Modules

Kohana_Kodoc_Markdown
extends MarkdownExtra_Parser
extends Markdown_Parser

Custom Markdown parser for Kohana documentation.

package
Kohana/Userguide
category
Base
author
Kohana Team
copyright
© 2009-2012 Kohana Team
license
http://kohanaphp.com/license

Class declared in MODPATH/userguide/classes/kohana/kodoc/markdown.php on line 11.

Constants

  • None

Methods

Properties

public $abbr_desciptions

public $abbr_word_re

public $auto_close_tags_re

public static string $base_url

base url for links

string(11) "/3.2/guide/"

public $block_gamut

public $block_tags_re

public $clean_tags_re

public $contain_span_tags_re

public $context_block_tags_re

public $document_gamut

public $em_relist

public $em_strong_prepared_relist

public $em_strong_relist

public $empty_element_suffix

public $escape_chars

public $escape_chars_re

public $fn_id_prefix

public $footnote_counter

public $footnotes

public $footnotes_ordered

public $html_hashes

public static string $image_url

base url for images

string(17) "/3.2/guide/media/"

public $in_anchor

public $list_level

public $nested_brackets_depth

public $nested_brackets_re

public $nested_url_parenthesis_depth

public $nested_url_parenthesis_re

public $no_entities

public $no_markup

public $predef_abbr

public $predef_titles

public $predef_urls

public static $show_toc

Slightly less terrible way to make it so the TOC only shows up when we want it to. set this to true to show the toc.

bool FALSE

public $span_gamut

public $strong_relist

public $tab_width

public $titles

public $urls

public $utf8_strlen

protected array $_heading_ids

Currently defined heading ids.
Used to prevent creating multiple headings with same id.

protected static string $_toc

the generated table of contents

array(22) (
    0 => array(3) (
        "level" => integer 3
        "name" => string(23) "Supported cache engines"
        "id" => string(23) "supported-cache-engines"
    )
    1 => array(3) (
        "level" => integer 3
        "name" => string(23) "Introduction to caching"
        "id" => string(23) "introduction-to-caching"
    )
    2 => array(3) (
        "level" => integer 3
        "name" => string(22) "Configuration settings"
        "id" => string(22) "configuration-settings"
    )
    3 => array(3) (
        "level" => integer 4
        "name" => string(21) "Configuration example"
        "id" => string(21) "configuration-example"
    )
    4 => array(3) (
        "level" => integer 4
        "name" => string(42) "General cache group configuration settings"
        "id" => string(42) "general-cache-group-configuration-settings"
    )
    5 => array(3) (
        "level" => integer 3
        "name" => string(19) "System requirements"
        "id" => string(19) "system-requirements"
    )
    6 => array(3) (
        "level" => integer 3
        "name" => string(21) "Configuration example"
        "id" => string(21) "configuration-example"
    )
    7 => array(3) (
        "level" => integer 4
        "name" => string(42) "General cache group configuration settings"
        "id" => string(42) "general-cache-group-configuration-settings"
    )
    8 => array(3) (
        "level" => integer 3
        "name" => string(19) "System requirements"
        "id" => string(19) "system-requirements"
    )
    9 => array(3) (
        "level" => integer 3
        "name" => string(21) "Configuration example"
        "id" => string(21) "configuration-example"
    )
    10 => array(3) (
        "level" => integer 4
        "name" => string(42) "General cache group configuration settings"
        "id" => string(42) "general-cache-group-configuration-settings"
    )
    11 => array(3) (
        "level" => integer 3
        "name" => string(19) "System requirements"
        "id" => string(19) "system-requirements"
    )
    12 => array(3) (
        "level" => integer 3
        "name" => string(23) "Supported cache engines"
        "id" => string(23) "supported-cache-engines"
    )
    13 => array(3) (
        "level" => integer 3
        "name" => string(21) "Configuration example"
        "id" => string(21) "configuration-example"
    )
    14 => array(3) (
        "level" => integer 4
        "name" => string(42) "General cache group configuration settings"
        "id" => string(42) "general-cache-group-configuration-settings"
    )
    15 => array(3) (
        "level" => integer 4
        "name" => string(29) "Memcache server configuration"
        "id" => string(29) "memcache-server-configuration"
    )
    16 => array(3) (
        "level" => integer 3
        "name" => string(19) "System requirements"
        "id" => string(19) "system-requirements"
    )
    17 => array(3) (
        "level" => integer 3
        "name" => string(21) "Configuration example"
        "id" => string(21) "configuration-example"
    )
    18 => array(3) (
        "level" => integer 4
        "name" => string(42) "General cache group configuration settings"
        "id" => string(42) "general-cache-group-configuration-settings"
    )
    19 => array(3) (
        "level" => integer 3
        "name" => string(19) "System requirements"
        "id" => string(19) "system-requirements"
    )
    20 => array(3) (
        "level" => integer 1
        "name" => string(9) "Heading 1"
        "id" => string(9) "heading-1"
    )
    21 => array(3) (
        "level" => integer 1
        "name" => string(9) "Heading 1"
        "id" => string(9) "heading-1"
    )
)

Methods

public __construct( ) (defined in Kohana_Kodoc_Markdown)

Source Code

public function __construct()
{
	// doImage is 10, add image url just before
	$this->span_gamut['doImageURL'] = 9;

	// doLink is 20, add base url just before
	$this->span_gamut['doBaseURL'] = 19;

	// Add API links
	$this->span_gamut['doAPI'] = 90;

	// Add note spans last
	$this->span_gamut['doNotes'] = 100;

	// Parse Kohana view inclusions at the very end
	$this->document_gamut['doIncludeViews'] = 99;

	// Show table of contents for userguide pages
	$this->document_gamut['doTOC'] = 100;

	// PHP4 makes me sad.
	parent::MarkdownExtra_Parser();
}

public _doHeaders_callback_atx( array $matches ) (defined in Kohana_Kodoc_Markdown)

Callback for the heading atx style

Heading 1

Parameters

  • array $matches required - Matches from regex call

Return Values

  • string - Generated html

Source Code

function _doHeaders_callback_atx($matches) 
{
	$level = strlen($matches[1]);
	$attr  = $this->_doHeaders_attr($id =& $matches[3]);
	
	// Only auto-generate id if one doesn't exist
	if(empty($attr))
		$attr = ' id="'.$this->make_heading_id($matches[2]).'"';
	
	// Add this header to the page toc
	$this->_add_to_toc($level, $matches[2], $this->make_heading_id(empty($matches[3]) ? $matches[2] : $matches[3]));
	
	$block = "<h$level$attr>".$this->runSpanGamut($matches[2])."</h$level>";
	return "\n" . $this->hashBlock($block) . "\n\n";
}

public _doHeaders_callback_setext( array $matches ) (defined in Kohana_Kodoc_Markdown)

Callback for the heading setext style

Heading 1

Parameters

  • array $matches required - Matches from regex call

Return Values

  • string - Generated html

Source Code

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]);
	
	// Only auto-generate id if one doesn't exist
	if(empty($attr))
		$attr = ' id="'.$this->make_heading_id($matches[1]).'"';
	
	// Add this header to the page toc
	$this->_add_to_toc($level,$matches[1],$this->make_heading_id($matches[1]));
	
	$block = "<h$level$attr>".$this->runSpanGamut($matches[1])."</h$level>";
	return "\n" . $this->hashBlock($block) . "\n\n";
}

public doAPI( string $text ) (defined in Kohana_Kodoc_Markdown)

Parses links to the API browser.

[Class_Name], [Class::method] or [Class::$property]

Parameters

  • string $text required - Span text

Return Values

  • string

Source Code

public function doAPI($text)
{
	return preg_replace_callback('/\['.Kodoc::$regex_class_member.'\]/i', 'Kodoc::link_class_member', $text);
}

public doBaseURL( string $text ) (defined in Kohana_Kodoc_Markdown)

Add the current base url to all local links.

[filesystem](about.filesystem "Optional title")

Parameters

  • string $text required - Span text

Return Values

  • string

Source Code

public function doBaseURL($text)
{
	// URLs containing "://" are left untouched
	return preg_replace('~(?<!!)(\[.+?\]\()(?!\w++://)(?!#)(\S*(?:\s*+".+?")?\))~', '$1'.Kodoc_Markdown::$base_url.'$2', $text);
}

public doImageURL( string $text ) (defined in Kohana_Kodoc_Markdown)

Add the current base url to all local images.

![Install Page](img/install.png "Optional title")

Parameters

  • string $text required - Span text

Return Values

  • string

Source Code

public function doImageURL($text)
{
	// URLs containing "://" are left untouched
	return preg_replace('~(!\[.+?\]\()(?!\w++://)(\S*(?:\s*+".+?")?\))~', '$1'.Kodoc_Markdown::$image_url.'$2', $text);
}

public doIncludeViews( ) (defined in Kohana_Kodoc_Markdown)

Source Code

public function doIncludeViews($text)
{
	if (preg_match_all('/{{([^\s{}]++)}}/', $text, $matches, PREG_SET_ORDER))
	{
		$replace = array();

		$replace = array();

		foreach ($matches as $set)
		{
			list($search, $view) = $set;

			if (Kohana::find_file('views', $view))
			{
				try
				{
					$replace[$search] = View::factory($view)->render();
				}
				catch (Exception $e)
				{
					ob_start();

					// Capture the exception handler output and insert it instead
					Kohana_exception::handler($e);

					$replace[$search] = ob_get_clean();
				}
			}
		}

		$text = strtr($text, $replace);
	}

	return $text;
}

public doNotes( string $text ) (defined in Kohana_Kodoc_Markdown)

Wrap notes in the applicable markup. Notes can contain single newlines.

[!!] Remember the milk!

Parameters

  • string $text required - Span text

Return Values

  • string

Source Code

public function doNotes($text)
{
	if ( ! preg_match('/^\[!!\]\s*+(.+?)(?=\n{2,}|$)/s', $text, $match))
	{
		return $text;
	}

	return $this->hashBlock('<p class="note">'.$match[1].'</p>');
}

public doTOC( ) (defined in Kohana_Kodoc_Markdown)

Source Code

public function doTOC($text)
{
	// Only add the toc do userguide pages, not api since they already have one
	if (self::$show_toc AND Route::name(Request::current()->route()) == "docs/guide")
	{
		$toc = View::factory('userguide/page-toc')
			->set('array', self::$_toc)
			->render()
			;

		if (($offset = strpos($text, '<p>')) !== FALSE)
		{
			// Insert the page TOC just before the first <p>, which every
			// Markdown page should (will?) have.
			$text = substr_replace($text, $toc, $offset, 0);
		}
	}

	return $text;
}

public make_heading_id( string $heading ) (defined in Kohana_Kodoc_Markdown)

Makes a heading id from the heading text If any heading share the same name then subsequent headings will have an integer appended

Parameters

  • string $heading required - The heading text

Return Values

  • string - ID for the heading

Source Code

function make_heading_id($heading)
{
	$id = url::title($heading, '-', TRUE);
	
	if(isset($this->_heading_ids[$id]))
	{
		$id .= '-';
		
		$count = 0;
		
		while (isset($this->_heading_ids[$id]) AND ++$count)
		{
			$id .= $count;
		}
	}		
	
	return $id;
}

public static markdown( string $text ) (defined in Kohana_Kodoc_Markdown)

Transform some text using Kodoc_Markdown

Parameters

  • string $text required - Text to parse

Tags

  • See - Markdown()

Return Values

  • string - Transformed text

Source Code

public static function markdown($text)
{
	static $instance;

	if ($instance === NULL)
	{
		$instance = new Kodoc_Markdown;
	}

	return $instance->transform($text);
}

public MarkdownExtra_Parser( ) (defined in MarkdownExtra_Parser)

Source Code

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();
}

public _appendFootnotes_callback( ) (defined in MarkdownExtra_Parser)

Source Code

function _appendFootnotes_callback($matches) {
	$node_id = $this->fn_id_prefix . $matches[1];
	
	# Create footnote marker only if it has a corresponding footnote *and*
	# the footnote hasn't been used by another marker.
	if (isset($this->footnotes[$node_id])) {
		# Transfert footnote content to the ordered list.
		$this->footnotes_ordered[$node_id] = $this->footnotes[$node_id];
		unset($this->footnotes[$node_id]);
		
		$num = $this->footnote_counter++;
		$attr = " rel=\"footnote\"";
		if ($this->fn_link_class != "") {
			$class = $this->fn_link_class;
			$class = $this->encodeAttribute($class);
			$attr .= " class=\"$class\"";
		}
		if ($this->fn_link_title != "") {
			$title = $this->fn_link_title;
			$title = $this->encodeAttribute($title);
			$attr .= " title=\"$title\"";
		}
		
		$attr = str_replace("%%", $num, $attr);
		$node_id = $this->encodeAttribute($node_id);
		
		return
			"<sup id=\"fnref:$node_id\">".
			"<a href=\"#fn:$node_id\"$attr>$num</a>".
			"</sup>";
	}
	
	return "[^".$matches[1]."]";
}

public _doAbbreviations_callback( ) (defined in MarkdownExtra_Parser)

Source Code

function _doAbbreviations_callback($matches) {
	$abbr = $matches[0];
	if (isset($this->abbr_desciptions[$abbr])) {
		$desc = $this->abbr_desciptions[$abbr];
		if (empty($desc)) {
			return $this->hashPart("<abbr>$abbr</abbr>");
		} else {
			$desc = $this->encodeAttribute($desc);
			return $this->hashPart("<abbr title=\"$desc\">$abbr</abbr>");
		}
	} else {
		return $matches[0];
	}
}

public _doDefLists_callback( ) (defined in MarkdownExtra_Parser)

Source Code

function _doDefLists_callback($matches) {
	# Re-usable patterns to match list item bullets and number markers:
	$list = $matches[1];
	
	# Turn double returns into triple returns, so that we can make a
	# paragraph for the last item in a list, if necessary:
	$result = trim($this->processDefListItems($list));
	$result = "<dl>\n" . $result . "\n</dl>";
	return $this->hashBlock($result) . "\n\n";
}

public _doFencedCodeBlocks_callback( ) (defined in MarkdownExtra_Parser)

Source Code

function _doFencedCodeBlocks_callback($matches) {
	$codeblock = $matches[2];
	$codeblock = htmlspecialchars($codeblock, ENT_NOQUOTES);
	$codeblock = preg_replace_callback('/^\n+/',
		array(&$this, '_doFencedCodeBlocks_newlines'), $codeblock);
	$codeblock = "<pre><code>$codeblock</code></pre>";
	return "\n\n".$this->hashBlock($codeblock)."\n\n";
}

public _doFencedCodeBlocks_newlines( ) (defined in MarkdownExtra_Parser)

Source Code

function _doFencedCodeBlocks_newlines($matches) {
	return str_repeat("<br$this->empty_element_suffix", 
		strlen($matches[0]));
}

public _doHeaders_attr( ) (defined in MarkdownExtra_Parser)

Source Code

function _doHeaders_attr($attr) {
	if (empty($attr))  return "";
	return " id=\"$attr\"";
}

public _doTable_callback( ) (defined in MarkdownExtra_Parser)

Source Code

function _doTable_callback($matches) {
	$head		= $matches[1];
	$underline	= $matches[2];
	$content	= $matches[3];

	# Remove any tailing pipes for each line.
	$head		= preg_replace('/[|] *$/m', '', $head);
	$underline	= preg_replace('/[|] *$/m', '', $underline);
	$content	= preg_replace('/[|] *$/m', '', $content);
	
	# Reading alignement from header underline.
	$separators	= preg_split('/ *[|] */', $underline);
	foreach ($separators as $n => $s) {
		if (preg_match('/^ *-+: *$/', $s))		$attr[$n] = ' align="right"';
		else if (preg_match('/^ *:-+: *$/', $s))$attr[$n] = ' align="center"';
		else if (preg_match('/^ *:-+ *$/', $s))	$attr[$n] = ' align="left"';
		else									$attr[$n] = '';
	}
	
	# Parsing span elements, including code spans, character escapes, 
	# and inline HTML tags, so that pipes inside those gets ignored.
	$head		= $this->parseSpan($head);
	$headers	= preg_split('/ *[|] */', $head);
	$col_count	= count($headers);
	
	# Write column headers.
	$text = "<table>\n";
	$text .= "<thead>\n";
	$text .= "<tr>\n";
	foreach ($headers as $n => $header)
		$text .= "  <th$attr[$n]>".$this->runSpanGamut(trim($header))."</th>\n";
	$text .= "</tr>\n";
	$text .= "</thead>\n";
	
	# Split content by row.
	$rows = explode("\n", trim($content, "\n"));
	
	$text .= "<tbody>\n";
	foreach ($rows as $row) {
		# Parsing span elements, including code spans, character escapes, 
		# and inline HTML tags, so that pipes inside those gets ignored.
		$row = $this->parseSpan($row);
		
		# Split row by cell.
		$row_cells = preg_split('/ *[|] */', $row, $col_count);
		$row_cells = array_pad($row_cells, $col_count, '');
		
		$text .= "<tr>\n";
		foreach ($row_cells as $n => $cell)
			$text .= "  <td$attr[$n]>".$this->runSpanGamut(trim($cell))."</td>\n";
		$text .= "</tr>\n";
	}
	$text .= "</tbody>\n";
	$text .= "</table>";
	
	return $this->hashBlock($text) . "\n";
}

public _doTable_leadingPipe_callback( ) (defined in MarkdownExtra_Parser)

Source Code

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));
}

public _hashHTMLBlocks_inHTML( ) (defined in MarkdownExtra_Parser)

Source Code

function _hashHTMLBlocks_inHTML($text, $hash_method, $md_attr) {
#
# Parse HTML, calling _HashHTMLBlocks_InMarkdown for block tags.
#
# *   Calls $hash_method to convert any blocks.
# *   Stops when the first opening tag closes.
# *   $md_attr indicate if the use of the `markdown="1"` attribute is allowed.
#     (it is not inside clean tags)
#
# Returns an array of that form: ( processed text , remaining text )
#
	if ($text === '') return array('', '');
	
	# Regex to match `markdown` attribute inside of a tag.
	$markdown_attr_re = '
		{
			\s*			# Eat whitespace before the `markdown` attribute
			markdown
			\s*=\s*
			(?>
				(["\'])		# $1: quote delimiter		
				(.*?)		# $2: attribute value
				\1			# matching delimiter	
			|
				([^\s>]*)	# $3: unquoted attribute value
			)
			()				# $4: make $3 always defined (avoid warnings)
		}xs';
	
	# Regex to match any tag.
	$tag_re = '{
			(					# $2: Capture hole tag.
				</?					# Any opening or closing tag.
					[\w:$]+			# Tag name.
					(?:
						(?=[\s"\'/a-zA-Z0-9])	# Allowed characters after tag name.
						(?>
							".*?"		|	# Double quotes (can contain `>`)
							\'.*?\'   	|	# Single quotes (can contain `>`)
							.+?				# Anything but quotes and `>`.
						)*?
					)?
				>					# End of tag.
			|
				<!--    .*?     -->	# HTML Comment
			|
				<\?.*?\?> | <%.*?%>	# Processing instruction
			|
				<!\[CDATA\[.*?\]\]>	# CData Block
			)
		}xs';
	
	$original_text = $text;		# Save original text in case of faliure.
	
	$depth		= 0;	# Current depth inside the tag tree.
	$block_text	= "";	# Temporary text holder for current text.
	$parsed		= "";	# Parsed text that will be returned.

	#
	# Get the name of the starting tag.
	# (This pattern makes $base_tag_name_re safe without quoting.)
	#
	if (preg_match('/^<([\w:$]*)\b/', $text, $matches))
		$base_tag_name_re = $matches[1];

	#
	# Loop through every tag until we find the corresponding closing tag.
	#
	do {
		#
		# Split the text using the first $tag_match pattern found.
		# Text before  pattern will be first in the array, text after
		# pattern will be at the end, and between will be any catches made 
		# by the pattern.
		#
		$parts = preg_split($tag_re, $text, 2, PREG_SPLIT_DELIM_CAPTURE);
		
		if (count($parts) < 3) {
			#
			# End of $text reached with unbalenced tag(s).
			# In that case, we return original text unchanged and pass the
			# first character as filtered to prevent an infinite loop in the 
			# parent function.
			#
			return array($original_text{0}, substr($original_text, 1));
		}
		
		$block_text .= $parts[0]; # Text before current tag.
		$tag         = $parts[1]; # Tag to handle.
		$text        = $parts[2]; # Remaining text after current tag.
		
		#
		# Check for: Auto-close tag (like <hr/>)
		#			 Comments and Processing Instructions.
		#
		if (preg_match('{^</?(?:'.$this->auto_close_tags_re.')\b}', $tag) ||
			$tag{1} == '!' || $tag{1} == '?')
		{
			# Just add the tag to the block as if it was text.
			$block_text .= $tag;
		}
		else {
			#
			# Increase/decrease nested tag count. Only do so if
			# the tag's name match base tag's.
			#
			if (preg_match('{^</?'.$base_tag_name_re.'\b}', $tag)) {
				if ($tag{1} == '/')						$depth--;
				else if ($tag{strlen($tag)-2} != '/')	$depth++;
			}
			
			#
			# Check for `markdown="1"` attribute and handle it.
			#
			if ($md_attr && 
				preg_match($markdown_attr_re, $tag, $attr_m) &&
				preg_match('/^1|block|span$/', $attr_m[2] . $attr_m[3]))
			{
				# Remove `markdown` attribute from opening tag.
				$tag = preg_replace($markdown_attr_re, '', $tag);
				
				# Check if text inside this tag must be parsed in span mode.
				$this->mode = $attr_m[2] . $attr_m[3];
				$span_mode = $this->mode == 'span' || $this->mode != 'block' &&
					preg_match('{^<(?:'.$this->contain_span_tags_re.')\b}', $tag);
				
				# Calculate indent before tag.
				if (preg_match('/(?:^|\n)( *?)(?! ).*?$/', $block_text, $matches)) {
					$strlen = $this->utf8_strlen;
					$indent = $strlen($matches[1], 'UTF-8');
				} else {
					$indent = 0;
				}
				
				# End preceding block with this tag.
				$block_text .= $tag;
				$parsed .= $this->$hash_method($block_text);
				
				# Get enclosing tag name for the ParseMarkdown function.
				# (This pattern makes $tag_name_re safe without quoting.)
				preg_match('/^<([\w:$]*)\b/', $tag, $matches);
				$tag_name_re = $matches[1];
				
				# Parse the content using the HTML-in-Markdown parser.
				list ($block_text, $text)
					= $this->_hashHTMLBlocks_inMarkdown($text, $indent, 
						$tag_name_re, $span_mode);
				
				# Outdent markdown text.
				if ($indent > 0) {
					$block_text = preg_replace("/^[ ]{1,$indent}/m", "", 
												$block_text);
				}
				
				# Append tag content to parsed text.
				if (!$span_mode)	$parsed .= "\n\n$block_text\n\n";
				else				$parsed .= "$block_text";
				
				# Start over a new block.
				$block_text = "";
			}
			else $block_text .= $tag;
		}
		
	} while ($depth > 0);
	
	#
	# Hash last block text that wasn't processed inside the loop.
	#
	$parsed .= $this->$hash_method($block_text);
	
	return array($parsed, $text);
}

public _hashHTMLBlocks_inMarkdown( ) (defined in MarkdownExtra_Parser)

Source Code

function _hashHTMLBlocks_inMarkdown($text, $indent = 0, 
									$enclosing_tag_re = '', $span = false)
{
#
# Parse markdown text, calling _HashHTMLBlocks_InHTML for block tags.
#
# *   $indent is the number of space to be ignored when checking for code 
#     blocks. This is important because if we don't take the indent into 
#     account, something like this (which looks right) won't work as expected:
#
#     <div>
#         <div markdown="1">
#         Hello World.  <-- Is this a Markdown code block or text?
#         </div>  <-- Is this a Markdown code block or a real tag?
#     <div>
#
#     If you don't like this, just don't indent the tag on which
#     you apply the markdown="1" attribute.
#
# *   If $enclosing_tag_re is not empty, stops at the first unmatched closing 
#     tag with that name. Nested tags supported.
#
# *   If $span is true, text inside must treated as span. So any double 
#     newline will be replaced by a single newline so that it does not create 
#     paragraphs.
#
# Returns an array of that form: ( processed text , remaining text )
#
	if ($text === '') return array('', '');

	# Regex to check for the presense of newlines around a block tag.
	$newline_before_re = '/(?:^\n?|\n\n)*$/';
	$newline_after_re = 
		'{
			^						# Start of text following the tag.
			(?>[ ]*<!--.*?-->)?		# Optional comment.
			[ ]*\n					# Must be followed by newline.
		}xs';
	
	# Regex to match any tag.
	$block_tag_re =
		'{
			(					# $2: Capture hole tag.
				</?					# Any opening or closing tag.
					(?>				# Tag name.
						'.$this->block_tags_re.'			|
						'.$this->context_block_tags_re.'	|
						'.$this->clean_tags_re.'        	|
						(?!\s)'.$enclosing_tag_re.'
					)
					(?:
						(?=[\s"\'/a-zA-Z0-9])	# Allowed characters after tag name.
						(?>
							".*?"		|	# Double quotes (can contain `>`)
							\'.*?\'   	|	# Single quotes (can contain `>`)
							.+?				# Anything but quotes and `>`.
						)*?
					)?
				>					# End of tag.
			|
				<!--    .*?     -->	# HTML Comment
			|
				<\?.*?\?> | <%.*?%>	# Processing instruction
			|
				<!\[CDATA\[.*?\]\]>	# CData Block
			|
				# Code span marker
				`+
			'. ( !$span ? ' # If not in span.
			|
				# Indented code block
				(?> ^[ ]*\n? | \n[ ]*\n )
				[ ]{'.($indent+4).'}[^\n]* \n
				(?>
					(?: [ ]{'.($indent+4).'}[^\n]* | [ ]* ) \n
				)*
			|
				# Fenced code block marker
				(?> ^ | \n )
				[ ]{'.($indent).'}~~~+[ ]*\n
			' : '' ). ' # End (if not is span).
			)
		}xs';

	
	$depth = 0;		# Current depth inside the tag tree.
	$parsed = "";	# Parsed text that will be returned.

	#
	# Loop through every tag until we find the closing tag of the parent
	# or loop until reaching the end of text if no parent tag specified.
	#
	do {
		#
		# Split the text using the first $tag_match pattern found.
		# Text before  pattern will be first in the array, text after
		# pattern will be at the end, and between will be any catches made 
		# by the pattern.
		#
		$parts = preg_split($block_tag_re, $text, 2, 
							PREG_SPLIT_DELIM_CAPTURE);
		
		# If in Markdown span mode, add a empty-string span-level hash 
		# after each newline to prevent triggering any block element.
		if ($span) {
			$void = $this->hashPart("", ':');
			$newline = "$void\n";
			$parts[0] = $void . str_replace("\n", $newline, $parts[0]) . $void;
		}
		
		$parsed .= $parts[0]; # Text before current tag.
		
		# If end of $text has been reached. Stop loop.
		if (count($parts) < 3) {
			$text = "";
			break;
		}
		
		$tag  = $parts[1]; # Tag to handle.
		$text = $parts[2]; # Remaining text after current tag.
		$tag_re = preg_quote($tag); # For use in a regular expression.
		
		#
		# Check for: Code span marker
		#
		if ($tag{0} == "`") {
			# Find corresponding end marker.
			$tag_re = preg_quote($tag);
			if (preg_match('{^(?>.+?|\n(?!\n))*?(?<!`)'.$tag_re.'(?!`)}',
				$text, $matches))
			{
				# End marker found: pass text unchanged until marker.
				$parsed .= $tag . $matches[0];
				$text = substr($text, strlen($matches[0]));
			}
			else {
				# Unmatched marker: just skip it.
				$parsed .= $tag;
			}
		}
		#
		# Check for: Indented code block or fenced code block marker.
		#
		else if ($tag{0} == "\n" || $tag{0} == "~") {
			if ($tag{1} == "\n" || $tag{1} == " ") {
				# Indented code block: pass it unchanged, will be handled 
				# later.
				$parsed .= $tag;
			}
			else {
				# Fenced code block marker: find matching end marker.
				$tag_re = preg_quote(trim($tag));
				if (preg_match('{^(?>.*\n)+?'.$tag_re.' *\n}', $text, 
					$matches)) 
				{
					# End marker found: pass text unchanged until marker.
					$parsed .= $tag . $matches[0];
					$text = substr($text, strlen($matches[0]));
				}
				else {
					# No end marker: just skip it.
					$parsed .= $tag;
				}
			}
		}
		#
		# Check for: Opening Block level tag or
		#            Opening Context Block tag (like ins and del) 
		#               used as a block tag (tag is alone on it's line).
		#
		else if (preg_match('{^<(?:'.$this->block_tags_re.')\b}', $tag) ||
			(	preg_match('{^<(?:'.$this->context_block_tags_re.')\b}', $tag) &&
				preg_match($newline_before_re, $parsed) &&
				preg_match($newline_after_re, $text)	)
			)
		{
			# Need to parse tag and following text using the HTML parser.
			list($block_text, $text) = 
				$this->_hashHTMLBlocks_inHTML($tag . $text, "hashBlock", true);
			
			# Make sure it stays outside of any paragraph by adding newlines.
			$parsed .= "\n\n$block_text\n\n";
		}
		#
		# Check for: Clean tag (like script, math)
		#            HTML Comments, processing instructions.
		#
		else if (preg_match('{^<(?:'.$this->clean_tags_re.')\b}', $tag) ||
			$tag{1} == '!' || $tag{1} == '?')
		{
			# Need to parse tag and following text using the HTML parser.
			# (don't check for markdown attribute)
			list($block_text, $text) = 
				$this->_hashHTMLBlocks_inHTML($tag . $text, "hashClean", false);
			
			$parsed .= $block_text;
		}
		#
		# Check for: Tag with same name as enclosing tag.
		#
		else if ($enclosing_tag_re !== '' &&
			# Same name as enclosing tag.
			preg_match('{^</?(?:'.$enclosing_tag_re.')\b}', $tag))
		{
			#
			# Increase/decrease nested tag count.
			#
			if ($tag{1} == '/')						$depth--;
			else if ($tag{strlen($tag)-2} != '/')	$depth++;

			if ($depth < 0) {
				#
				# Going out of parent element. Clean up and break so we
				# return to the calling function.
				#
				$text = $tag . $text;
				break;
			}
			
			$parsed .= $tag;
		}
		else {
			$parsed .= $tag;
		}
	} while ($depth >= 0);
	
	return array($parsed, $text);
}

public _processDefListItems_callback_dd( ) (defined in MarkdownExtra_Parser)

Source Code

function _processDefListItems_callback_dd($matches) {
	$leading_line	= $matches[1];
	$marker_space	= $matches[2];
	$def			= $matches[3];

	if ($leading_line || preg_match('/\n{2,}/', $def)) {
		# Replace marker with the appropriate whitespace indentation
		$def = str_repeat(' ', strlen($marker_space)) . $def;
		$def = $this->runBlockGamut($this->outdent($def . "\n\n"));
		$def = "\n". $def ."\n";
	}
	else {
		$def = rtrim($def);
		$def = $this->runSpanGamut($this->outdent($def));
	}

	return "\n<dd>" . $def . "</dd>\n";
}

public _processDefListItems_callback_dt( ) (defined in MarkdownExtra_Parser)

Source Code

function _processDefListItems_callback_dt($matches) {
	$terms = explode("\n", trim($matches[1]));
	$text = '';
	foreach ($terms as $term) {
		$term = $this->runSpanGamut(trim($term));
		$text .= "\n<dt>" . $term . "</dt>";
	}
	return $text . "\n";
}

public _stripAbbreviations_callback( ) (defined in MarkdownExtra_Parser)

Source Code

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
}

public _stripFootnotes_callback( ) (defined in MarkdownExtra_Parser)

Source Code

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
}

public appendFootnotes( ) (defined in MarkdownExtra_Parser)

Source Code

function appendFootnotes($text) {
#
# Append footnote list to text.
#
	$text = preg_replace_callback('{F\x1Afn:(.*?)\x1A:}', 
		array(&$this, '_appendFootnotes_callback'), $text);

	if (!empty($this->footnotes_ordered)) {
		$text .= "\n\n";
		$text .= "<div class=\"footnotes\">\n";
		$text .= "<hr". MARKDOWN_EMPTY_ELEMENT_SUFFIX ."\n";
		$text .= "<ol>\n\n";
		
		$attr = " rev=\"footnote\"";
		if ($this->fn_backlink_class != "") {
			$class = $this->fn_backlink_class;
			$class = $this->encodeAttribute($class);
			$attr .= " class=\"$class\"";
		}
		if ($this->fn_backlink_title != "") {
			$title = $this->fn_backlink_title;
			$title = $this->encodeAttribute($title);
			$attr .= " title=\"$title\"";
		}
		$num = 0;
		
		while (!empty($this->footnotes_ordered)) {
			$footnote = reset($this->footnotes_ordered);
			$note_id = key($this->footnotes_ordered);
			unset($this->footnotes_ordered[$note_id]);
			
			$footnote .= "\n"; # Need to append newline before parsing.
			$footnote = $this->runBlockGamut("$footnote\n");				
			$footnote = preg_replace_callback('{F\x1Afn:(.*?)\x1A:}', 
				array(&$this, '_appendFootnotes_callback'), $footnote);
			
			$attr = str_replace("%%", ++$num, $attr);
			$note_id = $this->encodeAttribute($note_id);
			
			# Add backlink to last paragraph; create new paragraph if needed.
			$backlink = "<a href=\"#fnref:$note_id\"$attr>&#8617;</a>";
			if (preg_match('{</p>$}', $footnote)) {
				$footnote = substr($footnote, 0, -4) . "&#160;$backlink</p>";
			} else {
				$footnote .= "\n\n<p>$backlink</p>";
			}
			
			$text .= "<li id=\"fn:$note_id\">\n";
			$text .= $footnote . "\n";
			$text .= "</li>\n\n";
		}
		
		$text .= "</ol>\n";
		$text .= "</div>";
	}
	return $text;
}

public doAbbreviations( ) (defined in MarkdownExtra_Parser)

Source Code

function doAbbreviations($text) {
#
# Find defined abbreviations in text and wrap them in <abbr> elements.
#
	if ($this->abbr_word_re) {
		// cannot use the /x modifier because abbr_word_re may 
		// contain significant spaces:
		$text = preg_replace_callback('{'.
			'(?<![\w\x1A])'.
			'(?:'.$this->abbr_word_re.')'.
			'(?![\w\x1A])'.
			'}', 
			array(&$this, '_doAbbreviations_callback'), $text);
	}
	return $text;
}

public doDefLists( ) (defined in MarkdownExtra_Parser)

Source Code

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;
}

public doFencedCodeBlocks( ) (defined in MarkdownExtra_Parser)

Source Code

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;
}

public doFootnotes( ) (defined in MarkdownExtra_Parser)

Source Code

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;
}

public doHeaders( ) (defined in MarkdownExtra_Parser)

Source Code

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;
}

public doTables( ) (defined in MarkdownExtra_Parser)

Source Code

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;
}

public formParagraphs( ) (defined in MarkdownExtra_Parser)

Source Code

function formParagraphs($text) {
#
#	Params:
#		$text - string to process with html <p> tags
#
	# Strip leading and trailing lines:
	$text = preg_replace('/\A\n+|\n+\z/', '', $text);
	
	$grafs = preg_split('/\n{2,}/', $text, -1, PREG_SPLIT_NO_EMPTY);

	#
	# Wrap <p> tags and unhashify HTML blocks
	#
	foreach ($grafs as $key => $value) {
		$value = trim($this->runSpanGamut($value));
		
		# Check if this should be enclosed in a paragraph.
		# Clean tag hashes & block tag hashes are left alone.
		$is_p = !preg_match('/^B\x1A[0-9]+B|^C\x1A[0-9]+C$/', $value);
		
		if ($is_p) {
			$value = "<p>$value</p>";
		}
		$grafs[$key] = $value;
	}
	
	# Join grafs in one text, then unhash HTML tags. 
	$text = implode("\n\n", $grafs);
	
	# Finish by removing any tag hashes still present in $text.
	$text = $this->unhash($text);
	
	return $text;
}

public hashClean( ) (defined in MarkdownExtra_Parser)

Source Code

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');
}

public hashHTMLBlocks( ) (defined in MarkdownExtra_Parser)

Source Code

function hashHTMLBlocks($text) {
#
# Hashify HTML Blocks and "clean tags".
#
# We only want to do this for block-level HTML tags, such as headers,
# lists, and tables. That's because we still want to wrap <p>s around
# "paragraphs" that are wrapped in non-block-level tags, such as anchors,
# phrase emphasis, and spans. The list of tags we're looking for is
# hard-coded.
#
# This works by calling _HashHTMLBlocks_InMarkdown, which then calls
# _HashHTMLBlocks_InHTML when it encounter block tags. When the markdown="1" 
# attribute is found whitin a tag, _HashHTMLBlocks_InHTML calls back
#  _HashHTMLBlocks_InMarkdown to handle the Markdown syntax within the tag.
# These two functions are calling each other. It's recursive!
#
	#
	# Call the HTML-in-Markdown hasher.
	#
	list($text, ) = $this->_hashHTMLBlocks_inMarkdown($text);
	
	return $text;
}

public processDefListItems( ) (defined in MarkdownExtra_Parser)

Source Code

function processDefListItems($list_str) {
#
#	Process the contents of a single definition list, splitting it
#	into individual term and definition list items.
#
	$less_than_tab = $this->tab_width - 1;
	
	# trim trailing blank lines:
	$list_str = preg_replace("/\n{2,}\\z/", "\n", $list_str);

	# Process definition terms.
	$list_str = preg_replace_callback('{
		(?>\A\n?|\n\n+)					# leading line
		(								# definition terms = $1
			[ ]{0,'.$less_than_tab.'}	# leading whitespace
			(?![:][ ]|[ ])				# negative lookahead for a definition 
										#   mark (colon) or more whitespace.
			(?> \S.* \n)+?				# actual term (not whitespace).	
		)			
		(?=\n?[ ]{0,3}:[ ])				# lookahead for following line feed 
										#   with a definition mark.
		}xm',
		array(&$this, '_processDefListItems_callback_dt'), $list_str);

	# Process actual definitions.
	$list_str = preg_replace_callback('{
		\n(\n+)?						# leading line = $1
		(								# marker space = $2
			[ ]{0,'.$less_than_tab.'}	# whitespace before colon
			[:][ ]+						# definition mark (colon)
		)
		((?s:.+?))						# definition text = $3
		(?= \n+ 						# stop at next definition mark,
			(?:							# next term or end of text
				[ ]{0,'.$less_than_tab.'} [:][ ]	|
				<dt> | \z
			)						
		)					
		}xm',
		array(&$this, '_processDefListItems_callback_dd'), $list_str);

	return $list_str;
}

public setup( ) (defined in MarkdownExtra_Parser)

Source Code

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);
	}
}

public stripAbbreviations( ) (defined in MarkdownExtra_Parser)

Source Code

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;
}

public stripFootnotes( ) (defined in MarkdownExtra_Parser)

Source Code

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;
}

public teardown( ) (defined in MarkdownExtra_Parser)

Source Code

function teardown() {
#
# Clearing Extra-specific variables.
#
	$this->footnotes = array();
	$this->footnotes_ordered = array();
	$this->abbr_desciptions = array();
	$this->abbr_word_re = '';
	
	parent::teardown();
}

public Markdown_Parser( ) (defined in Markdown_Parser)

Source Code

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);
}

public _detab_callback( ) (defined in Markdown_Parser)

Source Code

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;
}

public _doAnchors_inline_callback( ) (defined in Markdown_Parser)

Source Code

function _doAnchors_inline_callback($matches) {
	$whole_match	=  $matches[1];
	$link_text		=  $this->runSpanGamut($matches[2]);
	$url			=  $matches[3] == '' ? $matches[4] : $matches[3];
	$title			=& $matches[7];

	$url = $this->encodeAttribute($url);

	$result = "<a href=\"$url\"";
	if (isset($title)) {
		$title = $this->encodeAttribute($title);
		$result .=  " title=\"$title\"";
	}
	
	$link_text = $this->runSpanGamut($link_text);
	$result .= ">$link_text</a>";

	return $this->hashPart($result);
}

public _doAnchors_reference_callback( ) (defined in Markdown_Parser)

Source Code

function _doAnchors_reference_callback($matches) {
	$whole_match =  $matches[1];
	$link_text   =  $matches[2];
	$link_id     =& $matches[3];

	if ($link_id == "") {
		# for shortcut links like [this][] or [this].
		$link_id = $link_text;
	}
	
	# lower-case and turn embedded newlines into spaces
	$link_id = strtolower($link_id);
	$link_id = preg_replace('{[ ]?\n}', ' ', $link_id);

	if (isset($this->urls[$link_id])) {
		$url = $this->urls[$link_id];
		$url = $this->encodeAttribute($url);
		
		$result = "<a href=\"$url\"";
		if ( isset( $this->titles[$link_id] ) ) {
			$title = $this->titles[$link_id];
			$title = $this->encodeAttribute($title);
			$result .=  " title=\"$title\"";
		}
	
		$link_text = $this->runSpanGamut($link_text);
		$result .= ">$link_text</a>";
		$result = $this->hashPart($result);
	}
	else {
		$result = $whole_match;
	}
	return $result;
}

Source Code

function _doAutoLinks_email_callback($matches) {
	$address = $matches[1];
	$link = $this->encodeEmailAddress($address);
	return $this->hashPart($link);
}

Source Code

function _doAutoLinks_url_callback($matches) {
	$url = $this->encodeAttribute($matches[1]);
	$link = "<a href=\"$url\">$url</a>";
	return $this->hashPart($link);
}

public _doBlockQuotes_callback( ) (defined in Markdown_Parser)

Source Code

function _doBlockQuotes_callback($matches) {
	$bq = $matches[1];
	# trim one level of quoting - trim whitespace-only lines
	$bq = preg_replace('/^[ ]*>[ ]?|^[ ]+$/m', '', $bq);
	$bq = $this->runBlockGamut($bq);		# recurse

	$bq = preg_replace('/^/m', "  ", $bq);
	# These leading spaces cause problem with <pre> content, 
	# so we need to fix that:
	$bq = preg_replace_callback('{(\s*<pre>.+?</pre>)}sx', 
		array(&$this, '_DoBlockQuotes_callback2'), $bq);

	return "\n". $this->hashBlock("<blockquote>\n$bq\n</blockquote>")."\n\n";
}

public _doBlockQuotes_callback2( ) (defined in Markdown_Parser)

Source Code

function _doBlockQuotes_callback2($matches) {
	$pre = $matches[1];
	$pre = preg_replace('/^  /m', '', $pre);
	return $pre;
}

public _doCodeBlocks_callback( ) (defined in Markdown_Parser)

Source Code

function _doCodeBlocks_callback($matches) {
	$codeblock = $matches[1];

	$codeblock = $this->outdent($codeblock);
	$codeblock = htmlspecialchars($codeblock, ENT_NOQUOTES);

	# trim leading newlines and trailing newlines
	$codeblock = preg_replace('/\A\n+|\n+\z/', '', $codeblock);

	$codeblock = "<pre><code>$codeblock\n</code></pre>";
	return "\n\n".$this->hashBlock($codeblock)."\n\n";
}

public _doHardBreaks_callback( ) (defined in Markdown_Parser)

Source Code

function _doHardBreaks_callback($matches) {
	return $this->hashPart("<br$this->empty_element_suffix\n");
}

public _doImages_inline_callback( ) (defined in Markdown_Parser)

Source Code

function _doImages_inline_callback($matches) {
	$whole_match	= $matches[1];
	$alt_text		= $matches[2];
	$url			= $matches[3] == '' ? $matches[4] : $matches[3];
	$title			=& $matches[7];

	$alt_text = $this->encodeAttribute($alt_text);
	$url = $this->encodeAttribute($url);
	$result = "<img src=\"$url\" alt=\"$alt_text\"";
	if (isset($title)) {
		$title = $this->encodeAttribute($title);
		$result .=  " title=\"$title\""; # $title already quoted
	}
	$result .= $this->empty_element_suffix;

	return $this->hashPart($result);
}

public _doImages_reference_callback( ) (defined in Markdown_Parser)

Source Code

function _doImages_reference_callback($matches) {
	$whole_match = $matches[1];
	$alt_text    = $matches[2];
	$link_id     = strtolower($matches[3]);

	if ($link_id == "") {
		$link_id = strtolower($alt_text); # for shortcut links like ![this][].
	}

	$alt_text = $this->encodeAttribute($alt_text);
	if (isset($this->urls[$link_id])) {
		$url = $this->encodeAttribute($this->urls[$link_id]);
		$result = "<img src=\"$url\" alt=\"$alt_text\"";
		if (isset($this->titles[$link_id])) {
			$title = $this->titles[$link_id];
			$title = $this->encodeAttribute($title);
			$result .=  " title=\"$title\"";
		}
		$result .= $this->empty_element_suffix;
		$result = $this->hashPart($result);
	}
	else {
		# If there's no such link ID, leave intact:
		$result = $whole_match;
	}

	return $result;
}

public _doLists_callback( ) (defined in Markdown_Parser)

Source Code

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[3]) ? "ul" : "ol";
	
	$marker_any_re = ( $list_type == "ul" ? $marker_ul_re : $marker_ol_re );
	
	$list .= "\n";
	$result = $this->processListItems($list, $marker_any_re);
	
	$result = $this->hashBlock("<$list_type>\n" . $result . "</$list_type>");
	return "\n". $result ."\n\n";
}

public _hashHTMLBlocks_callback( ) (defined in Markdown_Parser)

Source Code

function _hashHTMLBlocks_callback($matches) {
	$text = $matches[1];
	$key  = $this->hashBlock($text);
	return "\n\n$key\n\n";
}

public _initDetab( ) (defined in Markdown_Parser)

Source Code

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);');
}

public _processListItems_callback( ) (defined in Markdown_Parser)

Source Code

function _processListItems_callback($matches) {
	$item = $matches[4];
	$leading_line =& $matches[1];
	$leading_space =& $matches[2];
	$marker_space = $matches[3];
	$tailing_blank_line =& $matches[5];

	if ($leading_line || $tailing_blank_line || 
		preg_match('/\n{2,}/', $item))
	{
		# Replace marker with the appropriate whitespace indentation
		$item = $leading_space . str_repeat(' ', strlen($marker_space)) . $item;
		$item = $this->runBlockGamut($this->outdent($item)."\n");
	}
	else {
		# Recursion for sub-lists:
		$item = $this->doLists($this->outdent($item));
		$item = preg_replace('/\n+$/', '', $item);
		$item = $this->runSpanGamut($item);
	}

	return "<li>" . $item . "</li>\n";
}

public _stripLinkDefinitions_callback( ) (defined in Markdown_Parser)

Source Code

function _stripLinkDefinitions_callback($matches) {
	$link_id = strtolower($matches[1]);
	$this->urls[$link_id] = $matches[2];
	$this->titles[$link_id] =& $matches[3];
	return ''; # String that will replace the block
}

public _unhash_callback( ) (defined in Markdown_Parser)

Source Code

function _unhash_callback($matches) {
	return $this->html_hashes[$matches[0]];
}

public detab( ) (defined in Markdown_Parser)

Source Code

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;
}

public doAnchors( ) (defined in Markdown_Parser)

Source Code

function doAnchors($text) {
#
# Turn Markdown link shortcuts into XHTML <a> tags.
#
	if ($this->in_anchor) return $text;
	$this->in_anchor = true;
	
	#
	# First, handle reference-style links: [link text] [id]
	#
	$text = preg_replace_callback('{
		(					# wrap whole match in $1
		  \[
			('.$this->nested_brackets_re.')	# link text = $2
		  \]

		  [ ]?				# one optional space
		  (?:\n[ ]*)?		# one optional newline followed by spaces

		  \[
			(.*?)		# id = $3
		  \]
		)
		}xs',
		array(&$this, '_doAnchors_reference_callback'), $text);

	#
	# Next, inline-style links: [link text](url "optional title")
	#
	$text = preg_replace_callback('{
		(				# wrap whole match in $1
		  \[
			('.$this->nested_brackets_re.')	# link text = $2
		  \]
		  \(			# literal paren
			[ ]*
			(?:
				<(\S*)>	# href = $3
			|
				('.$this->nested_url_parenthesis_re.')	# href = $4
			)
			[ ]*
			(			# $5
			  ([\'"])	# quote char = $6
			  (.*?)		# Title = $7
			  \6		# matching quote
			  [ ]*	# ignore any spaces/tabs between closing quote and )
			)?			# title is optional
		  \)
		)
		}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 test][1]
	# or [link test](/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;
}

Source Code

function doAutoLinks($text) {
	$text = preg_replace_callback('{<((https?|ftp|dict):[^\'">\s]+)>}i', 
		array(&$this, '_doAutoLinks_url_callback'), $text);

	# Email addresses: <[email protected]>
	$text = preg_replace_callback('{
		<
		(?:mailto:)?
		(
			[-.\w\x80-\xFF]+
			\@
			[-a-z0-9\x80-\xFF]+(\.[-a-z0-9\x80-\xFF]+)*\.[a-z]+
		)
		>
		}xi',
		array(&$this, '_doAutoLinks_email_callback'), $text);

	return $text;
}

public doBlockQuotes( ) (defined in Markdown_Parser)

Source Code

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;
}

public doCodeBlocks( ) (defined in Markdown_Parser)

Source Code

function doCodeBlocks($text) {
#
#	Process Markdown `<pre><code>` blocks.
#
	$text = preg_replace_callback('{
			(?:\n\n|\A\n?)
			(	            # $1 = the code block -- one or more lines, starting with a space/tab
			  (?>
				[ ]{'.$this->tab_width.'}  # Lines must start with a tab or a tab-width of spaces
				.*\n+
			  )+
			)
			((?=^[ ]{0,'.$this->tab_width.'}\S)|\Z)	# Lookahead for non-space at line-start, or end of doc
		}xm',
		array(&$this, '_doCodeBlocks_callback'), $text);

	return $text;
}

public doHardBreaks( ) (defined in Markdown_Parser)

Source Code

function doHardBreaks($text) {
	# Do hard breaks:
	return preg_replace_callback('/ {2,}\n/', 
		array(&$this, '_doHardBreaks_callback'), $text);
}

public doHorizontalRules( ) (defined in Markdown_Parser)

Source Code

function doHorizontalRules($text) {
	# Do Horizontal Rules:
	return preg_replace(
		'{
			^[ ]{0,3}	# Leading space
			([-*_])		# $1: First marker
			(?>			# Repeated marker group
				[ ]{0,2}	# Zero, one, or two spaces.
				\1			# Marker character
			){2,}		# Group repeated at least twice
			[ ]*		# Tailing spaces
			$			# End of line.
		}mx',
		"\n".$this->hashBlock("<hr$this->empty_element_suffix")."\n", 
		$text);
}

public doImages( ) (defined in Markdown_Parser)

Source Code

function doImages($text) {
#
# Turn Markdown image shortcuts into <img> tags.
#
	#
	# First, handle reference-style labeled images: ![alt text][id]
	#
	$text = preg_replace_callback('{
		(				# wrap whole match in $1
		  !\[
			('.$this->nested_brackets_re.')		# alt text = $2
		  \]

		  [ ]?				# one optional space
		  (?:\n[ ]*)?		# one optional newline followed by spaces

		  \[
			(.*?)		# id = $3
		  \]

		)
		}xs', 
		array(&$this, '_doImages_reference_callback'), $text);

	#
	# Next, handle inline images:  ![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
		  \(			# literal paren
			[ ]*
			(?:
				<(\S*)>	# src url = $3
			|
				('.$this->nested_url_parenthesis_re.')	# src url = $4
			)
			[ ]*
			(			# $5
			  ([\'"])	# quote char = $6
			  (.*?)		# title = $7
			  \6		# matching quote
			  [ ]*
			)?			# title is optional
		  \)
		)
		}xs',
		array(&$this, '_doImages_inline_callback'), $text);

	return $text;
}

public doItalicsAndBold( ) (defined in Markdown_Parser)

Source Code

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 seach for the next emphasis token. 
		# Each token is then passed to handleSpanToken.
		#
		$parts = preg_split($token_re, $text, 2, PREG_SPLIT_DELIM_CAPTURE);
		$text_stack[0] .= $parts[0];
		$token =& $parts[1];
		$text =& $parts[2];
		
		if (empty($token)) {
			# Reached end of text span: empty stack without emitting.
			# any more emphasis.
			while ($token_stack[0]) {
				$text_stack[1] .= array_shift($token_stack);
				$text_stack[0] .= array_shift($text_stack);
			}
			break;
		}
		
		$token_len = strlen($token);
		if ($tree_char_em) {
			# Reached closing marker while inside a three-char emphasis.
			if ($token_len == 3) {
				# Three-char closing marker, close em and strong.
				array_shift($token_stack);
				$span = array_shift($text_stack);
				$span = $this->runSpanGamut($span);
				$span = "<strong><em>$span</em></strong>";
				$text_stack[0] .= $this->hashPart($span);
				$em = '';
				$strong = '';
			} else {
				# Other closing marker: close one em or strong and
				# change current token state to match the other
				$token_stack[0] = str_repeat($token{0}, 3-$token_len);
				$tag = $token_len == 2 ? "strong" : "em";
				$span = $text_stack[0];
				$span = $this->runSpanGamut($span);
				$span = "<$tag>$span</$tag>";
				$text_stack[0] = $this->hashPart($span);
				$$tag = ''; # $$tag stands for $em or $strong
			}
			$tree_char_em = false;
		} else if ($token_len == 3) {
			if ($em) {
				# Reached closing marker for both em and strong.
				# Closing strong marker:
				for ($i = 0; $i < 2; ++$i) {
					$shifted_token = array_shift($token_stack);
					$tag = strlen($shifted_token) == 2 ? "strong" : "em";
					$span = array_shift($text_stack);
					$span = $this->runSpanGamut($span);
					$span = "<$tag>$span</$tag>";
					$text_stack[0] .= $this->hashPart($span);
					$$tag = ''; # $$tag stands for $em or $strong
				}
			} else {
				# Reached opening three-char emphasis marker. Push on token 
				# stack; will be handled by the special condition above.
				$em = $token{0};
				$strong = "$em$em";
				array_unshift($token_stack, $token);
				array_unshift($text_stack, '');
				$tree_char_em = true;
			}
		} else if ($token_len == 2) {
			if ($strong) {
				# Unwind any dangling emphasis marker:
				if (strlen($token_stack[0]) == 1) {
					$text_stack[1] .= array_shift($token_stack);
					$text_stack[0] .= array_shift($text_stack);
				}
				# Closing strong marker:
				array_shift($token_stack);
				$span = array_shift($text_stack);
				$span = $this->runSpanGamut($span);
				$span = "<strong>$span</strong>";
				$text_stack[0] .= $this->hashPart($span);
				$strong = '';
			} else {
				array_unshift($token_stack, $token);
				array_unshift($text_stack, '');
				$strong = $token;
			}
		} else {
			# Here $token_len == 1
			if ($em) {
				if (strlen($token_stack[0]) == 1) {
					# Closing emphasis marker:
					array_shift($token_stack);
					$span = array_shift($text_stack);
					$span = $this->runSpanGamut($span);
					$span = "<em>$span</em>";
					$text_stack[0] .= $this->hashPart($span);
					$em = '';
				} else {
					$text_stack[0] .= $token;
				}
			} else {
				array_unshift($token_stack, $token);
				array_unshift($text_stack, '');
				$em = $token;
			}
		}
	}
	return $text_stack[0];
}

public doLists( ) (defined in Markdown_Parser)

Source Code

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);

	foreach ($markers_relist as $marker_re) {
		# Re-usable pattern to match any entirel ul or ol list:
		$whole_list_re = '
			(								# $1 = whole list
			  (								# $2
				[ ]{0,'.$less_than_tab.'}
				('.$marker_re.')			# $3 = first list item marker
				[ ]+
			  )
			  (?s:.+?)
			  (								# $4
				  \z
				|
				  \n{2,}
				  (?=\S)
				  (?!						# Negative lookahead for another list item marker
					[ ]*
					'.$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;
}

public encodeAmpsAndAngles( ) (defined in Markdown_Parser)

Source Code

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('&', '&amp;', $text);
	} else {
		# Ampersand-encoding based entirely on Nat Irons's Amputator
		# MT plugin: <http://bumppo.net/projects/amputator/>
		$text = preg_replace('/&(?!#?[xX]?(?:[0-9a-fA-F]+|\w+);)/', 
							'&amp;', $text);;
	}
	# Encode remaining <'s
	$text = str_replace('<', '&lt;', $text);

	return $text;
}

public encodeAttribute( ) (defined in Markdown_Parser)

Source Code

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('"', '&quot;', $text);
	return $text;
}

public encodeEmailAddress( ) (defined in Markdown_Parser)

Source Code

function encodeEmailAddress($addr) {
#
#	Input: an email address, e.g. "[email protected]"
#
#	Output: the email address as a mailto link, with each character
#		of the address encoded as either a decimal or hex entity, in
#		the hopes of foiling most address harvesting spam bots. E.g.:
#
#	  <p><a href="&#109;&#x61;&#105;&#x6c;&#116;&#x6f;&#58;&#x66;o&#111;
#        &#x40;&#101;&#x78;&#97;&#x6d;&#112;&#x6c;&#101;&#46;&#x63;&#111;
#        &#x6d;">&#x66;o&#111;&#x40;&#101;&#x78;&#97;&#x6d;&#112;&#x6c;
#        &#101;&#46;&#x63;&#111;&#x6d;</a></p>
#
#	Based by a filter by Matthew Wickline, posted to BBEdit-Talk.
#   With some optimizations by Milian Wolff.
#
	$addr = "mailto:" . $addr;
	$chars = preg_split('/(?<!^)(?!$)/', $addr);
	$seed = (int)abs(crc32($addr) / strlen($addr)); # Deterministic seed.
	
	foreach ($chars as $key => $char) {
		$ord = ord($char);
		# Ignore non-ascii chars.
		if ($ord < 128) {
			$r = ($seed * (1 + $key)) % 100; # Pseudo-random function.
			# roughly 10% raw, 45% hex, 45% dec
			# '@' *must* be encoded. I insist.
			if ($r > 90 && $char != '@') /* do nothing */;
			else if ($r < 45) $chars[$key] = '&#x'.dechex($ord).';';
			else              $chars[$key] = '&#'.$ord.';';
		}
	}
	
	$addr = implode('', $chars);
	$text = implode('', array_slice($chars, 7)); # text without `mailto:`
	$addr = "<a href=\"$addr\">$text</a>";

	return $addr;
}

public handleSpanToken( ) (defined in Markdown_Parser)

Source Code

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);
	}
}

public hashBlock( ) (defined in Markdown_Parser)

Source Code

function hashBlock($text) {
#
# Shortcut function for hashPart with block-level boundaries.
#
	return $this->hashPart($text, 'B');
}

public hashPart( ) (defined in Markdown_Parser)

Source Code

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.
}

public makeCodeSpan( ) (defined in Markdown_Parser)

Source Code

function makeCodeSpan($code) {
#
# Create a code span markup for $code. Called from handleSpanToken.
#
	$code = htmlspecialchars(trim($code), ENT_NOQUOTES);
	return $this->hashPart("<code>$code</code>");
}

public outdent( ) (defined in Markdown_Parser)

Source Code

function outdent($text) {
#
# Remove one level of line-leading tabs or spaces
#
	return preg_replace('/^(\t|[ ]{1,'.$this->tab_width.'})/m', '', $text);
}

public parseSpan( ) (defined in Markdown_Parser)

Source Code

function parseSpan($str) {
#
# Take the string $str and parse it into tokens, hashing embeded HTML,
# escaped characters and handling code spans.
#
	$output = '';
	
	$span_re = '{
			(
				\\\\'.$this->escape_chars_re.'
			|
				(?<![`\\\\])
				`+						# code span marker
		'.( $this->no_markup ? '' : '
			|
				<!--    .*?     -->		# comment
			|
				<\?.*?\?> | <%.*?%>		# processing instruction
			|
				<[/!$]?[-a-zA-Z0-9:]+	# regular tags
				(?>
					\s
					(?>[^"\'>]+|"[^"]*"|\'[^\']*\')*
				)?
				>
		').'
			)
			}xs';

	while (1) {
		#
		# Each loop iteration seach for either the next tag, the next 
		# openning code span marker, or the next escaped character. 
		# Each token is then passed to handleSpanToken.
		#
		$parts = preg_split($span_re, $str, 2, PREG_SPLIT_DELIM_CAPTURE);
		
		# Create token from text preceding tag.
		if ($parts[0] != "") {
			$output .= $parts[0];
		}
		
		# Check if we reach the end.
		if (isset($parts[1])) {
			$output .= $this->handleSpanToken($parts[1], $parts[2]);
			$str = $parts[2];
		}
		else {
			break;
		}
	}
	
	return $output;
}

public prepareItalicsAndBold( ) (defined in Markdown_Parser)

Source Code

function prepareItalicsAndBold() {
#
# Prepare regular expressions for seraching emphasis tokens in any
# context.
#
	foreach ($this->em_relist as $em => $em_re) {
		foreach ($this->strong_relist as $strong => $strong_re) {
			# Construct list of allowed token expressions.
			$token_relist = array();
			if (isset($this->em_strong_relist["$em$strong"])) {
				$token_relist[] = $this->em_strong_relist["$em$strong"];
			}
			$token_relist[] = $em_re;
			$token_relist[] = $strong_re;
			
			# Construct master expression from list.
			$token_re = '{('. implode('|', $token_relist) .')}';
			$this->em_strong_prepared_relist["$em$strong"] = $token_re;
		}
	}
}

public processListItems( ) (defined in Markdown_Parser)

Source Code

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;
}

public runBasicBlockGamut( ) (defined in Markdown_Parser)

Source Code

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;
}

public runBlockGamut( ) (defined in Markdown_Parser)

Source Code

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);
}

public runSpanGamut( ) (defined in Markdown_Parser)

Source Code

function runSpanGamut($text) {
#
# Run span gamut tranformations.
#
	foreach ($this->span_gamut as $method => $priority) {
		$text = $this->$method($text);
	}

	return $text;
}

public stripLinkDefinitions( ) (defined in Markdown_Parser)

Source Code

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
						  [ ]*
						<?(\S+?)>?			# url = $2
						  [ ]*
						  \n?				# maybe one newline
						  [ ]*
						(?:
							(?<=\s)			# lookbehind for whitespace
							["(]
							(.*?)			# title = $3
							[")]
							[ ]*
						)?	# title is optional
						(?:\n+|\Z)
		}xm',
		array(&$this, '_stripLinkDefinitions_callback'),
		$text);
	return $text;
}

public transform( ) (defined in Markdown_Parser)

Source Code

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";
}

public unhash( ) (defined in Markdown_Parser)

Source Code

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);
}

protected _add_to_toc( ) (defined in Kohana_Kodoc_Markdown)

Source Code

protected function _add_to_toc($level, $name, $id)
{
	self::$_toc[] = array(
		'level' => $level,
		'name'  => $name,
		'id'    => $id);
}