Context Navigation

Back to Ticket #1706

Ticket #1706: functions-formatting.php

File functions-formatting.php, 32.7 KB (added by rockinfree, 20 years ago)
Fixed version of file with line 75 in wpautop() updated (sorry, no diff on this system)

Line
1	<?php
2
3	function wptexturize($text) {
4	$output = '';
5	// Capture tags and everything inside them
6	$textarr = preg_split("/(<.*>)/Us", $text, -1, PREG_SPLIT_DELIM_CAPTURE);
7	$stop = count($textarr); $next = true; // loop stuff
8	for ($i = 0; $i < $stop; $i++) {
9	$curl = $textarr[$i];
10
11	if (isset($curl{0}) && '<' != $curl{0} && $next) { // If it's not a tag
12	$curl = str_replace('---', '—', $curl);
13	$curl = str_replace(' -- ', ' — ', $curl);
14	$curl = str_replace('--', '–', $curl);
15	$curl = str_replace('xn–', 'xn--', $curl);
16	$curl = str_replace('...', '…', $curl);
17	$curl = str_replace('``', '“', $curl);
18
19	// This is a hack, look at this more later. It works pretty well though.
20	$cockney = array("'tain't","'twere","'twas","'tis","'twill","'til","'bout","'nuff","'round","'cause");
21	$cockneyreplace = array("’tain’t","’twere","’twas","’tis","’twill","’til","’bout","’nuff","’round","’cause");
22	$curl = str_replace($cockney, $cockneyreplace, $curl);
23
24	$curl = preg_replace("/'s/", '’s', $curl);
25	$curl = preg_replace("/'(\d\d(?:’\|')?s)/", "’$1", $curl);
26	$curl = preg_replace('/(\s\|\A\|")\'/', '$1‘', $curl);
27	$curl = preg_replace('/(\d+)"/', '$1″', $curl);
28	$curl = preg_replace("/(\d+)'/", '$1′', $curl);
29	$curl = preg_replace("/(\S)'([^'\s])/", "$1’$2", $curl);
30	$curl = preg_replace('/(\s\|\A)"(?!\s)/', '$1“$2', $curl);
31	$curl = preg_replace('/"(\s\|\S\|\Z)/', '”$1', $curl);
32	$curl = preg_replace("/'([\s.]\|\Z)/", '’$1', $curl);
33	$curl = preg_replace("/ $tm$/i", ' ™', $curl);
34	$curl = str_replace("''", '”', $curl);
35
36	$curl = preg_replace('/(\d+)x(\d+)/', "$1×$2", $curl);
37
38	} elseif (strstr($curl, '<code') \|\| strstr($curl, '<pre') \|\| strstr($curl, '<kbd' \|\| strstr($curl, '<style') \|\| strstr($curl, '<script'))) {
39	// strstr is fast
40	$next = false;
41	} else {
42	$next = true;
43	}
44	$curl = preg_replace('/&([^#])(?![a-z12]{1,8};)/', '&$1', $curl);
45	$output .= $curl;
46	}
47	return $output;
48	}
49
50	function clean_pre($text) {
51	$text = str_replace('<br />', '', $text);
52	$text = str_replace('<p>', "\n", $text);
53	$text = str_replace('</p>', '', $text);
54	return $text;
55	}
56
57	function wpautop($pee, $br = 1) {
58	$pee = $pee . "\n"; // just to make things a little easier, pad the end
59	$pee = preg_replace('\|<br />\s*<br />\|', "\n\n", $pee);
60	// Space things out a little
61	$pee = preg_replace('!(<(?:table\|thead\|tfoot\|caption\|colgroup\|tbody\|tr\|td\|th\|div\|dl\|dd\|dt\|ul\|ol\|li\|pre\|select\|form\|blockquote\|address\|math\|p\|h[1-6])[^>]*>)!', "\n$1", $pee);
62	$pee = preg_replace('!(</(?:table\|thead\|tfoot\|caption\|colgroup\|tbody\|tr\|td\|th\|div\|dl\|dd\|dt\|ul\|ol\|li\|pre\|select\|form\|blockquote\|address\|math\|p\|h[1-6])>)!', "$1\n", $pee);
63	$pee = str_replace(array("\r\n", "\r"), "\n", $pee); // cross-platform newlines
64	$pee = preg_replace("/\n\n+/", "\n\n", $pee); // take care of duplicates
65	$pee = preg_replace('/\n?(.+?)(?:\n\s*\n\|\z)/s', "\t<p>$1</p>\n", $pee); // make paragraphs, including one at the end
66	$pee = preg_replace('\|<p>\s*?</p>\|', '', $pee); // under certain strange conditions it could create a P of entirely whitespace
67	$pee = preg_replace('!<p>\s(</?(?:table\|thead\|tfoot\|caption\|colgroup\|tbody\|tr\|td\|th\|div\|dl\|dd\|dt\|ul\|ol\|li\|hr\|pre\|select\|form\|blockquote\|address\|math\|p\|h[1-6])[^>]>)\s*</p>!', "$1", $pee); // don't pee all over a tag
68	$pee = preg_replace("\|<p>(<li.+?)</p>\|", "$1", $pee); // problem with nested lists
69	$pee = preg_replace('\|<p><blockquote([^>]*)>\|i', "<blockquote$1><p>", $pee);
70	$pee = str_replace('</blockquote></p>', '</p></blockquote>', $pee);
71	$pee = preg_replace('!<p>\s(</?(?:table\|thead\|tfoot\|caption\|colgroup\|tbody\|tr\|td\|th\|div\|dl\|dd\|dt\|ul\|ol\|li\|hr\|pre\|select\|form\|blockquote\|address\|math\|p\|h[1-6])[^>]>)!', "$1", $pee);
72	$pee = preg_replace('!(</?(?:table\|thead\|tfoot\|caption\|colgroup\|tbody\|tr\|td\|th\|div\|dl\|dd\|dt\|ul\|ol\|li\|pre\|select\|form\|blockquote\|address\|math\|p\|h[1-6])[^>]>)\s</p>!', "$1", $pee);
73	if ($br) $pee = preg_replace('\|(?<!<br />)\s*\n\|', "<br />\n", $pee); // optionally make line breaks
74	$pee = preg_replace('!(</?(?:table\|thead\|tfoot\|caption\|tbody\|tr\|td\|th\|div\|dl\|dd\|dt\|ul\|ol\|li\|pre\|select\|form\|blockquote\|address\|math\|p\|h[1-6])[^>]>)\s<br />!', "$1", $pee);
75	$pee = preg_replace('!<br />(\s</?(?:p\|li\|div\|dl\|dd\|dt\|th\|pre\|td\|ul\|ol)[^>]>)!', '$1', $pee);
76	$pee = preg_replace('!(<pre.?>)(.?)</pre>!ise', " stripslashes('$1') . clean_pre('$2') . '</pre>' ", $pee);
77
78	return $pee;
79	}
80
81	function seems_utf8($Str) { # by bmorel at ssi dot fr
82	for ($i=0; $i<strlen($Str); $i++) {
83	if (ord($Str[$i]) < 0x80) continue; # 0bbbbbbb
84	elseif ((ord($Str[$i]) & 0xE0) == 0xC0) $n=1; # 110bbbbb
85	elseif ((ord($Str[$i]) & 0xF0) == 0xE0) $n=2; # 1110bbbb
86	elseif ((ord($Str[$i]) & 0xF8) == 0xF0) $n=3; # 11110bbb
87	elseif ((ord($Str[$i]) & 0xFC) == 0xF8) $n=4; # 111110bb
88	elseif ((ord($Str[$i]) & 0xFE) == 0xFC) $n=5; # 1111110b
89	else return false; # Does not match any model
90	for ($j=0; $j<$n; $j++) { # n bytes matching 10bbbbbb follow ?
91	if ((++$i == strlen($Str)) \|\| ((ord($Str[$i]) & 0xC0) != 0x80))
92	return false;
93	}
94	}
95	return true;
96	}
97
98	function wp_specialchars( $text, $quotes = 0 ) {
99	// Like htmlspecialchars except don't double-encode HTML entities
100	$text = preg_replace('/&([^#])(?![a-z12]{1,8};)/', '&$1', $text);-
101	$text = str_replace('<', '<', $text);
102	$text = str_replace('>', '>', $text);
103	if ( $quotes ) {
104	$text = str_replace('"', '"', $text);
105	$text = str_replace("'", ''', $text);
106	}
107	return $text;
108	}
109
110	function utf8_uri_encode( $utf8_string ) {
111	$unicode = '';
112	$values = array();
113	$num_octets = 1;
114
115	for ($i = 0; $i < strlen( $utf8_string ); $i++ ) {
116
117	$value = ord( $utf8_string[ $i ] );
118
119	if ( $value < 128 ) {
120	$unicode .= chr($value);
121	} else {
122	if ( count( $values ) == 0 ) $num_octets = ( $value < 224 ) ? 2 : 3;
123
124	$values[] = $value;
125
126	if ( count( $values ) == $num_octets ) {
127	if ($num_octets == 3) {
128	$unicode .= '%' . dechex($values[0]) . '%' . dechex($values[1]) . '%' . dechex($values[2]);
129	} else {
130	$unicode .= '%' . dechex($values[0]) . '%' . dechex($values[1]);
131	}
132
133	$values = array();
134	$num_octets = 1;
135	}
136	}
137	}
138
139	return $unicode;
140	}
141
142	function remove_accents($string) {
143	if (seems_utf8($string)) {
144	$chars = array(
145	// Decompositions for Latin-1 Supplement
146	chr(195).chr(128) => 'A', chr(195).chr(129) => 'A',
147	chr(195).chr(130) => 'A', chr(195).chr(131) => 'A',
148	chr(195).chr(132) => 'A', chr(195).chr(133) => 'A',
149	chr(195).chr(135) => 'C', chr(195).chr(136) => 'E',
150	chr(195).chr(137) => 'E', chr(195).chr(138) => 'E',
151	chr(195).chr(139) => 'E', chr(195).chr(140) => 'I',
152	chr(195).chr(141) => 'I', chr(195).chr(142) => 'I',
153	chr(195).chr(143) => 'I', chr(195).chr(145) => 'N',
154	chr(195).chr(146) => 'O', chr(195).chr(147) => 'O',
155	chr(195).chr(148) => 'O', chr(195).chr(149) => 'O',
156	chr(195).chr(150) => 'O', chr(195).chr(153) => 'U',
157	chr(195).chr(154) => 'U', chr(195).chr(155) => 'U',
158	chr(195).chr(156) => 'U', chr(195).chr(157) => 'Y',
159	chr(195).chr(159) => 's', chr(195).chr(160) => 'a',
160	chr(195).chr(161) => 'a', chr(195).chr(162) => 'a',
161	chr(195).chr(163) => 'a', chr(195).chr(164) => 'a',
162	chr(195).chr(165) => 'a', chr(195).chr(167) => 'c',
163	chr(195).chr(168) => 'e', chr(195).chr(169) => 'e',
164	chr(195).chr(170) => 'e', chr(195).chr(171) => 'e',
165	chr(195).chr(172) => 'i', chr(195).chr(173) => 'i',
166	chr(195).chr(174) => 'i', chr(195).chr(175) => 'i',
167	chr(195).chr(177) => 'n', chr(195).chr(178) => 'o',
168	chr(195).chr(179) => 'o', chr(195).chr(180) => 'o',
169	chr(195).chr(181) => 'o', chr(195).chr(182) => 'o',
170	chr(195).chr(182) => 'o', chr(195).chr(185) => 'u',
171	chr(195).chr(186) => 'u', chr(195).chr(187) => 'u',
172	chr(195).chr(188) => 'u', chr(195).chr(189) => 'y',
173	chr(195).chr(191) => 'y',
174	// Decompositions for Latin Extended-A
175	chr(196).chr(128) => 'A', chr(196).chr(129) => 'a',
176	chr(196).chr(130) => 'A', chr(196).chr(131) => 'a',
177	chr(196).chr(132) => 'A', chr(196).chr(133) => 'a',
178	chr(196).chr(134) => 'C', chr(196).chr(134) => 'c',
179	chr(196).chr(136) => 'C', chr(196).chr(137) => 'c',
180	chr(196).chr(138) => 'C', chr(196).chr(139) => 'c',
181	chr(196).chr(140) => 'C', chr(196).chr(141) => 'c',
182	chr(196).chr(142) => 'D', chr(196).chr(143) => 'd',
183	chr(196).chr(144) => 'D', chr(196).chr(145) => 'd',
184	chr(196).chr(146) => 'E', chr(196).chr(147) => 'e',
185	chr(196).chr(148) => 'E', chr(196).chr(149) => 'e',
186	chr(196).chr(150) => 'E', chr(196).chr(151) => 'e',
187	chr(196).chr(152) => 'E', chr(196).chr(153) => 'e',
188	chr(196).chr(154) => 'E', chr(196).chr(155) => 'e',
189	chr(196).chr(156) => 'G', chr(196).chr(157) => 'g',
190	chr(196).chr(158) => 'G', chr(196).chr(159) => 'g',
191	chr(196).chr(160) => 'G', chr(196).chr(161) => 'g',
192	chr(196).chr(162) => 'G', chr(196).chr(163) => 'g',
193	chr(196).chr(164) => 'H', chr(196).chr(165) => 'h',
194	chr(196).chr(166) => 'H', chr(196).chr(167) => 'h',
195	chr(196).chr(168) => 'I', chr(196).chr(169) => 'i',
196	chr(196).chr(170) => 'I', chr(196).chr(171) => 'i',
197	chr(196).chr(172) => 'I', chr(196).chr(173) => 'i',
198	chr(196).chr(174) => 'I', chr(196).chr(175) => 'i',
199	chr(196).chr(176) => 'I', chr(196).chr(177) => 'i',
200	chr(196).chr(178) => 'IJ',chr(196).chr(179) => 'ij',
201	chr(196).chr(180) => 'J', chr(196).chr(181) => 'j',
202	chr(196).chr(182) => 'K', chr(196).chr(183) => 'k',
203	chr(196).chr(184) => 'k', chr(196).chr(185) => 'L',
204	chr(196).chr(186) => 'l', chr(196).chr(187) => 'L',
205	chr(196).chr(188) => 'l', chr(196).chr(189) => 'L',
206	chr(196).chr(190) => 'l', chr(196).chr(191) => 'L',
207	chr(197).chr(128) => 'l', chr(196).chr(129) => 'L',
208	chr(197).chr(130) => 'l', chr(196).chr(131) => 'N',
209	chr(197).chr(132) => 'n', chr(196).chr(133) => 'N',
210	chr(197).chr(134) => 'n', chr(196).chr(135) => 'N',
211	chr(197).chr(136) => 'n', chr(196).chr(137) => 'N',
212	chr(197).chr(138) => 'n', chr(196).chr(139) => 'N',
213	chr(197).chr(140) => 'O', chr(196).chr(141) => 'o',
214	chr(197).chr(142) => 'O', chr(196).chr(143) => 'o',
215	chr(197).chr(144) => 'O', chr(196).chr(145) => 'o',
216	chr(197).chr(146) => 'OE',chr(197).chr(147) => 'oe',
217	chr(197).chr(148) => 'R',chr(197).chr(149) => 'r',
218	chr(197).chr(150) => 'R',chr(197).chr(151) => 'r',
219	chr(197).chr(152) => 'R',chr(197).chr(153) => 'r',
220	chr(197).chr(154) => 'S',chr(197).chr(155) => 's',
221	chr(197).chr(156) => 'S',chr(197).chr(157) => 's',
222	chr(197).chr(158) => 'S',chr(197).chr(159) => 's',
223	chr(197).chr(160) => 'S', chr(197).chr(161) => 's',
224	chr(197).chr(162) => 'T', chr(197).chr(163) => 't',
225	chr(197).chr(164) => 'T', chr(197).chr(165) => 't',
226	chr(197).chr(166) => 'T', chr(197).chr(167) => 't',
227	chr(197).chr(168) => 'U', chr(197).chr(169) => 'u',
228	chr(197).chr(170) => 'U', chr(197).chr(171) => 'u',
229	chr(197).chr(172) => 'U', chr(197).chr(173) => 'u',
230	chr(197).chr(174) => 'U', chr(197).chr(175) => 'u',
231	chr(197).chr(176) => 'U', chr(197).chr(177) => 'u',
232	chr(197).chr(178) => 'U', chr(197).chr(179) => 'u',
233	chr(197).chr(180) => 'W', chr(197).chr(181) => 'w',
234	chr(197).chr(182) => 'Y', chr(197).chr(183) => 'y',
235	chr(197).chr(184) => 'Y', chr(197).chr(185) => 'Z',
236	chr(197).chr(186) => 'z', chr(197).chr(187) => 'Z',
237	chr(197).chr(188) => 'z', chr(197).chr(189) => 'Z',
238	chr(197).chr(190) => 'z', chr(197).chr(191) => 's',
239	// Euro Sign
240	chr(226).chr(130).chr(172) => 'E');
241
242	$string = strtr($string, $chars);
243	} else {
244	// Assume ISO-8859-1 if not UTF-8
245	$chars['in'] = chr(128).chr(131).chr(138).chr(142).chr(154).chr(158)
246	.chr(159).chr(162).chr(165).chr(181).chr(192).chr(193).chr(194)
247	.chr(195).chr(196).chr(197).chr(199).chr(200).chr(201).chr(202)
248	.chr(203).chr(204).chr(205).chr(206).chr(207).chr(209).chr(210)
249	.chr(211).chr(212).chr(213).chr(214).chr(216).chr(217).chr(218)
250	.chr(219).chr(220).chr(221).chr(224).chr(225).chr(226).chr(227)
251	.chr(228).chr(229).chr(231).chr(232).chr(233).chr(234).chr(235)
252	.chr(236).chr(237).chr(238).chr(239).chr(241).chr(242).chr(243)
253	.chr(244).chr(245).chr(246).chr(248).chr(249).chr(250).chr(251)
254	.chr(252).chr(253).chr(255);
255
256	$chars['out'] = "EfSZszYcYuAAAAAACEEEEIIIINOOOOOOUUUUYaaaaaaceeeeiiiinoooooouuuuyy";
257
258	$string = strtr($string, $chars['in'], $chars['out']);
259	$double_chars['in'] = array(chr(140), chr(156), chr(198), chr(208), chr(222), chr(223), chr(230), chr(240), chr(254));
260	$double_chars['out'] = array('OE', 'oe', 'AE', 'DH', 'TH', 'ss', 'ae', 'dh', 'th');
261	$string = str_replace($double_chars['in'], $double_chars['out'], $string);
262	}
263
264	return $string;
265	}
266
267	function sanitize_title($title, $fallback_title = '') {
268	$title = strip_tags($title);
269	$title = apply_filters('sanitize_title', $title);
270
271	if (empty($title)) {
272	$title = $fallback_title;
273	}
274
275	return $title;
276	}
277
278	function sanitize_title_with_dashes($title) {
279	$title = strip_tags($title);
280	// Preserve escaped octets.
281	$title = preg_replace('\|%([a-fA-F0-9][a-fA-F0-9])\|', '---$1---', $title);
282	// Remove percent signs that are not part of an octet.
283	$title = str_replace('%', '', $title);
284	// Restore octets.
285	$title = preg_replace('\|---([a-fA-F0-9][a-fA-F0-9])---\|', '%$1', $title);
286
287	$title = remove_accents($title);
288	if (seems_utf8($title)) {
289	if (function_exists('mb_strtolower')) {
290	$title = mb_strtolower($title, 'UTF-8');
291	}
292	$title = utf8_uri_encode($title);
293	}
294
295	$title = strtolower($title);
296	$title = preg_replace('/&.+?;/', '', $title); // kill entities
297	$title = preg_replace('/[^%a-z0-9 _-]/', '', $title);
298	$title = preg_replace('/\s+/', '-', $title);
299	$title = preg_replace('\|-+\|', '-', $title);
300	$title = trim($title, '-');
301
302	return $title;
303	}
304
305	function convert_chars($content, $flag = 'obsolete') {
306	// Translation of invalid Unicode references range to valid range
307	$wp_htmltranswinuni = array(
308	'' => '€', // the Euro sign
309	'' => '',
310	'' => '‚', // these are Windows CP1252 specific characters
311	'' => 'ƒ', // they would look weird on non-Windows browsers
312	'' => '„',
313	'' => '…',
314	'' => '†',
315	'' => '‡',
316	'' => 'ˆ',
317	'' => '‰',
318	'' => 'Š',
319	'' => '‹',
320	'' => 'Œ',
321	'' => '',
322	'' => 'ž',
323	'' => '',
324	'' => '',
325	'' => '‘',
326	'' => '’',
327	'' => '“',
328	'' => '”',
329	'' => '•',
330	'' => '–',
331	'' => '—',
332	'' => '˜',
333	'' => '™',
334	'' => 'š',
335	'' => '›',
336	'' => 'œ',
337	'' => '',
338	'' => '',
339	'' => 'Ÿ'
340	);
341
342	// Remove metadata tags
343	$content = preg_replace('/<title>(.+?)<\/title>/','',$content);
344	$content = preg_replace('/<category>(.+?)<\/category>/','',$content);
345
346	// Converts lone & characters into & (a.k.a. &)
347	$content = preg_replace('/&([^#])(?![a-z]{1,8};)/i', '&$1', $content);
348
349	// Fix Word pasting
350	$content = strtr($content, $wp_htmltranswinuni);
351
352	// Just a little XHTML help
353	$content = str_replace('<br>', '<br />', $content);
354	$content = str_replace('<hr>', '<hr />', $content);
355
356	return $content;
357	}
358
359	function funky_javascript_fix($text) {
360	// Fixes for browsers' javascript bugs
361	global $is_macIE, $is_winIE;
362
363	if ( $is_winIE \|\| $is_macIE )
364	$text = preg_replace("/\%u([0-9A-F]{4,4})/e", "'&#'.base_convert('\\1',16,10).';'", $text);
365
366	return $text;
367	}
368
369	/*
370	balanceTags
371
372	Balances Tags of string using a modified stack.
373
374	@param text Text to be balanced
375	@return Returns balanced text
376	@author Leonard Lin (leonard@acm.org)
377	@version v1.1
378	@date November 4, 2001
379	@license GPL v2.0
380	@notes
381	@changelog
382	--- Modified by Scott Reilly (coffee2code) 02 Aug 2004
383	1.2 *TODO* Make better - change loop condition to $text
384	1.1 Fixed handling of append/stack pop order of end text
385	Added Cleaning Hooks
386	1.0 First Version
387	*/
388	function balanceTags($text, $is_comment = 0) {
389
390	if (get_settings('use_balanceTags') == 0) {
391	return $text;
392	}
393
394	$tagstack = array(); $stacksize = 0; $tagqueue = ''; $newtext = '';
395
396	# WP bug fix for comments - in case you REALLY meant to type '< !--'
397	$text = str_replace('< !--', '< !--', $text);
398	# WP bug fix for LOVE <3 (and other situations with '<' before a number)
399	$text = preg_replace('#<([0-9]{1})#', '<$1', $text);
400
401	while (preg_match("/<(\/?\w)\s([^>]*)>/",$text,$regex)) {
402	$newtext .= $tagqueue;
403
404	$i = strpos($text,$regex[0]);
405	$l = strlen($regex[0]);
406
407	// clear the shifter
408	$tagqueue = '';
409	// Pop or Push
410	if ($regex[1][0] == "/") { // End Tag
411	$tag = strtolower(substr($regex[1],1));
412	// if too many closing tags
413	if($stacksize <= 0) {
414	$tag = '';
415	//or close to be safe $tag = '/' . $tag;
416	}
417	// if stacktop value = tag close value then pop
418	else if ($tagstack[$stacksize - 1] == $tag) { // found closing tag
419	$tag = '</' . $tag . '>'; // Close Tag
420	// Pop
421	array_pop ($tagstack);
422	$stacksize--;
423	} else { // closing tag not at top, search for it
424	for ($j=$stacksize-1;$j>=0;$j--) {
425	if ($tagstack[$j] == $tag) {
426	// add tag to tagqueue
427	for ($k=$stacksize-1;$k>=$j;$k--){
428	$tagqueue .= '</' . array_pop ($tagstack) . '>';
429	$stacksize--;
430	}
431	break;
432	}
433	}
434	$tag = '';
435	}
436	} else { // Begin Tag
437	$tag = strtolower($regex[1]);
438
439	// Tag Cleaning
440
441	// If self-closing or '', don't do anything.
442	if((substr($regex[2],-1) == '/') \|\| ($tag == '')) {
443	}
444	// ElseIf it's a known single-entity tag but it doesn't close itself, do so
445	elseif ($tag == 'br' \|\| $tag == 'img' \|\| $tag == 'hr' \|\| $tag == 'input') {
446	$regex[2] .= '/';
447	} else { // Push the tag onto the stack
448	// If the top of the stack is the same as the tag we want to push, close previous tag
449	if (($stacksize > 0) && ($tag != 'div') && ($tagstack[$stacksize - 1] == $tag)) {
450	$tagqueue = '</' . array_pop ($tagstack) . '>';
451	$stacksize--;
452	}
453	$stacksize = array_push ($tagstack, $tag);
454	}
455
456	// Attributes
457	$attributes = $regex[2];
458	if($attributes) {
459	$attributes = ' '.$attributes;
460	}
461	$tag = '<'.$tag.$attributes.'>';
462	//If already queuing a close tag, then put this tag on, too
463	if ($tagqueue) {
464	$tagqueue .= $tag;
465	$tag = '';
466	}
467	}
468	$newtext .= substr($text,0,$i) . $tag;
469	$text = substr($text,$i+$l);
470	}
471
472	// Clear Tag Queue
473	$newtext .= $tagqueue;
474
475	// Add Remaining text
476	$newtext .= $text;
477
478	// Empty Stack
479	while($x = array_pop($tagstack)) {
480	$newtext .= '</' . $x . '>'; // Add remaining tags to close
481	}
482
483	// WP fix for the bug with HTML comments
484	$newtext = str_replace("< !--","<!--",$newtext);
485	$newtext = str_replace("< !--","< !--",$newtext);
486
487	return $newtext;
488	}
489
490
491	function format_to_edit($content) {
492	$content = apply_filters('format_to_edit', $content);
493	$content = htmlspecialchars($content);
494	return $content;
495	}
496
497	function format_to_post($content) {
498	global $wpdb;
499	$content = apply_filters('format_to_post', $content);
500	return $content;
501	}
502
503	function zeroise($number,$threshold) { // function to add leading zeros when necessary
504	return sprintf('%0'.$threshold.'s', $number);
505	}
506
507
508	function backslashit($string) {
509	$string = preg_replace('/([a-z])/i', '\\\\\1', $string);
510	return $string;
511	}
512
513	function trailingslashit($string) {
514	if ( '/' != substr($string, -1)) {
515	$string .= '/';
516	}
517	return $string;
518	}
519
520	function addslashes_gpc($gpc) {
521	if (!get_magic_quotes_gpc()) {
522	$gpc = addslashes($gpc);
523	}
524	return $gpc;
525	}
526
527	function antispambot($emailaddy, $mailto=0) {
528	$emailNOSPAMaddy = '';
529	srand ((float) microtime() * 1000000);
530	for ($i = 0; $i < strlen($emailaddy); $i = $i + 1) {
531	$j = floor(rand(0, 1+$mailto));
532	if ($j==0) {
533	$emailNOSPAMaddy .= '&#'.ord(substr($emailaddy,$i,1)).';';
534	} elseif ($j==1) {
535	$emailNOSPAMaddy .= substr($emailaddy,$i,1);
536	} elseif ($j==2) {
537	$emailNOSPAMaddy .= '%'.zeroise(dechex(ord(substr($emailaddy, $i, 1))), 2);
538	}
539	}
540	$emailNOSPAMaddy = str_replace('@','@',$emailNOSPAMaddy);
541	return $emailNOSPAMaddy;
542	}
543
544	function make_clickable($ret) {
545	$ret = ' ' . $ret . ' ';
546	$ret = preg_replace("#([\s>])(https?)://([^\s<>{}()]+[^\s.,<>{}()])#i", "$1<a href='$2://$3' rel='nofollow'>$2://$3</a>", $ret);
547	$ret = preg_replace("#(\s)www\.([a-z0-9\-]+)\.([a-z0-9\-.\~]+)((?:/[^ <>{}()\n\r]*[^., <>{}()\n\r]?)?)#i", "$1<a href='http://www.$2.$3$4' rel='nofollow'>www.$2.$3$4</a>", $ret);
548	$ret = preg_replace("#(\s)([a-z0-9\-_.]+)@([^,< \n\r]+)#i", "$1<a href=\"mailto:$2@$3\">$2@$3</a>", $ret);
549	$ret = trim($ret);
550	return $ret;
551	}
552
553	function wp_rel_nofollow( $text ) {
554	$text = preg_replace('\|<a (.+?)>\|i', '<a $1 rel="nofollow">', $text);
555	return $text;
556	}
557
558	function convert_smilies($text) {
559	global $wp_smiliessearch, $wp_smiliesreplace;
560	$output = '';
561	if (get_settings('use_smilies')) {
562	// HTML loop taken from texturize function, could possible be consolidated
563	$textarr = preg_split("/(<.*>)/U", $text, -1, PREG_SPLIT_DELIM_CAPTURE); // capture the tags as well as in between
564	$stop = count($textarr);// loop stuff
565	for ($i = 0; $i < $stop; $i++) {
566	$content = $textarr[$i];
567	if ((strlen($content) > 0) && ('<' != $content{0})) { // If it's not a tag
568	$content = str_replace($wp_smiliessearch, $wp_smiliesreplace, $content);
569	}
570	$output .= $content;
571	}
572	} else {
573	// return default text.
574	$output = $text;
575	}
576	return $output;
577	}
578
579
580	function is_email($user_email) {
581	$chars = "/^([a-z0-9+_]\|\\-\|\\.)+@(([a-z0-9_]\|\\-)+\\.)+[a-z]{2,6}\$/i";
582	if(strstr($user_email, '@') && strstr($user_email, '.')) {
583	if (preg_match($chars, $user_email)) {
584	return true;
585	} else {
586	return false;
587	}
588	} else {
589	return false;
590	}
591	}
592
593
594	function strip_all_but_one_link($text, $mylink) {
595	$match_link = '#(<a.+?href.+?'.'>)(.+?)(</a>)#';
596	preg_match_all($match_link, $text, $matches);
597	$count = count($matches[0]);
598	for ($i=0; $i<$count; $i++) {
599	if (!strstr($matches[0][$i], $mylink)) {
600	$text = str_replace($matches[0][$i], $matches[2][$i], $text);
601	}
602	}
603	return $text;
604	}
605
606
607	// used by wp-mail to handle charsets in email subjects
608	function wp_iso_descrambler($string) {
609	/* this may only work with iso-8859-1, I'm afraid */
610	if (!preg_match('#\=\?(.+)\?Q\?(.+)\?\=#i', $string, $matches)) {
611	return $string;
612	} else {
613	$subject = str_replace('_', ' ', $matches[2]);
614	$subject = preg_replace('#\=([0-9a-f]{2})#ei', "chr(hexdec(strtolower('$1')))", $subject);
615	return $subject;
616	}
617	}
618
619
620	// give it a date, it will give you the same date as GMT
621	function get_gmt_from_date($string) {
622	// note: this only substracts $time_difference from the given date
623	preg_match('#([0-9]{1,4})-([0-9]{1,2})-([0-9]{1,2}) ([0-9]{1,2}):([0-9]{1,2}):([0-9]{1,2})#', $string, $matches);
624	$string_time = gmmktime($matches[4], $matches[5], $matches[6], $matches[2], $matches[3], $matches[1]);
625	$string_gmt = gmdate('Y-m-d H:i:s', $string_time - get_settings('gmt_offset') * 3600);
626	return $string_gmt;
627	}
628
629	// give it a GMT date, it will give you the same date with $time_difference added
630	function get_date_from_gmt($string) {
631	// note: this only adds $time_difference to the given date
632	preg_match('#([0-9]{1,4})-([0-9]{1,2})-([0-9]{1,2}) ([0-9]{1,2}):([0-9]{1,2}):([0-9]{1,2})#', $string, $matches);
633	$string_time = gmmktime($matches[4], $matches[5], $matches[6], $matches[2], $matches[3], $matches[1]);
634	$string_localtime = gmdate('Y-m-d H:i:s', $string_time + get_settings('gmt_offset')*3600);
635	return $string_localtime;
636	}
637
638	// computes an offset in seconds from an iso8601 timezone
639	function iso8601_timezone_to_offset($timezone) {
640	// $timezone is either 'Z' or '[+\|-]hhmm'
641	if ($timezone == 'Z') {
642	$offset = 0;
643	} else {
644	$sign = (substr($timezone, 0, 1) == '+') ? 1 : -1;
645	$hours = intval(substr($timezone, 1, 2));
646	$minutes = intval(substr($timezone, 3, 4)) / 60;
647	$offset = $sign * 3600 * ($hours + $minutes);
648	}
649	return $offset;
650	}
651
652	// converts an iso8601 date to MySQL DateTime format used by post_date[_gmt]
653	function iso8601_to_datetime($date_string, $timezone = USER) {
654	if ($timezone == GMT) {
655	preg_match('#([0-9]{4})([0-9]{2})([0-9]{2})T([0-9]{2}):([0-9]{2}):([0-9]{2})(Z\|[\+\|\-][0-9]{2,4}){0,1}#', $date_string, $date_bits);
656	if (!empty($date_bits[7])) { // we have a timezone, so let's compute an offset
657	$offset = iso8601_timezone_to_offset($date_bits[7]);
658	} else { // we don't have a timezone, so we assume user local timezone (not server's!)
659	$offset = 3600 * get_settings('gmt_offset');
660	}
661	$timestamp = gmmktime($date_bits[4], $date_bits[5], $date_bits[6], $date_bits[2], $date_bits[3], $date_bits[1]);
662	$timestamp -= $offset;
663	return gmdate('Y-m-d H:i:s', $timestamp);
664	} elseif ($timezone == USER) {
665	return preg_replace('#([0-9]{4})([0-9]{2})([0-9]{2})T([0-9]{2}):([0-9]{2}):([0-9]{2})(Z\|[\+\|\-][0-9]{2,4}){0,1}#', '$1-$2-$3 $4:$5:$6', $date_string);
666	}
667	}
668
669	function popuplinks($text) {
670	// Comment text in popup windows should be filtered through this.
671	// Right now it's a moderately dumb function, ideally it would detect whether
672	// a target or rel attribute was already there and adjust its actions accordingly.
673	$text = preg_replace('/<a (.+?)>/i', "<a $1 target='_blank' rel='external'>", $text);
674	return $text;
675	}
676
677	function sanitize_email($email) {
678	return preg_replace('/[^a-z0-9+_.@-]/i', '', $email);
679	}
680
681	function human_time_diff( $from, $to = '' ) {
682	if ( empty($to) )
683	$to = time();
684	$diff = (int) abs($to - $from);
685	if ($diff <= 3600) {
686	$mins = round($diff / 60);
687	if ($mins <= 1)
688	$since = __('1 min');
689	else
690	$since = sprintf( __('%s mins'), $mins);
691	} else if (($diff <= 86400) && ($diff > 3600)) {
692	$hours = round($diff / 3600);
693	if ($hours <= 1)
694	$since = __('1 hour');
695	else
696	$since = sprintf( __('%s hours'), $hours );
697	} elseif ($diff >= 86400) {
698	$days = round($diff / 86400);
699	if ($days <= 1)
700	$since = __('1 day');
701	else
702	$since = sprintf( __('%s days'), $days );
703	}
704	return $since;
705	}
706
707	function wp_trim_excerpt($text) { // Fakes an excerpt if needed
708	global $post;
709	if ( '' == $text ) {
710	$text = $post->post_content;
711	$text = apply_filters('the_content', $text);
712	$text = str_replace(']]>', ']]>', $text);
713	$text = strip_tags($text);
714	$excerpt_length = 55;
715	$words = explode(' ', $text, $excerpt_length + 1);
716	if (count($words) > $excerpt_length) {
717	array_pop($words);
718	array_push($words, '[...]');
719	$text = implode(' ', $words);
720	}
721	}
722	return $text;
723	}
724
725	function ent2ncr($text) {
726	$to_ncr = array(
727	'"' => '"',
728	'&' => '&',
729	'&frasl;' => '/',
730	'<' => '<',
731	'>' => '>',
732	' ' => ' ',
733	'¡' => '¡',
734	'¢' => '¢',
735	'£' => '£',
736	'¤' => '¤',
737	'¥' => '¥',
738	'\|' => '¦',
739	'¦' => '¦',
740	'&brkbar;' => '¦',
741	'§' => '§',
742	'¨' => '¨',
743	'&die;' => '¨',
744	'©' => '©',
745	'ª' => 'ª',
746	'«' => '«',
747	'¬' => '¬',
748	'' => '',
749	'®' => '®',
750	'¯' => '¯',
751	'&hibar;' => '¯',
752	'°' => '°',
753	'±' => '±',
754	'²' => '²',
755	'³' => '³',
756	'´' => '´',
757	'µ' => 'µ',
758	'¶' => '¶',
759	'·' => '·',
760	'¸' => '¸',
761	'¹' => '¹',
762	'º' => 'º',
763	'»' => '»',
764	'¼' => '¼',
765	'½' => '½',
766	'¾' => '¾',
767	'¿' => '¿',
768	'À' => 'À',
769	'Á' => 'Á',
770	'Â' => 'Â',
771	'Ã' => 'Ã',
772	'Ä' => 'Ä',
773	'Å' => 'Å',
774	'Æ' => 'Æ',
775	'Ç' => 'Ç',
776	'È' => 'È',
777	'É' => 'É',
778	'Ê' => 'Ê',
779	'Ë' => 'Ë',
780	'Ì' => 'Ì',
781	'Í' => 'Í',
782	'Î' => 'Î',
783	'Ï' => 'Ï',
784	'Ð' => 'Ð',
785	'Ñ' => 'Ñ',
786	'Ò' => 'Ò',
787	'Ó' => 'Ó',
788	'Ô' => 'Ô',
789	'Õ' => 'Õ',
790	'Ö' => 'Ö',
791	'×' => '×',
792	'Ø' => 'Ø',
793	'Ù' => 'Ù',
794	'Ú' => 'Ú',
795	'Û' => 'Û',
796	'Ü' => 'Ü',
797	'Ý' => 'Ý',
798	'Þ' => 'Þ',
799	'ß' => 'ß',
800	'à' => 'à',
801	'á' => 'á',
802	'â' => 'â',
803	'ã' => 'ã',
804	'ä' => 'ä',
805	'å' => 'å',
806	'æ' => 'æ',
807	'ç' => 'ç',
808	'è' => 'è',
809	'é' => 'é',
810	'ê' => 'ê',
811	'ë' => 'ë',
812	'ì' => 'ì',
813	'í' => 'í',
814	'î' => 'î',
815	'ï' => 'ï',
816	'ð' => 'ð',
817	'ñ' => 'ñ',
818	'ò' => 'ò',
819	'ó' => 'ó',
820	'ô' => 'ô',
821	'õ' => 'õ',
822	'ö' => 'ö',
823	'÷' => '÷',
824	'ø' => 'ø',
825	'ù' => 'ù',
826	'ú' => 'ú',
827	'û' => 'û',
828	'ü' => 'ü',
829	'ý' => 'ý',
830	'þ' => 'þ',
831	'ÿ' => 'ÿ',
832	'&OElig;' => 'Œ',
833	'&oelig;' => 'œ',
834	'&Scaron;' => 'Š',
835	'&scaron;' => 'š',
836	'&Yuml;' => 'Ÿ',
837	'&fnof;' => 'ƒ',
838	'&circ;' => 'ˆ',
839	'&tilde;' => '˜',
840	'Α' => 'Α',
841	'Β' => 'Β',
842	'Γ' => 'Γ',
843	'Δ' => 'Δ',
844	'Ε' => 'Ε',
845	'Ζ' => 'Ζ',
846	'Η' => 'Η',
847	'Θ' => 'Θ',
848	'Ι' => 'Ι',
849	'Κ' => 'Κ',
850	'Λ' => 'Λ',
851	'Μ' => 'Μ',
852	'Ν' => 'Ν',
853	'Ξ' => 'Ξ',
854	'Ο' => 'Ο',
855	'Π' => 'Π',
856	'Ρ' => 'Ρ',
857	'Σ' => 'Σ',
858	'Τ' => 'Τ',
859	'Υ' => 'Υ',
860	'Φ' => 'Φ',
861	'Χ' => 'Χ',
862	'Ψ' => 'Ψ',
863	'Ω' => 'Ω',
864	'α' => 'α',
865	'β' => 'β',
866	'γ' => 'γ',
867	'δ' => 'δ',
868	'ε' => 'ε',
869	'ζ' => 'ζ',
870	'η' => 'η',
871	'θ' => 'θ',
872	'ι' => 'ι',
873	'κ' => 'κ',
874	'λ' => 'λ',
875	'μ' => 'μ',
876	'ν' => 'ν',
877	'ξ' => 'ξ',
878	'ο' => 'ο',
879	'π' => 'π',
880	'ρ' => 'ρ',
881	'&sigmaf;' => 'ς',
882	'σ' => 'σ',
883	'τ' => 'τ',
884	'υ' => 'υ',
885	'φ' => 'φ',
886	'χ' => 'χ',
887	'ψ' => 'ψ',
888	'ω' => 'ω',
889	'&thetasym;' => 'ϑ',
890	'&upsih;' => 'ϒ',
891	'ϖ' => 'ϖ',
892	'&ensp;' => ' ',
893	'&emsp;' => ' ',
894	' ' => ' ',
895	'&zwnj;' => '‌',
896	'&zwj;' => '‍',
897	'&lrm;' => '‎',
898	'&rlm;' => '‏',
899	'–' => '–',
900	'—' => '—',
901	'‘' => '‘',
902	'’' => '’',
903	'&sbquo;' => '‚',
904	'“' => '“',
905	'”' => '”',
906	'&bdquo;' => '„',
907	'&dagger;' => '†',
908	'&Dagger;' => '‡',
909	'•' => '•',
910	'…' => '…',
911	'&permil;' => '‰',
912	'′' => '′',
913	'″' => '″',
914	'&lsaquo;' => '‹',
915	'&rsaquo;' => '›',
916	'&oline;' => '‾',
917	'&frasl;' => '⁄',
918	'€' => '€',
919	'&image;' => 'ℑ',
920	'&weierp;' => '℘',
921	'&real;' => 'ℜ',
922	'™' => '™',
923	'&alefsym;' => 'ℵ',
924	'&crarr;' => '↵',
925	'⇐' => '⇐',
926	'&uArr;' => '⇑',
927	'⇒' => '⇒',
928	'&dArr;' => '⇓',
929	'⇔' => '⇔',
930	'∀' => '∀',
931	'∂' => '∂',
932	'∃' => '∃',
933	'∅' => '∅',
934	'∇' => '∇',
935	'∈' => '∈',
936	'∉' => '∉',
937	'&ni;' => '∋',
938	'∏' => '∏',
939	'∑' => '∑',
940	'−' => '−',
941	'&lowast;' => '∗',
942	'√' => '√',
943	'&prop;' => '∝',
944	'∞' => '∞',
945	'&ang;' => '∠',
946	'&and;' => '∧',
947	'&or;' => '∨',
948	'∩' => '∩',
949	'∪' => '∪',
950	'∫' => '∫',
951	'&there4;' => '∴',
952	'&sim;' => '∼',
953	'&cong;' => '≅',
954	'≈' => '≈',
955	'≠' => '≠',
956	'&equiv;' => '≡',
957	'≤' => '≤',
958	'≥' => '≥',
959	'⊂' => '⊂',
960	'⊃' => '⊃',
961	'&nsub;' => '⊄',
962	'&sube;' => '⊆',
963	'&supe;' => '⊇',
964	'&oplus;' => '⊕',
965	'&otimes;' => '⊗',
966	'&perp;' => '⊥',
967	'⋅' => '⋅',
968	'&lceil;' => '⌈',
969	'&rceil;' => '⌉',
970	'&lfloor;' => '⌊',
971	'&rfloor;' => '⌋',
972	'&lang;' => '〈',
973	'&rang;' => '〉',
974	'←' => '←',
975	'↑' => '↑',
976	'→' => '→',
977	'↓' => '↓',
978	'↔' => '↔',
979	'&loz;' => '◊',
980	'&spades;' => '♠',
981	'&clubs;' => '♣',
982	'&hearts;' => '♥',
983	'&diams;' => '♦'
984	);
985
986	foreach ($to_ncr as $entity => $ncr) {
987	$text = str_replace($entity, $ncr, $text);
988	}
989	return $text;
990	}
991
992	?>

Trac UI Preferences

Download in other formats:

Original Format

Make WordPress Core

Context Navigation

Ticket #1706: functions-formatting.php

Download in other formats: