#
-define( 'MARKDOWN_VERSION', "1.0.1f" ); # Wed 7 Feb 2007
-define( 'MARKDOWNEXTRA_VERSION', "1.1.2" ); # Wed 7 Feb 2007
+define( 'MARKDOWN_VERSION', "1.0.1h" ); # Fri 3 Aug 2007
+define( 'MARKDOWNEXTRA_VERSION', "1.1.4" ); # Fri 3 Aug 2007
#
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: 1.1.2
+Version: 1.1.4
Author: Michel Fortin
Author URI: http://www.michelf.com/
*/
# - Run Markdown on excerpt, then remove all tags.
# - Add paragraph tag around the excerpt, but remove it for the excerpt rss.
if (MARKDOWN_WP_POSTS) {
- remove_filter('the_content', 'wpautop');
- remove_filter('the_excerpt', 'wpautop');
+ remove_filter('the_content', 'wpautop');
+ remove_filter('the_content_rss', 'wpautop');
+ remove_filter('the_excerpt', 'wpautop');
add_filter('the_content', 'Markdown', 6);
+ add_filter('the_content_rss', 'Markdown', 6);
add_filter('get_the_excerpt', 'Markdown', 6);
add_filter('get_the_excerpt', 'trim', 7);
add_filter('the_excerpt', 'mdwp_add_p');
# - Scramble important tags before passing them to the kses filter.
# - Run Markdown on excerpt then remove paragraph tags.
if (MARKDOWN_WP_COMMENTS) {
- remove_filter('comment_text', 'wpautop');
+ remove_filter('comment_text', 'wpautop', 30);
remove_filter('comment_text', 'make_clickable');
add_filter('pre_comment_content', 'Markdown', 6);
add_filter('pre_comment_content', 'mdwp_hide_tags', 8);
add_filter('get_comment_excerpt', 'Markdown', 6);
add_filter('get_comment_excerpt', 'mdwp_strip_p', 7);
- global $markdown_hidden_tags;
- $markdown_hidden_tags = array(
- '<p>' => md5('<p>'), '</p>' => md5('</p>'),
- '<pre>' => md5('<pre>'), '</pre>'=> md5('</pre>'),
- '<ol>' => md5('<ol>'), '</ol>' => md5('</ol>'),
- '<ul>' => md5('<ul>'), '</ul>' => md5('</ul>'),
- '<li>' => md5('<li>'), '</li>' => md5('</li>'),
- );
+ global $mdwp_hidden_tags, $mdwp_placeholders;
+ $mdwp_hidden_tags = explode(' ',
+ '<p> </p> <pre> </pre> <ol> </ol> <ul> </ul> <li> </li>');
+ $mdwp_placeholders = explode(' ', str_rot13(
+ 'pEj07ZbbBZ U1kqgh4w4p pre2zmeN6K QTi31t9pre ol0MP1jzJR '.
+ 'ML5IjmbRol ulANi1NsGY J7zRLJqPul liA8ctl16T K9nhooUHli'));
}
function mdwp_add_p($text) {
function mdwp_strip_p($t) { return preg_replace('{</?p>}i', '', $t); }
function mdwp_hide_tags($text) {
- global $markdown_hidden_tags;
- return str_replace(array_keys($markdown_hidden_tags),
- array_values($markdown_hidden_tags), $text);
+ global $mdwp_hidden_tags, $mdwp_placeholders;
+ return str_replace($mdwp_hidden_tags, $mdwp_placeholders, $text);
}
function mdwp_show_tags($text) {
- global $markdown_hidden_tags;
- return str_replace(array_values($markdown_hidden_tags),
- array_keys($markdown_hidden_tags), $text);
+ global $mdwp_hidden_tags, $mdwp_placeholders;
+ return str_replace($mdwp_placeholders, $mdwp_hidden_tags, $text);
}
}
# Needed to insert a maximum bracked depth while converting to PHP.
var $nested_brackets_depth = 6;
var $nested_brackets;
+
+ var $nested_url_parenthesis_depth = 4;
+ var $nested_url_parenthesis;
# Table of hash values for escaped characters:
var $escape_chars = '\`*_{}[]()>#+-.!';
- var $escape_table = array();
+// var $escape_table = array();
var $backslash_escape_table = array();
# Change to ">" for HTML output.
var $empty_element_suffix = MARKDOWN_EMPTY_ELEMENT_SUFFIX;
var $tab_width = MARKDOWN_TAB_WIDTH;
+
+ # Change to `true` to disallow markup or entities.
+ var $no_markup = false;
+ var $no_entities = false;
function Markdown_Parser() {
$this->nested_brackets =
str_repeat('(?>[^\[\]]+|\[', $this->nested_brackets_depth).
str_repeat('\])*', $this->nested_brackets_depth);
+
+ $this->nested_url_parenthesis =
+ str_repeat('(?>[^()\s]+|\(', $this->nested_url_parenthesis_depth).
+ str_repeat('(?>\)))*', $this->nested_url_parenthesis_depth);
# Create an identical table but for escaped characters.
foreach (preg_split('/(?!^|$)/', $this->escape_chars) as $char) {
- $hash = md5($char);
- $this->escape_table[$char] = $hash;
- $this->backslash_escape_table["\\$char"] = $hash;
+ $entity = "&#". ord($char). ";";
+// $this->escape_table[$char] = $entity;
+ $this->backslash_escape_table["\\$char"] = $entity;
}
# Sort document, block, and span gamut in ascendent priority order.
var $titles = array();
var $html_blocks = array();
var $html_hashes = array(); # Contains both blocks and span hashes.
+
+ # Status flag to avoid invalid nesting.
+ var $in_anchor = false;
function transform($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 /[ \t]*\n+/ .
- $text = preg_replace('/^[ \t]+$/m', '', $text);
+ # contorted like /[ ]*\n+/ .
+ $text = preg_replace('/^[ ]+$/m', '', $text);
# Run document gamut methods.
foreach ($this->document_gamut as $method => $priority) {
"stripLinkDefinitions" => 20,
"runBasicBlockGamut" => 30,
- "unescapeSpecialChars" => 90,
);
# Link defs are in the form: ^[id]: url "optional title"
$text = preg_replace_callback('{
^[ ]{0,'.$less_than_tab.'}\[(.+)\][ ]?: # id = $1
- [ \t]*
+ [ ]*
\n? # maybe *one* newline
- [ \t]*
+ [ ]*
<?(\S+?)>? # url = $2
- [ \t]*
+ [ ]*
\n? # maybe one newline
- [ \t]*
+ [ ]*
(?:
(?<=\s) # lookbehind for whitespace
["(]
(.*?) # title = $3
[")]
- [ \t]*
+ [ ]*
)? # title is optional
(?:\n+|\Z)
}xm',
function hashHTMLBlocks($text) {
+ if ($this->no_markup) return $text;
+
$less_than_tab = $this->tab_width - 1;
# Hashify HTML blocks:
'.$attr.'>\n # attributes followed by > and \n
'.$content.' # content, support nesting
</\2> # the matching end tag
- [ \t]* # trailing spaces/tabs
+ [ ]* # trailing spaces/tabs
(?=\n+|\Z) # followed by a newline or end of document
)
- }xm',
+ }xmi',
array(&$this, '_hashHTMLBlocks_callback'),
$text);
'.$attr.'> # attributes followed by >
'.$content.' # content, support nesting
</\2> # the matching end tag
- [ \t]* # trailing spaces/tabs
+ [ ]* # trailing spaces/tabs
(?=\n+|\Z) # followed by a newline or end of document
)
- }xm',
+ }xmi',
array(&$this, '_hashHTMLBlocks_callback'),
$text);
\b # word break
([^<>])*? #
/?> # the matching end tag
- [ \t]*
+ [ ]*
(?=\n{2,}|\Z) # followed by a blank line or end of document
)
- }x',
+ }xi',
array(&$this, '_hashHTMLBlocks_callback'),
$text);
(?s:
<!-- .*? -->
)
- [ \t]*
+ [ ]*
(?=\n{2,}|\Z) # followed by a blank line or end of document
)
}x',
.*?
\2>
)
- [ \t]*
+ [ ]*
(?=\n{2,}|\Z) # followed by a blank line or end of document
)
}x',
$text = $this->unhash($text);
# Then hash the block.
- $key = md5($text);
+ $key = "B\x1A". md5($text);
$this->html_hashes[$key] = $text;
$this->html_blocks[$key] = $text;
return $key; # String that will replace the tag.
}
- function hashSpan($text) {
+ function hashSpan($text, $word_separator = false) {
#
# Called whenever a tag must be hashed when a function insert a span-level
# element in $text, it pass through this function and is automaticaly
- # escaped, blocking invalid nested overlap.
+ # escaped, blocking invalid nested overlap. If optional argument
+ # $word_separator is true, surround the hash value by spaces.
#
# 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 span.
- $key = md5($text);
+ $key = "S\x1A". md5($text);
+ if ($word_separator) $key = ":$key:";
+
$this->html_hashes[$key] = $text;
return $key; # String that will replace the span tag.
}
function doHorizontalRules($text) {
# Do Horizontal Rules:
return preg_replace(
- array('{^[ ]{0,2}([ ]?\*[ ]?){3,}[ \t]*$}mx',
- '{^[ ]{0,2}([ ]? -[ ]?){3,}[ \t]*$}mx',
- '{^[ ]{0,2}([ ]? _[ ]?){3,}[ \t]*$}mx'),
+ array('{^[ ]{0,2}([ ]?\*[ ]?){3,}[ ]*$}mx',
+ '{^[ ]{0,2}([ ]? -[ ]?){3,}[ ]*$}mx',
+ '{^[ ]{0,2}([ ]? _[ ]?){3,}[ ]*$}mx'),
"\n".$this->hashBlock("<hr$this->empty_element_suffix")."\n",
$text);
}
# value; this is likely overkill, but it should prevent us from colliding
# with the escape values by accident.
#
+ if ($this->no_markup) return $text;
+
$tokens = $this->tokenizeHTML($text);
$text = ''; # rebuild $text from the tokens
foreach ($tokens as $cur_token) {
if ($cur_token[0] == 'tag') {
- $cur_token[1] = str_replace('\\', $this->escape_table['\\'], $cur_token[1]);
- $cur_token[1] = str_replace(array('`'), $this->escape_table['`'], $cur_token[1]);
- $cur_token[1] = str_replace('*', $this->escape_table['*'], $cur_token[1]);
- $cur_token[1] = str_replace('_', $this->escape_table['_'], $cur_token[1]);
+// $cur_token[1] = str_replace('\\', $this->escape_table['\\'], $cur_token[1]);
+// $cur_token[1] = str_replace('`', $this->escape_table['`'], $cur_token[1]);
+// $cur_token[1] = str_replace('*', $this->escape_table['*'], $cur_token[1]);
+// $cur_token[1] = str_replace('_', $this->escape_table['_'], $cur_token[1]);
+ $cur_token[1] = $this->hashSpan($cur_token[1]);
}
$text .= $cur_token[1];
}
#
# Turn Markdown link shortcuts into XHTML <a> tags.
#
+ if ($this->in_anchor) return $text;
+ $this->in_anchor = true;
+
#
# First, handle reference-style links: [link text] [id]
#
('.$this->nested_brackets.') # link text = $2
\]
\( # literal paren
- [ \t]*
- <?(.*?)>? # href = $3
- [ \t]*
- ( # $4
- ([\'"]) # quote char = $5
- (.*?) # Title = $6
- \5 # matching quote
- [ \t]* # ignore any spaces/tabs between closing quote and )
+ [ ]*
+ (?:
+ <(\S*)> # href = $3
+ |
+ ('.$this->nested_url_parenthesis.') # href = $4
+ )
+ [ ]*
+ ( # $5
+ ([\'"]) # quote char = $6
+ (.*?) # Title = $7
+ \6 # matching quote
+ [ ]* # ignore any spaces/tabs between closing quote and )
)? # title is optional
\)
)
// }xs',
// array(&$this, '_doAnchors_reference_callback'), $text);
+ $this->in_anchor = false;
return $text;
}
function _doAnchors_reference_callback($matches) {
function _doAnchors_inline_callback($matches) {
$whole_match = $matches[1];
$link_text = $this->runSpanGamut($matches[2]);
- $url = $matches[3];
- $title =& $matches[6];
-
+ $url = $matches[3] == '' ? $matches[4] : $matches[3];
+ $title =& $matches[7];
+
$url = $this->encodeAmpsAndAngles($url);
$result = "<a href=\"$url\"";
\]
\s? # One optional whitespace character
\( # literal paren
- [ \t]*
- <?(\S+?)>? # src url = $3
- [ \t]*
- ( # $4
- ([\'"]) # quote char = $5
- (.*?) # title = $6
- \5 # matching quote
- [ \t]*
+ [ ]*
+ (?:
+ <(\S*)> # src url = $3
+ |
+ ('.$this->nested_url_parenthesis.') # src url = $4
+ )
+ [ ]*
+ ( # $5
+ ([\'"]) # quote char = $6
+ (.*?) # title = $7
+ \6 # matching quote
+ [ ]*
)? # title is optional
\)
)
function _doImages_inline_callback($matches) {
$whole_match = $matches[1];
$alt_text = $matches[2];
- $url = $matches[3];
- $title =& $matches[6];
+ $url = $matches[3] == '' ? $matches[4] : $matches[3];
+ $title =& $matches[7];
$alt_text = str_replace('"', '"', $alt_text);
$result = "<img src=\"$url\" alt=\"$alt_text\"";
# Header 2
# --------
#
- $text = preg_replace_callback('{ ^(.+)[ \t]*\n=+[ \t]*\n+ }mx',
+ $text = preg_replace_callback('{ ^(.+?)[ ]*\n=+[ ]*\n+ }mx',
array(&$this, '_doHeaders_callback_setext_h1'), $text);
- $text = preg_replace_callback('{ ^(.+)[ \t]*\n-+[ \t]*\n+ }mx',
+ $text = preg_replace_callback('{ ^(.+?)[ ]*\n-+[ ]*\n+ }mx',
array(&$this, '_doHeaders_callback_setext_h2'), $text);
# atx-style headers:
#
$text = preg_replace_callback('{
^(\#{1,6}) # $1 = string of #\'s
- [ \t]*
+ [ ]*
(.+?) # $2 = Header text
- [ \t]*
+ [ ]*
\#* # optional closing #\'s (not counted)
\n+
}xm',
( # $2
[ ]{0,'.$less_than_tab.'}
('.$marker.') # $3 = first list item marker
- [ \t]+
+ [ ]+
)
(?s:.+?)
( # $4
\n{2,}
(?=\S)
(?! # Negative lookahead for another list item marker
- [ \t]*
- '.$marker.'[ \t]+
+ [ ]*
+ '.$marker.'[ ]+
)
)
)
$list_str = preg_replace_callback('{
(\n)? # leading line = $1
- (^[ \t]*) # leading whitespace = $2
- ('.$marker_any.') [ \t]+ # list marker = $3
+ (^[ ]*) # leading whitespace = $2
+ ('.$marker_any.') [ ]+ # list marker = $3
((?s:.+?)) # list item text = $4
(?:(\n+(?=\n))|\n) # tailing blank line = $5
- (?= \n* (\z | \2 ('.$marker_any.') [ \t]+))
+ (?= \n* (\z | \2 ('.$marker_any.') [ ]+))
}xm',
array(&$this, '_processListItems_callback'), $list_str);
$codeblock = $matches[1];
$codeblock = $this->encodeCode($this->outdent($codeblock));
- // $codeblock = $this->detab($codeblock);
+// $codeblock = $this->detab($codeblock);
# trim leading newlines and trailing whitespace
$codeblock = preg_replace(array('/\A\n+/', '/\n+\z/'), '', $codeblock);
}
function _doCodeSpans_callback($matches) {
$c = $matches[2];
- $c = preg_replace('/^[ \t]*/', '', $c); # leading whitespace
- $c = preg_replace('/[ \t]*$/', '', $c); # trailing whitespace
+ $c = preg_replace('/^[ ]*/', '', $c); # leading whitespace
+ $c = preg_replace('/[ ]*$/', '', $c); # trailing whitespace
$c = $this->encodeCode($c);
return $this->hashSpan("<code>$c</code>");
}
(?=\S) # Not followed by whitespace
(?!\1\1) # or two others marker chars.
( # $2: Content
- (?:
+ (?>
[^*_]+? # Anthing not em markers.
|
# Balence any regular emphasis inside.
\1 (?=\S) .+? (?<=\S) \1
|
- (?! \1 ) . # Allow unbalenced * and _.
+ . # Allow unbalenced * and _.
)+?
)
(?<=\S) \1\1 # End mark not preceded by whitespace.
array(&$this, '_doItalicAndBold_strong_callback'), $text);
# Then <em>:
$text = preg_replace_callback(
- '{ ( (?<!\*)\* | (?<!_)_ ) (?=\S) (?! \1) (.+?) (?<=\S) \1 }sx',
+ '{ ( (?<!\*)\* | (?<!_)_ ) (?=\S) (?! \1) (.+?) (?<=\S)(?<!\s(?=\1).) \1 }sx',
array(&$this, '_doItalicAndBold_em_callback'), $text);
return $text;
$text = preg_replace_callback('/
( # Wrap whole match in $1
(
- ^[ \t]*>[ \t]? # ">" at the start of a line
+ ^[ ]*>[ ]? # ">" at the start of a line
.+\n # rest of the first line
(.+\n)* # subsequent consecutive lines
\n* # blanks
function _doBlockQuotes_callback($matches) {
$bq = $matches[1];
# trim one level of quoting - trim whitespace-only lines
- $bq = preg_replace(array('/^[ \t]*>[ \t]?/m', '/^[ \t]+$/m'), '', $bq);
+ $bq = preg_replace(array('/^[ ]*>[ ]?/m', '/^[ ]+$/m'), '', $bq);
$bq = $this->runBlockGamut($bq); # recurse
$bq = preg_replace('/^/m', " ", $bq);
foreach ($grafs as $key => $value) {
if (!isset( $this->html_blocks[$value] )) {
$value = $this->runSpanGamut($value);
- $value = preg_replace('/^([
\t]*)/', "<p>", $value);
+ $value = preg_replace('/^([ ]*)/', "<p>", $value);
$value .= "</p>";
$grafs[$key] = $this->unhash($value);
}
function encodeAmpsAndAngles($text) {
# Smart processing for ampersands and angle brackets that need to be encoded.
+ if ($this->no_entities) {
+ $text = str_replace('&', '&', $text);
+ $text = str_replace('<', '<', $text);
+ return $text;
+ }
# Ampersand-encoding based entirely on Nat Irons's Amputator MT plugin:
# http://bumppo.net/projects/amputator/
# Returns: The string, with after processing the following backslash
# escape sequences.
#
- # Must process escaped backslashes first.
- return str_replace(array_keys($this->backslash_escape_table),
- array_values($this->backslash_escape_table), $text);
+ # Must process escaped backslashes first (should be first in list).
+ foreach ($this->backslash_escape_table as $search => $replacement) {
+ $text = str_replace($search, $this->hashSpan($replacement), $text);
+ }
+ return $text;
}
}
function _doAutoLinks_email_callback($matches) {
$address = $matches[1];
- $address = $this->unescapeSpecialChars($address);
$link = $this->encodeEmailAddress($address);
return $this->hashSpan($link);
}
}
- function unescapeSpecialChars($text) {
- #
- # Swap back in all the special characters we've hidden.
- #
- return str_replace(array_values($this->escape_table),
- array_keys($this->escape_table), $text);
- }
-
-
function tokenizeHTML($str) {
#
# Parameter: String containing HTML + Markdown markup.
# tab characters. Then we reconstruct every line by adding the
# appropriate number of space between each blocks.
- $strlen = $this->utf8_strlen; # best strlen function for UTF-8.
+ $strlen = $this->utf8_strlen; # strlen function for UTF-8.
$lines = explode("\n", $text);
$text = "";
function _initDetab() {
#
# Check for the availability of the function in the `utf8_strlen` property
- # (probably `mb_strlen`). If the function is not available, create a
+ # (initially `mb_strlen`). If the function is not available, create a
# function that will loosely count the number of UTF-8 characters with a
# regular expression.
#
if (function_exists($this->utf8_strlen)) return;
- $this->utf8_strlen = 'Markdown_UTF8_strlen';
-
- if (function_exists($this->utf8_strlen)) return;
- function Markdown_UTF8_strlen($text) {
- return preg_match_all('/[\x00-\xBF]|[\xC0-\xFF][\x80-\xBF]*/',
- $text, $m);
- }
+ $this->utf8_strlen = create_function('$text', 'return preg_match_all(
+ "/[\\\\x00-\\\\xBF]|[\\\\xC0-\\\\xFF][\\\\x80-\\\\xBF]*/",
+ $text, $m);');
}
"doDefLists" => 45,
);
$this->span_gamut += array(
- "doFootnotes" => 4,
- "doAbbreviations" => 5,
+ "doFootnotes" => 5,
+ "doAbbreviations" => 70,
);
parent::Markdown_Parser();
var $abbr_matches = array();
var $html_cleans = array();
+ # Status flag to avoid invalid nesting.
+ var $in_footnote = false;
+
function transform($text) {
#
(?!\s)'.$enclosing_tag.'
)
\s* # Whitespace.
- (?:
+ (?>
".*?" | # Double quotes (can contain `>`)
\'.*?\' | # Single quotes (can contain `>`)
.+? # Anything but quotes and `>`.
# If in Markdown span mode, add a empty-string span-level hash
# after each newline to prevent triggering any block element.
if ($span) {
- $newline = $this->hashSpan("") . "\n";
- $parts[0] = str_replace("\n", $newline, $parts[0]);
+ $void = $this->hashSpan("", true) ;
+ $newline = $this->hashSpan("", true) . "\n";
+ $parts[0] = $void . str_replace("\n", $newline, $parts[0]) . $void;
}
$parsed .= $parts[0]; # Text before current tag.
\s* # Eat whitespace before the `markdown` attribute
markdown
\s*=\s*
- (["\']) # $1: quote delimiter
- (.*?) # $2: attribute value
- \1 # matching delimiter
+ (?:
+ (["\']) # $1: quote delimiter
+ (.*?) # $2: attribute value
+ \1 # matching delimiter
+ |
+ ([^\s>]*) # $3: unquoted attribute value
+ )
+ () # $4: make $3 always defined (avoid warnings)
}xs';
# Regex to match any tag.
</? # Any opening or closing tag.
[\w:$]+ # Tag name.
\s* # Whitespace.
- (?:
+ (?>
".*?" | # Double quotes (can contain `>`)
\'.*?\' | # Single quotes (can contain `>`)
.+? # Anything but quotes and `>`.
# Check for `markdown="1"` attribute and handle it.
#
if ($md_attr &&
- preg_match($markdown_attr_match, $tag, $attr_matches) &&
- preg_match('/^1|block|span$/', $attr_matches[2]))
+ preg_match($markdown_attr_match, $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);
# Check if text inside this tag must be parsed in span mode.
- $this->mode = $attr_matches[2];
+ $this->mode = $attr_m[2] . $attr_m[3];
$span_mode = $this->mode == 'span' || $this->mode != 'block' &&
preg_match("{^<(?:$this->contain_span_tags)\b}", $tag);
$text = $this->unhash($text);
# Then hash the tag.
- $key = md5($text);
+ $key = "C\x1A". md5($text);
$this->html_cleans[$key] = $text;
$this->html_hashes[$key] = $text;
return $key; # String that will replace the clean tag.
# --------
#
$text = preg_replace_callback(
- '{ (^.+?) (?:[ ]+\{\#([-_:a-zA-Z0-9]+)\})? [ \t]*\n=+[ \t]*\n+ }mx',
+ '{ (^.+?) (?:[ ]+\{\#([-_:a-zA-Z0-9]+)\})? [ ]*\n=+[ ]*\n+ }mx',
array(&$this, '_doHeaders_callback_setext_h1'), $text);
$text = preg_replace_callback(
- '{ (^.+?) (?:[ ]+\{\#([-_:a-zA-Z0-9]+)\})? [ \t]*\n-+[ \t]*\n+ }mx',
+ '{ (^.+?) (?:[ ]+\{\#([-_:a-zA-Z0-9]+)\})? [ ]*\n-+[ ]*\n+ }mx',
array(&$this, '_doHeaders_callback_setext_h2'), $text);
# atx-style headers:
#
$text = preg_replace_callback('{
^(\#{1,6}) # $1 = string of #\'s
- [ \t]*
+ [ ]*
(.+?) # $2 = Header text
- [ \t]*
+ [ ]*
\#* # optional closing #\'s (not counted)
(?:[ ]+\{\#([-_:a-zA-Z0-9]+)\})? # id attribute
- [ \t]*
+ [ ]*
\n+
}xm',
array(&$this, '_doHeaders_callback_atx'), $text);
(?=\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.
)+?
)
(?<=\S) __ # End mark not preceded by whitespace.
(?=\S) # Not followed by whitespace
(?!\1) # or two others marker chars.
( # $2: Content
- (?:
+ (?>
[^*]+? # Anthing not em markers.
|
# Balence any regular * emphasis inside.
\* (?=\S) (.+?) (?<=\S) \*
+ |
+ \* # Allow unbalenced as last resort.
)+?
)
(?<=\S) \*\* # End mark not preceded by whitespace.
# Then <em>:
$text = preg_replace_callback(array(
'{ ( (?<![a-zA-Z0-9])(?<!_)_ ) (?=\S) (?! \1) (.+?) (?<=\S) \1(?![a-zA-Z0-9]) }sx',
- '{ ( (?<!\*)\* ) (?=\S) (?! \1) (.+?) (?<=\S) \1 }sx',
+ '{ ( (?<!\*)\* ) (?=\S) (?! \1) (.+?) (?<=\S)(?<!\s\*) \1 }sx',
),
array(&$this, '_doItalicAndBold_em_callback'), $text);
# Check if this should be enclosed in a paragraph.
# Clean tag hashes & block tag hashes are left alone.
$clean_key = $value;
- $block_key = substr($value, 0, 32);
+ $block_key = substr($value, 0, 34);
$is_p = (!isset($this->html_blocks[$block_key]) &&
!isset($this->html_cleans[$clean_key]));
# Link defs are in the form: [^id]: url "optional title"
$text = preg_replace_callback('{
^[ ]{0,'.$less_than_tab.'}\[\^(.+?)\][ ]?: # note_id = $1
- [ \t]*
+ [ ]*
\n? # maybe *one* newline
( # text = $2 (no blank lines allowed)
(?:
return $text;
}
function _stripFootnotes_callback($matches) {
- $note_id = $matches[1];
+ $note_id = $this->fn_id_prefix . $matches[1];
$this->footnotes[$note_id] = $this->outdent($matches[2]);
return ''; # String that will replace the block
}
# Replace footnote references in $text [^id] with a special text-token
# which will be can be
#
- $text = preg_replace('{\[\^(.+?)\]}', "a\0fn:\\1\0z", $text);
+ if (!$this->in_footnote && !$this->in_anchor) {
+ $text = preg_replace('{\[\^(.+?)\]}', "F\x1Afn:\\1\x1A:", $text);
+ }
return $text;
}
#
# Append footnote list to text.
#
- $text = preg_replace_callback('{a\0fn:(.*?)\0z}',
+
+ $text = preg_replace_callback('{F\x1Afn:(.*?)\x1A:}',
array(&$this, '_appendFootnotes_callback'), $text);
if (!empty($this->footnotes_ordered)) {
}
$num = 0;
+ $this->in_footnote = true;
+
foreach ($this->footnotes_ordered as $note_id => $footnote) {
$footnote .= "\n"; # Need to append newline before parsing.
$footnote = $this->runBlockGamut("$footnote\n");
$text .= "</li>\n\n";
}
+ $this->in_footnote = false;
+
$text .= "</ol>\n";
$text .= "</div>";
-
- $text = preg_replace('{a\{fn:(.*?)\}z}', '[^\\1]', $text);
}
return $text;
}
function stripAbbreviations($text) {
#
- # Strips abbreviations from text, stores the URLs and titles in
- # hash references.
+ # Strips abbreviations from text, stores titles in hash references.
#
$less_than_tab = $this->tab_width - 1;
function doAbbreviations($text) {
#
- # Replace footnote references in $text [^id] with a link to the footnote.
+ # Find defined abbreviations in text and wrap them in <abbr> elements.
#
if ($this->abbr_matches) {
- $regex = '{(?<!\w)(?:'. implode('|', $this->abbr_matches) .')(?!\w)}';
-
- $text = preg_replace_callback($regex,
+ // cannot use the /x modifier because abbr_matches may
+ // contain spaces:
+ $text = preg_replace_callback('{'.
+ '(?<![\w\x1A])'.
+ '(?:'. implode('|', $this->abbr_matches) .')'.
+ '(?![\w\x1A])'.
+ '}',
array(&$this, '_doAbbreviations_callback'), $text);
}
return $text;
See Readme file for details.
+Extra 1.1.4 (3 Aug 2007):
+
+Extra 1.1.3 (3 Jul 2007):
+
Extra 1.1.2 (7 Feb 2007)
Extra 1.1.1 (28 Dec 2006)
projects / moodle.git / commitdiff