()', 50);}</script> +<script type="text/javascript"> +/* ASCIIMathML.js - copyright Peter Jipsen, released under the GPL +See http://www1.chapman.edu/~jipsen/mathml/asciimath.html/ */ + +var checkForMathML = true; // check if browser can display MathML +var notifyIfNoMathML = true; // display note if no MathML capability +var alertIfNoMathML = false; // show alert box if no MathML capability +var mathcolor = "red"; // change it to "" (to inherit) or any other color +var mathfontfamily = "serif"; // change to "" to inherit (works in IE) + // or another family (e.g. "arial") +var displaystyle = true; // puts limits above and below large operators +var showasciiformulaonhover = true; // helps students learn ASCIIMath +var decimalsign = "."; // change to "," if you like, beware of `(1,2)`! +var AMdelimiter1 = "`", AMescape1 = "\\\\`"; // can use other characters +var AMdelimiter2 = "$", AMescape2 = "\\\\\\$", AMdelimiter2regexp = "\\$"; +var doubleblankmathdelimiter = false; // if true, x+1 is equal to `x+1` + // for IE this works only in <!-- --> +//var separatetokens;// has been removed (email me if this is a problem) +var isIE = document.createElementNS==null; + +if (document.getElementById==null) + alert("This webpage requires a recent browser such as\ +\nMozilla/Netscape 7+ or Internet Explorer 6+MathPlayer") + +// all further global variables start with "AM" + +function AMcreateElementXHTML(t) { + if (isIE) return document.createElement(t); + else return document.createElementNS("http://www.w3.org/1999/xhtml",t); +} + +function AMnoMathMLNote() { + var nd = AMcreateElementXHTML("h3"); + nd.setAttribute("align","center") + nd.appendChild(AMcreateElementXHTML("p")); + nd.appendChild(document.createTextNode("To view the ")); + var an = AMcreateElementXHTML("a"); + an.appendChild(document.createTextNode("ASCIIMathML")); + an.setAttribute("href","http://www.chapman.edu/~jipsen/asciimath.html"); + nd.appendChild(an); + nd.appendChild(document.createTextNode(" notation use Internet Explorer 6+")); + an = AMcreateElementXHTML("a"); + an.appendChild(document.createTextNode("MathPlayer")); + an.setAttribute("href","http://www.dessci.com/en/products/mathplayer/download.htm"); + nd.appendChild(an); + nd.appendChild(document.createTextNode(" or Netscape/Mozilla/Firefox")); + nd.appendChild(AMcreateElementXHTML("p")); + return nd; +} + +function AMisMathMLavailable() { + var regex = /KHTML/; /* ASCIIMathML.js - copyright Peter Jipsen, released under the GPL +See http://www1.chapman.edu/~jipsen/mathml/asciimath.html/ */ + if (navigator.appName.slice(0,8)=="Netscape") + if (navigator.appVersion.slice(0,1)>="5" && !regex.test(navigator.userAgent)) return null; + else return AMnoMathMLNote(); + else if (navigator.appName.slice(0,9)=="Microsoft") + try { + var ActiveX = new ActiveXObject("MathPlayer.Factory.1"); + return null; + } catch (e) { + return AMnoMathMLNote(); + } + else return AMnoMathMLNote(); +} + +// character lists for Mozilla/Netscape fonts +var AMcal = [0xEF35,0x212C,0xEF36,0xEF37,0x2130,0x2131,0xEF38,0x210B,0x2110,0xEF39,0xEF3A,0x2112,0x2133,0xEF3B,0xEF3C,0xEF3D,0xEF3E,0x211B,0xEF3F,0xEF40,0xEF41,0xEF42,0xEF43,0xEF44,0xEF45,0xEF46]; +var AMfrk = [0xEF5D,0xEF5E,0x212D,0xEF5F,0xEF60,0xEF61,0xEF62,0x210C,0x2111,0xEF63,0xEF64,0xEF65,0xEF66,0xEF67,0xEF68,0xEF69,0xEF6A,0x211C,0xEF6B,0xEF6C,0xEF6D,0xEF6E,0xEF6F,0xEF70,0xEF71,0x2128]; +var AMbbb = [0xEF8C,0xEF8D,0x2102,0xEF8E,0xEF8F,0xEF90,0xEF91,0x210D,0xEF92,0xEF93,0xEF94,0xEF95,0xEF96,0x2115,0xEF97,0x2119,0x211A,0x211D,0xEF98,0xEF99,0xEF9A,0xEF9B,0xEF9C,0xEF9D,0xEF9E,0x2124]; + +var CONST = 0, UNARY = 1, BINARY = 2, INFIX = 3, LEFTBRACKET = 4, + RIGHTBRACKET = 5, SPACE = 6, UNDEROVER = 7, DEFINITION = 8, + LEFTRIGHT = 9, TEXT = 10; // token types + +var AMsqrt = {input:"sqrt", tag:"msqrt", output:"sqrt", tex:null, ttype:UNARY}, + AMroot = {input:"root", tag:"mroot", output:"root", tex:null, ttype:BINARY}, + AMfrac = {input:"frac", tag:"mfrac", output:"/", tex:null, ttype:BINARY}, + AMdiv = {input:"/", tag:"mfrac", output:"/", tex:null, ttype:INFIX}, + AMover = {input:"stackrel", tag:"mover", output:"stackrel", tex:null, ttype:BINARY}, + AMsub = {input:"_", tag:"msub", output:"_", tex:null, ttype:INFIX}, + AMsup = {input:"^", tag:"msup", output:"^", tex:null, ttype:INFIX}, + AMtext = {input:"text", tag:"mtext", output:"text", tex:null, ttype:TEXT}, + AMmbox = {input:"mbox", tag:"mtext", output:"mbox", tex:null, ttype:TEXT}, + AMquote = {input:"\"", tag:"mtext", output:"mbox", tex:null, ttype:TEXT}; + +var AMsymbols = [ +//some greek symbols +{input:"alpha", tag:"mi", output:"\u03B1", tex:null, ttype:CONST}, +{input:"beta", tag:"mi", output:"\u03B2", tex:null, ttype:CONST}, +{input:"chi", tag:"mi", output:"\u03C7", tex:null, ttype:CONST}, +{input:"delta", tag:"mi", output:"\u03B4", tex:null, ttype:CONST}, +{input:"Delta", tag:"mo", output:"\u0394", tex:null, ttype:CONST}, +{input:"epsi", tag:"mi", output:"\u03B5", tex:"epsilon", ttype:CONST}, +{input:"varepsilon", tag:"mi", output:"\u025B", tex:null, ttype:CONST}, +{input:"eta", tag:"mi", output:"\u03B7", tex:null, ttype:CONST}, +{input:"gamma", tag:"mi", output:"\u03B3", tex:null, ttype:CONST}, +{input:"Gamma", tag:"mo", output:"\u0393", tex:null, ttype:CONST}, +{input:"iota", tag:"mi", output:"\u03B9", tex:null, ttype:CONST}, +{input:"kappa", tag:"mi", output:"\u03BA", tex:null, ttype:CONST}, +{input:"lambda", tag:"mi", output:"\u03BB", tex:null, ttype:CONST}, +{input:"Lambda", tag:"mo", output:"\u039B", tex:null, ttype:CONST}, +{input:"mu", tag:"mi", output:"\u03BC", tex:null, ttype:CONST}, +{input:"nu", tag:"mi", output:"\u03BD", tex:null, ttype:CONST}, +{input:"omega", tag:"mi", output:"\u03C9", tex:null, ttype:CONST}, +{input:"Omega", tag:"mo", output:"\u03A9", tex:null, ttype:CONST}, +{input:"phi", tag:"mi", output:"\u03C6", tex:null, ttype:CONST}, +{input:"varphi", tag:"mi", output:"\u03D5", tex:null, ttype:CONST}, +{input:"Phi", tag:"mo", output:"\u03A6", tex:null, ttype:CONST}, +{input:"pi", tag:"mi", output:"\u03C0", tex:null, ttype:CONST}, +{input:"Pi", tag:"mo", output:"\u03A0", tex:null, ttype:CONST}, +{input:"psi", tag:"mi", output:"\u03C8", tex:null, ttype:CONST}, +{input:"Psi", tag:"mi", output:"\u03A8", tex:null, ttype:CONST}, +{input:"rho", tag:"mi", output:"\u03C1", tex:null, ttype:CONST}, +{input:"sigma", tag:"mi", output:"\u03C3", tex:null, ttype:CONST}, +{input:"Sigma", tag:"mo", output:"\u03A3", tex:null, ttype:CONST}, +{input:"tau", tag:"mi", output:"\u03C4", tex:null, ttype:CONST}, +{input:"theta", tag:"mi", output:"\u03B8", tex:null, ttype:CONST}, +{input:"vartheta", tag:"mi", output:"\u03D1", tex:null, ttype:CONST}, +{input:"Theta", tag:"mo", output:"\u0398", tex:null, ttype:CONST}, +{input:"upsilon", tag:"mi", output:"\u03C5", tex:null, ttype:CONST}, +{input:"xi", tag:"mi", output:"\u03BE", tex:null, ttype:CONST}, +{input:"Xi", tag:"mo", output:"\u039E", tex:null, ttype:CONST}, +{input:"zeta", tag:"mi", output:"\u03B6", tex:null, ttype:CONST}, + +//binary operation symbols +{input:"*", tag:"mo", output:"\u22C5", tex:"cdot", ttype:CONST}, +{input:"**", tag:"mo", output:"\u22C6", tex:"star", ttype:CONST}, +{input:"//", tag:"mo", output:"/", tex:null, ttype:CONST}, +{input:"\\\\", tag:"mo", output:"\\", tex:"backslash", ttype:CONST}, +{input:"setminus", tag:"mo", output:"\\", tex:null, ttype:CONST}, +{input:"xx", tag:"mo", output:"\u00D7", tex:"times", ttype:CONST}, +{input:"-:", tag:"mo", output:"\u00F7", tex:"divide", ttype:CONST}, +{input:"@", tag:"mo", output:"\u2218", tex:"circ", ttype:CONST}, +{input:"o+", tag:"mo", output:"\u2295", tex:"oplus", ttype:CONST}, +{input:"ox", tag:"mo", output:"\u2297", tex:"otimes", ttype:CONST}, +{input:"o.", tag:"mo", output:"\u2299", tex:"odot", ttype:CONST}, +{input:"sum", tag:"mo", output:"\u2211", tex:null, ttype:UNDEROVER}, +{input:"prod", tag:"mo", output:"\u220F", tex:null, ttype:UNDEROVER}, +{input:"^^", tag:"mo", output:"\u2227", tex:"wedge", ttype:CONST}, +{input:"^^^", tag:"mo", output:"\u22C0", tex:"bigwedge", ttype:UNDEROVER}, +{input:"vv", tag:"mo", output:"\u2228", tex:"vee", ttype:CONST}, +{input:"vvv", tag:"mo", output:"\u22C1", tex:"bigvee", ttype:UNDEROVER}, +{input:"nn", tag:"mo", output:"\u2229", tex:"cap", ttype:CONST}, +{input:"nnn", tag:"mo", output:"\u22C2", tex:"bigcap", ttype:UNDEROVER}, +{input:"uu", tag:"mo", output:"\u222A", tex:"cup", ttype:CONST}, +{input:"uuu", tag:"mo", output:"\u22C3", tex:"bigcup", ttype:UNDEROVER}, + +//binary relation symbols +{input:"!=", tag:"mo", output:"\u2260", tex:"ne", ttype:CONST}, +{input:":=", tag:"mo", output:":=", tex:null, ttype:CONST}, +{input:"lt", tag:"mo", output:"<", tex:null, ttype:CONST}, +{input:"<=", tag:"mo", output:"\u2264", tex:"le", ttype:CONST}, +{input:"lt=", tag:"mo", output:"\u2264", tex:"leq", ttype:CONST}, +{input:">=", tag:"mo", output:"\u2265", tex:"ge", ttype:CONST}, +{input:"geq", tag:"mo", output:"\u2265", tex:null, ttype:CONST}, +{input:"-<", tag:"mo", output:"\u227A", tex:"prec", ttype:CONST}, +{input:"-lt", tag:"mo", output:"\u227A", tex:null, ttype:CONST}, +{input:">-", tag:"mo", output:"\u227B", tex:"succ", ttype:CONST}, +{input:"-<=", tag:"mo", output:"\u2AAF", tex:"preceq", ttype:CONST}, +{input:">-=", tag:"mo", output:"\u2AB0", tex:"succeq", ttype:CONST}, +{input:"in", tag:"mo", output:"\u2208", tex:null, ttype:CONST}, +{input:"!in", tag:"mo", output:"\u2209", tex:"notin", ttype:CONST}, +{input:"sub", tag:"mo", output:"\u2282", tex:"subset", ttype:CONST}, +{input:"sup", tag:"mo", output:"\u2283", tex:"supset", ttype:CONST}, +{input:"sube", tag:"mo", output:"\u2286", tex:"subseteq", ttype:CONST}, +{input:"supe", tag:"mo", output:"\u2287", tex:"supseteq", ttype:CONST}, +{input:"-=", tag:"mo", output:"\u2261", tex:"equiv", ttype:CONST}, +{input:"~=", tag:"mo", output:"\u2245", tex:"cong", ttype:CONST}, +{input:"~~", tag:"mo", output:"\u2248", tex:"approx", ttype:CONST}, +{input:"prop", tag:"mo", output:"\u221D", tex:"propto", ttype:CONST}, + +//logical symbols +{input:"and", tag:"mtext", output:"and", tex:null, ttype:SPACE}, +{input:"or", tag:"mtext", output:"or", tex:null, ttype:SPACE}, +{input:"not", tag:"mo", output:"\u00AC", tex:"neg", ttype:CONST}, +{input:"=>", tag:"mo", output:"\u21D2", tex:"implies", ttype:CONST}, +{input:"if", tag:"mo", output:"if", tex:null, ttype:SPACE}, +{input:"<=>", tag:"mo", output:"\u21D4", tex:"iff", ttype:CONST}, +{input:"AA", tag:"mo", output:"\u2200", tex:"forall", ttype:CONST}, +{input:"EE", tag:"mo", output:"\u2203", tex:"exists", ttype:CONST}, +{input:"_|_", tag:"mo", output:"\u22A5", tex:"bot", ttype:CONST}, +{input:"TT", tag:"mo", output:"\u22A4", tex:"top", ttype:CONST}, +{input:"|--", tag:"mo", output:"\u22A2", tex:"vdash", ttype:CONST}, +{input:"|==", tag:"mo", output:"\u22A8", tex:"models", ttype:CONST}, + +//grouping brackets +{input:"(", tag:"mo", output:"(", tex:null, ttype:LEFTBRACKET}, +{input:")", tag:"mo", output:")", tex:null, ttype:RIGHTBRACKET}, +{input:"[", tag:"mo", output:"[", tex:null, ttype:LEFTBRACKET}, +{input:"]", tag:"mo", output:"]", tex:null, ttype:RIGHTBRACKET}, +{input:"{", tag:"mo", output:"{", tex:null, ttype:LEFTBRACKET}, +{input:"}", tag:"mo", output:"}", tex:null, ttype:RIGHTBRACKET}, +{input:"|", tag:"mo", output:"|", tex:null, ttype:LEFTRIGHT}, +//{input:"||", tag:"mo", output:"||", tex:null, ttype:LEFTRIGHT}, +{input:"(:", tag:"mo", output:"\u2329", tex:"langle", ttype:LEFTBRACKET}, +{input:":)", tag:"mo", output:"\u232A", tex:"rangle", ttype:RIGHTBRACKET}, +{input:"<<", tag:"mo", output:"\u2329", tex:null, ttype:LEFTBRACKET}, +{input:">>", tag:"mo", output:"\u232A", tex:null, ttype:RIGHTBRACKET}, +{input:"{:", tag:"mo", output:"{:", tex:null, ttype:LEFTBRACKET, invisible:true}, +{input:":}", tag:"mo", output:":}", tex:null, ttype:RIGHTBRACKET, invisible:true}, + +//miscellaneous symbols +{input:"int", tag:"mo", output:"\u222B", tex:null, ttype:CONST}, +{input:"dx", tag:"mi", output:"{:d x:}", tex:null, ttype:DEFINITION}, +{input:"dy", tag:"mi", output:"{:d y:}", tex:null, ttype:DEFINITION}, +{input:"dz", tag:"mi", output:"{:d z:}", tex:null, ttype:DEFINITION}, +{input:"dt", tag:"mi", output:"{:d t:}", tex:null, ttype:DEFINITION}, +{input:"oint", tag:"mo", output:"\u222E", tex:null, ttype:CONST}, +{input:"del", tag:"mo", output:"\u2202", tex:"partial", ttype:CONST}, +{input:"grad", tag:"mo", output:"\u2207", tex:"nabla", ttype:CONST}, +{input:"+-", tag:"mo", output:"\u00B1", tex:"pm", ttype:CONST}, +{input:"O/", tag:"mo", output:"\u2205", tex:"emptyset", ttype:CONST}, +{input:"oo", tag:"mo", output:"\u221E", tex:"infty", ttype:CONST}, +{input:"aleph", tag:"mo", output:"\u2135", tex:null, ttype:CONST}, +{input:"...", tag:"mo", output:"...", tex:"ldots", ttype:CONST}, +{input:":.", tag:"mo", output:"\u2234", tex:"therefore", ttype:CONST}, +{input:"/_", tag:"mo", output:"\u2220", tex:"angle", ttype:CONST}, +{input:"\\ ", tag:"mo", output:"\u00A0", tex:null, ttype:CONST}, +{input:"quad", tag:"mo", output:"\u00A0\u00A0", tex:null, ttype:CONST}, +{input:"qquad", tag:"mo", output:"\u00A0\u00A0\u00A0\u00A0", tex:null, ttype:CONST}, +{input:"cdots", tag:"mo", output:"\u22EF", tex:null, ttype:CONST}, +{input:"vdots", tag:"mo", output:"\u22EE", tex:null, ttype:CONST}, +{input:"ddots", tag:"mo", output:"\u22F1", tex:null, ttype:CONST}, +{input:"diamond", tag:"mo", output:"\u22C4", tex:null, ttype:CONST}, +{input:"square", tag:"mo", output:"\u25A1", tex:null, ttype:CONST}, +{input:"|__", tag:"mo", output:"\u230A", tex:"lfloor", ttype:CONST}, +{input:"__|", tag:"mo", output:"\u230B", tex:"rfloor", ttype:CONST}, +{input:"|~", tag:"mo", output:"\u2308", tex:"lceiling", ttype:CONST}, +{input:"~|", tag:"mo", output:"\u2309", tex:"rceiling", ttype:CONST}, +{input:"CC", tag:"mo", output:"\u2102", tex:null, ttype:CONST}, +{input:"NN", tag:"mo", output:"\u2115", tex:null, ttype:CONST}, +{input:"QQ", tag:"mo", output:"\u211A", tex:null, ttype:CONST}, +{input:"RR", tag:"mo", output:"\u211D", tex:null, ttype:CONST}, +{input:"ZZ", tag:"mo", output:"\u2124", tex:null, ttype:CONST}, +{input:"f", tag:"mi", output:"f", tex:null, ttype:UNARY, func:true}, +{input:"g", tag:"mi", output:"g", tex:null, ttype:UNARY, func:true}, + +//standard functions +{input:"lim", tag:"mo", output:"lim", tex:null, ttype:UNDEROVER}, +{input:"Lim", tag:"mo", output:"Lim", tex:null, ttype:UNDEROVER}, +{input:"sin", tag:"mo", output:"sin", tex:null, ttype:UNARY, func:true}, +{input:"cos", tag:"mo", output:"cos", tex:null, ttype:UNARY, func:true}, +{input:"tan", tag:"mo", output:"tan", tex:null, ttype:UNARY, func:true}, +{input:"sinh", tag:"mo", output:"sinh", tex:null, ttype:UNARY, func:true}, +{input:"cosh", tag:"mo", output:"cosh", tex:null, ttype:UNARY, func:true}, +{input:"tanh", tag:"mo", output:"tanh", tex:null, ttype:UNARY, func:true}, +{input:"cot", tag:"mo", output:"cot", tex:null, ttype:UNARY, func:true}, +{input:"sec", tag:"mo", output:"sec", tex:null, ttype:UNARY, func:true}, +{input:"csc", tag:"mo", output:"csc", tex:null, ttype:UNARY, func:true}, +{input:"log", tag:"mo", output:"log", tex:null, ttype:UNARY, func:true}, +{input:"ln", tag:"mo", output:"ln", tex:null, ttype:UNARY, func:true}, +{input:"det", tag:"mo", output:"det", tex:null, ttype:UNARY, func:true}, +{input:"dim", tag:"mo", output:"dim", tex:null, ttype:CONST}, +{input:"mod", tag:"mo", output:"mod", tex:null, ttype:CONST}, +{input:"gcd", tag:"mo", output:"gcd", tex:null, ttype:UNARY, func:true}, +{input:"lcm", tag:"mo", output:"lcm", tex:null, ttype:UNARY, func:true}, +{input:"lub", tag:"mo", output:"lub", tex:null, ttype:CONST}, +{input:"glb", tag:"mo", output:"glb", tex:null, ttype:CONST}, +{input:"min", tag:"mo", output:"min", tex:null, ttype:UNDEROVER}, +{input:"max", tag:"mo", output:"max", tex:null, ttype:UNDEROVER}, + +//arrows +{input:"uarr", tag:"mo", output:"\u2191", tex:"uparrow", ttype:CONST}, +{input:"darr", tag:"mo", output:"\u2193", tex:"downarrow", ttype:CONST}, +{input:"rarr", tag:"mo", output:"\u2192", tex:"rightarrow", ttype:CONST}, +{input:"->", tag:"mo", output:"\u2192", tex:"to", ttype:CONST}, +{input:"|->", tag:"mo", output:"\u21A6", tex:"mapsto", ttype:CONST}, +{input:"larr", tag:"mo", output:"\u2190", tex:"leftarrow", ttype:CONST}, +{input:"harr", tag:"mo", output:"\u2194", tex:"leftrightarrow", ttype:CONST}, +{input:"rArr", tag:"mo", output:"\u21D2", tex:"Rightarrow", ttype:CONST}, +{input:"lArr", tag:"mo", output:"\u21D0", tex:"Leftarrow", ttype:CONST}, +{input:"hArr", tag:"mo", output:"\u21D4", tex:"Leftrightarrow", ttype:CONST}, + +//commands with argument +AMsqrt, AMroot, AMfrac, AMdiv, AMover, AMsub, AMsup, +{input:"hat", tag:"mover", output:"\u005E", tex:null, ttype:UNARY, acc:true}, +{input:"bar", tag:"mover", output:"\u00AF", tex:"overline", ttype:UNARY, acc:true}, +{input:"vec", tag:"mover", output:"\u2192", tex:null, ttype:UNARY, acc:true}, +{input:"dot", tag:"mover", output:".", tex:null, ttype:UNARY, acc:true}, +{input:"ddot", tag:"mover", output:"..", tex:null, ttype:UNARY, acc:true}, +{input:"ul", tag:"munder", output:"\u0332", tex:"underline", ttype:UNARY, acc:true}, +AMtext, AMmbox, AMquote, +{input:"bb", tag:"mstyle", atname:"fontweight", atval:"bold", output:"bb", tex:null, ttype:UNARY}, +{input:"mathbf", tag:"mstyle", atname:"fontweight", atval:"bold", output:"mathbf", tex:null, ttype:UNARY}, +{input:"sf", tag:"mstyle", atname:"fontfamily", atval:"sans-serif", output:"sf", tex:null, ttype:UNARY}, +{input:"mathsf", tag:"mstyle", atname:"fontfamily", atval:"sans-serif", output:"mathsf", tex:null, ttype:UNARY}, +{input:"bbb", tag:"mstyle", atname:"mathvariant", atval:"double-struck", output:"bbb", tex:null, ttype:UNARY, codes:AMbbb}, +{input:"mathbb", tag:"mstyle", atname:"mathvariant", atval:"double-struck", output:"mathbb", tex:null, ttype:UNARY, codes:AMbbb}, +{input:"cc", tag:"mstyle", atname:"mathvariant", atval:"script", output:"cc", tex:null, ttype:UNARY, codes:AMcal}, +{input:"mathcal", tag:"mstyle", atname:"mathvariant", atval:"script", output:"mathcal", tex:null, ttype:UNARY, codes:AMcal}, +{input:"tt", tag:"mstyle", atname:"fontfamily", atval:"monospace", output:"tt", tex:null, ttype:UNARY}, +{input:"mathtt", tag:"mstyle", atname:"fontfamily", atval:"monospace", output:"mathtt", tex:null, ttype:UNARY}, +{input:"fr", tag:"mstyle", atname:"mathvariant", atval:"fraktur", output:"fr", tex:null, ttype:UNARY, codes:AMfrk}, +{input:"mathfrak", tag:"mstyle", atname:"mathvariant", atval:"fraktur", output:"mathfrak", tex:null, ttype:UNARY, codes:AMfrk} +]; + +function compareNames(s1,s2) { + if (s1.input > s2.input) return 1 + else return -1; +} + +var AMnames = []; //list of input symbols + +function AMinitSymbols() { + var texsymbols = [], i; + for (i=0; i<AMsymbols.length; i++) + if (AMsymbols[i].tex) + texsymbols[texsymbols.length] = {input:AMsymbols[i].tex, + tag:AMsymbols[i].tag, output:AMsymbols[i].output, ttype:AMsymbols[i].ttype}; + AMsymbols = AMsymbols.concat(texsymbols); + AMsymbols.sort(compareNames); + for (i=0; i<AMsymbols.length; i++) AMnames[i] = AMsymbols[i].input; +} + +var AMmathml = "http://www.w3.org/1998/Math/MathML"; + +function AMcreateElementMathML(t) { + if (isIE) return document.createElement("m:"+t); + else return document.createElementNS(AMmathml,t); +} + +function AMcreateMmlNode(t,frag) { +// var node = AMcreateElementMathML(name); + if (isIE) var node = document.createElement("m:"+t); + else var node = document.createElementNS(AMmathml,t); + node.appendChild(frag); + return node; +} + +function newcommand(oldstr,newstr) { + AMsymbols = AMsymbols.concat([{input:oldstr, tag:"mo", output:newstr, + tex:null, ttype:DEFINITION}]); +} + +function AMremoveCharsAndBlanks(str,n) { +//remove n characters and any following blanks + var st; + if (str.charAt(n)=="\\" && str.charAt(n+1)!="\\" && str.charAt(n+1)!=" ") + st = str.slice(n+1); + else st = str.slice(n); + for (var i=0; i<st.length && st.charCodeAt(i)<=32; i=i+1); + return st.slice(i); +} + +function AMposition(arr, str, n) { +// return position >=n where str appears or would be inserted +// assumes arr is sorted + if (n==0) { + var h,m; + n = -1; + h = arr.length; + while (n+1<h) { + m = (n+h) >> 1; + if (arr[m]<str) n = m; else h = m; + } + return h; + } else + for (var i=n; i<arr.length && arr[i]<str; i++); + return i; // i=arr.length || arr[i]>=str +} + +function AMgetSymbol(str) { +//return maximal initial substring of str that appears in names +//return null if there is none + var k = 0; //new pos + var j = 0; //old pos + var mk; //match pos + var st; + var tagst; + var match = ""; + var more = true; + for (var i=1; i<=str.length && more; i++) { + st = str.slice(0,i); //initial substring of length i + j = k; + k = AMposition(AMnames, st, j); + if (k<AMnames.length && str.slice(0,AMnames[k].length)==AMnames[k]){ + match = AMnames[k]; + mk = k; + i = match.length; + } + more = k<AMnames.length && str.slice(0,AMnames[k].length)>=AMnames[k]; + } + AMpreviousSymbol=AMcurrentSymbol; + if (match!=""){ + AMcurrentSymbol=AMsymbols[mk].ttype; + return AMsymbols[mk]; + } +// if str[0] is a digit or - return maxsubstring of digits.digits + AMcurrentSymbol=CONST; + k = 1; + st = str.slice(0,1); + var integ = true; + while ("0"<=st && st<="9" && k<=str.length) { + st = str.slice(k,k+1); + k++; + } + if (st == decimalsign) { + st = str.slice(k,k+1); + if ("0"<=st && st<="9") { + integ = false; + k++; + while ("0"<=st && st<="9" && k<=str.length) { + st = str.slice(k,k+1); + k++; + } + } + } + if ((integ && k>1) || k>2) { + st = str.slice(0,k-1); + tagst = "mn"; + } else { + k = 2; + st = str.slice(0,1); //take 1 character + tagst = (("A">st || st>"Z") && ("a">st || st>"z")?"mo":"mi"); + } + if (st=="-" && AMpreviousSymbol==INFIX) { + AMcurrentSymbol = INFIX; //trick "/" into recognizing "-" on second parse + return {input:st, tag:tagst, output:st, ttype:UNARY, func:true}; + } + return {input:st, tag:tagst, output:st, ttype:CONST}; +} + +function AMremoveBrackets(node) { + var st; + if (node.nodeName=="mrow") { + st = node.firstChild.firstChild.nodeValue; + if (st=="(" || st=="[" || st=="{") node.removeChild(node.firstChild); + } + if (node.nodeName=="mrow") { + st = node.lastChild.firstChild.nodeValue; + if (st==")" || st=="]" || st=="}") node.removeChild(node.lastChild); + } +} + +/* ASCIIMathML.js - copyright Peter Jipsen, released under the GPL +See http://www1.chapman.edu/~jipsen/mathml/asciimath.html/ */ + +var AMnestingDepth,AMpreviousSymbol,AMcurrentSymbol; + +function AMparseSexpr(str) { //parses str and returns [node,tailstr] + var symbol, node, result, i, st,// rightvert = false, + newFrag = document.createDocumentFragment(); + str = AMremoveCharsAndBlanks(str,0); + symbol = AMgetSymbol(str); //either a token or a bracket or empty + if (symbol == null || symbol.ttype == RIGHTBRACKET && AMnestingDepth > 0) { + return [null,str]; + } + if (symbol.ttype == DEFINITION) { + str = symbol.output+AMremoveCharsAndBlanks(str,symbol.input.length); + symbol = AMgetSymbol(str); + } + switch (symbol.ttype) { + case UNDEROVER: + case CONST: + str = AMremoveCharsAndBlanks(str,symbol.input.length); + return [AMcreateMmlNode(symbol.tag, //its a constant + document.createTextNode(symbol.output)),str]; + case LEFTBRACKET: //read (expr+) + AMnestingDepth++; + str = AMremoveCharsAndBlanks(str,symbol.input.length); + result = AMparseExpr(str,true); + AMnestingDepth--; + if (typeof symbol.invisible == "boolean" && symbol.invisible) + node = AMcreateMmlNode("mrow",result[0]); + else { + node = AMcreateMmlNode("mo",document.createTextNode(symbol.output)); + node = AMcreateMmlNode("mrow",node); + node.appendChild(result[0]); + } + return [node,result[1]]; + case TEXT: + if (symbol!=AMquote) str = AMremoveCharsAndBlanks(str,symbol.input.length); + if (str.charAt(0)=="{") i=str.indexOf("}"); + else if (str.charAt(0)=="(") i=str.indexOf(")"); + else if (str.charAt(0)=="[") i=str.indexOf("]"); + else if (symbol==AMquote) i=str.slice(1).indexOf("\"")+1; + else i = 0; + if (i==-1) i = str.length; + st = str.slice(1,i); + if (st.charAt(0) == " ") { + node = AMcreateElementMathML("mspace"); + node.setAttribute("width","1ex"); + newFrag.appendChild(node); + } + newFrag.appendChild( + AMcreateMmlNode(symbol.tag,document.createTextNode(st))); + if (st.charAt(st.length-1) == " ") { + node = AMcreateElementMathML("mspace"); + node.setAttribute("width","1ex"); + newFrag.appendChild(node); + } + str = AMremoveCharsAndBlanks(str,i+1); + return [AMcreateMmlNode("mrow",newFrag),str]; + case UNARY: + str = AMremoveCharsAndBlanks(str,symbol.input.length); + result = AMparseSexpr(str); + if (result[0]==null) return [AMcreateMmlNode(symbol.tag, + document.createTextNode(symbol.output)),str]; + if (typeof symbol.func == "boolean" && symbol.func) { // functions hack + st = str.charAt(0); + if (st=="^" || st=="_" || st=="/" || st=="|" || st==",") { + return [AMcreateMmlNode(symbol.tag, + document.createTextNode(symbol.output)),str]; + } else { + node = AMcreateMmlNode("mrow", + AMcreateMmlNode(symbol.tag,document.createTextNode(symbol.output))); + node.appendChild(result[0]); + return [node,result[1]]; + } + } + AMremoveBrackets(result[0]); + if (symbol.input == "sqrt") { // sqrt + return [AMcreateMmlNode(symbol.tag,result[0]),result[1]]; + } else if (typeof symbol.acc == "boolean" && symbol.acc) { // accent + node = AMcreateMmlNode(symbol.tag,result[0]); + node.appendChild(AMcreateMmlNode("mo",document.createTextNode(symbol.output))); + return [node,result[1]]; + } else { // font change command + if (!isIE && typeof symbol.codes != "undefined") { + for (i=0; i<result[0].childNodes.length; i++) + if (result[0].childNodes[i].nodeName=="mi" || result[0].nodeName=="mi") { + st = (result[0].nodeName=="mi"?result[0].firstChild.nodeValue: + result[0].childNodes[i].firstChild.nodeValue); + var newst = []; + for (var j=0; j<st.length; j++) + if (st.charCodeAt(j)>64 && st.charCodeAt(j)<91) newst = newst + + String.fromCharCode(symbol.codes[st.charCodeAt(j)-65]); + else newst = newst + st.charAt(j); + if (result[0].nodeName=="mi") + result[0]=AMcreateElementMathML("mo"). + appendChild(document.createTextNode(newst)); + else result[0].replaceChild(AMcreateElementMathML("mo"). + appendChild(document.createTextNode(newst)),result[0].childNodes[i]); + } + } + node = AMcreateMmlNode(symbol.tag,result[0]); + node.setAttribute(symbol.atname,symbol.atval); + return [node,result[1]]; + } + case BINARY: + str = AMremoveCharsAndBlanks(str,symbol.input.length); + result = AMparseSexpr(str); + if (result[0]==null) return [AMcreateMmlNode("mo", + document.createTextNode(symbol.input)),str]; + AMremoveBrackets(result[0]); + var result2 = AMparseSexpr(result[1]); + if (result2[0]==null) return [AMcreateMmlNode("mo", + document.createTextNode(symbol.input)),str]; + AMremoveBrackets(result2[0]); + if (symbol.input=="root" || symbol.input=="stackrel") + newFrag.appendChild(result2[0]); + newFrag.appendChild(result[0]); + if (symbol.input=="frac") newFrag.appendChild(result2[0]); + return [AMcreateMmlNode(symbol.tag,newFrag),result2[1]]; + case INFIX: + str = AMremoveCharsAndBlanks(str,symbol.input.length); + return [AMcreateMmlNode("mo",document.createTextNode(symbol.output)),str]; + case SPACE: + str = AMremoveCharsAndBlanks(str,symbol.input.length); + node = AMcreateElementMathML("mspace"); + node.setAttribute("width","1ex"); + newFrag.appendChild(node); + newFrag.appendChild( + AMcreateMmlNode(symbol.tag,document.createTextNode(symbol.output))); + node = AMcreateElementMathML("mspace"); + node.setAttribute("width","1ex"); + newFrag.appendChild(node); + return [AMcreateMmlNode("mrow",newFrag),str]; + case LEFTRIGHT: +// if (rightvert) return [null,str]; else rightvert = true; + AMnestingDepth++; + str = AMremoveCharsAndBlanks(str,symbol.input.length); + result = AMparseExpr(str,false); + AMnestingDepth--; + var st = ""; + if (result[0].lastChild!=null) + st = result[0].lastChild.firstChild.nodeValue; + if (st == "|") { // its an absolute value subterm + node = AMcreateMmlNode("mo",document.createTextNode(symbol.output)); + node = AMcreateMmlNode("mrow",node); + node.appendChild(result[0]); + return [node,result[1]]; + } else { // the "|" is a \mid + node = AMcreateMmlNode("mo",document.createTextNode(symbol.output)); + node = AMcreateMmlNode("mrow",node); + return [node,str]; + } + default: +//alert("default"); + str = AMremoveCharsAndBlanks(str,symbol.input.length); + return [AMcreateMmlNode(symbol.tag, //its a constant + document.createTextNode(symbol.output)),str]; + } +} + +function AMparseIexpr(str) { + var symbol, sym1, sym2, node, result, underover; + str = AMremoveCharsAndBlanks(str,0); + sym1 = AMgetSymbol(str); + result = AMparseSexpr(str); + node = result[0]; + str = result[1]; + symbol = AMgetSymbol(str); + if (symbol.ttype == INFIX && symbol.input != "/") { + str = AMremoveCharsAndBlanks(str,symbol.input.length); +// if (symbol.input == "/") result = AMparseIexpr(str); else ... + result = AMparseSexpr(str); + if (result[0] == null) // show box in place of missing argument + result[0] = AMcreateMmlNode("mo",document.createTextNode("\u25A1")); + else AMremoveBrackets(result[0]); + str = result[1]; +// if (symbol.input == "/") AMremoveBrackets(node); + if (symbol.input == "_") { + sym2 = AMgetSymbol(str); + underover = (sym1.ttype == UNDEROVER); + if (sym2.input == "^") { + str = AMremoveCharsAndBlanks(str,sym2.input.length); + var res2 = AMparseSexpr(str); + AMremoveBrackets(res2[0]); + str = res2[1]; + node = AMcreateMmlNode((underover?"munderover":"msubsup"),node); + node.appendChild(result[0]); + node.appendChild(res2[0]); + node = AMcreateMmlNode("mrow",node); // so sum does not stretch + } else { + node = AMcreateMmlNode((underover?"munder":"msub"),node); + node.appendChild(result[0]); + } + } else { + node = AMcreateMmlNode(symbol.tag,node); + node.appendChild(result[0]); + } + } + return [node,str]; +} + +function AMparseExpr(str,rightbracket) { + var symbol, node, result, i, nodeList = [], + newFrag = document.createDocumentFragment(); + do { + str = AMremoveCharsAndBlanks(str,0); + result = AMparseIexpr(str); + node = result[0]; + str = result[1]; + symbol = AMgetSymbol(str); + if (symbol.ttype == INFIX && symbol.input == "/") { + str = AMremoveCharsAndBlanks(str,symbol.input.length); + result = AMparseIexpr(str); + if (result[0] == null) // show box in place of missing argument + result[0] = AMcreateMmlNode("mo",document.createTextNode("\u25A1")); + else AMremoveBrackets(result[0]); + str = result[1]; + AMremoveBrackets(node); + node = AMcreateMmlNode(symbol.tag,node); + node.appendChild(result[0]); + newFrag.appendChild(node); + symbol = AMgetSymbol(str); + } + else if (node!=undefined) newFrag.appendChild(node); + } while ((symbol.ttype != RIGHTBRACKET && + (symbol.ttype != LEFTRIGHT || rightbracket) + || AMnestingDepth == 0) && symbol!=null && symbol.output!=""); + if (symbol.ttype == RIGHTBRACKET || symbol.ttype == LEFTRIGHT) { +// if (AMnestingDepth > 0) AMnestingDepth--; + var len = newFrag.childNodes.length; + if (len>0 && newFrag.childNodes[len-1].nodeName == "mrow" && len>1 && + newFrag.childNodes[len-2].nodeName == "mo" && + newFrag.childNodes[len-2].firstChild.nodeValue == ",") { //matrix + var right = newFrag.childNodes[len-1].lastChild.firstChild.nodeValue; + if (right==")" || right=="]") { + var left = newFrag.childNodes[len-1].firstChild.firstChild.nodeValue; + if (left=="(" && right==")" && symbol.output != "}" || + left=="[" && right=="]") { + var pos = []; // positions of commas + var matrix = true; + var m = newFrag.childNodes.length; + for (i=0; matrix && i<m; i=i+2) { + pos[i] = []; + node = newFrag.childNodes[i]; + if (matrix) matrix = node.nodeName=="mrow" && + (i==m-1 || node.nextSibling.nodeName=="mo" && + node.nextSibling.firstChild.nodeValue==",")&& + node.firstChild.firstChild.nodeValue==left && + node.lastChild.firstChild.nodeValue==right; + if (matrix) + for (var j=0; j<node.childNodes.length; j++) + if (node.childNodes[j].firstChild.nodeValue==",") + pos[i][pos[i].length]=j; + if (matrix && i>1) matrix = pos[i].length == pos[i-2].length; + } + if (matrix) { + var row, frag, n, k, table = document.createDocumentFragment(); + for (i=0; i<m; i=i+2) { + row = document.createDocumentFragment(); + frag = document.createDocumentFragment(); + node = newFrag.firstChild; // <mrow>(-,-,...,-,-)</mrow> + n = node.childNodes.length; + k = 0; + node.removeChild(node.firstChild); //remove ( + for (j=1; j<n-1; j++) { + if (typeof pos[i][k] != "undefined" && j==pos[i][k]){ + node.removeChild(node.firstChild); //remove , + row.appendChild(AMcreateMmlNode("mtd",frag)); + k++; + } else frag.appendChild(node.firstChild); + } + row.appendChild(AMcreateMmlNode("mtd",frag)); + if (newFrag.childNodes.length>2) { + newFrag.removeChild(newFrag.firstChild); //remove <mrow>)</mrow> + newFrag.removeChild(newFrag.firstChild); //remove <mo>,</mo> + } + table.appendChild(AMcreateMmlNode("mtr",row)); + } + node = AMcreateMmlNode("mtable",table); + if (typeof symbol.invisible == "boolean" && symbol.invisible) node.setAttribute("columnalign","left"); + newFrag.replaceChild(node,newFrag.firstChild); + } + } + } + } + str = AMremoveCharsAndBlanks(str,symbol.input.length); + if (typeof symbol.invisible != "boolean" || !symbol.invisible) { + node = AMcreateMmlNode("mo",document.createTextNode(symbol.output)); + newFrag.appendChild(node); + } + } + return [newFrag,str]; +} + +function AMparseMath(str) { + var result, node = AMcreateElementMathML("mstyle"); + if (mathcolor != "") node.setAttribute("mathcolor",mathcolor); + if (displaystyle) node.setAttribute("displaystyle","true"); + if (mathfontfamily != "") node.setAttribute("fontfamily",mathfontfamily); + AMnestingDepth = 0; + node.appendChild(AMparseExpr(str.replace(/^\s+/g,""),false)[0]); + node = AMcreateMmlNode("math",node); + if (showasciiformulaonhover) //fixed by djhsu so newline + node.setAttribute("title",str.replace(/\s+/g," "));//does not show in Gecko + if (mathfontfamily != "" && (isIE || mathfontfamily != "serif")) { + var fnode = AMcreateElementXHTML("font"); + fnode.setAttribute("face",mathfontfamily); + fnode.appendChild(node); + return fnode; + } + return node; +} + +function AMstrarr2docFrag(arr, linebreaks) { + var newFrag=document.createDocumentFragment(); + var expr = false; + for (var i=0; i<arr.length; i++) { + if (expr) newFrag.appendChild(AMparseMath(arr[i])); + else { + var arri = (linebreaks ? arr[i].split("\n\n") : [arr[i]]); + newFrag.appendChild(AMcreateElementXHTML("span"). + appendChild(document.createTextNode(arri[0]))); + for (var j=1; j<arri.length; j++) { + newFrag.appendChild(AMcreateElementXHTML("p")); + newFrag.appendChild(AMcreateElementXHTML("span"). + appendChild(document.createTextNode(arri[j]))); + } + } + expr = !expr; + } + return newFrag; +} + +function AMprocessNodeR(n, linebreaks) { + var mtch, str, arr, frg, i; + if (n.childNodes.length == 0) { + if ((n.nodeType!=8 || linebreaks) && + n.parentNode.nodeName!="form" && n.parentNode.nodeName!="FORM" && + n.parentNode.nodeName!="textarea" && n.parentNode.nodeName!="TEXTAREA" && + n.parentNode.nodeName!="code" && n.parentNode.nodeName!="CODE" && /* ASCIIMathML.js - copyright Peter Jipsen, released under the GPL +See http://www1.chapman.edu/~jipsen/mathml/asciimath.html/ */ + n.parentNode.nodeName!="pre" && n.parentNode.nodeName!="PRE") { + str = n.nodeValue; + if (!(str == null)) { + str = str.replace(/\r\n\r\n/g,"\n\n"); + if (doubleblankmathdelimiter) { + str = str.replace(/\x20\x20\./g," "+AMdelimiter1+"."); + str = str.replace(/\x20\x20,/g," "+AMdelimiter1+","); + str = str.replace(/\x20\x20/g," "+AMdelimiter1+" "); + } + str = str.replace(/\x20+/g," "); + str = str.replace(/\s*\r\n/g," "); + mtch = false; + str = str.replace(new RegExp(AMescape2, "g"), + function(st){mtch=true;return "AMescape2"}); + str = str.replace(new RegExp(AMescape1, "g"), + function(st){mtch=true;return "AMescape1"}); + str = str.replace(new RegExp(AMdelimiter2regexp, "g"),AMdelimiter1); + arr = str.split(AMdelimiter1); + for (i=0; i<arr.length; i++) + arr[i]=arr[i].replace(/AMescape2/g,AMdelimiter2). + replace(/AMescape1/g,AMdelimiter1); + if (arr.length>1 || mtch) { + if (checkForMathML) { + checkForMathML = false; + var nd = AMisMathMLavailable(); + AMnoMathML = nd != null; + if (AMnoMathML && notifyIfNoMathML) + if (alertIfNoMathML) + alert("To view the ASCIIMathML notation use Internet Explorer 6 +\nMathPlayer (free from www.dessci.com)\n\ + or Firefox/Mozilla/Netscape"); + else AMbody.insertBefore(nd,AMbody.childNodes[0]); + } + if (!AMnoMathML) { + frg = AMstrarr2docFrag(arr,n.nodeType==8); + var len = frg.childNodes.length; + n.parentNode.replaceChild(frg,n); + return len-1; + } else return 0; + } + } + } else return 0; + } else if (n.nodeName!="math") { + for (i=0; i<n.childNodes.length; i++) + i += AMprocessNodeR(n.childNodes[i], linebreaks); + } + return 0; +} + +function AMprocessNode(n, linebreaks, spanclassAM) { + var frag,st; + if (spanclassAM!=null) { + frag = document.getElementsByTagName("span") + for (var i=0;i<frag.length;i++) + if (frag[i].className == "AM") + AMprocessNodeR(frag[i],linebreaks); + } else { + try { + st = n.innerHTML; + } catch(err) {} + if (st==null || + st.indexOf(AMdelimiter1)!=-1 || st.indexOf(AMdelimiter2)!=-1) + AMprocessNodeR(n,linebreaks); + } + if (isIE) { //needed to match size and font of formula to surrounding text + frag = document.getElementsByTagName('math'); + for (var i=0;i<frag.length;i++) frag[i].update() + } +} + +var AMbody; +var AMnoMathML = false, AMtranslated = false; + +function translate(spanclassAM) { + if (!AMtranslated) { // run this only once + AMtranslated = true; + AMinitSymbols(); + AMbody = document.getElementsByTagName("body")[0]; + AMprocessNode(AMbody, false, spanclassAM); + } +} + +if (isIE) { // avoid adding MathPlayer info explicitly to each webpage + document.write("<object id=\"mathplayer\"\ + classid=\"clsid:32F66A20-7614-11D4-BD11-00104BD3F987\"></object>"); + document.write("<?import namespace=\"m\" implementation=\"#mathplayer\"?>"); +} + +// GO1.1 Generic onload by Brothercake +// http://www.brothercake.com/ +//onload function (replaces the onload="translate()" in the <body> tag) +function generic() +{ + translate(); +}; +//setup onload function +if(typeof window.addEventListener != 'undefined') +{ + //.. gecko, safari, konqueror and standard + window.addEventListener('load', generic, false); +} +else if(typeof document.addEventListener != 'undefined') +{ + //.. opera 7 + document.addEventListener('load', generic, false); +} +else if(typeof window.attachEvent != 'undefined') +{ + //.. win/ie + window.attachEvent('onload', generic); +} +//** remove this condition to degrade older browsers +else +{ + //.. mac/ie5 and anything else that gets this far + //if there's an existing onload function + if(typeof window.onload == 'function') + { + //store it + var existing = onload; + //add new onload handler + window.onload = function() + { + //call existing onload function + existing(); + //call generic onload function + generic(); + }; + } + else + { + //setup onload function + window.onload = generic; + } +} +</script> +<meta name="author" content="Sam Smith, Jen Jones" /> +<meta name="date" content="July 15, 2006" /> +<title>My S5 Document</title> +</head> +<body> +<div class="layout"> +<div id="controls"></div> +<div id="currentSlide"></div> +<div id="header"></div> +<div id="footer"> +<h1>July 15, 2006</h1> +<h2>My S5 Document</h2> +</div> +</div> +<div class="presentation"> + +<div class="slide"> +<h1>My S5 Document</h1> +<h3>Sam Smith, Jen Jones</h3> +<h4>July 15, 2006</h4> +</div> +<div class="slide"> +<h1>First slide</h1> +<ul class="incremental"> +<li>first bullet</li> +<li>second bullet</li> +</ul> +</div> +<div class="slide"> +<h1>Smarty</h1> +<ul> +<li>“Hello there”</li> +<li>Here’s a—dash</li> +<li>And ‘ellipses’…</li> +</ul> +</div> +<div class="slide"> +<h1>Math</h1> +<ul class="incremental"> +<li>$\frac{d}{dx}f(x)=\lim_{h\to 0}\frac{f(x+h)-f(x)}{h}$</li> +</ul> +</div> +</div> +</body> +</html> + diff --git a/tests/s5.fragment.html b/tests/s5.fragment.html new file mode 100644 index 000000000..d77c484dc --- /dev/null +++ b/tests/s5.fragment.html @@ -0,0 +1,18 @@ +<h1>First slide</h1> +<ul> +<li>first bullet</li> +<li>second bullet</li> +</ul> +<h1>Smarty</h1> +<blockquote> +<ul> +<li>"Hello there"</li> +<li>Here's a -- dash</li> +<li>And 'ellipses'...</li> +</ul> +</blockquote> +<h1>Math</h1> +<ul> +<li>$\frac{d}{dx}f(x)=\lim_{h\to 0}\frac{f(x+h)-f(x)}{h}$</li> +</ul> + diff --git a/tests/s5.inserts.html b/tests/s5.inserts.html new file mode 100644 index 000000000..7ebdf23e4 --- /dev/null +++ b/tests/s5.inserts.html @@ -0,0 +1,41 @@ +<!DOCTYPE HTML PUBLIC "-//W3C//DTD HTML 4.01 Transitional//EN" + "http://www.w3.org/TR/html4/loose.dtd"> +<html> +<head> +<meta http-equiv="Content-Type" content="text/html; charset=UTF-8" /> +<meta name="generator" content="pandoc" /> +<style type="text/css"> +div.pandocNote { border-left: 1px solid grey; padding-left: 1em; } +span.pandocNoteRef { vertical-align: super; font-size: 80%; } +span.pandocNoteMarker { } +</style> +<link rel="stylesheet" href="main.css" type="text/css" media="all" /> +STUFF INSERTED +<meta name="author" content="Sam Smith, Jen Jones" /> +<meta name="date" content="July 15, 2006" /> +<title>My S5 Document</title> +</head> +<body> +STUFF INSERTED +<h1 class="title">My S5 Document</h1> +<h1>First slide</h1> +<ul> +<li>first bullet</li> +<li>second bullet</li> +</ul> +<h1>Smarty</h1> +<blockquote> +<ul> +<li>"Hello there"</li> +<li>Here's a -- dash</li> +<li>And 'ellipses'...</li> +</ul> +</blockquote> +<h1>Math</h1> +<ul> +<li>$\frac{d}{dx}f(x)=\lim_{h\to 0}\frac{f(x+h)-f(x)}{h}$</li> +</ul> +STUFF INSERTED +</body> +</html> + diff --git a/tests/s5.native b/tests/s5.native new file mode 100644 index 000000000..154011f68 --- /dev/null +++ b/tests/s5.native @@ -0,0 +1,15 @@ +Pandoc (Meta [Str "My",Space,Str "S5",Space,Str "Document"] ["Sam Smith","Jen Jones"] "July 15, 2006") +[ Header 1 [Str "First",Space,Str "slide"] +, BulletList + [ [ Plain [Str "first",Space,Str "bullet"] ] + , [ Plain [Str "second",Space,Str "bullet"] ] ] +, Header 1 [Str "Smarty"] +, BlockQuote + [ BulletList + [ [ Plain [Str "\"Hello",Space,Str "there\""] ] + , [ Plain [Str "Here's",Space,Str "a",Space,Str "--",Space,Str "dash"] ] + , [ Plain [Str "And",Space,Str "'ellipses'..."] ] ] ] +, Header 1 [Str "Math"] +, BulletList + [ [ Plain [TeX "$\\frac{d}{dx}f(x)=\\lim_{h\\to 0}\\frac{f(x+h)-f(x)}{h}$"] ] + ] ] diff --git a/tests/testsuite.native b/tests/testsuite.native new file mode 100644 index 000000000..8ec543e89 --- /dev/null +++ b/tests/testsuite.native @@ -0,0 +1,329 @@ +Pandoc (Meta [Str "Pandoc",Space,Str "Test",Space,Str "Suite"] ["John MacFarlane","Anonymous"] "July 17, 2006") +[ Para [Str "This",Space,Str "is",Space,Str "a",Space,Str "set",Space,Str "of",Space,Str "tests",Space,Str "for",Space,Str "pandoc.",Space,Str "Most",Space,Str "of",Space,Str "them",Space,Str "are",Space,Str "adapted",Space,Str "from",Space,Str "John",Space,Str "Gruber's",Space,Str "markdown",Space,Str "test",Space,Str "suite."] +, HorizontalRule +, Header 1 [Str "Headers"] +, Header 2 [Str "Level",Space,Str "2",Space,Str "with",Space,Str "an",Space,Link [Str "embedded",Space,Str "link"] (Src "/url" "")] +, Header 3 [Str "Level",Space,Str "3",Space,Str "with",Space,Emph [Str "emphasis"]] +, Header 4 [Str "Level",Space,Str "4"] +, Header 5 [Str "Level",Space,Str "5"] +, Header 1 [Str "Level",Space,Str "1"] +, Header 2 [Str "Level",Space,Str "2",Space,Str "with",Space,Emph [Str "emphasis"]] +, Header 3 [Str "Level",Space,Str "3"] +, Para [Str "with",Space,Str "no",Space,Str "blank",Space,Str "line"] +, Header 2 [Str "Level",Space,Str "2"] +, Para [Str "with",Space,Str "no",Space,Str "blank",Space,Str "line"] +, HorizontalRule +, Header 1 [Str "Paragraphs"] +, Para [Str "Here's",Space,Str "a",Space,Str "regular",Space,Str "paragraph."] +, Para [Str "In",Space,Str "Markdown",Space,Str "1.0.0",Space,Str "and",Space,Str "earlier.",Space,Str "Version",Space,Str "8.",Space,Str "This",Space,Str "line",Space,Str "turns",Space,Str "into",Space,Str "a",Space,Str "list",Space,Str "item.",Space,Str "Because",Space,Str "a",Space,Str "hard",Str "-",Str "wrapped",Space,Str "line",Space,Str "in",Space,Str "the",Space,Str "middle",Space,Str "of",Space,Str "a",Space,Str "paragraph",Space,Str "looked",Space,Str "like",Space,Str "a",Space,Str "list",Space,Str "item."] +, Para [Str "Here's",Space,Str "one",Space,Str "with",Space,Str "a",Space,Str "bullet.",Space,Str "*",Space,Str "criminey."] +, Para [Str "There",Space,Str "should",Space,Str "be",Space,Str "a",Space,Str "hard",Space,Str "line",Space,Str "break",LineBreak,Str "here."] +, HorizontalRule +, Header 1 [Str "Block",Space,Str "Quotes"] +, Para [Str "E",Str "-",Str "mail",Space,Str "style:"] +, BlockQuote + [ Para [Str "This",Space,Str "is",Space,Str "a",Space,Str "block",Space,Str "quote.",Space,Str "It",Space,Str "is",Space,Str "pretty",Space,Str "short."] ] + +, BlockQuote + [ Para [Str "Code",Space,Str "in",Space,Str "a",Space,Str "block",Space,Str "quote:"] + , CodeBlock "sub status {\n print \"working\";\n}\n" + , Para [Str "A",Space,Str "list:"] + , OrderedList + [ [ Plain [Str "item",Space,Str "one"] ] + , [ Plain [Str "item",Space,Str "two"] ] ] + , Para [Str "Nested",Space,Str "block",Space,Str "quotes:"] + , BlockQuote + [ Para [Str "nested"] ] + + , BlockQuote + [ Para [Str "nested"] ] + ] +, Para [Str "This",Space,Str "should",Space,Str "not",Space,Str "be",Space,Str "a",Space,Str "block",Space,Str "quote:",Space,Str "2",Space,Str ">",Space,Str "1."] +, Para [Str "Box",Str "-",Str "style:"] +, BlockQuote + [ Para [Str "Example:"] + , CodeBlock "sub status {\n print \"working\";\n}\n" ] +, BlockQuote + [ OrderedList + [ [ Plain [Str "do",Space,Str "laundry"] ] + , [ Plain [Str "take",Space,Str "out",Space,Str "the",Space,Str "trash"] ] ] ] +, Para [Str "Here's",Space,Str "a",Space,Str "nested",Space,Str "one:"] +, BlockQuote + [ Para [Str "Joe",Space,Str "said:"] + , BlockQuote + [ Para [Str "Don't",Space,Str "quote",Space,Str "me."] ] + ] +, Para [Str "And",Space,Str "a",Space,Str "following",Space,Str "paragraph."] +, HorizontalRule +, Header 1 [Str "Code",Space,Str "Blocks"] +, Para [Str "Code:"] +, CodeBlock "---- (should be four hyphens)\n\nsub status {\n print \"working\";\n}\n\nthis code block is indented by one tab\n" +, Para [Str "And:"] +, CodeBlock " this code block is indented by two tabs\n\nThese should not be escaped: \\$ \\\\ \\> \\[ \\{\n" +, HorizontalRule +, Header 1 [Str "Lists"] +, Header 2 [Str "Unordered"] +, Para [Str "Asterisks",Space,Str "tight:"] +, BulletList + [ [ Plain [Str "asterisk",Space,Str "1"] ] + , [ Plain [Str "asterisk",Space,Str "2"] ] + , [ Plain [Str "asterisk",Space,Str "3"] ] ] +, Para [Str "Asterisks",Space,Str "loose:"] +, BulletList + [ [ Para [Str "asterisk",Space,Str "1"] ] + , [ Para [Str "asterisk",Space,Str "2"] ] + , [ Para [Str "asterisk",Space,Str "3"] ] ] +, Para [Str "Pluses",Space,Str "tight:"] +, BulletList + [ [ Plain [Str "Plus",Space,Str "1"] ] + , [ Plain [Str "Plus",Space,Str "2"] ] + , [ Plain [Str "Plus",Space,Str "3"] ] ] +, Para [Str "Pluses",Space,Str "loose:"] +, BulletList + [ [ Para [Str "Plus",Space,Str "1"] ] + , [ Para [Str "Plus",Space,Str "2"] ] + , [ Para [Str "Plus",Space,Str "3"] ] ] +, Para [Str "Minuses",Space,Str "tight:"] +, BulletList + [ [ Plain [Str "Minus",Space,Str "1"] ] + , [ Plain [Str "Minus",Space,Str "2"] ] + , [ Plain [Str "Minus",Space,Str "3"] ] ] +, Para [Str "Minuses",Space,Str "loose:"] +, BulletList + [ [ Para [Str "Minus",Space,Str "1"] ] + , [ Para [Str "Minus",Space,Str "2"] ] + , [ Para [Str "Minus",Space,Str "3"] ] ] +, Header 2 [Str "Ordered"] +, Para [Str "Tight:"] +, OrderedList + [ [ Plain [Str "First"] ] + , [ Plain [Str "Second"] ] + , [ Plain [Str "Third"] ] ] +, Para [Str "and:"] +, OrderedList + [ [ Plain [Str "One"] ] + , [ Plain [Str "Two"] ] + , [ Plain [Str "Three"] ] ] +, Para [Str "Loose",Space,Str "using",Space,Str "tabs:"] +, OrderedList + [ [ Para [Str "First"] ] + , [ Para [Str "Second"] ] + , [ Para [Str "Third"] ] ] +, Para [Str "and",Space,Str "using",Space,Str "spaces:"] +, OrderedList + [ [ Para [Str "One"] ] + , [ Para [Str "Two"] ] + , [ Para [Str "Three"] ] ] +, Para [Str "Multiple",Space,Str "paragraphs:"] +, OrderedList + [ [ Para [Str "Item",Space,Str "1,",Space,Str "graf",Space,Str "one."] + , Para [Str "Item",Space,Str "1.",Space,Str "graf",Space,Str "two.",Space,Str "The",Space,Str "quick",Space,Str "brown",Space,Str "fox",Space,Str "jumped",Space,Str "over",Space,Str "the",Space,Str "lazy",Space,Str "dog's",Space,Str "back."] ], [ Para [Str "Item",Space,Str "2."] ] + , [ Para [Str "Item",Space,Str "3."] ] ] +, Header 2 [Str "Nested"] +, BulletList + [ [ Plain [Str "Tab"] + , BulletList + [ [ Plain [Str "Tab"] + , BulletList + [ [ Plain [Str "Tab"] ] + ] ] ] ] ] +, Para [Str "Here's",Space,Str "another:"] +, OrderedList + [ [ Plain [Str "First"] ] + , [ Plain [Str "Second:"] + , BulletList + [ [ Plain [Str "Fee"] ] + , [ Plain [Str "Fie"] ] + , [ Plain [Str "Foe"] ] ] ], [ Plain [Str "Third"] ] ] +, Para [Str "Same",Space,Str "thing",Space,Str "but",Space,Str "with",Space,Str "paragraphs:"] +, OrderedList + [ [ Para [Str "First"] ] + , [ Para [Str "Second:"] + , BulletList + [ [ Plain [Str "Fee"] ] + , [ Plain [Str "Fie"] ] + , [ Plain [Str "Foe"] ] ] ], [ Para [Str "Third"] ] ] +, Header 2 [Str "Tabs",Space,Str "and",Space,Str "spaces"] +, BulletList + [ [ Para [Str "this",Space,Str "is",Space,Str "a",Space,Str "list",Space,Str "item",Space,Str "indented",Space,Str "with",Space,Str "tabs"] ] + , [ Para [Str "this",Space,Str "is",Space,Str "a",Space,Str "list",Space,Str "item",Space,Str "indented",Space,Str "with",Space,Str "spaces"] + , BulletList + [ [ Para [Str "this",Space,Str "is",Space,Str "an",Space,Str "example",Space,Str "list",Space,Str "item",Space,Str "indented",Space,Str "with",Space,Str "tabs"] ] + , [ Para [Str "this",Space,Str "is",Space,Str "an",Space,Str "example",Space,Str "list",Space,Str "item",Space,Str "indented",Space,Str "with",Space,Str "spaces"] ] ] ] ] +, HorizontalRule +, Header 1 [Str "HTML",Space,Str "Blocks"] +, Para [Str "Simple",Space,Str "block",Space,Str "on",Space,Str "one",Space,Str "line:"] +, RawHtml "<div>" +, Plain [Str "foo"] +, RawHtml "</div>\n" +, Para [Str "And",Space,Str "nested",Space,Str "without",Space,Str "indentation:"] +, RawHtml "<div>\n<div>\n<div>" +, Plain [Str "foo"] +, RawHtml "</div>\n</div>\n<div>" +, Plain [Str "bar"] +, RawHtml "</div>\n</div>\n" +, Para [Str "Interpreted",Space,Str "markdown",Space,Str "in",Space,Str "a",Space,Str "table:"] +, RawHtml "<table>\n<tr>\n<td>" +, Plain [Str "This",Space,Str "is",Space,Emph [Str "emphasized"]] +, RawHtml "</td>\n<td>" +, Plain [Str "And",Space,Str "this",Space,Str "is",Space,Strong [Str "strong"]] +, RawHtml "</td>\n</tr>\n</table>\n\n<script type=\"text/javascript\">document.write('This *should not* be interpreted as markdown');</script>\n" +, Para [Str "Here's",Space,Str "a",Space,Str "simple",Space,Str "block:"] +, RawHtml "<div>\n " +, Plain [Str "foo"] +, RawHtml "</div>\n" +, Para [Str "This",Space,Str "should",Space,Str "be",Space,Str "a",Space,Str "code",Space,Str "block,",Space,Str "though:"] +, CodeBlock "<div>\n foo\n</div>\n" +, Para [Str "As",Space,Str "should",Space,Str "this:"] +, CodeBlock "<div>foo</div>\n" +, Para [Str "Now,",Space,Str "nested:"] +, RawHtml "<div>\n <div>\n <div>\n " +, Plain [Str "foo"] +, RawHtml "</div>\n </div>\n</div>\n" +, Para [Str "This",Space,Str "should",Space,Str "just",Space,Str "be",Space,Str "an",Space,Str "HTML",Space,Str "comment:"] +, RawHtml "<!-- Comment -->\n" +, Para [Str "Multiline:"] +, RawHtml "<!--\nBlah\nBlah\n-->\n\n<!--\n This is another comment.\n-->\n" +, Para [Str "Code",Space,Str "block:"] +, CodeBlock "<!-- Comment -->\n" +, Para [Str "Just",Space,Str "plain",Space,Str "comment,",Space,Str "with",Space,Str "trailing",Space,Str "spaces",Space,Str "on",Space,Str "the",Space,Str "line:"] +, RawHtml "<!-- foo --> \n" +, Para [Str "Code:"] +, CodeBlock "<hr />\n" +, Para [Str "Hr's:"] +, RawHtml "<hr>\n\n<hr />\n\n<hr />\n\n<hr> \n\n<hr /> \n\n<hr /> \n\n<hr class=\"foo\" id=\"bar\" />\n\n<hr class=\"foo\" id=\"bar\" />\n\n<hr class=\"foo\" id=\"bar\">\n" +, HorizontalRule +, Header 1 [Str "Inline",Space,Str "Markup"] +, Para [Str "This",Space,Str "is",Space,Emph [Str "emphasized"],Str ",",Space,Str "and",Space,Str "so",Space,Emph [Str "is",Space,Str "this"],Str "."] +, Para [Str "This",Space,Str "is",Space,Strong [Str "strong"],Str ",",Space,Str "and",Space,Str "so",Space,Strong [Str "is",Space,Str "this"],Str "."] +, Para [Str "An",Space,Emph [Link [Str "emphasized",Space,Str "link"] (Src "/url" "")],Str "."] +, Para [Strong [Emph [Str "This",Space,Str "is",Space,Str "strong",Space,Str "and",Space,Str "em."]]] +, Para [Str "So",Space,Str "is",Space,Strong [Emph [Str "this"]],Space,Str "word."] +, Para [Strong [Emph [Str "This",Space,Str "is",Space,Str "strong",Space,Str "and",Space,Str "em."]]] +, Para [Str "So",Space,Str "is",Space,Strong [Emph [Str "this"]],Space,Str "word."] +, Para [Str "This",Space,Str "is",Space,Str "code:",Space,Code ">",Str ",",Space,Code "$",Str ",",Space,Code "\\",Str ",",Space,Code "\\$",Str ",",Space,Code "<html>",Str "."] +, HorizontalRule +, Header 1 [Str "Smart",Space,Str "quotes,",Space,Str "ellipses,",Space,Str "dashes"] +, Para [Str "\"Hello,\"",Space,Str "said",Space,Str "the",Space,Str "spider.",Space,Str "\"'Shelob'",Space,Str "is",Space,Str "my",Space,Str "name.\""] +, Para [Str "'A',",Space,Str "'B',",Space,Str "and",Space,Str "'C'",Space,Str "are",Space,Str "letters."] +, Para [Str "'Oak,'",Space,Str "'elm,'",Space,Str "and",Space,Str "'beech'",Space,Str "are",Space,Str "names",Space,Str "of",Space,Str "trees.",Space,Str "So",Space,Str "is",Space,Str "'pine.'"] +, Para [Str "'He",Space,Str "said,",Space,Str "\"I",Space,Str "want",Space,Str "to",Space,Str "go.\"'",Space,Str "Were",Space,Str "you",Space,Str "alive",Space,Str "in",Space,Str "the",Space,Str "70's?"] +, Para [Str "Here",Space,Str "is",Space,Str "some",Space,Str "quoted",Space,Str "'",Code "code",Str "'",Space,Str "and",Space,Str "a",Space,Str "\"",Link [Str "quoted",Space,Str "link"] (Ref [Str "1"]),Str "\"."] +, Para [Str "Some",Space,Str "dashes:",Space,Str "one",Str "---",Str "two",Space,Str "---",Space,Str "three",Str "--",Str "four",Space,Str "--",Space,Str "five."] +, Para [Str "Dashes",Space,Str "between",Space,Str "numbers:",Space,Str "5",Str "-",Str "7,",Space,Str "255",Str "-",Str "66,",Space,Str "1987",Str "-",Str "1999."] +, Para [Str "Ellipses...and.",Space,Str ".",Space,Str ".and",Space,Str ".",Space,Str ".",Space,Str ".",Space,Str "."] +, HorizontalRule +, Header 1 [Str "LaTeX"] +, BulletList + [ [ Plain [TeX "\\cite[22-23]{smith.1899}"] ] + , [ Plain [TeX "\\doublespacing"] ] + , [ Plain [TeX "$2+2=4$"] ] + , [ Plain [TeX "$x \\in y$"] ] + , [ Plain [TeX "$\\alpha \\wedge \\omega$"] ] + , [ Plain [TeX "$223$"] ] + , [ Plain [TeX "$p$",Str "-",Str "Tree"] ] + , [ Plain [TeX "$\\frac{d}{dx}f(x)=\\lim_{h\\to 0}\\frac{f(x+h)-f(x)}{h}$"] ] + , [ Plain [Str "Here's",Space,Str "one",Space,Str "that",Space,Str "has",Space,Str "a",Space,Str "line",Space,Str "break",Space,Str "in",Space,Str "it:",Space,TeX "$\\alpha + \\omega \\times x^2$",Str "."] ] ] +, Para [Str "These",Space,Str "shouldn't",Space,Str "be",Space,Str "math:"] +, BulletList + [ [ Plain [Str "To",Space,Str "get",Space,Str "the",Space,Str "famous",Space,Str "equation,",Space,Str "write",Space,Code "$e = mc^2$",Str "."] ] + , [ Plain [Str "$",Str "22,000",Space,Str "is",Space,Str "a",Space,Emph [Str "lot"],Space,Str "of",Space,Str "money.",Space,Str "So",Space,Str "is",Space,Str "$",Str "34,000.",Space,Str "(It",Space,Str "worked",Space,Str "if",Space,Str "\"lot\"",Space,Str "is",Space,Str "emphasized.)"] ] + , [ Plain [Str "Escaped",Space,Code "$",Str ":",Space,Str "$",Str "73",Space,Emph [Str "this",Space,Str "should",Space,Str "be",Space,Str "emphasized"],Space,Str "23",Str "$",Str "."] ] ] +, Para [Str "Here's",Space,Str "a",Space,Str "LaTeX",Space,Str "table:"] +, Para [TeX "\\begin{tabular}{|l|l|}\\hline\nAnimal & Number \\\\ \\hline\nDog & 2 \\\\\nCat & 1 \\\\ \\hline\n\\end{tabular}"] +, HorizontalRule +, Header 1 [Str "Special",Space,Str "Characters"] +, Para [Str "Here",Space,Str "is",Space,Str "some",Space,Str "unicode:"] +, BulletList + [ [ Plain [Str "I",Space,Str "hat:",Space,Str "\206"] ] + , [ Plain [Str "o",Space,Str "umlaut:",Space,Str "\246"] ] + , [ Plain [Str "section:",Space,Str "\167"] ] + , [ Plain [Str "set",Space,Str "membership:",Space,Str "\8712"] ] + , [ Plain [Str "copyright:",Space,Str "\169"] ] ] +, Para [Str "AT&T",Space,Str "has",Space,Str "an",Space,Str "ampersand",Space,Str "in",Space,Str "their",Space,Str "name."] +, Para [Str "AT&T",Space,Str "is",Space,Str "another",Space,Str "way",Space,Str "to",Space,Str "write",Space,Str "it."] +, Para [Str "This",Space,Str "&",Space,Str "that."] +, Para [Str "4",Space,Str "<",Space,Str "5."] +, Para [Str "6",Space,Str ">",Space,Str "5."] +, Para [Str "Backslash:",Space,Str "\\"] +, Para [Str "Backtick:",Space,Str "`"] +, Para [Str "Asterisk:",Space,Str "*"] +, Para [Str "Underscore:",Space,Str "_"] +, Para [Str "Left",Space,Str "brace:",Space,Str "{"] +, Para [Str "Right",Space,Str "brace:",Space,Str "}"] +, Para [Str "Left",Space,Str "bracket:",Space,Str "["] +, Para [Str "Right",Space,Str "bracket:",Space,Str "]"] +, Para [Str "Left",Space,Str "paren:",Space,Str "("] +, Para [Str "Right",Space,Str "paren:",Space,Str ")"] +, Para [Str "Greater",Str "-",Str "than:",Space,Str ">"] +, Para [Str "Hash:",Space,Str "#"] +, Para [Str "Period:",Space,Str "."] +, Para [Str "Bang:",Space,Str "!"] +, Para [Str "Plus:",Space,Str "+"] +, Para [Str "Minus:",Space,Str "-"] +, HorizontalRule +, Header 1 [Str "Links"] +, Header 2 [Str "Explicit"] +, Para [Str "Just",Space,Str "a",Space,Link [Str "URL"] (Src "/url/" ""),Str "."] +, Para [Link [Str "URL",Space,Str "and",Space,Str "title"] (Src "/url/" "title"),Str "."] +, Para [Link [Str "URL",Space,Str "and",Space,Str "title"] (Src "/url/" "title preceded by two spaces"),Str "."] +, Para [Link [Str "URL",Space,Str "and",Space,Str "title"] (Src "/url/" "title preceded by a tab"),Str "."] +, Para [Link [Str "URL",Space,Str "and",Space,Str "title"] (Src "/url/" "title with "quotes" in it")] +, Para [Link [Str "URL",Space,Str "and",Space,Str "title"] (Src "/url/" "title with single quotes")] +, Para [Link [Str "Email",Space,Str "link"] (Src "mailto:nobody@nowhere.net" "")] +, Para [Link [Str "Empty"] (Src "" ""),Str "."] +, Header 2 [Str "Reference"] +, Para [Str "Foo",Space,Link [Str "bar"] (Ref [Str "a"]),Str "."] +, Para [Str "Foo",Space,Link [Str "bar"] (Ref [Str "a"]),Str "."] +, Para [Str "Foo",Space,Link [Str "bar"] (Ref [Str "a"]),Str "."] +, Key [Str "a"] (Src "/url/" "") +, Para [Str "With",Space,Link [Str "embedded",Space,Link [Str "brackets"] (Ref [])] (Ref [Str "b"]),Str "."] +, Para [Link [Str "b"] (Ref []),Space,Str "by",Space,Str "itself",Space,Str "should",Space,Str "be",Space,Str "a",Space,Str "link."] +, Para [Str "Indented",Space,Link [Str "once"] (Ref []),Str "."] +, Para [Str "Indented",Space,Link [Str "twice"] (Ref []),Str "."] +, Para [Str "Indented",Space,Link [Str "thrice"] (Ref []),Str "."] +, Para [Str "This",Space,Str "should",Space,Link [Str "not"] (Ref []),Space,Str "be",Space,Str "a",Space,Str "link."] +, Key [Str "once"] (Src "/url" "") +, Key [Str "twice"] (Src "/url" "") +, Key [Str "thrice"] (Src "/url" "") +, CodeBlock "[not]: /url\n" +, Key [Str "b"] (Src "/url/" "") +, Para [Str "Foo",Space,Link [Str "bar"] (Ref []),Str "."] +, Para [Str "Foo",Space,Link [Str "biz"] (Src "/url/" "Title with "quote" inside"),Str "."] +, Key [Str "bar"] (Src "/url/" "Title with "quotes" inside") +, Header 2 [Str "With",Space,Str "ampersands"] +, Para [Str "Here's",Space,Str "a",Space,Link [Str "link",Space,Str "with",Space,Str "an",Space,Str "ampersand",Space,Str "in",Space,Str "the",Space,Str "URL"] (Ref [Str "1"]),Str "."] +, Para [Str "Here's",Space,Str "a",Space,Str "link",Space,Str "with",Space,Str "an",Space,Str "amersand",Space,Str "in",Space,Str "the",Space,Str "link",Space,Str "text:",Space,Link [Str "AT&T"] (Ref [Str "2"]),Str "."] +, Para [Str "Here's",Space,Str "an",Space,Link [Str "inline",Space,Str "link"] (Src "/script?foo=1&bar=2" ""),Str "."] +, Para [Str "Here's",Space,Str "an",Space,Link [Str "inline",Space,Str "link",Space,Str "in",Space,Str "pointy",Space,Str "braces"] (Src "/script?foo=1&bar=2" ""),Str "."] +, Key [Str "1"] (Src "http://example.com/?foo=1&bar=2" "") +, Key [Str "2"] (Src "http://att.com/" "AT&T") +, Header 2 [Str "Autolinks"] +, Para [Str "With",Space,Str "an",Space,Str "ampersand:",Space,Link [Str "http://example.com/?foo=1&bar=2"] (Src "http://example.com/?foo=1&bar=2" "")] +, BulletList + [ [ Plain [Str "In",Space,Str "a",Space,Str "list?"] ] + , [ Plain [Link [Str "http://example.com/"] (Src "http://example.com/" "")] ] + , [ Plain [Str "It",Space,Str "should."] ] ] +, Para [Str "An",Space,Str "e",Str "-",Str "mail",Space,Str "address:",Space,Link [Str "nobody@nowhere.net"] (Src "mailto:nobody@nowhere.net" "")] +, BlockQuote + [ Para [Str "Blockquoted:",Space,Link [Str "http://example.com/"] (Src "http://example.com/" "")] ] + +, Para [Str "Auto",Str "-",Str "links",Space,Str "should",Space,Str "not",Space,Str "occur",Space,Str "here:",Space,Code "<http://example.com/>"] +, CodeBlock "or here: <http://example.com/>\n" +, HorizontalRule +, Header 1 [Str "Images"] +, Para [Str "From",Space,Str "\"Voyage",Space,Str "dans",Space,Str "la",Space,Str "Lune\"",Space,Str "by",Space,Str "Georges",Space,Str "Melies",Space,Str "(1902):"] +, Para [Image [Str "lalune"] (Ref [])] +, Key [Str "lalune"] (Src "lalune.jpg" "Voyage dans la Lune") +, Para [Str "Here",Space,Str "is",Space,Str "a",Space,Str "movie",Space,Image [Str "movie"] (Src "movie.jpg" ""),Space,Str "icon."] +, HorizontalRule +, Header 1 [Str "Footnotes"] +, Para [Str "Here",Space,Str "is",Space,Str "a",Space,Str "footnote",Space,Str "reference",NoteRef "1",Str ",",Space,Str "and",Space,Str "another",NoteRef "longnote",Str ".",Space,Str "This",Space,Str "should",Space,Emph [Str "not"],Space,Str "be",Space,Str "a",Space,Str "footnote",Space,Str "reference,",Space,Str "because",Space,Str "it",Space,Str "contains",Space,Str "a",Space,Str "space",Str "^",Str "(my",Space,Str "note)."] +, Note "1" + [ Para [Str "Here",Space,Str "is",Space,Str "the",Space,Str "footnote.",Space,Str "It",Space,Str "can",Space,Str "go",Space,Str "anywhere",Space,Str "in",Space,Str "the",Space,Str "document,",Space,Str "not",Space,Str "just",Space,Str "at",Space,Str "the",Space,Str "end."] ] + +, Note "longnote" + [ Para [Str "Here's",Space,Str "the",Space,Str "other",Space,Str "note.",Space,Str "This",Space,Str "one",Space,Str "contains",Space,Str "multiple",Space,Str "blocks."] + , Para [Str "Caret",Space,Str "characters",Space,Str "are",Space,Str "used",Space,Str "to",Space,Str "indicate",Space,Str "that",Space,Str "the",Space,Str "blocks",Space,Str "all",Space,Str "belong",Space,Str "to",Space,Str "a",Space,Str "single",Space,Str "footnote",Space,Str "(as",Space,Str "with",Space,Str "block",Space,Str "quotes)."] + , CodeBlock " { <code> }\n" + , Para [Str "If",Space,Str "you",Space,Str "want,",Space,Str "you",Space,Str "can",Space,Str "use",Space,Str "a",Space,Str "caret",Space,Str "at",Space,Str "the",Space,Str "beginning",Space,Str "of",Space,Str "every",Space,Str "line,",Space,Str "as",Space,Str "with",Space,Str "blockquotes,",Space,Str "but",Space,Str "all",Space,Str "that",Space,Str "you",Space,Str "need",Space,Str "is",Space,Str "a",Space,Str "caret",Space,Str "at",Space,Str "the",Space,Str "beginning",Space,Str "of",Space,Str "the",Space,Str "first",Space,Str "line",Space,Str "of",Space,Str "the",Space,Str "block",Space,Str "and",Space,Str "any",Space,Str "preceding",Space,Str "blank",Space,Str "lines."] ] ] diff --git a/tests/testsuite.txt b/tests/testsuite.txt new file mode 100644 index 000000000..8bcbbd0f9 --- /dev/null +++ b/tests/testsuite.txt @@ -0,0 +1,612 @@ +% Pandoc Test Suite +% John MacFarlane, Anonymous +% July 17, 2006 + +This is a set of tests for pandoc. Most of them are adapted from +John Gruber's markdown test suite. + +----- + +# Headers + +## Level 2 with an [embedded link](/url) + +### Level 3 with *emphasis* + +#### Level 4 + +##### Level 5 + +Level 1 +======= + +Level 2 with *emphasis* +----------------------- + +### Level 3 +with no blank line + +Level 2 +------- +with no blank line + +---------- + +# Paragraphs + +Here's a regular paragraph. + +In Markdown 1.0.0 and earlier. Version +8. This line turns into a list item. +Because a hard-wrapped line in the +middle of a paragraph looked like a +list item. + +Here's one with a bullet. +* criminey. + +There should be a hard line break +here. + +--- + +# Block Quotes + +E-mail style: + +> This is a block quote. +> It is pretty short. + +> Code in a block quote: +> +> sub status { +> print "working"; +> } +> +> A list: +> +> 1. item one +> 2. item two +> +> Nested block quotes: +> +> > nested +> +>> nested +> + +This should not be a block quote: 2 +> 1. + +Box-style: + +,---- +| Example: +| +| sub status { +| print "working"; +| } +`---- + +,---- +| 1. do laundry +| 2. take out the trash +`---- + +Here's a nested one: + +,---- +| Joe said: +| +| ,---- +| | Don't quote me. +| `---- +`---- + +And a following paragraph. + +* * * * + +# Code Blocks + +Code: + + ---- (should be four hyphens) + + sub status { + print "working"; + } + + this code block is indented by one tab + +And: + + this code block is indented by two tabs + + These should not be escaped: \$ \\ \> \[ \{ + +___________ + +# Lists + +## 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 1. 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 + +## Tabs and spaces + ++ this is a list item + indented with tabs + ++ this is a list item + indented with spaces + + + this is an example list item + indented with tabs + + + this is an example list item + indented with spaces + + * * * * * + +# HTML Blocks + +Simple block on one line: + +<div>foo</div> + +And nested without indentation: + +<div> +<div> +<div> +foo +</div> +</div> +<div>bar</div> +</div> + +Interpreted markdown in a table: + +<table> +<tr> +<td>This is *emphasized*</td> +<td>And this is **strong**</td> +</tr> +</table> + +<script type="text/javascript">document.write('This *should not* be interpreted as markdown');</script> + +Here's a simple block: + +<div> + foo +</div> + +This should be a code block, though: + + <div> + foo + </div> + +As should this: + + <div>foo</div> + +Now, nested: + +<div> + <div> + <div> + foo + </div> + </div> +</div> + +This should just be an HTML comment: + +<!-- Comment --> + +Multiline: + +<!-- +Blah +Blah +--> + +<!-- + This is another comment. +--> + +Code block: + + <!-- Comment --> + +Just plain comment, with trailing spaces on the line: + +<!-- foo --> + +Code: + + <hr /> + +Hr's: + +<hr> + +<hr/> + +<hr /> + +<hr> + +<hr/> + +<hr /> + +<hr class="foo" id="bar" /> + +<hr class="foo" id="bar"/> + +<hr class="foo" id="bar" > + +----- + +# Inline Markup + +This is *emphasized*, and so _is this_. + +This is **strong**, and so __is this__. + +An *[emphasized link](/url)*. + +***This is strong and em.*** + +So is ***this*** word. + +___This is strong and em.___ + +So is ___this___ word. + +This is code: `>`, `$`, `\`, `\$`, `<html>`. + +----- + +# Smart quotes, ellipses, dashes + +"Hello," said the spider. "'Shelob' is my name." + +'A', 'B', and 'C' are letters. + +'Oak,' 'elm,' and 'beech' are names of trees. +So is 'pine.' + +'He said, "I want to go."' Were you alive in the +70's? + +Here is some quoted '`code`' and a "[quoted link][1]". + +Some dashes: one---two --- three--four -- five. + +Dashes between numbers: 5-7, 255-66, 1987-1999. + +Ellipses...and. . .and . . . . + +----- + +# LaTeX + +- \cite[22-23]{smith.1899} +- \doublespacing +- $2+2=4$ +- $x \in y$ +- $\alpha \wedge \omega$ +- $223$ +- $p$-Tree +- $\frac{d}{dx}f(x)=\lim_{h\to 0}\frac{f(x+h)-f(x)}{h}$ +- Here's one that has a line break in it: $\alpha + \omega \times +x^2$. + +These shouldn't be math: + +- To get the famous equation, write `$e = mc^2$`. +- $22,000 is a *lot* of money. So is $34,000. + (It worked if "lot" is emphasized.) +- Escaped `$`: $73 *this should be emphasized* 23\$. + +Here's a LaTeX table: + +\begin{tabular}{|l|l|}\hline +Animal & Number \\ \hline +Dog & 2 \\ +Cat & 1 \\ \hline +\end{tabular} + +* * * * * + +# Special Characters + +Here is some unicode: + +- I hat: Î +- o umlaut: ö +- section: § +- set membership: ∈ +- copyright: © + +AT&T has an ampersand in their name. + +AT&T is another way to write it. + +This & that. + +4 < 5. + +6 > 5. + +Backslash: \\ + +Backtick: \` + +Asterisk: \* + +Underscore: \_ + +Left brace: \{ + +Right brace: \} + +Left bracket: \[ + +Right bracket: \] + +Left paren: \( + +Right paren: \) + +Greater-than: \> + +Hash: \# + +Period: \. + +Bang: \! + +Plus: \+ + +Minus: \- + +- - - - - - - - - - - - - + +# Links + +## Explicit + +Just a [URL](/url/). + +[URL and title](/url/ "title"). + +[URL and title](/url/ "title preceded by two spaces"). + +[URL and title](/url/ "title preceded by a tab"). + +[URL and title](/url/ "title with \"quotes\" in it") + +[URL and title](/url/ 'title with single quotes') + +[Email link](mailto:nobody@nowhere.net) + +[Empty](). + +## Reference + +Foo [bar] [a]. + +Foo [bar][a]. + +Foo [bar] +[a]. + +[a]: /url/ + +With [embedded [brackets]] [b]. + +[b] by itself should be a link. + +Indented [once][]. + +Indented [twice][]. + +Indented [thrice][]. + +This should [not][] be a link. + + [once]: /url + + [twice]: /url + + [thrice]: /url + + [not]: /url + +[b]: /url/ + +Foo [bar][]. + +Foo [biz](/url/ "Title with \"quote\" inside"). + + [bar]: /url/ "Title with \"quotes\" inside" + +## With ampersands + +Here's a [link with an ampersand in the URL] [1]. + +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 in pointy braces](</script?foo=1&bar=2>). + +[1]: http://example.com/?foo=1&bar=2 +[2]: http://att.com/ "AT&T" + +## Autolinks + +With an ampersand: <http://example.com/?foo=1&bar=2> + +* In a list? +* <http://example.com/> +* It should. + +An e-mail address: <nobody@nowhere.net> + +> Blockquoted: <http://example.com/> + +Auto-links should not occur here: `<http://example.com/>` + + or here: <http://example.com/> + +---- + +# Images + +From "Voyage dans la Lune" by Georges Melies (1902): + +![lalune][] + + [lalune]: lalune.jpg "Voyage dans la Lune" + +Here is a movie  icon. + +---- + +# Footnotes + +Here is a footnote reference^(1), and another^(longnote). +This should *not* be a footnote reference, because it +contains a space^(my note). + +^(1) Here is the footnote. It can go anywhere in the document, +not just at the end. + +^(longnote) Here's the other note. This one contains multiple +blocks. +^ +^ Caret characters are used to indicate that the blocks all belong +to a single footnote (as with block quotes). +^ +^ { <code> } +^ +^ If you want, you can use a caret at the beginning of every line, +^ as with blockquotes, but all that you need is a caret at the +^ beginning of the first line of the block and any preceding +^ blank lines. + diff --git a/tests/writer.html b/tests/writer.html new file mode 100644 index 000000000..0eb528a63 --- /dev/null +++ b/tests/writer.html @@ -0,0 +1,456 @@ +<!DOCTYPE HTML PUBLIC "-//W3C//DTD HTML 4.01 Transitional//EN" + "http://www.w3.org/TR/html4/loose.dtd"> +<html> +<head> +<meta http-equiv="Content-Type" content="text/html; charset=UTF-8" /> +<meta name="generator" content="pandoc" /> +<style type="text/css"> +div.pandocNote { border-left: 1px solid grey; padding-left: 1em; } +span.pandocNoteRef { vertical-align: super; font-size: 80%; } +span.pandocNoteMarker { } +</style> +<meta name="author" content="John MacFarlane, Anonymous" /> +<meta name="date" content="July 17, 2006" /> +<title>Pandoc Test Suite</title> +</head> +<body> +<h1 class="title">Pandoc Test Suite</h1> +<p>This is a set of tests for pandoc. Most of them are adapted from John Gruber's markdown test suite.</p> +<hr /> +<h1>Headers</h1> +<h2>Level 2 with an <a href="/url">embedded link</a></h2> +<h3>Level 3 with <em>emphasis</em></h3> +<h4>Level 4</h4> +<h5>Level 5</h5> +<h1>Level 1</h1> +<h2>Level 2 with <em>emphasis</em></h2> +<h3>Level 3</h3> +<p>with no blank line</p> +<h2>Level 2</h2> +<p>with no blank line</p> +<hr /> +<h1>Paragraphs</h1> +<p>Here's a regular paragraph.</p> +<p>In Markdown 1.0.0 and earlier. Version 8. This line turns into a list item. Because a hard-wrapped line in the middle of a paragraph looked like a list item.</p> +<p>Here's one with a bullet. * criminey.</p> +<p>There should be a hard line break<br /> +here.</p> +<hr /> +<h1>Block Quotes</h1> +<p>E-mail style:</p> +<blockquote> +<p>This is a block quote. It is pretty short.</p> +</blockquote> +<blockquote> +<p>Code in a block quote:</p> +<pre><code>sub status { + print "working"; +} +</code></pre> +<p>A list:</p> +<ol> +<li>item one</li> +<li>item two</li> +</ol> +<p>Nested block quotes:</p> +<blockquote> +<p>nested</p> +</blockquote> +<blockquote> +<p>nested</p> +</blockquote> +</blockquote> +<p>This should not be a block quote: 2 > 1.</p> +<p>Box-style:</p> +<blockquote> +<p>Example:</p> +<pre><code>sub status { + print "working"; +} +</code></pre> +</blockquote> +<blockquote> +<ol> +<li>do laundry</li> +<li>take out the trash</li> +</ol> +</blockquote> +<p>Here's a nested one:</p> +<blockquote> +<p>Joe said:</p> +<blockquote> +<p>Don't quote me.</p> +</blockquote> +</blockquote> +<p>And a following paragraph.</p> +<hr /> +<h1>Code Blocks</h1> +<p>Code:</p> +<pre><code>---- (should be four hyphens) + +sub status { + print "working"; +} + +this code block is indented by one tab +</code></pre> +<p>And:</p> +<pre><code> this code block is indented by two tabs + +These should not be escaped: \$ \\ \> \[ \{ +</code></pre> +<hr /> +<h1>Lists</h1> +<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> +<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> +<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 1. 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> +<h2>Tabs and spaces</h2> +<ul> +<li><p>this is a list item indented with tabs</p> +</li> +<li><p>this is a list item indented with spaces</p> +<ul> +<li><p>this is an example list item indented with tabs</p> +</li> +<li><p>this is an example list item indented with spaces</p> +</li> +</ul> +</li> +</ul> +<hr /> +<h1>HTML Blocks</h1> +<p>Simple block on one line:</p> +<div>foo</div> +<p>And nested without indentation:</p> +<div> +<div> +<div>foo</div> +</div> +<div>bar</div> +</div> +<p>Interpreted markdown in a table:</p> +<table> +<tr> +<td>This is <em>emphasized</em></td> +<td>And this is <strong>strong</strong></td> +</tr> +</table> + +<script type="text/javascript">document.write('This *should not* be interpreted as markdown');</script> +<p>Here's a simple block:</p> +<div> + foo</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 +--> + +<!-- + This is another comment. +--> +<p>Code block:</p> +<pre><code><!-- Comment --> +</code></pre> +<p>Just plain comment, with trailing spaces on the line:</p> +<!-- foo --> +<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"> +<hr /> +<h1>Inline Markup</h1> +<p>This is <em>emphasized</em>, and so <em>is this</em>.</p> +<p>This is <strong>strong</strong>, and so <strong>is this</strong>.</p> +<p>An <em><a href="/url">emphasized link</a></em>.</p> +<p><strong><em>This is strong and em.</em></strong></p> +<p>So is <strong><em>this</em></strong> word.</p> +<p><strong><em>This is strong and em.</em></strong></p> +<p>So is <strong><em>this</em></strong> word.</p> +<p>This is code: <code>></code>, <code>$</code>, <code>\</code>, <code>\$</code>, <code><html></code>.</p> +<hr /> +<h1>Smart quotes, ellipses, dashes</h1> +<p>"Hello," said the spider. "'Shelob' is my name."</p> +<p>'A', 'B', and 'C' are letters.</p> +<p>'Oak,' 'elm,' and 'beech' are names of trees. So is 'pine.'</p> +<p>'He said, "I want to go."' Were you alive in the 70's?</p> +<p>Here is some quoted '<code>code</code>' and a "<a href="http://example.com/?foo=1&bar=2">quoted link</a>".</p> +<p>Some dashes: one---two --- three--four -- five.</p> +<p>Dashes between numbers: 5-7, 255-66, 1987-1999.</p> +<p>Ellipses...and. . .and . . . .</p> +<hr /> +<h1>LaTeX</h1> +<ul> +<li>\cite[22-23]{smith.1899}</li> +<li>\doublespacing</li> +<li>$2+2=4$</li> +<li>$x \in y$</li> +<li>$\alpha \wedge \omega$</li> +<li>$223$</li> +<li>$p$-Tree</li> +<li>$\frac{d}{dx}f(x)=\lim_{h\to 0}\frac{f(x+h)-f(x)}{h}$</li> +<li>Here's one that has a line break in it: $\alpha + \omega \times x^2$.</li> +</ul> +<p>These shouldn't be math:</p> +<ul> +<li>To get the famous equation, write <code>$e = mc^2$</code>.</li> +<li>$22,000 is a <em>lot</em> of money. So is $34,000. (It worked if "lot" is emphasized.)</li> +<li>Escaped <code>$</code>: $73 <em>this should be emphasized</em> 23$.</li> +</ul> +<p>Here's a LaTeX table:</p> +<p>\begin{tabular}{|l|l|}\hline +Animal & Number \\ \hline +Dog & 2 \\ +Cat & 1 \\ \hline +\end{tabular}</p> +<hr /> +<h1>Special Characters</h1> +<p>Here is some unicode:</p> +<ul> +<li>I hat: Î</li> +<li>o umlaut: ö</li> +<li>section: §</li> +<li>set membership: ∈</li> +<li>copyright: ©</li> +</ul> +<p>AT&T has an ampersand in their name.</p> +<p>AT&T is another way to write it.</p> +<p>This & that.</p> +<p>4 < 5.</p> +<p>6 > 5.</p> +<p>Backslash: \</p> +<p>Backtick: `</p> +<p>Asterisk: *</p> +<p>Underscore: _</p> +<p>Left brace: {</p> +<p>Right brace: }</p> +<p>Left bracket: [</p> +<p>Right bracket: ]</p> +<p>Left paren: (</p> +<p>Right paren: )</p> +<p>Greater-than: ></p> +<p>Hash: #</p> +<p>Period: .</p> +<p>Bang: !</p> +<p>Plus: +</p> +<p>Minus: -</p> +<hr /> +<h1>Links</h1> +<h2>Explicit</h2> +<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 with "quotes" in it">URL and title</a></p> +<p><a href="/url/" title="title with single quotes">URL and title</a></p> +<p><script type="text/javascript">h='nowhere.net';n='nobody';e=n+'@'+h;document.write('<a href="mailto:'+e+'">'+'Email link'+'<\/a>');</script><noscript>Email link (nobody [at] nowhere.net)</noscript></p> +<p><a href="">Empty</a>.</p> +<h2>Reference</h2> +<p>Foo <a href="/url/">bar</a>.</p> +<p>Foo <a href="/url/">bar</a>.</p> +<p>Foo <a href="/url/">bar</a>.</p> +<p>With <a href="/url/">embedded [brackets]</a>.</p> +<p><a href="/url/">b</a> by itself should be a link.</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>This should [not] be a link.</p> +<pre><code>[not]: /url +</code></pre> +<p>Foo <a href="/url/" title="Title with "quotes" inside">bar</a>.</p> +<p>Foo <a href="/url/" title="Title with "quote" inside">biz</a>.</p> +<h2>With ampersands</h2> +<p>Here's a <a href="http://example.com/?foo=1&bar=2">link with an ampersand in the URL</a>.</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 <a href="/script?foo=1&bar=2">inline link</a>.</p> +<p>Here's an <a href="/script?foo=1&bar=2">inline link in pointy braces</a>.</p> +<h2>Autolinks</h2> +<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> +<p>An e-mail address: <script type="text/javascript">h='nowhere.net';n='nobody';e=n+'@'+h;document.write('<a href="mailto:'+e+'">'+e+'<\/a>');</script><noscript>nobody [at] nowhere.net</noscript></p> +<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> +<hr /> +<h1>Images</h1> +<p>From "Voyage dans la Lune" by Georges Melies (1902):</p> +<p><img src="lalune.jpg" title="Voyage dans la Lune" alt="lalune"></p> +<p>Here is a movie <img src="movie.jpg" alt="movie"> icon.</p> +<hr /> +<h1>Footnotes</h1> +<p>Here is a footnote reference<span class="pandocNoteRef"><a name="ref_1" href="#note_1">(1)</a></span>, and another<span class="pandocNoteRef"><a name="ref_longnote" href="#note_longnote">(longnote)</a></span>. This should <em>not</em> be a footnote reference, because it contains a space^(my note).</p> +<div class="pandocNote"> +<p class="first"><span class="pandocNoteMarker"><a name="note_1" href="#ref_1">(1)</a></span> Here is the footnote. It can go anywhere in the document, not just at the end.</p> + +</div> +<div class="pandocNote"> +<p class="first"><span class="pandocNoteMarker"><a name="note_longnote" href="#ref_longnote">(longnote)</a></span> Here's the other note. This one contains multiple blocks.</p> +<p>Caret characters are used to indicate that the blocks all belong to a single footnote (as with block quotes).</p> +<pre><code> { <code> } +</code></pre> +<p>If you want, you can use a caret at the beginning of every line, as with blockquotes, but all that you need is a caret at the beginning of the first line of the block and any preceding blank lines.</p> + +</div> +</body> +</html> + diff --git a/tests/writer.latex b/tests/writer.latex new file mode 100644 index 000000000..6f3efc710 --- /dev/null +++ b/tests/writer.latex @@ -0,0 +1,581 @@ +\documentclass{article} +\usepackage{hyperref} +\usepackage{ucs} +\usepackage[utf8x]{inputenc} +\usepackage{graphicx} +\setlength{\parindent}{0pt} +\setlength{\parskip}{6pt plus 2pt minus 1pt} +% This is needed for code blocks in footnotes: +\usepackage{fancyvrb} +\VerbatimFootnotes +\setcounter{secnumdepth}{0} +\title{Pandoc Test Suite} +\author{John MacFarlane\\Anonymous} +\date{July 17, 2006} +\begin{document} +\maketitle +This is a set of tests for pandoc. Most of them are adapted from John Gruber's markdown test suite. + +\begin{center}\rule{3in}{0.4pt}\end{center} + +\section{Headers} + +\subsection{Level 2 with an \href{/url}{embedded link}} + +\subsubsection{Level 3 with \emph{emphasis}} + +Level 4 + +Level 5 + +\section{Level 1} + +\subsection{Level 2 with \emph{emphasis}} + +\subsubsection{Level 3} + +with no blank line + +\subsection{Level 2} + +with no blank line + +\begin{center}\rule{3in}{0.4pt}\end{center} + +\section{Paragraphs} + +Here's a regular paragraph. + +In Markdown 1.0.0 and earlier. Version 8. This line turns into a list item. Because a hard-wrapped line in the middle of a paragraph looked like a list item. + +Here's one with a bullet. * criminey. + +There should be a hard line break\\ +here. + +\begin{center}\rule{3in}{0.4pt}\end{center} + +\section{Block Quotes} + +E-mail style: + +\begin{quote} +This is a block quote. It is pretty short. + +\end{quote} +\begin{quote} +Code in a block quote: + +\begin{verbatim} +sub status { + print "working"; +} +\end{verbatim} +A list: + +\begin{enumerate} +\item item one +\item item two +\end{enumerate} +Nested block quotes: + +\begin{quote} +nested + +\end{quote} +\begin{quote} +nested + +\end{quote} +\end{quote} +This should not be a block quote: 2 \textgreater{} 1. + +Box-style: + +\begin{quote} +Example: + +\begin{verbatim} +sub status { + print "working"; +} +\end{verbatim} +\end{quote} +\begin{quote} +\begin{enumerate} +\item do laundry +\item take out the trash +\end{enumerate} +\end{quote} +Here's a nested one: + +\begin{quote} +Joe said: + +\begin{quote} +Don't quote me. + +\end{quote} +\end{quote} +And a following paragraph. + +\begin{center}\rule{3in}{0.4pt}\end{center} + +\section{Code Blocks} + +Code: + +\begin{verbatim} +---- (should be four hyphens) + +sub status { + print "working"; +} + +this code block is indented by one tab +\end{verbatim} +And: + +\begin{verbatim} + this code block is indented by two tabs + +These should not be escaped: \$ \\ \> \[ \{ +\end{verbatim} +\begin{center}\rule{3in}{0.4pt}\end{center} + +\section{Lists} + +\subsection{Unordered} + +Asterisks tight: + +\begin{itemize} +\item asterisk 1 +\item asterisk 2 +\item asterisk 3 +\end{itemize} +Asterisks loose: + +\begin{itemize} +\item asterisk 1 + +\item asterisk 2 + +\item asterisk 3 + +\end{itemize} +Pluses tight: + +\begin{itemize} +\item Plus 1 +\item Plus 2 +\item Plus 3 +\end{itemize} +Pluses loose: + +\begin{itemize} +\item Plus 1 + +\item Plus 2 + +\item Plus 3 + +\end{itemize} +Minuses tight: + +\begin{itemize} +\item Minus 1 +\item Minus 2 +\item Minus 3 +\end{itemize} +Minuses loose: + +\begin{itemize} +\item Minus 1 + +\item Minus 2 + +\item Minus 3 + +\end{itemize} +\subsection{Ordered} + +Tight: + +\begin{enumerate} +\item First +\item Second +\item Third +\end{enumerate} +and: + +\begin{enumerate} +\item One +\item Two +\item Three +\end{enumerate} +Loose using tabs: + +\begin{enumerate} +\item First + +\item Second + +\item Third + +\end{enumerate} +and using spaces: + +\begin{enumerate} +\item One + +\item Two + +\item Three + +\end{enumerate} +Multiple paragraphs: + +\begin{enumerate} +\item Item 1, graf one. + +Item 1. graf two. The quick brown fox jumped over the lazy dog's back. + +\item Item 2. + +\item Item 3. + +\end{enumerate} +\subsection{Nested} + +\begin{itemize} +\item Tab +\begin{itemize} +\item Tab +\begin{itemize} +\item Tab +\end{itemize} +\end{itemize} +\end{itemize} +Here's another: + +\begin{enumerate} +\item First +\item Second: +\begin{itemize} +\item Fee +\item Fie +\item Foe +\end{itemize} +\item Third +\end{enumerate} +Same thing but with paragraphs: + +\begin{enumerate} +\item First + +\item Second: + +\begin{itemize} +\item Fee +\item Fie +\item Foe +\end{itemize} +\item Third + +\end{enumerate} +\subsection{Tabs and spaces} + +\begin{itemize} +\item this is a list item indented with tabs + +\item this is a list item indented with spaces + +\begin{itemize} +\item this is an example list item indented with tabs + +\item this is an example list item indented with spaces + +\end{itemize} +\end{itemize} +\begin{center}\rule{3in}{0.4pt}\end{center} + +\section{HTML Blocks} + +Simple block on one line: + +foo +And nested without indentation: + +foo +bar +Interpreted markdown in a table: + +This is \emph{emphasized} +And this is \textbf{strong} +Here's a simple block: + +foo +This should be a code block, though: + +\begin{verbatim} +<div> + foo +</div> +\end{verbatim} +As should this: + +\begin{verbatim} +<div>foo</div> +\end{verbatim} +Now, nested: + +foo +This should just be an HTML comment: + +Multiline: + +Code block: + +\begin{verbatim} +<!-- Comment --> +\end{verbatim} +Just plain comment, with trailing spaces on the line: + +Code: + +\begin{verbatim} +<hr /> +\end{verbatim} +Hr's: + +\begin{center}\rule{3in}{0.4pt}\end{center} + +\section{Inline Markup} + +This is \emph{emphasized}, and so \emph{is this}. + +This is \textbf{strong}, and so \textbf{is this}. + +An \emph{\href{/url}{emphasized link}}. + +\textbf{\emph{This is strong and em.}} + +So is \textbf{\emph{this}} word. + +\textbf{\emph{This is strong and em.}} + +So is \textbf{\emph{this}} word. + +This is code: \verb!>!, \verb!$!, \verb!\!, \verb!\$!, \verb!<html>!. + +\begin{center}\rule{3in}{0.4pt}\end{center} + +\section{Smart quotes, ellipses, dashes} + +``Hello,'' said the spider. ``{}`Shelob' is my name.'' + +`A', `B', and `C' are letters. + +`Oak,' `elm,' and `beech' are names of trees. So is `pine.' + +`He said, ``I want to go.''' Were you alive in the 70's? + +Here is some quoted `\verb!code!' and a ``\href{http://example.com/?foo=1&bar=2}{quoted link}''. + +Some dashes: one---two --- three---four---five. + +Dashes between numbers: 5--7, 255--66, 1987--1999. + +Ellipses\ldots{}and\ldots{}and \ldots{} . + +\begin{center}\rule{3in}{0.4pt}\end{center} + +\section{LaTeX} + +\begin{itemize} +\item \cite[22-23]{smith.1899} +\item \doublespacing +\item $2+2=4$ +\item $x \in y$ +\item $\alpha \wedge \omega$ +\item $223$ +\item $p$-Tree +\item $\frac{d}{dx}f(x)=\lim_{h\to 0}\frac{f(x+h)-f(x)}{h}$ +\item Here's one that has a line break in it: $\alpha + \omega \times x^2$. +\end{itemize} +These shouldn't be math: + +\begin{itemize} +\item To get the famous equation, write \verb!$e = mc^2$!. +\item \$22,000 is a \emph{lot} of money. So is \$34,000. (It worked if ``lot'' is emphasized.) +\item Escaped \verb!$!: \$73 \emph{this should be emphasized} 23\$. +\end{itemize} +Here's a LaTeX table: + +\begin{tabular}{|l|l|}\hline +Animal & Number \\ \hline +Dog & 2 \\ +Cat & 1 \\ \hline +\end{tabular} + +\begin{center}\rule{3in}{0.4pt}\end{center} + +\section{Special Characters} + +Here is some unicode: + +\begin{itemize} +\item I hat: Î +\item o umlaut: ö +\item section: § +\item set membership: ∈ +\item copyright: © +\end{itemize} +AT\&T has an ampersand in their name. + +AT\&T is another way to write it. + +This \& that. + +4 \textless{} 5. + +6 \textgreater{} 5. + +Backslash: \textbackslash{} + +Backtick: ` + +Asterisk: * + +Underscore: \_ + +Left brace: \{ + +Right brace: \} + +Left bracket: [ + +Right bracket: ] + +Left paren: ( + +Right paren: ) + +Greater-than: \textgreater{} + +Hash: \# + +Period: . + +Bang: ! + +Plus: + + +Minus: - + +\begin{center}\rule{3in}{0.4pt}\end{center} + +\section{Links} + +\subsection{Explicit} + +Just a \href{/url/}{URL}. + +\href{/url/}{URL and title}. + +\href{/url/}{URL and title}. + +\href{/url/}{URL and title}. + +\href{/url/}{URL and title} + +\href{/url/}{URL and title} + +\href{mailto:nobody@nowhere.net}{Email link} + +\href{}{Empty}. + +\subsection{Reference} + +Foo \href{/url/}{bar}. + +Foo \href{/url/}{bar}. + +Foo \href{/url/}{bar}. + +With \href{/url/}{embedded [brackets]}. + +\href{/url/}{b} by itself should be a link. + +Indented \href{/url}{once}. + +Indented \href{/url}{twice}. + +Indented \href{/url}{thrice}. + +This should [not] be a link. + +\begin{verbatim} +[not]: /url +\end{verbatim} +Foo \href{/url/}{bar}. + +Foo \href{/url/}{biz}. + +\subsection{With ampersands} + +Here's a \href{http://example.com/?foo=1&bar=2}{link with an ampersand in the URL}. + +Here's a link with an amersand in the link text: \href{http://att.com/}{AT\&T}. + +Here's an \href{/script?foo=1&bar=2}{inline link}. + +Here's an \href{/script?foo=1&bar=2}{inline link in pointy braces}. + +\subsection{Autolinks} + +With an ampersand: \href{http://example.com/?foo=1&bar=2}{http://example.com/?foo=1\&bar=2} + +\begin{itemize} +\item In a list? +\item \href{http://example.com/}{http://example.com/} +\item It should. +\end{itemize} +An e-mail address: \href{mailto:nobody@nowhere.net}{nobody@nowhere.net} + +\begin{quote} +Blockquoted: \href{http://example.com/}{http://example.com/} + +\end{quote} +Auto-links should not occur here: \verb!<http://example.com/>! + +\begin{verbatim} +or here: <http://example.com/> +\end{verbatim} +\begin{center}\rule{3in}{0.4pt}\end{center} + +\section{Images} + +From ``Voyage dans la Lune'' by Georges Melies (1902): + +\includegraphics{lalune.jpg} + +Here is a movie \includegraphics{movie.jpg} icon. + +\begin{center}\rule{3in}{0.4pt}\end{center} + +\section{Footnotes} + +Here is a footnote reference\footnote{Here is the footnote. It can go anywhere in the document, not just at the end.}, and another\footnote{Here's the other note. This one contains multiple blocks. + +Caret characters are used to indicate that the blocks all belong to a single footnote (as with block quotes). + +\begin{verbatim} + { <code> } +\end{verbatim} +If you want, you can use a caret at the beginning of every line, as with blockquotes, but all that you need is a caret at the beginning of the first line of the block and any preceding blank lines.}. This should \emph{not} be a footnote reference, because it contains a space\^{}(my note). + + +\end{document} + diff --git a/tests/writer.markdown b/tests/writer.markdown new file mode 100644 index 000000000..c086190d2 --- /dev/null +++ b/tests/writer.markdown @@ -0,0 +1,628 @@ +% Pandoc Test Suite +% John MacFarlane, Anonymous +% July 17, 2006 + +This is a set of tests for pandoc. Most of them are adapted from +John Gruber's markdown test suite. + + +* * * * * + +# Headers + +## Level 2 with an [embedded link](/url) + +### Level 3 with *emphasis* + +#### Level 4 + +##### Level 5 + +# Level 1 + +## Level 2 with *emphasis* + +### Level 3 + +with no blank line + +## Level 2 + +with no blank line + + +* * * * * + +# Paragraphs + +Here's a regular paragraph. + +In Markdown 1.0.0 and earlier. Version 8. This line turns into a +list item. Because a hard-wrapped line in the middle of a paragraph +looked like a list item. + +Here's one with a bullet. \* criminey. + +There should be a hard line break +here. + + +* * * * * + +# Block Quotes + +E-mail style: + +> This is a block quote. It is pretty short. + +> Code in a block quote: +> +> sub status { +> print "working"; +> } +> +> A list: +> +> 1. item one +> 2. item two +> +> Nested block quotes: +> +> > nested +> +> > nested + +This should not be a block quote: 2 > 1. + +Box-style: + +> Example: +> +> sub status { +> print "working"; +> } + +> 1. do laundry +> 2. take out the trash + +Here's a nested one: + +> Joe said: +> +> > Don't quote me. + +And a following paragraph. + + +* * * * * + +# Code Blocks + +Code: + + ---- (should be four hyphens) + + sub status { + print "working"; + } + + this code block is indented by one tab + +And: + + this code block is indented by two tabs + + These should not be escaped: \$ \\ \> \[ \{ + + +* * * * * + +# Lists + +## 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 1. 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 + + +## Tabs and spaces + +- this is a list item indented with tabs + +- this is a list item indented with spaces + + - this is an example list item indented with tabs + + - this is an example list item indented with spaces + + + + +* * * * * + +# HTML Blocks + +Simple block on one line: + +<div> +foo +</div> + +And nested without indentation: + +<div> +<div> +<div> +foo +</div> +</div> +<div> +bar +</div> +</div> + +Interpreted markdown in a table: + +<table> +<tr> +<td> +This is *emphasized* +</td> +<td> +And this is **strong** +</td> +</tr> +</table> + +<script type="text/javascript">document.write('This *should not* be interpreted as markdown');</script> + +Here's a simple block: + +<div> + +foo +</div> + +This should be a code block, though: + + <div> + foo + </div> + +As should this: + + <div>foo</div> + +Now, nested: + +<div> + <div> + <div> + +foo +</div> + </div> +</div> + +This should just be an HTML comment: + +<!-- Comment --> + +Multiline: + +<!-- +Blah +Blah +--> + +<!-- + This is another comment. +--> + +Code block: + + <!-- Comment --> + +Just plain comment, with trailing spaces on the line: + +<!-- foo --> + +Code: + + <hr /> + +Hr's: + +<hr> + +<hr /> + +<hr /> + +<hr> + +<hr /> + +<hr /> + +<hr class="foo" id="bar" /> + +<hr class="foo" id="bar" /> + +<hr class="foo" id="bar"> + + +* * * * * + +# Inline Markup + +This is *emphasized*, and so *is this*. + +This is **strong**, and so **is this**. + +An *[emphasized link](/url)*. + +***This is strong and em.*** + +So is ***this*** word. + +***This is strong and em.*** + +So is ***this*** word. + +This is code: `>`, `$`, `\`, `\$`, `<html>`. + + +* * * * * + +# Smart quotes, ellipses, dashes + +"Hello," said the spider. "'Shelob' is my name." + +'A', 'B', and 'C' are letters. + +'Oak,' 'elm,' and 'beech' are names of trees. So is 'pine.' + +'He said, "I want to go."' Were you alive in the 70's? + +Here is some quoted '`code`' and a "[quoted link][1]". + +Some dashes: one---two --- three--four -- five. + +Dashes between numbers: 5-7, 255-66, 1987-1999. + +Ellipses...and. . .and . . . . + + +* * * * * + +# LaTeX + +- \cite[22-23]{smith.1899} +- \doublespacing +- $2+2=4$ +- $x \in y$ +- $\alpha \wedge \omega$ +- $223$ +- $p$-Tree +- $\frac{d}{dx}f(x)=\lim_{h\to 0}\frac{f(x+h)-f(x)}{h}$ +- Here's one that has a line break in it: + $\alpha + \omega \times x^2$. + +These shouldn't be math: + +- To get the famous equation, write `$e = mc^2$`. +- $22,000 is a *lot* of money. So is $34,000. (It worked if "lot" + is emphasized.) +- Escaped `$`: $73 *this should be emphasized* 23$. + +Here's a LaTeX table: + +\begin{tabular}{|l|l|}\hline +Animal & Number \\ \hline +Dog & 2 \\ +Cat & 1 \\ \hline +\end{tabular} + + +* * * * * + +# Special Characters + +Here is some unicode: + +- I hat: Î +- o umlaut: ö +- section: § +- set membership: ∈ +- copyright: © + +AT&T has an ampersand in their name. + +AT&T is another way to write it. + +This & that. + +4 \< 5. + +6 > 5. + +Backslash: \\ + +Backtick: \` + +Asterisk: \* + +Underscore: \_ + +Left brace: { + +Right brace: } + +Left bracket: [ + +Right bracket: ] + +Left paren: ( + +Right paren: ) + +Greater-than: > + +Hash: # + +Period: . + +Bang: ! + +Plus: + + +Minus: - + + +* * * * * + +# Links + +## Explicit + +Just a [URL](/url/). + +[URL and title](/url/ "title"). + +[URL and title](/url/ "title preceded by two spaces"). + +[URL and title](/url/ "title preceded by a tab"). + +[URL and title](/url/ "title with "quotes" in it") + +[URL and title](/url/ "title with single quotes") + +[Email link](mailto:nobody@nowhere.net) + +[Empty](). + +## Reference + +Foo [bar][a]. + +Foo [bar][a]. + +Foo [bar][a]. + + + [a]: /url/ + +With [embedded [brackets][]][b]. + +[b][] by itself should be a link. + +Indented [once][]. + +Indented [twice][]. + +Indented [thrice][]. + +This should [not][] be a link. + + + [once]: /url + [twice]: /url + [thrice]: /url + [not]: /url + + + [b]: /url/ + +Foo [bar][]. + +Foo [biz](/url/ "Title with "quote" inside"). + + + [bar]: /url/ "Title with "quotes" inside" + +## With ampersands + +Here's a [link with an ampersand in the URL][1]. + +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 in pointy braces](/script?foo=1&bar=2). + + + [1]: http://example.com/?foo=1&bar=2 + [2]: http://att.com/ "AT&T" + +## Autolinks + +With an ampersand: +[http://example.com/?foo=1&bar=2](http://example.com/?foo=1&bar=2) + +- In a list? +- [http://example.com/](http://example.com/) +- It should. + +An e-mail address: [nobody@nowhere.net](mailto:nobody@nowhere.net) + +> Blockquoted: [http://example.com/](http://example.com/) + +Auto-links should not occur here: `<http://example.com/>` + + or here: <http://example.com/> + + +* * * * * + +# Images + +From "Voyage dans la Lune" by Georges Melies (1902): + +![lalune] + + + [lalune]: lalune.jpg "Voyage dans la Lune" + +Here is a movie  icon. + + +* * * * * + +# Footnotes + +Here is a footnote reference^(1), and another^(longnote). This +should *not* be a footnote reference, because it contains a +space\^(my note). + +^(1) Here is the footnote. It can go anywhere in the document, not just +^ at the end. + +^(longnote) Here's the other note. This one contains multiple blocks. +^ +^ Caret characters are used to indicate that the blocks all belong to +^ a single footnote (as with block quotes). +^ +^ { <code> } +^ +^ If you want, you can use a caret at the beginning of every line, as +^ with blockquotes, but all that you need is a caret at the beginning +^ of the first line of the block and any preceding blank lines. + + diff --git a/tests/writer.native b/tests/writer.native new file mode 100644 index 000000000..8ec543e89 --- /dev/null +++ b/tests/writer.native @@ -0,0 +1,329 @@ +Pandoc (Meta [Str "Pandoc",Space,Str "Test",Space,Str "Suite"] ["John MacFarlane","Anonymous"] "July 17, 2006") +[ Para [Str "This",Space,Str "is",Space,Str "a",Space,Str "set",Space,Str "of",Space,Str "tests",Space,Str "for",Space,Str "pandoc.",Space,Str "Most",Space,Str "of",Space,Str "them",Space,Str "are",Space,Str "adapted",Space,Str "from",Space,Str "John",Space,Str "Gruber's",Space,Str "markdown",Space,Str "test",Space,Str "suite."] +, HorizontalRule +, Header 1 [Str "Headers"] +, Header 2 [Str "Level",Space,Str "2",Space,Str "with",Space,Str "an",Space,Link [Str "embedded",Space,Str "link"] (Src "/url" "")] +, Header 3 [Str "Level",Space,Str "3",Space,Str "with",Space,Emph [Str "emphasis"]] +, Header 4 [Str "Level",Space,Str "4"] +, Header 5 [Str "Level",Space,Str "5"] +, Header 1 [Str "Level",Space,Str "1"] +, Header 2 [Str "Level",Space,Str "2",Space,Str "with",Space,Emph [Str "emphasis"]] +, Header 3 [Str "Level",Space,Str "3"] +, Para [Str "with",Space,Str "no",Space,Str "blank",Space,Str "line"] +, Header 2 [Str "Level",Space,Str "2"] +, Para [Str "with",Space,Str "no",Space,Str "blank",Space,Str "line"] +, HorizontalRule +, Header 1 [Str "Paragraphs"] +, Para [Str "Here's",Space,Str "a",Space,Str "regular",Space,Str "paragraph."] +, Para [Str "In",Space,Str "Markdown",Space,Str "1.0.0",Space,Str "and",Space,Str "earlier.",Space,Str "Version",Space,Str "8.",Space,Str "This",Space,Str "line",Space,Str "turns",Space,Str "into",Space,Str "a",Space,Str "list",Space,Str "item.",Space,Str "Because",Space,Str "a",Space,Str "hard",Str "-",Str "wrapped",Space,Str "line",Space,Str "in",Space,Str "the",Space,Str "middle",Space,Str "of",Space,Str "a",Space,Str "paragraph",Space,Str "looked",Space,Str "like",Space,Str "a",Space,Str "list",Space,Str "item."] +, Para [Str "Here's",Space,Str "one",Space,Str "with",Space,Str "a",Space,Str "bullet.",Space,Str "*",Space,Str "criminey."] +, Para [Str "There",Space,Str "should",Space,Str "be",Space,Str "a",Space,Str "hard",Space,Str "line",Space,Str "break",LineBreak,Str "here."] +, HorizontalRule +, Header 1 [Str "Block",Space,Str "Quotes"] +, Para [Str "E",Str "-",Str "mail",Space,Str "style:"] +, BlockQuote + [ Para [Str "This",Space,Str "is",Space,Str "a",Space,Str "block",Space,Str "quote.",Space,Str "It",Space,Str "is",Space,Str "pretty",Space,Str "short."] ] + +, BlockQuote + [ Para [Str "Code",Space,Str "in",Space,Str "a",Space,Str "block",Space,Str "quote:"] + , CodeBlock "sub status {\n print \"working\";\n}\n" + , Para [Str "A",Space,Str "list:"] + , OrderedList + [ [ Plain [Str "item",Space,Str "one"] ] + , [ Plain [Str "item",Space,Str "two"] ] ] + , Para [Str "Nested",Space,Str "block",Space,Str "quotes:"] + , BlockQuote + [ Para [Str "nested"] ] + + , BlockQuote + [ Para [Str "nested"] ] + ] +, Para [Str "This",Space,Str "should",Space,Str "not",Space,Str "be",Space,Str "a",Space,Str "block",Space,Str "quote:",Space,Str "2",Space,Str ">",Space,Str "1."] +, Para [Str "Box",Str "-",Str "style:"] +, BlockQuote + [ Para [Str "Example:"] + , CodeBlock "sub status {\n print \"working\";\n}\n" ] +, BlockQuote + [ OrderedList + [ [ Plain [Str "do",Space,Str "laundry"] ] + , [ Plain [Str "take",Space,Str "out",Space,Str "the",Space,Str "trash"] ] ] ] +, Para [Str "Here's",Space,Str "a",Space,Str "nested",Space,Str "one:"] +, BlockQuote + [ Para [Str "Joe",Space,Str "said:"] + , BlockQuote + [ Para [Str "Don't",Space,Str "quote",Space,Str "me."] ] + ] +, Para [Str "And",Space,Str "a",Space,Str "following",Space,Str "paragraph."] +, HorizontalRule +, Header 1 [Str "Code",Space,Str "Blocks"] +, Para [Str "Code:"] +, CodeBlock "---- (should be four hyphens)\n\nsub status {\n print \"working\";\n}\n\nthis code block is indented by one tab\n" +, Para [Str "And:"] +, CodeBlock " this code block is indented by two tabs\n\nThese should not be escaped: \\$ \\\\ \\> \\[ \\{\n" +, HorizontalRule +, Header 1 [Str "Lists"] +, Header 2 [Str "Unordered"] +, Para [Str "Asterisks",Space,Str "tight:"] +, BulletList + [ [ Plain [Str "asterisk",Space,Str "1"] ] + , [ Plain [Str "asterisk",Space,Str "2"] ] + , [ Plain [Str "asterisk",Space,Str "3"] ] ] +, Para [Str "Asterisks",Space,Str "loose:"] +, BulletList + [ [ Para [Str "asterisk",Space,Str "1"] ] + , [ Para [Str "asterisk",Space,Str "2"] ] + , [ Para [Str "asterisk",Space,Str "3"] ] ] +, Para [Str "Pluses",Space,Str "tight:"] +, BulletList + [ [ Plain [Str "Plus",Space,Str "1"] ] + , [ Plain [Str "Plus",Space,Str "2"] ] + , [ Plain [Str "Plus",Space,Str "3"] ] ] +, Para [Str "Pluses",Space,Str "loose:"] +, BulletList + [ [ Para [Str "Plus",Space,Str "1"] ] + , [ Para [Str "Plus",Space,Str "2"] ] + , [ Para [Str "Plus",Space,Str "3"] ] ] +, Para [Str "Minuses",Space,Str "tight:"] +, BulletList + [ [ Plain [Str "Minus",Space,Str "1"] ] + , [ Plain [Str "Minus",Space,Str "2"] ] + , [ Plain [Str "Minus",Space,Str "3"] ] ] +, Para [Str "Minuses",Space,Str "loose:"] +, BulletList + [ [ Para [Str "Minus",Space,Str "1"] ] + , [ Para [Str "Minus",Space,Str "2"] ] + , [ Para [Str "Minus",Space,Str "3"] ] ] +, Header 2 [Str "Ordered"] +, Para [Str "Tight:"] +, OrderedList + [ [ Plain [Str "First"] ] + , [ Plain [Str "Second"] ] + , [ Plain [Str "Third"] ] ] +, Para [Str "and:"] +, OrderedList + [ [ Plain [Str "One"] ] + , [ Plain [Str "Two"] ] + , [ Plain [Str "Three"] ] ] +, Para [Str "Loose",Space,Str "using",Space,Str "tabs:"] +, OrderedList + [ [ Para [Str "First"] ] + , [ Para [Str "Second"] ] + , [ Para [Str "Third"] ] ] +, Para [Str "and",Space,Str "using",Space,Str "spaces:"] +, OrderedList + [ [ Para [Str "One"] ] + , [ Para [Str "Two"] ] + , [ Para [Str "Three"] ] ] +, Para [Str "Multiple",Space,Str "paragraphs:"] +, OrderedList + [ [ Para [Str "Item",Space,Str "1,",Space,Str "graf",Space,Str "one."] + , Para [Str "Item",Space,Str "1.",Space,Str "graf",Space,Str "two.",Space,Str "The",Space,Str "quick",Space,Str "brown",Space,Str "fox",Space,Str "jumped",Space,Str "over",Space,Str "the",Space,Str "lazy",Space,Str "dog's",Space,Str "back."] ], [ Para [Str "Item",Space,Str "2."] ] + , [ Para [Str "Item",Space,Str "3."] ] ] +, Header 2 [Str "Nested"] +, BulletList + [ [ Plain [Str "Tab"] + , BulletList + [ [ Plain [Str "Tab"] + , BulletList + [ [ Plain [Str "Tab"] ] + ] ] ] ] ] +, Para [Str "Here's",Space,Str "another:"] +, OrderedList + [ [ Plain [Str "First"] ] + , [ Plain [Str "Second:"] + , BulletList + [ [ Plain [Str "Fee"] ] + , [ Plain [Str "Fie"] ] + , [ Plain [Str "Foe"] ] ] ], [ Plain [Str "Third"] ] ] +, Para [Str "Same",Space,Str "thing",Space,Str "but",Space,Str "with",Space,Str "paragraphs:"] +, OrderedList + [ [ Para [Str "First"] ] + , [ Para [Str "Second:"] + , BulletList + [ [ Plain [Str "Fee"] ] + , [ Plain [Str "Fie"] ] + , [ Plain [Str "Foe"] ] ] ], [ Para [Str "Third"] ] ] +, Header 2 [Str "Tabs",Space,Str "and",Space,Str "spaces"] +, BulletList + [ [ Para [Str "this",Space,Str "is",Space,Str "a",Space,Str "list",Space,Str "item",Space,Str "indented",Space,Str "with",Space,Str "tabs"] ] + , [ Para [Str "this",Space,Str "is",Space,Str "a",Space,Str "list",Space,Str "item",Space,Str "indented",Space,Str "with",Space,Str "spaces"] + , BulletList + [ [ Para [Str "this",Space,Str "is",Space,Str "an",Space,Str "example",Space,Str "list",Space,Str "item",Space,Str "indented",Space,Str "with",Space,Str "tabs"] ] + , [ Para [Str "this",Space,Str "is",Space,Str "an",Space,Str "example",Space,Str "list",Space,Str "item",Space,Str "indented",Space,Str "with",Space,Str "spaces"] ] ] ] ] +, HorizontalRule +, Header 1 [Str "HTML",Space,Str "Blocks"] +, Para [Str "Simple",Space,Str "block",Space,Str "on",Space,Str "one",Space,Str "line:"] +, RawHtml "<div>" +, Plain [Str "foo"] +, RawHtml "</div>\n" +, Para [Str "And",Space,Str "nested",Space,Str "without",Space,Str "indentation:"] +, RawHtml "<div>\n<div>\n<div>" +, Plain [Str "foo"] +, RawHtml "</div>\n</div>\n<div>" +, Plain [Str "bar"] +, RawHtml "</div>\n</div>\n" +, Para [Str "Interpreted",Space,Str "markdown",Space,Str "in",Space,Str "a",Space,Str "table:"] +, RawHtml "<table>\n<tr>\n<td>" +, Plain [Str "This",Space,Str "is",Space,Emph [Str "emphasized"]] +, RawHtml "</td>\n<td>" +, Plain [Str "And",Space,Str "this",Space,Str "is",Space,Strong [Str "strong"]] +, RawHtml "</td>\n</tr>\n</table>\n\n<script type=\"text/javascript\">document.write('This *should not* be interpreted as markdown');</script>\n" +, Para [Str "Here's",Space,Str "a",Space,Str "simple",Space,Str "block:"] +, RawHtml "<div>\n " +, Plain [Str "foo"] +, RawHtml "</div>\n" +, Para [Str "This",Space,Str "should",Space,Str "be",Space,Str "a",Space,Str "code",Space,Str "block,",Space,Str "though:"] +, CodeBlock "<div>\n foo\n</div>\n" +, Para [Str "As",Space,Str "should",Space,Str "this:"] +, CodeBlock "<div>foo</div>\n" +, Para [Str "Now,",Space,Str "nested:"] +, RawHtml "<div>\n <div>\n <div>\n " +, Plain [Str "foo"] +, RawHtml "</div>\n </div>\n</div>\n" +, Para [Str "This",Space,Str "should",Space,Str "just",Space,Str "be",Space,Str "an",Space,Str "HTML",Space,Str "comment:"] +, RawHtml "<!-- Comment -->\n" +, Para [Str "Multiline:"] +, RawHtml "<!--\nBlah\nBlah\n-->\n\n<!--\n This is another comment.\n-->\n" +, Para [Str "Code",Space,Str "block:"] +, CodeBlock "<!-- Comment -->\n" +, Para [Str "Just",Space,Str "plain",Space,Str "comment,",Space,Str "with",Space,Str "trailing",Space,Str "spaces",Space,Str "on",Space,Str "the",Space,Str "line:"] +, RawHtml "<!-- foo --> \n" +, Para [Str "Code:"] +, CodeBlock "<hr />\n" +, Para [Str "Hr's:"] +, RawHtml "<hr>\n\n<hr />\n\n<hr />\n\n<hr> \n\n<hr /> \n\n<hr /> \n\n<hr class=\"foo\" id=\"bar\" />\n\n<hr class=\"foo\" id=\"bar\" />\n\n<hr class=\"foo\" id=\"bar\">\n" +, HorizontalRule +, Header 1 [Str "Inline",Space,Str "Markup"] +, Para [Str "This",Space,Str "is",Space,Emph [Str "emphasized"],Str ",",Space,Str "and",Space,Str "so",Space,Emph [Str "is",Space,Str "this"],Str "."] +, Para [Str "This",Space,Str "is",Space,Strong [Str "strong"],Str ",",Space,Str "and",Space,Str "so",Space,Strong [Str "is",Space,Str "this"],Str "."] +, Para [Str "An",Space,Emph [Link [Str "emphasized",Space,Str "link"] (Src "/url" "")],Str "."] +, Para [Strong [Emph [Str "This",Space,Str "is",Space,Str "strong",Space,Str "and",Space,Str "em."]]] +, Para [Str "So",Space,Str "is",Space,Strong [Emph [Str "this"]],Space,Str "word."] +, Para [Strong [Emph [Str "This",Space,Str "is",Space,Str "strong",Space,Str "and",Space,Str "em."]]] +, Para [Str "So",Space,Str "is",Space,Strong [Emph [Str "this"]],Space,Str "word."] +, Para [Str "This",Space,Str "is",Space,Str "code:",Space,Code ">",Str ",",Space,Code "$",Str ",",Space,Code "\\",Str ",",Space,Code "\\$",Str ",",Space,Code "<html>",Str "."] +, HorizontalRule +, Header 1 [Str "Smart",Space,Str "quotes,",Space,Str "ellipses,",Space,Str "dashes"] +, Para [Str "\"Hello,\"",Space,Str "said",Space,Str "the",Space,Str "spider.",Space,Str "\"'Shelob'",Space,Str "is",Space,Str "my",Space,Str "name.\""] +, Para [Str "'A',",Space,Str "'B',",Space,Str "and",Space,Str "'C'",Space,Str "are",Space,Str "letters."] +, Para [Str "'Oak,'",Space,Str "'elm,'",Space,Str "and",Space,Str "'beech'",Space,Str "are",Space,Str "names",Space,Str "of",Space,Str "trees.",Space,Str "So",Space,Str "is",Space,Str "'pine.'"] +, Para [Str "'He",Space,Str "said,",Space,Str "\"I",Space,Str "want",Space,Str "to",Space,Str "go.\"'",Space,Str "Were",Space,Str "you",Space,Str "alive",Space,Str "in",Space,Str "the",Space,Str "70's?"] +, Para [Str "Here",Space,Str "is",Space,Str "some",Space,Str "quoted",Space,Str "'",Code "code",Str "'",Space,Str "and",Space,Str "a",Space,Str "\"",Link [Str "quoted",Space,Str "link"] (Ref [Str "1"]),Str "\"."] +, Para [Str "Some",Space,Str "dashes:",Space,Str "one",Str "---",Str "two",Space,Str "---",Space,Str "three",Str "--",Str "four",Space,Str "--",Space,Str "five."] +, Para [Str "Dashes",Space,Str "between",Space,Str "numbers:",Space,Str "5",Str "-",Str "7,",Space,Str "255",Str "-",Str "66,",Space,Str "1987",Str "-",Str "1999."] +, Para [Str "Ellipses...and.",Space,Str ".",Space,Str ".and",Space,Str ".",Space,Str ".",Space,Str ".",Space,Str "."] +, HorizontalRule +, Header 1 [Str "LaTeX"] +, BulletList + [ [ Plain [TeX "\\cite[22-23]{smith.1899}"] ] + , [ Plain [TeX "\\doublespacing"] ] + , [ Plain [TeX "$2+2=4$"] ] + , [ Plain [TeX "$x \\in y$"] ] + , [ Plain [TeX "$\\alpha \\wedge \\omega$"] ] + , [ Plain [TeX "$223$"] ] + , [ Plain [TeX "$p$",Str "-",Str "Tree"] ] + , [ Plain [TeX "$\\frac{d}{dx}f(x)=\\lim_{h\\to 0}\\frac{f(x+h)-f(x)}{h}$"] ] + , [ Plain [Str "Here's",Space,Str "one",Space,Str "that",Space,Str "has",Space,Str "a",Space,Str "line",Space,Str "break",Space,Str "in",Space,Str "it:",Space,TeX "$\\alpha + \\omega \\times x^2$",Str "."] ] ] +, Para [Str "These",Space,Str "shouldn't",Space,Str "be",Space,Str "math:"] +, BulletList + [ [ Plain [Str "To",Space,Str "get",Space,Str "the",Space,Str "famous",Space,Str "equation,",Space,Str "write",Space,Code "$e = mc^2$",Str "."] ] + , [ Plain [Str "$",Str "22,000",Space,Str "is",Space,Str "a",Space,Emph [Str "lot"],Space,Str "of",Space,Str "money.",Space,Str "So",Space,Str "is",Space,Str "$",Str "34,000.",Space,Str "(It",Space,Str "worked",Space,Str "if",Space,Str "\"lot\"",Space,Str "is",Space,Str "emphasized.)"] ] + , [ Plain [Str "Escaped",Space,Code "$",Str ":",Space,Str "$",Str "73",Space,Emph [Str "this",Space,Str "should",Space,Str "be",Space,Str "emphasized"],Space,Str "23",Str "$",Str "."] ] ] +, Para [Str "Here's",Space,Str "a",Space,Str "LaTeX",Space,Str "table:"] +, Para [TeX "\\begin{tabular}{|l|l|}\\hline\nAnimal & Number \\\\ \\hline\nDog & 2 \\\\\nCat & 1 \\\\ \\hline\n\\end{tabular}"] +, HorizontalRule +, Header 1 [Str "Special",Space,Str "Characters"] +, Para [Str "Here",Space,Str "is",Space,Str "some",Space,Str "unicode:"] +, BulletList + [ [ Plain [Str "I",Space,Str "hat:",Space,Str "\206"] ] + , [ Plain [Str "o",Space,Str "umlaut:",Space,Str "\246"] ] + , [ Plain [Str "section:",Space,Str "\167"] ] + , [ Plain [Str "set",Space,Str "membership:",Space,Str "\8712"] ] + , [ Plain [Str "copyright:",Space,Str "\169"] ] ] +, Para [Str "AT&T",Space,Str "has",Space,Str "an",Space,Str "ampersand",Space,Str "in",Space,Str "their",Space,Str "name."] +, Para [Str "AT&T",Space,Str "is",Space,Str "another",Space,Str "way",Space,Str "to",Space,Str "write",Space,Str "it."] +, Para [Str "This",Space,Str "&",Space,Str "that."] +, Para [Str "4",Space,Str "<",Space,Str "5."] +, Para [Str "6",Space,Str ">",Space,Str "5."] +, Para [Str "Backslash:",Space,Str "\\"] +, Para [Str "Backtick:",Space,Str "`"] +, Para [Str "Asterisk:",Space,Str "*"] +, Para [Str "Underscore:",Space,Str "_"] +, Para [Str "Left",Space,Str "brace:",Space,Str "{"] +, Para [Str "Right",Space,Str "brace:",Space,Str "}"] +, Para [Str "Left",Space,Str "bracket:",Space,Str "["] +, Para [Str "Right",Space,Str "bracket:",Space,Str "]"] +, Para [Str "Left",Space,Str "paren:",Space,Str "("] +, Para [Str "Right",Space,Str "paren:",Space,Str ")"] +, Para [Str "Greater",Str "-",Str "than:",Space,Str ">"] +, Para [Str "Hash:",Space,Str "#"] +, Para [Str "Period:",Space,Str "."] +, Para [Str "Bang:",Space,Str "!"] +, Para [Str "Plus:",Space,Str "+"] +, Para [Str "Minus:",Space,Str "-"] +, HorizontalRule +, Header 1 [Str "Links"] +, Header 2 [Str "Explicit"] +, Para [Str "Just",Space,Str "a",Space,Link [Str "URL"] (Src "/url/" ""),Str "."] +, Para [Link [Str "URL",Space,Str "and",Space,Str "title"] (Src "/url/" "title"),Str "."] +, Para [Link [Str "URL",Space,Str "and",Space,Str "title"] (Src "/url/" "title preceded by two spaces"),Str "."] +, Para [Link [Str "URL",Space,Str "and",Space,Str "title"] (Src "/url/" "title preceded by a tab"),Str "."] +, Para [Link [Str "URL",Space,Str "and",Space,Str "title"] (Src "/url/" "title with "quotes" in it")] +, Para [Link [Str "URL",Space,Str "and",Space,Str "title"] (Src "/url/" "title with single quotes")] +, Para [Link [Str "Email",Space,Str "link"] (Src "mailto:nobody@nowhere.net" "")] +, Para [Link [Str "Empty"] (Src "" ""),Str "."] +, Header 2 [Str "Reference"] +, Para [Str "Foo",Space,Link [Str "bar"] (Ref [Str "a"]),Str "."] +, Para [Str "Foo",Space,Link [Str "bar"] (Ref [Str "a"]),Str "."] +, Para [Str "Foo",Space,Link [Str "bar"] (Ref [Str "a"]),Str "."] +, Key [Str "a"] (Src "/url/" "") +, Para [Str "With",Space,Link [Str "embedded",Space,Link [Str "brackets"] (Ref [])] (Ref [Str "b"]),Str "."] +, Para [Link [Str "b"] (Ref []),Space,Str "by",Space,Str "itself",Space,Str "should",Space,Str "be",Space,Str "a",Space,Str "link."] +, Para [Str "Indented",Space,Link [Str "once"] (Ref []),Str "."] +, Para [Str "Indented",Space,Link [Str "twice"] (Ref []),Str "."] +, Para [Str "Indented",Space,Link [Str "thrice"] (Ref []),Str "."] +, Para [Str "This",Space,Str "should",Space,Link [Str "not"] (Ref []),Space,Str "be",Space,Str "a",Space,Str "link."] +, Key [Str "once"] (Src "/url" "") +, Key [Str "twice"] (Src "/url" "") +, Key [Str "thrice"] (Src "/url" "") +, CodeBlock "[not]: /url\n" +, Key [Str "b"] (Src "/url/" "") +, Para [Str "Foo",Space,Link [Str "bar"] (Ref []),Str "."] +, Para [Str "Foo",Space,Link [Str "biz"] (Src "/url/" "Title with "quote" inside"),Str "."] +, Key [Str "bar"] (Src "/url/" "Title with "quotes" inside") +, Header 2 [Str "With",Space,Str "ampersands"] +, Para [Str "Here's",Space,Str "a",Space,Link [Str "link",Space,Str "with",Space,Str "an",Space,Str "ampersand",Space,Str "in",Space,Str "the",Space,Str "URL"] (Ref [Str "1"]),Str "."] +, Para [Str "Here's",Space,Str "a",Space,Str "link",Space,Str "with",Space,Str "an",Space,Str "amersand",Space,Str "in",Space,Str "the",Space,Str "link",Space,Str "text:",Space,Link [Str "AT&T"] (Ref [Str "2"]),Str "."] +, Para [Str "Here's",Space,Str "an",Space,Link [Str "inline",Space,Str "link"] (Src "/script?foo=1&bar=2" ""),Str "."] +, Para [Str "Here's",Space,Str "an",Space,Link [Str "inline",Space,Str "link",Space,Str "in",Space,Str "pointy",Space,Str "braces"] (Src "/script?foo=1&bar=2" ""),Str "."] +, Key [Str "1"] (Src "http://example.com/?foo=1&bar=2" "") +, Key [Str "2"] (Src "http://att.com/" "AT&T") +, Header 2 [Str "Autolinks"] +, Para [Str "With",Space,Str "an",Space,Str "ampersand:",Space,Link [Str "http://example.com/?foo=1&bar=2"] (Src "http://example.com/?foo=1&bar=2" "")] +, BulletList + [ [ Plain [Str "In",Space,Str "a",Space,Str "list?"] ] + , [ Plain [Link [Str "http://example.com/"] (Src "http://example.com/" "")] ] + , [ Plain [Str "It",Space,Str "should."] ] ] +, Para [Str "An",Space,Str "e",Str "-",Str "mail",Space,Str "address:",Space,Link [Str "nobody@nowhere.net"] (Src "mailto:nobody@nowhere.net" "")] +, BlockQuote + [ Para [Str "Blockquoted:",Space,Link [Str "http://example.com/"] (Src "http://example.com/" "")] ] + +, Para [Str "Auto",Str "-",Str "links",Space,Str "should",Space,Str "not",Space,Str "occur",Space,Str "here:",Space,Code "<http://example.com/>"] +, CodeBlock "or here: <http://example.com/>\n" +, HorizontalRule +, Header 1 [Str "Images"] +, Para [Str "From",Space,Str "\"Voyage",Space,Str "dans",Space,Str "la",Space,Str "Lune\"",Space,Str "by",Space,Str "Georges",Space,Str "Melies",Space,Str "(1902):"] +, Para [Image [Str "lalune"] (Ref [])] +, Key [Str "lalune"] (Src "lalune.jpg" "Voyage dans la Lune") +, Para [Str "Here",Space,Str "is",Space,Str "a",Space,Str "movie",Space,Image [Str "movie"] (Src "movie.jpg" ""),Space,Str "icon."] +, HorizontalRule +, Header 1 [Str "Footnotes"] +, Para [Str "Here",Space,Str "is",Space,Str "a",Space,Str "footnote",Space,Str "reference",NoteRef "1",Str ",",Space,Str "and",Space,Str "another",NoteRef "longnote",Str ".",Space,Str "This",Space,Str "should",Space,Emph [Str "not"],Space,Str "be",Space,Str "a",Space,Str "footnote",Space,Str "reference,",Space,Str "because",Space,Str "it",Space,Str "contains",Space,Str "a",Space,Str "space",Str "^",Str "(my",Space,Str "note)."] +, Note "1" + [ Para [Str "Here",Space,Str "is",Space,Str "the",Space,Str "footnote.",Space,Str "It",Space,Str "can",Space,Str "go",Space,Str "anywhere",Space,Str "in",Space,Str "the",Space,Str "document,",Space,Str "not",Space,Str "just",Space,Str "at",Space,Str "the",Space,Str "end."] ] + +, Note "longnote" + [ Para [Str "Here's",Space,Str "the",Space,Str "other",Space,Str "note.",Space,Str "This",Space,Str "one",Space,Str "contains",Space,Str "multiple",Space,Str "blocks."] + , Para [Str "Caret",Space,Str "characters",Space,Str "are",Space,Str "used",Space,Str "to",Space,Str "indicate",Space,Str "that",Space,Str "the",Space,Str "blocks",Space,Str "all",Space,Str "belong",Space,Str "to",Space,Str "a",Space,Str "single",Space,Str "footnote",Space,Str "(as",Space,Str "with",Space,Str "block",Space,Str "quotes)."] + , CodeBlock " { <code> }\n" + , Para [Str "If",Space,Str "you",Space,Str "want,",Space,Str "you",Space,Str "can",Space,Str "use",Space,Str "a",Space,Str "caret",Space,Str "at",Space,Str "the",Space,Str "beginning",Space,Str "of",Space,Str "every",Space,Str "line,",Space,Str "as",Space,Str "with",Space,Str "blockquotes,",Space,Str "but",Space,Str "all",Space,Str "that",Space,Str "you",Space,Str "need",Space,Str "is",Space,Str "a",Space,Str "caret",Space,Str "at",Space,Str "the",Space,Str "beginning",Space,Str "of",Space,Str "the",Space,Str "first",Space,Str "line",Space,Str "of",Space,Str "the",Space,Str "block",Space,Str "and",Space,Str "any",Space,Str "preceding",Space,Str "blank",Space,Str "lines."] ] ] diff --git a/tests/writer.rst b/tests/writer.rst new file mode 100644 index 000000000..cd67cdaba --- /dev/null +++ b/tests/writer.rst @@ -0,0 +1,743 @@ +================= +Pandoc Test Suite +================= + +:Author: John MacFarlane +:Author: Anonymous +:Date: July 17, 2006 + +This is a set of tests for pandoc. Most of them are adapted from +John Gruber's markdown test suite. + +-------------- + +Headers +======= + +Level 2 with an `embedded link`_ +-------------------------------- + +Level 3 with *emphasis* +~~~~~~~~~~~~~~~~~~~~~~~ + +Level 4 +^^^^^^^ + +Level 5 +''''''' + +Level 1 +======= + +Level 2 with *emphasis* +----------------------- + +Level 3 +~~~~~~~ + +with no blank line + +Level 2 +------- + +with no blank line + +-------------- + +Paragraphs +========== + +Here's a regular paragraph. + +In Markdown 1.0.0 and earlier. Version 8. This line turns into a +list item. Because a hard-wrapped line in the middle of a paragraph +looked like a list item. + +Here's one with a bullet. \* criminey. + +There should be a hard line break here. + +-------------- + +Block Quotes +============ + +E-mail style: + + This is a block quote. It is pretty short. + + + Code in a block quote: + + :: + + sub status { + print "working"; + } + + A list: + + 1. item one + 2. item two + + Nested block quotes: + + nested + + + nested + + + +This should not be a block quote: 2 > 1. + +Box-style: + + Example: + + :: + + sub status { + print "working"; + } + + + 1. do laundry + 2. take out the trash + + +Here's a nested one: + + Joe said: + + Don't quote me. + + + +And a following paragraph. + +-------------- + +Code Blocks +=========== + +Code: + +:: + + ---- (should be four hyphens) + + sub status { + print "working"; + } + + this code block is indented by one tab + +And: + +:: + + this code block is indented by two tabs + + These should not be escaped: \$ \\ \> \[ \{ + +-------------- + +Lists +===== + +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 1. 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 + + +Tabs and spaces +--------------- + +- this is a list item indented with tabs + +- this is a list item indented with spaces + + - this is an example list item indented with tabs + + - this is an example list item indented with spaces + + + +-------------- + +HTML Blocks +=========== + +Simple block on one line: + + +.. raw:: html + + <div> + +foo + +.. raw:: html + + </div> + +And nested without indentation: + + +.. raw:: html + + <div> + <div> + <div> + +foo + +.. raw:: html + + </div> + </div> + <div> + +bar + +.. raw:: html + + </div> + </div> + +Interpreted markdown in a table: + + +.. raw:: html + + <table> + <tr> + <td> + +This is *emphasized* + +.. raw:: html + + </td> + <td> + +And this is **strong** + +.. raw:: html + + </td> + </tr> + </table> + + <script type="text/javascript">document.write('This *should not* be interpreted as markdown');</script> + +Here's a simple block: + + +.. raw:: html + + <div> + + +foo + +.. raw:: html + + </div> + +This should be a code block, though: + +:: + + <div> + foo + </div> + +As should this: + +:: + + <div>foo</div> + +Now, nested: + + +.. raw:: html + + <div> + <div> + <div> + + +foo + +.. raw:: html + + </div> + </div> + </div> + +This should just be an HTML comment: + + +.. raw:: html + + <!-- Comment --> + +Multiline: + + +.. raw:: html + + <!-- + Blah + Blah + --> + + <!-- + This is another comment. + --> + +Code block: + +:: + + <!-- Comment --> + +Just plain comment, with trailing spaces on the line: + + +.. raw:: html + + <!-- foo --> + +Code: + +:: + + <hr /> + +Hr's: + + +.. raw:: html + + <hr> + + <hr /> + + <hr /> + + <hr> + + <hr /> + + <hr /> + + <hr class="foo" id="bar" /> + + <hr class="foo" id="bar" /> + + <hr class="foo" id="bar"> + +-------------- + +Inline Markup +============= + +This is *emphasized*, and so *is this*. + +This is **strong**, and so **is this**. + +An *`emphasized link`_*. + +***This is strong and em.*** + +So is ***this*** word. + +***This is strong and em.*** + +So is ***this*** word. + +This is code: ``>``, ``$``, ``\``, ``\$``, ``<html>``. + +-------------- + +Smart quotes, ellipses, dashes +============================== + +"Hello," said the spider. "'Shelob' is my name." + +'A', 'B', and 'C' are letters. + +'Oak,' 'elm,' and 'beech' are names of trees. So is 'pine.' + +'He said, "I want to go."' Were you alive in the 70's? + +Here is some quoted '``code``' and a "`quoted link`_". + +Some dashes: one---two --- three--four -- five. + +Dashes between numbers: 5-7, 255-66, 1987-1999. + +Ellipses...and. . .and . . . . + +-------------- + +LaTeX +===== + +- \cite[22-23]{smith.1899} +- \doublespacing +- $2+2=4$ +- $x \in y$ +- $\alpha \wedge \omega$ +- $223$ +- $p$-Tree +- $\frac{d}{dx}f(x)=\lim_{h\to 0}\frac{f(x+h)-f(x)}{h}$ +- Here's one that has a line break in it: + $\alpha + \omega \times x^2$. + +These shouldn't be math: + +- To get the famous equation, write ``$e = mc^2$``. +- $22,000 is a *lot* of money. So is $34,000. (It worked if "lot" + is emphasized.) +- Escaped ``$``: $73 *this should be emphasized* 23$. + +Here's a LaTeX table: + + +.. raw:: latex + + \begin{tabular}{|l|l|}\hline + Animal & Number \\ \hline + Dog & 2 \\ + Cat & 1 \\ \hline + \end{tabular} + +-------------- + +Special Characters +================== + +Here is some unicode: + +- I hat: Î +- o umlaut: ö +- section: § +- set membership: ∈ +- copyright: © + +AT&T has an ampersand in their name. + +AT&T is another way to write it. + +This & that. + +4 < 5. + +6 > 5. + +Backslash: \\ + +Backtick: \` + +Asterisk: \* + +Underscore: \_ + +Left brace: { + +Right brace: } + +Left bracket: [ + +Right bracket: ] + +Left paren: ( + +Right paren: ) + +Greater-than: > + +Hash: # + +Period: . + +Bang: ! + +Plus: + + +Minus: - + +-------------- + +Links +===== + +Explicit +-------- + +Just a `URL`_. + +`URL and title`_. + +`URL and title`_. + +`URL and title`_. + +`URL and title`_ + +`URL and title`_ + +`Email link`_ + +`Empty`_. + +Reference +--------- + +Foo `bar`_. + +Foo `bar`_. + +Foo `bar`_. + +With `embedded [brackets]`_. + +`b`_ by itself should be a link. + +Indented `once`_. + +Indented `twice`_. + +Indented `thrice`_. + +This should [not] be a link. + +:: + + [not]: /url + +Foo `bar`_. + +Foo `biz`_. + +With ampersands +--------------- + +Here's a `link with an ampersand in the URL`_. + +Here's a link with an amersand in the link text: `AT&T`_. + +Here's an `inline link`_. + +Here's an `inline link in pointy braces`_. + +Autolinks +--------- + +With an ampersand: `http://example.com/?foo=1&bar=2`_ + +- In a list? +- `http://example.com/`_ +- It should. + +An e-mail address: `nobody@nowhere.net`_ + + Blockquoted: `http://example.com/`_ + + +Auto-links should not occur here: ``<http://example.com/>`` + +:: + + or here: <http://example.com/> + +-------------- + +Images +====== + +From "Voyage dans la Lune" by Georges Melies (1902): + +|lalune| + +Here is a movie |movie| icon. + +-------------- + +Footnotes +========= + +Here is a footnote reference [1]_, and another [longnote]_. This +should *not* be a footnote reference, because it contains a +space^(my note). + +.. [1] + Here is the footnote. It can go anywhere in the document, not just + at the end. + +.. [longnote] + Here's the other note. This one contains multiple blocks. + + Caret characters are used to indicate that the blocks all belong to + a single footnote (as with block quotes). + + :: + + { <code> } + + If you want, you can use a caret at the beginning of every line, as + with blockquotes, but all that you need is a caret at the beginning + of the first line of the block and any preceding blank lines. + + +.. _embedded link: /url +.. _emphasized link: /url +.. _quoted link: http://example.com/?foo=1&bar=2 +.. _URL: /url/ +.. _URL and title: /url/ +.. _Email link: mailto:nobody@nowhere.net +.. _Empty: +.. _bar: /url/ +.. _embedded [brackets]: /url/ +.. _b: /url/ +.. _once: /url +.. _twice: /url +.. _thrice: /url +.. _biz: /url/ +.. _link with an ampersand in the URL: http://example.com/?foo=1&bar=2 +.. _AT&T: http://att.com/ +.. _inline link: /script?foo=1&bar=2 +.. _inline link in pointy braces: /script?foo=1&bar=2 +.. _`http://example.com/?foo=1&bar=2`: http://example.com/?foo=1&bar=2 +.. _`http://example.com/`: http://example.com/ +.. _nobody@nowhere.net: mailto:nobody@nowhere.net +.. |lalune| image:: lalune.jpg +.. |movie| image:: movie.jpg diff --git a/tests/writer.rtf b/tests/writer.rtf new file mode 100644 index 000000000..84c82aa9b --- /dev/null +++ b/tests/writer.rtf @@ -0,0 +1,378 @@ +{\rtf1\ansi\deff0{\fonttbl{\f0 Times New Roman;}{\f1 Courier;}} +{\colortbl;\red255\green0\blue0;\red0\green0\blue255;} +\widowctrl\hyphauto + +{\pard \sa180 \li0 \fi0 \qc \b \fs36 Pandoc Test Suite\par} +{\pard \sa180 \li0 \fi0 \qc John MacFarlane\Anonymous\par} +{\pard \sa180 \li0 \fi0 \qc July 17, 2006\par} +{\pard \sa180 \li0 \fi0 \par} +{\pard \sa180 \li0 \fi0 This is a set of tests for pandoc. Most of them are adapted from John Gruber's markdown test suite.\par} +{\pard \sa180 \li0 \fi0 \qc \emdash\emdash\emdash\emdash\emdash\par} +{\pard \sa180 \li0 \fi0 \b \fs36 Headers\par} +{\pard \sa180 \li0 \fi0 \b \fs32 Level 2 with an {\field{\*\fldinst{HYPERLINK "/url"}}{\fldrslt{\ul +embedded link +}}} +\par} +{\pard \sa180 \li0 \fi0 \b \fs28 Level 3 with {\i emphasis} \par} +{\pard \sa180 \li0 \fi0 \b \fs24 Level 4\par} +{\pard \sa180 \li0 \fi0 \b \fs20 Level 5\par} +{\pard \sa180 \li0 \fi0 \b \fs36 Level 1\par} +{\pard \sa180 \li0 \fi0 \b \fs32 Level 2 with {\i emphasis} \par} +{\pard \sa180 \li0 \fi0 \b \fs28 Level 3\par} +{\pard \sa180 \li0 \fi0 with no blank line\par} +{\pard \sa180 \li0 \fi0 \b \fs32 Level 2\par} +{\pard \sa180 \li0 \fi0 with no blank line\par} +{\pard \sa180 \li0 \fi0 \qc \emdash\emdash\emdash\emdash\emdash\par} +{\pard \sa180 \li0 \fi0 \b \fs36 Paragraphs\par} +{\pard \sa180 \li0 \fi0 Here's a regular paragraph.\par} +{\pard \sa180 \li0 \fi0 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.\par} +{\pard \sa180 \li0 \fi0 Here's one with a bullet. * criminey.\par} +{\pard \sa180 \li0 \fi0 There should be a hard line break\line here.\par} +{\pard \sa180 \li0 \fi0 \qc \emdash\emdash\emdash\emdash\emdash\par} +{\pard \sa180 \li0 \fi0 \b \fs36 Block Quotes\par} +{\pard \sa180 \li0 \fi0 E-mail style:\par} +{\pard \sa180 \li720 \fi0 This is a block quote. It is pretty short.\par} +{\pard \sa180 \li720 \fi0 Code in a block quote:\par} +{\pard \sa180 \li720 \fi0 \f1 sub status \{\line + print "working";\line +\}\par} +{\pard \sa180 \li720 \fi0 A list:\par} +{\pard \sa0 \li1080 \fi-360 1.\tx360\tab item one\par} +{\pard \sa0 \li1080 \fi-360 2.\tx360\tab item two\sa180\par} +{\pard \sa180 \li720 \fi0 Nested block quotes:\par} +{\pard \sa180 \li1440 \fi0 nested\par} +{\pard \sa180 \li1440 \fi0 nested\par} +{\pard \sa180 \li0 \fi0 This should not be a block quote: 2 > 1.\par} +{\pard \sa180 \li0 \fi0 Box-style:\par} +{\pard \sa180 \li720 \fi0 Example:\par} +{\pard \sa180 \li720 \fi0 \f1 sub status \{\line + print "working";\line +\}\par} +{\pard \sa0 \li1080 \fi-360 1.\tx360\tab do laundry\par} +{\pard \sa0 \li1080 \fi-360 2.\tx360\tab take out the trash\sa180\par} +{\pard \sa180 \li0 \fi0 Here's a nested one:\par} +{\pard \sa180 \li720 \fi0 Joe said:\par} +{\pard \sa180 \li1440 \fi0 Don't quote me.\par} +{\pard \sa180 \li0 \fi0 And a following paragraph.\par} +{\pard \sa180 \li0 \fi0 \qc \emdash\emdash\emdash\emdash\emdash\par} +{\pard \sa180 \li0 \fi0 \b \fs36 Code Blocks\par} +{\pard \sa180 \li0 \fi0 Code:\par} +{\pard \sa180 \li0 \fi0 \f1 ---- (should be four hyphens)\line +\line +sub status \{\line + print "working";\line +\}\line +\line +this code block is indented by one tab\par} +{\pard \sa180 \li0 \fi0 And:\par} +{\pard \sa180 \li0 \fi0 \f1 this code block is indented by two tabs\line +\line +These should not be escaped: \\$ \\\\ \\> \\[ \\\{\par} +{\pard \sa180 \li0 \fi0 \qc \emdash\emdash\emdash\emdash\emdash\par} +{\pard \sa180 \li0 \fi0 \b \fs36 Lists\par} +{\pard \sa180 \li0 \fi0 \b \fs32 Unordered\par} +{\pard \sa180 \li0 \fi0 Asterisks tight:\par} +{\pard \sa0 \li360 \fi-360 \bullet \tx360\tab asterisk 1\par} +{\pard \sa0 \li360 \fi-360 \bullet \tx360\tab asterisk 2\par} +{\pard \sa0 \li360 \fi-360 \bullet \tx360\tab asterisk 3\sa180\par} +{\pard \sa180 \li0 \fi0 Asterisks loose:\par} +{\pard \sa180 \li360 \fi-360 \bullet \tx360\tab asterisk 1\par} +{\pard \sa180 \li360 \fi-360 \bullet \tx360\tab asterisk 2\par} +{\pard \sa180 \li360 \fi-360 \bullet \tx360\tab asterisk 3\sa180\par} +{\pard \sa180 \li0 \fi0 Pluses tight:\par} +{\pard \sa0 \li360 \fi-360 \bullet \tx360\tab Plus 1\par} +{\pard \sa0 \li360 \fi-360 \bullet \tx360\tab Plus 2\par} +{\pard \sa0 \li360 \fi-360 \bullet \tx360\tab Plus 3\sa180\par} +{\pard \sa180 \li0 \fi0 Pluses loose:\par} +{\pard \sa180 \li360 \fi-360 \bullet \tx360\tab Plus 1\par} +{\pard \sa180 \li360 \fi-360 \bullet \tx360\tab Plus 2\par} +{\pard \sa180 \li360 \fi-360 \bullet \tx360\tab Plus 3\sa180\par} +{\pard \sa180 \li0 \fi0 Minuses tight:\par} +{\pard \sa0 \li360 \fi-360 \bullet \tx360\tab Minus 1\par} +{\pard \sa0 \li360 \fi-360 \bullet \tx360\tab Minus 2\par} +{\pard \sa0 \li360 \fi-360 \bullet \tx360\tab Minus 3\sa180\par} +{\pard \sa180 \li0 \fi0 Minuses loose:\par} +{\pard \sa180 \li360 \fi-360 \bullet \tx360\tab Minus 1\par} +{\pard \sa180 \li360 \fi-360 \bullet \tx360\tab Minus 2\par} +{\pard \sa180 \li360 \fi-360 \bullet \tx360\tab Minus 3\sa180\par} +{\pard \sa180 \li0 \fi0 \b \fs32 Ordered\par} +{\pard \sa180 \li0 \fi0 Tight:\par} +{\pard \sa0 \li360 \fi-360 1.\tx360\tab First\par} +{\pard \sa0 \li360 \fi-360 2.\tx360\tab Second\par} +{\pard \sa0 \li360 \fi-360 3.\tx360\tab Third\sa180\par} +{\pard \sa180 \li0 \fi0 and:\par} +{\pard \sa0 \li360 \fi-360 1.\tx360\tab One\par} +{\pard \sa0 \li360 \fi-360 2.\tx360\tab Two\par} +{\pard \sa0 \li360 \fi-360 3.\tx360\tab Three\sa180\par} +{\pard \sa180 \li0 \fi0 Loose using tabs:\par} +{\pard \sa180 \li360 \fi-360 1.\tx360\tab First\par} +{\pard \sa180 \li360 \fi-360 2.\tx360\tab Second\par} +{\pard \sa180 \li360 \fi-360 3.\tx360\tab Third\sa180\par} +{\pard \sa180 \li0 \fi0 and using spaces:\par} +{\pard \sa180 \li360 \fi-360 1.\tx360\tab One\par} +{\pard \sa180 \li360 \fi-360 2.\tx360\tab Two\par} +{\pard \sa180 \li360 \fi-360 3.\tx360\tab Three\sa180\par} +{\pard \sa180 \li0 \fi0 Multiple paragraphs:\par} +{\pard \sa180 \li360 \fi-360 1.\tx360\tab Item 1, graf one.\par} +{\pard \sa180 \li360 \fi0 Item 1. graf two. The quick brown fox jumped over the lazy dog's back.\par} +{\pard \sa180 \li360 \fi-360 2.\tx360\tab Item 2.\par} +{\pard \sa180 \li360 \fi-360 3.\tx360\tab Item 3.\sa180\par} +{\pard \sa180 \li0 \fi0 \b \fs32 Nested\par} +{\pard \sa0 \li360 \fi-360 \bullet \tx360\tab Tab\par} +{\pard \sa0 \li720 \fi-360 \endash \tx360\tab Tab\par} +{\pard \sa0 \li1080 \fi-360 \bullet \tx360\tab Tab\sa180\sa180\sa180\par} +{\pard \sa180 \li0 \fi0 Here's another:\par} +{\pard \sa0 \li360 \fi-360 1.\tx360\tab First\par} +{\pard \sa0 \li360 \fi-360 2.\tx360\tab Second:\par} +{\pard \sa0 \li720 \fi-360 \endash \tx360\tab Fee\par} +{\pard \sa0 \li720 \fi-360 \endash \tx360\tab Fie\par} +{\pard \sa0 \li720 \fi-360 \endash \tx360\tab Foe\sa180\par} +{\pard \sa0 \li360 \fi-360 3.\tx360\tab Third\sa180\par} +{\pard \sa180 \li0 \fi0 Same thing but with paragraphs:\par} +{\pard \sa180 \li360 \fi-360 1.\tx360\tab First\par} +{\pard \sa180 \li360 \fi-360 2.\tx360\tab Second:\par} +{\pard \sa0 \li720 \fi-360 \endash \tx360\tab Fee\par} +{\pard \sa0 \li720 \fi-360 \endash \tx360\tab Fie\par} +{\pard \sa0 \li720 \fi-360 \endash \tx360\tab Foe\sa180\par} +{\pard \sa180 \li360 \fi-360 3.\tx360\tab Third\sa180\par} +{\pard \sa180 \li0 \fi0 \b \fs32 Tabs and spaces\par} +{\pard \sa180 \li360 \fi-360 \bullet \tx360\tab this is a list item indented with tabs\par} +{\pard \sa180 \li360 \fi-360 \bullet \tx360\tab this is a list item indented with spaces\par} +{\pard \sa180 \li720 \fi-360 \endash \tx360\tab this is an example list item indented with tabs\par} +{\pard \sa180 \li720 \fi-360 \endash \tx360\tab this is an example list item indented with spaces\sa180\sa180\par} +{\pard \sa180 \li0 \fi0 \qc \emdash\emdash\emdash\emdash\emdash\par} +{\pard \sa180 \li0 \fi0 \b \fs36 HTML Blocks\par} +{\pard \sa180 \li0 \fi0 Simple block on one line:\par} +{\pard \sa0 \li0 \fi0 foo\par} +{\pard \sa180 \li0 \fi0 And nested without indentation:\par} +{\pard \sa0 \li0 \fi0 foo\par} +{\pard \sa0 \li0 \fi0 bar\par} +{\pard \sa180 \li0 \fi0 Interpreted markdown in a table:\par} +{\pard \sa0 \li0 \fi0 This is {\i emphasized} \par} +{\pard \sa0 \li0 \fi0 And this is {\b strong} \par} +{\pard \sa180 \li0 \fi0 Here's a simple block:\par} +{\pard \sa0 \li0 \fi0 foo\par} +{\pard \sa180 \li0 \fi0 This should be a code block, though:\par} +{\pard \sa180 \li0 \fi0 \f1 <div>\line + foo\line +</div>\par} +{\pard \sa180 \li0 \fi0 As should this:\par} +{\pard \sa180 \li0 \fi0 \f1 <div>foo</div>\par} +{\pard \sa180 \li0 \fi0 Now, nested:\par} +{\pard \sa0 \li0 \fi0 foo\par} +{\pard \sa180 \li0 \fi0 This should just be an HTML comment:\par} +{\pard \sa180 \li0 \fi0 Multiline:\par} +{\pard \sa180 \li0 \fi0 Code block:\par} +{\pard \sa180 \li0 \fi0 \f1 <!-- Comment -->\par} +{\pard \sa180 \li0 \fi0 Just plain comment, with trailing spaces on the line:\par} +{\pard \sa180 \li0 \fi0 Code:\par} +{\pard \sa180 \li0 \fi0 \f1 <hr />\par} +{\pard \sa180 \li0 \fi0 Hr's:\par} +{\pard \sa180 \li0 \fi0 \qc \emdash\emdash\emdash\emdash\emdash\par} +{\pard \sa180 \li0 \fi0 \b \fs36 Inline Markup\par} +{\pard \sa180 \li0 \fi0 This is {\i emphasized} , and so {\i is this} .\par} +{\pard \sa180 \li0 \fi0 This is {\b strong} , and so {\b is this} .\par} +{\pard \sa180 \li0 \fi0 An {\i {\field{\*\fldinst{HYPERLINK "/url"}}{\fldrslt{\ul +emphasized link +}}} +} .\par} +{\pard \sa180 \li0 \fi0 {\b {\i This is strong and em.} } \par} +{\pard \sa180 \li0 \fi0 So is {\b {\i this} } word.\par} +{\pard \sa180 \li0 \fi0 {\b {\i This is strong and em.} } \par} +{\pard \sa180 \li0 \fi0 So is {\b {\i this} } word.\par} +{\pard \sa180 \li0 \fi0 This is code: {\f1 >} , {\f1 $} , {\f1 \\} , {\f1 \\$} , {\f1 <html>} .\par} +{\pard \sa180 \li0 \fi0 \qc \emdash\emdash\emdash\emdash\emdash\par} +{\pard \sa180 \li0 \fi0 \b \fs36 Smart quotes, ellipses, dashes\par} +{\pard \sa180 \li0 \fi0 "Hello," said the spider. "'Shelob' is my name."\par} +{\pard \sa180 \li0 \fi0 'A', 'B', and 'C' are letters.\par} +{\pard \sa180 \li0 \fi0 'Oak,' 'elm,' and 'beech' are names of trees. So is 'pine.'\par} +{\pard \sa180 \li0 \fi0 'He said, "I want to go."' Were you alive in the 70's?\par} +{\pard \sa180 \li0 \fi0 Here is some quoted '{\f1 code} ' and a "{\field{\*\fldinst{HYPERLINK "http://example.com/?foo=1&bar=2"}}{\fldrslt{\ul +quoted link +}}} +".\par} +{\pard \sa180 \li0 \fi0 Some dashes: one---two --- three--four -- five.\par} +{\pard \sa180 \li0 \fi0 Dashes between numbers: 5-7, 255-66, 1987-1999.\par} +{\pard \sa180 \li0 \fi0 Ellipses...and. . .and . . . .\par} +{\pard \sa180 \li0 \fi0 \qc \emdash\emdash\emdash\emdash\emdash\par} +{\pard \sa180 \li0 \fi0 \b \fs36 LaTeX\par} +{\pard \sa0 \li360 \fi-360 \bullet \tx360\tab {\cf1 \\cite[22-23]\{smith.1899\}\cf0 } \par} +{\pard \sa0 \li360 \fi-360 \bullet \tx360\tab {\cf1 \\doublespacing\cf0 } \par} +{\pard \sa0 \li360 \fi-360 \bullet \tx360\tab {\cf1 $2+2=4$\cf0 } \par} +{\pard \sa0 \li360 \fi-360 \bullet \tx360\tab {\cf1 $x \\in y$\cf0 } \par} +{\pard \sa0 \li360 \fi-360 \bullet \tx360\tab {\cf1 $\\alpha \\wedge \\omega$\cf0 } \par} +{\pard \sa0 \li360 \fi-360 \bullet \tx360\tab {\cf1 $223$\cf0 } \par} +{\pard \sa0 \li360 \fi-360 \bullet \tx360\tab {\cf1 $p$\cf0 } -Tree\par} +{\pard \sa0 \li360 \fi-360 \bullet \tx360\tab {\cf1 $\\frac\{d\}\{dx\}f(x)=\\lim_\{h\\to 0\}\\frac\{f(x+h)-f(x)\}\{h\}$\cf0 } \par} +{\pard \sa0 \li360 \fi-360 \bullet \tx360\tab Here's one that has a line break in it: {\cf1 $\\alpha + \\omega \\times x^2$\cf0 } .\sa180\par} +{\pard \sa180 \li0 \fi0 These shouldn't be math:\par} +{\pard \sa0 \li360 \fi-360 \bullet \tx360\tab To get the famous equation, write {\f1 $e = mc^2$} .\par} +{\pard \sa0 \li360 \fi-360 \bullet \tx360\tab $22,000 is a {\i lot} of money. So is $34,000. (It worked if "lot" is emphasized.)\par} +{\pard \sa0 \li360 \fi-360 \bullet \tx360\tab Escaped {\f1 $} : $73 {\i this should be emphasized} 23$.\sa180\par} +{\pard \sa180 \li0 \fi0 Here's a LaTeX table:\par} +{\pard \sa180 \li0 \fi0 {\cf1 \\begin\{tabular\}\{|l|l|\}\\hline +Animal & Number \\\\ \\hline +Dog & 2 \\\\ +Cat & 1 \\\\ \\hline +\\end\{tabular\}\cf0 } \par} +{\pard \sa180 \li0 \fi0 \qc \emdash\emdash\emdash\emdash\emdash\par} +{\pard \sa180 \li0 \fi0 \b \fs36 Special Characters\par} +{\pard \sa180 \li0 \fi0 Here is some unicode:\par} +{\pard \sa0 \li360 \fi-360 \bullet \tx360\tab I hat: \u206?\par} +{\pard \sa0 \li360 \fi-360 \bullet \tx360\tab o umlaut: \u246?\par} +{\pard \sa0 \li360 \fi-360 \bullet \tx360\tab section: \u167?\par} +{\pard \sa0 \li360 \fi-360 \bullet \tx360\tab set membership: \u8712?\par} +{\pard \sa0 \li360 \fi-360 \bullet \tx360\tab copyright: \u169?\sa180\par} +{\pard \sa180 \li0 \fi0 AT&T has an ampersand in their name.\par} +{\pard \sa180 \li0 \fi0 AT&T is another way to write it.\par} +{\pard \sa180 \li0 \fi0 This & that.\par} +{\pard \sa180 \li0 \fi0 4 < 5.\par} +{\pard \sa180 \li0 \fi0 6 > 5.\par} +{\pard \sa180 \li0 \fi0 Backslash: \\\par} +{\pard \sa180 \li0 \fi0 Backtick: `\par} +{\pard \sa180 \li0 \fi0 Asterisk: *\par} +{\pard \sa180 \li0 \fi0 Underscore: _\par} +{\pard \sa180 \li0 \fi0 Left brace: \{\par} +{\pard \sa180 \li0 \fi0 Right brace: \}\par} +{\pard \sa180 \li0 \fi0 Left bracket: [\par} +{\pard \sa180 \li0 \fi0 Right bracket: ]\par} +{\pard \sa180 \li0 \fi0 Left paren: (\par} +{\pard \sa180 \li0 \fi0 Right paren: )\par} +{\pard \sa180 \li0 \fi0 Greater-than: >\par} +{\pard \sa180 \li0 \fi0 Hash: #\par} +{\pard \sa180 \li0 \fi0 Period: .\par} +{\pard \sa180 \li0 \fi0 Bang: !\par} +{\pard \sa180 \li0 \fi0 Plus: +\par} +{\pard \sa180 \li0 \fi0 Minus: -\par} +{\pard \sa180 \li0 \fi0 \qc \emdash\emdash\emdash\emdash\emdash\par} +{\pard \sa180 \li0 \fi0 \b \fs36 Links\par} +{\pard \sa180 \li0 \fi0 \b \fs32 Explicit\par} +{\pard \sa180 \li0 \fi0 Just a {\field{\*\fldinst{HYPERLINK "/url/"}}{\fldrslt{\ul +URL +}}} +.\par} +{\pard \sa180 \li0 \fi0 {\field{\*\fldinst{HYPERLINK "/url/"}}{\fldrslt{\ul +URL and title +}}} +.\par} +{\pard \sa180 \li0 \fi0 {\field{\*\fldinst{HYPERLINK "/url/"}}{\fldrslt{\ul +URL and title +}}} +.\par} +{\pard \sa180 \li0 \fi0 {\field{\*\fldinst{HYPERLINK "/url/"}}{\fldrslt{\ul +URL and title +}}} +.\par} +{\pard \sa180 \li0 \fi0 {\field{\*\fldinst{HYPERLINK "/url/"}}{\fldrslt{\ul +URL and title +}}} +\par} +{\pard \sa180 \li0 \fi0 {\field{\*\fldinst{HYPERLINK "/url/"}}{\fldrslt{\ul +URL and title +}}} +\par} +{\pard \sa180 \li0 \fi0 {\field{\*\fldinst{HYPERLINK "mailto:nobody@nowhere.net"}}{\fldrslt{\ul +Email link +}}} +\par} +{\pard \sa180 \li0 \fi0 {\field{\*\fldinst{HYPERLINK ""}}{\fldrslt{\ul +Empty +}}} +.\par} +{\pard \sa180 \li0 \fi0 \b \fs32 Reference\par} +{\pard \sa180 \li0 \fi0 Foo {\field{\*\fldinst{HYPERLINK "/url/"}}{\fldrslt{\ul +bar +}}} +.\par} +{\pard \sa180 \li0 \fi0 Foo {\field{\*\fldinst{HYPERLINK "/url/"}}{\fldrslt{\ul +bar +}}} +.\par} +{\pard \sa180 \li0 \fi0 Foo {\field{\*\fldinst{HYPERLINK "/url/"}}{\fldrslt{\ul +bar +}}} +.\par} +{\pard \sa180 \li0 \fi0 With {\field{\*\fldinst{HYPERLINK "/url/"}}{\fldrslt{\ul +embedded [brackets] +}}} +.\par} +{\pard \sa180 \li0 \fi0 {\field{\*\fldinst{HYPERLINK "/url/"}}{\fldrslt{\ul +b +}}} + by itself should be a link.\par} +{\pard \sa180 \li0 \fi0 Indented {\field{\*\fldinst{HYPERLINK "/url"}}{\fldrslt{\ul +once +}}} +.\par} +{\pard \sa180 \li0 \fi0 Indented {\field{\*\fldinst{HYPERLINK "/url"}}{\fldrslt{\ul +twice +}}} +.\par} +{\pard \sa180 \li0 \fi0 Indented {\field{\*\fldinst{HYPERLINK "/url"}}{\fldrslt{\ul +thrice +}}} +.\par} +{\pard \sa180 \li0 \fi0 This should [not] be a link.\par} +{\pard \sa180 \li0 \fi0 \f1 [not]: /url\par} +{\pard \sa180 \li0 \fi0 Foo {\field{\*\fldinst{HYPERLINK "/url/"}}{\fldrslt{\ul +bar +}}} +.\par} +{\pard \sa180 \li0 \fi0 Foo {\field{\*\fldinst{HYPERLINK "/url/"}}{\fldrslt{\ul +biz +}}} +.\par} +{\pard \sa180 \li0 \fi0 \b \fs32 With ampersands\par} +{\pard \sa180 \li0 \fi0 Here's a {\field{\*\fldinst{HYPERLINK "http://example.com/?foo=1&bar=2"}}{\fldrslt{\ul +link with an ampersand in the URL +}}} +.\par} +{\pard \sa180 \li0 \fi0 Here's a link with an amersand in the link text: {\field{\*\fldinst{HYPERLINK "http://att.com/"}}{\fldrslt{\ul +AT&T +}}} +.\par} +{\pard \sa180 \li0 \fi0 Here's an {\field{\*\fldinst{HYPERLINK "/script?foo=1&bar=2"}}{\fldrslt{\ul +inline link +}}} +.\par} +{\pard \sa180 \li0 \fi0 Here's an {\field{\*\fldinst{HYPERLINK "/script?foo=1&bar=2"}}{\fldrslt{\ul +inline link in pointy braces +}}} +.\par} +{\pard \sa180 \li0 \fi0 \b \fs32 Autolinks\par} +{\pard \sa180 \li0 \fi0 With an ampersand: {\field{\*\fldinst{HYPERLINK "http://example.com/?foo=1&bar=2"}}{\fldrslt{\ul +http://example.com/?foo=1&bar=2 +}}} +\par} +{\pard \sa0 \li360 \fi-360 \bullet \tx360\tab In a list?\par} +{\pard \sa0 \li360 \fi-360 \bullet \tx360\tab {\field{\*\fldinst{HYPERLINK "http://example.com/"}}{\fldrslt{\ul +http://example.com/ +}}} +\par} +{\pard \sa0 \li360 \fi-360 \bullet \tx360\tab It should.\sa180\par} +{\pard \sa180 \li0 \fi0 An e-mail address: {\field{\*\fldinst{HYPERLINK "mailto:nobody@nowhere.net"}}{\fldrslt{\ul +nobody@nowhere.net +}}} +\par} +{\pard \sa180 \li720 \fi0 Blockquoted: {\field{\*\fldinst{HYPERLINK "http://example.com/"}}{\fldrslt{\ul +http://example.com/ +}}} +\par} +{\pard \sa180 \li0 \fi0 Auto-links should not occur here: {\f1 <http://example.com/>} \par} +{\pard \sa180 \li0 \fi0 \f1 or here: <http://example.com/>\par} +{\pard \sa180 \li0 \fi0 \qc \emdash\emdash\emdash\emdash\emdash\par} +{\pard \sa180 \li0 \fi0 \b \fs36 Images\par} +{\pard \sa180 \li0 \fi0 From "Voyage dans la Lune" by Georges Melies (1902):\par} +{\pard \sa180 \li0 \fi0 {\cf1 [image: lalune.jpg]\cf0}\par} +{\pard \sa180 \li0 \fi0 Here is a movie {\cf1 [image: movie.jpg]\cf0} icon.\par} +{\pard \sa180 \li0 \fi0 \qc \emdash\emdash\emdash\emdash\emdash\par} +{\pard \sa180 \li0 \fi0 \b \fs36 Footnotes\par} +{\pard \sa180 \li0 \fi0 Here is a footnote reference{\super\chftn}{\*\footnote\chftn\~\plain\pard {\pard \sa180 \li0 \fi0 Here is the footnote. It can go anywhere in the document, not just at the end.\par} +}, and another{\super\chftn}{\*\footnote\chftn\~\plain\pard {\pard \sa180 \li0 \fi0 Here's the other note. This one contains multiple blocks.\par} +{\pard \sa180 \li0 \fi0 Caret characters are used to indicate that the blocks all belong to a single footnote (as with block quotes).\par} +{\pard \sa180 \li0 \fi0 \f1 \{ <code> \}\par} +{\pard \sa180 \li0 \fi0 If you want, you can use a caret at the beginning of every line, as with blockquotes, but all that you need is a caret at the beginning of the first line of the block and any preceding blank lines.\par} +}. This should {\i not} be a footnote reference, because it contains a space^(my note).\par} + +} + diff --git a/tests/writer.smart.html b/tests/writer.smart.html new file mode 100644 index 000000000..1ab182558 --- /dev/null +++ b/tests/writer.smart.html @@ -0,0 +1,456 @@ +<!DOCTYPE HTML PUBLIC "-//W3C//DTD HTML 4.01 Transitional//EN" + "http://www.w3.org/TR/html4/loose.dtd"> +<html> +<head> +<meta http-equiv="Content-Type" content="text/html; charset=UTF-8" /> +<meta name="generator" content="pandoc" /> +<style type="text/css"> +div.pandocNote { border-left: 1px solid grey; padding-left: 1em; } +span.pandocNoteRef { vertical-align: super; font-size: 80%; } +span.pandocNoteMarker { } +</style> +<meta name="author" content="John MacFarlane, Anonymous" /> +<meta name="date" content="July 17, 2006" /> +<title>Pandoc Test Suite</title> +</head> +<body> +<h1 class="title">Pandoc Test Suite</h1> +<p>This is a set of tests for pandoc. Most of them are adapted from John Gruber’s markdown test suite.</p> +<hr /> +<h1>Headers</h1> +<h2>Level 2 with an <a href="/url">embedded link</a></h2> +<h3>Level 3 with <em>emphasis</em></h3> +<h4>Level 4</h4> +<h5>Level 5</h5> +<h1>Level 1</h1> +<h2>Level 2 with <em>emphasis</em></h2> +<h3>Level 3</h3> +<p>with no blank line</p> +<h2>Level 2</h2> +<p>with no blank line</p> +<hr /> +<h1>Paragraphs</h1> +<p>Here’s a regular paragraph.</p> +<p>In Markdown 1.0.0 and earlier. Version 8. This line turns into a list item. Because a hard-wrapped line in the middle of a paragraph looked like a list item.</p> +<p>Here’s one with a bullet. * criminey.</p> +<p>There should be a hard line break<br /> +here.</p> +<hr /> +<h1>Block Quotes</h1> +<p>E-mail style:</p> +<blockquote> +<p>This is a block quote. It is pretty short.</p> +</blockquote> +<blockquote> +<p>Code in a block quote:</p> +<pre><code>sub status { + print "working"; +} +</code></pre> +<p>A list:</p> +<ol> +<li>item one</li> +<li>item two</li> +</ol> +<p>Nested block quotes:</p> +<blockquote> +<p>nested</p> +</blockquote> +<blockquote> +<p>nested</p> +</blockquote> +</blockquote> +<p>This should not be a block quote: 2 > 1.</p> +<p>Box-style:</p> +<blockquote> +<p>Example:</p> +<pre><code>sub status { + print "working"; +} +</code></pre> +</blockquote> +<blockquote> +<ol> +<li>do laundry</li> +<li>take out the trash</li> +</ol> +</blockquote> +<p>Here’s a nested one:</p> +<blockquote> +<p>Joe said:</p> +<blockquote> +<p>Don’t quote me.</p> +</blockquote> +</blockquote> +<p>And a following paragraph.</p> +<hr /> +<h1>Code Blocks</h1> +<p>Code:</p> +<pre><code>---- (should be four hyphens) + +sub status { + print "working"; +} + +this code block is indented by one tab +</code></pre> +<p>And:</p> +<pre><code> this code block is indented by two tabs + +These should not be escaped: \$ \\ \> \[ \{ +</code></pre> +<hr /> +<h1>Lists</h1> +<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> +<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> +<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 1. 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> +<h2>Tabs and spaces</h2> +<ul> +<li><p>this is a list item indented with tabs</p> +</li> +<li><p>this is a list item indented with spaces</p> +<ul> +<li><p>this is an example list item indented with tabs</p> +</li> +<li><p>this is an example list item indented with spaces</p> +</li> +</ul> +</li> +</ul> +<hr /> +<h1>HTML Blocks</h1> +<p>Simple block on one line:</p> +<div>foo</div> +<p>And nested without indentation:</p> +<div> +<div> +<div>foo</div> +</div> +<div>bar</div> +</div> +<p>Interpreted markdown in a table:</p> +<table> +<tr> +<td>This is <em>emphasized</em></td> +<td>And this is <strong>strong</strong></td> +</tr> +</table> + +<script type="text/javascript">document.write('This *should not* be interpreted as markdown');</script> +<p>Here’s a simple block:</p> +<div> + foo</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 +--> + +<!-- + This is another comment. +--> +<p>Code block:</p> +<pre><code><!-- Comment --> +</code></pre> +<p>Just plain comment, with trailing spaces on the line:</p> +<!-- foo --> +<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"> +<hr /> +<h1>Inline Markup</h1> +<p>This is <em>emphasized</em>, and so <em>is this</em>.</p> +<p>This is <strong>strong</strong>, and so <strong>is this</strong>.</p> +<p>An <em><a href="/url">emphasized link</a></em>.</p> +<p><strong><em>This is strong and em.</em></strong></p> +<p>So is <strong><em>this</em></strong> word.</p> +<p><strong><em>This is strong and em.</em></strong></p> +<p>So is <strong><em>this</em></strong> word.</p> +<p>This is code: <code>></code>, <code>$</code>, <code>\</code>, <code>\$</code>, <code><html></code>.</p> +<hr /> +<h1>Smart quotes, ellipses, dashes</h1> +<p>“Hello,” said the spider. “‘Shelob’ is my name.”</p> +<p>‘A’, ‘B’, and ‘C’ are letters.</p> +<p>‘Oak,’ ‘elm,’ and ‘beech’ are names of trees. So is ‘pine.’</p> +<p>‘He said, “I want to go.”’ Were you alive in the 70’s?</p> +<p>Here is some quoted ‘<code>code</code>’ and a “<a href="http://example.com/?foo=1&bar=2">quoted link</a>”.</p> +<p>Some dashes: one—two—three—four—five.</p> +<p>Dashes between numbers: 5–7, 255–66, 1987–1999.</p> +<p>Ellipses…and…and … .</p> +<hr /> +<h1>LaTeX</h1> +<ul> +<li>\cite[22-23]{smith.1899}</li> +<li>\doublespacing</li> +<li>$2+2=4$</li> +<li>$x \in y$</li> +<li>$\alpha \wedge \omega$</li> +<li>$223$</li> +<li>$p$-Tree</li> +<li>$\frac{d}{dx}f(x)=\lim_{h\to 0}\frac{f(x+h)-f(x)}{h}$</li> +<li>Here’s one that has a line break in it: $\alpha + \omega \times x^2$.</li> +</ul> +<p>These shouldn’t be math:</p> +<ul> +<li>To get the famous equation, write <code>$e = mc^2$</code>.</li> +<li>$22,000 is a <em>lot</em> of money. So is $34,000. (It worked if “lot” is emphasized.)</li> +<li>Escaped <code>$</code>: $73 <em>this should be emphasized</em> 23$.</li> +</ul> +<p>Here’s a LaTeX table:</p> +<p>\begin{tabular}{|l|l|}\hline +Animal & Number \\ \hline +Dog & 2 \\ +Cat & 1 \\ \hline +\end{tabular}</p> +<hr /> +<h1>Special Characters</h1> +<p>Here is some unicode:</p> +<ul> +<li>I hat: Î</li> +<li>o umlaut: ö</li> +<li>section: §</li> +<li>set membership: ∈</li> +<li>copyright: ©</li> +</ul> +<p>AT&T has an ampersand in their name.</p> +<p>AT&T is another way to write it.</p> +<p>This & that.</p> +<p>4 < 5.</p> +<p>6 > 5.</p> +<p>Backslash: \</p> +<p>Backtick: ‘</p> +<p>Asterisk: *</p> +<p>Underscore: _</p> +<p>Left brace: {</p> +<p>Right brace: }</p> +<p>Left bracket: [</p> +<p>Right bracket: ]</p> +<p>Left paren: (</p> +<p>Right paren: )</p> +<p>Greater-than: ></p> +<p>Hash: #</p> +<p>Period: .</p> +<p>Bang: !</p> +<p>Plus: +</p> +<p>Minus: -</p> +<hr /> +<h1>Links</h1> +<h2>Explicit</h2> +<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 with "quotes" in it">URL and title</a></p> +<p><a href="/url/" title="title with single quotes">URL and title</a></p> +<p><script type="text/javascript">h='nowhere.net';n='nobody';e=n+'@'+h;document.write('<a href="mailto:'+e+'">'+'Email link'+'<\/a>');</script><noscript>Email link (nobody [at] nowhere.net)</noscript></p> +<p><a href="">Empty</a>.</p> +<h2>Reference</h2> +<p>Foo <a href="/url/">bar</a>.</p> +<p>Foo <a href="/url/">bar</a>.</p> +<p>Foo <a href="/url/">bar</a>.</p> +<p>With <a href="/url/">embedded [brackets]</a>.</p> +<p><a href="/url/">b</a> by itself should be a link.</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>This should [not] be a link.</p> +<pre><code>[not]: /url +</code></pre> +<p>Foo <a href="/url/" title="Title with "quotes" inside">bar</a>.</p> +<p>Foo <a href="/url/" title="Title with "quote" inside">biz</a>.</p> +<h2>With ampersands</h2> +<p>Here’s a <a href="http://example.com/?foo=1&bar=2">link with an ampersand in the URL</a>.</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 <a href="/script?foo=1&bar=2">inline link</a>.</p> +<p>Here’s an <a href="/script?foo=1&bar=2">inline link in pointy braces</a>.</p> +<h2>Autolinks</h2> +<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> +<p>An e-mail address: <script type="text/javascript">h='nowhere.net';n='nobody';e=n+'@'+h;document.write('<a href="mailto:'+e+'">'+e+'<\/a>');</script><noscript>nobody [at] nowhere.net</noscript></p> +<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> +<hr /> +<h1>Images</h1> +<p>From “Voyage dans la Lune” by Georges Melies (1902):</p> +<p><img src="lalune.jpg" title="Voyage dans la Lune" alt="lalune"></p> +<p>Here is a movie <img src="movie.jpg" alt="movie"> icon.</p> +<hr /> +<h1>Footnotes</h1> +<p>Here is a footnote reference<span class="pandocNoteRef"><a name="ref_1" href="#note_1">(1)</a></span>, and another<span class="pandocNoteRef"><a name="ref_longnote" href="#note_longnote">(longnote)</a></span>. This should <em>not</em> be a footnote reference, because it contains a space^(my note).</p> +<div class="pandocNote"> +<p class="first"><span class="pandocNoteMarker"><a name="note_1" href="#ref_1">(1)</a></span> Here is the footnote. It can go anywhere in the document, not just at the end.</p> + +</div> +<div class="pandocNote"> +<p class="first"><span class="pandocNoteMarker"><a name="note_longnote" href="#ref_longnote">(longnote)</a></span> Here’s the other note. This one contains multiple blocks.</p> +<p>Caret characters are used to indicate that the blocks all belong to a single footnote (as with block quotes).</p> +<pre><code> { <code> } +</code></pre> +<p>If you want, you can use a caret at the beginning of every line, as with blockquotes, but all that you need is a caret at the beginning of the first line of the block and any preceding blank lines.</p> + +</div> +</body> +</html> + |
