libmarkdown-php-1.0.2/0000755000000000000000000000000012246135735013316 5ustar rootrootlibmarkdown-php-1.0.2/License.text0000644000000000000000000000313712246135735015612 0ustar rootrootPHP Markdown Copyright (c) 2004-2013 Michel Fortin All rights reserved. Based on Markdown Copyright (c) 2003-2006 John Gruber 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. libmarkdown-php-1.0.2/PHP Markdown Readme.text0000644000000000000000000006516412246135735017610 0ustar rootrootPHP Markdown ============ Version 1.0.2 - 29 Nov 2013 by Michel Fortin based on work by John Gruber Introduction ------------ 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, as a modifier for the Smarty templating engine, or as a replacement for Textile formatting in any software that supports Textile. Full documentation of Markdown's syntax is available on John's Markdown page: Installation and Requirement ---------------------------- PHP Markdown requires PHP version 4.0.5 or later. Before PHP 5.3.7, pcre.backtrack_limit defaults to 100 000, which is too small in many situations. You might need to set it to higher values. Later PHP releases defaults to 1 000 000, which is usually fine. ### 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 "markdown.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 as 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 formatted 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. ### 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 *Textile 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.ca/projects/php-smartypants/ ### 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 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/markdown.php` 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/ ### 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. Configuration ------------- By default, PHP Markdown produces XHTML output for tags with empty elements. E.g.:
Markdown can be configured to produce HTML-style tags; e.g.:
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: Please include with your report: (1) the example input; (2) the output you expected; (3) the output PHP Markdown actually produced. If you have a problem where Markdown gives you an empty result, first check that the backtrack limit is not too low by running `php --info | grep pcre`. See Installation and Requirement above for details. Version History --------------- 1.0.2 (29 Nov 2013) * Added support for the `tel:` URL scheme in automatic links. It gets converted to this (note the `tel:` prefix becomes invisible): +1-111-111-1111 1.0.1q (11 Apr 2013): * Fixed a small mistake that could cause the parser to retain an invalid state related to parsing links across multiple runs. This was never observed (that I know of), but it's still worth fixing. 1.0.1p (13 Jan 2013): * Fixed an issue where some XML-style empty tags (such as `
`) were not recognized correctly as such when inserted into Markdown-formatted text. * The following HTML 5 elements are treated as block elements when at the root of an HTML block: `article`, `section`, `nav`, `aside`, `hgroup`, `header`, `footer`, and `figure`. `svg` too. 1.0.1o (8 Jan 2012): * Silenced a new warning introduced around PHP 5.3 complaining about POSIX characters classes not being implemented. PHP Markdown does not use POSIX character classes, but it nevertheless trigged that warning. 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@def"@example.com> <"Fred Bloggs"@example.com> * Now accepting spaces in URLs for inline and reference-style links. Such URLs need to be surrounded by angle brakets. For instance: [link text]( "optional title") [link text][ref] [ref]: "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. 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. 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 ``. * Fixed a problem where `` 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. 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. 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. 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. 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. 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:

The MD5 value for "+" is "+".

* 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: \-- 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. 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. 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: bar bar `` * Changed the parsing of HTML comments to match simply from `` instead using of the more complicated SGML-style rule with paired `--`. This is how most browsers parse comments and how XML defines them too. * `
` 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 1.0.1c (9 Dec 2005) * Fixed a problem occurring with PHP 5.1.1 due to a small change to strings variable replacement behaviour in this version. 1.0.1b (6 Jun 2005) * Fixed a bug where an inline image followed by a reference link would give a completely wrong result. * Fix for escaped backticks still triggering code spans: There are two raw backticks here: \` and here: \`, not a code span * Fix for an ordered list following an unordered list, and the reverse. There is now a loop in _DoList that does the two separately. * Fix for nested sub-lists in list-paragraph mode. Previously we got a spurious extra level of `

` tags for something like this: * this * sub that * Fixed some incorrect behaviour with emphasis. This will now work as it should: *test **thing*** **test *thing*** ***thing* test** ***thing** test* Name: __________ Address: _______ * Correct a small bug in `_TokenizeHTML` where a Doctype declaration was not seen as HTML. * Major rewrite of the WordPress integration code that should correct many problems by preventing default WordPress filters from tampering with Markdown-formatted text. More details here: 1.0.1a (15 Apr 2005) * Fixed an issue where PHP warnings were trigged when converting text with list items running on PHP 4.0.6. This was comming from the `rtrim` function which did not support the second argument prior version 4.1. Replaced by a regular expression. * Markdown now filter correctly post excerpts and comment excerpts in WordPress. * Automatic links and some code sample were "corrected" by the balenceTag filter in WordPress meant to ensure HTML is well formed. This new version of PHP Markdown postpone this filter so that it runs after Markdown. * Blockquote syntax and some code sample were stripped by a new WordPress 1.5 filter meant to remove unwanted HTML in comments. This new version of PHP Markdown postpone this filter so that it runs after Markdown. 1.0.1 (16 Dec 2004): * Changed the syntax rules for code blocks and spans. Previously, backslash escapes for special Markdown characters were processed everywhere other than within inline HTML tags. Now, the contents of code blocks and spans are no longer processed for backslash escapes. This means that code blocks and spans are now treated literally, with no special rules to worry about regarding backslashes. **IMPORTANT**: This breaks the syntax from all previous versions of Markdown. Code blocks and spans involving backslash characters will now generate different output than before. Implementation-wise, this change was made by moving the call to `_EscapeSpecialChars()` from the top-level `Markdown()` function to within `_RunSpanGamut()`. * Significants performance improvement in `_DoHeader`, `_Detab` and `_TokenizeHTML`. * Added `>`, `+`, and `-` to the list of backslash-escapable characters. These should have been done when these characters were added as unordered list item markers. * Inline links using `<` and `>` URL delimiters weren't working: like [this]() Fixed by moving `_DoAutoLinks()` after `_DoAnchors()` in `_RunSpanGamut()`. * Fixed bug where auto-links were being processed within code spans: like this: `` Fixed by moving `_DoAutoLinks()` from `_RunBlockGamut()` to `_RunSpanGamut()`. * Sort-of fixed a bug where lines in the middle of hard-wrapped paragraphs, which lines look like the start of a list item, would accidentally trigger the creation of a list. E.g. a paragraph that looked like this: I recommend upgrading to version 8. Oops, now this line is treated as a sub-list. This is fixed for top-level lists, but it can still happen for sub-lists. E.g., the following list item will not be parsed properly: * I recommend upgrading to version 8. Oops, now this line is treated as a sub-list. Given Markdown's list-creation rules, I'm not sure this can be fixed. * Fix for horizontal rules preceded by 2 or 3 spaces or followed by trailing spaces and tabs. * Standalone HTML comments are now handled; previously, they'd get wrapped in a spurious `

` tag. * `_HashHTMLBlocks()` now tolerates trailing spaces and tabs following HTML comments and `


` tags. * Changed special case pattern for hashing `
` tags in `_HashHTMLBlocks()` so that they must occur within three spaces of left margin. (With 4 spaces or a tab, they should be code blocks, but weren't before this fix.) * Auto-linked email address can now optionally contain a 'mailto:' protocol. I.e. these are equivalent: * Fixed annoying bug where nested lists would wind up with spurious (and invalid) `

` tags. * Changed `_StripLinkDefinitions()` so that link definitions must occur within three spaces of the left margin. Thus if you indent a link definition by four spaces or a tab, it will now be a code block. * You can now write empty links: [like this]() and they'll be turned into anchor tags with empty href attributes. This should have worked before, but didn't. * `***this***` and `___this___` are now turned into this Instead of this which isn't valid. * Fixed problem for links defined with urls that include parens, e.g.: [1]: http://sources.wikipedia.org/wiki/Middle_East_Policy_(Chomsky) "Chomsky" was being erroneously treated as the URL's title. * Double quotes in the title of an inline link used to give strange results (incorrectly made entities). Fixed. * Tabs are now correctly changed into spaces. Previously, only the first tab was converted. In code blocks, the second one was too, but was not always correctly aligned. * Fixed a bug where a tab character inserted after a quote on the same line could add a slash before the quotes. This is "before" [tab] and "after" a tab. Previously gave this result:

This is \"before\" [tab] and "after" a tab.

* Removed a call to `htmlentities`. This fixes a bug where multibyte characters present in the title of a link reference could lead to invalid utf-8 characters. * Changed a regular expression in `_TokenizeHTML` that could lead to a segmentation fault with PHP 4.3.8 on Linux. * Fixed some notices that could show up if PHP error reporting E_NOTICE flag was set. Copyright and License --------------------- PHP Markdown Copyright (c) 2004-2013 Michel Fortin All rights reserved. Based on Markdown Copyright (c) 2003-2006 John Gruber 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. libmarkdown-php-1.0.2/markdown.php0000644000000000000000000014030512246135735015654 0ustar rootroot # # Original Markdown # Copyright (c) 2004-2006 John Gruber # # define( 'MARKDOWN_VERSION', "1.0.2" ); # 29 Nov 2013 # # 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 ); # # 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', 'Markdown_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 Plugin URI: http://michelf.ca/projects/php-markdown/ Description: Markdown syntax allows you to write using an easy-to-read, easy-to-write plain text format. Based on the original Perl version by John Gruber. More... Version: 1.0.2 Author: Michel Fortin Author URI: http://michelf.ca/ */ if (isset($wp_version)) { # More details about how it works here: # # 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', 'Markdown', 6); add_filter('the_content_rss', 'Markdown', 6); add_filter('get_the_excerpt', 'Markdown', 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); } # 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(' ', '

 
  • '); $mdwp_placeholders = explode(' ', str_rot13( 'pEj07ZbbBZ U1kqgh4w4p pre2zmeN6K QTi31t9pre ol0MP1jzJR '. 'ML5IjmbRol ulANi1NsGY J7zRLJqPul liA8ctl16T K9nhooUHli')); } function mdwp_add_p($text) { if (!preg_match('{^$|^<(p|ul|ol|dl|pre|blockquote)>}i', $text)) { $text = '

    '.$text.'

    '; $text = preg_replace('{\n{2,}}', "

    \n\n

    ", $text); } return $text; } function mdwp_strip_p($t) { return preg_replace('{}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, $text); } } ### bBlog Plugin Info ### function identify_modifier_markdown() { return array( 'name' => 'markdown', 'type' => 'modifier', 'nicename' => 'Markdown', 'description' => 'A text-to-HTML conversion tool for web writers', 'authors' => 'Michel Fortin and John Gruber', 'licence' => 'BSD-like', 'version' => MARKDOWN_VERSION, 'help' => 'Markdown syntax allows you to write using an easy-to-read, easy-to-write plain text format. Based on the original Perl version by John Gruber. More...' ); } ### Smarty Modifier Interface ### function smarty_modifier_markdown($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 { ### Configuration Variables ### # 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(); ### Parser Implementation ### # 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; 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(); $this->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

    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|svg|'. 'article|section|nav|aside|hgroup|header|footer|'. 'figure'; # 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(' # 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.: #

    #
    # tags for inner block must be indented. #
    #
    # # 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 `
    ` and stop at the first `
    `. $text = preg_replace_callback('{(?> (?> (?<=\n\n) # Starting after a blank line | # or \A\n? # the beginning of the doc ) ( # save in $1 # Match from `\n` to `\n`, handling nested tags # in between. [ ]{0,'.$less_than_tab.'} <('.$block_tags_b_re.')# start tag = $2 '.$attr.'> # attributes followed by > and \n '.$content.' # content, support nesting # the matching end tag [ ]* # trailing spaces/tabs (?=\n+|\Z) # followed by a newline or end of document | # Special version for tags of group a. [ ]{0,'.$less_than_tab.'} <('.$block_tags_a_re.')# start tag = $3 '.$attr.'>[ ]*\n # attributes followed by > '.$content2.' # content, support nesting # the matching end tag [ ]* # trailing spaces/tabs (?=\n+|\Z) # followed by a newline or end of document | # Special case just for
    . It was easier to make a special # case than to make the other regex more complicated. [ ]{0,'.$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,'.$less_than_tab.'} (?s: ) [ ]* (?=\n{2,}|\Z) # followed by a blank line or end of document | # PHP and ASP-style processor instructions ( ) [ ]* (?=\n{2,}|\Z) # followed by a blank line or end of document ) )}Sxmi', array(&$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("empty_element_suffix")."\n", $text); } var $span_gamut = array( # # These are all the transformations that occur *within* block-level # tags like paragraphs, headers, and list items. # # Process character escapes, code spans, and inline HTML # in one shot. "parseSpan" => -30, # Process anchor and image tags. Images must come first, # because ![foo][f] looks like an anchor. "doImages" => 10, "doAnchors" => 20, # Make links out of things like `` # Must come after doAnchors, because you can use < and > # delimiters in inline links like [this](). "doAutoLinks" => 30, "encodeAmpsAndAngles" => 40, "doItalicsAndBold" => 50, "doHardBreaks" => 60, ); function runSpanGamut($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 $this->hashPart("empty_element_suffix\n"); } function doAnchors($text) { # # Turn Markdown link shortcuts into XHTML 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); $result = "titles[$link_id] ) ) { $title = $this->titles[$link_id]; $title = $this->encodeAttribute($title); $result .= " title=\"$title\""; } $link_text = $this->runSpanGamut($link_text); $result .= ">$link_text"; $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); $result = "encodeAttribute($title); $result .= " title=\"$title\""; } $link_text = $this->runSpanGamut($link_text); $result .= ">$link_text"; return $this->hashPart($result); } function doImages($text) { # # Turn Markdown image shortcuts into 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: ![alt text](url "optional title") # 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]); $result = "\"$alt_text\"";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); $result = "\"$alt_text\"";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; $block = "".$this->runSpanGamut($matches[1]).""; return "\n" . $this->hashBlock($block) . "\n\n"; } function _doHeaders_callback_atx($matches) { $level = strlen($matches[1]); $block = "".$this->runSpanGamut($matches[2]).""; 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 . ""); 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 "
  • " . $item . "
  • \n"; } function doCodeBlocks($text) { # # Process Markdown `
    ` 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 = "
    $codeblock\n
    "; return "\n\n".$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"); } var $em_relist = array( '' => '(?:(? '(?<=\S|^)(? '(?<=\S|^)(? '(?:(? '(?<=\S|^)(? '(?<=\S|^)(? '(?:(? '(?<=\S|^)(? '(?<=\S|^)(?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); $span = "$span"; $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"; $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"; $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); $span = "$span"; $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); $span = "$span"; $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
     content, 
    		# so we need to fix that:
    		$bq = preg_replace_callback('{(\s*
    .+?
    )}sx', array(&$this, '_doBlockQuotes_callback2'), $bq); return "\n". $this->hashBlock("
    \n$bq\n
    ")."\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

    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

    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('/^([ ]*)/', "

    ", $value); $value .= "

    "; $grafs[$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 =
    tag //
    ]* // \b // markdown\s*=\s* ([\'"]) # $2 = attr quote char // 1 // \2 // [^>]* // > // ) // ( # $3 = contents // .* // ) // (
    ) # $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: $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: $text = preg_replace_callback('{ < (?:mailto:)? ( (?: [-!#$%&\'*+/=?^_`.{|}~\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); $text = preg_replace_callback('{<(tel:([^\'">\s]+))>}i',array(&$this, '_doAutoLinks_tel_callback'), $text); return $text; } function _doAutoLinks_tel_callback($matches) { $url = $this->encodeAttribute($matches[1]); $tel = $this->encodeAttribute($matches[2]); $link = "$tel"; return $this->hashPart($link); } function _doAutoLinks_url_callback($matches) { $url = $this->encodeAttribute($matches[1]); $link = "$url"; 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.: # #

    foo@exampl # e.com

    # # Based by a filter by Matthew Wickline, posted to BBEdit-Talk. # With some optimizations by Milian Wolff. # $addr = "mailto:" . $addr; $chars = preg_split('/(? $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:` $addr = "$text"; 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.' | (?no_markup ? '' : ' | # comment | <\?.*?\?> | <%.*?%> # processing instruction | <[!$]?[-a-zA-Z0-9:_]+ # regular tags (?> \s (?>[^"\'>]+|"[^"]*"|\'[^\']*\')* )? > | <[-a-zA-Z0-9:_]+\s*/> # xml-style empty tag | # closing tag ').' ) }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]]; } } /* PHP Markdown ============ Description ----------- This is a PHP translation of the original Markdown formatter written in Perl by John Gruber. 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 mostly 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
    and as well). For more information about Markdown's syntax, see: Bugs ---- To file bug reports please send email to: 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 Copyright (c) 2004-2013 Michel Fortin All rights reserved. Based on Markdown Copyright (c) 2003-2006 John Gruber 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. */ ?>