pax_global_header 0000666 0000000 0000000 00000000064 12636646133 0014524 g ustar 00root root 0000000 0000000 52 comment=156e56ee036505ec637d761ee62dc425d807183c
php-markdown-1.6.0/ 0000775 0000000 0000000 00000000000 12636646133 0014137 5 ustar 00root root 0000000 0000000 php-markdown-1.6.0/License.md 0000664 0000000 0000000 00000003150 12636646133 0016042 0 ustar 00root root 0000000 0000000 PHP Markdown Lib
Copyright (c) 2004-2015 Michel Fortin
All rights reserved.
Based on Markdown
Copyright (c) 2003-2006 John Gruber
All rights reserved.
Redistribution and use in source and binary forms, with or without
modification, are permitted provided that the following conditions are
met:
* Redistributions of source code must retain the above copyright notice,
this list of conditions and the following disclaimer.
* Redistributions in binary form must reproduce the above copyright
notice, this list of conditions and the following disclaimer in the
documentation and/or other materials provided with the distribution.
* Neither the name "Markdown" nor the names of its contributors may
be used to endorse or promote products derived from this software
without specific prior written permission.
This software is provided by the copyright holders and contributors "as
is" and any express or implied warranties, including, but not limited
to, the implied warranties of merchantability and fitness for a
particular purpose are disclaimed. In no event shall the copyright owner
or contributors be liable for any direct, indirect, incidental, special,
exemplary, or consequential damages (including, but not limited to,
procurement of substitute goods or services; loss of use, data, or
profits; or business interruption) however caused and on any theory of
liability, whether in contract, strict liability, or tort (including
negligence or otherwise) arising in any way out of the use of this
software, even if advised of the possibility of such damage.
php-markdown-1.6.0/Michelf/ 0000775 0000000 0000000 00000000000 12636646133 0015506 5 ustar 00root root 0000000 0000000 php-markdown-1.6.0/Michelf/Markdown.inc.php 0000664 0000000 0000000 00000000563 12636646133 0020555 0 ustar 00root root 0000000 0000000
#
# Original Markdown
# Copyright (c) 2004-2006 John Gruber
#
#
namespace Michelf;
#
# Markdown Parser Class
#
class Markdown implements MarkdownInterface {
### Version ###
const MARKDOWNLIB_VERSION = "1.6.0";
### Simple Function Interface ###
public static function defaultTransform($text) {
#
# Initialize the parser and return the result of its transform method.
# This will work fine for derived classes too.
#
# Take parser class on which this function was called.
$parser_class = \get_called_class();
# try to take parser from the static parser list
static $parser_list;
$parser =& $parser_list[$parser_class];
# create the parser it not already set
if (!$parser)
$parser = new $parser_class;
# Transform text using parser.
return $parser->transform($text);
}
### Configuration Variables ###
# Change to ">" for HTML output.
public $empty_element_suffix = " />";
public $tab_width = 4;
# Change to `true` to disallow markup or entities.
public $no_markup = false;
public $no_entities = false;
# Predefined urls and titles for reference links and images.
public $predef_urls = array();
public $predef_titles = array();
# Optional filter function for URLs
public $url_filter_func = null;
# Optional header id="" generation callback function.
public $header_id_func = null;
# Optional function for converting code block content to HTML
public $code_block_content_func = null;
# Class attribute to toggle "enhanced ordered list" behaviour
# setting this to true will allow ordered lists to start from the index
# number that is defined first. For example:
# 2. List item two
# 3. List item three
#
# becomes
#
#
List item two
#
List item three
#
public $enhanced_ordered_list = false;
### Parser Implementation ###
# Regex to match balanced [brackets].
# Needed to insert a maximum bracked depth while converting to PHP.
protected $nested_brackets_depth = 6;
protected $nested_brackets_re;
protected $nested_url_parenthesis_depth = 4;
protected $nested_url_parenthesis_re;
# Table of hash values for escaped characters:
protected $escape_chars = '\`*_{}[]()>#+-.!';
protected $escape_chars_re;
public function __construct() {
#
# Constructor function. Initialize appropriate member variables.
#
$this->_initDetab();
$this->prepareItalicsAndBold();
$this->nested_brackets_re =
str_repeat('(?>[^\[\]]+|\[', $this->nested_brackets_depth).
str_repeat('\])*', $this->nested_brackets_depth);
$this->nested_url_parenthesis_re =
str_repeat('(?>[^()\s]+|\(', $this->nested_url_parenthesis_depth).
str_repeat('(?>\)))*', $this->nested_url_parenthesis_depth);
$this->escape_chars_re = '['.preg_quote($this->escape_chars).']';
# Sort document, block, and span gamut in ascendent priority order.
asort($this->document_gamut);
asort($this->block_gamut);
asort($this->span_gamut);
}
# Internal hashes used during transformation.
protected $urls = array();
protected $titles = array();
protected $html_hashes = array();
# Status flag to avoid invalid nesting.
protected $in_anchor = false;
protected function setup() {
#
# Called before the transformation process starts to setup parser
# states.
#
# Clear global hashes.
$this->urls = $this->predef_urls;
$this->titles = $this->predef_titles;
$this->html_hashes = array();
$this->in_anchor = false;
}
protected function teardown() {
#
# Called after the transformation process to clear any variable
# which may be taking up memory unnecessarly.
#
$this->urls = array();
$this->titles = array();
$this->html_hashes = array();
}
public function transform($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";
}
protected $document_gamut = array(
# Strip link definitions, store in hashes.
"stripLinkDefinitions" => 20,
"runBasicBlockGamut" => 30,
);
protected function stripLinkDefinitions($text) {
#
# Strips link definitions from text, stores the URLs and titles in
# hash references.
#
$less_than_tab = $this->tab_width - 1;
# Link defs are in the form: ^[id]: url "optional title"
$text = preg_replace_callback('{
^[ ]{0,'.$less_than_tab.'}\[(.+)\][ ]?: # id = $1
[ ]*
\n? # maybe *one* newline
[ ]*
(?:
<(.+?)> # url = $2
|
(\S+?) # url = $3
)
[ ]*
\n? # maybe one newline
[ ]*
(?:
(?<=\s) # lookbehind for whitespace
["(]
(.*?) # title = $4
[")]
[ ]*
)? # title is optional
(?:\n+|\Z)
}xm',
array($this, '_stripLinkDefinitions_callback'),
$text);
return $text;
}
protected function _stripLinkDefinitions_callback($matches) {
$link_id = strtolower($matches[1]);
$url = $matches[2] == '' ? $matches[3] : $matches[2];
$this->urls[$link_id] = $url;
$this->titles[$link_id] =& $matches[4];
return ''; # String that will replace the block
}
protected function hashHTMLBlocks($text) {
if ($this->no_markup) return $text;
$less_than_tab = $this->tab_width - 1;
# Hashify HTML blocks:
# We only want to do this for block-level HTML tags, such as headers,
# lists, and tables. That's because we still want to wrap
s around
# "paragraphs" that are wrapped in non-block-level tags, such as anchors,
# phrase emphasis, and spans. The list of tags we're looking for is
# hard-coded:
#
# * List "a" is made of tags which can be both inline or block-level.
# These will be treated block-level when the start tag is alone on
# its line, otherwise they're not matched here and will be taken as
# inline later.
# * List "b" is made of tags which are always block-level;
#
$block_tags_a_re = 'ins|del';
$block_tags_b_re = 'p|div|h[1-6]|blockquote|pre|table|dl|ol|ul|address|'.
'script|noscript|style|form|fieldset|iframe|math|svg|'.
'article|section|nav|aside|hgroup|header|footer|'.
'figure';
# Regular expression for the content of a block tag.
$nested_tags_level = 4;
$attr = '
(?> # optional tag attributes
\s # starts with whitespace
(?>
[^>"/]+ # text outside quotes
|
/+(?!>) # slash not followed by ">"
|
"[^"]*" # text inside double quotes (tolerate ">")
|
\'[^\']*\' # text inside single quotes (tolerate ">")
)*
)?
';
$content =
str_repeat('
(?>
[^<]+ # content without tag
|
<\2 # nested opening tag
'.$attr.' # attributes
(?>
/>
|
>', $nested_tags_level). # end of opening tag
'.*?'. # last level nested tag content
str_repeat('
# closing nested tag
)
|
<(?!/\2\s*> # other tags with a different name
)
)*',
$nested_tags_level);
$content2 = str_replace('\2', '\3', $content);
# First, look for nested blocks, e.g.:
#
#
# tags for inner block must be indented.
#
#
#
# The outermost tags must start at the left margin for this to match, and
# the inner nested divs must be indented.
# We need to do this before the next, more liberal match, because the next
# match will start at the first `
` and stop at the first `
`.
$text = preg_replace_callback('{(?>
(?>
(?<=\n) # Starting on its own line
| # or
\A\n? # the at beginning of the doc
)
( # save in $1
# Match from `\n` to `\n`, handling nested tags
# in between.
[ ]{0,'.$less_than_tab.'}
<('.$block_tags_b_re.')# start tag = $2
'.$attr.'> # attributes followed by > and \n
'.$content.' # content, support nesting
# the matching end tag
[ ]* # trailing spaces/tabs
(?=\n+|\Z) # followed by a newline or end of document
| # Special version for tags of group a.
[ ]{0,'.$less_than_tab.'}
<('.$block_tags_a_re.')# start tag = $3
'.$attr.'>[ ]*\n # attributes followed by >
'.$content2.' # content, support nesting
# the matching end tag
[ ]* # trailing spaces/tabs
(?=\n+|\Z) # followed by a newline or end of document
| # Special case just for . It was easier to make a special
# case than to make the other regex more complicated.
[ ]{0,'.$less_than_tab.'}
<(hr) # start tag = $2
'.$attr.' # attributes
/?> # the matching end tag
[ ]*
(?=\n{2,}|\Z) # followed by a blank line or end of document
| # Special case for standalone HTML comments:
[ ]{0,'.$less_than_tab.'}
(?s:
)
[ ]*
(?=\n{2,}|\Z) # followed by a blank line or end of document
| # PHP and ASP-style processor instructions (
)
[ ]*
(?=\n{2,}|\Z) # followed by a blank line or end of document
)
)}Sxmi',
array($this, '_hashHTMLBlocks_callback'),
$text);
return $text;
}
protected function _hashHTMLBlocks_callback($matches) {
$text = $matches[1];
$key = $this->hashBlock($text);
return "\n\n$key\n\n";
}
protected function hashPart($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 $key; # String that will replace the tag.
}
protected function hashBlock($text) {
#
# Shortcut function for hashPart with block-level boundaries.
#
return $this->hashPart($text, 'B');
}
protected $block_gamut = array(
#
# These are all the transformations that form block-level
# tags like paragraphs, headers, and list items.
#
"doHeaders" => 10,
"doHorizontalRules" => 20,
"doLists" => 40,
"doCodeBlocks" => 50,
"doBlockQuotes" => 60,
);
protected function runBlockGamut($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);
}
protected 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 $text;
}
protected function doHorizontalRules($text) {
# Do Horizontal Rules:
return preg_replace(
'{
^[ ]{0,3} # Leading space
([-*_]) # $1: First marker
(?> # Repeated marker group
[ ]{0,2} # Zero, one, or two spaces.
\1 # Marker character
){2,} # Group repeated at least twice
[ ]* # Tailing spaces
$ # End of line.
}mx',
"\n".$this->hashBlock("empty_element_suffix")."\n",
$text);
}
protected $span_gamut = array(
#
# These are all the transformations that occur *within* block-level
# tags like paragraphs, headers, and list items.
#
# Process character escapes, code spans, and inline HTML
# in one shot.
"parseSpan" => -30,
# Process anchor and image tags. Images must come first,
# because ![foo][f] looks like an anchor.
"doImages" => 10,
"doAnchors" => 20,
# Make links out of things like ``
# Must come after doAnchors, because you can use < and >
# delimiters in inline links like [this]().
"doAutoLinks" => 30,
"encodeAmpsAndAngles" => 40,
"doItalicsAndBold" => 50,
"doHardBreaks" => 60,
);
protected function runSpanGamut($text) {
#
# Run span gamut tranformations.
#
foreach ($this->span_gamut as $method => $priority) {
$text = $this->$method($text);
}
return $text;
}
protected function doHardBreaks($text) {
# Do hard breaks:
return preg_replace_callback('/ {2,}\n/',
array($this, '_doHardBreaks_callback'), $text);
}
protected function _doHardBreaks_callback($matches) {
return $this->hashPart("empty_element_suffix\n");
}
protected function doAnchors($text) {
#
# Turn Markdown link shortcuts into XHTML tags.
#
if ($this->in_anchor) return $text;
$this->in_anchor = true;
#
# First, handle reference-style links: [link text] [id]
#
$text = preg_replace_callback('{
( # wrap whole match in $1
\[
('.$this->nested_brackets_re.') # link text = $2
\]
[ ]? # one optional space
(?:\n[ ]*)? # one optional newline followed by spaces
\[
(.*?) # id = $3
\]
)
}xs',
array($this, '_doAnchors_reference_callback'), $text);
#
# Next, inline-style links: [link text](url "optional title")
#
$text = preg_replace_callback('{
( # wrap whole match in $1
\[
('.$this->nested_brackets_re.') # link text = $2
\]
\( # literal paren
[ \n]*
(?:
<(.+?)> # href = $3
|
('.$this->nested_url_parenthesis_re.') # href = $4
)
[ \n]*
( # $5
([\'"]) # quote char = $6
(.*?) # Title = $7
\6 # matching quote
[ \n]* # ignore any spaces/tabs between closing quote and )
)? # title is optional
\)
)
}xs',
array($this, '_doAnchors_inline_callback'), $text);
#
# Last, handle reference-style shortcuts: [link text]
# These must come last in case you've also got [link text][1]
# or [link text](/foo)
#
$text = preg_replace_callback('{
( # wrap whole match in $1
\[
([^\[\]]+) # link text = $2; can\'t contain [ or ]
\]
)
}xs',
array($this, '_doAnchors_reference_callback'), $text);
$this->in_anchor = false;
return $text;
}
protected function _doAnchors_reference_callback($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 = $this->encodeURLAttribute($url);
$result = "titles[$link_id] ) ) {
$title = $this->titles[$link_id];
$title = $this->encodeAttribute($title);
$result .= " title=\"$title\"";
}
$link_text = $this->runSpanGamut($link_text);
$result .= ">$link_text";
$result = $this->hashPart($result);
}
else {
$result = $whole_match;
}
return $result;
}
protected function _doAnchors_inline_callback($matches) {
$whole_match = $matches[1];
$link_text = $this->runSpanGamut($matches[2]);
$url = $matches[3] == '' ? $matches[4] : $matches[3];
$title =& $matches[7];
// if the URL was of the form it got caught by the HTML
// tag parser and hashed. Need to reverse the process before using the URL.
$unhashed = $this->unhash($url);
if ($unhashed != $url)
$url = preg_replace('/^<(.*)>$/', '\1', $unhashed);
$url = $this->encodeURLAttribute($url);
$result = "encodeAttribute($title);
$result .= " title=\"$title\"";
}
$link_text = $this->runSpanGamut($link_text);
$result .= ">$link_text";
return $this->hashPart($result);
}
protected function doImages($text) {
#
# Turn Markdown image shortcuts into tags.
#
#
# First, handle reference-style labeled images: ![alt text][id]
#
$text = preg_replace_callback('{
( # wrap whole match in $1
!\[
('.$this->nested_brackets_re.') # alt text = $2
\]
[ ]? # one optional space
(?:\n[ ]*)? # one optional newline followed by spaces
\[
(.*?) # id = $3
\]
)
}xs',
array($this, '_doImages_reference_callback'), $text);
#
# Next, handle inline images: 
# Don't forget: encode * and _
#
$text = preg_replace_callback('{
( # wrap whole match in $1
!\[
('.$this->nested_brackets_re.') # alt text = $2
\]
\s? # One optional whitespace character
\( # literal paren
[ \n]*
(?:
<(\S*)> # src url = $3
|
('.$this->nested_url_parenthesis_re.') # src url = $4
)
[ \n]*
( # $5
([\'"]) # quote char = $6
(.*?) # title = $7
\6 # matching quote
[ \n]*
)? # title is optional
\)
)
}xs',
array($this, '_doImages_inline_callback'), $text);
return $text;
}
protected function _doImages_reference_callback($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 = $this->encodeURLAttribute($this->urls[$link_id]);
$result = "titles[$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 $result;
}
protected function _doImages_inline_callback($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 = $this->encodeURLAttribute($url);
$result = "encodeAttribute($title);
$result .= " title=\"$title\""; # $title already quoted
}
$result .= $this->empty_element_suffix;
return $this->hashPart($result);
}
protected function doHeaders($text) {
# Setext-style headers:
# Header 1
# ========
#
# Header 2
# --------
#
$text = preg_replace_callback('{ ^(.+?)[ ]*\n(=+|-+)[ ]*\n+ }mx',
array($this, '_doHeaders_callback_setext'), $text);
# atx-style headers:
# # Header 1
# ## Header 2
# ## Header 2 with closing hashes ##
# ...
# ###### Header 6
#
$text = preg_replace_callback('{
^(\#{1,6}) # $1 = string of #\'s
[ ]*
(.+?) # $2 = Header text
[ ]*
\#* # optional closing #\'s (not counted)
\n+
}xm',
array($this, '_doHeaders_callback_atx'), $text);
return $text;
}
protected function _doHeaders_callback_setext($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;
# id attribute generation
$idAtt = $this->_generateIdFromHeaderValue($matches[1]);
$block = "".$this->runSpanGamut($matches[1])."";
return "\n" . $this->hashBlock($block) . "\n\n";
}
protected function _doHeaders_callback_atx($matches) {
# id attribute generation
$idAtt = $this->_generateIdFromHeaderValue($matches[2]);
$level = strlen($matches[1]);
$block = "".$this->runSpanGamut($matches[2])."";
return "\n" . $this->hashBlock($block) . "\n\n";
}
protected function _generateIdFromHeaderValue($headerValue) {
# if a header_id_func property is set, we can use it to automatically
# generate an id attribute.
#
# This method returns a string in the form id="foo", or an empty string
# otherwise.
if (!is_callable($this->header_id_func)) {
return "";
}
$idValue = call_user_func($this->header_id_func, $headerValue);
if (!$idValue) return "";
return ' id="' . $this->encodeAttribute($idValue) . '"';
}
protected 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+[\.]';
$markers_relist = array(
$marker_ul_re => $marker_ol_re,
$marker_ol_re => $marker_ul_re,
);
foreach ($markers_relist as $marker_re => $other_marker_re) {
# Re-usable pattern to match any entirel ul or ol list:
$whole_list_re = '
( # $1 = whole list
( # $2
([ ]{0,'.$less_than_tab.'}) # $3 = number of spaces
('.$marker_re.') # $4 = first list item marker
[ ]+
)
(?s:.+?)
( # $5
\z
|
\n{2,}
(?=\S)
(?! # Negative lookahead for another list item marker
[ ]*
'.$marker_re.'[ ]+
)
|
(?= # Lookahead for another kind of list
\n
\3 # Must have the same indentation
'.$other_marker_re.'[ ]+
)
)
)
'; // mx
# We use a different prefix before nested lists than top-level lists.
# See extended comment in _ProcessListItems().
if ($this->list_level) {
$text = preg_replace_callback('{
^
'.$whole_list_re.'
}mx',
array($this, '_doLists_callback'), $text);
}
else {
$text = preg_replace_callback('{
(?:(?<=\n)\n|\A\n?) # Must eat the newline
'.$whole_list_re.'
}mx',
array($this, '_doLists_callback'), $text);
}
}
return $text;
}
protected function _doLists_callback($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)";
$marker_ol_start_re = '[0-9]+';
$list = $matches[1];
$list_type = preg_match("/$marker_ul_re/", $matches[4]) ? "ul" : "ol";
$marker_any_re = ( $list_type == "ul" ? $marker_ul_re : $marker_ol_re );
$list .= "\n";
$result = $this->processListItems($list, $marker_any_re);
$ol_start = 1;
if ($this->enhanced_ordered_list) {
# Get the start number for ordered list.
if ($list_type == 'ol') {
$ol_start_array = array();
$ol_start_check = preg_match("/$marker_ol_start_re/", $matches[4], $ol_start_array);
if ($ol_start_check){
$ol_start = $ol_start_array[0];
}
}
}
if ($ol_start > 1 && $list_type == 'ol'){
$result = $this->hashBlock("<$list_type start=\"$ol_start\">\n" . $result . "");
} else {
$result = $this->hashBlock("<$list_type>\n" . $result . "");
}
return "\n". $result ."\n\n";
}
protected $list_level = 0;
protected function processListItems($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 $list_str;
}
protected function _processListItems_callback($matches) {
$item = $matches[4];
$leading_line =& $matches[1];
$leading_space =& $matches[2];
$marker_space = $matches[3];
$tailing_blank_line =& $matches[5];
if ($leading_line || $tailing_blank_line ||
preg_match('/\n{2,}/', $item))
{
# Replace marker with the appropriate whitespace indentation
$item = $leading_space . str_repeat(' ', strlen($marker_space)) . $item;
$item = $this->runBlockGamut($this->outdent($item)."\n");
}
else {
# Recursion for sub-lists:
$item = $this->doLists($this->outdent($item));
$item = preg_replace('/\n+$/', '', $item);
$item = $this->runSpanGamut($item);
}
return "
" . $item . "
\n";
}
protected function doCodeBlocks($text) {
#
# Process Markdown `
` blocks.
#
$text = preg_replace_callback('{
(?:\n\n|\A\n?)
( # $1 = the code block -- one or more lines, starting with a space/tab
(?>
[ ]{'.$this->tab_width.'} # Lines must start with a tab or a tab-width of spaces
.*\n+
)+
)
((?=^[ ]{0,'.$this->tab_width.'}\S)|\Z) # Lookahead for non-space at line-start, or end of doc
}xm',
array($this, '_doCodeBlocks_callback'), $text);
return $text;
}
protected function _doCodeBlocks_callback($matches) {
$codeblock = $matches[1];
$codeblock = $this->outdent($codeblock);
if ($this->code_block_content_func) {
$codeblock = call_user_func($this->code_block_content_func, $codeblock, "");
} else {
$codeblock = htmlspecialchars($codeblock, ENT_NOQUOTES);
}
# trim leading newlines and trailing newlines
$codeblock = preg_replace('/\A\n+|\n+\z/', '', $codeblock);
$codeblock = "
$codeblock\n
";
return "\n\n".$this->hashBlock($codeblock)."\n\n";
}
protected function makeCodeSpan($code) {
#
# Create a code span markup for $code. Called from handleSpanToken.
#
$code = htmlspecialchars(trim($code), ENT_NOQUOTES);
return $this->hashPart("$code");
}
protected $em_relist = array(
'' => '(?:(? '(? '(? '(?:(? '(? '(? '(?:(? '(? '(?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"] = $token_re;
}
}
}
protected function doItalicsAndBold($text) {
$token_stack = array('');
$text_stack = array('');
$em = '';
$strong = '';
$tree_char_em = false;
while (1) {
#
# Get prepared regular expression for seraching emphasis tokens
# in current context.
#
$token_re = $this->em_strong_prepared_relist["$em$strong"];
#
# Each loop iteration search for the next emphasis token.
# Each token is then passed to handleSpanToken.
#
$parts = preg_split($token_re, $text, 2, PREG_SPLIT_DELIM_CAPTURE);
$text_stack[0] .= $parts[0];
$token =& $parts[1];
$text =& $parts[2];
if (empty($token)) {
# Reached end of text span: empty stack without emitting.
# any more emphasis.
while ($token_stack[0]) {
$text_stack[1] .= array_shift($token_stack);
$text_stack[0] .= array_shift($text_stack);
}
break;
}
$token_len = strlen($token);
if ($tree_char_em) {
# Reached closing marker while inside a three-char emphasis.
if ($token_len == 3) {
# Three-char closing marker, close em and strong.
array_shift($token_stack);
$span = array_shift($text_stack);
$span = $this->runSpanGamut($span);
$span = "$span";
$text_stack[0] .= $this->hashPart($span);
$em = '';
$strong = '';
} else {
# Other closing marker: close one em or strong and
# change current token state to match the other
$token_stack[0] = str_repeat($token{0}, 3-$token_len);
$tag = $token_len == 2 ? "strong" : "em";
$span = $text_stack[0];
$span = $this->runSpanGamut($span);
$span = "<$tag>$span";
$text_stack[0] = $this->hashPart($span);
$$tag = ''; # $$tag stands for $em or $strong
}
$tree_char_em = false;
} else if ($token_len == 3) {
if ($em) {
# Reached closing marker for both em and strong.
# Closing strong marker:
for ($i = 0; $i < 2; ++$i) {
$shifted_token = array_shift($token_stack);
$tag = strlen($shifted_token) == 2 ? "strong" : "em";
$span = array_shift($text_stack);
$span = $this->runSpanGamut($span);
$span = "<$tag>$span";
$text_stack[0] .= $this->hashPart($span);
$$tag = ''; # $$tag stands for $em or $strong
}
} else {
# Reached opening three-char emphasis marker. Push on token
# stack; will be handled by the special condition above.
$em = $token{0};
$strong = "$em$em";
array_unshift($token_stack, $token);
array_unshift($text_stack, '');
$tree_char_em = true;
}
} else if ($token_len == 2) {
if ($strong) {
# Unwind any dangling emphasis marker:
if (strlen($token_stack[0]) == 1) {
$text_stack[1] .= array_shift($token_stack);
$text_stack[0] .= array_shift($text_stack);
}
# Closing strong marker:
array_shift($token_stack);
$span = array_shift($text_stack);
$span = $this->runSpanGamut($span);
$span = "$span";
$text_stack[0] .= $this->hashPart($span);
$strong = '';
} else {
array_unshift($token_stack, $token);
array_unshift($text_stack, '');
$strong = $token;
}
} else {
# Here $token_len == 1
if ($em) {
if (strlen($token_stack[0]) == 1) {
# Closing emphasis marker:
array_shift($token_stack);
$span = array_shift($text_stack);
$span = $this->runSpanGamut($span);
$span = "$span";
$text_stack[0] .= $this->hashPart($span);
$em = '';
} else {
$text_stack[0] .= $token;
}
} else {
array_unshift($token_stack, $token);
array_unshift($text_stack, '');
$em = $token;
}
}
}
return $text_stack[0];
}
protected function doBlockQuotes($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 $text;
}
protected function _doBlockQuotes_callback($matches) {
$bq = $matches[1];
# trim one level of quoting - trim whitespace-only lines
$bq = preg_replace('/^[ ]*>[ ]?|^[ ]+$/m', '', $bq);
$bq = $this->runBlockGamut($bq); # recurse
$bq = preg_replace('/^/m', " ", $bq);
# These leading spaces cause problem with
content,
# so we need to fix that:
$bq = preg_replace_callback('{(\s*
tags and unhashify HTML blocks
#
foreach ($grafs as $key => $value) {
if (!preg_match('/^B\x1A[0-9]+B$/', $value)) {
# Is a paragraph.
$value = $this->runSpanGamut($value);
$value = preg_replace('/^([ ]*)/', "
", $value);
$value .= "
";
$grafs[$key] = $this->unhash($value);
}
else {
# Is a block.
# Modify elements of @grafs in-place...
$graf = $value;
$block = $this->html_hashes[$graf];
$graf = $block;
// if (preg_match('{
// \A
// ( # $1 =
) # $4 = closing tag
// \z
// }xs', $block, $matches))
// {
// list(, $div_open, , $div_content, $div_close) = $matches;
//
// # We can't call Markdown(), because that resets the hash;
// # that initialization code should be pulled into its own sub, though.
// $div_content = $this->hashHTMLBlocks($div_content);
//
// # Run document gamut methods on the content.
// foreach ($this->document_gamut as $method => $priority) {
// $div_content = $this->$method($div_content);
// }
//
// $div_open = preg_replace(
// '{\smarkdown\s*=\s*([\'"]).+?\1}', '', $div_open);
//
// $graf = $div_open . "\n" . $div_content . "\n" . $div_close;
// }
$grafs[$key] = $graf;
}
}
return implode("\n\n", $grafs);
}
protected function encodeAttribute($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 $text;
}
protected function encodeURLAttribute($url, &$text = null) {
#
# Encode text for a double-quoted HTML attribute containing a URL,
# applying the URL filter if set. Also generates the textual
# representation for the URL (removing mailto: or tel:) storing it in $text.
# This function is *not* suitable for attributes enclosed in single quotes.
#
if ($this->url_filter_func)
$url = call_user_func($this->url_filter_func, $url);
if (preg_match('{^mailto:}i', $url))
$url = $this->encodeEntityObfuscatedAttribute($url, $text, 7);
else if (preg_match('{^tel:}i', $url))
{
$url = $this->encodeAttribute($url);
$text = substr($url, 4);
}
else
{
$url = $this->encodeAttribute($url);
$text = $url;
}
return $url;
}
protected function encodeAmpsAndAngles($text) {
#
# Smart processing for ampersands and angle brackets that need to
# be encoded. Valid character entities are left alone unless the
# no-entities mode is set.
#
if ($this->no_entities) {
$text = str_replace('&', '&', $text);
} else {
# Ampersand-encoding based entirely on Nat Irons's Amputator
# MT plugin:
$text = preg_replace('/&(?!#?[xX]?(?:[0-9a-fA-F]+|\w+);)/',
'&', $text);
}
# Encode remaining <'s
$text = str_replace('<', '<', $text);
return $text;
}
protected function doAutoLinks($text) {
$text = preg_replace_callback('{<((https?|ftp|dict|tel):[^\'">\s]+)>}i',
array($this, '_doAutoLinks_url_callback'), $text);
# Email addresses:
$text = preg_replace_callback('{
<
(?:mailto:)?
(
(?:
[-!#$%&\'*+/=?^_`.{|}~\w\x80-\xFF]+
|
".*?"
)
\@
(?:
[-a-z0-9\x80-\xFF]+(\.[-a-z0-9\x80-\xFF]+)*\.[a-z]+
|
\[[\d.a-fA-F:]+\] # IPv4 & IPv6
)
)
>
}xi',
array($this, '_doAutoLinks_email_callback'), $text);
return $text;
}
protected function _doAutoLinks_url_callback($matches) {
$url = $this->encodeURLAttribute($matches[1], $text);
$link = "$text";
return $this->hashPart($link);
}
protected function _doAutoLinks_email_callback($matches) {
$addr = $matches[1];
$url = $this->encodeURLAttribute("mailto:$addr", $text);
$link = "$text";
return $this->hashPart($link);
}
protected function encodeEntityObfuscatedAttribute($text, &$tail = null, $head_length = 0) {
#
# Input: some text to obfuscate, e.g. "mailto:foo@example.com"
#
# Output: the same text but with most characters encoded as either a
# decimal or hex entity, in the hopes of foiling most address
# harvesting spam bots. E.g.:
#
# mailto:foo
# @example.co
# m
#
# Note: the additional output $tail is assigned the same value as the
# ouput, minus the number of characters specified by $head_length.
#
# Based by a filter by Matthew Wickline, posted to BBEdit-Talk.
# With some optimizations by Milian Wolff. Forced encoding of HTML
# attribute special characters by Allan Odgaard.
#
if ($text == "") return $tail = "";
$chars = preg_split('/(? $char) {
$ord = ord($char);
# Ignore non-ascii chars.
if ($ord < 128) {
$r = ($seed * (1 + $key)) % 100; # Pseudo-random function.
# roughly 10% raw, 45% hex, 45% dec
# '@' *must* be encoded. I insist.
# '"' and '>' have to be encoded inside the attribute
if ($r > 90 && strpos('@"&>', $char) === false) /* do nothing */;
else if ($r < 45) $chars[$key] = '&#x'.dechex($ord).';';
else $chars[$key] = '&#'.$ord.';';
}
}
$text = implode('', $chars);
$tail = $head_length ? implode('', array_slice($chars, $head_length)) : $text;
return $text;
}
protected function parseSpan($str) {
#
# Take the string $str and parse it into tokens, hashing embeded HTML,
# escaped characters and handling code spans.
#
$output = '';
$span_re = '{
(
\\\\'.$this->escape_chars_re.'
|
(?no_markup ? '' : '
|
# comment
|
<\?.*?\?> | <%.*?%> # processing instruction
|
<[!$]?[-a-zA-Z0-9:_]+ # regular tags
(?>
\s
(?>[^"\'>]+|"[^"]*"|\'[^\']*\')*
)?
>
|
<[-a-zA-Z0-9:_]+\s*/> # xml-style empty tag
|
# closing tag
').'
)
}xs';
while (1) {
#
# Each loop iteration seach for either the next tag, the next
# openning code span marker, or the next escaped character.
# Each token is then passed to handleSpanToken.
#
$parts = preg_split($span_re, $str, 2, PREG_SPLIT_DELIM_CAPTURE);
# Create token from text preceding tag.
if ($parts[0] != "") {
$output .= $parts[0];
}
# Check if we reach the end.
if (isset($parts[1])) {
$output .= $this->handleSpanToken($parts[1], $parts[2]);
$str = $parts[2];
}
else {
break;
}
}
return $output;
}
protected function handleSpanToken($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);
}
}
protected function outdent($text) {
#
# Remove one level of line-leading tabs or spaces
#
return preg_replace('/^(\t|[ ]{1,'.$this->tab_width.'})/m', '', $text);
}
# String length function for detab. `_initDetab` will create a function to
# hanlde UTF-8 if the default function does not exist.
protected $utf8_strlen = 'mb_strlen';
protected function detab($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 $text;
}
protected function _detab_callback($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 $line;
}
protected function _initDetab() {
#
# Check for the availability of the function in the `utf8_strlen` property
# (initially `mb_strlen`). If the function is not available, create a
# function that will loosely count the number of UTF-8 characters with a
# regular expression.
#
if (function_exists($this->utf8_strlen)) return;
$this->utf8_strlen = create_function('$text', 'return preg_match_all(
"/[\\\\x00-\\\\xBF]|[\\\\xC0-\\\\xFF][\\\\x80-\\\\xBF]*/",
$text, $m);');
}
protected function unhash($text) {
#
# Swap back in all the tags hashed by _HashHTMLBlocks.
#
return preg_replace_callback('/(.)\x1A[0-9]+\1/',
array($this, '_unhash_callback'), $text);
}
protected function _unhash_callback($matches) {
return $this->html_hashes[$matches[0]];
}
}
php-markdown-1.6.0/Michelf/MarkdownExtra.inc.php 0000664 0000000 0000000 00000000657 12636646133 0021565 0 ustar 00root root 0000000 0000000
#
# Original Markdown
# Copyright (c) 2004-2006 John Gruber
#
#
namespace Michelf;
#
# Markdown Extra Parser Class
#
class MarkdownExtra extends \Michelf\Markdown {
### Configuration Variables ###
# Prefix for footnote ids.
public $fn_id_prefix = "";
# Optional title attribute for footnote links and backlinks.
public $fn_link_title = "";
public $fn_backlink_title = "";
# Optional class attribute for footnote links and backlinks.
public $fn_link_class = "footnote-ref";
public $fn_backlink_class = "footnote-backref";
# Content to be displayed within footnote backlinks. The default is '↩';
# the U+FE0E on the end is a Unicode variant selector used to prevent iOS
# from displaying the arrow character as an emoji.
public $fn_backlink_html = '↩︎';
# Class name for table cell alignment (%% replaced left/center/right)
# For instance: 'go-%%' becomes 'go-left' or 'go-right' or 'go-center'
# If empty, the align attribute is used instead of a class name.
public $table_align_class_tmpl = '';
# Optional class prefix for fenced code block.
public $code_class_prefix = "";
# Class attribute for code blocks goes on the `code` tag;
# setting this to true will put attributes on the `pre` tag instead.
public $code_attr_on_pre = false;
# Predefined abbreviations.
public $predef_abbr = array();
### Parser Implementation ###
public function __construct() {
#
# 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,
);
$this->enhanced_ordered_list = true;
parent::__construct();
}
# Extra variables used during extra transformations.
protected $footnotes = array();
protected $footnotes_ordered = array();
protected $footnotes_ref_count = array();
protected $footnotes_numbers = array();
protected $abbr_desciptions = array();
protected $abbr_word_re = '';
# Give the current footnote number.
protected $footnote_counter = 1;
protected function setup() {
#
# Setting up Extra-specific variables.
#
parent::setup();
$this->footnotes = array();
$this->footnotes_ordered = array();
$this->footnotes_ref_count = array();
$this->footnotes_numbers = 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);
}
}
protected function teardown() {
#
# Clearing Extra-specific variables.
#
$this->footnotes = array();
$this->footnotes_ordered = array();
$this->footnotes_ref_count = array();
$this->footnotes_numbers = array();
$this->abbr_desciptions = array();
$this->abbr_word_re = '';
parent::teardown();
}
### Extra Attribute Parser ###
# Expression to use to catch attributes (includes the braces)
protected $id_class_attr_catch_re = '\{((?>[ ]*[#.a-z][-_:a-zA-Z0-9=]+){1,})[ ]*\}';
# Expression to use when parsing in a context when no capture is desired
protected $id_class_attr_nocatch_re = '\{(?>[ ]*[#.a-z][-_:a-zA-Z0-9=]+){1,}[ ]*\}';
protected function doExtraAttributes($tag_name, $attr, $defaultIdValue = null, $classes = array()) {
#
# Parse attributes caught by the $this->id_class_attr_catch_re expression
# and return the HTML-formatted list of attributes.
#
# Currently supported attributes are .class and #id.
#
# In addition, this method also supports supplying a default Id value,
# which will be used to populate the id attribute in case it was not
# overridden.
if (empty($attr) && !$defaultIdValue && empty($classes)) return "";
# Split on components
preg_match_all('/[#.a-z][-_:a-zA-Z0-9=]+/', $attr, $matches);
$elements = $matches[0];
# handle classes and ids (only first id taken into account)
$attributes = array();
$id = false;
foreach ($elements as $element) {
if ($element{0} == '.') {
$classes[] = substr($element, 1);
} else if ($element{0} == '#') {
if ($id === false) $id = substr($element, 1);
} else if (strpos($element, '=') > 0) {
$parts = explode('=', $element, 2);
$attributes[] = $parts[0] . '="' . $parts[1] . '"';
}
}
if (!$id) $id = $defaultIdValue;
# compose attributes as string
$attr_str = "";
if (!empty($id)) {
$attr_str .= ' id="'.$this->encodeAttribute($id) .'"';
}
if (!empty($classes)) {
$attr_str .= ' class="'. implode(" ", $classes) . '"';
}
if (!$this->no_markup && !empty($attributes)) {
$attr_str .= ' '.implode(" ", $attributes);
}
return $attr_str;
}
protected function stripLinkDefinitions($text) {
#
# Strips link definitions from text, stores the URLs and titles in
# hash references.
#
$less_than_tab = $this->tab_width - 1;
# Link defs are in the form: ^[id]: url "optional title"
$text = preg_replace_callback('{
^[ ]{0,'.$less_than_tab.'}\[(.+)\][ ]?: # id = $1
[ ]*
\n? # maybe *one* newline
[ ]*
(?:
<(.+?)> # url = $2
|
(\S+?) # url = $3
)
[ ]*
\n? # maybe one newline
[ ]*
(?:
(?<=\s) # lookbehind for whitespace
["(]
(.*?) # title = $4
[")]
[ ]*
)? # title is optional
(?:[ ]* '.$this->id_class_attr_catch_re.' )? # $5 = extra id & class attr
(?:\n+|\Z)
}xm',
array($this, '_stripLinkDefinitions_callback'),
$text);
return $text;
}
protected function _stripLinkDefinitions_callback($matches) {
$link_id = strtolower($matches[1]);
$url = $matches[2] == '' ? $matches[3] : $matches[2];
$this->urls[$link_id] = $url;
$this->titles[$link_id] =& $matches[4];
$this->ref_attr[$link_id] = $this->doExtraAttributes("", $dummy =& $matches[5]);
return ''; # String that will replace the block
}
### HTML Block Parser ###
# Tags that are always treated as block tags:
protected $block_tags_re = 'p|div|h[1-6]|blockquote|pre|table|dl|ol|ul|address|form|fieldset|iframe|hr|legend|article|section|nav|aside|hgroup|header|footer|figcaption|figure';
# Tags treated as block tags only if the opening tag is alone on its line:
protected $context_block_tags_re = 'script|noscript|style|ins|del|iframe|object|source|track|param|math|svg|canvas|audio|video';
# Tags where markdown="1" default to span mode:
protected $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:
protected $clean_tags_re = 'script|style|math|svg';
# Tags that do not need to be closed.
protected $auto_close_tags_re = 'hr|img|param|source|track';
protected function hashHTMLBlocks($text) {
#
# Hashify HTML Blocks and "clean tags".
#
# We only want to do this for block-level HTML tags, such as headers,
# lists, and tables. That's because we still want to wrap
s around
# "paragraphs" that are wrapped in non-block-level tags, such as anchors,
# phrase emphasis, and spans. The list of tags we're looking for is
# hard-coded.
#
# This works by calling _HashHTMLBlocks_InMarkdown, which then calls
# _HashHTMLBlocks_InHTML when it encounter block tags. When the markdown="1"
# attribute is found within 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!
#
if ($this->no_markup) return $text;
#
# Call the HTML-in-Markdown hasher.
#
list($text, ) = $this->_hashHTMLBlocks_inMarkdown($text);
return $text;
}
protected function _hashHTMLBlocks_inMarkdown($text, $indent = 0,
$enclosing_tag_re = '', $span = false)
{
#
# Parse markdown text, calling _HashHTMLBlocks_InHTML for block tags.
#
# * $indent is the number of space to be ignored when checking for code
# blocks. This is important because if we don't take the indent into
# account, something like this (which looks right) won't work as expected:
#
#
#
# Hello World. <-- Is this a Markdown code block or text?
#
<-- Is this a Markdown code block or a real tag?
#
#
# If you don't like this, just don't indent the tag on which
# you apply the markdown="1" attribute.
#
# * If $enclosing_tag_re is not empty, stops at the first unmatched closing
# tag with that name. Nested tags supported.
#
# * If $span is true, text inside must treated as span. So any double
# newline will be replaced by a single newline so that it does not create
# paragraphs.
#
# Returns an array of that form: ( processed text , remaining text )
#
if ($text === '') return array('', '');
# Regex to check for the presense of newlines around a block tag.
$newline_before_re = '/(?:^\n?|\n\n)*$/';
$newline_after_re =
'{
^ # Start of text following the tag.
(?>[ ]*)? # Optional comment.
[ ]*\n # Must be followed by newline.
}xs';
# Regex to match any tag.
$block_tag_re =
'{
( # $2: Capture whole tag.
# Tag name.
'.$this->block_tags_re.' |
'.$this->context_block_tags_re.' |
'.$this->clean_tags_re.' |
(?!\s)'.$enclosing_tag_re.'
)
(?:
(?=[\s"\'/a-zA-Z0-9]) # Allowed characters after tag name.
(?>
".*?" | # Double quotes (can contain `>`)
\'.*?\' | # Single quotes (can contain `>`)
.+? # Anything but quotes and `>`.
)*?
)?
> # End of tag.
|
# HTML Comment
|
<\?.*?\?> | <%.*?%> # Processing instruction
|
# CData Block
'. ( !$span ? ' # If not in span.
|
# Indented code block
(?: ^[ ]*\n | ^ | \n[ ]*\n )
[ ]{'.($indent+4).'}[^\n]* \n
(?>
(?: [ ]{'.($indent+4).'}[^\n]* | [ ]* ) \n
)*
|
# Fenced code block marker
(?<= ^ | \n )
[ ]{0,'.($indent+3).'}(?:~{3,}|`{3,})
[ ]*
(?: \.?[-_:a-zA-Z0-9]+ )? # standalone class name
[ ]*
(?: '.$this->id_class_attr_nocatch_re.' )? # extra attributes
[ ]*
(?= \n )
' : '' ). ' # End (if not is span).
|
# Code span marker
# Note, this regex needs to go after backtick fenced
# code blocks but it should also be kept outside of the
# "if not in span" condition adding backticks to the parser
`+
)
}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: Fenced code block marker.
# Note: need to recheck the whole tag to disambiguate backtick
# fences from code spans
#
if (preg_match('{^\n?([ ]{0,'.($indent+3).'})(~{3,}|`{3,})[ ]*(?:\.?[-_:a-zA-Z0-9]+)?[ ]*(?:'.$this->id_class_attr_nocatch_re.')?[ ]*\n?$}', $tag, $capture)) {
# Fenced code block marker: find matching end marker.
$fence_indent = strlen($capture[1]); # use captured indent in re
$fence_re = $capture[2]; # use captured fence in re
if (preg_match('{^(?>.*\n)*?[ ]{'.($fence_indent).'}'.$fence_re.'[ ]*(?:\n|$)}', $text,
$matches))
{
# End marker found: pass text unchanged until marker.
$parsed .= $tag . $matches[0];
$text = substr($text, strlen($matches[0]));
}
else {
# No end marker: just skip it.
$parsed .= $tag;
}
}
#
# Check for: Indented code block.
#
else if ($tag{0} == "\n" || $tag{0} == " ") {
# Indented code block: pass it unchanged, will be handled
# later.
$parsed .= $tag;
}
#
# Check for: Code span marker
# Note: need to check this after backtick fenced code blocks
#
else if ($tag{0} == "`") {
# Find corresponding end marker.
$tag_re = preg_quote($tag);
if (preg_match('{^(?>.+?|\n(?!\n))*?(?block_tags_re.')\b}', $tag) ||
( preg_match('{^<(?:'.$this->context_block_tags_re.')\b}', $tag) &&
preg_match($newline_before_re, $parsed) &&
preg_match($newline_after_re, $text) )
)
{
# Need to parse tag and following text using the HTML parser.
list($block_text, $text) =
$this->_hashHTMLBlocks_inHTML($tag . $text, "hashBlock", true);
# Make sure it stays outside of any paragraph by adding newlines.
$parsed .= "\n\n$block_text\n\n";
}
#
# Check for: Clean tag (like script, math)
# HTML Comments, processing instructions.
#
else if (preg_match('{^<(?:'.$this->clean_tags_re.')\b}', $tag) ||
$tag{1} == '!' || $tag{1} == '?')
{
# Need to parse tag and following text using the HTML parser.
# (don't check for markdown attribute)
list($block_text, $text) =
$this->_hashHTMLBlocks_inHTML($tag . $text, "hashClean", false);
$parsed .= $block_text;
}
#
# Check for: Tag with same name as enclosing tag.
#
else if ($enclosing_tag_re !== '' &&
# Same name as enclosing tag.
preg_match('{^= 0);
return array($parsed, $text);
}
protected function _hashHTMLBlocks_inHTML($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 whole tag.
".*?" | # Double quotes (can contain `>`)
\'.*?\' | # Single quotes (can contain `>`)
.+? # Anything but quotes and `>`.
)*?
)?
> # End of tag.
|
# HTML Comment
|
<\?.*?\?> | <%.*?%> # Processing instruction
|
# CData Block
)
}xs';
$original_text = $text; # Save original text in case of faliure.
$depth = 0; # Current depth inside the tag tree.
$block_text = ""; # Temporary text holder for current text.
$parsed = ""; # Parsed text that will be returned.
#
# Get the name of the starting tag.
# (This pattern makes $base_tag_name_re safe without quoting.)
#
if (preg_match('/^<([\w:$]*)\b/', $text, $matches))
$base_tag_name_re = $matches[1];
#
# Loop through every tag until we find the corresponding closing tag.
#
do {
#
# Split the text using the first $tag_match pattern found.
# Text before pattern will be first in the array, text after
# pattern will be at the end, and between will be any catches made
# by the pattern.
#
$parts = preg_split($tag_re, $text, 2, PREG_SPLIT_DELIM_CAPTURE);
if (count($parts) < 3) {
#
# End of $text reached with unbalenced tag(s).
# In that case, we return original text unchanged and pass the
# first character as filtered to prevent an infinite loop in the
# parent function.
#
return array($original_text{0}, substr($original_text, 1));
}
$block_text .= $parts[0]; # Text before current tag.
$tag = $parts[1]; # Tag to handle.
$text = $parts[2]; # Remaining text after current tag.
#
# Check for: Auto-close tag (like )
# Comments and Processing Instructions.
#
if (preg_match('{^auto_close_tags_re.')\b}', $tag) ||
$tag{1} == '!' || $tag{1} == '?')
{
# Just add the tag to the block as if it was text.
$block_text .= $tag;
}
else {
#
# Increase/decrease nested tag count. Only do so if
# the tag's name match base tag's.
#
if (preg_match('{^mode = $attr_m[2] . $attr_m[3];
$span_mode = $this->mode == 'span' || $this->mode != 'block' &&
preg_match('{^<(?:'.$this->contain_span_tags_re.')\b}', $tag);
# Calculate indent before tag.
if (preg_match('/(?:^|\n)( *?)(?! ).*?$/', $block_text, $matches)) {
$strlen = $this->utf8_strlen;
$indent = $strlen($matches[1], 'UTF-8');
} else {
$indent = 0;
}
# End preceding block with this tag.
$block_text .= $tag;
$parsed .= $this->$hash_method($block_text);
# Get enclosing tag name for the ParseMarkdown function.
# (This pattern makes $tag_name_re safe without quoting.)
preg_match('/^<([\w:$]*)\b/', $tag, $matches);
$tag_name_re = $matches[1];
# Parse the content using the HTML-in-Markdown parser.
list ($block_text, $text)
= $this->_hashHTMLBlocks_inMarkdown($text, $indent,
$tag_name_re, $span_mode);
# Outdent markdown text.
if ($indent > 0) {
$block_text = preg_replace("/^[ ]{1,$indent}/m", "",
$block_text);
}
# Append tag content to parsed text.
if (!$span_mode) $parsed .= "\n\n$block_text\n\n";
else $parsed .= "$block_text";
# Start over with 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, $text);
}
protected function hashClean($text) {
#
# Called whenever a tag must be hashed when a function inserts a "clean" tag
# in $text, it passes through this function and is automaticaly escaped,
# blocking invalid nested overlap.
#
return $this->hashPart($text, 'C');
}
protected function doAnchors($text) {
#
# Turn Markdown link shortcuts into XHTML tags.
#
if ($this->in_anchor) return $text;
$this->in_anchor = true;
#
# First, handle reference-style links: [link text] [id]
#
$text = preg_replace_callback('{
( # wrap whole match in $1
\[
('.$this->nested_brackets_re.') # link text = $2
\]
[ ]? # one optional space
(?:\n[ ]*)? # one optional newline followed by spaces
\[
(.*?) # id = $3
\]
)
}xs',
array($this, '_doAnchors_reference_callback'), $text);
#
# Next, inline-style links: [link text](url "optional title")
#
$text = preg_replace_callback('{
( # wrap whole match in $1
\[
('.$this->nested_brackets_re.') # link text = $2
\]
\( # literal paren
[ \n]*
(?:
<(.+?)> # href = $3
|
('.$this->nested_url_parenthesis_re.') # href = $4
)
[ \n]*
( # $5
([\'"]) # quote char = $6
(.*?) # Title = $7
\6 # matching quote
[ \n]* # ignore any spaces/tabs between closing quote and )
)? # title is optional
\)
(?:[ ]? '.$this->id_class_attr_catch_re.' )? # $8 = id/class attributes
)
}xs',
array($this, '_doAnchors_inline_callback'), $text);
#
# Last, handle reference-style shortcuts: [link text]
# These must come last in case you've also got [link text][1]
# or [link text](/foo)
#
$text = preg_replace_callback('{
( # wrap whole match in $1
\[
([^\[\]]+) # link text = $2; can\'t contain [ or ]
\]
)
}xs',
array($this, '_doAnchors_reference_callback'), $text);
$this->in_anchor = false;
return $text;
}
protected function _doAnchors_reference_callback($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 = $this->encodeURLAttribute($url);
$result = "titles[$link_id] ) ) {
$title = $this->titles[$link_id];
$title = $this->encodeAttribute($title);
$result .= " title=\"$title\"";
}
if (isset($this->ref_attr[$link_id]))
$result .= $this->ref_attr[$link_id];
$link_text = $this->runSpanGamut($link_text);
$result .= ">$link_text";
$result = $this->hashPart($result);
}
else {
$result = $whole_match;
}
return $result;
}
protected function _doAnchors_inline_callback($matches) {
$whole_match = $matches[1];
$link_text = $this->runSpanGamut($matches[2]);
$url = $matches[3] == '' ? $matches[4] : $matches[3];
$title =& $matches[7];
$attr = $this->doExtraAttributes("a", $dummy =& $matches[8]);
// if the URL was of the form it got caught by the HTML
// tag parser and hashed. Need to reverse the process before using the URL.
$unhashed = $this->unhash($url);
if ($unhashed != $url)
$url = preg_replace('/^<(.*)>$/', '\1', $unhashed);
$url = $this->encodeURLAttribute($url);
$result = "encodeAttribute($title);
$result .= " title=\"$title\"";
}
$result .= $attr;
$link_text = $this->runSpanGamut($link_text);
$result .= ">$link_text";
return $this->hashPart($result);
}
protected function doImages($text) {
#
# Turn Markdown image shortcuts into tags.
#
#
# First, handle reference-style labeled images: ![alt text][id]
#
$text = preg_replace_callback('{
( # wrap whole match in $1
!\[
('.$this->nested_brackets_re.') # alt text = $2
\]
[ ]? # one optional space
(?:\n[ ]*)? # one optional newline followed by spaces
\[
(.*?) # id = $3
\]
)
}xs',
array($this, '_doImages_reference_callback'), $text);
#
# Next, handle inline images: 
# Don't forget: encode * and _
#
$text = preg_replace_callback('{
( # wrap whole match in $1
!\[
('.$this->nested_brackets_re.') # alt text = $2
\]
\s? # One optional whitespace character
\( # literal paren
[ \n]*
(?:
<(\S*)> # src url = $3
|
('.$this->nested_url_parenthesis_re.') # src url = $4
)
[ \n]*
( # $5
([\'"]) # quote char = $6
(.*?) # title = $7
\6 # matching quote
[ \n]*
)? # title is optional
\)
(?:[ ]? '.$this->id_class_attr_catch_re.' )? # $8 = id/class attributes
)
}xs',
array($this, '_doImages_inline_callback'), $text);
return $text;
}
protected function _doImages_reference_callback($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 = $this->encodeURLAttribute($this->urls[$link_id]);
$result = "titles[$link_id])) {
$title = $this->titles[$link_id];
$title = $this->encodeAttribute($title);
$result .= " title=\"$title\"";
}
if (isset($this->ref_attr[$link_id]))
$result .= $this->ref_attr[$link_id];
$result .= $this->empty_element_suffix;
$result = $this->hashPart($result);
}
else {
# If there's no such link ID, leave intact:
$result = $whole_match;
}
return $result;
}
protected function _doImages_inline_callback($matches) {
$whole_match = $matches[1];
$alt_text = $matches[2];
$url = $matches[3] == '' ? $matches[4] : $matches[3];
$title =& $matches[7];
$attr = $this->doExtraAttributes("img", $dummy =& $matches[8]);
$alt_text = $this->encodeAttribute($alt_text);
$url = $this->encodeURLAttribute($url);
$result = "encodeAttribute($title);
$result .= " title=\"$title\""; # $title already quoted
}
$result .= $attr;
$result .= $this->empty_element_suffix;
return $this->hashPart($result);
}
protected function doHeaders($text) {
#
# Redefined to add id and class attribute support.
#
# Setext-style headers:
# Header 1 {#header1}
# ========
#
# Header 2 {#header2 .class1 .class2}
# --------
#
$text = preg_replace_callback(
'{
(^.+?) # $1: Header text
(?:[ ]+ '.$this->id_class_attr_catch_re.' )? # $3 = id/class attributes
[ ]*\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.class1.class2}
# ...
# ###### Header 6 {.class2}
#
$text = preg_replace_callback('{
^(\#{1,6}) # $1 = string of #\'s
[ ]*
(.+?) # $2 = Header text
[ ]*
\#* # optional closing #\'s (not counted)
(?:[ ]+ '.$this->id_class_attr_catch_re.' )? # $3 = id/class attributes
[ ]*
\n+
}xm',
array($this, '_doHeaders_callback_atx'), $text);
return $text;
}
protected function _doHeaders_callback_setext($matches) {
if ($matches[3] == '-' && preg_match('{^- }', $matches[1]))
return $matches[0];
$level = $matches[3]{0} == '=' ? 1 : 2;
$defaultId = is_callable($this->header_id_func) ? call_user_func($this->header_id_func, $matches[1]) : null;
$attr = $this->doExtraAttributes("h$level", $dummy =& $matches[2], $defaultId);
$block = "".$this->runSpanGamut($matches[1])."";
return "\n" . $this->hashBlock($block) . "\n\n";
}
protected function _doHeaders_callback_atx($matches) {
$level = strlen($matches[1]);
$defaultId = is_callable($this->header_id_func) ? call_user_func($this->header_id_func, $matches[2]) : null;
$attr = $this->doExtraAttributes("h$level", $dummy =& $matches[3], $defaultId);
$block = "".$this->runSpanGamut($matches[2])."";
return "\n" . $this->hashBlock($block) . "\n\n";
}
protected 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 $text;
}
protected function _doTable_leadingPipe_callback($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, $content));
}
protected function _doTable_makeAlignAttr($alignname)
{
if (empty($this->table_align_class_tmpl))
return " align=\"$alignname\"";
$classname = str_replace('%%', $alignname, $this->table_align_class_tmpl);
return " class=\"$classname\"";
}
protected 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] = $this->_doTable_makeAlignAttr('right');
else if (preg_match('/^ *:-+: *$/', $s))
$attr[$n] = $this->_doTable_makeAlignAttr('center');
else if (preg_match('/^ *:-+ *$/', $s))
$attr[$n] = $this->_doTable_makeAlignAttr('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);
$attr = array_pad($attr, $col_count, '');
# Write column headers.
$text = "
";
return $this->hashBlock($text) . "\n";
}
protected 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 $text;
}
protected function _doDefLists_callback($matches) {
# Re-usable patterns to match list item bullets and number markers:
$list = $matches[1];
# Turn double returns into triple returns, so that we can make a
# paragraph for the last item in a list, if necessary:
$result = trim($this->processDefListItems($list));
$result = "
\n" . $result . "\n
";
return $this->hashBlock($result) . "\n\n";
}
protected 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.'} \:[ ] |
\n";
}
protected function doFencedCodeBlocks($text) {
#
# Adding the fenced code block syntax to regular Markdown:
#
# ~~~
# Code block
# ~~~
#
$less_than_tab = $this->tab_width;
$text = preg_replace_callback('{
(?:\n|\A)
# 1: Opening marker
(
(?:~{3,}|`{3,}) # 3 or more tildes/backticks.
)
[ ]*
(?:
\.?([-_:a-zA-Z0-9]+) # 2: standalone class name
)?
[ ]*
(?:
'.$this->id_class_attr_catch_re.' # 3: Extra attributes
)?
[ ]* \n # Whitespace and newline following marker.
# 4: Content
(
(?>
(?!\1 [ ]* \n) # Not a closing marker.
.*\n+
)+
)
# Closing marker.
\1 [ ]* (?= \n )
}xm',
array($this, '_doFencedCodeBlocks_callback'), $text);
return $text;
}
protected function _doFencedCodeBlocks_callback($matches) {
$classname =& $matches[2];
$attrs =& $matches[3];
$codeblock = $matches[4];
if ($this->code_block_content_func) {
$codeblock = call_user_func($this->code_block_content_func, $codeblock, $classname);
} else {
$codeblock = htmlspecialchars($codeblock, ENT_NOQUOTES);
}
$codeblock = preg_replace_callback('/^\n+/',
array($this, '_doFencedCodeBlocks_newlines'), $codeblock);
$classes = array();
if ($classname != "") {
if ($classname{0} == '.')
$classname = substr($classname, 1);
$classes[] = $this->code_class_prefix.$classname;
}
$attr_str = $this->doExtraAttributes($this->code_attr_on_pre ? "pre" : "code", $attrs, null, $classes);
$pre_attr_str = $this->code_attr_on_pre ? $attr_str : '';
$code_attr_str = $this->code_attr_on_pre ? '' : $attr_str;
$codeblock = "$codeblock";
return "\n\n".$this->hashBlock($codeblock)."\n\n";
}
protected function _doFencedCodeBlocks_newlines($matches) {
return str_repeat("empty_element_suffix",
strlen($matches[0]));
}
#
# Redefining emphasis markers so that emphasis by underscore does not
# work in the middle of a word.
#
protected $em_relist = array(
'' => '(?:(? '(? '(? '(?:(? '(? '(? '(?:(? '(? '(? tags
#
# Strip leading and trailing lines:
$text = preg_replace('/\A\n+|\n+\z/', '', $text);
$grafs = preg_split('/\n{2,}/', $text, -1, PREG_SPLIT_NO_EMPTY);
#
# Wrap
tags and unhashify HTML blocks
#
foreach ($grafs as $key => $value) {
$value = trim($this->runSpanGamut($value));
# Check if this should be enclosed in a paragraph.
# Clean tag hashes & block tag hashes are left alone.
$is_p = !preg_match('/^B\x1A[0-9]+B|^C\x1A[0-9]+C$/', $value);
if ($is_p) {
$value = "
$value
";
}
$grafs[$key] = $value;
}
# Join grafs in one text, then unhash HTML tags.
$text = implode("\n\n", $grafs);
# Finish by removing any tag hashes still present in $text.
$text = $this->unhash($text);
return $text;
}
### Footnotes
protected function stripFootnotes($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 or link definition marker.
(?!\n+[ ]{0,3}\S)# ensure line is not blank and followed
# by non-indented content
)*
)
}xm',
array($this, '_stripFootnotes_callback'),
$text);
return $text;
}
protected function _stripFootnotes_callback($matches) {
$note_id = $this->fn_id_prefix . $matches[1];
$this->footnotes[$note_id] = $this->outdent($matches[2]);
return ''; # String that will replace the block
}
protected 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 $text;
}
protected function appendFootnotes($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 .= "
";
}
return $text;
}
protected function _appendFootnotes_callback($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])) {
$num =& $this->footnotes_numbers[$node_id];
if (!isset($num)) {
# Transfer footnote content to the ordered list and give it its
# number
$this->footnotes_ordered[$node_id] = $this->footnotes[$node_id];
$this->footnotes_ref_count[$node_id] = 1;
$num = $this->footnote_counter++;
$ref_count_mark = '';
} else {
$ref_count_mark = $this->footnotes_ref_count[$node_id] += 1;
}
$attr = "";
if ($this->fn_link_class != "") {
$class = $this->fn_link_class;
$class = $this->encodeAttribute($class);
$attr .= " class=\"$class\"";
}
if ($this->fn_link_title != "") {
$title = $this->fn_link_title;
$title = $this->encodeAttribute($title);
$attr .= " title=\"$title\"";
}
$attr = str_replace("%%", $num, $attr);
$node_id = $this->encodeAttribute($node_id);
return
"".
"$num".
"";
}
return "[^".$matches[1]."]";
}
### Abbreviations ###
protected 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 $text;
}
protected function _stripAbbreviations_callback($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($abbr_desc);
return ''; # String that will replace the block
}
protected function doAbbreviations($text) {
#
# Find defined abbreviations in text and wrap them in elements.
#
if ($this->abbr_word_re) {
// cannot use the /x modifier because abbr_word_re may
// contain significant spaces:
$text = preg_replace_callback('{'.
'(?abbr_word_re.')'.
'(?![\w\x1A])'.
'}',
array($this, '_doAbbreviations_callback'), $text);
}
return $text;
}
protected function _doAbbreviations_callback($matches) {
$abbr = $matches[0];
if (isset($this->abbr_desciptions[$abbr])) {
$desc = $this->abbr_desciptions[$abbr];
if (empty($desc)) {
return $this->hashPart("$abbr");
} else {
$desc = $this->encodeAttribute($desc);
return $this->hashPart("$abbr");
}
} else {
return $matches[0];
}
}
}
php-markdown-1.6.0/Michelf/MarkdownInterface.inc.php 0000664 0000000 0000000 00000000515 12636646133 0022373 0 ustar 00root root 0000000 0000000
#
# Original Markdown
# Copyright (c) 2004-2006 John Gruber
#
#
namespace Michelf;
#
# Markdown Parser Interface
#
interface MarkdownInterface {
#
# Initialize the parser and return the result of its transform method.
# This will work fine for derived classes too.
#
public static function defaultTransform($text);
#
# Main function. Performs some preprocessing on the input text
# and pass it through the document gamut.
#
public function transform($text);
}
php-markdown-1.6.0/Readme.md 0000664 0000000 0000000 00000033040 12636646133 0015656 0 ustar 00root root 0000000 0000000 PHP Markdown
============
PHP Markdown Lib 1.6.0 - 23 Dec 2015
by Michel Fortin
based on Markdown by John Gruber
Introduction
------------
This is a library package that includes the PHP Markdown parser and its
sibling PHP Markdown Extra with additional features.
Markdown is a text-to-HTML conversion tool for web writers. Markdown
allows you to write using an easy-to-read, easy-to-write plain text
format, then convert it to structurally valid XHTML (or HTML).
"Markdown" is actually two things: a plain text markup syntax, and a
software tool, originally written in Perl, that converts the plain text
markup to HTML. PHP Markdown is a port to PHP of the original Markdown
program by John Gruber.
* [Full documentation of the Markdown syntax]()
— Daring Fireball (John Gruber)
* [Markdown Extra syntax additions]()
— Michel Fortin
Requirement
-----------
This library package requires PHP 5.3 or later.
Note: The older plugin/library hybrid package for PHP Markdown and
PHP Markdown Extra is still maintained and will work with PHP 4.0.5 and later.
Before PHP 5.3.7, pcre.backtrack_limit defaults to 100 000, which is too small
in many situations. You might need to set it to higher values. Later PHP
releases defaults to 1 000 000, which is usually fine.
Usage
-----
This library package is meant to be used with class autoloading. For autoloading
to work, your project needs have setup a PSR-0-compatible autoloader. See the
included Readme.php file for a minimal autoloader setup. (If you cannot use
autoloading, see below.)
With class autoloading in place, putting the 'Michelf' folder in your
include path should be enough for this to work:
use \Michelf\Markdown;
$my_html = Markdown::defaultTransform($my_text);
Markdown Extra syntax is also available the same way:
use \Michelf\MarkdownExtra;
$my_html = MarkdownExtra::defaultTransform($my_text);
If you wish to use PHP Markdown with another text filter function
built to parse HTML, you should filter the text *after* the `transform`
function call. This is an example with [PHP SmartyPants][psp]:
use \Michelf\Markdown, \Michelf\SmartyPants;
$my_html = Markdown::defaultTransform($my_text);
$my_html = SmartyPants::defaultTransform($my_html);
All these examples are using the static `defaultTransform` static function
found inside the parser class. If you want to customize the parser
configuration, you can also instantiate it directly and change some
configuration variables:
use \Michelf\MarkdownExtra;
$parser = new MarkdownExtra;
$parser->fn_id_prefix = "post22-";
$my_html = $parser->transform($my_text);
To learn more, see the full list of [configuration variables].
[configuration variables]: https://michelf.ca/projects/php-markdown/configuration/
### Usage without an autoloader
If you cannot use class autoloading, you can still use `include` or `require`
to access the parser. To load the `\Michelf\Markdown` parser, do it this way:
require_once 'Michelf/Markdown.inc.php';
Or, if you need the `\Michelf\MarkdownExtra` parser:
require_once 'Michelf/MarkdownExtra.inc.php';
While the plain `.php` files depend on autoloading to work correctly, using the
`.inc.php` files instead will eagerly load the dependencies that would be
loaded on demand if you were using autoloading.
Public API and Versioning Policy
---------------------------------
Version numbers are of the form *major*.*minor*.*patch*.
The public API of PHP Markdown consist of the two parser classes `Markdown`
and `MarkdownExtra`, their constructors, the `transform` and `defaultTransform`
functions and their configuration variables. The public API is stable for
a given major version number. It might get additions when the minor version
number increments.
**Protected members are not considered public API.** This is unconventional
and deserves an explanation. Incrementing the major version number every time
the underlying implementation of something changes is going to give
nonessential version numbers for the vast majority of people who just use the
parser. Protected members are meant to create parser subclasses that behave in
different ways. Very few people create parser subclasses. I don't want to
discourage it by making everything private, but at the same time I can't
guarantee any stable hook between versions if you use protected members.
**Syntax changes** will increment the minor number for new features, and the
patch number for small corrections. A *new feature* is something that needs a
change in the syntax documentation. Note that since PHP Markdown Lib includes
two parsers, a syntax change for either of them will increment the minor
number. Also note that there is nothing perfectly backward-compatible with the
Markdown syntax: all inputs are always valid, so new features always replace
something that was previously legal, although generally nonsensical to do.
Bugs
----
To file bug reports please send email to:
Please include with your report: (1) the example input; (2) the output you
expected; (3) the output PHP Markdown actually produced.
If you have a problem where Markdown gives you an empty result, first check
that the backtrack limit is not too low by running `php --info | grep pcre`.
See Installation and Requirement above for details.
Development and Testing
-----------------------
Pull requests for fixing bugs are welcome. Proposed new features are
going meticulously reviewed -- taking into account backward compatibility,
potential side effects, and future extensibility -- before deciding on
acceptance or rejection.
If you make a pull request that includes changes to the parser please add
tests for what is being changed to [MDTest][] and make a pull request there
too.
[MDTest]: https://github.com/michelf/mdtest/
Donations
---------
If you wish to make a donation that will help me devote more time to
PHP Markdown, please visit [michelf.ca/donate] or send Bitcoin to
[1HiuX34czvVPPdhXbUAsAu7pZcesniDCGH].
[michelf.ca/donate]: https://michelf.ca/donate/#!Thanks%20for%20PHP%20Markdown
[1HiuX34czvVPPdhXbUAsAu7pZcesniDCGH]: bitcoin:1HiuX34czvVPPdhXbUAsAu7pZcesniDCGH
Version History
---------------
PHP Markdown Lib 1.6.0 (23 Dec 2015)
Note: this version was incorrectly released as 1.5.1 on Dec 22, a number
that contradicted the versioning policy.
* For fenced code blocks in Markdown Extra, can now set a class name for the
code block's language before the special attribute block. Previously, this
class name was only allowed in the absence of the special attribute block.
* Added a `code_block_content_func` configuration variable which takes a
function that will convert the content of the code block to HTML. This is
most useful for syntax highlighting. For fenced code blocks in Markdown
Extra, the function has access to the language class name (the one outside
of the special attribute block). Credits to Mario Konrad for providing the
implementation.
* The curled arrow character for the backlink in footnotes is now followed
by a Unicode variant selector to prevent it from being displayed in emoji
form on iOS.
Note that in older browsers the variant selector is often interpreted as a
separate character, making it visible after the arrow. So there is now a
also a `fn_backlink_html` configuration variable that can be used to set
the link text to something else. Credits to Dana for providing the
implementation.
* Fixed an issue in MarkdownExtra where long header lines followed by a
special attribute block would hit the backtrack limit an cause an empty
string to be returned.
PHP Markdown Lib 1.5.0 (1 Mar 2015)
* Added the ability start ordered lists with a number different from 1 and
and have that reflected in the HTML output. This can be enabled with
the `enhanced_ordered_lists` configuration variable for the Markdown
parser; it is enabled by default for Markdown Extra.
Credits to Matt Gorle for providing the implementation.
* Added the ability to insert custom HTML attributes with simple values
everywhere an extra attribute block is allowed (links, images, headers).
The value must be unquoted, cannot contains spaces and is limited to
alphanumeric ASCII characters.
Credits to Peter Droogmans for providing the implementation.
* Added a `header_id_func` configuration variable which takes a function
that can generate an `id` attribute value from the header text.
Credits to Evert Pot for providing the implementation.
* Added a `url_filter_func` configuration variable which takes a function
that can rewrite any link or image URL to something different.
PHP Markdown Lib 1.4.1 (4 May 2014)
* The HTML block parser will now treat `` as a block-level element
(as it should) and no longer wrap it in `
` or parse it's content with
the as Markdown syntax (although with Extra you can use `markdown="1"`
if you wish to use the Markdown syntax inside it).
* The content of `
![\"$alt_text\"";](\"$url\")
titles[$link_id])) {
$title = $this->titles[$link_id];
$title = $this->encodeAttribute($title);
$result .= " title=\"$title\"";
}
if (isset($this->ref_attr[$link_id]))
$result .= $this->ref_attr[$link_id];
$result .= $this->empty_element_suffix;
$result = $this->hashPart($result);
}
else {
# If there's no such link ID, leave intact:
$result = $whole_match;
}
return $result;
}
protected function _doImages_inline_callback($matches) {
$whole_match = $matches[1];
$alt_text = $matches[2];
$url = $matches[3] == '' ? $matches[4] : $matches[3];
$title =& $matches[7];
$attr = $this->doExtraAttributes("img", $dummy =& $matches[8]);
$alt_text = $this->encodeAttribute($alt_text);
$url = $this->encodeURLAttribute($url);
$result = "