diff options
Diffstat (limited to 'vendors/markdown')
| -rw-r--r-- | vendors/markdown/License.text | 36 | ||||
| -rw-r--r-- | vendors/markdown/PHP Markdown Extra Readme.text | 786 | ||||
| -rw-r--r-- | vendors/markdown/UPSTREAM_WARNING | 5 | ||||
| -rw-r--r-- | vendors/markdown/markdown.php | 2933 |
4 files changed, 3760 insertions, 0 deletions
diff --git a/vendors/markdown/License.text b/vendors/markdown/License.text new file mode 100644 index 000000000..4d6bf8b63 --- /dev/null +++ b/vendors/markdown/License.text @@ -0,0 +1,36 @@ +PHP Markdown & Extra +Copyright (c) 2004-2009 Michel Fortin +<http://michelf.com/> +All rights reserved. + +Based on Markdown +Copyright (c) 2003-2006 John Gruber +<http://daringfireball.net/> +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 "Markdown" 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. diff --git a/vendors/markdown/PHP Markdown Extra Readme.text b/vendors/markdown/PHP Markdown Extra Readme.text new file mode 100644 index 000000000..b72ee998e --- /dev/null +++ b/vendors/markdown/PHP Markdown Extra Readme.text @@ -0,0 +1,786 @@ +PHP Markdown Extra +================== + +Version 1.2.4 - Sat 10 Oct 2009 + +by Michel Fortin +<http://michelf.com/> + +based on Markdown by John Gruber +<http://daringfireball.net/> + + +Introduction +------------ + +This is a special version of PHP Markdown with extra features. See +<http://michelf.com/projects/php-markdown/extra/> for details. + +Markdown is a text-to-HTML conversion tool for web writers. Markdown +allows you to write using an easy-to-read, easy-to-write plain text +format, then convert it to structurally valid XHTML (or HTML). + +"Markdown" is two things: a plain text markup syntax, and a software +tool, written in Perl, that converts the plain text markup to HTML. +PHP Markdown is a port to PHP of the original Markdown program by +John Gruber. + +PHP Markdown can work as a plug-in for WordPress and bBlog, as a +modifier for the Smarty templating engine, or as a remplacement for +textile formatting in any software that support textile. + +Full documentation of Markdown's syntax is available on John's +Markdown page: <http://daringfireball.net/projects/markdown/> + + +Installation and Requirement +---------------------------- + +PHP Markdown requires PHP version 4.0.5 or later. + + +### WordPress ### + +PHP Markdown works with [WordPress][wp], version 1.2 or later. + + [wp]: http://wordpress.org/ + +1. To use PHP Markdown with WordPress, place the "makrdown.php" file + in the "plugins" folder. This folder is located inside + "wp-content" at the root of your site: + + (site home)/wp-content/plugins/ + +2. Activate the plugin with the administrative interface of + WordPress. In the "Plugins" section you will now find Markdown. + To activate the plugin, click on the "Activate" button on the + same line than Markdown. Your entries will now be formatted by + PHP Markdown. + +3. To post Markdown content, you'll first have to disable the + "visual" editor in the User section of WordPress. + +You can configure PHP Markdown to not apply to the comments on your +WordPress weblog. See the "Configuration" section below. + +It is not possible at this time to apply a different set of +filters to different entries. All your entries will be formated by +PHP Markdown. This is a limitation of WordPress. If your old entries +are written in HTML (as opposed to another formatting syntax, like +Textile), they'll probably stay fine after installing Markdown. + + +### bBlog ### + +PHP Markdown also works with [bBlog][bb]. + + [bb]: http://www.bblog.com/ + +To use PHP Markdown with bBlog, rename "markdown.php" to +"modifier.markdown.php" and place the file in the "bBlog_plugins" +folder. This folder is located inside the "bblog" directory of +your site, like this: + + (site home)/bblog/bBlog_plugins/modifier.markdown.php + +Select "Markdown" as the "Entry Modifier" when you post a new +entry. This setting will only apply to the entry you are editing. + + +### Replacing Textile in TextPattern ### + +[TextPattern][tp] use [Textile][tx] to format your text. You can +replace Textile by Markdown in TextPattern without having to change +any code by using the *Texitle Compatibility Mode*. This may work +with other software that expect Textile too. + + [tx]: http://www.textism.com/tools/textile/ + [tp]: http://www.textpattern.com/ + +1. Rename the "markdown.php" file to "classTextile.php". This will + make PHP Markdown behave as if it was the actual Textile parser. + +2. Replace the "classTextile.php" file TextPattern installed in your + web directory. It can be found in the "lib" directory: + + (site home)/textpattern/lib/ + +Contrary to Textile, Markdown does not convert quotes to curly ones +and does not convert multiple hyphens (`--` and `---`) into en- and +em-dashes. If you use PHP Markdown in Textile Compatibility Mode, you +can solve this problem by installing the "smartypants.php" file from +[PHP SmartyPants][psp] beside the "classTextile.php" file. The Textile +Compatibility Mode function will use SmartyPants automatically without +further modification. + + [psp]: http://michelf.com/projects/php-smartypants/ + + +### In Your Own Programs ### + +You can use PHP Markdown easily in your current PHP program. Simply +include the file and then call the Markdown function on the text you +want to convert: + + include_once "markdown.php"; + $my_html = Markdown($my_text); + +If you wish to use PHP Markdown with another text filter function +built to parse HTML, you should filter the text *after* the Markdown +function call. This is an example with [PHP SmartyPants][psp]: + + $my_html = SmartyPants(Markdown($my_text)); + + +### With Smarty ### + +If your program use the [Smarty][sm] template engine, PHP Markdown +can now be used as a modifier for your templates. Rename "markdown.php" +to "modifier.markdown.php" and put it in your smarty plugins folder. + + [sm]: http://smarty.php.net/ + +If you are using MovableType 3.1 or later, the Smarty plugin folder is +located at `(MT CGI root)/php/extlib/smarty/plugins`. This will allow +Markdown to work on dynamic pages. + + +### Updating Markdown in Other Programs ### + +Many web applications now ship with PHP Markdown, or have plugins to +perform the conversion to HTML. You can update PHP Markdown -- or +replace it with PHP Markdown Extra -- in many of these programs by +swapping the old "markdown.php" file for the new one. + +Here is a short non-exhaustive list of some programs and where they +hide the "markdown.php" file. + +| Program | Path to Markdown +| ------- | ---------------- +| [Pivot][] | `(site home)/pivot/includes/markdown/` + +If you're unsure if you can do this with your application, ask the +developer, or wait for the developer to update his application or +plugin with the new version of PHP Markdown. + + [Pivot]: http://pivotlog.net/ + + +Configuration +------------- + +By default, PHP Markdown produces XHTML output for tags with empty +elements. E.g.: + + <br /> + +Markdown can be configured to produce HTML-style tags; e.g.: + + <br> + +To do this, you must edit the "MARKDOWN_EMPTY_ELEMENT_SUFFIX" +definition below the "Global default settings" header at the start of +the "markdown.php" file. + + +### WordPress-Specific Settings ### + +By default, the Markdown plugin applies to both posts and comments on +your WordPress weblog. To deactivate one or the other, edit the +`MARKDOWN_WP_POSTS` or `MARKDOWN_WP_COMMENTS` definitions under the +"WordPress settings" header at the start of the "markdown.php" file. + + +Bugs +---- + +To file bug reports please send email to: +<michel.fortin@michelf.com> + +Please include with your report: (1) the example input; (2) the output you +expected; (3) the output PHP Markdown actually produced. + + +Version History +--------------- + +1.0.1n (10 Oct 2009): + +* Enabled reference-style shortcut links. Now you can write reference-style + links with less brakets: + + This is [my website]. + + [my website]: http://example.com/ + + This was added in the 1.0.2 betas, but commented out in the 1.0.1 branch, + waiting for the feature to be officialized. [But half of the other Markdown + implementations are supporting this syntax][half], so it makes sense for + compatibility's sake to allow it in PHP Markdown too. + + [half]: http://babelmark.bobtfish.net/?markdown=This+is+%5Bmy+website%5D.%0D%0A%09%09%0D%0A%5Bmy+website%5D%3A+http%3A%2F%2Fexample.com%2F%0D%0A&src=1&dest=2 + +* Now accepting many valid email addresses in autolinks that were + previously rejected, such as: + + <abc+mailbox/department=shipping@example.com> + <!#$%&'*+-/=?^_`.{|}~@example.com> + <"abc@def"@example.com> + <"Fred Bloggs"@example.com> + <jsmith@[192.0.2.1]> + +* Now accepting spaces in URLs for inline and reference-style links. Such + URLs need to be surrounded by angle brakets. For instance: + + [link text](<http://url/with space> "optional title") + + [link text][ref] + [ref]: <http://url/with space> "optional title" + + There is still a quirk which may prevent this from working correctly with + relative URLs in inline-style links however. + +* Fix for adjacent list of different kind where the second list could + end as a sublist of the first when not separated by an empty line. + +* Fixed a bug where inline-style links wouldn't be recognized when the link + definition contains a line break between the url and the title. + +* Fixed a bug where tags where the name contains an underscore aren't parsed + correctly. + +* Fixed some corner-cases mixing underscore-ephasis and asterisk-emphasis. + + +Extra 1.2.4: + +* Fixed a problem where unterminated tags in indented code blocks could + prevent proper escaping of characaters in the code block. + + +Extra 1.2.3 (31 Dec 2008): + +* In WordPress pages featuring more than one post, footnote id prefixes are + now automatically applied with the current post ID to avoid clashes + between footnotes belonging to different posts. + +* Fix for a bug introduced in Extra 1.2 where block-level HTML tags where + not detected correctly, thus the addition of erroneous `<p>` tags and + interpretation of their content as Markdown-formatted instead of + HTML-formatted. + + +Extra 1.2.2 (21 Jun 2008): + +* Fixed a problem where abbreviation definitions, footnote + definitions and link references were stripped inside + fenced code blocks. + +* Fixed a bug where characters such as `"` in abbreviation + definitions weren't properly encoded to HTML entities. + +* Fixed a bug where double quotes `"` were not correctly encoded + as HTML entities when used inside a footnote reference id. + + +1.0.1m (21 Jun 2008): + +* Lists can now have empty items. + +* Rewrote the emphasis and strong emphasis parser to fix some issues + with odly placed and overlong markers. + + +Extra 1.2.1 (27 May 2008): + +* Fixed a problem where Markdown headers and horizontal rules were + transformed into their HTML equivalent inside fenced code blocks. + + +Extra 1.2 (11 May 2008): + +* Added fenced code block syntax which don't require indentation + and can start and end with blank lines. A fenced code block + starts with a line of consecutive tilde (~) and ends on the + next line with the same number of consecutive tilde. Here's an + example: + + ~~~~~~~~~~~~ + Hello World! + ~~~~~~~~~~~~ + +* Rewrote parts of the HTML block parser to better accomodate + fenced code blocks. + +* Footnotes may now be referenced from within another footnote. + +* Added programatically-settable parser property `predef_attr` for + predefined attribute definitions. + +* Fixed an issue where an indented code block preceded by a blank + line containing some other whitespace would confuse the HTML + block parser into creating an HTML block when it should have + been code. + + +1.0.1l (11 May 2008): + +* Now removing the UTF-8 BOM at the start of a document, if present. + +* Now accepting capitalized URI schemes (such as HTTP:) in automatic + links, such as `<HTTP://EXAMPLE.COM/>`. + +* Fixed a problem where `<hr@example.com>` was seen as a horizontal + rule instead of an automatic link. + +* Fixed an issue where some characters in Markdown-generated HTML + attributes weren't properly escaped with entities. + +* Fix for code blocks as first element of a list item. Previously, + this didn't create any code block for item 2: + + * Item 1 (regular paragraph) + + * Item 2 (code block) + +* A code block starting on the second line of a document wasn't seen + as a code block. This has been fixed. + +* Added programatically-settable parser properties `predef_urls` and + `predef_titles` for predefined URLs and titles for reference-style + links. To use this, your PHP code must call the parser this way: + + $parser = new Markdwon_Parser; + $parser->predef_urls = array('linkref' => 'http://example.com'); + $html = $parser->transform($text); + + You can then use the URL as a normal link reference: + + [my link][linkref] + [my link][linkRef] + + Reference names in the parser properties *must* be lowercase. + Reference names in the Markdown source may have any case. + +* Added `setup` and `teardown` methods which can be used by subclassers + as hook points to arrange the state of some parser variables before and + after parsing. + + +Extra 1.1.7 (26 Sep 2007): + +1.0.1k (26 Sep 2007): + +* Fixed a problem introduced in 1.0.1i where three or more identical + uppercase letters, as well as a few other symbols, would trigger + a horizontal line. + + +Extra 1.1.6 (4 Sep 2007): + +1.0.1j (4 Sep 2007): + +* Fixed a problem introduced in 1.0.1i where the closing `code` and + `pre` tags at the end of a code block were appearing in the wrong + order. + +* Overriding configuration settings by defining constants from an + external before markdown.php is included is now possible without + producing a PHP warning. + + +Extra 1.1.5 (31 Aug 2007): + +1.0.1i (31 Aug 2007): + +* Fixed a problem where an escaped backslash before a code span + would prevent the code span from being created. This should now + work as expected: + + Litteral backslash: \\`code span` + +* Overall speed improvements, especially with long documents. + + +Extra 1.1.4 (3 Aug 2007): + +1.0.1h (3 Aug 2007): + +* Added two properties (`no_markup` and `no_entities`) to the parser + allowing HTML tags and entities to be disabled. + +* Fix for a problem introduced in 1.0.1g where posting comments in + WordPress would trigger PHP warnings and cause some markup to be + incorrectly filtered by the kses filter in WordPress. + + +Extra 1.1.3 (3 Jul 2007): + +* Fixed a performance problem when parsing some invalid HTML as an HTML + block which was resulting in too much recusion and a segmentation fault + for long documents. + +* The markdown="" attribute now accepts unquoted values. + +* Fixed an issue where underscore-emphasis didn't work when applied on the + first or the last word of an element having the markdown="1" or + markdown="span" attribute set unless there was some surrounding whitespace. + This didn't work: + + <p markdown="1">_Hello_ _world_</p> + + Now it does produce emphasis as expected. + +* Fixed an issue preventing footnotes from working when the parser's + footnote id prefix variable (fn_id_prefix) is not empty. + +* Fixed a performance problem where the regular expression for strong + emphasis introduced in version 1.1 could sometime be long to process, + give slightly wrong results, and in some circumstances could remove + entirely the content for a whole paragraph. + +* Fixed an issue were abbreviations tags could be incorrectly added + inside URLs and title of links. + +* Placing footnote markers inside a link, resulting in two nested links, is + no longer allowed. + + +1.0.1g (3 Jul 2007): + +* Fix for PHP 5 compiled without the mbstring module. Previous fix to + calculate the length of UTF-8 strings in `detab` when `mb_strlen` is + not available was only working with PHP 4. + +* Fixed a problem with WordPress 2.x where full-content posts in RSS feeds + were not processed correctly by Markdown. + +* Now supports URLs containing literal parentheses for inline links + and images, such as: + + [WIMP](http://en.wikipedia.org/wiki/WIMP_(computing)) + + Such parentheses may be arbitrarily nested, but must be + balanced. Unbalenced parentheses are allowed however when the URL + when escaped or when the URL is enclosed in angle brakets `<>`. + +* Fixed a performance problem where the regular expression for strong + emphasis introduced in version 1.0.1d could sometime be long to process, + give slightly wrong results, and in some circumstances could remove + entirely the content for a whole paragraph. + +* Some change in version 1.0.1d made possible the incorrect nesting of + anchors within each other. This is now fixed. + +* Fixed a rare issue where certain MD5 hashes in the content could + be changed to their corresponding text. For instance, this: + + The MD5 value for "+" is "26b17225b626fb9238849fd60eabdf60". + + was incorrectly changed to this in previous versions of PHP Markdown: + + <p>The MD5 value for "+" is "+".</p> + +* Now convert escaped characters to their numeric character + references equivalent. + + This fix an integration issue with SmartyPants and backslash escapes. + Since Markdown and SmartyPants have some escapable characters in common, + it was sometime necessary to escape them twice. Previously, two + backslashes were sometime required to prevent Markdown from "eating" the + backslash before SmartyPants sees it: + + Here are two hyphens: \\-- + + Now, only one backslash will do: + + Here are two hyphens: \-- + + +Extra 1.1.2 (7 Feb 2007) + +* Fixed an issue where headers preceded too closely by a paragraph + (with no blank line separating them) where put inside the paragraph. + +* Added the missing TextileRestricted method that was added to regular + PHP Markdown since 1.0.1d but which I forgot to add to Extra. + + +1.0.1f (7 Feb 2007): + +* Fixed an issue with WordPress where manually-entered excerpts, but + not the auto-generated ones, would contain nested paragraphs. + +* Fixed an issue introduced in 1.0.1d where headers and blockquotes + preceded too closely by a paragraph (not separated by a blank line) + where incorrectly put inside the paragraph. + +* Fixed an issue introduced in 1.0.1d in the tokenizeHTML method where + two consecutive code spans would be merged into one when together they + form a valid tag in a multiline paragraph. + +* Fixed an long-prevailing issue where blank lines in code blocks would + be doubled when the code block is in a list item. + + This was due to the list processing functions relying on artificially + doubled blank lines to correctly determine when list items should + contain block-level content. The list item processing model was thus + changed to avoid the need for double blank lines. + +* Fixed an issue with `<% asp-style %>` instructions used as inline + content where the opening `<` was encoded as `<`. + +* Fixed a parse error occuring when PHP is configured to accept + ASP-style delimiters as boundaries for PHP scripts. + +* Fixed a bug introduced in 1.0.1d where underscores in automatic links + got swapped with emphasis tags. + + +Extra 1.1.1 (28 Dec 2006) + +* Fixed a problem where whitespace at the end of the line of an atx-style + header would cause tailing `#` to appear as part of the header's content. + This was caused by a small error in the regex that handles the definition + for the id attribute in PHP Markdown Extra. + +* Fixed a problem where empty abbreviations definitions would eat the + following line as its definition. + +* Fixed an issue with calling the Markdown parser repetitivly with text + containing footnotes. The footnote hashes were not reinitialized properly. + + +1.0.1e (28 Dec 2006) + +* Added support for internationalized domain names for email addresses in + automatic link. Improved the speed at which email addresses are converted + to entities. Thanks to Milian Wolff for his optimisations. + +* Made deterministic the conversion to entities of email addresses in + automatic links. This means that a given email address will always be + encoded the same way. + +* PHP Markdown will now use its own function to calculate the length of an + UTF-8 string in `detab` when `mb_strlen` is not available instead of + giving a fatal error. + + +Extra 1.1 (1 Dec 2006) + +* Added a syntax for footnotes. + +* Added an experimental syntax to define abbreviations. + + +1.0.1d (1 Dec 2006) + +* Fixed a bug where inline images always had an empty title attribute. The + title attribute is now present only when explicitly defined. + +* Link references definitions can now have an empty title, previously if the + title was defined but left empty the link definition was ignored. This can + be useful if you want an empty title attribute in images to hide the + tooltip in Internet Explorer. + +* Made `detab` aware of UTF-8 characters. UTF-8 multi-byte sequences are now + correctly mapped to one character instead of the number of bytes. + +* Fixed a small bug with WordPress where WordPress' default filter `wpautop` + was not properly deactivated on comment text, resulting in hard line breaks + where Markdown do not prescribes them. + +* Added a `TextileRestrited` method to the textile compatibility mode. There + is no restriction however, as Markdown does not have a restricted mode at + this point. This should make PHP Markdown work again in the latest + versions of TextPattern. + +* Converted PHP Markdown to a object-oriented design. + +* Changed span and block gamut methods so that they loop over a + customizable list of methods. This makes subclassing the parser a more + interesting option for creating syntax extensions. + +* Also added a "document" gamut loop which can be used to hook document-level + methods (like for striping link definitions). + +* Changed all methods which were inserting HTML code so that they now return + a hashed representation of the code. New methods `hashSpan` and `hashBlock` + are used to hash respectivly span- and block-level generated content. This + has a couple of significant effects: + + 1. It prevents invalid nesting of Markdown-generated elements which + could occur occuring with constructs like `*something [link*][1]`. + 2. It prevents problems occuring with deeply nested lists on which + paragraphs were ill-formed. + 3. It removes the need to call `hashHTMLBlocks` twice during the the + block gamut. + + Hashes are turned back to HTML prior output. + +* Made the block-level HTML parser smarter using a specially-crafted regular + expression capable of handling nested tags. + +* Solved backtick issues in tag attributes by rewriting the HTML tokenizer to + be aware of code spans. All these lines should work correctly now: + + <span attr='`ticks`'>bar</span> + <span attr='``double ticks``'>bar</span> + `<test a="` content of attribute `">` + +* Changed the parsing of HTML comments to match simply from `<!--` to `-->` + instead using of the more complicated SGML-style rule with paired `--`. + This is how most browsers parse comments and how XML defines them too. + +* `<address>` has been added to the list of block-level elements and is now + treated as an HTML block instead of being wrapped within paragraph tags. + +* Now only trim trailing newlines from code blocks, instead of trimming + all trailing whitespace characters. + +* Fixed bug where this: + + [text](http://m.com "title" ) + + wasn't working as expected, because the parser wasn't allowing for spaces + before the closing paren. + +* Filthy hack to support markdown='1' in div tags. + +* _DoAutoLinks() now supports the 'dict://' URL scheme. + +* PHP- and ASP-style processor instructions are now protected as + raw HTML blocks. + + <? ... ?> + <% ... %> + +* Fix for escaped backticks still triggering code spans: + + There are two raw backticks here: \` and here: \`, not a code span + + +Extra 1.0 - 5 September 2005 + +* Added support for setting the id attributes for headers like this: + + Header 1 {#header1} + ======== + + ## Header 2 ## {#header2} + + This only work only for headers for now. + +* Tables will now work correctly as the first element of a definition + list. For example, this input: + + Term + + : Header | Header + ------- | ------- + Cell | Cell + + used to produce no definition list and a table where the first + header was named ": Header". This is now fixed. + +* Fix for a problem where a paragraph following a table was not + placed between `<p>` tags. + + +Extra 1.0b4 - 1 August 2005 + +* Fixed some issues where whitespace around HTML blocks were trigging + empty paragraph tags. + +* Fixed an HTML block parsing issue that would cause a block element + following a code span or block with unmatched opening bracket to be + placed inside a paragraph. + +* Removed some PHP notices that could appear when parsing definition + lists and tables with PHP notice reporting flag set. + + +Extra 1.0b3 - 29 July 2005 + +* Definition lists now require a blank line before each term. Solves + an ambiguity where the last line of lazy-indented definitions could + be mistaken by PHP Markdown as a new term in the list. + +* Definition lists now support multiple terms per definition. + +* Some special tags were replaced in the output by their md5 hash + key. Things such as this now work as expected: + + ## Header <?php echo $number ?> ## + + +Extra 1.0b2 - 26 July 2005 + +* Definition lists can now take two or more definitions for one term. + This should have been the case before, but a bug prevented this + from working right. + +* Fixed a problem where single column table with a pipe only at the + end where not parsed as table. Here is such a table: + + | header + | ------ + | cell + +* Fixed problems with empty cells in the first column of a table with + no leading pipe, like this one: + + header | header + ------ | ------ + | cell + +* Code spans containing pipes did not within a table. This is now + fixed by parsing code spans before splitting rows into cells. + +* Added the pipe character to the backlash escape character lists. + +Extra 1.0b1 (25 Jun 2005) + +* First public release of PHP Markdown Extra. + + +Copyright and License +--------------------- + +PHP Markdown & Extra +Copyright (c) 2004-2009 Michel Fortin +<http://michelf.com/> +All rights reserved. + +Based on Markdown +Copyright (c) 2003-2005 John Gruber +<http://daringfireball.net/> +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 "Markdown" 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. diff --git a/vendors/markdown/UPSTREAM_WARNING b/vendors/markdown/UPSTREAM_WARNING new file mode 100644 index 000000000..d0a664f2a --- /dev/null +++ b/vendors/markdown/UPSTREAM_WARNING @@ -0,0 +1,5 @@ +This file has been modified from its upstream. When upgrading, be sure to check the following mods: + +* Headers can be created with =, ==, etc instead of just #, ##. +* @todo Autolink (f|ht)tp(s)?://link.com. +* @todo GFM improvement for newlines: http://github.github.com/github-flavored-markdown/
\ No newline at end of file diff --git a/vendors/markdown/markdown.php b/vendors/markdown/markdown.php new file mode 100644 index 000000000..3f1f3a715 --- /dev/null +++ b/vendors/markdown/markdown.php @@ -0,0 +1,2933 @@ +<?php +# +# Markdown Extra - A text-to-HTML conversion tool for web writers +# +# PHP Markdown & Extra +# Copyright (c) 2004-2009 Michel Fortin +# <http://michelf.com/projects/php-markdown/> +# +# Original Markdown +# Copyright (c) 2004-2006 John Gruber +# <http://daringfireball.net/projects/markdown/> +# + + +define( 'MARKDOWN_VERSION', "1.0.1n" ); # Sat 10 Oct 2009 +define( 'MARKDOWNEXTRA_VERSION', "1.2.4" ); # Sat 10 Oct 2009 + + +# +# Global default settings: +# + +# Change to ">" for HTML output +@define( 'MARKDOWN_EMPTY_ELEMENT_SUFFIX', " />"); + +# Define the width of a tab for code blocks. +@define( 'MARKDOWN_TAB_WIDTH', 4 ); + +# Optional title attribute for footnote links and backlinks. +@define( 'MARKDOWN_FN_LINK_TITLE', "" ); +@define( 'MARKDOWN_FN_BACKLINK_TITLE', "" ); + +# Optional class attribute for footnote links and backlinks. +@define( 'MARKDOWN_FN_LINK_CLASS', "" ); +@define( 'MARKDOWN_FN_BACKLINK_CLASS', "" ); + + +# +# WordPress settings: +# + +# Change to false to remove Markdown from posts and/or comments. +@define( 'MARKDOWN_WP_POSTS', true ); +@define( 'MARKDOWN_WP_COMMENTS', true ); + + + +### Standard Function Interface ### + +@define( 'MARKDOWN_PARSER_CLASS', 'MarkdownExtra_Parser' ); + +function Markdown($text) { +# +# Initialize the parser and return the result of its transform method. +# + # Setup static parser variable. + static $parser; + if (!isset($parser)) { + $parser_class = MARKDOWN_PARSER_CLASS; + $parser = new $parser_class; + } + + # Transform text using parser. + return $parser->transform($text); +} + + +### WordPress Plugin Interface ### + +/* +Plugin Name: Markdown Extra +Plugin URI: http://michelf.com/projects/php-markdown/ +Description: <a href="http://daringfireball.net/projects/markdown/syntax">Markdown syntax</a> allows you to write using an easy-to-read, easy-to-write plain text format. Based on the original Perl version by <a href="http://daringfireball.net/">John Gruber</a>. <a href="http://michelf.com/projects/php-markdown/">More...</a> +Version: 1.2.4 +Author: Michel Fortin +Author URI: http://michelf.com/ +*/ + +if (isset($wp_version)) { + # More details about how it works here: + # <http://michelf.com/weblog/2005/wordpress-text-flow-vs-markdown/> + + # Post content and excerpts + # - Remove WordPress paragraph generator. + # - Run Markdown on excerpt, then remove all tags. + # - Add paragraph tag around the excerpt, but remove it for the excerpt rss. + if (MARKDOWN_WP_POSTS) { + remove_filter('the_content', 'wpautop'); + remove_filter('the_content_rss', 'wpautop'); + remove_filter('the_excerpt', 'wpautop'); + add_filter('the_content', 'mdwp_MarkdownPost', 6); + add_filter('the_content_rss', 'mdwp_MarkdownPost', 6); + add_filter('get_the_excerpt', 'mdwp_MarkdownPost', 6); + add_filter('get_the_excerpt', 'trim', 7); + add_filter('the_excerpt', 'mdwp_add_p'); + add_filter('the_excerpt_rss', 'mdwp_strip_p'); + + remove_filter('content_save_pre', 'balanceTags', 50); + remove_filter('excerpt_save_pre', 'balanceTags', 50); + add_filter('the_content', 'balanceTags', 50); + add_filter('get_the_excerpt', 'balanceTags', 9); + } + + # Add a footnote id prefix to posts when inside a loop. + function mdwp_MarkdownPost($text) { + static $parser; + if (!$parser) { + $parser_class = MARKDOWN_PARSER_CLASS; + $parser = new $parser_class; + } + if (is_single() || is_page() || is_feed()) { + $parser->fn_id_prefix = ""; + } else { + $parser->fn_id_prefix = get_the_ID() . "."; + } + return $parser->transform($text); + } + + # Comments + # - Remove WordPress paragraph generator. + # - Remove WordPress auto-link generator. + # - Scramble important tags before passing them to the kses filter. + # - Run Markdown on excerpt then remove paragraph tags. + if (MARKDOWN_WP_COMMENTS) { + remove_filter('comment_text', 'wpautop', 30); + remove_filter('comment_text', 'make_clickable'); + add_filter('pre_comment_content', 'Markdown', 6); + add_filter('pre_comment_content', 'mdwp_hide_tags', 8); + add_filter('pre_comment_content', 'mdwp_show_tags', 12); + add_filter('get_comment_text', 'Markdown', 6); + add_filter('get_comment_excerpt', 'Markdown', 6); + add_filter('get_comment_excerpt', 'mdwp_strip_p', 7); + + global $mdwp_hidden_tags, $mdwp_placeholders; + $mdwp_hidden_tags = explode(' ', + '<p> </p> <pre> </pre> <ol> </ol> <ul> </ul> <li> </li>'); + $mdwp_placeholders = explode(' ', str_rot13( + 'pEj07ZbbBZ U1kqgh4w4p pre2zmeN6K QTi31t9pre ol0MP1jzJR '. + 'ML5IjmbRol ulANi1NsGY J7zRLJqPul liA8ctl16T K9nhooUHli')); + } + + function mdwp_add_p($text) { + if (!preg_match('{^$|^<(p|ul|ol|dl|pre|blockquote)>}i', $text)) { + $text = '<p>'.$text.'</p>'; + $text = preg_replace('{\n{2,}}', "</p>\n\n<p>", $text); + } + return $text; + } + + function mdwp_strip_p($t) { return preg_replace('{</?p>}i', '', $t); } + + function mdwp_hide_tags($text) { + global $mdwp_hidden_tags, $mdwp_placeholders; + return str_replace($mdwp_hidden_tags, $mdwp_placeholders, $text); + } + function mdwp_show_tags($text) { + global $mdwp_hidden_tags, $mdwp_placeholders; + return str_replace($mdwp_placeholders, $mdwp_hidden_tags, $text); + } +} + + +### bBlog Plugin Info ### + +function identify_modifier_markdown() { + return array( + 'name' => 'markdown', + 'type' => 'modifier', + 'nicename' => 'PHP Markdown Extra', + 'description' => 'A text-to-HTML conversion tool for web writers', + 'authors' => 'Michel Fortin and John Gruber', + 'licence' => 'GPL', + 'version' => MARKDOWNEXTRA_VERSION, + 'help' => '<a href="http://daringfireball.net/projects/markdown/syntax">Markdown syntax</a> allows you to write using an easy-to-read, easy-to-write plain text format. Based on the original Perl version by <a href="http://daringfireball.net/">John Gruber</a>. <a href="http://michelf.com/projects/php-markdown/">More...</a>', + ); +} + + +### Smarty Modifier Interface ### + +function smarty_modifier_markdown($text) { + return Markdown($text); +} + + +### Textile Compatibility Mode ### + +# Rename this file to "classTextile.php" and it can replace Textile everywhere. + +if (strcasecmp(substr(__FILE__, -16), "classTextile.php") == 0) { + # Try to include PHP SmartyPants. Should be in the same directory. + @include_once 'smartypants.php'; + # Fake Textile class. It calls Markdown instead. + class Textile { + function TextileThis($text, $lite='', $encode='') { + if ($lite == '' && $encode == '') $text = Markdown($text); + if (function_exists('SmartyPants')) $text = SmartyPants($text); + return $text; + } + # Fake restricted version: restrictions are not supported for now. + function TextileRestricted($text, $lite='', $noimage='') { + return $this->TextileThis($text, $lite); + } + # Workaround to ensure compatibility with TextPattern 4.0.3. + function blockLite($text) { return $text; } + } +} + + + +# +# Markdown Parser Class +# + +class Markdown_Parser { + + # Regex to match balanced [brackets]. + # Needed to insert a maximum bracked depth while converting to PHP. + var $nested_brackets_depth = 6; + var $nested_brackets_re; + + var $nested_url_parenthesis_depth = 4; + var $nested_url_parenthesis_re; + + # Table of hash values for escaped characters: + var $escape_chars = '\`*_{}[]()>#+-.!'; + var $escape_chars_re; + + # Change to ">" for HTML output. + var $empty_element_suffix = MARKDOWN_EMPTY_ELEMENT_SUFFIX; + var $tab_width = MARKDOWN_TAB_WIDTH; + + # Change to `true` to disallow markup or entities. + var $no_markup = false; + var $no_entities = false; + + # Predefined urls and titles for reference links and images. + var $predef_urls = array(); + var $predef_titles = array(); + + + function Markdown_Parser() { + # + # Constructor function. Initialize appropriate member variables. + # + $this->_initDetab(); + $this->prepareItalicsAndBold(); + + $this->nested_brackets_re = + str_repeat('(?>[^\[\]]+|\[', $this->nested_brackets_depth). + str_repeat('\])*', $this->nested_brackets_depth); + + $this->nested_url_parenthesis_re = + str_repeat('(?>[^()\s]+|\(', $this->nested_url_parenthesis_depth). + str_repeat('(?>\)))*', $this->nested_url_parenthesis_depth); + + $this->escape_chars_re = '['.preg_quote($this->escape_chars).']'; + + # Sort document, block, and span gamut in ascendent priority order. + asort($this->document_gamut); + asort($this->block_gamut); + asort($this->span_gamut); + } + + + # Internal hashes used during transformation. + var $urls = array(); + var $titles = array(); + var $html_hashes = array(); + + # Status flag to avoid invalid nesting. + var $in_anchor = false; + + + function setup() { + # + # Called before the transformation process starts to setup parser + # states. + # + # Clear global hashes. + $this->urls = $this->predef_urls; + $this->titles = $this->predef_titles; + $this->html_hashes = array(); + + $in_anchor = false; + } + + function teardown() { + # + # Called after the transformation process to clear any variable + # which may be taking up memory unnecessarly. + # + $this->urls = array(); + $this->titles = array(); + $this->html_hashes = array(); + } + + + function transform($text) { + # + # Main function. Performs some preprocessing on the input text + # and pass it through the document gamut. + # + $this->setup(); + + # Remove UTF-8 BOM and marker character in input, if present. + $text = preg_replace('{^\xEF\xBB\xBF|\x1A}', '', $text); + + # Standardize line endings: + # DOS to Unix and Mac to Unix + $text = preg_replace('{\r\n?}', "\n", $text); + + # Make sure $text ends with a couple of newlines: + $text .= "\n\n"; + + # Convert all tabs to spaces. + $text = $this->detab($text); + + # Turn block-level HTML blocks into hash entries + $text = $this->hashHTMLBlocks($text); + + # Strip any lines consisting only of spaces and tabs. + # This makes subsequent regexen easier to write, because we can + # match consecutive blank lines with /\n+/ instead of something + # contorted like /[ ]*\n+/ . + $text = preg_replace('/^[ ]+$/m', '', $text); + + # Run document gamut methods. + foreach ($this->document_gamut as $method => $priority) { + $text = $this->$method($text); + } + + $this->teardown(); + + return $text . "\n"; + } + + var $document_gamut = array( + # Strip link definitions, store in hashes. + "stripLinkDefinitions" => 20, + + "runBasicBlockGamut" => 30, + ); + + + function stripLinkDefinitions($text) { + # + # Strips link definitions from text, stores the URLs and titles in + # hash references. + # + $less_than_tab = $this->tab_width - 1; + + # Link defs are in the form: ^[id]: url "optional title" + $text = preg_replace_callback('{ + ^[ ]{0,'.$less_than_tab.'}\[(.+)\][ ]?: # id = $1 + [ ]* + \n? # maybe *one* newline + [ ]* + (?: + <(.+?)> # url = $2 + | + (\S+?) # url = $3 + ) + [ ]* + \n? # maybe one newline + [ ]* + (?: + (?<=\s) # lookbehind for whitespace + ["(] + (.*?) # title = $4 + [")] + [ ]* + )? # title is optional + (?:\n+|\Z) + }xm', + array(&$this, '_stripLinkDefinitions_callback'), + $text); + return $text; + } + function _stripLinkDefinitions_callback($matches) { + $link_id = strtolower($matches[1]); + $url = $matches[2] == '' ? $matches[3] : $matches[2]; + $this->urls[$link_id] = $url; + $this->titles[$link_id] =& $matches[4]; + return ''; # String that will replace the block + } + + + function hashHTMLBlocks($text) { + if ($this->no_markup) return $text; + + $less_than_tab = $this->tab_width - 1; + + # Hashify HTML blocks: + # We only want to do this for block-level HTML tags, such as headers, + # lists, and tables. That's because we still want to wrap <p>s around + # "paragraphs" that are wrapped in non-block-level tags, such as anchors, + # phrase emphasis, and spans. The list of tags we're looking for is + # hard-coded: + # + # * List "a" is made of tags which can be both inline or block-level. + # These will be treated block-level when the start tag is alone on + # its line, otherwise they're not matched here and will be taken as + # inline later. + # * List "b" is made of tags which are always block-level; + # + $block_tags_a_re = 'ins|del'; + $block_tags_b_re = 'p|div|h[1-6]|blockquote|pre|table|dl|ol|ul|address|'. + 'script|noscript|form|fieldset|iframe|math'; + + # Regular expression for the content of a block tag. + $nested_tags_level = 4; + $attr = ' + (?> # optional tag attributes + \s # starts with whitespace + (?> + [^>"/]+ # text outside quotes + | + /+(?!>) # slash not followed by ">" + | + "[^"]*" # text inside double quotes (tolerate ">") + | + \'[^\']*\' # text inside single quotes (tolerate ">") + )* + )? + '; + $content = + str_repeat(' + (?> + [^<]+ # content without tag + | + <\2 # nested opening tag + '.$attr.' # attributes + (?> + /> + | + >', $nested_tags_level). # end of opening tag + '.*?'. # last level nested tag content + str_repeat(' + </\2\s*> # closing nested tag + ) + | + <(?!/\2\s*> # other tags with a different name + ) + )*', + $nested_tags_level); + $content2 = str_replace('\2', '\3', $content); + + # First, look for nested blocks, e.g.: + # <div> + # <div> + # tags for inner block must be indented. + # </div> + # </div> + # + # The outermost tags must start at the left margin for this to match, and + # the inner nested divs must be indented. + # We need to do this before the next, more liberal match, because the next + # match will start at the first `<div>` and stop at the first `</div>`. + $text = preg_replace_callback('{(?> + (?> + (?<=\n\n) # Starting after a blank line + | # or + \A\n? # the beginning of the doc + ) + ( # save in $1 + + # Match from `\n<tag>` to `</tag>\n`, handling nested tags + # in between. + + [ ]{0,'.$less_than_tab.'} + <('.$block_tags_b_re.')# start tag = $2 + '.$attr.'> # attributes followed by > and \n + '.$content.' # content, support nesting + </\2> # the matching end tag + [ ]* # trailing spaces/tabs + (?=\n+|\Z) # followed by a newline or end of document + + | # Special version for tags of group a. + + [ ]{0,'.$less_than_tab.'} + <('.$block_tags_a_re.')# start tag = $3 + '.$attr.'>[ ]*\n # attributes followed by > + '.$content2.' # content, support nesting + </\3> # the matching end tag + [ ]* # trailing spaces/tabs + (?=\n+|\Z) # followed by a newline or end of document + + | # Special case just for <hr />. It was easier to make a special + # case than to make the other regex more complicated. + + [ ]{0,'.$less_than_tab.'} + <(hr) # start tag = $2 + '.$attr.' # attributes + /?> # the matching end tag + [ ]* + (?=\n{2,}|\Z) # followed by a blank line or end of document + + | # Special case for standalone HTML comments: + + [ ]{0,'.$less_than_tab.'} + (?s: + <!-- .*? --> + ) + [ ]* + (?=\n{2,}|\Z) # followed by a blank line or end of document + + | # PHP and ASP-style processor instructions (<? and <%) + + [ ]{0,'.$less_than_tab.'} + (?s: + <([?%]) # $2 + .*? + \2> + ) + [ ]* + (?=\n{2,}|\Z) # followed by a blank line or end of document + + ) + )}Sxmi', + array(&$this, '_hashHTMLBlocks_callback'), + $text); + + return $text; + } + function _hashHTMLBlocks_callback($matches) { + $text = $matches[1]; + $key = $this->hashBlock($text); + return "\n\n$key\n\n"; + } + + + function hashPart($text, $boundary = 'X') { + # + # Called whenever a tag must be hashed when a function insert an atomic + # element in the text stream. Passing $text to through this function gives + # a unique text-token which will be reverted back when calling unhash. + # + # The $boundary argument specify what character should be used to surround + # the token. By convension, "B" is used for block elements that needs not + # to be wrapped into paragraph tags at the end, ":" is used for elements + # that are word separators and "X" is used in the general case. + # + # Swap back any tag hash found in $text so we do not have to `unhash` + # multiple times at the end. + $text = $this->unhash($text); + + # Then hash the block. + static $i = 0; + $key = "$boundary\x1A" . ++$i . $boundary; + $this->html_hashes[$key] = $text; + return $key; # String that will replace the tag. + } + + + function hashBlock($text) { + # + # Shortcut function for hashPart with block-level boundaries. + # + return $this->hashPart($text, 'B'); + } + + + var $block_gamut = array( + # + # These are all the transformations that form block-level + # tags like paragraphs, headers, and list items. + # + "doHeaders" => 10, + "doHorizontalRules" => 20, + + "doLists" => 40, + "doCodeBlocks" => 50, + "doBlockQuotes" => 60, + ); + + function runBlockGamut($text) { + # + # Run block gamut tranformations. + # + # We need to escape raw HTML in Markdown source before doing anything + # else. This need to be done for each block, and not only at the + # begining in the Markdown function since hashed blocks can be part of + # list items and could have been indented. Indented blocks would have + # been seen as a code block in a previous pass of hashHTMLBlocks. + $text = $this->hashHTMLBlocks($text); + + return $this->runBasicBlockGamut($text); + } + + function runBasicBlockGamut($text) { + # + # Run block gamut tranformations, without hashing HTML blocks. This is + # useful when HTML blocks are known to be already hashed, like in the first + # whole-document pass. + # + foreach ($this->block_gamut as $method => $priority) { + $text = $this->$method($text); + } + + # Finally form paragraph and restore hashed blocks. + $text = $this->formParagraphs($text); + + return $text; + } + + + function doHorizontalRules($text) { + # Do Horizontal Rules: + return preg_replace( + '{ + ^[ ]{0,3} # Leading space + ([-*_]) # $1: First marker + (?> # Repeated marker group + [ ]{0,2} # Zero, one, or two spaces. + \1 # Marker character + ){2,} # Group repeated at least twice + [ ]* # Tailing spaces + $ # End of line. + }mx', + "\n".$this->hashBlock("<hr$this->empty_element_suffix")."\n", + $text); + } + + + var $span_gamut = array( + # + # These are all the transformations that occur *within* block-level + # tags like paragraphs, headers, and list items. + # + # Process character escapes, code spans, and inline HTML + # in one shot. + "parseSpan" => -30, + + # Process anchor and image tags. Images must come first, + # because ![foo][f] looks like an anchor. + "doImages" => 10, + "doAnchors" => 20, + + # Make links out of things like `<http://example.com/>` + # Must come after doAnchors, because you can use < and > + # delimiters in inline links like [this](<url>). + "doAutoLinks" => 30, + "encodeAmpsAndAngles" => 40, + + "doItalicsAndBold" => 50, + "doHardBreaks" => 60, + ); + + function runSpanGamut($text) { + # + # Run span gamut tranformations. + # + foreach ($this->span_gamut as $method => $priority) { + $text = $this->$method($text); + } + + return $text; + } + + + function doHardBreaks($text) { + # Do hard breaks: + return preg_replace_callback('/ {2,}\n/', + array(&$this, '_doHardBreaks_callback'), $text); + } + function _doHardBreaks_callback($matches) { + return $this->hashPart("<br$this->empty_element_suffix\n"); + } + + + function doAnchors($text) { + # + # Turn Markdown link shortcuts into XHTML <a> tags. + # + if ($this->in_anchor) return $text; + $this->in_anchor = true; + + # + # First, handle reference-style links: [link text] [id] + # + $text = preg_replace_callback('{ + ( # wrap whole match in $1 + \[ + ('.$this->nested_brackets_re.') # link text = $2 + \] + + [ ]? # one optional space + (?:\n[ ]*)? # one optional newline followed by spaces + + \[ + (.*?) # id = $3 + \] + ) + }xs', + array(&$this, '_doAnchors_reference_callback'), $text); + + # + # Next, inline-style links: [link text](url "optional title") + # + $text = preg_replace_callback('{ + ( # wrap whole match in $1 + \[ + ('.$this->nested_brackets_re.') # link text = $2 + \] + \( # literal paren + [ \n]* + (?: + <(.+?)> # href = $3 + | + ('.$this->nested_url_parenthesis_re.') # href = $4 + ) + [ \n]* + ( # $5 + ([\'"]) # quote char = $6 + (.*?) # Title = $7 + \6 # matching quote + [ \n]* # ignore any spaces/tabs between closing quote and ) + )? # title is optional + \) + ) + }xs', + array(&$this, '_doAnchors_inline_callback'), $text); + + # + # Last, handle reference-style shortcuts: [link text] + # These must come last in case you've also got [link text][1] + # or [link text](/foo) + # + $text = preg_replace_callback('{ + ( # wrap whole match in $1 + \[ + ([^\[\]]+) # link text = $2; can\'t contain [ or ] + \] + ) + }xs', + array(&$this, '_doAnchors_reference_callback'), $text); + + $this->in_anchor = false; + return $text; + } + function _doAnchors_reference_callback($matches) { + $whole_match = $matches[1]; + $link_text = $matches[2]; + $link_id =& $matches[3]; + + if ($link_id == "") { + # for shortcut links like [this][] or [this]. + $link_id = $link_text; + } + + # lower-case and turn embedded newlines into spaces + $link_id = strtolower($link_id); + $link_id = preg_replace('{[ ]?\n}', ' ', $link_id); + + if (isset($this->urls[$link_id])) { + $url = $this->urls[$link_id]; + $url = $this->encodeAttribute($url); + + $result = "<a href=\"$url\""; + if ( isset( $this->titles[$link_id] ) ) { + $title = $this->titles[$link_id]; + $title = $this->encodeAttribute($title); + $result .= " title=\"$title\""; + } + + $link_text = $this->runSpanGamut($link_text); + $result .= ">$link_text</a>"; + $result = $this->hashPart($result); + } + else { + $result = $whole_match; + } + return $result; + } + function _doAnchors_inline_callback($matches) { + $whole_match = $matches[1]; + $link_text = $this->runSpanGamut($matches[2]); + $url = $matches[3] == '' ? $matches[4] : $matches[3]; + $title =& $matches[7]; + + $url = $this->encodeAttribute($url); + + $result = "<a href=\"$url\""; + if (isset($title)) { + $title = $this->encodeAttribute($title); + $result .= " title=\"$title\""; + } + + $link_text = $this->runSpanGamut($link_text); + $result .= ">$link_text</a>"; + + return $this->hashPart($result); + } + + + function doImages($text) { + # + # Turn Markdown image shortcuts into <img> tags. + # + # + # First, handle reference-style labeled images: ![alt text][id] + # + $text = preg_replace_callback('{ + ( # wrap whole match in $1 + !\[ + ('.$this->nested_brackets_re.') # alt text = $2 + \] + + [ ]? # one optional space + (?:\n[ ]*)? # one optional newline followed by spaces + + \[ + (.*?) # id = $3 + \] + + ) + }xs', + array(&$this, '_doImages_reference_callback'), $text); + + # + # Next, handle inline images:  + # Don't forget: encode * and _ + # + $text = preg_replace_callback('{ + ( # wrap whole match in $1 + !\[ + ('.$this->nested_brackets_re.') # alt text = $2 + \] + \s? # One optional whitespace character + \( # literal paren + [ \n]* + (?: + <(\S*)> # src url = $3 + | + ('.$this->nested_url_parenthesis_re.') # src url = $4 + ) + [ \n]* + ( # $5 + ([\'"]) # quote char = $6 + (.*?) # title = $7 + \6 # matching quote + [ \n]* + )? # title is optional + \) + ) + }xs', + array(&$this, '_doImages_inline_callback'), $text); + + return $text; + } + function _doImages_reference_callback($matches) { + $whole_match = $matches[1]; + $alt_text = $matches[2]; + $link_id = strtolower($matches[3]); + + if ($link_id == "") { + $link_id = strtolower($alt_text); # for shortcut links like ![this][]. + } + + $alt_text = $this->encodeAttribute($alt_text); + if (isset($this->urls[$link_id])) { + $url = $this->encodeAttribute($this->urls[$link_id]); + $result = "<img src=\"$url\" alt=\"$alt_text\""; + if (isset($this->titles[$link_id])) { + $title = $this->titles[$link_id]; + $title = $this->encodeAttribute($title); + $result .= " title=\"$title\""; + } + $result .= $this->empty_element_suffix; + $result = $this->hashPart($result); + } + else { + # If there's no such link ID, leave intact: + $result = $whole_match; + } + + return $result; + } + function _doImages_inline_callback($matches) { + $whole_match = $matches[1]; + $alt_text = $matches[2]; + $url = $matches[3] == '' ? $matches[4] : $matches[3]; + $title =& $matches[7]; + + $alt_text = $this->encodeAttribute($alt_text); + $url = $this->encodeAttribute($url); + $result = "<img src=\"$url\" alt=\"$alt_text\""; + if (isset($title)) { + $title = $this->encodeAttribute($title); + $result .= " title=\"$title\""; # $title already quoted + } + $result .= $this->empty_element_suffix; + + return $this->hashPart($result); + } + + + function doHeaders($text) { + # Setext-style headers: + # Header 1 + # ======== + # + # Header 2 + # -------- + # + $text = preg_replace_callback('{ ^(.+?)[ ]*\n(=+|-+)[ ]*\n+ }mx', + array(&$this, '_doHeaders_callback_setext'), $text); + + # atx-style headers: + # # Header 1 + # ## Header 2 + # ## Header 2 with closing hashes ## + # ... + # ###### Header 6 + # + $text = preg_replace_callback('{ + ^(\#{1,6}) # $1 = string of #\'s + [ ]* + (.+?) # $2 = Header text + [ ]* + \#* # optional closing #\'s (not counted) + \n+ + }xm', + array(&$this, '_doHeaders_callback_atx'), $text); + + return $text; + } + function _doHeaders_callback_setext($matches) { + # Terrible hack to check we haven't found an empty list item. + if ($matches[2] == '-' && preg_match('{^-(?: |$)}', $matches[1])) + return $matches[0]; + + $level = $matches[2]{0} == '=' ? 1 : 2; + $block = "<h$level>".$this->runSpanGamut($matches[1])."</h$level>"; + return "\n" . $this->hashBlock($block) . "\n\n"; + } + function _doHeaders_callback_atx($matches) { + $level = strlen($matches[1]); + $block = "<h$level>".$this->runSpanGamut($matches[2])."</h$level>"; + return "\n" . $this->hashBlock($block) . "\n\n"; + } + + + function doLists($text) { + # + # Form HTML ordered (numbered) and unordered (bulleted) lists. + # + $less_than_tab = $this->tab_width - 1; + + # Re-usable patterns to match list item bullets and number markers: + $marker_ul_re = '[*+-]'; + $marker_ol_re = '\d+[.]'; + $marker_any_re = "(?:$marker_ul_re|$marker_ol_re)"; + + $markers_relist = array( + $marker_ul_re => $marker_ol_re, + $marker_ol_re => $marker_ul_re, + ); + + foreach ($markers_relist as $marker_re => $other_marker_re) { + # Re-usable pattern to match any entirel ul or ol list: + $whole_list_re = ' + ( # $1 = whole list + ( # $2 + ([ ]{0,'.$less_than_tab.'}) # $3 = number of spaces + ('.$marker_re.') # $4 = first list item marker + [ ]+ + ) + (?s:.+?) + ( # $5 + \z + | + \n{2,} + (?=\S) + (?! # Negative lookahead for another list item marker + [ ]* + '.$marker_re.'[ ]+ + ) + | + (?= # Lookahead for another kind of list + \n + \3 # Must have the same indentation + '.$other_marker_re.'[ ]+ + ) + ) + ) + '; // mx + + # We use a different prefix before nested lists than top-level lists. + # See extended comment in _ProcessListItems(). + + if ($this->list_level) { + $text = preg_replace_callback('{ + ^ + '.$whole_list_re.' + }mx', + array(&$this, '_doLists_callback'), $text); + } + else { + $text = preg_replace_callback('{ + (?:(?<=\n)\n|\A\n?) # Must eat the newline + '.$whole_list_re.' + }mx', + array(&$this, '_doLists_callback'), $text); + } + } + + return $text; + } + function _doLists_callback($matches) { + # Re-usable patterns to match list item bullets and number markers: + $marker_ul_re = '[*+-]'; + $marker_ol_re = '\d+[.]'; + $marker_any_re = "(?:$marker_ul_re|$marker_ol_re)"; + + $list = $matches[1]; + $list_type = preg_match("/$marker_ul_re/", $matches[4]) ? "ul" : "ol"; + + $marker_any_re = ( $list_type == "ul" ? $marker_ul_re : $marker_ol_re ); + + $list .= "\n"; + $result = $this->processListItems($list, $marker_any_re); + + $result = $this->hashBlock("<$list_type>\n" . $result . "</$list_type>"); + return "\n". $result ."\n\n"; + } + + var $list_level = 0; + + function processListItems($list_str, $marker_any_re) { + # + # Process the contents of a single ordered or unordered list, splitting it + # into individual list items. + # + # The $this->list_level global keeps track of when we're inside a list. + # Each time we enter a list, we increment it; when we leave a list, + # we decrement. If it's zero, we're not in a list anymore. + # + # We do this because when we're not inside a list, we want to treat + # something like this: + # + # I recommend upgrading to version + # 8. Oops, now this line is treated + # as a sub-list. + # + # As a single paragraph, despite the fact that the second line starts + # with a digit-period-space sequence. + # + # Whereas when we're inside a list (or sub-list), that line will be + # treated as the start of a sub-list. What a kludge, huh? This is + # an aspect of Markdown's syntax that's hard to parse perfectly + # without resorting to mind-reading. Perhaps the solution is to + # change the syntax rules such that sub-lists must start with a + # starting cardinal number; e.g. "1." or "a.". + + $this->list_level++; + + # trim trailing blank lines: + $list_str = preg_replace("/\n{2,}\\z/", "\n", $list_str); + + $list_str = preg_replace_callback('{ + (\n)? # leading line = $1 + (^[ ]*) # leading whitespace = $2 + ('.$marker_any_re.' # list marker and space = $3 + (?:[ ]+|(?=\n)) # space only required if item is not empty + ) + ((?s:.*?)) # list item text = $4 + (?:(\n+(?=\n))|\n) # tailing blank line = $5 + (?= \n* (\z | \2 ('.$marker_any_re.') (?:[ ]+|(?=\n)))) + }xm', + array(&$this, '_processListItems_callback'), $list_str); + + $this->list_level--; + return $list_str; + } + function _processListItems_callback($matches) { + $item = $matches[4]; + $leading_line =& $matches[1]; + $leading_space =& $matches[2]; + $marker_space = $matches[3]; + $tailing_blank_line =& $matches[5]; + + if ($leading_line || $tailing_blank_line || + preg_match('/\n{2,}/', $item)) + { + # Replace marker with the appropriate whitespace indentation + $item = $leading_space . str_repeat(' ', strlen($marker_space)) . $item; + $item = $this->runBlockGamut($this->outdent($item)."\n"); + } + else { + # Recursion for sub-lists: + $item = $this->doLists($this->outdent($item)); + $item = preg_replace('/\n+$/', '', $item); + $item = $this->runSpanGamut($item); + } + + return "<li>" . $item . "</li>\n"; + } + + + function doCodeBlocks($text) { + # + # Process Markdown `<pre><code>` blocks. + # + $text = preg_replace_callback('{ + (?:\n\n|\A\n?) + ( # $1 = the code block -- one or more lines, starting with a space/tab + (?> + [ ]{'.$this->tab_width.'} # Lines must start with a tab or a tab-width of spaces + .*\n+ + )+ + ) + ((?=^[ ]{0,'.$this->tab_width.'}\S)|\Z) # Lookahead for non-space at line-start, or end of doc + }xm', + array(&$this, '_doCodeBlocks_callback'), $text); + + return $text; + } + function _doCodeBlocks_callback($matches) { + $codeblock = $matches[1]; + + $codeblock = $this->outdent($codeblock); + $codeblock = htmlspecialchars($codeblock, ENT_NOQUOTES); + + # trim leading newlines and trailing newlines + $codeblock = preg_replace('/\A\n+|\n+\z/', '', $codeblock); + + $codeblock = "<pre><code>$codeblock\n</code></pre>"; + return "\n\n".$this->hashBlock($codeblock)."\n\n"; + } + + + function makeCodeSpan($code) { + # + # Create a code span markup for $code. Called from handleSpanToken. + # + $code = htmlspecialchars(trim($code), ENT_NOQUOTES); + return $this->hashPart("<code>$code</code>"); + } + + + var $em_relist = array( + '' => '(?:(?<!\*)\*(?!\*)|(?<!_)_(?!_))(?=\S|$)(?![.,:;]\s)', + '*' => '(?<=\S|^)(?<!\*)\*(?!\*)', + '_' => '(?<=\S|^)(?<!_)_(?!_)', + ); + var $strong_relist = array( + '' => '(?:(?<!\*)\*\*(?!\*)|(?<!_)__(?!_))(?=\S|$)(?![.,:;]\s)', + '**' => '(?<=\S|^)(?<!\*)\*\*(?!\*)', + '__' => '(?<=\S|^)(?<!_)__(?!_)', + ); + var $em_strong_relist = array( + '' => '(?:(?<!\*)\*\*\*(?!\*)|(?<!_)___(?!_))(?=\S|$)(?![.,:;]\s)', + '***' => '(?<=\S|^)(?<!\*)\*\*\*(?!\*)', + '___' => '(?<=\S|^)(?<!_)___(?!_)', + ); + var $em_strong_prepared_relist; + + function prepareItalicsAndBold() { + # + # Prepare regular expressions for searching emphasis tokens in any + # context. + # + foreach ($this->em_relist as $em => $em_re) { + foreach ($this->strong_relist as $strong => $strong_re) { + # Construct list of allowed token expressions. + $token_relist = array(); + if (isset($this->em_strong_relist["$em$strong"])) { + $token_relist[] = $this->em_strong_relist["$em$strong"]; + } + $token_relist[] = $em_re; + $token_relist[] = $strong_re; + + # Construct master expression from list. + $token_re = '{('. implode('|', $token_relist) .')}'; + $this->em_strong_prepared_relist["$em$strong"] = $token_re; + } + } + } + + function doItalicsAndBold($text) { + $token_stack = array(''); + $text_stack = array(''); + $em = ''; + $strong = ''; + $tree_char_em = false; + + while (1) { + # + # Get prepared regular expression for seraching emphasis tokens + # in current context. + # + $token_re = $this->em_strong_prepared_relist["$em$strong"]; + + # + # Each loop iteration search for the next emphasis token. + # Each token is then passed to handleSpanToken. + # + $parts = preg_split($token_re, $text, 2, PREG_SPLIT_DELIM_CAPTURE); + $text_stack[0] .= $parts[0]; + $token =& $parts[1]; + $text =& $parts[2]; + + if (empty($token)) { + # Reached end of text span: empty stack without emitting. + # any more emphasis. + while ($token_stack[0]) { + $text_stack[1] .= array_shift($token_stack); + $text_stack[0] .= array_shift($text_stack); + } + break; + } + + $token_len = strlen($token); + if ($tree_char_em) { + # Reached closing marker while inside a three-char emphasis. + if ($token_len == 3) { + # Three-char closing marker, close em and strong. + array_shift($token_stack); + $span = array_shift($text_stack); + $span = $this->runSpanGamut($span); + $span = "<strong><em>$span</em></strong>"; + $text_stack[0] .= $this->hashPart($span); + $em = ''; + $strong = ''; + } else { + # Other closing marker: close one em or strong and + # change current token state to match the other + $token_stack[0] = str_repeat($token{0}, 3-$token_len); + $tag = $token_len == 2 ? "strong" : "em"; + $span = $text_stack[0]; + $span = $this->runSpanGamut($span); + $span = "<$tag>$span</$tag>"; + $text_stack[0] = $this->hashPart($span); + $$tag = ''; # $$tag stands for $em or $strong + } + $tree_char_em = false; + } else if ($token_len == 3) { + if ($em) { + # Reached closing marker for both em and strong. + # Closing strong marker: + for ($i = 0; $i < 2; ++$i) { + $shifted_token = array_shift($token_stack); + $tag = strlen($shifted_token) == 2 ? "strong" : "em"; + $span = array_shift($text_stack); + $span = $this->runSpanGamut($span); + $span = "<$tag>$span</$tag>"; + $text_stack[0] .= $this->hashPart($span); + $$tag = ''; # $$tag stands for $em or $strong + } + } else { + # Reached opening three-char emphasis marker. Push on token + # stack; will be handled by the special condition above. + $em = $token{0}; + $strong = "$em$em"; + array_unshift($token_stack, $token); + array_unshift($text_stack, ''); + $tree_char_em = true; + } + } else if ($token_len == 2) { + if ($strong) { + # Unwind any dangling emphasis marker: + if (strlen($token_stack[0]) == 1) { + $text_stack[1] .= array_shift($token_stack); + $text_stack[0] .= array_shift($text_stack); + } + # Closing strong marker: + array_shift($token_stack); + $span = array_shift($text_stack); + $span = $this->runSpanGamut($span); + $span = "<strong>$span</strong>"; + $text_stack[0] .= $this->hashPart($span); + $strong = ''; + } else { + array_unshift($token_stack, $token); + array_unshift($text_stack, ''); + $strong = $token; + } + } else { + # Here $token_len == 1 + if ($em) { + if (strlen($token_stack[0]) == 1) { + # Closing emphasis marker: + array_shift($token_stack); + $span = array_shift($text_stack); + $span = $this->runSpanGamut($span); + $span = "<em>$span</em>"; + $text_stack[0] .= $this->hashPart($span); + $em = ''; + } else { + $text_stack[0] .= $token; + } + } else { + array_unshift($token_stack, $token); + array_unshift($text_stack, ''); + $em = $token; + } + } + } + return $text_stack[0]; + } + + + function doBlockQuotes($text) { + $text = preg_replace_callback('/ + ( # Wrap whole match in $1 + (?> + ^[ ]*>[ ]? # ">" at the start of a line + .+\n # rest of the first line + (.+\n)* # subsequent consecutive lines + \n* # blanks + )+ + ) + /xm', + array(&$this, '_doBlockQuotes_callback'), $text); + + return $text; + } + function _doBlockQuotes_callback($matches) { + $bq = $matches[1]; + # trim one level of quoting - trim whitespace-only lines + $bq = preg_replace('/^[ ]*>[ ]?|^[ ]+$/m', '', $bq); + $bq = $this->runBlockGamut($bq); # recurse + + $bq = preg_replace('/^/m', " ", $bq); + # These leading spaces cause problem with <pre> content, + # so we need to fix that: + $bq = preg_replace_callback('{(\s*<pre>.+?</pre>)}sx', + array(&$this, '_doBlockQuotes_callback2'), $bq); + + return "\n". $this->hashBlock("<blockquote>\n$bq\n</blockquote>")."\n\n"; + } + function _doBlockQuotes_callback2($matches) { + $pre = $matches[1]; + $pre = preg_replace('/^ /m', '', $pre); + return $pre; + } + + + function formParagraphs($text) { + # + # Params: + # $text - string to process with html <p> tags + # + # Strip leading and trailing lines: + $text = preg_replace('/\A\n+|\n+\z/', '', $text); + + $grafs = preg_split('/\n{2,}/', $text, -1, PREG_SPLIT_NO_EMPTY); + + # + # Wrap <p> tags and unhashify HTML blocks + # + foreach ($grafs as $key => $value) { + if (!preg_match('/^B\x1A[0-9]+B$/', $value)) { + # Is a paragraph. + $value = $this->runSpanGamut($value); + $value = preg_replace('/^([ ]*)/', "<p>", $value); + $value .= "</p>"; + $grafs[$key] = $this->unhash($value); + } + else { + # Is a block. + # Modify elements of @grafs in-place... + $graf = $value; + $block = $this->html_hashes[$graf]; + $graf = $block; +// if (preg_match('{ +// \A +// ( # $1 = <div> tag +// <div \s+ +// [^>]* +// \b +// markdown\s*=\s* ([\'"]) # $2 = attr quote char +// 1 +// \2 +// [^>]* +// > +// ) +// ( # $3 = contents +// .* +// ) +// (</div>) # $4 = closing tag +// \z +// }xs', $block, $matches)) +// { +// list(, $div_open, , $div_content, $div_close) = $matches; +// +// # We can't call Markdown(), because that resets the hash; +// # that initialization code should be pulled into its own sub, though. +// $div_content = $this->hashHTMLBlocks($div_content); +// +// # Run document gamut methods on the content. +// foreach ($this->document_gamut as $method => $priority) { +// $div_content = $this->$method($div_content); +// } +// +// $div_open = preg_replace( +// '{\smarkdown\s*=\s*([\'"]).+?\1}', '', $div_open); +// +// $graf = $div_open . "\n" . $div_content . "\n" . $div_close; +// } + $grafs[$key] = $graf; + } + } + + return implode("\n\n", $grafs); + } + + + function encodeAttribute($text) { + # + # Encode text for a double-quoted HTML attribute. This function + # is *not* suitable for attributes enclosed in single quotes. + # + $text = $this->encodeAmpsAndAngles($text); + $text = str_replace('"', '"', $text); + return $text; + } + + + function encodeAmpsAndAngles($text) { + # + # Smart processing for ampersands and angle brackets that need to + # be encoded. Valid character entities are left alone unless the + # no-entities mode is set. + # + if ($this->no_entities) { + $text = str_replace('&', '&', $text); + } else { + # Ampersand-encoding based entirely on Nat Irons's Amputator + # MT plugin: <http://bumppo.net/projects/amputator/> + $text = preg_replace('/&(?!#?[xX]?(?:[0-9a-fA-F]+|\w+);)/', + '&', $text);; + } + # Encode remaining <'s + $text = str_replace('<', '<', $text); + + return $text; + } + + + function doAutoLinks($text) { + $text = preg_replace_callback('{<((https?|ftp|dict):[^\'">\s]+)>}i', + array(&$this, '_doAutoLinks_url_callback'), $text); + + # Email addresses: <address@domain.foo> + $text = preg_replace_callback('{ + < + (?:mailto:)? + ( + (?: + [-!#$%&\'*+/=?^_`.{|}~\w\x80-\xFF]+ + | + ".*?" + ) + \@ + (?: + [-a-z0-9\x80-\xFF]+(\.[-a-z0-9\x80-\xFF]+)*\.[a-z]+ + | + \[[\d.a-fA-F:]+\] # IPv4 & IPv6 + ) + ) + > + }xi', + array(&$this, '_doAutoLinks_email_callback'), $text); + + return $text; + } + function _doAutoLinks_url_callback($matches) { + $url = $this->encodeAttribute($matches[1]); + $link = "<a href=\"$url\">$url</a>"; + return $this->hashPart($link); + } + function _doAutoLinks_email_callback($matches) { + $address = $matches[1]; + $link = $this->encodeEmailAddress($address); + return $this->hashPart($link); + } + + + function encodeEmailAddress($addr) { + # + # Input: an email address, e.g. "foo@example.com" + # + # Output: the email address as a mailto link, with each character + # of the address encoded as either a decimal or hex entity, in + # the hopes of foiling most address harvesting spam bots. E.g.: + # + # <p><a href="mailto:foo + # @example.co + # m">foo@exampl + # e.com</a></p> + # + # Based by a filter by Matthew Wickline, posted to BBEdit-Talk. + # With some optimizations by Milian Wolff. + # + $addr = "mailto:" . $addr; + $chars = preg_split('/(?<!^)(?!$)/', $addr); + $seed = (int)abs(crc32($addr) / strlen($addr)); # Deterministic seed. + + foreach ($chars as $key => $char) { + $ord = ord($char); + # Ignore non-ascii chars. + if ($ord < 128) { + $r = ($seed * (1 + $key)) % 100; # Pseudo-random function. + # roughly 10% raw, 45% hex, 45% dec + # '@' *must* be encoded. I insist. + if ($r > 90 && $char != '@') /* do nothing */; + else if ($r < 45) $chars[$key] = '&#x'.dechex($ord).';'; + else $chars[$key] = '&#'.$ord.';'; + } + } + + $addr = implode('', $chars); + $text = implode('', array_slice($chars, 7)); # text without `mailto:` + $addr = "<a href=\"$addr\">$text</a>"; + + return $addr; + } + + + function parseSpan($str) { + # + # Take the string $str and parse it into tokens, hashing embeded HTML, + # escaped characters and handling code spans. + # + $output = ''; + + $span_re = '{ + ( + \\\\'.$this->escape_chars_re.' + | + (?<![`\\\\]) + `+ # code span marker + '.( $this->no_markup ? '' : ' + | + <!-- .*? --> # comment + | + <\?.*?\?> | <%.*?%> # processing instruction + | + <[/!$]?[-a-zA-Z0-9:_]+ # regular tags + (?> + \s + (?>[^"\'>]+|"[^"]*"|\'[^\']*\')* + )? + > + ').' + ) + }xs'; + + while (1) { + # + # Each loop iteration seach for either the next tag, the next + # openning code span marker, or the next escaped character. + # Each token is then passed to handleSpanToken. + # + $parts = preg_split($span_re, $str, 2, PREG_SPLIT_DELIM_CAPTURE); + + # Create token from text preceding tag. + if ($parts[0] != "") { + $output .= $parts[0]; + } + + # Check if we reach the end. + if (isset($parts[1])) { + $output .= $this->handleSpanToken($parts[1], $parts[2]); + $str = $parts[2]; + } + else { + break; + } + } + + return $output; + } + + + function handleSpanToken($token, &$str) { + # + # Handle $token provided by parseSpan by determining its nature and + # returning the corresponding value that should replace it. + # + switch ($token{0}) { + case "\\": + return $this->hashPart("&#". ord($token{1}). ";"); + case "`": + # Search for end marker in remaining text. + if (preg_match('/^(.*?[^`])'.preg_quote($token).'(?!`)(.*)$/sm', + $str, $matches)) + { + $str = $matches[2]; + $codespan = $this->makeCodeSpan($matches[1]); + return $this->hashPart($codespan); + } + return $token; // return as text since no ending marker found. + default: + return $this->hashPart($token); + } + } + + + function outdent($text) { + # + # Remove one level of line-leading tabs or spaces + # + return preg_replace('/^(\t|[ ]{1,'.$this->tab_width.'})/m', '', $text); + } + + + # String length function for detab. `_initDetab` will create a function to + # hanlde UTF-8 if the default function does not exist. + var $utf8_strlen = 'mb_strlen'; + + function detab($text) { + # + # Replace tabs with the appropriate amount of space. + # + # For each line we separate the line in blocks delemited by + # tab characters. Then we reconstruct every line by adding the + # appropriate number of space between each blocks. + + $text = preg_replace_callback('/^.*\t.*$/m', + array(&$this, '_detab_callback'), $text); + + return $text; + } + function _detab_callback($matches) { + $line = $matches[0]; + $strlen = $this->utf8_strlen; # strlen function for UTF-8. + + # Split in blocks. + $blocks = explode("\t", $line); + # Add each blocks to the line. + $line = $blocks[0]; + unset($blocks[0]); # Do not add first block twice. + foreach ($blocks as $block) { + # Calculate amount of space, insert spaces, insert block. + $amount = $this->tab_width - + $strlen($line, 'UTF-8') % $this->tab_width; + $line .= str_repeat(" ", $amount) . $block; + } + return $line; + } + function _initDetab() { + # + # Check for the availability of the function in the `utf8_strlen` property + # (initially `mb_strlen`). If the function is not available, create a + # function that will loosely count the number of UTF-8 characters with a + # regular expression. + # + if (function_exists($this->utf8_strlen)) return; + $this->utf8_strlen = create_function('$text', 'return preg_match_all( + "/[\\\\x00-\\\\xBF]|[\\\\xC0-\\\\xFF][\\\\x80-\\\\xBF]*/", + $text, $m);'); + } + + + function unhash($text) { + # + # Swap back in all the tags hashed by _HashHTMLBlocks. + # + return preg_replace_callback('/(.)\x1A[0-9]+\1/', + array(&$this, '_unhash_callback'), $text); + } + function _unhash_callback($matches) { + return $this->html_hashes[$matches[0]]; + } + +} + + +# +# Markdown Extra Parser Class +# + +class MarkdownExtra_Parser extends Markdown_Parser { + + # Prefix for footnote ids. + var $fn_id_prefix = ""; + + # Optional title attribute for footnote links and backlinks. + var $fn_link_title = MARKDOWN_FN_LINK_TITLE; + var $fn_backlink_title = MARKDOWN_FN_BACKLINK_TITLE; + + # Optional class attribute for footnote links and backlinks. + var $fn_link_class = MARKDOWN_FN_LINK_CLASS; + var $fn_backlink_class = MARKDOWN_FN_BACKLINK_CLASS; + + # Predefined abbreviations. + var $predef_abbr = array(); + + + function MarkdownExtra_Parser() { + # + # Constructor function. Initialize the parser object. + # + # Add extra escapable characters before parent constructor + # initialize the table. + $this->escape_chars .= ':|'; + + # Insert extra document, block, and span transformations. + # Parent constructor will do the sorting. + $this->document_gamut += array( + "doFencedCodeBlocks" => 5, + "stripFootnotes" => 15, + "stripAbbreviations" => 25, + "appendFootnotes" => 50, + ); + $this->block_gamut += array( + "doFencedCodeBlocks" => 5, + "doTables" => 15, + "doDefLists" => 45, + ); + $this->span_gamut += array( + "doFootnotes" => 5, + "doAbbreviations" => 70, + ); + + parent::Markdown_Parser(); + } + + + # Extra variables used during extra transformations. + var $footnotes = array(); + var $footnotes_ordered = array(); + var $abbr_desciptions = array(); + var $abbr_word_re = ''; + + # Give the current footnote number. + var $footnote_counter = 1; + + + function setup() { + # + # Setting up Extra-specific variables. + # + parent::setup(); + + $this->footnotes = array(); + $this->footnotes_ordered = array(); + $this->abbr_desciptions = array(); + $this->abbr_word_re = ''; + $this->footnote_counter = 1; + + foreach ($this->predef_abbr as $abbr_word => $abbr_desc) { + if ($this->abbr_word_re) + $this->abbr_word_re .= '|'; + $this->abbr_word_re .= preg_quote($abbr_word); + $this->abbr_desciptions[$abbr_word] = trim($abbr_desc); + } + } + + function teardown() { + # + # Clearing Extra-specific variables. + # + $this->footnotes = array(); + $this->footnotes_ordered = array(); + $this->abbr_desciptions = array(); + $this->abbr_word_re = ''; + + parent::teardown(); + } + + + ### HTML Block Parser ### + + # Tags that are always treated as block tags: + var $block_tags_re = 'p|div|h[1-6]|blockquote|pre|table|dl|ol|ul|address|form|fieldset|iframe|hr|legend'; + + # Tags treated as block tags only if the opening tag is alone on it's line: + var $context_block_tags_re = 'script|noscript|math|ins|del'; + + # Tags where markdown="1" default to span mode: + var $contain_span_tags_re = 'p|h[1-6]|li|dd|dt|td|th|legend|address'; + + # Tags which must not have their contents modified, no matter where + # they appear: + var $clean_tags_re = 'script|math'; + + # Tags that do not need to be closed. + var $auto_close_tags_re = 'hr|img'; + + + function hashHTMLBlocks($text) { + # + # Hashify HTML Blocks and "clean tags". + # + # We only want to do this for block-level HTML tags, such as headers, + # lists, and tables. That's because we still want to wrap <p>s around + # "paragraphs" that are wrapped in non-block-level tags, such as anchors, + # phrase emphasis, and spans. The list of tags we're looking for is + # hard-coded. + # + # This works by calling _HashHTMLBlocks_InMarkdown, which then calls + # _HashHTMLBlocks_InHTML when it encounter block tags. When the markdown="1" + # attribute is found whitin a tag, _HashHTMLBlocks_InHTML calls back + # _HashHTMLBlocks_InMarkdown to handle the Markdown syntax within the tag. + # These two functions are calling each other. It's recursive! + # + # + # Call the HTML-in-Markdown hasher. + # + list($text, ) = $this->_hashHTMLBlocks_inMarkdown($text); + + return $text; + } + function _hashHTMLBlocks_inMarkdown($text, $indent = 0, + $enclosing_tag_re = '', $span = false) + { + # + # Parse markdown text, calling _HashHTMLBlocks_InHTML for block tags. + # + # * $indent is the number of space to be ignored when checking for code + # blocks. This is important because if we don't take the indent into + # account, something like this (which looks right) won't work as expected: + # + # <div> + # <div markdown="1"> + # Hello World. <-- Is this a Markdown code block or text? + # </div> <-- Is this a Markdown code block or a real tag? + # <div> + # + # If you don't like this, just don't indent the tag on which + # you apply the markdown="1" attribute. + # + # * If $enclosing_tag_re is not empty, stops at the first unmatched closing + # tag with that name. Nested tags supported. + # + # * If $span is true, text inside must treated as span. So any double + # newline will be replaced by a single newline so that it does not create + # paragraphs. + # + # Returns an array of that form: ( processed text , remaining text ) + # + if ($text === '') return array('', ''); + + # Regex to check for the presense of newlines around a block tag. + $newline_before_re = '/(?:^\n?|\n\n)*$/'; + $newline_after_re = + '{ + ^ # Start of text following the tag. + (?>[ ]*<!--.*?-->)? # Optional comment. + [ ]*\n # Must be followed by newline. + }xs'; + + # Regex to match any tag. + $block_tag_re = + '{ + ( # $2: Capture hole tag. + </? # Any opening or closing tag. + (?> # Tag name. + '.$this->block_tags_re.' | + '.$this->context_block_tags_re.' | + '.$this->clean_tags_re.' | + (?!\s)'.$enclosing_tag_re.' + ) + (?: + (?=[\s"\'/a-zA-Z0-9]) # Allowed characters after tag name. + (?> + ".*?" | # Double quotes (can contain `>`) + \'.*?\' | # Single quotes (can contain `>`) + .+? # Anything but quotes and `>`. + )*? + )? + > # End of tag. + | + <!-- .*? --> # HTML Comment + | + <\?.*?\?> | <%.*?%> # Processing instruction + | + <!\[CDATA\[.*?\]\]> # CData Block + | + # Code span marker + `+ + '. ( !$span ? ' # If not in span. + | + # Indented code block + (?: ^[ ]*\n | ^ | \n[ ]*\n ) + [ ]{'.($indent+4).'}[^\n]* \n + (?> + (?: [ ]{'.($indent+4).'}[^\n]* | [ ]* ) \n + )* + | + # Fenced code block marker + (?> ^ | \n ) + [ ]{'.($indent).'}~~~+[ ]*\n + ' : '' ). ' # End (if not is span). + ) + }xs'; + + + $depth = 0; # Current depth inside the tag tree. + $parsed = ""; # Parsed text that will be returned. + + # + # Loop through every tag until we find the closing tag of the parent + # or loop until reaching the end of text if no parent tag specified. + # + do { + # + # Split the text using the first $tag_match pattern found. + # Text before pattern will be first in the array, text after + # pattern will be at the end, and between will be any catches made + # by the pattern. + # + $parts = preg_split($block_tag_re, $text, 2, + PREG_SPLIT_DELIM_CAPTURE); + + # If in Markdown span mode, add a empty-string span-level hash + # after each newline to prevent triggering any block element. + if ($span) { + $void = $this->hashPart("", ':'); + $newline = "$void\n"; + $parts[0] = $void . str_replace("\n", $newline, $parts[0]) . $void; + } + + $parsed .= $parts[0]; # Text before current tag. + + # If end of $text has been reached. Stop loop. + if (count($parts) < 3) { + $text = ""; + break; + } + + $tag = $parts[1]; # Tag to handle. + $text = $parts[2]; # Remaining text after current tag. + $tag_re = preg_quote($tag); # For use in a regular expression. + + # + # Check for: Code span marker + # + if ($tag{0} == "`") { + # Find corresponding end marker. + $tag_re = preg_quote($tag); + if (preg_match('{^(?>.+?|\n(?!\n))*?(?<!`)'.$tag_re.'(?!`)}', + $text, $matches)) + { + # End marker found: pass text unchanged until marker. + $parsed .= $tag . $matches[0]; + $text = substr($text, strlen($matches[0])); + } + else { + # Unmatched marker: just skip it. + $parsed .= $tag; + } + } + # + # Check for: Indented code block. + # + else if ($tag{0} == "\n" || $tag{0} == " ") { + # Indented code block: pass it unchanged, will be handled + # later. + $parsed .= $tag; + } + # + # Check for: Fenced code block marker. + # + else if ($tag{0} == "~") { + # Fenced code block marker: find matching end marker. + $tag_re = preg_quote(trim($tag)); + if (preg_match('{^(?>.*\n)+?'.$tag_re.' *\n}', $text, + $matches)) + { + # End marker found: pass text unchanged until marker. + $parsed .= $tag . $matches[0]; + $text = substr($text, strlen($matches[0])); + } + else { + # No end marker: just skip it. + $parsed .= $tag; + } + } + # + # Check for: Opening Block level tag or + # Opening Context Block tag (like ins and del) + # used as a block tag (tag is alone on it's line). + # + else if (preg_match('{^<(?:'.$this->block_tags_re.')\b}', $tag) || + ( preg_match('{^<(?:'.$this->context_block_tags_re.')\b}', $tag) && + preg_match($newline_before_re, $parsed) && + preg_match($newline_after_re, $text) ) + ) + { + # Need to parse tag and following text using the HTML parser. + list($block_text, $text) = + $this->_hashHTMLBlocks_inHTML($tag . $text, "hashBlock", true); + + # Make sure it stays outside of any paragraph by adding newlines. + $parsed .= "\n\n$block_text\n\n"; + } + # + # Check for: Clean tag (like script, math) + # HTML Comments, processing instructions. + # + else if (preg_match('{^<(?:'.$this->clean_tags_re.')\b}', $tag) || + $tag{1} == '!' || $tag{1} == '?') + { + # Need to parse tag and following text using the HTML parser. + # (don't check for markdown attribute) + list($block_text, $text) = + $this->_hashHTMLBlocks_inHTML($tag . $text, "hashClean", false); + + $parsed .= $block_text; + } + # + # Check for: Tag with same name as enclosing tag. + # + else if ($enclosing_tag_re !== '' && + # Same name as enclosing tag. + preg_match('{^</?(?:'.$enclosing_tag_re.')\b}', $tag)) + { + # + # Increase/decrease nested tag count. + # + if ($tag{1} == '/') $depth--; + else if ($tag{strlen($tag)-2} != '/') $depth++; + + if ($depth < 0) { + # + # Going out of parent element. Clean up and break so we + # return to the calling function. + # + $text = $tag . $text; + break; + } + + $parsed .= $tag; + } + else { + $parsed .= $tag; + } + } while ($depth >= 0); + + return array($parsed, $text); + } + function _hashHTMLBlocks_inHTML($text, $hash_method, $md_attr) { + # + # Parse HTML, calling _HashHTMLBlocks_InMarkdown for block tags. + # + # * Calls $hash_method to convert any blocks. + # * Stops when the first opening tag closes. + # * $md_attr indicate if the use of the `markdown="1"` attribute is allowed. + # (it is not inside clean tags) + # + # Returns an array of that form: ( processed text , remaining text ) + # + if ($text === '') return array('', ''); + + # Regex to match `markdown` attribute inside of a tag. + $markdown_attr_re = ' + { + \s* # Eat whitespace before the `markdown` attribute + markdown + \s*=\s* + (?> + (["\']) # $1: quote delimiter + (.*?) # $2: attribute value + \1 # matching delimiter + | + ([^\s>]*) # $3: unquoted attribute value + ) + () # $4: make $3 always defined (avoid warnings) + }xs'; + + # Regex to match any tag. + $tag_re = '{ + ( # $2: Capture hole tag. + </? # Any opening or closing tag. + [\w:$]+ # Tag name. + (?: + (?=[\s"\'/a-zA-Z0-9]) # Allowed characters after tag name. + (?> + ".*?" | # Double quotes (can contain `>`) + \'.*?\' | # Single quotes (can contain `>`) + .+? # Anything but quotes and `>`. + )*? + )? + > # End of tag. + | + <!-- .*? --> # HTML Comment + | + <\?.*?\?> | <%.*?%> # Processing instruction + | + <!\[CDATA\[.*?\]\]> # CData Block + ) + }xs'; + + $original_text = $text; # Save original text in case of faliure. + + $depth = 0; # Current depth inside the tag tree. + $block_text = ""; # Temporary text holder for current text. + $parsed = ""; # Parsed text that will be returned. + + # + # Get the name of the starting tag. + # (This pattern makes $base_tag_name_re safe without quoting.) + # + if (preg_match('/^<([\w:$]*)\b/', $text, $matches)) + $base_tag_name_re = $matches[1]; + + # + # Loop through every tag until we find the corresponding closing tag. + # + do { + # + # Split the text using the first $tag_match pattern found. + # Text before pattern will be first in the array, text after + # pattern will be at the end, and between will be any catches made + # by the pattern. + # + $parts = preg_split($tag_re, $text, 2, PREG_SPLIT_DELIM_CAPTURE); + + if (count($parts) < 3) { + # + # End of $text reached with unbalenced tag(s). + # In that case, we return original text unchanged and pass the + # first character as filtered to prevent an infinite loop in the + # parent function. + # + return array($original_text{0}, substr($original_text, 1)); + } + + $block_text .= $parts[0]; # Text before current tag. + $tag = $parts[1]; # Tag to handle. + $text = $parts[2]; # Remaining text after current tag. + + # + # Check for: Auto-close tag (like <hr/>) + # Comments and Processing Instructions. + # + if (preg_match('{^</?(?:'.$this->auto_close_tags_re.')\b}', $tag) || + $tag{1} == '!' || $tag{1} == '?') + { + # Just add the tag to the block as if it was text. + $block_text .= $tag; + } + else { + # + # Increase/decrease nested tag count. Only do so if + # the tag's name match base tag's. + # + if (preg_match('{^</?'.$base_tag_name_re.'\b}', $tag)) { + if ($tag{1} == '/') $depth--; + else if ($tag{strlen($tag)-2} != '/') $depth++; + } + + # + # Check for `markdown="1"` attribute and handle it. + # + if ($md_attr && + preg_match($markdown_attr_re, $tag, $attr_m) && + preg_match('/^1|block|span$/', $attr_m[2] . $attr_m[3])) + { + # Remove `markdown` attribute from opening tag. + $tag = preg_replace($markdown_attr_re, '', $tag); + + # Check if text inside this tag must be parsed in span mode. + $this->mode = $attr_m[2] . $attr_m[3]; + $span_mode = $this->mode == 'span' || $this->mode != 'block' && + preg_match('{^<(?:'.$this->contain_span_tags_re.')\b}', $tag); + + # Calculate indent before tag. + if (preg_match('/(?:^|\n)( *?)(?! ).*?$/', $block_text, $matches)) { + $strlen = $this->utf8_strlen; + $indent = $strlen($matches[1], 'UTF-8'); + } else { + $indent = 0; + } + + # End preceding block with this tag. + $block_text .= $tag; + $parsed .= $this->$hash_method($block_text); + + # Get enclosing tag name for the ParseMarkdown function. + # (This pattern makes $tag_name_re safe without quoting.) + preg_match('/^<([\w:$]*)\b/', $tag, $matches); + $tag_name_re = $matches[1]; + + # Parse the content using the HTML-in-Markdown parser. + list ($block_text, $text) + = $this->_hashHTMLBlocks_inMarkdown($text, $indent, + $tag_name_re, $span_mode); + + # Outdent markdown text. + if ($indent > 0) { + $block_text = preg_replace("/^[ ]{1,$indent}/m", "", + $block_text); + } + + # Append tag content to parsed text. + if (!$span_mode) $parsed .= "\n\n$block_text\n\n"; + else $parsed .= "$block_text"; + + # Start over a new block. + $block_text = ""; + } + else $block_text .= $tag; + } + + } while ($depth > 0); + + # + # Hash last block text that wasn't processed inside the loop. + # + $parsed .= $this->$hash_method($block_text); + + return array($parsed, $text); + } + + + function hashClean($text) { + # + # Called whenever a tag must be hashed when a function insert a "clean" tag + # in $text, it pass through this function and is automaticaly escaped, + # blocking invalid nested overlap. + # + return $this->hashPart($text, 'C'); + } + + + function doHeaders($text) { + # + # Redefined to add id attribute support. + # + # Setext-style headers: + # Header 1 {#header1} + # ======== + # + # Header 2 {#header2} + # -------- + # + $text = preg_replace_callback( + '{ + (^.+?) # $1: Header text + (?:[ ]+\{\#([-_:a-zA-Z0-9]+)\})? # $2: Id attribute + [ ]*\n(=+|-+)[ ]*\n+ # $3: Header footer + }mx', + array(&$this, '_doHeaders_callback_setext'), $text); + + # atx-style headers: + # # Header 1 {#header1} + # ## Header 2 {#header2} + # ## Header 2 with closing hashes ## {#header3} + # ... + # ###### Header 6 {#header2} + # + # @note Added for Elgg: You can use = in place of hashes for atx-style. + $text = preg_replace_callback('{ + ^([\#=]{1,6}) # $1 = string of #\'s + [ ]* + (.+?) # $2 = Header text + [ ]* + [\#=]* # optional closing #\'s (not counted) + (?:[ ]+\{\#([-_:a-zA-Z0-9]+)\})? # id attribute + [ ]* + \n+ + }xm', + array(&$this, '_doHeaders_callback_atx'), $text); + + return $text; + } + function _doHeaders_attr($attr) { + if (empty($attr)) return ""; + return " id=\"$attr\""; + } + function _doHeaders_callback_setext($matches) { + if ($matches[3] == '-' && preg_match('{^- }', $matches[1])) + return $matches[0]; + $level = $matches[3]{0} == '=' ? 1 : 2; + $attr = $this->_doHeaders_attr($id =& $matches[2]); + $block = "<h$level$attr>".$this->runSpanGamut($matches[1])."</h$level>"; + return "\n" . $this->hashBlock($block) . "\n\n"; + } + function _doHeaders_callback_atx($matches) { + $level = strlen($matches[1]); + $attr = $this->_doHeaders_attr($id =& $matches[3]); + $block = "<h$level$attr>".$this->runSpanGamut($matches[2])."</h$level>"; + return "\n" . $this->hashBlock($block) . "\n\n"; + } + + + function doTables($text) { + # + # Form HTML tables. + # + $less_than_tab = $this->tab_width - 1; + # + # Find tables with leading pipe. + # + # | Header 1 | Header 2 + # | -------- | -------- + # | Cell 1 | Cell 2 + # | Cell 3 | Cell 4 + # + $text = preg_replace_callback(' + { + ^ # Start of a line + [ ]{0,'.$less_than_tab.'} # Allowed whitespace. + [|] # Optional leading pipe (present) + (.+) \n # $1: Header row (at least one pipe) + + [ ]{0,'.$less_than_tab.'} # Allowed whitespace. + [|] ([ ]*[-:]+[-| :]*) \n # $2: Header underline + + ( # $3: Cells + (?> + [ ]* # Allowed whitespace. + [|] .* \n # Row content. + )* + ) + (?=\n|\Z) # Stop at final double newline. + }xm', + array(&$this, '_doTable_leadingPipe_callback'), $text); + + # + # Find tables without leading pipe. + # + # Header 1 | Header 2 + # -------- | -------- + # Cell 1 | Cell 2 + # Cell 3 | Cell 4 + # + $text = preg_replace_callback(' + { + ^ # Start of a line + [ ]{0,'.$less_than_tab.'} # Allowed whitespace. + (\S.*[|].*) \n # $1: Header row (at least one pipe) + + [ ]{0,'.$less_than_tab.'} # Allowed whitespace. + ([-:]+[ ]*[|][-| :]*) \n # $2: Header underline + + ( # $3: Cells + (?> + .* [|] .* \n # Row content + )* + ) + (?=\n|\Z) # Stop at final double newline. + }xm', + array(&$this, '_DoTable_callback'), $text); + + return $text; + } + function _doTable_leadingPipe_callback($matches) { + $head = $matches[1]; + $underline = $matches[2]; + $content = $matches[3]; + + # Remove leading pipe for each row. + $content = preg_replace('/^ *[|]/m', '', $content); + + return $this->_doTable_callback(array($matches[0], $head, $underline, $content)); + } + function _doTable_callback($matches) { + $head = $matches[1]; + $underline = $matches[2]; + $content = $matches[3]; + + # Remove any tailing pipes for each line. + $head = preg_replace('/[|] *$/m', '', $head); + $underline = preg_replace('/[|] *$/m', '', $underline); + $content = preg_replace('/[|] *$/m', '', $content); + + # Reading alignement from header underline. + $separators = preg_split('/ *[|] */', $underline); + foreach ($separators as $n => $s) { + if (preg_match('/^ *-+: *$/', $s)) $attr[$n] = ' align="right"'; + else if (preg_match('/^ *:-+: *$/', $s))$attr[$n] = ' align="center"'; + else if (preg_match('/^ *:-+ *$/', $s)) $attr[$n] = ' align="left"'; + else $attr[$n] = ''; + } + + # Parsing span elements, including code spans, character escapes, + # and inline HTML tags, so that pipes inside those gets ignored. + $head = $this->parseSpan($head); + $headers = preg_split('/ *[|] */', $head); + $col_count = count($headers); + + # Write column headers. + $text = "<table>\n"; + $text .= "<thead>\n"; + $text .= "<tr>\n"; + foreach ($headers as $n => $header) + $text .= " <th$attr[$n]>".$this->runSpanGamut(trim($header))."</th>\n"; + $text .= "</tr>\n"; + $text .= "</thead>\n"; + + # Split content by row. + $rows = explode("\n", trim($content, "\n")); + + $text .= "<tbody>\n"; + foreach ($rows as $row) { + # Parsing span elements, including code spans, character escapes, + # and inline HTML tags, so that pipes inside those gets ignored. + $row = $this->parseSpan($row); + + # Split row by cell. + $row_cells = preg_split('/ *[|] */', $row, $col_count); + $row_cells = array_pad($row_cells, $col_count, ''); + + $text .= "<tr>\n"; + foreach ($row_cells as $n => $cell) + $text .= " <td$attr[$n]>".$this->runSpanGamut(trim($cell))."</td>\n"; + $text .= "</tr>\n"; + } + $text .= "</tbody>\n"; + $text .= "</table>"; + + return $this->hashBlock($text) . "\n"; + } + + + function doDefLists($text) { + # + # Form HTML definition lists. + # + $less_than_tab = $this->tab_width - 1; + + # Re-usable pattern to match any entire dl list: + $whole_list_re = '(?> + ( # $1 = whole list + ( # $2 + [ ]{0,'.$less_than_tab.'} + ((?>.*\S.*\n)+) # $3 = defined term + \n? + [ ]{0,'.$less_than_tab.'}:[ ]+ # colon starting definition + ) + (?s:.+?) + ( # $4 + \z + | + \n{2,} + (?=\S) + (?! # Negative lookahead for another term + [ ]{0,'.$less_than_tab.'} + (?: \S.*\n )+? # defined term + \n? + [ ]{0,'.$less_than_tab.'}:[ ]+ # colon starting definition + ) + (?! # Negative lookahead for another definition + [ ]{0,'.$less_than_tab.'}:[ ]+ # colon starting definition + ) + ) + ) + )'; // mx + + $text = preg_replace_callback('{ + (?>\A\n?|(?<=\n\n)) + '.$whole_list_re.' + }mx', + array(&$this, '_doDefLists_callback'), $text); + + return $text; + } + function _doDefLists_callback($matches) { + # Re-usable patterns to match list item bullets and number markers: + $list = $matches[1]; + + # Turn double returns into triple returns, so that we can make a + # paragraph for the last item in a list, if necessary: + $result = trim($this->processDefListItems($list)); + $result = "<dl>\n" . $result . "\n</dl>"; + return $this->hashBlock($result) . "\n\n"; + } + + + function processDefListItems($list_str) { + # + # Process the contents of a single definition list, splitting it + # into individual term and definition list items. + # + $less_than_tab = $this->tab_width - 1; + + # trim trailing blank lines: + $list_str = preg_replace("/\n{2,}\\z/", "\n", $list_str); + + # Process definition terms. + $list_str = preg_replace_callback('{ + (?>\A\n?|\n\n+) # leading line + ( # definition terms = $1 + [ ]{0,'.$less_than_tab.'} # leading whitespace + (?![:][ ]|[ ]) # negative lookahead for a definition + # mark (colon) or more whitespace. + (?> \S.* \n)+? # actual term (not whitespace). + ) + (?=\n?[ ]{0,3}:[ ]) # lookahead for following line feed + # with a definition mark. + }xm', + array(&$this, '_processDefListItems_callback_dt'), $list_str); + + # Process actual definitions. + $list_str = preg_replace_callback('{ + \n(\n+)? # leading line = $1 + ( # marker space = $2 + [ ]{0,'.$less_than_tab.'} # whitespace before colon + [:][ ]+ # definition mark (colon) + ) + ((?s:.+?)) # definition text = $3 + (?= \n+ # stop at next definition mark, + (?: # next term or end of text + [ ]{0,'.$less_than_tab.'} [:][ ] | + <dt> | \z + ) + ) + }xm', + array(&$this, '_processDefListItems_callback_dd'), $list_str); + + return $list_str; + } + function _processDefListItems_callback_dt($matches) { + $terms = explode("\n", trim($matches[1])); + $text = ''; + foreach ($terms as $term) { + $term = $this->runSpanGamut(trim($term)); + $text .= "\n<dt>" . $term . "</dt>"; + } + return $text . "\n"; + } + function _processDefListItems_callback_dd($matches) { + $leading_line = $matches[1]; + $marker_space = $matches[2]; + $def = $matches[3]; + + if ($leading_line || preg_match('/\n{2,}/', $def)) { + # Replace marker with the appropriate whitespace indentation + $def = str_repeat(' ', strlen($marker_space)) . $def; + $def = $this->runBlockGamut($this->outdent($def . "\n\n")); + $def = "\n". $def ."\n"; + } + else { + $def = rtrim($def); + $def = $this->runSpanGamut($this->outdent($def)); + } + + return "\n<dd>" . $def . "</dd>\n"; + } + + + function doFencedCodeBlocks($text) { + # + # Adding the fenced code block syntax to regular Markdown: + # + # ~~~ + # Code block + # ~~~ + # + $less_than_tab = $this->tab_width; + + $text = preg_replace_callback('{ + (?:\n|\A) + # 1: Opening marker + ( + ~{3,} # Marker: three tilde or more. + ) + [ ]* \n # Whitespace and newline following marker. + + # 2: Content + ( + (?> + (?!\1 [ ]* \n) # Not a closing marker. + .*\n+ + )+ + ) + + # Closing marker. + \1 [ ]* \n + }xm', + array(&$this, '_doFencedCodeBlocks_callback'), $text); + + return $text; + } + function _doFencedCodeBlocks_callback($matches) { + $codeblock = $matches[2]; + $codeblock = htmlspecialchars($codeblock, ENT_NOQUOTES); + $codeblock = preg_replace_callback('/^\n+/', + array(&$this, '_doFencedCodeBlocks_newlines'), $codeblock); + $codeblock = "<pre><code>$codeblock</code></pre>"; + return "\n\n".$this->hashBlock($codeblock)."\n\n"; + } + function _doFencedCodeBlocks_newlines($matches) { + return str_repeat("<br$this->empty_element_suffix", + strlen($matches[0])); + } + + + # + # Redefining emphasis markers so that emphasis by underscore does not + # work in the middle of a word. + # + var $em_relist = array( + '' => '(?:(?<!\*)\*(?!\*)|(?<![a-zA-Z0-9_])_(?!_))(?=\S|$)(?![.,:;]\s)', + '*' => '(?<=\S|^)(?<!\*)\*(?!\*)', + '_' => '(?<=\S|^)(?<!_)_(?![a-zA-Z0-9_])', + ); + var $strong_relist = array( + '' => '(?:(?<!\*)\*\*(?!\*)|(?<![a-zA-Z0-9_])__(?!_))(?=\S|$)(?![.,:;]\s)', + '**' => '(?<=\S|^)(?<!\*)\*\*(?!\*)', + '__' => '(?<=\S|^)(?<!_)__(?![a-zA-Z0-9_])', + ); + var $em_strong_relist = array( + '' => '(?:(?<!\*)\*\*\*(?!\*)|(?<![a-zA-Z0-9_])___(?!_))(?=\S|$)(?![.,:;]\s)', + '***' => '(?<=\S|^)(?<!\*)\*\*\*(?!\*)', + '___' => '(?<=\S|^)(?<!_)___(?![a-zA-Z0-9_])', + ); + + + function formParagraphs($text) { + # + # Params: + # $text - string to process with html <p> tags + # + # Strip leading and trailing lines: + $text = preg_replace('/\A\n+|\n+\z/', '', $text); + + $grafs = preg_split('/\n{2,}/', $text, -1, PREG_SPLIT_NO_EMPTY); + + # + # Wrap <p> tags and unhashify HTML blocks + # + foreach ($grafs as $key => $value) { + $value = trim($this->runSpanGamut($value)); + + # Check if this should be enclosed in a paragraph. + # Clean tag hashes & block tag hashes are left alone. + $is_p = !preg_match('/^B\x1A[0-9]+B|^C\x1A[0-9]+C$/', $value); + + if ($is_p) { + $value = "<p>$value</p>"; + } + $grafs[$key] = $value; + } + + # Join grafs in one text, then unhash HTML tags. + $text = implode("\n\n", $grafs); + + # Finish by removing any tag hashes still present in $text. + $text = $this->unhash($text); + + return $text; + } + + + ### Footnotes + + function stripFootnotes($text) { + # + # Strips link definitions from text, stores the URLs and titles in + # hash references. + # + $less_than_tab = $this->tab_width - 1; + + # Link defs are in the form: [^id]: url "optional title" + $text = preg_replace_callback('{ + ^[ ]{0,'.$less_than_tab.'}\[\^(.+?)\][ ]?: # note_id = $1 + [ ]* + \n? # maybe *one* newline + ( # text = $2 (no blank lines allowed) + (?: + .+ # actual text + | + \n # newlines but + (?!\[\^.+?\]:\s)# negative lookahead for footnote marker. + (?!\n+[ ]{0,3}\S)# ensure line is not blank and followed + # by non-indented content + )* + ) + }xm', + array(&$this, '_stripFootnotes_callback'), + $text); + return $text; + } + function _stripFootnotes_callback($matches) { + $note_id = $this->fn_id_prefix . $matches[1]; + $this->footnotes[$note_id] = $this->outdent($matches[2]); + return ''; # String that will replace the block + } + + + function doFootnotes($text) { + # + # Replace footnote references in $text [^id] with a special text-token + # which will be replaced by the actual footnote marker in appendFootnotes. + # + if (!$this->in_anchor) { + $text = preg_replace('{\[\^(.+?)\]}', "F\x1Afn:\\1\x1A:", $text); + } + return $text; + } + + + function appendFootnotes($text) { + # + # Append footnote list to text. + # + $text = preg_replace_callback('{F\x1Afn:(.*?)\x1A:}', + array(&$this, '_appendFootnotes_callback'), $text); + + if (!empty($this->footnotes_ordered)) { + $text .= "\n\n"; + $text .= "<div class=\"footnotes\">\n"; + $text .= "<hr". $this->empty_element_suffix ."\n"; + $text .= "<ol>\n\n"; + + $attr = " rev=\"footnote\""; + if ($this->fn_backlink_class != "") { + $class = $this->fn_backlink_class; + $class = $this->encodeAttribute($class); + $attr .= " class=\"$class\""; + } + if ($this->fn_backlink_title != "") { + $title = $this->fn_backlink_title; + $title = $this->encodeAttribute($title); + $attr .= " title=\"$title\""; + } + $num = 0; + + while (!empty($this->footnotes_ordered)) { + $footnote = reset($this->footnotes_ordered); + $note_id = key($this->footnotes_ordered); + unset($this->footnotes_ordered[$note_id]); + + $footnote .= "\n"; # Need to append newline before parsing. + $footnote = $this->runBlockGamut("$footnote\n"); + $footnote = preg_replace_callback('{F\x1Afn:(.*?)\x1A:}', + array(&$this, '_appendFootnotes_callback'), $footnote); + + $attr = str_replace("%%", ++$num, $attr); + $note_id = $this->encodeAttribute($note_id); + + # Add backlink to last paragraph; create new paragraph if needed. + $backlink = "<a href=\"#fnref:$note_id\"$attr>↩</a>"; + if (preg_match('{</p>$}', $footnote)) { + $footnote = substr($footnote, 0, -4) . " $backlink</p>"; + } else { + $footnote .= "\n\n<p>$backlink</p>"; + } + + $text .= "<li id=\"fn:$note_id\">\n"; + $text .= $footnote . "\n"; + $text .= "</li>\n\n"; + } + + $text .= "</ol>\n"; + $text .= "</div>"; + } + return $text; + } + function _appendFootnotes_callback($matches) { + $node_id = $this->fn_id_prefix . $matches[1]; + + # Create footnote marker only if it has a corresponding footnote *and* + # the footnote hasn't been used by another marker. + if (isset($this->footnotes[$node_id])) { + # Transfert footnote content to the ordered list. + $this->footnotes_ordered[$node_id] = $this->footnotes[$node_id]; + unset($this->footnotes[$node_id]); + + $num = $this->footnote_counter++; + $attr = " rel=\"footnote\""; + if ($this->fn_link_class != "") { + $class = $this->fn_link_class; + $class = $this->encodeAttribute($class); + $attr .= " class=\"$class\""; + } + if ($this->fn_link_title != "") { + $title = $this->fn_link_title; + $title = $this->encodeAttribute($title); + $attr .= " title=\"$title\""; + } + + $attr = str_replace("%%", $num, $attr); + $node_id = $this->encodeAttribute($node_id); + + return + "<sup id=\"fnref:$node_id\">". + "<a href=\"#fn:$node_id\"$attr>$num</a>". + "</sup>"; + } + + return "[^".$matches[1]."]"; + } + + + ### Abbreviations ### + + function stripAbbreviations($text) { + # + # Strips abbreviations from text, stores titles in hash references. + # + $less_than_tab = $this->tab_width - 1; + + # Link defs are in the form: [id]*: url "optional title" + $text = preg_replace_callback('{ + ^[ ]{0,'.$less_than_tab.'}\*\[(.+?)\][ ]?: # abbr_id = $1 + (.*) # text = $2 (no blank lines allowed) + }xm', + array(&$this, '_stripAbbreviations_callback'), + $text); + return $text; + } + function _stripAbbreviations_callback($matches) { + $abbr_word = $matches[1]; + $abbr_desc = $matches[2]; + if ($this->abbr_word_re) + $this->abbr_word_re .= '|'; + $this->abbr_word_re .= preg_quote($abbr_word); + $this->abbr_desciptions[$abbr_word] = trim($abbr_desc); + return ''; # String that will replace the block + } + + + function doAbbreviations($text) { + # + # Find defined abbreviations in text and wrap them in <abbr> elements. + # + if ($this->abbr_word_re) { + // cannot use the /x modifier because abbr_word_re may + // contain significant spaces: + $text = preg_replace_callback('{'. + '(?<![\w\x1A])'. + '(?:'.$this->abbr_word_re.')'. + '(?![\w\x1A])'. + '}', + array(&$this, '_doAbbreviations_callback'), $text); + } + return $text; + } + function _doAbbreviations_callback($matches) { + $abbr = $matches[0]; + if (isset($this->abbr_desciptions[$abbr])) { + $desc = $this->abbr_desciptions[$abbr]; + if (empty($desc)) { + return $this->hashPart("<abbr>$abbr</abbr>"); + } else { + $desc = $this->encodeAttribute($desc); + return $this->hashPart("<abbr title=\"$desc\">$abbr</abbr>"); + } + } else { + return $matches[0]; + } + } + +} + + +/* + +PHP Markdown Extra +================== + +Description +----------- + +This is a PHP port of the original Markdown formatter written in Perl +by John Gruber. This special "Extra" version of PHP Markdown features +further enhancements to the syntax for making additional constructs +such as tables and definition list. + +Markdown is a text-to-HTML filter; it translates an easy-to-read / +easy-to-write structured text format into HTML. Markdown's text format +is most similar to that of plain text email, and supports features such +as headers, *emphasis*, code blocks, blockquotes, and links. + +Markdown's syntax is designed not as a generic markup language, but +specifically to serve as a front-end to (X)HTML. You can use span-level +HTML tags anywhere in a Markdown document, and you can use block level +HTML tags (like <div> and <table> as well). + +For more information about Markdown's syntax, see: + +<http://daringfireball.net/projects/markdown/> + + +Bugs +---- + +To file bug reports please send email to: + +<michel.fortin@michelf.com> + +Please include with your report: (1) the example input; (2) the output you +expected; (3) the output Markdown actually produced. + + +Version History +--------------- + +See the readme file for detailed release notes for this version. + + +Copyright and License +--------------------- + +PHP Markdown & Extra +Copyright (c) 2004-2009 Michel Fortin +<http://michelf.com/> +All rights reserved. + +Based on Markdown +Copyright (c) 2003-2006 John Gruber +<http://daringfireball.net/> +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 "Markdown" 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. + +*/ +?>
\ No newline at end of file |