From 2f46675a89b1dcb453654be4be2117114a3d0a65 Mon Sep 17 00:00:00 2001 From: Michael Vogel Date: Sun, 22 Feb 2015 17:38:28 +0100 Subject: [PATCH] New routines for markdown to html and html to markdown. --- include/bb2diaspora.php | 19 +- include/bbcode.php | 7 +- library/html-to-markdown/HTML_To_Markdown.php | 592 ++++ library/html-to-markdown/LICENSE | 20 + library/html-to-markdown/README.md | 138 + library/markdown.php | 2932 +---------------- library/parsedown/LICENSE.txt | 20 + library/parsedown/Parsedown.php | 1528 +++++++++ library/parsedown/README.md | 48 + 9 files changed, 2368 insertions(+), 2936 deletions(-) create mode 100644 library/html-to-markdown/HTML_To_Markdown.php create mode 100644 library/html-to-markdown/LICENSE create mode 100644 library/html-to-markdown/README.md create mode 100644 library/parsedown/LICENSE.txt create mode 100755 library/parsedown/Parsedown.php create mode 100644 library/parsedown/README.md diff --git a/include/bb2diaspora.php b/include/bb2diaspora.php index 7107c4913..272b69dff 100644 --- a/include/bb2diaspora.php +++ b/include/bb2diaspora.php @@ -5,7 +5,8 @@ require_once("include/event.php"); require_once("library/markdown.php"); require_once("include/html2bbcode.php"); require_once("include/bbcode.php"); -require_once("include/markdownify/markdownify.php"); +require_once("library/html-to-markdown/HTML_To_Markdown.php"); +//require_once("include/markdownify/markdownify.php"); // we don't want to support a bbcode specific markdown interpreter @@ -21,15 +22,15 @@ function diaspora2bb($s) { $s = str_replace("\r","",$s); //
is invalid. Replace it with the valid expression - $s = str_replace(array("
", "

", "

", '

'),array("
", "
", "
", "
"),$s); - - $s = preg_replace('/\@\{(.+?)\; (.+?)\@(.+?)\}/','@[url=https://$3/u/$2]$1[/url]',$s); + //$s = str_replace(array("
", "

", "

", '

'),array("
", "
", "
", "
"),$s); // Escaping the hash tags $s = preg_replace('/\#([^\s\#])/','#$1',$s); $s = Markdown($s); + $s = preg_replace('/\@\{(.+?)\; (.+?)\@(.+?)\}/','@[url=https://$3/u/$2]$1[/url]',$s); + $s = str_replace('#','#',$s); $s = html2bbcode($s); @@ -92,12 +93,15 @@ function bb2diaspora($Text,$preserve_nl = false, $fordiaspora = true) { $Text = bbcode($Text, $preserve_nl, false, 4); // Libertree doesn't convert a harizontal rule if there isn't a linefeed - $Text = str_replace(array("


", "
"), array("

", "

"), $Text); + //$Text = str_replace(array("
", "
"), array("

", "

"), $Text); } // Now convert HTML to Markdown - $md = new Markdownify(false, false, false); - $Text = $md->parseString($Text); + $Text = new HTML_To_Markdown($Text); + +/* + //$md = new Markdownify(false, false, false); + //$Text = $md->parseString($Text); // The Markdownify converter converts underscores '_' in URLs to '\_', which // messes up the URL. Manually fix these @@ -123,6 +127,7 @@ function bb2diaspora($Text,$preserve_nl = false, $fordiaspora = true) { // Remove all unconverted tags $Text = strip_tags($Text); +*/ // Remove any leading or trailing whitespace, as this will mess up // the Diaspora signature verification and cause the item to disappear diff --git a/include/bbcode.php b/include/bbcode.php index 9a3563527..d461b9848 100644 --- a/include/bbcode.php +++ b/include/bbcode.php @@ -168,6 +168,8 @@ function bb_remove_share_information($Text, $plaintext = false, $nolink = false) } function bb_cleanup_share($shared, $plaintext, $nolink) { + $shared[1] = trim($shared[1]); + if (!in_array($shared[2], array("type-link", "type-video"))) return($shared[0]); @@ -178,7 +180,7 @@ function bb_cleanup_share($shared, $plaintext, $nolink) { return($shared[0]); if ($nolink) - return(trim($shared[1])); + return($shared[1]); $title = ""; $link = ""; @@ -189,6 +191,9 @@ function bb_cleanup_share($shared, $plaintext, $nolink) { if (isset($bookmark[1][0])) $link = $bookmark[1][0]; + if (($title != "") AND (strpos($title, $shared[1]) !== false)) + $shared[1] = $title; + if (($title != "") AND ((strpos($shared[1],$title) !== false) OR (similar_text($shared[1],$title) / strlen($title)) > 0.9)) $title = ""; diff --git a/library/html-to-markdown/HTML_To_Markdown.php b/library/html-to-markdown/HTML_To_Markdown.php new file mode 100644 index 000000000..1cc86505b --- /dev/null +++ b/library/html-to-markdown/HTML_To_Markdown.php @@ -0,0 +1,592 @@ + + * @link https://github.com/nickcernis/html2markdown/ Latest version on GitHub. + * @link http://twitter.com/nickcernis Nick on twitter. + * @license http://www.opensource.org/licenses/mit-license.php MIT + */ +class HTML_To_Markdown +{ + /** + * @var DOMDocument The root of the document tree that holds our HTML. + */ + private $document; + + /** + * @var string|boolean The Markdown version of the original HTML, or false if conversion failed + */ + private $output; + + /** + * @var array Class-wide options users can override. + */ + private $options = array( + 'header_style' => 'setext', // Set to "atx" to output H1 and H2 headers as # Header1 and ## Header2 + 'suppress_errors' => true, // Set to false to show warnings when loading malformed HTML + 'strip_tags' => false, // Set to true to strip tags that don't have markdown equivalents. N.B. Strips tags, not their content. Useful to clean MS Word HTML output. + 'bold_style' => '**', // Set to '__' if you prefer the underlined style + 'italic_style' => '*', // Set to '_' if you prefer the underlined style + 'remove_nodes' => '', // space-separated list of dom nodes that should be removed. example: "meta style script" + ); + + + /** + * Constructor + * + * Set up a new DOMDocument from the supplied HTML, convert it to Markdown, and store it in $this->$output. + * + * @param string $html The HTML to convert to Markdown. + * @param array $overrides [optional] List of style and error display overrides. + */ + public function __construct($html = null, $overrides = null) + { + if ($overrides) + $this->options = array_merge($this->options, $overrides); + + if ($html) + $this->convert($html); + } + + + /** + * Setter for conversion options + * + * @param $name + * @param $value + */ + public function set_option($name, $value) + { + $this->options[$name] = $value; + } + + + /** + * Convert + * + * Loads HTML and passes to get_markdown() + * + * @param $html + * @return string The Markdown version of the html + */ + public function convert($html) + { + $html = preg_replace('~>\s+<~', '><', $html); // Strip white space between tags to prevent creation of empty #text nodes + + $this->document = new DOMDocument(); + + if ($this->options['suppress_errors']) + libxml_use_internal_errors(true); // Suppress conversion errors (from http://bit.ly/pCCRSX ) + + $this->document->loadHTML('' . $html); // Hack to load utf-8 HTML (from http://bit.ly/pVDyCt ) + $this->document->encoding = 'UTF-8'; + + if ($this->options['suppress_errors']) + libxml_clear_errors(); + + return $this->get_markdown($html); + } + + + /** + * Is Child Of? + * + * Is the node a child of the given parent tag? + * + * @param $parent_name string The name of the parent node to search for (e.g. 'code') + * @param $node + * @return bool + */ + private static function is_child_of($parent_name, $node) + { + for ($p = $node->parentNode; $p != false; $p = $p->parentNode) { + if (is_null($p)) + return false; + + if ($p->nodeName == $parent_name) + return true; + } + return false; + } + + + /** + * Convert Children + * + * Recursive function to drill into the DOM and convert each node into Markdown from the inside out. + * + * Finds children of each node and convert those to #text nodes containing their Markdown equivalent, + * starting with the innermost element and working up to the outermost element. + * + * @param $node + */ + private function convert_children($node) + { + // Don't convert HTML code inside and
 blocks to Markdown - that should stay as HTML
+        if (self::is_child_of('pre', $node) || self::is_child_of('code', $node))
+            return;
+
+        // If the node has children, convert those to Markdown first
+        if ($node->hasChildNodes()) {
+            $length = $node->childNodes->length;
+
+            for ($i = 0; $i < $length; $i++) {
+                $child = $node->childNodes->item($i);
+                $this->convert_children($child);
+            }
+        }
+
+        // Now that child nodes have been converted, convert the original node
+        $markdown = $this->convert_to_markdown($node);
+
+        // Create a DOM text node containing the Markdown equivalent of the original node
+        $markdown_node = $this->document->createTextNode($markdown);
+
+        // Replace the old $node e.g. "

Title

" with the new $markdown_node e.g. "### Title" + $node->parentNode->replaceChild($markdown_node, $node); + } + + + /** + * Get Markdown + * + * Sends the body node to convert_children() to change inner nodes to Markdown #text nodes, then saves and + * returns the resulting converted document as a string in Markdown format. + * + * @return string|boolean The converted HTML as Markdown, or false if conversion failed + */ + private function get_markdown() + { + // Work on the entire DOM tree (including head and body) + $input = $this->document->getElementsByTagName("html")->item(0); + + if (!$input) + return false; + + // Convert all children of this root element. The DOMDocument stored in $this->doc will + // then consist of #text nodes, each containing a Markdown version of the original node + // that it replaced. + $this->convert_children($input); + + // Sanitize and return the body contents as a string. + $markdown = $this->document->saveHTML(); // stores the DOMDocument as a string + $markdown = html_entity_decode($markdown, ENT_QUOTES, 'UTF-8'); + $markdown = html_entity_decode($markdown, ENT_QUOTES, 'UTF-8'); // Double decode to cover cases like &nbsp; http://www.php.net/manual/en/function.htmlentities.php#99984 + $markdown = preg_replace("/]+>/", "", $markdown); // Strip doctype declaration + $unwanted = array('', '', '', '', '', '', '', ' '); + $markdown = str_replace($unwanted, '', $markdown); // Strip unwanted tags + $markdown = trim($markdown, "\n\r\0\x0B"); + + $this->output = $markdown; + + return $markdown; + } + + + /** + * Convert to Markdown + * + * Converts an individual node into a #text node containing a string of its Markdown equivalent. + * + * Example: An

node with text content of "Title" becomes a text node with content of "### Title" + * + * @param $node + * @return string The converted HTML as Markdown + */ + private function convert_to_markdown($node) + { + $tag = $node->nodeName; // the type of element, e.g. h1 + $value = $node->nodeValue; // the value of that element, e.g. The Title + + // Strip nodes named in remove_nodes + $tags_to_remove = explode(' ', $this->options['remove_nodes']); + if ( in_array($tag, $tags_to_remove) ) + return false; + + switch ($tag) { + case "p": + $markdown = (trim($value)) ? rtrim($value) . PHP_EOL . PHP_EOL : ''; + break; + case "pre": + $markdown = PHP_EOL . $this->convert_code($node) . PHP_EOL; + break; + case "h1": + case "h2": + $markdown = $this->convert_header($tag, $node); + break; + case "h3": + $markdown = "### " . $value . PHP_EOL . PHP_EOL; + break; + case "h4": + $markdown = "#### " . $value . PHP_EOL . PHP_EOL; + break; + case "h5": + $markdown = "##### " . $value . PHP_EOL . PHP_EOL; + break; + case "h6": + $markdown = "###### " . $value . PHP_EOL . PHP_EOL; + break; + case "em": + case "i": + case "strong": + case "b": + $markdown = $this->convert_emphasis($tag, $value); + break; + case "hr": + $markdown = "- - - - - -" . PHP_EOL . PHP_EOL; + break; + case "br": + $markdown = " " . PHP_EOL; + break; + case "blockquote": + $markdown = $this->convert_blockquote($node); + break; + case "code": + $markdown = $this->convert_code($node); + break; + case "ol": + case "ul": + $markdown = $value . PHP_EOL; + break; + case "li": + $markdown = $this->convert_list($node); + break; + case "img": + $markdown = $this->convert_image($node); + break; + case "a": + $markdown = $this->convert_anchor($node); + break; + case "#text": + $markdown = preg_replace('~\s+~', ' ', $value); + $markdown = preg_replace('~^#~', '\\\\#', $markdown); + break; + case "#comment": + $markdown = ''; + break; + case "div": + $markdown = ($this->options['strip_tags']) ? $value . PHP_EOL . PHP_EOL : html_entity_decode($node->C14N()); + break; + default: + // If strip_tags is false (the default), preserve tags that don't have Markdown equivalents, + // such as nodes on their own. C14N() canonicalizes the node to a string. + // See: http://www.php.net/manual/en/domnode.c14n.php + $markdown = ($this->options['strip_tags']) ? $value : html_entity_decode($node->C14N()); + } + + return $markdown; + } + + + /** + * Convert Header + * + * Converts h1 and h2 headers to Markdown-style headers in setext style, + * matching the number of underscores with the length of the title. + * + * e.g. Header 1 Header Two + * ======== ---------- + * + * Returns atx headers instead if $this->options['header_style'] is "atx" + * + * e.g. # Header 1 ## Header Two + * + * @param string $level The header level, including the "h". e.g. h1 + * @param string $node The node to convert. + * @return string The Markdown version of the header. + */ + private function convert_header($level, $node) + { + $content = $node->nodeValue; + + if (!$this->is_child_of('blockquote', $node) && $this->options['header_style'] == "setext") { + $length = (function_exists('mb_strlen')) ? mb_strlen($content, 'utf-8') : strlen($content); + $underline = ($level == "h1") ? "=" : "-"; + $markdown = $content . PHP_EOL . str_repeat($underline, $length) . PHP_EOL . PHP_EOL; // setext style + } else { + $prefix = ($level == "h1") ? "# " : "## "; + $markdown = $prefix . $content . PHP_EOL . PHP_EOL; // atx style + } + + return $markdown; + } + + + /** + * Converts inline styles + * This function is used to render strong and em tags + * + * eg bold text becomes **bold text** or __bold text__ + * + * @param string $tag + * @param string $value + * @return string + */ + private function convert_emphasis($tag, $value) + { + if ($tag == 'i' || $tag == 'em') { + $markdown = $this->options['italic_style'] . $value . $this->options['italic_style']; + } else { + $markdown = $this->options['bold_style'] . $value . $this->options['bold_style']; + } + + return $markdown; + } + + + /** + * Convert Image + * + * Converts tags to Markdown. + * + * e.g. alt text + * becomes ![alt text](/path/img.jpg "Title") + * + * @param $node + * @return string + */ + private function convert_image($node) + { + $src = $node->getAttribute('src'); + $alt = $node->getAttribute('alt'); + $title = $node->getAttribute('title'); + + if ($title != "") { + $markdown = '![' . $alt . '](' . $src . ' "' . $title . '")'; // No newlines added. should be in a block-level element. + } else { + $markdown = '![' . $alt . '](' . $src . ')'; + } + + return $markdown; + } + + + /** + * Convert Anchor + * + * Converts tags to Markdown. + * + * e.g. Modern Nerd + * becomes [Modern Nerd](http://modernnerd.net "Title") + * + * @param $node + * @return string + */ + private function convert_anchor($node) + { + $href = $node->getAttribute('href'); + $title = $node->getAttribute('title'); + $text = $node->nodeValue; + + if ($title != "") { + $markdown = '[' . $text . '](' . $href . ' "' . $title . '")'; + } else { + $markdown = '[' . $text . '](' . $href . ')'; + } + + // Append a space if the node after this one is also an anchor + $next_node_name = $this->get_next_node_name($node); + + if ($next_node_name == 'a') + $markdown = $markdown . ' '; + + return $markdown; + } + + + /** + * Convert List + * + * Converts
    and
      lists to Markdown. + * + * @param $node + * @return string + */ + private function convert_list($node) + { + // If parent is an ol, use numbers, otherwise, use dashes + $list_type = $node->parentNode->nodeName; + $value = $node->nodeValue; + + if ($list_type == "ul") { + $markdown = "- " . trim($value) . PHP_EOL; + } else { + $number = $this->get_position($node); + $markdown = $number . ". " . trim($value) . PHP_EOL; + } + + return $markdown; + } + + + /** + * Convert Code + * + * Convert code tags by indenting blocks of code and wrapping single lines in backticks. + * + * @param DOMNode $node + * @return string + */ + private function convert_code($node) + { + // Store the content of the code block in an array, one entry for each line + + $markdown = ''; + + $code_content = html_entity_decode($this->document->saveHTML($node)); + $code_content = str_replace(array("", ""), "", $code_content); + $code_content = str_replace(array("
      ", "
      "), "", $code_content); + + $lines = preg_split('/\r\n|\r|\n/', $code_content); + $total = count($lines); + + // If there's more than one line of code, prepend each line with four spaces and no backticks. + if ($total > 1 || $node->nodeName === 'pre') { + + // Remove the first and last line if they're empty + $first_line = trim($lines[0]); + $last_line = trim($lines[$total - 1]); + $first_line = trim($first_line, " "); //trim XML style carriage returns too + $last_line = trim($last_line, " "); + + if (empty($first_line)) + array_shift($lines); + + if (empty($last_line)) + array_pop($lines); + + $count = 1; + foreach ($lines as $line) { + $line = str_replace(' ', '', $line); + $markdown .= " " . $line; + // Add newlines, except final line of the code + if ($count != $total) + $markdown .= PHP_EOL; + $count++; + } + $markdown .= PHP_EOL; + + } else { // There's only one line of code. It's a code span, not a block. Just wrap it with backticks. + + $markdown .= "`" . $lines[0] . "`"; + + } + + return $markdown; + } + + + /** + * Convert blockquote + * + * Prepend blockquotes with > chars. + * + * @param $node + * @return string + */ + private function convert_blockquote($node) + { + // Contents should have already been converted to Markdown by this point, + // so we just need to add ">" symbols to each line. + + $markdown = ''; + + $quote_content = trim($node->nodeValue); + + $lines = preg_split('/\r\n|\r|\n/', $quote_content); + + $total_lines = count($lines); + + foreach ($lines as $i => $line) { + $markdown .= "> " . $line . PHP_EOL; + if ($i + 1 == $total_lines) + $markdown .= PHP_EOL; + } + + return $markdown; + } + + + /** + * Get Position + * + * Returns the numbered position of a node inside its parent + * + * @param $node + * @return int The numbered position of the node, starting at 1. + */ + private function get_position($node) + { + // Get all of the nodes inside the parent + $list_nodes = $node->parentNode->childNodes; + $total_nodes = $list_nodes->length; + + $position = 1; + + // Loop through all nodes and find the given $node + for ($a = 0; $a < $total_nodes; $a++) { + $current_node = $list_nodes->item($a); + + if ($current_node->isSameNode($node)) + $position = $a + 1; + } + + return $position; + } + + + /** + * Get Next Node Name + * + * Return the name of the node immediately after the passed one. + * + * @param $node + * @return string|null The node name (e.g. 'h1') or null. + */ + private function get_next_node_name($node) + { + $next_node_name = null; + + $current_position = $this->get_position($node); + $next_node = $node->parentNode->childNodes->item($current_position); + + if ($next_node) + $next_node_name = $next_node->nodeName; + + return $next_node_name; + } + + + /** + * To String + * + * Magic method to return Markdown output when HTML_To_Markdown instance is treated as a string. + * + * @return string + */ + public function __toString() + { + return $this->output(); + } + + + /** + * Output + * + * Getter for the converted Markdown contents stored in $this->output + * + * @return string + */ + public function output() + { + if (!$this->output) { + return ''; + } else { + return $this->output; + } + } +} diff --git a/library/html-to-markdown/LICENSE b/library/html-to-markdown/LICENSE new file mode 100644 index 000000000..f538c2ac9 --- /dev/null +++ b/library/html-to-markdown/LICENSE @@ -0,0 +1,20 @@ +The MIT License (MIT) + +Copyright (c) 2013 Nick Cernis + +Permission is hereby granted, free of charge, to any person obtaining a copy of +this software and associated documentation files (the "Software"), to deal in +the Software without restriction, including without limitation the rights to +use, copy, modify, merge, publish, distribute, sublicense, and/or sell copies of +the Software, and to permit persons to whom the Software is furnished to do so, +subject to the following conditions: + +The above copyright notice and this permission notice shall be included in all +copies or substantial portions of the Software. + +THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR +IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, FITNESS +FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR +COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER +IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN +CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE SOFTWARE. \ No newline at end of file diff --git a/library/html-to-markdown/README.md b/library/html-to-markdown/README.md new file mode 100644 index 000000000..124c9868a --- /dev/null +++ b/library/html-to-markdown/README.md @@ -0,0 +1,138 @@ +HTML To Markdown for PHP +======================== + +A helper class that converts HTML to [Markdown](http://daringfireball.net/projects/markdown/) for your sanity and convenience. + +[![Build Status](https://travis-ci.org/nickcernis/html-to-markdown.png?branch=master)](https://travis-ci.org/nickcernis/html-to-markdown) + +**Version**: 2.2.0 +**Requires**: PHP 5.3+ +**Author**: [@nickcernis](http://twitter.com/nickcernis) +**License**: [MIT](http://www.opensource.org/licenses/mit-license.php) + +### Why convert HTML to Markdown? + +*"What alchemy is this?"* you mutter. *"I can see why you'd convert [Markdown to HTML](http://michelf.com/projects/php-markdown/),"* you continue, already labouring the question somewhat, *"but why go the other way?"* + +Typically you would convert HTML to Markdown if: + +1. You have an existing HTML document that needs to be edited by people with good taste. +2. You want to store new content in HTML format but edit it as Markdown. +3. You want to convert HTML email to plain text email. +4. You know a guy who's been converting HTML to Markdown for years, and now he can speak Elvish. You'd quite like to be able to speak Elvish. +5. You just really like Markdown. + +### How to use it + +Either include HTML_To_Markdown.php directly: + + require_once( dirname( __FILE__) . '/HTML_To_Markdown.php' ); + +Or, require the library in your composer.json: + + { + "require": { + "nickcernis/html-to-markdown": "dev-master" + } + } + +Then `composer install` and add `require 'vendor/autoload.php';` to the top of your script. + +Next, create a new HTML_To_Markdown instance, passing in your valid HTML code: + + $html = "

      Quick, to the Batpoles!

      "; + $markdown = new HTML_To_Markdown($html); + +The `$markdown` object now contains the Markdown version of your HTML. Use it like a string: + + echo $markdown; // ==> ### Quick, to the Batpoles! + +Or access the Markdown output directly: + + $string = $markdown->output(); + +The included `demo` directory contains an HTML->Markdown conversion form to try out. + +### Conversion options + +By default, HTML To Markdown preserves HTML tags without Markdown equivalents, like `` and `
      `. + +To strip HTML tags that don't have a Markdown equivalent while preserving the content inside them, set `strip_tags` to true, like this: + + $html = 'Turnips!'; + $markdown = new HTML_To_Markdown($html, array('strip_tags' => true)); // $markdown now contains "Turnips!" + +Or more explicitly, like this: + + $html = 'Turnips!'; + $markdown = new HTML_To_Markdown(); + $markdown->set_option('strip_tags', true); + $markdown->convert($html); // $markdown now contains "Turnips!" + +Note that only the tags themselves are stripped, not the content they hold. + +To strip tags and their content, pass a space-separated list of tags in `remove_nodes`, like this: + + $html = 'Turnips!
      Monkeys!
      '; + $markdown = new HTML_To_Markdown($html, array('remove_nodes' => 'span div')); // $markdown now contains "" + +### Style options + +Bold and italic tags are converted using the asterisk syntax by default. Change this to the underlined syntax using the `bold_style` and `italic_style` options. + + $html = 'Italic and a bold'; + $markdown = new HTML_To_Markdown(); + $markdown->set_option('italic_style', '_'); + $markdown->set_option('bold_style', '__'); + $markdown->convert($html); // $markdown now contains "_Italic_ and a __bold__" + +### Limitations + +- Markdown Extra, MultiMarkdown and other variants aren't supported – just Markdown. + +### Known issues + +- Nested lists and lists containing multiple paragraphs aren't converted correctly. +- Lists inside blockquotes aren't converted correctly. +- Any reported [open issues here](https://github.com/nickcernis/html-to-markdown/issues?state=open). + +[Report your issue or request a feature here.](https://github.com/nickcernis/html2markdown/issues/new) Issues with patches or failing tests are especially welcome. + +### Style notes + +- Setext (underlined) headers are the default for H1 and H2. If you prefer the ATX style for H1 and H2 (# Header 1 and ## Header 2), set `header_style` to 'atx' in the options array when you instantiate the object: + + `$markdown = new HTML_To_Markdown( $html, array('header_style'=>'atx') );` + + Headers of H3 priority and lower always use atx style. + +- Links and images are referenced inline. Footnote references (where image src and anchor href attributes are listed in the footnotes) are not used. +- Blockquotes aren't line wrapped – it makes the converted Markdown easier to edit. + +### Dependencies + +HTML To Markdown requires PHP's [xml](http://www.php.net/manual/en/xml.installation.php), [lib-xml](http://www.php.net/manual/en/libxml.installation.php), and [dom](http://www.php.net/manual/en/dom.installation.php) extensions, all of which are enabled by default on most distributions. + +Errors such as "Fatal error: Class 'DOMDocument' not found" on distributions such as CentOS that disable PHP's xml extension can be resolved by installing php-xml. + +### Architecture notes + +HTML To Markdown is a single file that uses native DOM manipulation libraries (DOMDocument), not regex voodoo, to convert code. + +### Contributors + +Many thanks to all [contributors](https://github.com/nickcernis/html2markdown/graphs/contributors) so far. Further improvements and feature suggestions are very welcome. + +### How it works + +HTML To Markdown creates a DOMDocument from the supplied HTML, walks through the tree, and converts each node to a text node containing the equivalent markdown, starting from the most deeply nested node and working inwards towards the root node. + +### To-do + +- Support for nested lists and lists inside blockquotes. +- Offer an option to preserve tags as HTML if they contain attributes that can't be represented with Markdown (e.g. `style`). + +### Trying to convert Markdown to HTML? + +Use [PHP Markdown](http://michelf.com/projects/php-markdown/) from Michel Fortin. No guarantees about the Elvish, though. + diff --git a/library/markdown.php b/library/markdown.php index f548fc26c..271d2e36c 100644 --- a/library/markdown.php +++ b/library/markdown.php @@ -1,2932 +1,8 @@ -# -# Original Markdown -# Copyright (c) 2004-2006 John Gruber -# -# - - -define( 'MARKDOWN_VERSION', "1.0.1o" ); # Sun 8 Jan 2012 -define( 'MARKDOWNEXTRA_VERSION', "1.2.5" ); # Sun 8 Jan 2012 - - -# -# 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' ); +require_once("library/parsedown/Parsedown.php"); 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); + $Parsedown = new Parsedown(); + return($Parsedown->text($text)); } - - -### WordPress Plugin Interface ### - -/* -Plugin Name: Markdown Extra -Plugin URI: http://michelf.com/projects/php-markdown/ -Description: Markdown syntax allows you to write using an easy-to-read, easy-to-write plain text format. Based on the original Perl version by John Gruber. More... -Version: 1.2.5 -Author: Michel Fortin -Author URI: http://michelf.com/ -*/ - -if (isset($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', '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(' ', - '

       
    1. '); - $mdwp_placeholders = explode(' ', str_rot13( - 'pEj07ZbbBZ U1kqgh4w4p pre2zmeN6K QTi31t9pre ol0MP1jzJR '. - 'ML5IjmbRol ulANi1NsGY J7zRLJqPul liA8ctl16T K9nhooUHli')); - } - - function mdwp_add_p($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, $text); - } -} - - -### bBlog Plugin Info ### - -function identify_modifier_markdown() { - return array( - 'name' => 'markdown', - 'type' => 'modifier', - 'nicename' => 'PHP Markdown Extra', - 'description' => 'A text-to-HTML conversion tool for web writers', - 'authors' => 'Michel Fortin and John Gruber', - 'licence' => 'GPL', - 'version' => MARKDOWNEXTRA_VERSION, - 'help' => 'Markdown syntax allows you to write using an easy-to-read, easy-to-write plain text format. Based on the original Perl version by John Gruber. More...', - ); -} - - -### Smarty Modifier Interface ### - -function smarty_modifier_markdown($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 { - - # 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

      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(' - # 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 "
    2. " . $item . "
    3. \n"; - } - - - function doCodeBlocks($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); - - return $text; - } - function _doAutoLinks_url_callback($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 - (?>[^"\'>]+|"[^"]*"|\'[^\']*\')* - )? - > - ').' - ) - }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

      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: - # - #

      - #
      - # Hello World. <-- Is this a Markdown code block or text? - #
      <-- Is this a Markdown code block or a real tag? - #
      - # - # 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 = - '{ - ( # $2: Capture hole tag. - # Tag name. - '.$this->block_tags_re.' | - '.$this->context_block_tags_re.' | - '.$this->clean_tags_re.' | - (?!\s)'.$enclosing_tag_re.' - ) - (?: - (?=[\s"\'/a-zA-Z0-9]) # Allowed characters after tag name. - (?> - ".*?" | # Double quotes (can contain `>`) - \'.*?\' | # Single quotes (can contain `>`) - .+? # Anything but quotes and `>`. - )*? - )? - > # End of tag. - | - # HTML Comment - | - <\?.*?\?> | <%.*?%> # Processing instruction - | - # CData Block - | - # Code span marker - `+ - '. ( !$span ? ' # If not in span. - | - # Indented code block - (?: ^[ ]*\n | ^ | \n[ ]*\n ) - [ ]{'.($indent+4).'}[^\n]* \n - (?> - (?: [ ]{'.($indent+4).'}[^\n]* | [ ]* ) \n - )* - | - # Fenced code block marker - (?> ^ | \n ) - [ ]{0,'.($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))*?(?.*\n)+?[ ]{0,'.($indent).'}'.$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 .= $tag; - } - } - # - # Check for: Indented code block. - # - else if ($tag{0} == "\n" || $tag{0} == " ") { - # Indented code block: pass it unchanged, will be handled - # later. - $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('{^= 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. - - ".*?" | # Double quotes (can contain `>`) - \'.*?\' | # Single quotes (can contain `>`) - .+? # Anything but quotes and `>`. - )*? - )? - > # End of tag. - | - # HTML Comment - | - <\?.*?\?> | <%.*?%> # Processing instruction - | - # 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
      ) - # Comments and Processing Instructions. - # - if (preg_match('{^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('{^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} - # - $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]); - $block = "".$this->runSpanGamut($matches[1]).""; - return "\n" . $this->hashBlock($block) . "\n\n"; - } - function _doHeaders_callback_atx($matches) { - $level = strlen($matches[1]); - $attr = $this->_doHeaders_attr($id =& $matches[3]); - $block = "".$this->runSpanGamut($matches[2]).""; - 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 = "\n"; - $text .= "\n"; - $text .= "\n"; - foreach ($headers as $n => $header) - $text .= " ".$this->runSpanGamut(trim($header))."\n"; - $text .= "\n"; - $text .= "\n"; - - # Split content by row. - $rows = explode("\n", trim($content, "\n")); - - $text .= "\n"; - foreach ($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, ''); - - $text .= "\n"; - foreach ($row_cells as $n => $cell) - $text .= " ".$this->runSpanGamut(trim($cell))."\n"; - $text .= "\n"; - } - $text .= "\n"; - $text .= "
      "; - - 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 = "
      \n" . $result . "\n
      "; - 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.'} [:][ ] | -
      | \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
      " . $term . "
      "; - } - 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
      " . $def . "
      \n"; - } - - - function doFencedCodeBlocks($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 = "
      $codeblock
      "; - return "\n\n".$this->hashBlock($codeblock)."\n\n"; - } - function _doFencedCodeBlocks_newlines($matches) { - return str_repeat("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( - '' => '(?:(? '(?<=\S|^)(? '(?<=\S|^)(? '(?:(? '(?<=\S|^)(? '(?<=\S|^)(? '(?:(? '(?<=\S|^)(? '(?<=\S|^)(? 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) { - $value = trim($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 = "

      $value

      "; - } - $grafs[$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 .= "
      \n"; - $text .= "empty_element_suffix ."\n"; - $text .= "
        \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 = ""; - if (preg_match('{

        $}', $footnote)) { - $footnote = substr($footnote, 0, -4) . " $backlink

        "; - } else { - $footnote .= "\n\n

        $backlink

        "; - } - - $text .= "
      1. \n"; - $text .= $footnote . "\n"; - $text .= "
      2. \n\n"; - } - - $text .= "
      \n"; - $text .= "
      "; - } - 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 - "". - "$num". - ""; - } - - return "[^".$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 elements. - # - if ($this->abbr_word_re) { - // cannot use the /x modifier because abbr_word_re may - // contain significant spaces: - $text = preg_replace_callback('{'. - '(?abbr_word_re.')'. - '(?![\w\x1A])'. - '}', - array(&$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"); - } else { - $desc = $this->encodeAttribute($desc); - return $this->hashPart("$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
      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 & Extra -Copyright (c) 2004-2009 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. - -*/ -?> \ No newline at end of file +?> diff --git a/library/parsedown/LICENSE.txt b/library/parsedown/LICENSE.txt new file mode 100644 index 000000000..baca86f5b --- /dev/null +++ b/library/parsedown/LICENSE.txt @@ -0,0 +1,20 @@ +The MIT License (MIT) + +Copyright (c) 2013 Emanuil Rusev, erusev.com + +Permission is hereby granted, free of charge, to any person obtaining a copy of +this software and associated documentation files (the "Software"), to deal in +the Software without restriction, including without limitation the rights to +use, copy, modify, merge, publish, distribute, sublicense, and/or sell copies of +the Software, and to permit persons to whom the Software is furnished to do so, +subject to the following conditions: + +The above copyright notice and this permission notice shall be included in all +copies or substantial portions of the Software. + +THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR +IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, FITNESS +FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR +COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER +IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN +CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE SOFTWARE. \ No newline at end of file diff --git a/library/parsedown/Parsedown.php b/library/parsedown/Parsedown.php new file mode 100755 index 000000000..9bdae2221 --- /dev/null +++ b/library/parsedown/Parsedown.php @@ -0,0 +1,1528 @@ +DefinitionData = array(); + + # standardize line breaks + $text = str_replace(array("\r\n", "\r"), "\n", $text); + + # remove surrounding line breaks + $text = trim($text, "\n"); + + # split text into lines + $lines = explode("\n", $text); + + # iterate through lines to identify blocks + $markup = $this->lines($lines); + + # trim line breaks + $markup = trim($markup, "\n"); + + return $markup; + } + + # + # Setters + # + + function setBreaksEnabled($breaksEnabled) + { + $this->breaksEnabled = $breaksEnabled; + + return $this; + } + + protected $breaksEnabled; + + function setMarkupEscaped($markupEscaped) + { + $this->markupEscaped = $markupEscaped; + + return $this; + } + + protected $markupEscaped; + + function setUrlsLinked($urlsLinked) + { + $this->urlsLinked = $urlsLinked; + + return $this; + } + + protected $urlsLinked = true; + + # + # Lines + # + + protected $BlockTypes = array( + '#' => array('Header'), + '*' => array('Rule', 'List'), + '+' => array('List'), + '-' => array('SetextHeader', 'Table', 'Rule', 'List'), + '0' => array('List'), + '1' => array('List'), + '2' => array('List'), + '3' => array('List'), + '4' => array('List'), + '5' => array('List'), + '6' => array('List'), + '7' => array('List'), + '8' => array('List'), + '9' => array('List'), + ':' => array('Table'), + '<' => array('Comment', 'Markup'), + '=' => array('SetextHeader'), + '>' => array('Quote'), + '[' => array('Reference'), + '_' => array('Rule'), + '`' => array('FencedCode'), + '|' => array('Table'), + '~' => array('FencedCode'), + ); + + # ~ + + protected $DefinitionTypes = array( + '[' => array('Reference'), + ); + + # ~ + + protected $unmarkedBlockTypes = array( + 'Code', + ); + + # + # Blocks + # + + private function lines(array $lines) + { + $CurrentBlock = null; + + foreach ($lines as $line) + { + if (chop($line) === '') + { + if (isset($CurrentBlock)) + { + $CurrentBlock['interrupted'] = true; + } + + continue; + } + + if (strpos($line, "\t") !== false) + { + $parts = explode("\t", $line); + + $line = $parts[0]; + + unset($parts[0]); + + foreach ($parts as $part) + { + $shortage = 4 - mb_strlen($line, 'utf-8') % 4; + + $line .= str_repeat(' ', $shortage); + $line .= $part; + } + } + + $indent = 0; + + while (isset($line[$indent]) and $line[$indent] === ' ') + { + $indent ++; + } + + $text = $indent > 0 ? substr($line, $indent) : $line; + + # ~ + + $Line = array('body' => $line, 'indent' => $indent, 'text' => $text); + + # ~ + + if (isset($CurrentBlock['incomplete'])) + { + $Block = $this->{'block'.$CurrentBlock['type'].'Continue'}($Line, $CurrentBlock); + + if (isset($Block)) + { + $CurrentBlock = $Block; + + continue; + } + else + { + if (method_exists($this, 'block'.$CurrentBlock['type'].'Complete')) + { + $CurrentBlock = $this->{'block'.$CurrentBlock['type'].'Complete'}($CurrentBlock); + } + + unset($CurrentBlock['incomplete']); + } + } + + # ~ + + $marker = $text[0]; + + # ~ + + $blockTypes = $this->unmarkedBlockTypes; + + if (isset($this->BlockTypes[$marker])) + { + foreach ($this->BlockTypes[$marker] as $blockType) + { + $blockTypes []= $blockType; + } + } + + # + # ~ + + foreach ($blockTypes as $blockType) + { + $Block = $this->{'block'.$blockType}($Line, $CurrentBlock); + + if (isset($Block)) + { + $Block['type'] = $blockType; + + if ( ! isset($Block['identified'])) + { + $Blocks []= $CurrentBlock; + + $Block['identified'] = true; + } + + if (method_exists($this, 'block'.$blockType.'Continue')) + { + $Block['incomplete'] = true; + } + + $CurrentBlock = $Block; + + continue 2; + } + } + + # ~ + + if (isset($CurrentBlock) and ! isset($CurrentBlock['type']) and ! isset($CurrentBlock['interrupted'])) + { + $CurrentBlock['element']['text'] .= "\n".$text; + } + else + { + $Blocks []= $CurrentBlock; + + $CurrentBlock = $this->paragraph($Line); + + $CurrentBlock['identified'] = true; + } + } + + # ~ + + if (isset($CurrentBlock['incomplete']) and method_exists($this, 'block'.$CurrentBlock['type'].'Complete')) + { + $CurrentBlock = $this->{'block'.$CurrentBlock['type'].'Complete'}($CurrentBlock); + } + + # ~ + + $Blocks []= $CurrentBlock; + + unset($Blocks[0]); + + # ~ + + $markup = ''; + + foreach ($Blocks as $Block) + { + if (isset($Block['hidden'])) + { + continue; + } + + $markup .= "\n"; + $markup .= isset($Block['markup']) ? $Block['markup'] : $this->element($Block['element']); + } + + $markup .= "\n"; + + # ~ + + return $markup; + } + + # + # Code + + protected function blockCode($Line, $Block = null) + { + if (isset($Block) and ! isset($Block['type']) and ! isset($Block['interrupted'])) + { + return; + } + + if ($Line['indent'] >= 4) + { + $text = substr($Line['body'], 4); + + $Block = array( + 'element' => array( + 'name' => 'pre', + 'handler' => 'element', + 'text' => array( + 'name' => 'code', + 'text' => $text, + ), + ), + ); + + return $Block; + } + } + + protected function blockCodeContinue($Line, $Block) + { + if ($Line['indent'] >= 4) + { + if (isset($Block['interrupted'])) + { + $Block['element']['text']['text'] .= "\n"; + + unset($Block['interrupted']); + } + + $Block['element']['text']['text'] .= "\n"; + + $text = substr($Line['body'], 4); + + $Block['element']['text']['text'] .= $text; + + return $Block; + } + } + + protected function blockCodeComplete($Block) + { + $text = $Block['element']['text']['text']; + + $text = htmlspecialchars($text, ENT_NOQUOTES, 'UTF-8'); + + $Block['element']['text']['text'] = $text; + + return $Block; + } + + # + # Comment + + protected function blockComment($Line) + { + if ($this->markupEscaped) + { + return; + } + + if (isset($Line['text'][3]) and $Line['text'][3] === '-' and $Line['text'][2] === '-' and $Line['text'][1] === '!') + { + $Block = array( + 'markup' => $Line['body'], + ); + + if (preg_match('/-->$/', $Line['text'])) + { + $Block['closed'] = true; + } + + return $Block; + } + } + + protected function blockCommentContinue($Line, array $Block) + { + if (isset($Block['closed'])) + { + return; + } + + $Block['markup'] .= "\n" . $Line['body']; + + if (preg_match('/-->$/', $Line['text'])) + { + $Block['closed'] = true; + } + + return $Block; + } + + # + # Fenced Code + + protected function blockFencedCode($Line) + { + if (preg_match('/^(['.$Line['text'][0].']{3,})[ ]*([\w-]+)?[ ]*$/', $Line['text'], $matches)) + { + $Element = array( + 'name' => 'code', + 'text' => '', + ); + + if (isset($matches[2])) + { + $class = 'language-'.$matches[2]; + + $Element['attributes'] = array( + 'class' => $class, + ); + } + + $Block = array( + 'char' => $Line['text'][0], + 'element' => array( + 'name' => 'pre', + 'handler' => 'element', + 'text' => $Element, + ), + ); + + return $Block; + } + } + + protected function blockFencedCodeContinue($Line, $Block) + { + if (isset($Block['complete'])) + { + return; + } + + if (isset($Block['interrupted'])) + { + $Block['element']['text']['text'] .= "\n"; + + unset($Block['interrupted']); + } + + if (preg_match('/^'.$Block['char'].'{3,}[ ]*$/', $Line['text'])) + { + $Block['element']['text']['text'] = substr($Block['element']['text']['text'], 1); + + $Block['complete'] = true; + + return $Block; + } + + $Block['element']['text']['text'] .= "\n".$Line['body'];; + + return $Block; + } + + protected function blockFencedCodeComplete($Block) + { + $text = $Block['element']['text']['text']; + + $text = htmlspecialchars($text, ENT_NOQUOTES, 'UTF-8'); + + $Block['element']['text']['text'] = $text; + + return $Block; + } + + # + # Header + + protected function blockHeader($Line) + { + if (isset($Line['text'][1])) + { + $level = 1; + + while (isset($Line['text'][$level]) and $Line['text'][$level] === '#') + { + $level ++; + } + + if ($level > 6) + { + return; + } + + $text = trim($Line['text'], '# '); + + $Block = array( + 'element' => array( + 'name' => 'h' . min(6, $level), + 'text' => $text, + 'handler' => 'line', + ), + ); + + return $Block; + } + } + + # + # List + + protected function blockList($Line) + { + list($name, $pattern) = $Line['text'][0] <= '-' ? array('ul', '[*+-]') : array('ol', '[0-9]+[.]'); + + if (preg_match('/^('.$pattern.'[ ]+)(.*)/', $Line['text'], $matches)) + { + $Block = array( + 'indent' => $Line['indent'], + 'pattern' => $pattern, + 'element' => array( + 'name' => $name, + 'handler' => 'elements', + ), + ); + + $Block['li'] = array( + 'name' => 'li', + 'handler' => 'li', + 'text' => array( + $matches[2], + ), + ); + + $Block['element']['text'] []= & $Block['li']; + + return $Block; + } + } + + protected function blockListContinue($Line, array $Block) + { + if ($Block['indent'] === $Line['indent'] and preg_match('/^'.$Block['pattern'].'(?:[ ]+(.*)|$)/', $Line['text'], $matches)) + { + if (isset($Block['interrupted'])) + { + $Block['li']['text'] []= ''; + + unset($Block['interrupted']); + } + + unset($Block['li']); + + $text = isset($matches[1]) ? $matches[1] : ''; + + $Block['li'] = array( + 'name' => 'li', + 'handler' => 'li', + 'text' => array( + $text, + ), + ); + + $Block['element']['text'] []= & $Block['li']; + + return $Block; + } + + if ($Line['text'][0] === '[' and $this->blockReference($Line)) + { + return $Block; + } + + if ( ! isset($Block['interrupted'])) + { + $text = preg_replace('/^[ ]{0,4}/', '', $Line['body']); + + $Block['li']['text'] []= $text; + + return $Block; + } + + if ($Line['indent'] > 0) + { + $Block['li']['text'] []= ''; + + $text = preg_replace('/^[ ]{0,4}/', '', $Line['body']); + + $Block['li']['text'] []= $text; + + unset($Block['interrupted']); + + return $Block; + } + } + + # + # Quote + + protected function blockQuote($Line) + { + if (preg_match('/^>[ ]?(.*)/', $Line['text'], $matches)) + { + $Block = array( + 'element' => array( + 'name' => 'blockquote', + 'handler' => 'lines', + 'text' => (array) $matches[1], + ), + ); + + return $Block; + } + } + + protected function blockQuoteContinue($Line, array $Block) + { + if ($Line['text'][0] === '>' and preg_match('/^>[ ]?(.*)/', $Line['text'], $matches)) + { + if (isset($Block['interrupted'])) + { + $Block['element']['text'] []= ''; + + unset($Block['interrupted']); + } + + $Block['element']['text'] []= $matches[1]; + + return $Block; + } + + if ( ! isset($Block['interrupted'])) + { + $Block['element']['text'] []= $Line['text']; + + return $Block; + } + } + + # + # Rule + + protected function blockRule($Line) + { + if (preg_match('/^(['.$Line['text'][0].'])([ ]*\1){2,}[ ]*$/', $Line['text'])) + { + $Block = array( + 'element' => array( + 'name' => 'hr' + ), + ); + + return $Block; + } + } + + # + # Setext + + protected function blockSetextHeader($Line, array $Block = null) + { + if ( ! isset($Block) or isset($Block['type']) or isset($Block['interrupted'])) + { + return; + } + + if (chop($Line['text'], $Line['text'][0]) === '') + { + $Block['element']['name'] = $Line['text'][0] === '=' ? 'h1' : 'h2'; + + return $Block; + } + } + + # + # Markup + + protected function blockMarkup($Line) + { + if ($this->markupEscaped) + { + return; + } + + if (preg_match('/^<(\w*)(?:[ ]*'.$this->regexHtmlAttribute.')*[ ]*(\/)?>/', $Line['text'], $matches)) + { + if (in_array($matches[1], $this->textLevelElements)) + { + return; + } + + $Block = array( + 'name' => $matches[1], + 'depth' => 0, + 'markup' => $Line['text'], + ); + + $length = strlen($matches[0]); + + $remainder = substr($Line['text'], $length); + + if (trim($remainder) === '') + { + if (isset($matches[2]) or in_array($matches[1], $this->voidElements)) + { + $Block['closed'] = true; + + $Block['void'] = true; + } + } + else + { + if (isset($matches[2]) or in_array($matches[1], $this->voidElements)) + { + return; + } + + if (preg_match('/<\/'.$matches[1].'>[ ]*$/i', $remainder)) + { + $Block['closed'] = true; + } + } + + return $Block; + } + } + + protected function blockMarkupContinue($Line, array $Block) + { + if (isset($Block['closed'])) + { + return; + } + + if (preg_match('/^<'.$Block['name'].'(?:[ ]*'.$this->regexHtmlAttribute.')*[ ]*>/i', $Line['text'])) # open + { + $Block['depth'] ++; + } + + if (preg_match('/(.*?)<\/'.$Block['name'].'>[ ]*$/i', $Line['text'], $matches)) # close + { + if ($Block['depth'] > 0) + { + $Block['depth'] --; + } + else + { + $Block['closed'] = true; + } + } + + if (isset($Block['interrupted'])) + { + $Block['markup'] .= "\n"; + + unset($Block['interrupted']); + } + + $Block['markup'] .= "\n".$Line['body']; + + return $Block; + } + + # + # Reference + + protected function blockReference($Line) + { + if (preg_match('/^\[(.+?)\]:[ ]*?(?:[ ]+["\'(](.+)["\')])?[ ]*$/', $Line['text'], $matches)) + { + $id = strtolower($matches[1]); + + $Data = array( + 'url' => $matches[2], + 'title' => null, + ); + + if (isset($matches[3])) + { + $Data['title'] = $matches[3]; + } + + $this->DefinitionData['Reference'][$id] = $Data; + + $Block = array( + 'hidden' => true, + ); + + return $Block; + } + } + + # + # Table + + protected function blockTable($Line, array $Block = null) + { + if ( ! isset($Block) or isset($Block['type']) or isset($Block['interrupted'])) + { + return; + } + + if (strpos($Block['element']['text'], '|') !== false and chop($Line['text'], ' -:|') === '') + { + $alignments = array(); + + $divider = $Line['text']; + + $divider = trim($divider); + $divider = trim($divider, '|'); + + $dividerCells = explode('|', $divider); + + foreach ($dividerCells as $dividerCell) + { + $dividerCell = trim($dividerCell); + + if ($dividerCell === '') + { + continue; + } + + $alignment = null; + + if ($dividerCell[0] === ':') + { + $alignment = 'left'; + } + + if (substr($dividerCell, - 1) === ':') + { + $alignment = $alignment === 'left' ? 'center' : 'right'; + } + + $alignments []= $alignment; + } + + # ~ + + $HeaderElements = array(); + + $header = $Block['element']['text']; + + $header = trim($header); + $header = trim($header, '|'); + + $headerCells = explode('|', $header); + + foreach ($headerCells as $index => $headerCell) + { + $headerCell = trim($headerCell); + + $HeaderElement = array( + 'name' => 'th', + 'text' => $headerCell, + 'handler' => 'line', + ); + + if (isset($alignments[$index])) + { + $alignment = $alignments[$index]; + + $HeaderElement['attributes'] = array( + 'style' => 'text-align: '.$alignment.';', + ); + } + + $HeaderElements []= $HeaderElement; + } + + # ~ + + $Block = array( + 'alignments' => $alignments, + 'identified' => true, + 'element' => array( + 'name' => 'table', + 'handler' => 'elements', + ), + ); + + $Block['element']['text'] []= array( + 'name' => 'thead', + 'handler' => 'elements', + ); + + $Block['element']['text'] []= array( + 'name' => 'tbody', + 'handler' => 'elements', + 'text' => array(), + ); + + $Block['element']['text'][0]['text'] []= array( + 'name' => 'tr', + 'handler' => 'elements', + 'text' => $HeaderElements, + ); + + return $Block; + } + } + + protected function blockTableContinue($Line, array $Block) + { + if (isset($Block['interrupted'])) + { + return; + } + + if ($Line['text'][0] === '|' or strpos($Line['text'], '|')) + { + $Elements = array(); + + $row = $Line['text']; + + $row = trim($row); + $row = trim($row, '|'); + + preg_match_all('/(?:(\\\\[|])|[^|`]|`[^`]+`|`)+/', $row, $matches); + + foreach ($matches[0] as $index => $cell) + { + $cell = trim($cell); + + $Element = array( + 'name' => 'td', + 'handler' => 'line', + 'text' => $cell, + ); + + if (isset($Block['alignments'][$index])) + { + $Element['attributes'] = array( + 'style' => 'text-align: '.$Block['alignments'][$index].';', + ); + } + + $Elements []= $Element; + } + + $Element = array( + 'name' => 'tr', + 'handler' => 'elements', + 'text' => $Elements, + ); + + $Block['element']['text'][1]['text'] []= $Element; + + return $Block; + } + } + + # + # ~ + # + + protected function paragraph($Line) + { + $Block = array( + 'element' => array( + 'name' => 'p', + 'text' => $Line['text'], + 'handler' => 'line', + ), + ); + + return $Block; + } + + # + # Inline Elements + # + + protected $InlineTypes = array( + '"' => array('SpecialCharacter'), + '!' => array('Image'), + '&' => array('SpecialCharacter'), + '*' => array('Emphasis'), + ':' => array('Url'), + '<' => array('UrlTag', 'EmailTag', 'Markup', 'SpecialCharacter'), + '>' => array('SpecialCharacter'), + '[' => array('Link'), + '_' => array('Emphasis'), + '`' => array('Code'), + '~' => array('Strikethrough'), + '\\' => array('EscapeSequence'), + ); + + # ~ + + protected $inlineMarkerList = '!"*_&[:<>`~\\'; + + # + # ~ + # + + public function line($text) + { + $markup = ''; + + $unexaminedText = $text; + + $markerPosition = 0; + + while ($excerpt = strpbrk($unexaminedText, $this->inlineMarkerList)) + { + $marker = $excerpt[0]; + + $markerPosition += strpos($unexaminedText, $marker); + + $Excerpt = array('text' => $excerpt, 'context' => $text); + + foreach ($this->InlineTypes[$marker] as $inlineType) + { + $Inline = $this->{'inline'.$inlineType}($Excerpt); + + if ( ! isset($Inline)) + { + continue; + } + + if (isset($Inline['position']) and $Inline['position'] > $markerPosition) # position is ahead of marker + { + continue; + } + + if ( ! isset($Inline['position'])) + { + $Inline['position'] = $markerPosition; + } + + $unmarkedText = substr($text, 0, $Inline['position']); + + $markup .= $this->unmarkedText($unmarkedText); + + $markup .= isset($Inline['markup']) ? $Inline['markup'] : $this->element($Inline['element']); + + $text = substr($text, $Inline['position'] + $Inline['extent']); + + $unexaminedText = $text; + + $markerPosition = 0; + + continue 2; + } + + $unexaminedText = substr($excerpt, 1); + + $markerPosition ++; + } + + $markup .= $this->unmarkedText($text); + + return $markup; + } + + # + # ~ + # + + protected function inlineCode($Excerpt) + { + $marker = $Excerpt['text'][0]; + + if (preg_match('/^('.$marker.'+)[ ]*(.+?)[ ]*(? strlen($matches[0]), + 'element' => array( + 'name' => 'code', + 'text' => $text, + ), + ); + } + } + + protected function inlineEmailTag($Excerpt) + { + if (strpos($Excerpt['text'], '>') !== false and preg_match('/^<((mailto:)?\S+?@\S+?)>/i', $Excerpt['text'], $matches)) + { + $url = $matches[1]; + + if ( ! isset($matches[2])) + { + $url = 'mailto:' . $url; + } + + return array( + 'extent' => strlen($matches[0]), + 'element' => array( + 'name' => 'a', + 'text' => $matches[1], + 'attributes' => array( + 'href' => $url, + ), + ), + ); + } + } + + protected function inlineEmphasis($Excerpt) + { + if ( ! isset($Excerpt['text'][1])) + { + return; + } + + $marker = $Excerpt['text'][0]; + + if ($Excerpt['text'][1] === $marker and preg_match($this->StrongRegex[$marker], $Excerpt['text'], $matches)) + { + $emphasis = 'strong'; + } + elseif (preg_match($this->EmRegex[$marker], $Excerpt['text'], $matches)) + { + $emphasis = 'em'; + } + else + { + return; + } + + return array( + 'extent' => strlen($matches[0]), + 'element' => array( + 'name' => $emphasis, + 'handler' => 'line', + 'text' => $matches[1], + ), + ); + } + + protected function inlineEscapeSequence($Excerpt) + { + if (isset($Excerpt['text'][1]) and in_array($Excerpt['text'][1], $this->specialCharacters)) + { + return array( + 'markup' => $Excerpt['text'][1], + 'extent' => 2, + ); + } + } + + protected function inlineImage($Excerpt) + { + if ( ! isset($Excerpt['text'][1]) or $Excerpt['text'][1] !== '[') + { + return; + } + + $Excerpt['text']= substr($Excerpt['text'], 1); + + $Link = $this->inlineLink($Excerpt); + + if ($Link === null) + { + return; + } + + $Inline = array( + 'extent' => $Link['extent'] + 1, + 'element' => array( + 'name' => 'img', + 'attributes' => array( + 'src' => $Link['element']['attributes']['href'], + 'alt' => $Link['element']['text'], + ), + ), + ); + + $Inline['element']['attributes'] += $Link['element']['attributes']; + + unset($Inline['element']['attributes']['href']); + + return $Inline; + } + + protected function inlineLink($Excerpt) + { + $Element = array( + 'name' => 'a', + 'handler' => 'line', + 'text' => null, + 'attributes' => array( + 'href' => null, + 'title' => null, + ), + ); + + $extent = 0; + + $remainder = $Excerpt['text']; + + if (preg_match('/\[((?:[^][]|(?R))*)\]/', $remainder, $matches)) + { + $Element['text'] = $matches[1]; + + $extent += strlen($matches[0]); + + $remainder = substr($remainder, $extent); + } + else + { + return; + } + + if (preg_match('/^[(]((?:[^ ()]|[(][^ )]+[)])+)(?:[ ]+("[^"]*"|\'[^\']*\'))?[)]/', $remainder, $matches)) + { + $Element['attributes']['href'] = $matches[1]; + + if (isset($matches[2])) + { + $Element['attributes']['title'] = substr($matches[2], 1, - 1); + } + + $extent += strlen($matches[0]); + } + else + { + if (preg_match('/^\s*\[(.*?)\]/', $remainder, $matches)) + { + $definition = $matches[1] ? $matches[1] : $Element['text']; + $definition = strtolower($definition); + + $extent += strlen($matches[0]); + } + else + { + $definition = strtolower($Element['text']); + } + + if ( ! isset($this->DefinitionData['Reference'][$definition])) + { + return; + } + + $Definition = $this->DefinitionData['Reference'][$definition]; + + $Element['attributes']['href'] = $Definition['url']; + $Element['attributes']['title'] = $Definition['title']; + } + + $Element['attributes']['href'] = str_replace(array('&', '<'), array('&', '<'), $Element['attributes']['href']); + + return array( + 'extent' => $extent, + 'element' => $Element, + ); + } + + protected function inlineMarkup($Excerpt) + { + if ($this->markupEscaped or strpos($Excerpt['text'], '>') === false) + { + return; + } + + if ($Excerpt['text'][1] === '/' and preg_match('/^<\/\w*[ ]*>/s', $Excerpt['text'], $matches)) + { + return array( + 'markup' => $matches[0], + 'extent' => strlen($matches[0]), + ); + } + + if ($Excerpt['text'][1] === '!' and preg_match('/^/s', $Excerpt['text'], $matches)) + { + return array( + 'markup' => $matches[0], + 'extent' => strlen($matches[0]), + ); + } + + if ($Excerpt['text'][1] !== ' ' and preg_match('/^<\w*(?:[ ]*'.$this->regexHtmlAttribute.')*[ ]*\/?>/s', $Excerpt['text'], $matches)) + { + return array( + 'markup' => $matches[0], + 'extent' => strlen($matches[0]), + ); + } + } + + protected function inlineSpecialCharacter($Excerpt) + { + if ($Excerpt['text'][0] === '&' and ! preg_match('/^&#?\w+;/', $Excerpt['text'])) + { + return array( + 'markup' => '&', + 'extent' => 1, + ); + } + + $SpecialCharacter = array('>' => 'gt', '<' => 'lt', '"' => 'quot'); + + if (isset($SpecialCharacter[$Excerpt['text'][0]])) + { + return array( + 'markup' => '&'.$SpecialCharacter[$Excerpt['text'][0]].';', + 'extent' => 1, + ); + } + } + + protected function inlineStrikethrough($Excerpt) + { + if ( ! isset($Excerpt['text'][1])) + { + return; + } + + if ($Excerpt['text'][1] === '~' and preg_match('/^~~(?=\S)(.+?)(?<=\S)~~/', $Excerpt['text'], $matches)) + { + return array( + 'extent' => strlen($matches[0]), + 'element' => array( + 'name' => 'del', + 'text' => $matches[1], + 'handler' => 'line', + ), + ); + } + } + + protected function inlineUrl($Excerpt) + { + if ($this->urlsLinked !== true or ! isset($Excerpt['text'][2]) or $Excerpt['text'][2] !== '/') + { + return; + } + + if (preg_match('/\bhttps?:[\/]{2}[^\s<]+\b\/*/ui', $Excerpt['context'], $matches, PREG_OFFSET_CAPTURE)) + { + $Inline = array( + 'extent' => strlen($matches[0][0]), + 'position' => $matches[0][1], + 'element' => array( + 'name' => 'a', + 'text' => $matches[0][0], + 'attributes' => array( + 'href' => $matches[0][0], + ), + ), + ); + + return $Inline; + } + } + + protected function inlineUrlTag($Excerpt) + { + if (strpos($Excerpt['text'], '>') !== false and preg_match('/^<(\w+:\/{2}[^ >]+)>/i', $Excerpt['text'], $matches)) + { + $url = str_replace(array('&', '<'), array('&', '<'), $matches[1]); + + return array( + 'extent' => strlen($matches[0]), + 'element' => array( + 'name' => 'a', + 'text' => $url, + 'attributes' => array( + 'href' => $url, + ), + ), + ); + } + } + + # ~ + + protected function unmarkedText($text) + { + if ($this->breaksEnabled) + { + $text = preg_replace('/[ ]*\n/', "
      \n", $text); + } + else + { + $text = preg_replace('/(?:[ ][ ]+|[ ]*\\\\)\n/', "
      \n", $text); + $text = str_replace(" \n", "\n", $text); + } + + return $text; + } + + # + # Handlers + # + + protected function element(array $Element) + { + $markup = '<'.$Element['name']; + + if (isset($Element['attributes'])) + { + foreach ($Element['attributes'] as $name => $value) + { + if ($value === null) + { + continue; + } + + $markup .= ' '.$name.'="'.$value.'"'; + } + } + + if (isset($Element['text'])) + { + $markup .= '>'; + + if (isset($Element['handler'])) + { + $markup .= $this->{$Element['handler']}($Element['text']); + } + else + { + $markup .= $Element['text']; + } + + $markup .= ''; + } + else + { + $markup .= ' />'; + } + + return $markup; + } + + protected function elements(array $Elements) + { + $markup = ''; + + foreach ($Elements as $Element) + { + $markup .= "\n" . $this->element($Element); + } + + $markup .= "\n"; + + return $markup; + } + + # ~ + + protected function li($lines) + { + $markup = $this->lines($lines); + + $trimmedMarkup = trim($markup); + + if ( ! in_array('', $lines) and substr($trimmedMarkup, 0, 3) === '

      ') + { + $markup = $trimmedMarkup; + $markup = substr($markup, 3); + + $position = strpos($markup, "

      "); + + $markup = substr_replace($markup, '', $position, 4); + } + + return $markup; + } + + # + # Deprecated Methods + # + + function parse($text) + { + $markup = $this->text($text); + + return $markup; + } + + # + # Static Methods + # + + static function instance($name = 'default') + { + if (isset(self::$instances[$name])) + { + return self::$instances[$name]; + } + + $instance = new self(); + + self::$instances[$name] = $instance; + + return $instance; + } + + private static $instances = array(); + + # + # Fields + # + + protected $DefinitionData; + + # + # Read-Only + + protected $specialCharacters = array( + '\\', '`', '*', '_', '{', '}', '[', ']', '(', ')', '>', '#', '+', '-', '.', '!', '|', + ); + + protected $StrongRegex = array( + '*' => '/^[*]{2}((?:\\\\\*|[^*]|[*][^*]*[*])+?)[*]{2}(?![*])/s', + '_' => '/^__((?:\\\\_|[^_]|_[^_]*_)+?)__(?!_)/us', + ); + + protected $EmRegex = array( + '*' => '/^[*]((?:\\\\\*|[^*]|[*][*][^*]+?[*][*])+?)[*](?![*])/s', + '_' => '/^_((?:\\\\_|[^_]|__[^_]*__)+?)_(?!_)\b/us', + ); + + protected $regexHtmlAttribute = '[a-zA-Z_:][\w:.-]*(?:\s*=\s*(?:[^"\'=<>`\s]+|"[^"]*"|\'[^\']*\'))?'; + + protected $voidElements = array( + 'area', 'base', 'br', 'col', 'command', 'embed', 'hr', 'img', 'input', 'link', 'meta', 'param', 'source', + ); + + protected $textLevelElements = array( + 'a', 'br', 'bdo', 'abbr', 'blink', 'nextid', 'acronym', 'basefont', + 'b', 'em', 'big', 'cite', 'small', 'spacer', 'listing', + 'i', 'rp', 'del', 'code', 'strike', 'marquee', + 'q', 'rt', 'ins', 'font', 'strong', + 's', 'tt', 'sub', 'mark', + 'u', 'xm', 'sup', 'nobr', + 'var', 'ruby', + 'wbr', 'span', + 'time', + ); +} diff --git a/library/parsedown/README.md b/library/parsedown/README.md new file mode 100644 index 000000000..8d485e7d2 --- /dev/null +++ b/library/parsedown/README.md @@ -0,0 +1,48 @@ +## Parsedown + +Better Markdown Parser in PHP + +[[ demo ]](http://parsedown.org/demo) + +### Features + +* [Fast](http://parsedown.org/speed) +* [Consistent](http://parsedown.org/consistency) +* [GitHub flavored](https://help.github.com/articles/github-flavored-markdown) +* [Tested](http://parsedown.org/tests/) in PHP 5.2, 5.3, 5.4, 5.5, 5.6 and [hhvm](http://www.hhvm.com/) +* [Extensible](https://github.com/erusev/parsedown/wiki/Writing-Extensions) +* [Markdown Extra extension](https://github.com/erusev/parsedown-extra) + +### Installation + +Include `Parsedown.php` or install [the composer package](https://packagist.org/packages/erusev/parsedown). + +### Example + +``` php +$Parsedown = new Parsedown(); + +echo $Parsedown->text('Hello _Parsedown_!'); # prints:

      Hello Parsedown!

      +``` + +More examples in [the wiki](https://github.com/erusev/parsedown/wiki/Usage) and in [this video tutorial](http://youtu.be/wYZBY8DEikI). + +### Questions + +**How does Parsedown work?** + +It tries to read Markdown like a human. First, it looks at the lines. It’s interested in how the lines start. This helps it recognise blocks. It knows, for example, that if a line start with a `-` then it perhaps belong to a list. Once it recognises the blocks, it continues to the content. As it reads, it watches out for special characters. This helps it recognise inline elements (or inlines). + +We call this approach "line based". We believe that Parsedown is the first Markdown parser to use it. Since the release of Parsedown, other developers have used the same approach to develop other Markdown parsers in PHP and in other languages. + +**Is it compliant with CommonMark?** + +It passes most of the CommonMark tests. Most of the tests that don't pass deal with cases that are quite uncommon. Still, as CommonMark matures, compliance should improve. + +**Who uses it?** + +[phpDocumentor](http://www.phpdoc.org/), [October CMS](http://octobercms.com/), [Bolt CMS](http://bolt.cm/), [Kirby CMS](http://getkirby.com/), [Grav CMS](http://getgrav.org/), [Statamic CMS](http://www.statamic.com/), [RaspberryPi.org](http://www.raspberrypi.org/) and [more](https://www.versioneye.com/php/erusev:parsedown/references). + +**How can I help?** + +Use it, star it, share it and if you feel generous, [donate some money](https://www.paypal.com/cgi-bin/webscr?cmd=_s-xclick&hosted_button_id=528P3NZQMP8N2).