Navigation

← Previous Changeset
Next Changeset →

Changeset 2128

Timestamp:

01/24/05 06:30:16 (4 years ago)

Author:

saxmatt

Message:

Updating Markdown to 1.0.1 - http://mosquito.wordpress.org/view.php?id=730

Files:

trunk/wp-content/plugins/markdown.php (modified) (52 diffs)

Legend:

: Unmodified
: Added
: Removed
: Modified
: Copied
: Moved

trunk/wp-content/plugins/markdown.php

r1593	r2128
7	7	# <http://daringfireball.net/projects/markdown/>
8	8	#
9		# Copyright (c) 2004 Michel Fortin - ~~Translation to PHP~~
	9	# Copyright (c) 2004 Michel Fortin - PHP Port
10	10	# <http://www.michelf.com/projects/php-markdown/>
11	11	#
12
13		~~# This version has been modified for inclusion in WordPress~~
14		~~# For the original please see Michel's site~~
15	12
16	13
…	…
18	15	$md_empty_element_suffix, $md_tab_width,
19	16	$md_nested_brackets_depth, $md_nested_brackets,
20		$md_escape_table, $md_backslash_escape_table;
21
22
23		$MarkdownPHPVersion = '1.0~~'; # Sat 21 Aug~~ 2004
24		$MarkdownSyntaxVersion = '1.0~~'; # Fri 20 Aug~~ 2004
	17	$md_escape_table, $md_backslash_escape_table,
	18	$md_list_level;
	19
	20	$MarkdownPHPVersion = '1.0.1'; # Fri 17 Dec 2004
	21	$MarkdownSyntaxVersion = '1.0.1'; # Sun 12 Dec 2004
25	22
26	23
…	…
35	32	/*
36	33	Plugin Name: Markdown
37		Plugin URI: http://~~codex.wordpress.org/Plugin:Markdown~~
	34	Plugin URI: http://www.michelf.com/projects/php-markdown/
38	35	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>
39		Version: 1.0
	36	Version: 1.0.1
40	37	Author: Michel Fortin
41	38	Author URI: http://www.michelf.com/
…	…
52	49	}
53	50
	51
	52	# -- bBlog Plugin Info --------------------------------------------------------
	53	function identify_modifier_markdown() {
	54	global $MarkdownPHPVersion;
	55	return array(
	56	'name' => 'markdown',
	57	'type' => 'modifier',
	58	'nicename' => 'Markdown',
	59	'description' => 'A text-to-HTML conversion tool for web writers',
	60	'authors' => 'Michel Fortin and John Gruber',
	61	'licence' => 'GPL',
	62	'version' => $MarkdownPHPVersion,
	63	'help' => '<a href="http://daringfireball.net/projects/markdown/syntax">Markdown syntax</a> allows you to write using an easy-to-read, easy-to-write plain text format. Based on the original Perl version by <a href="http://daringfireball.net/">John Gruber</a>. <a href="http://www.michelf.com/projects/php-markdown/">More...</a>'
	64	);
	65	}
	66
	67	# -- Smarty Modifier Interface ------------------------------------------------
54	68	function smarty_modifier_markdown($text) {
55	69	return Markdown($text);
56	70	}
57	71
	72	# -- Textile Compatibility Mode -----------------------------------------------
	73	# Rename this file to "classTextile.php" and it can replace Textile anywhere.
	74	if (strcasecmp(substr(__FILE__, -16), "classTextile.php") == 0) {
	75	# Try to include PHP SmartyPants. Should be in the same directory.
	76	@include_once 'smartypants.php';
	77	# Fake Textile class. It calls Markdown instead.
	78	class Textile {
	79	function TextileThis($text, $lite='', $encode='', $noimage='', $strict='') {
	80	if ($lite == '' && $encode == '') $text = Markdown($text);
	81	if (function_exists('SmartyPants')) $text = SmartyPants($text);
	82	return $text;
	83	}
	84	}
	85	}
	86
	87
	88
	89	#
	90	# Globals:
	91	#
	92
	93	# Regex to match balanced [brackets].
	94	# Needed to insert a maximum bracked depth while converting to PHP.
58	95	$md_nested_brackets_depth = 6;
59	96	$md_nested_brackets =
…	…
61	98	str_repeat('\])*', $md_nested_brackets_depth);
62	99
	100	# Table of hash values for escaped characters:
63	101	$md_escape_table = array(
64	102	"\\" => md5("\\"),
…	…
72	110	"(" => md5("("),
73	111	")" => md5(")"),
	112	">" => md5(">"),
74	113	"#" => md5("#"),
	114	"+" => md5("+"),
	115	"-" => md5("-"),
75	116	"." => md5("."),
76	117	"!" => md5("!")
…	…
83	124
84	125	function Markdown($text) {
	126	#
	127	# Main function. The order in which other subs are called here is
	128	# essential. Link and image substitutions need to happen before
	129	# _EscapeSpecialChars(), so that any *'s or _'s in the <a>
	130	# and <img> tags get encoded.
	131	#
	132	# Clear the global hashes. If we don't clear these, you get conflicts
	133	# from other articles when generating a page which contains more than
	134	# one article (e.g. an index page that shows the N most recent
	135	# articles):
85	136	global $md_urls, $md_titles, $md_html_blocks;
86	137	$md_urls = array();
…	…
88	139	$md_html_blocks = array();
89	140
	141	# Standardize line endings:
	142	# DOS to Unix and Mac to Unix
90	143	$text = str_replace(array("\r\n", "\r"), "\n", $text);
91	144
	145	# Make sure $text ends with a couple of newlines:
92	146	$text .= "\n\n";
93	147
	148	# Convert all tabs to spaces.
94	149	$text = _Detab($text);
95	150
	151	# Strip any lines consisting only of spaces and tabs.
	152	# This makes subsequent regexen easier to write, because we can
	153	# match consecutive blank lines with /\n+/ instead of something
	154	# contorted like /[ \t]*\n+/ .
96	155	$text = preg_replace('/^[ \t]+$/m', '', $text);
97	156
	157	# Turn block-level HTML blocks into hash entries
98	158	$text = _HashHTMLBlocks($text);
99	159
	160	# Strip link definitions, store in hashes.
100	161	$text = _StripLinkDefinitions($text);
101	162
102		~~$text = _EscapeSpecialChars($text);~~
103
104	163	$text = _RunBlockGamut($text);
105	164
…	…
111	170
112	171	function _StripLinkDefinitions($text) {
	172	#
	173	# Strips link definitions from text, stores the URLs and titles in
	174	# hash references.
	175	#
	176	global $md_tab_width;
	177	$less_than_tab = $md_tab_width - 1;
	178
	179	# Link defs are in the form: ^[id]: url "optional title"
113	180	$text = preg_replace_callback('{
114		^[ \t]*\[(.+)\]: # id = $1
	181	^[ ]{0,'.$less_than_tab.'}\[(.+)\]: # id = $1
115	182	[ \t]*
116	183	\n? # maybe one newline
…	…
121	188	[ \t]*
122	189	(?:
123		~~# Todo: Titles are delimited by "quotes" or (parens).~~
	190	(?<=\s) # lookbehind for whitespace
124	191	["(]
125	192	(.+?) # title = $3
…	…
138	205	$md_urls[$link_id] = _EncodeAmpsAndAngles($matches[2]);
139	206	if (isset($matches[3]))
140		$md_titles[$link_id] = ~~htmlentities(~~$matches[3]);
	207	$md_titles[$link_id] = str_replace('"', '"', $matches[3]);
141	208	return ''; # String that will replace the block
142	209	}
…	…
144	211
145	212	function _HashHTMLBlocks($text) {
	213	global $md_tab_width;
	214	$less_than_tab = $md_tab_width - 1;
	215
	216	# Hashify HTML blocks:
	217	# We only want to do this for block-level HTML tags, such as headers,
	218	# lists, and tables. That's because we still want to wrap <p>s around
	219	# "paragraphs" that are wrapped in non-block-level tags, such as anchors,
	220	# phrase emphasis, and spans. The list of tags we're looking for is
	221	# hard-coded:
146	222	$block_tags_a = 'p\|div\|h[1-6]\|blockquote\|pre\|table\|dl\|ol\|ul\|'.
147	223	'script\|noscript\|form\|fieldset\|iframe\|math\|ins\|del';
…	…
149	225	'script\|noscript\|form\|fieldset\|iframe\|math';
150	226
	227	# First, look for nested blocks, e.g.:
	228	# <div>
	229	# <div>
	230	# tags for inner block must be indented.
	231	# </div>
	232	# </div>
	233	#
	234	# The outermost tags must start at the left margin for this to match, and
	235	# the inner nested divs must be indented.
	236	# We need to do this before the next, more liberal match, because the next
	237	# match will start at the first `<div>` and stop at the first `</div>`.
151	238	$text = preg_replace_callback("{
152	239	( # save in $1
…	…
163	250	$text);
164	251
	252	#
	253	# Now match more liberally, simply from `\n<tag>` to `</tag>\n`
	254	#
165	255	$text = preg_replace_callback("{
166	256	( # save in $1
…	…
177	267	$text);
178	268
	269	# Special case just for <hr />. It was easier to make a special case than
	270	# to make the other regex more complicated.
179	271	$text = preg_replace_callback('{
180	272	(?:
…	…
184	276	)
185	277	( # save in $1
186		[ \t]*
	278	[ ]{0,'.$less_than_tab.'}
187	279	<(hr) # start tag = $2
188	280	\b # word break
189	281	([^<>])*? #
190	282	/?> # the matching end tag
	283	[ \t]*
191	284	(?=\n{2,}\|\Z) # followed by a blank line or end of document
192	285	)
…	…
194	287	'_HashHTMLBlocks_callback',
195	288	$text);
	289
	290	# Special case for standalone HTML comments:
	291	$text = preg_replace_callback('{
	292	(?:
	293	(?<=\n\n) # Starting after a blank line
	294	\| # or
	295	\A\n? # the beginning of the doc
	296	)
	297	( # save in $1
	298	[ ]{0,'.$less_than_tab.'}
	299	(?s:
	300	<!
	301	(--.?--\s)+
	302	>
	303	)
	304	[ \t]*
	305	(?=\n{2,}\|\Z) # followed by a blank line or end of document
	306	)
	307	}x',
	308	'_HashHTMLBlocks_callback',
	309	$text);
196	310
197	311	return $text;
…	…
207	321
208	322	function _RunBlockGamut($text) {
	323	#
	324	# These are all the transformations that form block-level
	325	# tags like paragraphs, headers, and list items.
	326	#
209	327	global $md_empty_element_suffix;
210	328
…	…
213	331	# Do Horizontal Rules:
214	332	$text = preg_replace(
215		array('~~/^( ?\* ?){3,}$/m~~',
216		'~~/^( ?- ?){3,}$/m~~',
217		'~~/^( ?_ ?){3,}$/m~~'),
	333	array('{^[ ]{0,2}([ ]?\[ ]?){3,}[ \t]$}mx',
	334	'{^[ ]{0,2}([ ]? -[ ]?){3,}[ \t]*$}mx',
	335	'{^[ ]{0,2}([ ]? _[ ]?){3,}[ \t]*$}mx'),
218	336	"\n<hr$md_empty_element_suffix\n",
219	337	$text);
…	…
225	343	$text = _DoBlockQuotes($text);
226	344
227		# Make links out of things like `<http://example.com/>`
228		$text = _DoAutoLinks($text);
229
	345	# We already ran _HashHTMLBlocks() before, in Markdown(), but that
	346	# was to escape raw HTML in the original Markdown source. This time,
	347	# we're escaping the markup we've just created, so that we don't wrap
	348	# <p> tags around block-level tags.
230	349	$text = _HashHTMLBlocks($text);
231	350
…	…
237	356
238	357	function _RunSpanGamut($text) {
	358	#
	359	# These are all the transformations that occur within block-level
	360	# tags like paragraphs, headers, and list items.
	361	#
239	362	global $md_empty_element_suffix;
	363
240	364	$text = _DoCodeSpans($text);
241	365
242		# Fix unencoded ampersands and <'s:
243		$text = _EncodeAmpsAndAngles($text);
	366	$text = _EscapeSpecialChars($text);
244	367
245	368	# Process anchor and image tags. Images must come first,
…	…
248	371	$text = _DoAnchors($text);
249	372
	373	# Make links out of things like `<http://example.com/>`
	374	# Must come after _DoAnchors(), because you can use < and >
	375	# delimiters in inline links like [this](<url>).
	376	$text = _DoAutoLinks($text);
	377
	378	# Fix unencoded ampersands and <'s:
	379	$text = _EncodeAmpsAndAngles($text);
250	380
251	381	$text = _DoItalicsAndBold($text);
252	382
	383	# Do hard breaks:
253	384	$text = preg_replace('/ {2,}\n/', "<br$md_empty_element_suffix\n", $text);
254	385
…	…
262	393
263	394	$text = ''; # rebuild $text from the tokens
	395	# $in_pre = 0; # Keep track of when we're inside <pre> or <code> tags.
	396	# $tags_to_skip = "!<(/?)(?:pre\|code\|kbd\|script\|math)[\s>]!";
	397
264	398	foreach ($tokens as $cur_token) {
265	399	if ($cur_token[0] == 'tag') {
	400	# Within tags, encode * and _ so they don't conflict
	401	# with their use in Markdown for italics and strong.
	402	# We're replacing each such character with its
	403	# corresponding MD5 checksum value; this is likely
	404	# overkill, but it should prevent us from colliding
	405	# with the escape values by accident.
266	406	$cur_token[1] = str_replace(array('*', '_'),
267	407	array($md_escape_table['*'], $md_escape_table['_']),
…	…
279	419
280	420	function _DoAnchors($text) {
	421	#
	422	# Turn Markdown link shortcuts into XHTML <a> tags.
	423	#
281	424	global $md_nested_brackets;
282	425	#
…	…
299	442	'_DoAnchors_reference_callback', $text);
300	443
	444	#
	445	# Next, inline-style links: [link text](url "optional title")
	446	#
301	447	$text = preg_replace_callback("{
302	448	( # wrap whole match in $1
…	…
306	452	\\( # literal paren
307	453	[ \\t]*
308		<?(.+?)>? # href = $3
	454	<?(.*?)>? # href = $3
309	455	[ \\t]*
310	456	( # $4
…	…
353	499	function _DoAnchors_inline_callback($matches) {
354	500	global $md_escape_table;
355		$whole_match = $matches[1];
356		$link_text = $matches[2];
357		$url = $matches[3];
358		$title = $matches[6];
	501	$whole_match = $matches[1];
	502	$link_text = $matches[2];
	503	$url = $matches[3];
	504	$title =& $matches[6];
359	505
360	506	# We've got to encode these to avoid conflicting with italics/bold.
…	…
364	510	$result = "<a href=\"$url\"";
365	511	if (isset($title)) {
366		$title = str_replace('"', '&quot', $title);
	512	$title = str_replace('"', '"', $title);
367	513	$title = str_replace(array('*', '_'),
368	514	array($md_escape_table['*'], $md_escape_table['_']),
…	…
378	524
379	525	function _DoImages($text) {
	526	#
	527	# Turn Markdown image shortcuts into <img> tags.
	528	#
	529	#
	530	# First, handle reference-style labeled images: ![alt text][id]
	531	#
380	532	$text = preg_replace_callback('{
381	533	( # wrap whole match in $1
…	…
457	609	function _DoImages_inline_callback($matches) {
458	610	global $md_empty_element_suffix, $md_escape_table;
459		$whole_match = $matches[1];
460		$alt_text = $matches[2];
461		$url = $matches[3];
462		$title = '';
	611	$whole_match = $matches[1];
	612	$alt_text = $matches[2];
	613	$url = $matches[3];
	614	$title = '';
463	615	if (isset($matches[6])) {
464		$title = $matches[6];
	616	$title = $matches[6];
465	617	}
466	618
…	…
485	637
486	638	function _DoHeaders($text) {
	639	# Setext-style headers:
	640	# Header 1
	641	# ========
	642	#
	643	# Header 2
	644	# --------
	645	#
487	646	$text = preg_replace(
488		array(~~"/(.+)[ \t]\n=+[ \t]\n+/e"~~,
489		~~"/(.+)[ \t]\n-+[ \t]\n+/e"~~),
	647	array('{ ^(.+)[ \t]\n=+[ \t]\n+ }emx',
	648	'{ ^(.+)[ \t]\n-+[ \t]\n+ }emx'),
490	649	array("'<h1>'._RunSpanGamut(_UnslashQuotes('\\1')).'</h1>\n\n'",
491	650	"'<h2>'._RunSpanGamut(_UnslashQuotes('\\1')).'</h2>\n\n'"),
492	651	$text);
493	652
	653	# atx-style headers:
	654	# # Header 1
	655	# ## Header 2
	656	# ## Header 2 with closing hashes ##
	657	# ...
	658	# ###### Header 6
	659	#
494	660	$text = preg_replace("{
495	661	^(\\#{1,6}) # $1 = string of #'s
…	…
511	677	# Form HTML ordered (numbered) and unordered (bulleted) lists.
512	678	#
513		global $md_tab_width;
	679	global $md_tab_width, $md_list_level;
514	680	$less_than_tab = $md_tab_width - 1;
515	681
…	…
519	685	$marker_any = "(?:$marker_ul\|$marker_ol)";
520	686
521		$text = preg_replace_callback("{
522		( # $1
523		( # $2
524		^[ ]{0,$less_than_tab}
525		($marker_any) # $3 - first list item marker
526		[ \\t]+
	687	# Re-usable pattern to match any entirel ul or ol list:
	688	$whole_list = '
	689	( # $1 = whole list
	690	( # $2
	691	[ ]{0,'.$less_than_tab.'}
	692	('.$marker_any.') # $3 = first list item marker
	693	[ \t]+
	694	)
	695	(?s:.+?)
	696	( # $4
	697	\z
	698	\|
	699	\n{2,}
	700	(?=\S)
	701	(?! # Negative lookahead for another list item marker
	702	[ \t]*
	703	'.$marker_any.'[ \t]+
527	704	)
528		(?s:.+?)
529		( # $4
530		\\z
531		\|
532		\\n{2,}
533		(?=\\S)
534		(?! # Negative lookahead for another list item marker
535		[ \\t]*
536		{$marker_any}[ \\t]+
537		)
538		)
539		)
540		}xm",
541		'_DoLists_callback', $text);
	705	)
	706	)
	707	'; // mx
	708
	709	# We use a different prefix before nested lists than top-level lists.
	710	# See extended comment in _ProcessListItems().
	711
	712	if ($md_list_level) {
	713	$text = preg_replace_callback('{
	714	^
	715	'.$whole_list.'
	716	}mx',
	717	'_DoLists_callback', $text);
	718	}
	719	else {
	720	$text = preg_replace_callback('{
	721	(?:(?<=\n\n)\|\A\n?)
	722	'.$whole_list.'
	723	}mx',
	724	'_DoLists_callback', $text);
	725	}
542	726
543	727	return $text;
…	…
550	734
551	735	$list = $matches[1];
552		$list_type = preg_match(~~'/[*+-]/'~~, $matches[3]) ? "ul" : "ol";
	736	$list_type = preg_match("/$marker_ul/", $matches[3]) ? "ul" : "ol";
553	737	# Turn double returns into triple returns, so that we can make a
554	738	# paragraph for the last item in a list, if necessary:
555	739	$list = preg_replace("/\n{2,}/", "\n\n\n", $list);
556	740	$result = _ProcessListItems($list, $marker_any);
557		$result = "<$list_type>\n" . $result . "</$list_type>\n\n";
	741	$result = "<$list_type>\n" . $result . "</$list_type>\n";
558	742	return $result;
559	743	}
…	…
561	745
562	746	function _ProcessListItems($list_str, $marker_any) {
	747	#
	748	# Process the contents of a single ordered or unordered list, splitting it
	749	# into individual list items.
	750	#
	751	global $md_list_level;
	752
	753	# The $md_list_level global keeps track of when we're inside a list.
	754	# Each time we enter a list, we increment it; when we leave a list,
	755	# we decrement. If it's zero, we're not in a list anymore.
	756	#
	757	# We do this because when we're not inside a list, we want to treat
	758	# something like this:
	759	#
	760	# I recommend upgrading to version
	761	# 8. Oops, now this line is treated
	762	# as a sub-list.
	763	#
	764	# As a single paragraph, despite the fact that the second line starts
	765	# with a digit-period-space sequence.
	766	#
	767	# Whereas when we're inside a list (or sub-list), that line will be
	768	# treated as the start of a sub-list. What a kludge, huh? This is
	769	# an aspect of Markdown's syntax that's hard to parse perfectly
	770	# without resorting to mind-reading. Perhaps the solution is to
	771	# change the syntax rules such that sub-lists must start with a
	772	# starting cardinal number; e.g. "1." or "a.".
	773
	774	$md_list_level++;
	775
563	776	# trim trailing blank lines:
564	777	$list_str = preg_replace("/\n{2,}\\z/", "\n", $list_str);
…	…
574	787	'_ProcessListItems_callback', $list_str);
575	788
	789	$md_list_level--;
576	790	return $list_str;
577	791	}
578	792	function _ProcessListItems_callback($matches) {
579	793	$item = $matches[4];
580		$leading_line = $matches[1];
581		$leading_space = $matches[2];
	794	$leading_line =& $matches[1];
	795	$leading_space =& $matches[2];
582	796
583	797	if ($leading_line \|\| preg_match('/\n{2,}/', $item)) {
584	798	$item = _RunBlockGamut(_Outdent($item));
585		~~#$item =~ s/\n+/\n/g;~~
586	799	}
587	800	else {
…	…
597	810
598	811	function _DoCodeBlocks($text) {
	812	#
	813	# Process Markdown `<pre><code>` blocks.
	814	#
599	815	global $md_tab_width;
600	816	$text = preg_replace_callback("{
…	…
616	832
617	833	$codeblock = _EncodeCode(_Outdent($codeblock));
618		$codeblock = _Detab($codeblock);
	834	// $codeblock = _Detab($codeblock);
619	835	# trim leading newlines and trailing whitespace
620	836	$codeblock = preg_replace(array('/\A\n+/', '/\s+\z/'), '', $codeblock);
…	…
627	843
628	844	function _DoCodeSpans($text) {
	845	#
	846	# * Backtick quotes are used for <code></code> spans.
	847	#
	848	# * You can use multiple backticks as the delimiters if you want to
	849	# include literal backticks in the code span. So, this input:
	850	#
	851	# Just type ``foo `bar` baz`` at the prompt.
	852	#
	853	# Will translate to:
	854	#
	855	# <p>Just type <code>foo `bar` baz</code> at the prompt.</p>
	856	#
	857	# There's no arbitrary limit to the number of backticks you
	858	# can use as delimters. If you need three consecutive backticks
	859	# in your code, use four for delimiters, etc.
	860	#
	861	# * You can use spaces to get literal backticks at the edges:
	862	#
	863	# ... type `` `bar` `` ...
	864	#
	865	# Turns to:
	866	#
	867	# ... type <code>`bar`</code> ...
	868	#
629	869	$text = preg_replace_callback("@
630	870	(`+) # $1 = Opening run of `
…	…
648	888
649	889	function _EncodeCode($_) {
	890	#
	891	# Encode/escape certain characters inside Markdown code runs.
	892	# The point is that in code, these characters are literals,
	893	# and lose their special Markdown meanings.
	894	#
650	895	global $md_escape_table;
651	896
	897	# Encode all ampersands; HTML entities are not
	898	# entities within a Markdown code span.
652	899	$_ = str_replace('&', '&', $_);
653	900
	901	# Do the angle bracket song and dance:
654	902	$_ = str_replace(array('<', '>'),
655	903	array('<', '>'), $_);
656	904
	905	# Now, escape characters that are magic in Markdown:
657	906	$_ = str_replace(array_keys($md_escape_table),
658	907	array_values($md_escape_table), $_);
…	…
664	913	function _DoItalicsAndBold($text) {
665	914	# <strong> must go first:
666		$text = preg_replace('{ (\\\|__) (?=\S) (.+?) (?<=\S) \1 }sx',
	915	$text = preg_replace('{ (\\\|__) (?=\S) (.+?[_]) (?<=\S) \1 }sx',
667	916	'<strong>\2</strong>', $text);
668	917	# Then <em>:
…	…
710	959
711	960	function _FormParagraphs($text) {
	961	#
	962	# Params:
	963	# $text - string to process with html <p> tags
	964	#
712	965	global $md_html_blocks;
713	966
…	…
716	969
717	970	$grafs = preg_split('/\n{2,}/', $text, -1, PREG_SPLIT_NO_EMPTY);
718		$count = count($grafs);
719
	971
	972	#
	973	# Wrap <p> tags.
	974	#
720	975	foreach ($grafs as $key => $value) {
721	976	if (!isset( $md_html_blocks[$value] )) {
…	…
727	982	}
728	983
	984	#
	985	# Unhashify HTML blocks
	986	#
729	987	foreach ($grafs as $key => $value) {
730	988	if (isset( $md_html_blocks[$value] )) {
…	…
738	996
739	997	function _EncodeAmpsAndAngles($text) {
	998	# Smart processing for ampersands and angle brackets that need to be encoded.
	999
	1000	# Ampersand-encoding based entirely on Nat Irons's Amputator MT plugin:
	1001	# http://bumppo.net/projects/amputator/
740	1002	$text = preg_replace('/&(?!#?[xX]?(?:[0-9a-fA-F]+\|\w+);)/',
741	1003	'&', $text);;
…	…
749	1011
750	1012	function _EncodeBackslashEscapes($text) {
	1013	#
	1014	# Parameter: String.
	1015	# Returns: The string, with after processing the following backslash
	1016	# escape sequences.
	1017	#
751	1018	global $md_escape_table, $md_backslash_escape_table;
752	1019	# Must process escaped backslashes first.
…	…
763	1030	$text = preg_replace('{
764	1031	<
	1032	(?:mailto:)?
765	1033	(
766	1034	[-.\w]+
…	…
778	1046
779	1047	function _EncodeEmailAddress($addr) {
	1048	#
	1049	# Input: an email address, e.g. "foo@example.com"
	1050	#
	1051	# Output: the email address as a mailto link, with each character
	1052	# of the address encoded as either a decimal or hex entity, in
	1053	# the hopes of foiling most address harvesting spam bots. E.g.:
	1054	#
	1055	# <a href="mailto:foo@e
	1056	# xample.com">foo
	1057	# @example.com</a>
	1058	#
	1059	# Based by a filter by Matthew Wickline, posted to the BBEdit-Talk
	1060	# mailing list: <http://tinyurl.com/yu7ue>
	1061	#
780	1062	$addr = "mailto:" . $addr;
781	1063	$length = strlen($addr);
…	…
803	1085
804	1086	function _UnescapeSpecialChars($text) {
	1087	#
	1088	# Swap back in all the special characters we've hidden.
	1089	#
805	1090	global $md_escape_table;
806	1091	return str_replace(array_values($md_escape_table),
…	…
809	1094
810	1095
811		if (!function_exists('_TokenizeHTML')) {
812		function _TokenizeHTML($str) {
813		$index = 0;
814		$tokens = array();
815
816		$depth = 6;
817		$nested_tags = str_repeat('(?:<[a-z\/!$](?:[^<>]\|',$depth)
818		.str_repeat(')*>)', $depth);
819		$match = "(?s:<!(?:--.?--\s)+>)\|". # comment
820		"(?s:<\?.*?\?>)\|". # processing instruction
821		"$nested_tags"; # nested tags
822
823		$parts = preg_split("/($match)/", $str, -1, PREG_SPLIT_DELIM_CAPTURE);
824
825		foreach ($parts as $part) {
826		if (++$index % 2 && $part != '')
827		array_push($tokens, array('text', $part));
828		else
829		array_push($tokens, array('tag', $part));
830		}
831
832		return $tokens;
833		}
834		}
	1096	# _TokenizeHTML is shared between PHP Markdown and PHP SmartyPants.
	1097	# We only define it if it is not already defined.
	1098	if (!function_exists('_TokenizeHTML')) :
	1099	function _TokenizeHTML($str) {
	1100	#
	1101	# Parameter: String containing HTML markup.
	1102	# Returns: An array of the tokens comprising the input
	1103	# string. Each token is either a tag (possibly with nested,
	1104	# tags contained therein, such as <a href="<MTFoo>">, or a
	1105	# run of text between tags. Each element of the array is a
	1106	# two-element array; the first is either 'tag' or 'text';
	1107	# the second is the actual value.
	1108	#
	1109	#
	1110	# Regular expression derived from the _tokenize() subroutine in
	1111	# Brad Choate's MTRegex plugin.
	1112	# <http://www.bradchoate.com/past/mtregex.php>
	1113	#
	1114	$index = 0;
	1115	$tokens = array();
	1116
	1117	$match = '(?s:<!(?:--.?--\s)+>)\|'. # comment
	1118	'(?s:<\?.*?\?>)\|'. # processing instruction
	1119	'(?:</?[\w:$]+\b(?>[^"\'>]+\|"[^"]"\|\'[^\']\')*>)'; # regular tags
	1120
	1121	$parts = preg_split("{($match)}", $str, -1, PREG_SPLIT_DELIM_CAPTURE);
	1122
	1123	foreach ($parts as $part) {
	1124	if (++$index % 2 && $part != '')
	1125	array_push($tokens, array('text', $part));
	1126	else
	1127	array_push($tokens, array('tag', $part));
	1128	}
	1129
	1130	return $tokens;
	1131	}
	1132	endif;
835	1133
836	1134
837	1135	function _Outdent($text) {
	1136	#
	1137	# Remove one level of line-leading tabs or spaces
	1138	#
838	1139	global $md_tab_width;
839	1140	return preg_replace("/^(\\t\|[ ]{1,$md_tab_width})/m", "", $text);
…	…
842	1143
843	1144	function _Detab($text) {
	1145	#
	1146	# Replace tabs with the appropriate amount of space.
	1147	#
844	1148	global $md_tab_width;
845		$text = preg_replace(
846		"/(.*?)\t/e",
847		"'\\1'.str_repeat(' ', $md_tab_width - strlen('\\1') % $md_tab_width)",
848		$text);
	1149
	1150	# For each line we separate the line in blocks delemited by
	1151	# tab characters. Then we reconstruct the line adding the appropriate
	1152	# number of space charcters.
	1153
	1154	$lines = explode("\n", $text);
	1155	$text = "";
	1156
	1157	foreach ($lines as $line) {
	1158	# Split in blocks.
	1159	$blocks = explode("\t", $line);
	1160	# Add each blocks to the line.
	1161	$line = $blocks[0];
	1162	unset($blocks[0]); # Do not add first block twice.
	1163	foreach ($blocks as $block) {
	1164	# Calculate amount of space, insert spaces, insert block.
	1165	$amount = $md_tab_width - strlen($line) % $md_tab_width;
	1166	$line .= str_repeat(" ", $amount) . $block;
	1167	}
	1168	$text .= "$line\n";
	1169	}
849	1170	return $text;
850	1171	}
…	…
852	1173
853	1174	function _UnslashQuotes($text) {
	1175	#
	1176	# This function is useful to remove automaticaly slashed double quotes
	1177	# when using preg_replace and evaluating an expression.
	1178	# Parameter: String.
	1179	# Returns: The string with any slash-double-quote (\") sequence replaced
	1180	# by a single double quote.
	1181	#
854	1182	return str_replace('\"', '"', $text);
855	1183	}
856	1184
	1185
	1186	/*
	1187
	1188	PHP Markdown
	1189	============
	1190
	1191	Description
	1192	-----------
	1193
	1194	This is a PHP translation of the original Markdown formatter written in
	1195	Perl by John Gruber.
	1196
	1197	Markdown is a text-to-HTML filter; it translates an easy-to-read /
	1198	easy-to-write structured text format into HTML. Markdown's text format
	1199	is most similar to that of plain text email, and supports features such
	1200	as headers, emphasis, code blocks, blockquotes, and links.
	1201
	1202	Markdown's syntax is designed not as a generic markup language, but
	1203	specifically to serve as a front-end to (X)HTML. You can use span-level
	1204	HTML tags anywhere in a Markdown document, and you can use block level
	1205	HTML tags (like <div> and <table> as well).
	1206
	1207	For more information about Markdown's syntax, see:
	1208
	1209	<http://daringfireball.net/projects/markdown/>
	1210
	1211
	1212	Bugs
	1213	----
	1214
	1215	To file bug reports please send email to:
	1216
	1217	<michel.fortin@michelf.com>
	1218
	1219	Please include with your report: (1) the example input; (2) the output you
	1220	expected; (3) the output Markdown actually produced.
	1221
	1222
	1223	Version History
	1224	---------------
	1225
	1226	See the readme file for detailed release notes for this version.
	1227
	1228	1.0.1 - 17 Dec 2004
	1229
	1230	1.0 - 21 Aug 2004
	1231
	1232
	1233	Author & Contributors
	1234	---------------------
	1235
	1236	Original Perl version by John Gruber
	1237	<http://daringfireball.net/>
	1238
	1239	PHP port and other contributions by Michel Fortin
	1240	<http://www.michelf.com/>
	1241
	1242
	1243	Copyright and License
	1244	---------------------
	1245
	1246	Copyright (c) 2004 Michel Fortin
	1247	<http://www.michelf.com/>
	1248	All rights reserved.
	1249
	1250	Copyright (c) 2003-2004 John Gruber
	1251	<http://daringfireball.net/>
	1252	All rights reserved.
	1253
	1254	Redistribution and use in source and binary forms, with or without
	1255	modification, are permitted provided that the following conditions are
	1256	met:
	1257
	1258	* Redistributions of source code must retain the above copyright notice,
	1259	this list of conditions and the following disclaimer.
	1260
	1261	* Redistributions in binary form must reproduce the above copyright
	1262	notice, this list of conditions and the following disclaimer in the
	1263	documentation and/or other materials provided with the distribution.
	1264
	1265	* Neither the name "Markdown" nor the names of its contributors may
	1266	be used to endorse or promote products derived from this software
	1267	without specific prior written permission.
	1268
	1269	This software is provided by the copyright holders and contributors "as
	1270	is" and any express or implied warranties, including, but not limited
	1271	to, the implied warranties of merchantability and fitness for a
	1272	particular purpose are disclaimed. In no event shall the copyright owner
	1273	or contributors be liable for any direct, indirect, incidental, special,
	1274	exemplary, or consequential damages (including, but not limited to,
	1275	procurement of substitute goods or services; loss of use, data, or
	1276	profits; or business interruption) however caused and on any theory of
	1277	liability, whether in contract, strict liability, or tort (including
	1278	negligence or otherwise) arising in any way out of the use of this
	1279	software, even if advised of the possibility of such damage.
	1280
	1281	*/
857	1282	?>

Navigation

Changeset 2128

Legend:

trunk/wp-content/plugins/markdown.php

Download in other formats: