<?php
+#
+# Markdown Extra - A text-to-HTML conversion tool for web writers
+#
+# PHP Markdown & Extra
+# Copyright (c) 2004-2009 Michel Fortin
+# <http://michelf.com/projects/php-markdown/>
+#
+# Original Markdown
+# Copyright (c) 2004-2006 John Gruber
+# <http://daringfireball.net/projects/markdown/>
+#
-/**
- *
- * Markdown Extra - A text-to-HTML conversion tool for web writers
- *
- * PHP Markdown & Extra
- * Copyright (c) 2004-2007 Michel Fortin
- * <http://www.michelf.com/projects/php-markdown/>
- *
- * Original Markdown
- * Copyright (c) 2004-2006 John Gruber
- * <http://daringfireball.net/projects/markdown/>
- *
- * @package moodlecore
- * @copyright (c) 2004-2006 John Gruber
- */
-
-/** MARKDOWN_VERSION = 1.0.1j */
-define( 'MARKDOWN_VERSION', "1.0.1j" ); # Tue 4 Sep 2007
-/** MARKDOWNEXTRA_VERSION = 1.1.6 */
-define( 'MARKDOWNEXTRA_VERSION', "1.1.6" ); # Tue 4 Sep 2007
+
+define( 'MARKDOWN_VERSION', "1.0.1n" ); # Sat 10 Oct 2009
+define( 'MARKDOWNEXTRA_VERSION', "1.2.4" ); # Sat 10 Oct 2009
#
# Global default settings:
#
-/** Change to ">" for HTML output */
+# Change to ">" for HTML output
@define( 'MARKDOWN_EMPTY_ELEMENT_SUFFIX', " />");
-/** Define the width of a tab for code blocks. */
+# Define the width of a tab for code blocks.
@define( 'MARKDOWN_TAB_WIDTH', 4 );
-/** Optional title attribute for footnote links and backlinks. */
+# Optional title attribute for footnote links and backlinks.
@define( 'MARKDOWN_FN_LINK_TITLE', "" );
@define( 'MARKDOWN_FN_BACKLINK_TITLE', "" );
/*
Plugin Name: Markdown Extra
-Plugin URI: http://www.michelf.com/projects/php-markdown/
-Description: <a href="http://daringfireball.net/projects/markdown/syntax">Markdown syntax</a> allows you to write using an easy-to-read, easy-to-write plain text format. Based on the original Perl version by <a href="http://daringfireball.net/">John Gruber</a>. <a href="http://www.michelf.com/projects/php-markdown/">More...</a>
-Version: 1.1.6
+Plugin URI: http://michelf.com/projects/php-markdown/
+Description: <a href="http://daringfireball.net/projects/markdown/syntax">Markdown syntax</a> allows you to write using an easy-to-read, easy-to-write plain text format. Based on the original Perl version by <a href="http://daringfireball.net/">John Gruber</a>. <a href="http://michelf.com/projects/php-markdown/">More...</a>
+Version: 1.2.4
Author: Michel Fortin
-Author URI: http://www.michelf.com/
+Author URI: http://michelf.com/
*/
if (isset($wp_version)) {
# More details about how it works here:
- # <http://www.michelf.com/weblog/2005/wordpress-text-flow-vs-markdown/>
+ # <http://michelf.com/weblog/2005/wordpress-text-flow-vs-markdown/>
# Post content and excerpts
# - Remove WordPress paragraph generator.
remove_filter('the_content', 'wpautop');
remove_filter('the_content_rss', 'wpautop');
remove_filter('the_excerpt', 'wpautop');
- add_filter('the_content', 'Markdown', 6);
- add_filter('the_content_rss', 'Markdown', 6);
- add_filter('get_the_excerpt', 'Markdown', 6);
+ add_filter('the_content', 'mdwp_MarkdownPost', 6);
+ add_filter('the_content_rss', 'mdwp_MarkdownPost', 6);
+ add_filter('get_the_excerpt', 'mdwp_MarkdownPost', 6);
add_filter('get_the_excerpt', 'trim', 7);
add_filter('the_excerpt', 'mdwp_add_p');
add_filter('the_excerpt_rss', 'mdwp_strip_p');
add_filter('get_the_excerpt', 'balanceTags', 9);
}
+ # Add a footnote id prefix to posts when inside a loop.
+ function mdwp_MarkdownPost($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.
'authors' => 'Michel Fortin and John Gruber',
'licence' => 'GPL',
'version' => MARKDOWNEXTRA_VERSION,
- 'help' => '<a href="http://daringfireball.net/projects/markdown/syntax">Markdown syntax</a> allows you to write using an easy-to-read, easy-to-write plain text format. Based on the original Perl version by <a href="http://daringfireball.net/">John Gruber</a>. <a href="http://www.michelf.com/projects/php-markdown/">More...</a>',
+ 'help' => '<a href="http://daringfireball.net/projects/markdown/syntax">Markdown syntax</a> allows you to write using an easy-to-read, easy-to-write plain text format. Based on the original Perl version by <a href="http://daringfireball.net/">John Gruber</a>. <a href="http://michelf.com/projects/php-markdown/">More...</a>',
);
}
# Try to include PHP SmartyPants. Should be in the same directory.
@include_once 'smartypants.php';
# Fake Textile class. It calls Markdown instead.
- /**
- * @package moodlecore
- * @copyright (c) 2004-2006 John Gruber
- */
class Textile {
function TextileThis($text, $lite='', $encode='') {
if ($lite == '' && $encode == '') $text = Markdown($text);
-/**
- * Markdown Parser Class
- *
- * @package moodlecore
- * @copyright (c) 2004-2006 John Gruber
- */
+#
+# 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;
+ var $nested_brackets_re;
var $nested_url_parenthesis_depth = 4;
- var $nested_url_parenthesis;
+ 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;
# 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 =
+ $this->nested_brackets_re =
str_repeat('(?>[^\[\]]+|\[', $this->nested_brackets_depth).
str_repeat('\])*', $this->nested_brackets_depth);
- $this->nested_url_parenthesis =
+ $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);
# Status flag to avoid invalid nesting.
var $in_anchor = false;
-
-
- function transform($text) {
+
+
+ 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() {
#
- # Main function. The order in which other subs are called here is
- # essential. Link and image substitutions need to happen before
- # _EscapeSpecialCharsWithinTagAttributes(), so that any *'s or _'s in the <a>
- # and <img> tags get encoded.
+ # Called after the transformation process to clear any variable
+ # which may be taking up memory unnecessarly.
#
- # Clear the global hashes. If we don't clear these, you get conflicts
- # from other articles when generating a page which contains more than
- # one article (e.g. an index page that shows the N most recent
- # articles):
$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}', '', $text);
# Standardize line endings:
# DOS to Unix and Mac to Unix
foreach ($this->document_gamut as $method => $priority) {
$text = $this->$method($text);
}
+
+ $this->teardown();
return $text . "\n";
}
[ ]*
\n? # maybe *one* newline
[ ]*
- <?(\S+?)>? # url = $2
+ (?:
+ <(.+?)> # url = $2
+ |
+ (\S+?) # url = $3
+ )
[ ]*
\n? # maybe one newline
[ ]*
(?:
(?<=\s) # lookbehind for whitespace
["(]
- (.*?) # title = $3
+ (.*?) # title = $4
[")]
[ ]*
)? # title is optional
}
function _stripLinkDefinitions_callback($matches) {
$link_id = strtolower($matches[1]);
- $this->urls[$link_id] = $this->encodeAmpsAndAngles($matches[2]);
- if (isset($matches[3]))
- $this->titles[$link_id] = str_replace('"', '"', $matches[3]);
+ $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
}
# inline later.
# * List "b" is made of tags which are always block-level;
#
- $block_tags_a = 'ins|del';
- $block_tags_b = 'p|div|h[1-6]|blockquote|pre|table|dl|ol|ul|address|'.
- 'script|noscript|form|fieldset|iframe|math';
+ $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.
$nested_tags_level = 4;
# in between.
[ ]{0,'.$less_than_tab.'}
- <('.$block_tags_b.')# start tag = $2
+ <('.$block_tags_b_re.')# start tag = $2
'.$attr.'> # attributes followed by > and \n
'.$content.' # content, support nesting
</\2> # the matching end tag
| # Special version for tags of group a.
[ ]{0,'.$less_than_tab.'}
- <('.$block_tags_a.')# start tag = $3
+ <('.$block_tags_a_re.')# start tag = $3
'.$attr.'>[ ]*\n # attributes followed by >
'.$content2.' # content, support nesting
</\3> # the matching end tag
[ ]{0,'.$less_than_tab.'}
<(hr) # start tag = $2
- \b # word break
- ([^<>])*? #
+ '.$attr.' # attributes
/?> # the matching end tag
[ ]*
(?=\n{2,}|\Z) # followed by a blank line or end of document
# 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 "S" is used for general span-level 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.
return preg_replace(
'{
^[ ]{0,3} # Leading space
- ([*-_]) # $1: First marker
+ ([-*_]) # $1: First marker
(?> # Repeated marker group
[ ]{0,2} # Zero, one, or two spaces.
\1 # Marker character
$text = preg_replace_callback('{
( # wrap whole match in $1
\[
- ('.$this->nested_brackets.') # link text = $2
+ ('.$this->nested_brackets_re.') # link text = $2
\]
[ ]? # one optional space
$text = preg_replace_callback('{
( # wrap whole match in $1
\[
- ('.$this->nested_brackets.') # link text = $2
+ ('.$this->nested_brackets_re.') # link text = $2
\]
\( # literal paren
- [ ]*
+ [ \n]*
(?:
- <(\S*)> # href = $3
+ <(.+?)> # href = $3
|
- ('.$this->nested_url_parenthesis.') # href = $4
+ ('.$this->nested_url_parenthesis_re.') # href = $4
)
- [ ]*
+ [ \n]*
( # $5
([\'"]) # quote char = $6
(.*?) # Title = $7
\6 # matching quote
- [ ]* # ignore any spaces/tabs between closing quote and )
+ [ \n]* # ignore any spaces/tabs between closing quote and )
)? # title is optional
\)
)
}xs',
- array(&$this, '_DoAnchors_inline_callback'), $text);
+ array(&$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)
+ # 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);
+ $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 $text;
if (isset($this->urls[$link_id])) {
$url = $this->urls[$link_id];
- $url = $this->encodeAmpsAndAngles($url);
+ $url = $this->encodeAttribute($url);
$result = "<a href=\"$url\"";
if ( isset( $this->titles[$link_id] ) ) {
$title = $this->titles[$link_id];
- $title = $this->encodeAmpsAndAngles($title);
+ $title = $this->encodeAttribute($title);
$result .= " title=\"$title\"";
}
$url = $matches[3] == '' ? $matches[4] : $matches[3];
$title =& $matches[7];
- $url = $this->encodeAmpsAndAngles($url);
+ $url = $this->encodeAttribute($url);
$result = "<a href=\"$url\"";
if (isset($title)) {
- $title = str_replace('"', '"', $title);
- $title = $this->encodeAmpsAndAngles($title);
+ $title = $this->encodeAttribute($title);
$result .= " title=\"$title\"";
}
$text = preg_replace_callback('{
( # wrap whole match in $1
!\[
- ('.$this->nested_brackets.') # alt text = $2
+ ('.$this->nested_brackets_re.') # alt text = $2
\]
[ ]? # one optional space
$text = preg_replace_callback('{
( # wrap whole match in $1
!\[
- ('.$this->nested_brackets.') # alt text = $2
+ ('.$this->nested_brackets_re.') # alt text = $2
\]
\s? # One optional whitespace character
\( # literal paren
- [ ]*
+ [ \n]*
(?:
<(\S*)> # src url = $3
|
- ('.$this->nested_url_parenthesis.') # src url = $4
+ ('.$this->nested_url_parenthesis_re.') # src url = $4
)
- [ ]*
+ [ \n]*
( # $5
([\'"]) # quote char = $6
(.*?) # title = $7
\6 # matching quote
- [ ]*
+ [ \n]*
)? # title is optional
\)
)
$link_id = strtolower($alt_text); # for shortcut links like ![this][].
}
- $alt_text = str_replace('"', '"', $alt_text);
+ $alt_text = $this->encodeAttribute($alt_text);
if (isset($this->urls[$link_id])) {
- $url = $this->urls[$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;
$url = $matches[3] == '' ? $matches[4] : $matches[3];
$title =& $matches[7];
- $alt_text = str_replace('"', '"', $alt_text);
+ $alt_text = $this->encodeAttribute($alt_text);
+ $url = $this->encodeAttribute($url);
$result = "<img src=\"$url\" alt=\"$alt_text\"";
if (isset($title)) {
- $title = str_replace('"', '"', $title);
+ $title = $this->encodeAttribute($title);
$result .= " title=\"$title\""; # $title already quoted
}
$result .= $this->empty_element_suffix;
return $text;
}
function _doHeaders_callback_setext($matches) {
+ # Terrible hack to check we haven't found an empty list item.
+ if ($matches[2] == '-' && preg_match('{^-(?: |$)}', $matches[1]))
+ return $matches[0];
+
$level = $matches[2]{0} == '=' ? 1 : 2;
$block = "<h$level>".$this->runSpanGamut($matches[1])."</h$level>";
return "\n" . $this->hashBlock($block) . "\n\n";
$less_than_tab = $this->tab_width - 1;
# Re-usable patterns to match list item bullets and number markers:
- $marker_ul = '[*+-]';
- $marker_ol = '\d+[.]';
- $marker_any = "(?:$marker_ul|$marker_ol)";
+ $marker_ul_re = '[*+-]';
+ $marker_ol_re = '\d+[.]';
+ $marker_any_re = "(?:$marker_ul_re|$marker_ol_re)";
- $markers = array($marker_ul, $marker_ol);
+ $markers_relist = array(
+ $marker_ul_re => $marker_ol_re,
+ $marker_ol_re => $marker_ul_re,
+ );
- foreach ($markers as $marker) {
+ foreach ($markers_relist as $marker_re => $other_marker_re) {
# Re-usable pattern to match any entirel ul or ol list:
- $whole_list = '
+ $whole_list_re = '
( # $1 = whole list
( # $2
- [ ]{0,'.$less_than_tab.'}
- ('.$marker.') # $3 = first list item marker
+ ([ ]{0,'.$less_than_tab.'}) # $3 = number of spaces
+ ('.$marker_re.') # $4 = first list item marker
[ ]+
)
(?s:.+?)
- ( # $4
+ ( # $5
\z
|
\n{2,}
(?=\S)
(?! # Negative lookahead for another list item marker
[ ]*
- '.$marker.'[ ]+
+ '.$marker_re.'[ ]+
+ )
+ |
+ (?= # Lookahead for another kind of list
+ \n
+ \3 # Must have the same indentation
+ '.$other_marker_re.'[ ]+
)
)
)
if ($this->list_level) {
$text = preg_replace_callback('{
^
- '.$whole_list.'
+ '.$whole_list_re.'
}mx',
array(&$this, '_doLists_callback'), $text);
}
else {
$text = preg_replace_callback('{
(?:(?<=\n)\n|\A\n?) # Must eat the newline
- '.$whole_list.'
+ '.$whole_list_re.'
}mx',
array(&$this, '_doLists_callback'), $text);
}
}
function _doLists_callback($matches) {
# Re-usable patterns to match list item bullets and number markers:
- $marker_ul = '[*+-]';
- $marker_ol = '\d+[.]';
- $marker_any = "(?:$marker_ul|$marker_ol)";
+ $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/", $matches[3]) ? "ul" : "ol";
+ $list_type = preg_match("/$marker_ul_re/", $matches[4]) ? "ul" : "ol";
- $marker_any = ( $list_type == "ul" ? $marker_ul : $marker_ol );
+ $marker_any_re = ( $list_type == "ul" ? $marker_ul_re : $marker_ol_re );
$list .= "\n";
- $result = $this->processListItems($list, $marker_any);
+ $result = $this->processListItems($list, $marker_any_re);
$result = $this->hashBlock("<$list_type>\n" . $result . "</$list_type>");
return "\n". $result ."\n\n";
var $list_level = 0;
- function processListItems($list_str, $marker_any) {
+ function processListItems($list_str, $marker_any_re) {
#
# Process the contents of a single ordered or unordered list, splitting it
# into individual list items.
$list_str = preg_replace_callback('{
(\n)? # leading line = $1
- (^[ ]*) # leading whitespace = $2
- ('.$marker_any.') [ ]+ # list marker = $3
- ((?s:.+?)) # list item text = $4
+ (^[ ]*) # 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.') [ ]+))
+ (?= \n* (\z | \2 ('.$marker_any_re.') (?:[ ]+|(?=\n))))
}xm',
array(&$this, '_processListItems_callback'), $list_str);
$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 {
# Process Markdown `<pre><code>` blocks.
#
$text = preg_replace_callback('{
- (?:\n\n|\A)
+ (?:\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
}
- function doItalicsAndBold($text) {
- # <strong> must go first:
- $text = preg_replace_callback('{
- ( # $1: Marker
- (?<!\*\*) \* | # (not preceded by two chars of
- (?<!__) _ # the same marker)
- )
- \1
- (?=\S) # Not followed by whitespace
- (?!\1\1) # or two others marker chars.
- ( # $2: Content
- (?>
- [^*_]+? # Anthing not em markers.
- |
- # Balence any regular emphasis inside.
- \1 (?=\S) .+? (?<=\S) \1
- |
- . # Allow unbalenced * and _.
- )+?
- )
- (?<=\S) \1\1 # End mark not preceded by whitespace.
- }sx',
- array(&$this, '_doItalicAndBold_strong_callback'), $text);
- # Then <em>:
- $text = preg_replace_callback(
- '{ ( (?<!\*)\* | (?<!_)_ ) (?=\S) (?! \1) (.+?) (?<=\S)(?<!\s(?=\1).) \1 }sx',
- array(&$this, '_doItalicAndBold_em_callback'), $text);
-
- return $text;
- }
- function _doItalicAndBold_em_callback($matches) {
- $text = $matches[2];
- $text = $this->runSpanGamut($text);
- return $this->hashPart("<em>$text</em>");
+ var $em_relist = array(
+ '' => '(?:(?<!\*)\*(?!\*)|(?<!_)_(?!_))(?=\S|$)(?![.,:;]\s)',
+ '*' => '(?<=\S|^)(?<!\*)\*(?!\*)',
+ '_' => '(?<=\S|^)(?<!_)_(?!_)',
+ );
+ var $strong_relist = array(
+ '' => '(?:(?<!\*)\*\*(?!\*)|(?<!_)__(?!_))(?=\S|$)(?![.,:;]\s)',
+ '**' => '(?<=\S|^)(?<!\*)\*\*(?!\*)',
+ '__' => '(?<=\S|^)(?<!_)__(?!_)',
+ );
+ var $em_strong_relist = array(
+ '' => '(?:(?<!\*)\*\*\*(?!\*)|(?<!_)___(?!_))(?=\S|$)(?![.,:;]\s)',
+ '***' => '(?<=\S|^)(?<!\*)\*\*\*(?!\*)',
+ '___' => '(?<=\S|^)(?<!_)___(?!_)',
+ );
+ var $em_strong_prepared_relist;
+
+ function prepareItalicsAndBold() {
+ #
+ # Prepare regular expressions for searching emphasis tokens in any
+ # context.
+ #
+ foreach ($this->em_relist as $em => $em_re) {
+ foreach ($this->strong_relist as $strong => $strong_re) {
+ # Construct list of allowed token expressions.
+ $token_relist = array();
+ if (isset($this->em_strong_relist["$em$strong"])) {
+ $token_relist[] = $this->em_strong_relist["$em$strong"];
+ }
+ $token_relist[] = $em_re;
+ $token_relist[] = $strong_re;
+
+ # Construct master expression from list.
+ $token_re = '{('. implode('|', $token_relist) .')}';
+ $this->em_strong_prepared_relist["$em$strong"] = $token_re;
+ }
+ }
}
- function _doItalicAndBold_strong_callback($matches) {
- $text = $matches[2];
- $text = $this->runSpanGamut($text);
- return $this->hashPart("<strong>$text</strong>");
+
+ function doItalicsAndBold($text) {
+ $token_stack = array('');
+ $text_stack = array('');
+ $em = '';
+ $strong = '';
+ $tree_char_em = false;
+
+ while (1) {
+ #
+ # Get prepared regular expression for seraching emphasis tokens
+ # in current context.
+ #
+ $token_re = $this->em_strong_prepared_relist["$em$strong"];
+
+ #
+ # Each loop iteration search for the next emphasis token.
+ # Each token is then passed to handleSpanToken.
+ #
+ $parts = preg_split($token_re, $text, 2, PREG_SPLIT_DELIM_CAPTURE);
+ $text_stack[0] .= $parts[0];
+ $token =& $parts[1];
+ $text =& $parts[2];
+
+ if (empty($token)) {
+ # Reached end of text span: empty stack without emitting.
+ # any more emphasis.
+ while ($token_stack[0]) {
+ $text_stack[1] .= array_shift($token_stack);
+ $text_stack[0] .= array_shift($text_stack);
+ }
+ break;
+ }
+
+ $token_len = strlen($token);
+ if ($tree_char_em) {
+ # Reached closing marker while inside a three-char emphasis.
+ if ($token_len == 3) {
+ # Three-char closing marker, close em and strong.
+ array_shift($token_stack);
+ $span = array_shift($text_stack);
+ $span = $this->runSpanGamut($span);
+ $span = "<strong><em>$span</em></strong>";
+ $text_stack[0] .= $this->hashPart($span);
+ $em = '';
+ $strong = '';
+ } else {
+ # Other closing marker: close one em or strong and
+ # change current token state to match the other
+ $token_stack[0] = str_repeat($token{0}, 3-$token_len);
+ $tag = $token_len == 2 ? "strong" : "em";
+ $span = $text_stack[0];
+ $span = $this->runSpanGamut($span);
+ $span = "<$tag>$span</$tag>";
+ $text_stack[0] = $this->hashPart($span);
+ $$tag = ''; # $$tag stands for $em or $strong
+ }
+ $tree_char_em = false;
+ } else if ($token_len == 3) {
+ if ($em) {
+ # Reached closing marker for both em and strong.
+ # Closing strong marker:
+ for ($i = 0; $i < 2; ++$i) {
+ $shifted_token = array_shift($token_stack);
+ $tag = strlen($shifted_token) == 2 ? "strong" : "em";
+ $span = array_shift($text_stack);
+ $span = $this->runSpanGamut($span);
+ $span = "<$tag>$span</$tag>";
+ $text_stack[0] .= $this->hashPart($span);
+ $$tag = ''; # $$tag stands for $em or $strong
+ }
+ } else {
+ # Reached opening three-char emphasis marker. Push on token
+ # stack; will be handled by the special condition above.
+ $em = $token{0};
+ $strong = "$em$em";
+ array_unshift($token_stack, $token);
+ array_unshift($text_stack, '');
+ $tree_char_em = true;
+ }
+ } else if ($token_len == 2) {
+ if ($strong) {
+ # Unwind any dangling emphasis marker:
+ if (strlen($token_stack[0]) == 1) {
+ $text_stack[1] .= array_shift($token_stack);
+ $text_stack[0] .= array_shift($text_stack);
+ }
+ # Closing strong marker:
+ array_shift($token_stack);
+ $span = array_shift($text_stack);
+ $span = $this->runSpanGamut($span);
+ $span = "<strong>$span</strong>";
+ $text_stack[0] .= $this->hashPart($span);
+ $strong = '';
+ } else {
+ array_unshift($token_stack, $token);
+ array_unshift($text_stack, '');
+ $strong = $token;
+ }
+ } else {
+ # Here $token_len == 1
+ if ($em) {
+ if (strlen($token_stack[0]) == 1) {
+ # Closing emphasis marker:
+ array_shift($token_stack);
+ $span = array_shift($text_stack);
+ $span = $this->runSpanGamut($span);
+ $span = "<em>$span</em>";
+ $text_stack[0] .= $this->hashPart($span);
+ $em = '';
+ } else {
+ $text_stack[0] .= $token;
+ }
+ } else {
+ array_unshift($token_stack, $token);
+ array_unshift($text_stack, '');
+ $em = $token;
+ }
+ }
+ }
+ return $text_stack[0];
}
# 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'), $bq);
+ array(&$this, '_doBlockQuotes_callback2'), $bq);
return "\n". $this->hashBlock("<blockquote>\n$bq\n</blockquote>")."\n\n";
}
}
+ 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.
+ #
+ # 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);
- $text = str_replace('<', '<', $text);
- return $text;
+ } else {
+ # Ampersand-encoding based entirely on Nat Irons's Amputator
+ # MT plugin: <http://bumppo.net/projects/amputator/>
+ $text = preg_replace('/&(?!#?[xX]?(?:[0-9a-fA-F]+|\w+);)/',
+ '&', $text);;
}
-
- # Ampersand-encoding based entirely on Nat Irons's Amputator MT plugin:
- # http://bumppo.net/projects/amputator/
- $text = preg_replace('/&(?!#?[xX]?(?:[0-9a-fA-F]+|\w+);)/',
- '&', $text);;
-
- # Encode naked <'s
- $text = preg_replace('{<(?![a-z/?\$!%])}i', '<', $text);
+ # Encode remaining <'s
+ $text = str_replace('<', '<', $text);
return $text;
}
function doAutoLinks($text) {
- $text = preg_replace_callback('{<((https?|ftp|dict):[^\'">\s]+)>}',
+ $text = preg_replace_callback('{<((https?|ftp|dict):[^\'">\s]+)>}i',
array(&$this, '_doAutoLinks_url_callback'), $text);
# Email addresses: <address@domain.foo>
<
(?:mailto:)?
(
- [-.\w\x80-\xFF]+
+ (?:
+ [-!#$%&\'*+/=?^_`.{|}~\w\x80-\xFF]+
+ |
+ ".*?"
+ )
\@
- [-a-z0-9\x80-\xFF]+(\.[-a-z0-9\x80-\xFF]+)*\.[a-z]+
+ (?:
+ [-a-z0-9\x80-\xFF]+(\.[-a-z0-9\x80-\xFF]+)*\.[a-z]+
+ |
+ \[[\d.a-fA-F:]+\] # IPv4 & IPv6
+ )
)
>
}xi',
return $text;
}
function _doAutoLinks_url_callback($matches) {
- $url = $this->encodeAmpsAndAngles($matches[1]);
+ $url = $this->encodeAttribute($matches[1]);
$link = "<a href=\"$url\">$url</a>";
return $this->hashPart($link);
}
#
$output = '';
- $regex = '{
+ $span_re = '{
(
- \\\\['.preg_quote($this->escape_chars).']
+ \\\\'.$this->escape_chars_re.'
|
(?<![`\\\\])
`+ # code span marker
|
<\?.*?\?> | <%.*?%> # processing instruction
|
- <[/!$]?[-a-zA-Z0-9:]+ # regular tags
+ <[/!$]?[-a-zA-Z0-9:_]+ # regular tags
(?>
\s
(?>[^"\'>]+|"[^"]*"|\'[^\']*\')*
# openning code span marker, or the next escaped character.
# Each token is then passed to handleSpanToken.
#
- $parts = preg_split($regex, $str, 2, PREG_SPLIT_DELIM_CAPTURE);
+ $parts = preg_split($span_re, $str, 2, PREG_SPLIT_DELIM_CAPTURE);
# Create token from text preceding tag.
if ($parts[0] != "") {
return $this->hashPart("&#". ord($token{1}). ";");
case "`":
# Search for end marker in remaining text.
- if (preg_match('/^(.*?[^`])'.$token.'(?!`)(.*)$/sm',
+ if (preg_match('/^(.*?[^`])'.preg_quote($token).'(?!`)(.*)$/sm',
$str, $matches))
{
$str = $matches[2];
}
-/**
- * Markdown Extra Parser Class
- *
- * @package moodlecore
- * @copyright (c) 2004-2006 John Gruber
- */
+#
+# Markdown Extra Parser Class
+#
+
class MarkdownExtra_Parser extends Markdown_Parser {
# Prefix for footnote ids.
# 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() {
# 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,
);
}
- # Extra hashes used during extra transformations.
+ # Extra variables used during extra transformations.
var $footnotes = array();
var $footnotes_ordered = array();
var $abbr_desciptions = array();
- var $abbr_matches = array();
+ var $abbr_word_re = '';
- # Status flag to avoid invalid nesting.
- var $in_footnote = false;
+ # Give the current footnote number.
+ var $footnote_counter = 1;
- function transform($text) {
+ function setup() {
#
- # Added clear to the new $html_hashes, reordered `hashHTMLBlocks` before
- # blank line stripping and added extra parameter to `runBlockGamut`.
+ # Setting up Extra-specific variables.
#
- # Clear the global hashes. If we don't clear these, you get conflicts
- # from other articles when generating a page which contains more than
- # one article (e.g. an index page that shows the N most recent
- # articles):
+ parent::setup();
+
$this->footnotes = array();
$this->footnotes_ordered = array();
$this->abbr_desciptions = array();
- $this->abbr_matches = array();
-
- return parent::transform($text);
+ $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 = 'p|div|h[1-6]|blockquote|pre|table|dl|ol|ul|address|form|fieldset|iframe|hr|legend';
+ 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 = 'script|noscript|math|ins|del';
+ var $context_block_tags_re = 'script|noscript|math|ins|del';
# Tags where markdown="1" default to span mode:
- var $contain_span_tags = 'p|h[1-6]|li|dd|dt|td|th|legend|address';
+ 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 = 'script|math';
+ var $clean_tags_re = 'script|math';
# Tags that do not need to be closed.
- var $auto_close_tags = 'hr|img';
+ var $auto_close_tags_re = 'hr|img';
function hashHTMLBlocks($text) {
return $text;
}
function _hashHTMLBlocks_inMarkdown($text, $indent = 0,
- $enclosing_tag = '', $span = false)
+ $enclosing_tag_re = '', $span = false)
{
#
# Parse markdown text, calling _HashHTMLBlocks_InHTML for block tags.
# If you don't like this, just don't indent the tag on which
# you apply the markdown="1" attribute.
#
- # * If $enclosing_tag is not empty, stops at the first unmatched closing
+ # * If $enclosing_tag_re is not empty, stops at the first unmatched closing
# tag with that name. Nested tags supported.
#
# * If $span is true, text inside must treated as span. So any double
if ($text === '') return array('', '');
# Regex to check for the presense of newlines around a block tag.
- $newline_match_before = '/(?:^\n?|\n\n)*$/';
- $newline_match_after =
+ $newline_before_re = '/(?:^\n?|\n\n)*$/';
+ $newline_after_re =
'{
^ # Start of text following the tag.
- (?:[ ]*<!--.*?-->)? # Optional comment.
+ (?>[ ]*<!--.*?-->)? # Optional comment.
[ ]*\n # Must be followed by newline.
}xs';
# Regex to match any tag.
- $block_tag_match =
+ $block_tag_re =
'{
( # $2: Capture hole tag.
</? # Any opening or closing tag.
- (?: # Tag name.
- '.$this->block_tags.' |
- '.$this->context_block_tags.' |
- '.$this->clean_tags.' |
- (?!\s)'.$enclosing_tag.'
+ (?> # Tag name.
+ '.$this->block_tags_re.' |
+ '.$this->context_block_tags_re.' |
+ '.$this->clean_tags_re.' |
+ (?!\s)'.$enclosing_tag_re.'
)
- \s* # Whitespace.
- (?>
- ".*?" | # Double quotes (can contain `>`)
- \'.*?\' | # Single quotes (can contain `>`)
- .+? # Anything but quotes and `>`.
- )*?
+ (?:
+ (?=[\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';
# pattern will be at the end, and between will be any catches made
# by the pattern.
#
- $parts = preg_split($block_tag_match, $text, 2,
+ $parts = preg_split($block_tag_re, $text, 2,
PREG_SPLIT_DELIM_CAPTURE);
# If in Markdown span mode, add a empty-string span-level hash
$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: Tag inside code block or span
+ # Check for: Code span marker
#
- if (# Find current paragraph
- preg_match('/(?>^\n?|\n\n)((?>.+\n?)*?)$/', $parsed, $matches) &&
- (
- # Then match in it either a code block...
- preg_match('/^ {'.($indent+4).'}.*(?>\n {'.($indent+4).'}.*)*'.
- '(?!\n)$/', $matches[1], $x) ||
- # ...or unbalenced code span markers. (the regex matches balenced)
- !preg_match('/^(?>[^`]+|(`+)(?>[^`]+|(?!\1[^`])`)*?\1(?!`))*$/s',
- $matches[1])
- ))
- {
- # Tag is in code block or span and may not be a tag at all. So we
- # simply skip the first char (should be a `<`).
- $parsed .= $tag{0};
- $text = substr($tag, 1) . $text; # Put back $tag minus first char.
+ if ($tag{0} == "`") {
+ # Find corresponding end marker.
+ $tag_re = preg_quote($tag);
+ if (preg_match('{^(?>.+?|\n(?!\n))*?(?<!`)'.$tag_re.'(?!`)}',
+ $text, $matches))
+ {
+ # End marker found: pass text unchanged until marker.
+ $parsed .= $tag . $matches[0];
+ $text = substr($text, strlen($matches[0]));
+ }
+ else {
+ # Unmatched marker: just skip it.
+ $parsed .= $tag;
+ }
+ }
+ #
+ # Check for: Indented code block.
+ #
+ else if ($tag{0} == "\n" || $tag{0} == " ") {
+ # Indented code block: pass it unchanged, will be handled
+ # later.
+ $parsed .= $tag;
+ }
+ #
+ # Check for: Fenced code block marker.
+ #
+ else if ($tag{0} == "~") {
+ # Fenced code block marker: find matching end marker.
+ $tag_re = preg_quote(trim($tag));
+ if (preg_match('{^(?>.*\n)+?'.$tag_re.' *\n}', $text,
+ $matches))
+ {
+ # End marker found: pass text unchanged until marker.
+ $parsed .= $tag . $matches[0];
+ $text = substr($text, strlen($matches[0]));
+ }
+ else {
+ # No end marker: just skip it.
+ $parsed .= $tag;
+ }
}
#
# Check for: Opening Block level tag or
- # Opening Content Block tag (like ins and del)
+ # Opening Context Block tag (like ins and del)
# used as a block tag (tag is alone on it's line).
#
- else if (preg_match("{^<(?:$this->block_tags)\b}", $tag) ||
- ( preg_match("{^<(?:$this->context_block_tags)\b}", $tag) &&
- preg_match($newline_match_before, $parsed) &&
- preg_match($newline_match_after, $text) )
+ else if (preg_match('{^<(?:'.$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, $text) )
)
{
# Need to parse tag and following text using the HTML parser.
# Check for: Clean tag (like script, math)
# HTML Comments, processing instructions.
#
- else if (preg_match("{^<(?:$this->clean_tags)\b}", $tag) ||
+ else if (preg_match('{^<(?:'.$this->clean_tags_re.')\b}', $tag) ||
$tag{1} == '!' || $tag{1} == '?')
{
# Need to parse tag and following text using the HTML parser.
#
# Check for: Tag with same name as enclosing tag.
#
- else if ($enclosing_tag !== '' &&
+ else if ($enclosing_tag_re !== '' &&
# Same name as enclosing tag.
- preg_match("{^</?(?:$enclosing_tag)\b}", $tag))
+ preg_match('{^</?(?:'.$enclosing_tag_re.')\b}', $tag))
{
#
# Increase/decrease nested tag count.
if ($text === '') return array('', '');
# Regex to match `markdown` attribute inside of a tag.
- $markdown_attr_match = '
+ $markdown_attr_re = '
{
\s* # Eat whitespace before the `markdown` attribute
markdown
\s*=\s*
- (?:
+ (?>
(["\']) # $1: quote delimiter
(.*?) # $2: attribute value
\1 # matching delimiter
}xs';
# Regex to match any tag.
- $tag_match = '{
+ $tag_re = '{
( # $2: Capture hole tag.
</? # Any opening or closing tag.
[\w:$]+ # Tag name.
- \s* # Whitespace.
- (?>
- ".*?" | # Double quotes (can contain `>`)
- \'.*?\' | # Single quotes (can contain `>`)
- .+? # Anything but quotes and `>`.
- )*?
+ (?:
+ (?=[\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
#
# 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 = $matches[1];
+ if (preg_match('/^<([\w:$]*)\b/', $text, $matches))
+ $base_tag_name_re = $matches[1];
#
# Loop through every tag until we find the corresponding closing tag.
# pattern will be at the end, and between will be any catches made
# by the pattern.
#
- $parts = preg_split($tag_match, $text, 2, PREG_SPLIT_DELIM_CAPTURE);
+ $parts = preg_split($tag_re, $text, 2, PREG_SPLIT_DELIM_CAPTURE);
if (count($parts) < 3) {
#
# Check for: Auto-close tag (like <hr/>)
# Comments and Processing Instructions.
#
- if (preg_match("{^</?(?:$this->auto_close_tags)\b}", $tag) ||
+ if (preg_match('{^</?(?:'.$this->auto_close_tags_re.')\b}', $tag) ||
$tag{1} == '!' || $tag{1} == '?')
{
# Just add the tag to the block as if it was text.
# Increase/decrease nested tag count. Only do so if
# the tag's name match base tag's.
#
- if (preg_match("{^</?$base_tag_name\b}", $tag)) {
+ if (preg_match('{^</?'.$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_match, $tag, $attr_m) &&
+ preg_match($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_match, '', $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)\b}", $tag);
+ preg_match('{^<(?:'.$this->contain_span_tags_re.')\b}', $tag);
# Calculate indent before tag.
- preg_match('/(?:^|\n)( *?)(?! ).*?$/', $block_text, $matches);
- $indent = strlen($matches[1]);
+ 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 = $matches[1];
+ $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, $span_mode);
+ $tag_name_re, $span_mode);
# Outdent markdown text.
if ($indent > 0) {
return " id=\"$attr\"";
}
function _doHeaders_callback_setext($matches) {
+ if ($matches[3] == '-' && preg_match('{^- }', $matches[1]))
+ return $matches[0];
$level = $matches[3]{0} == '=' ? 1 : 2;
$attr = $this->_doHeaders_attr($id =& $matches[2]);
$block = "<h$level$attr>".$this->runSpanGamut($matches[1])."</h$level>";
$less_than_tab = $this->tab_width - 1;
# Re-usable pattern to match any entire dl list:
- $whole_list = '(?>
+ $whole_list_re = '(?>
( # $1 = whole list
( # $2
[ ]{0,'.$less_than_tab.'}
)'; // mx
$text = preg_replace_callback('{
- (?:(?<=\n\n)|\A\n?)
- '.$whole_list.'
+ (?>\A\n?|(?<=\n\n))
+ '.$whole_list_re.'
}mx',
array(&$this, '_doDefLists_callback'), $text);
# Process definition terms.
$list_str = preg_replace_callback('{
- (?:\n\n+|\A\n?) # leading line
+ (?>\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).
+ (?> \S.* \n)+? # actual term (not whitespace).
)
(?=\n?[ ]{0,3}:[ ]) # lookahead for following line feed
# with a definition mark.
# Process actual definitions.
$list_str = preg_replace_callback('{
\n(\n+)? # leading line = $1
- [ ]{0,'.$less_than_tab.'} # whitespace before colon
- [:][ ]+ # definition mark (colon)
- ((?s:.+?)) # definition text = $2
+ ( # 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.'} [:][ ] |
}
function _processDefListItems_callback_dd($matches) {
$leading_line = $matches[1];
- $def = $matches[2];
+ $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". $def ."\n";
}
}
- function doItalicsAndBold($text) {
+ function doFencedCodeBlocks($text) {
#
- # Redefined to change emphasis by underscore behaviour so that it does not
- # work in the middle of a word.
+ # Adding the fenced code block syntax to regular Markdown:
#
- # <strong> must go first:
- $text = preg_replace_callback(array(
- '{
- ( # $1: Marker
- (?<![a-zA-Z0-9]) # Not preceded by alphanum
- (?<!__) # or by two marker chars.
- __
- )
- (?=\S) # Not followed by whitespace
- (?!__) # or two others marker chars.
- ( # $2: Content
- (?>
- [^_]+? # Anthing not em markers.
- |
- # Balence any regular _ emphasis inside.
- (?<![a-zA-Z0-9]) _ (?=\S) (.+?)
- (?<=\S) _ (?![a-zA-Z0-9])
- |
- _+ # Allow unbalenced as last resort.
- )+?
+ # ~~~
+ # Code block
+ # ~~~
+ #
+ $less_than_tab = $this->tab_width;
+
+ $text = preg_replace_callback('{
+ (?:\n|\A)
+ # 1: Opening marker
+ (
+ ~{3,} # Marker: three tilde or more.
)
- (?<=\S) __ # End mark not preceded by whitespace.
- (?![a-zA-Z0-9]) # Not followed by alphanum
- (?!__) # or two others marker chars.
- }sx',
- '{
- ( (?<!\*\*) \*\* ) # $1: Marker (not preceded by two *)
- (?=\S) # Not followed by whitespace
- (?!\1) # or two others marker chars.
- ( # $2: Content
+ [ ]* \n # Whitespace and newline following marker.
+
+ # 2: Content
+ (
(?>
- [^*]+? # Anthing not em markers.
- |
- # Balence any regular * emphasis inside.
- \* (?=\S) (.+?) (?<=\S) \*
- |
- \* # Allow unbalenced as last resort.
- )+?
+ (?!\1 [ ]* \n) # Not a closing marker.
+ .*\n+
+ )+
)
- (?<=\S) \*\* # End mark not preceded by whitespace.
- }sx',
- ),
- array(&$this, '_doItalicAndBold_strong_callback'), $text);
- # Then <em>:
- $text = preg_replace_callback(array(
- '{ ( (?<![a-zA-Z0-9])(?<!_)_ ) (?=\S) (?! \1) (.+?) (?<=\S) \1(?![a-zA-Z0-9]) }sx',
- '{ ( (?<!\*)\* ) (?=\S) (?! \1) (.+?) (?<=\S)(?<!\s\*) \1 }sx',
- ),
- array(&$this, '_doItalicAndBold_em_callback'), $text);
+
+ # Closing marker.
+ \1 [ ]* \n
+ }xm',
+ array(&$this, '_doFencedCodeBlocks_callback'), $text);
return $text;
}
+ function _doFencedCodeBlocks_callback($matches) {
+ $codeblock = $matches[2];
+ $codeblock = htmlspecialchars($codeblock, ENT_NOQUOTES);
+ $codeblock = preg_replace_callback('/^\n+/',
+ array(&$this, '_doFencedCodeBlocks_newlines'), $codeblock);
+ $codeblock = "<pre><code>$codeblock</code></pre>";
+ return "\n\n".$this->hashBlock($codeblock)."\n\n";
+ }
+ function _doFencedCodeBlocks_newlines($matches) {
+ return str_repeat("<br$this->empty_element_suffix",
+ strlen($matches[0]));
+ }
+
+
+ #
+ # Redefining emphasis markers so that emphasis by underscore does not
+ # work in the middle of a word.
+ #
+ var $em_relist = array(
+ '' => '(?:(?<!\*)\*(?!\*)|(?<![a-zA-Z0-9_])_(?!_))(?=\S|$)(?![.,:;]\s)',
+ '*' => '(?<=\S|^)(?<!\*)\*(?!\*)',
+ '_' => '(?<=\S|^)(?<!_)_(?![a-zA-Z0-9_])',
+ );
+ var $strong_relist = array(
+ '' => '(?:(?<!\*)\*\*(?!\*)|(?<![a-zA-Z0-9_])__(?!_))(?=\S|$)(?![.,:;]\s)',
+ '**' => '(?<=\S|^)(?<!\*)\*\*(?!\*)',
+ '__' => '(?<=\S|^)(?<!_)__(?![a-zA-Z0-9_])',
+ );
+ var $em_strong_relist = array(
+ '' => '(?:(?<!\*)\*\*\*(?!\*)|(?<![a-zA-Z0-9_])___(?!_))(?=\S|$)(?![.,:;]\s)',
+ '***' => '(?<=\S|^)(?<!\*)\*\*\*(?!\*)',
+ '___' => '(?<=\S|^)(?<!_)___(?![a-zA-Z0-9_])',
+ );
function formParagraphs($text) {
function doFootnotes($text) {
#
# Replace footnote references in $text [^id] with a special text-token
- # which will be can be
+ # which will be replaced by the actual footnote marker in appendFootnotes.
#
- if (!$this->in_footnote && !$this->in_anchor) {
+ if (!$this->in_anchor) {
$text = preg_replace('{\[\^(.+?)\]}', "F\x1Afn:\\1\x1A:", $text);
}
return $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 .= "<hr". $this->empty_element_suffix ."\n";
$text .= "<ol>\n\n";
$attr = " rev=\"footnote\"";
if ($this->fn_backlink_class != "") {
$class = $this->fn_backlink_class;
- $class = $this->encodeAmpsAndAngles($class);
- $class = str_replace('"', '"', $class);
+ $class = $this->encodeAttribute($class);
$attr .= " class=\"$class\"";
}
if ($this->fn_backlink_title != "") {
$title = $this->fn_backlink_title;
- $title = $this->encodeAmpsAndAngles($title);
- $title = str_replace('"', '"', $title);
+ $title = $this->encodeAttribute($title);
$attr .= " title=\"$title\"";
}
$num = 0;
- $this->in_footnote = true;
-
- foreach ($this->footnotes_ordered as $note_id => $footnote) {
+ while (!empty($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 = $this->runBlockGamut("$footnote\n");
+ $footnote = preg_replace_callback('{F\x1Afn:(.*?)\x1A:}',
+ array(&$this, '_appendFootnotes_callback'), $footnote);
- $attr2 = str_replace("%%", ++$num, $attr);
+ $attr = str_replace("%%", ++$num, $attr);
+ $note_id = $this->encodeAttribute($note_id);
# Add backlink to last paragraph; create new paragraph if needed.
- $backlink = "<a href=\"#fnref:$note_id\"$attr2>↩</a>";
+ $backlink = "<a href=\"#fnref:$note_id\"$attr>↩</a>";
if (preg_match('{</p>$}', $footnote)) {
$footnote = substr($footnote, 0, -4) . " $backlink</p>";
} else {
$text .= "</li>\n\n";
}
- $this->in_footnote = false;
-
$text .= "</ol>\n";
$text .= "</div>";
}
$this->footnotes_ordered[$node_id] = $this->footnotes[$node_id];
unset($this->footnotes[$node_id]);
- $num = count($this->footnotes_ordered);
+ $num = $this->footnote_counter++;
$attr = " rel=\"footnote\"";
if ($this->fn_link_class != "") {
$class = $this->fn_link_class;
- $class = $this->encodeAmpsAndAngles($class);
- $class = str_replace('"', '"', $class);
+ $class = $this->encodeAttribute($class);
$attr .= " class=\"$class\"";
}
if ($this->fn_link_title != "") {
$title = $this->fn_link_title;
- $title = $this->encodeAmpsAndAngles($title);
- $title = str_replace('"', '"', $title);
+ $title = $this->encodeAttribute($title);
$attr .= " title=\"$title\"";
}
+
$attr = str_replace("%%", $num, $attr);
+ $node_id = $this->encodeAttribute($node_id);
return
"<sup id=\"fnref:$node_id\">".
function _stripAbbreviations_callback($matches) {
$abbr_word = $matches[1];
$abbr_desc = $matches[2];
- $this->abbr_matches[] = preg_quote($abbr_word);
+ if ($this->abbr_word_re)
+ $this->abbr_word_re .= '|';
+ $this->abbr_word_re .= preg_quote($abbr_word);
$this->abbr_desciptions[$abbr_word] = trim($abbr_desc);
return ''; # String that will replace the block
}
#
# Find defined abbreviations in text and wrap them in <abbr> elements.
#
- if ($this->abbr_matches) {
- // cannot use the /x modifier because abbr_matches may
- // contain spaces:
+ if ($this->abbr_word_re) {
+ // cannot use the /x modifier because abbr_word_re may
+ // contain significant spaces:
$text = preg_replace_callback('{'.
'(?<![\w\x1A])'.
- '(?:'. implode('|', $this->abbr_matches) .')'.
+ '(?:'.$this->abbr_word_re.')'.
'(?![\w\x1A])'.
'}',
array(&$this, '_doAbbreviations_callback'), $text);
if (empty($desc)) {
return $this->hashPart("<abbr>$abbr</abbr>");
} else {
- $desc = htmlspecialchars($desc, ENT_NOQUOTES);
+ $desc = $this->encodeAttribute($desc);
return $this->hashPart("<abbr title=\"$desc\">$abbr</abbr>");
}
} else {
}
-/**
- * PHP Markdown Extra
- * ==================
- *
- * Description
- * -----------
- *
- * This is a PHP port of the original Markdown formatter written in Perl
- * by John Gruber. This special "Extra" version of PHP Markdown features
- * further enhancements to the syntax for making additional constructs
- * such as tables and definition list.
- *
- * Markdown is a text-to-HTML filter; it translates an easy-to-read /
- * easy-to-write structured text format into HTML. Markdown's text format
- * is most similar to that of plain text email, and supports features such
- * as headers, *emphasis*, code blocks, blockquotes, and links.
- *
- * Markdown's syntax is designed not as a generic markup language, but
- * specifically to serve as a front-end to (X)HTML. You can use span-level
- * HTML tags anywhere in a Markdown document, and you can use block level
- * HTML tags (like <div> and <table> as well).
- *
- * For more information about Markdown's syntax, see:
- *
- * <http://daringfireball.net/projects/markdown/>
- *
- *
- * Bugs
- * ----
- *
- * To file bug reports please send email to:
- *
- * <michel.fortin@michelf.com>
- *
- * Please include with your report: (1) the example input; (2) the output you
- * expected; (3) the output Markdown actually produced.
- *
- *
- * Version History
- * ---------------
- *
- * See the readme file for detailed release notes for this version.
- *
- *
- * Copyright and License
- * ---------------------
- *
- * PHP Markdown & Extra
- * Copyright (c) 2004-2007 Michel Fortin
- * <http://www.michelf.com/>
- * All rights reserved.
- *
- * Based on Markdown
- * Copyright (c) 2003-2006 John Gruber
- * <http://daringfireball.net/>
- * All rights reserved.
- *
- * Redistribution and use in source and binary forms, with or without
- * modification, are permitted provided that the following conditions are
- * met:
- *
- * - Redistributions of source code must retain the above copyright notice,
- * this list of conditions and the following disclaimer.
- *
- * - Redistributions in binary form must reproduce the above copyright
- * notice, this list of conditions and the following disclaimer in the
- * documentation and/or other materials provided with the distribution.
- *
- * - Neither the name "Markdown" nor the names of its contributors may
- * be used to endorse or promote products derived from this software
- * without specific prior written permission.
- *
- * This software is provided by the copyright holders and contributors "as
- * is" and any express or implied warranties, including, but not limited
- * to, the implied warranties of merchantability and fitness for a
- * particular purpose are disclaimed. In no event shall the copyright owner
- * or contributors be liable for any direct, indirect, incidental, special,
- * exemplary, or consequential damages (including, but not limited to,
- * procurement of substitute goods or services; loss of use, data, or
- * profits; or business interruption) however caused and on any theory of
- * liability, whether in contract, strict liability, or tort (including
- * negligence or otherwise) arising in any way out of the use of this
- * software, even if advised of the possibility of such damage.
- */
+/*
+
+PHP Markdown Extra
+==================
+
+Description
+-----------
+
+This is a PHP port of the original Markdown formatter written in Perl
+by John Gruber. This special "Extra" version of PHP Markdown features
+further enhancements to the syntax for making additional constructs
+such as tables and definition list.
+
+Markdown is a text-to-HTML filter; it translates an easy-to-read /
+easy-to-write structured text format into HTML. Markdown's text format
+is most similar to that of plain text email, and supports features such
+as headers, *emphasis*, code blocks, blockquotes, and links.
+
+Markdown's syntax is designed not as a generic markup language, but
+specifically to serve as a front-end to (X)HTML. You can use span-level
+HTML tags anywhere in a Markdown document, and you can use block level
+HTML tags (like <div> and <table> as well).
+
+For more information about Markdown's syntax, see:
+
+<http://daringfireball.net/projects/markdown/>
+
+
+Bugs
+----
+
+To file bug reports please send email to:
+
+<michel.fortin@michelf.com>
+
+Please include with your report: (1) the example input; (2) the output you
+expected; (3) the output Markdown actually produced.
+
+
+Version History
+---------------
+
+See the readme file for detailed release notes for this version.
+
+
+Copyright and License
+---------------------
+
+PHP Markdown & Extra
+Copyright (c) 2004-2009 Michel Fortin
+<http://michelf.com/>
+All rights reserved.
+
+Based on Markdown
+Copyright (c) 2003-2006 John Gruber
+<http://daringfireball.net/>
+All rights reserved.
+
+Redistribution and use in source and binary forms, with or without
+modification, are permitted provided that the following conditions are
+met:
+
+* Redistributions of source code must retain the above copyright notice,
+ this list of conditions and the following disclaimer.
+
+* Redistributions in binary form must reproduce the above copyright
+ notice, this list of conditions and the following disclaimer in the
+ documentation and/or other materials provided with the distribution.
+
+* Neither the name "Markdown" nor the names of its contributors may
+ be used to endorse or promote products derived from this software
+ without specific prior written permission.
+
+This software is provided by the copyright holders and contributors "as
+is" and any express or implied warranties, including, but not limited
+to, the implied warranties of merchantability and fitness for a
+particular purpose are disclaimed. In no event shall the copyright owner
+or contributors be liable for any direct, indirect, incidental, special,
+exemplary, or consequential damages (including, but not limited to,
+procurement of substitute goods or services; loss of use, data, or
+profits; or business interruption) however caused and on any theory of
+liability, whether in contract, strict liability, or tort (including
+negligence or otherwise) arising in any way out of the use of this
+software, even if advised of the possibility of such damage.
+
+*/
?>
\ No newline at end of file
