Projects : mp-wp : mp-wp_svg-screenshots-and-errorreporting-r2

mp-wp/wp-includes/formatting.php

Dir - Raw

1<?php
2/**
3 * Main Wordpress Formatting API.
4 *
5 * Handles many functions for formatting output.
6 *
7 * @package WordPress
8 **/
9
10/**
11 * Replaces common plain text characters into formatted entities
12 *
13 * As an example,
14 * <code>
15 * 'cause today's effort makes it worth tomorrow's "holiday"...
16 * </code>
17 * Becomes:
18 * <code>
19 * &#8217;cause today&#8217;s effort makes it worth tomorrow&#8217;s &#8220;holiday&#8221;&#8230;
20 * </code>
21 * Code within certain html blocks are skipped.
22 *
23 * @since 0.71
24 * @uses $wp_cockneyreplace Array of formatted entities for certain common phrases
25 *
26 * @param string $text The text to be formatted
27 * @return string The string replaced with html entities
28 */
29function wptexturize($text) {
30/* global $wp_cockneyreplace;
31 $next = true;
32 $has_pre_parent = false;
33 $output = '';
34 $curl = '';
35 $textarr = preg_split('/(<.*>|\[.*\])/Us', $text, -1, PREG_SPLIT_DELIM_CAPTURE);
36 $stop = count($textarr);
37
38 // if a plugin has provided an autocorrect array, use it
39 if ( isset($wp_cockneyreplace) ) {
40 $cockney = array_keys($wp_cockneyreplace);
41 $cockneyreplace = array_values($wp_cockneyreplace);
42 } else {
43 $cockney = array("'tain't","'twere","'twas","'tis","'twill","'til","'bout","'nuff","'round","'cause");
44 $cockneyreplace = array("&#8217;tain&#8217;t","&#8217;twere","&#8217;twas","&#8217;tis","&#8217;twill","&#8217;til","&#8217;bout","&#8217;nuff","&#8217;round","&#8217;cause");
45 }
46
47 $static_characters = array_merge(array('---', ' -- ', '--', 'xn&#8211;', '...', '``', '\'s', '\'\'', ' (tm)'), $cockney);
48 $static_replacements = array_merge(array('&#8212;', ' &#8212; ', '&#8211;', 'xn--', '&#8230;', '&#8220;', '&#8217;s', '&#8221;', ' &#8482;'), $cockneyreplace);
49
50 $dynamic_characters = array('/\'(\d\d(?:&#8217;|\')?s)/', '/(\s|\A|")\'/', '/(\d+)"/', '/(\d+)\'/', '/(\S)\'([^\'\s])/', '/(\s|\A)"(?!\s)/', '/"(\s|\S|\Z)/', '/\'([\s.]|\Z)/', '/(\d+)x(\d+)/');
51 $dynamic_replacements = array('&#8217;$1','$1&#8216;', '$1&#8243;', '$1&#8242;', '$1&#8217;$2', '$1&#8220;$2', '&#8221;$1', '&#8217;$1', '$1&#215;$2');
52
53 for ( $i = 0; $i < $stop; $i++ ) {
54 $curl = $textarr[$i];
55
56 if ( !empty($curl) && '<' != $curl{0} && '[' != $curl{0} && $next && !$has_pre_parent) { // If it's not a tag
57 // static strings
58 $curl = str_replace($static_characters, $static_replacements, $curl);
59 // regular expressions
60 $curl = preg_replace($dynamic_characters, $dynamic_replacements, $curl);
61 } elseif (strpos($curl, '<code') !== false || strpos($curl, '<kbd') !== false || strpos($curl, '<style') !== false || strpos($curl, '<script') !== false) {
62 $next = false;
63 } elseif (strpos($curl, '<pre') !== false) {
64 $has_pre_parent = true;
65 } elseif (strpos($curl, '</pre>') !== false) {
66 $has_pre_parent = false;
67 } else {
68 $next = true;
69 }
70
71 $curl = preg_replace('/&([^#])(?![a-zA-Z1-4]{1,8};)/', '&#038;$1', $curl);
72 $output .= $curl;
73 }
74
75 return $output;
76*/
77return $text;
78}
79
80/**
81 * Accepts matches array from preg_replace_callback in wpautop() or a string.
82 *
83 * Ensures that the contents of a <<pre>>...<</pre>> HTML block are not
84 * converted into paragraphs or line-breaks.
85 *
86 * @since 1.2.0
87 *
88 * @param array|string $matches The array or string
89 * @return string The pre block without paragraph/line-break conversion.
90 */
91function clean_pre($matches) {
92 if ( is_array($matches) )
93 $text = $matches[1] . $matches[2] . "</pre>";
94 else
95 $text = $matches;
96
97 $text = str_replace('<br />', '', $text);
98 $text = str_replace('<p>', "\n", $text);
99 $text = str_replace('</p>', '', $text);
100
101 return $text;
102}
103
104/**
105 * Replaces double line-breaks with paragraph elements.
106 *
107 * A group of regex replaces used to identify text formatted with newlines and
108 * replace double line-breaks with HTML paragraph tags. The remaining
109 * line-breaks after conversion become <<br />> tags, unless $br is set to '0'
110 * or 'false'.
111 *
112 * @since 0.71
113 *
114 * @param string $pee The text which has to be formatted.
115 * @param int|bool $br Optional. If set, this will convert all remaining line-breaks after paragraphing. Default true.
116 * @return string Text which has been converted into correct paragraph tags.
117 */
118function wpautop($pee, $br = 1) {
119 $pee = $pee . "\n"; // just to make things a little easier, pad the end
120 $pee = preg_replace('|<br />\s*<br />|', "\n\n", $pee);
121 // Space things out a little
122 $allblocks = '(?:table|thead|tfoot|caption|colgroup|tbody|tr|td|th|div|dl|dd|dt|ul|ol|li|pre|select|form|map|area|blockquote|address|math|style|input|p|h[1-6]|hr)';
123 $pee = preg_replace('!(<' . $allblocks . '[^>]*>)!', "\n$1", $pee);
124 $pee = preg_replace('!(</' . $allblocks . '>)!', "$1\n\n", $pee);
125 $pee = str_replace(array("\r\n", "\r"), "\n", $pee); // cross-platform newlines
126 if ( strpos($pee, '<object') !== false ) {
127 $pee = preg_replace('|\s*<param([^>]*)>\s*|', "<param$1>", $pee); // no pee inside object/embed
128 $pee = preg_replace('|\s*</embed>\s*|', '</embed>', $pee);
129 }
130 $pee = preg_replace("/\n\n+/", "\n\n", $pee); // take care of duplicates
131 // make paragraphs, including one at the end
132 $pees = preg_split('/\n\s*\n/', $pee, -1, PREG_SPLIT_NO_EMPTY);
133 $pee = '';
134 foreach ( $pees as $tinkle )
135 $pee .= '<p>' . trim($tinkle, "\n") . "</p>\n";
136 $pee = preg_replace('|<p>\s*?</p>|', '', $pee); // under certain strange conditions it could create a P of entirely whitespace
137 $pee = preg_replace('!<p>([^<]+)\s*?(</(?:div|address|form)[^>]*>)!', "<p>$1</p>$2", $pee);
138 $pee = preg_replace( '|<p>|', "$1<p>", $pee );
139 $pee = preg_replace('!<p>\s*(</?' . $allblocks . '[^>]*>)\s*</p>!', "$1", $pee); // don't pee all over a tag
140 $pee = preg_replace("|<p>(<li.+?)</p>|", "$1", $pee); // problem with nested lists
141 $pee = preg_replace('|<p><blockquote([^>]*)>|i', "<blockquote$1><p>", $pee);
142 $pee = str_replace('</blockquote></p>', '</p></blockquote>', $pee);
143 $pee = preg_replace('!<p>\s*(</?' . $allblocks . '[^>]*>)!', "$1", $pee);
144 $pee = preg_replace('!(</?' . $allblocks . '[^>]*>)\s*</p>!', "$1", $pee);
145 if ($br) {
146 $pee = preg_replace_callback('/<(script|style).*?<\/\\1>/s', create_function('$matches', 'return str_replace("\n", "<WPPreserveNewline />", $matches[0]);'), $pee);
147 $pee = preg_replace('|(?<!<br />)\s*\n|', "<br />\n", $pee); // optionally make line breaks
148 $pee = str_replace('<WPPreserveNewline />', "\n", $pee);
149 }
150 $pee = preg_replace('!(</?' . $allblocks . '[^>]*>)\s*<br />!', "$1", $pee);
151 $pee = preg_replace('!<br />(\s*</?(?:p|li|div|dl|dd|dt|th|pre|td|ul|ol)[^>]*>)!', '$1', $pee);
152 if (strpos($pee, '<pre') !== false)
153 $pee = preg_replace_callback('!(<pre.*?>)(.*?)</pre>!is', 'clean_pre', $pee );
154 $pee = preg_replace( "|\n</p>$|", '</p>', $pee );
155 $pee = preg_replace('/<p>\s*?(' . get_shortcode_regex() . ')\s*<\/p>/s', '$1', $pee); // don't auto-p wrap shortcodes that stand alone
156
157 return $pee;
158}
159
160/**
161 * Checks to see if a string is utf8 encoded.
162 *
163 * @author bmorel at ssi dot fr
164 *
165 * @since 1.2.1
166 *
167 * @param string $Str The string to be checked
168 * @return bool True if $Str fits a UTF-8 model, false otherwise.
169 */
170function seems_utf8($Str) { # by bmorel at ssi dot fr
171 $length = strlen($Str);
172 for ($i=0; $i < $length; $i++) {
173 if (ord($Str[$i]) < 0x80) continue; # 0bbbbbbb
174 elseif ((ord($Str[$i]) & 0xE0) == 0xC0) $n=1; # 110bbbbb
175 elseif ((ord($Str[$i]) & 0xF0) == 0xE0) $n=2; # 1110bbbb
176 elseif ((ord($Str[$i]) & 0xF8) == 0xF0) $n=3; # 11110bbb
177 elseif ((ord($Str[$i]) & 0xFC) == 0xF8) $n=4; # 111110bb
178 elseif ((ord($Str[$i]) & 0xFE) == 0xFC) $n=5; # 1111110b
179 else return false; # Does not match any model
180 for ($j=0; $j<$n; $j++) { # n bytes matching 10bbbbbb follow ?
181 if ((++$i == $length) || ((ord($Str[$i]) & 0xC0) != 0x80))
182 return false;
183 }
184 }
185 return true;
186}
187
188/**
189 * Converts a number of special characters into their HTML entities.
190 *
191 * Differs from htmlspecialchars as existing HTML entities will not be encoded.
192 * Specifically changes: & to &#038;, < to &lt; and > to &gt;.
193 *
194 * $quotes can be set to 'single' to encode ' to &#039;, 'double' to encode " to
195 * &quot;, or '1' to do both. Default is 0 where no quotes are encoded.
196 *
197 * @since 1.2.2
198 *
199 * @param string $text The text which is to be encoded.
200 * @param mixed $quotes Optional. Converts single quotes if set to 'single', double if set to 'double' or both if otherwise set. Default 0.
201 * @return string The encoded text with HTML entities.
202 */
203function wp_specialchars( $text, $quotes = 0 ) {
204 // Like htmlspecialchars except don't double-encode HTML entities
205 $text = str_replace('&&', '&#038;&', $text);
206 $text = str_replace('&&', '&#038;&', $text);
207 $text = preg_replace('/&(?:$|([^#])(?![a-z1-4]{1,8};))/', '&#038;$1', $text);
208 $text = str_replace('<', '&lt;', $text);
209 $text = str_replace('>', '&gt;', $text);
210 if ( 'double' === $quotes ) {
211 $text = str_replace('"', '&quot;', $text);
212 } elseif ( 'single' === $quotes ) {
213 $text = str_replace("'", '&#039;', $text);
214 } elseif ( $quotes ) {
215 $text = str_replace('"', '&quot;', $text);
216 $text = str_replace("'", '&#039;', $text);
217 }
218 return $text;
219}
220
221/**
222 * Encode the Unicode values to be used in the URI.
223 *
224 * @since 1.5.0
225 *
226 * @param string $utf8_string
227 * @param int $length Max length of the string
228 * @return string String with Unicode encoded for URI.
229 */
230function utf8_uri_encode( $utf8_string, $length = 0 ) {
231 $unicode = '';
232 $values = array();
233 $num_octets = 1;
234 $unicode_length = 0;
235
236 $string_length = strlen( $utf8_string );
237 for ($i = 0; $i < $string_length; $i++ ) {
238
239 $value = ord( $utf8_string[ $i ] );
240
241 if ( $value < 128 ) {
242 if ( $length && ( $unicode_length >= $length ) )
243 break;
244 $unicode .= chr($value);
245 $unicode_length++;
246 } else {
247 if ( count( $values ) == 0 ) $num_octets = ( $value < 224 ) ? 2 : 3;
248
249 $values[] = $value;
250
251 if ( $length && ( $unicode_length + ($num_octets * 3) ) > $length )
252 break;
253 if ( count( $values ) == $num_octets ) {
254 if ($num_octets == 3) {
255 $unicode .= '%' . dechex($values[0]) . '%' . dechex($values[1]) . '%' . dechex($values[2]);
256 $unicode_length += 9;
257 } else {
258 $unicode .= '%' . dechex($values[0]) . '%' . dechex($values[1]);
259 $unicode_length += 6;
260 }
261
262 $values = array();
263 $num_octets = 1;
264 }
265 }
266 }
267
268 return $unicode;
269}
270
271/**
272 * Converts all accent characters to ASCII characters.
273 *
274 * If there are no accent characters, then the string given is just returned.
275 *
276 * @since 1.2.1
277 *
278 * @param string $string Text that might have accent characters
279 * @return string Filtered string with replaced "nice" characters.
280 */
281function remove_accents($string) {
282 if ( !preg_match('/[\x80-\xff]/', $string) )
283 return $string;
284
285 if (seems_utf8($string)) {
286 $chars = array(
287 // Decompositions for Latin-1 Supplement
288 chr(195).chr(128) => 'A', chr(195).chr(129) => 'A',
289 chr(195).chr(130) => 'A', chr(195).chr(131) => 'A',
290 chr(195).chr(132) => 'A', chr(195).chr(133) => 'A',
291 chr(195).chr(135) => 'C', chr(195).chr(136) => 'E',
292 chr(195).chr(137) => 'E', chr(195).chr(138) => 'E',
293 chr(195).chr(139) => 'E', chr(195).chr(140) => 'I',
294 chr(195).chr(141) => 'I', chr(195).chr(142) => 'I',
295 chr(195).chr(143) => 'I', chr(195).chr(145) => 'N',
296 chr(195).chr(146) => 'O', chr(195).chr(147) => 'O',
297 chr(195).chr(148) => 'O', chr(195).chr(149) => 'O',
298 chr(195).chr(150) => 'O', chr(195).chr(153) => 'U',
299 chr(195).chr(154) => 'U', chr(195).chr(155) => 'U',
300 chr(195).chr(156) => 'U', chr(195).chr(157) => 'Y',
301 chr(195).chr(159) => 's', chr(195).chr(160) => 'a',
302 chr(195).chr(161) => 'a', chr(195).chr(162) => 'a',
303 chr(195).chr(163) => 'a', chr(195).chr(164) => 'a',
304 chr(195).chr(165) => 'a', chr(195).chr(167) => 'c',
305 chr(195).chr(168) => 'e', chr(195).chr(169) => 'e',
306 chr(195).chr(170) => 'e', chr(195).chr(171) => 'e',
307 chr(195).chr(172) => 'i', chr(195).chr(173) => 'i',
308 chr(195).chr(174) => 'i', chr(195).chr(175) => 'i',
309 chr(195).chr(177) => 'n', chr(195).chr(178) => 'o',
310 chr(195).chr(179) => 'o', chr(195).chr(180) => 'o',
311 chr(195).chr(181) => 'o', chr(195).chr(182) => 'o',
312 chr(195).chr(182) => 'o', chr(195).chr(185) => 'u',
313 chr(195).chr(186) => 'u', chr(195).chr(187) => 'u',
314 chr(195).chr(188) => 'u', chr(195).chr(189) => 'y',
315 chr(195).chr(191) => 'y',
316 // Decompositions for Latin Extended-A
317 chr(196).chr(128) => 'A', chr(196).chr(129) => 'a',
318 chr(196).chr(130) => 'A', chr(196).chr(131) => 'a',
319 chr(196).chr(132) => 'A', chr(196).chr(133) => 'a',
320 chr(196).chr(134) => 'C', chr(196).chr(135) => 'c',
321 chr(196).chr(136) => 'C', chr(196).chr(137) => 'c',
322 chr(196).chr(138) => 'C', chr(196).chr(139) => 'c',
323 chr(196).chr(140) => 'C', chr(196).chr(141) => 'c',
324 chr(196).chr(142) => 'D', chr(196).chr(143) => 'd',
325 chr(196).chr(144) => 'D', chr(196).chr(145) => 'd',
326 chr(196).chr(146) => 'E', chr(196).chr(147) => 'e',
327 chr(196).chr(148) => 'E', chr(196).chr(149) => 'e',
328 chr(196).chr(150) => 'E', chr(196).chr(151) => 'e',
329 chr(196).chr(152) => 'E', chr(196).chr(153) => 'e',
330 chr(196).chr(154) => 'E', chr(196).chr(155) => 'e',
331 chr(196).chr(156) => 'G', chr(196).chr(157) => 'g',
332 chr(196).chr(158) => 'G', chr(196).chr(159) => 'g',
333 chr(196).chr(160) => 'G', chr(196).chr(161) => 'g',
334 chr(196).chr(162) => 'G', chr(196).chr(163) => 'g',
335 chr(196).chr(164) => 'H', chr(196).chr(165) => 'h',
336 chr(196).chr(166) => 'H', chr(196).chr(167) => 'h',
337 chr(196).chr(168) => 'I', chr(196).chr(169) => 'i',
338 chr(196).chr(170) => 'I', chr(196).chr(171) => 'i',
339 chr(196).chr(172) => 'I', chr(196).chr(173) => 'i',
340 chr(196).chr(174) => 'I', chr(196).chr(175) => 'i',
341 chr(196).chr(176) => 'I', chr(196).chr(177) => 'i',
342 chr(196).chr(178) => 'IJ',chr(196).chr(179) => 'ij',
343 chr(196).chr(180) => 'J', chr(196).chr(181) => 'j',
344 chr(196).chr(182) => 'K', chr(196).chr(183) => 'k',
345 chr(196).chr(184) => 'k', chr(196).chr(185) => 'L',
346 chr(196).chr(186) => 'l', chr(196).chr(187) => 'L',
347 chr(196).chr(188) => 'l', chr(196).chr(189) => 'L',
348 chr(196).chr(190) => 'l', chr(196).chr(191) => 'L',
349 chr(197).chr(128) => 'l', chr(197).chr(129) => 'L',
350 chr(197).chr(130) => 'l', chr(197).chr(131) => 'N',
351 chr(197).chr(132) => 'n', chr(197).chr(133) => 'N',
352 chr(197).chr(134) => 'n', chr(197).chr(135) => 'N',
353 chr(197).chr(136) => 'n', chr(197).chr(137) => 'N',
354 chr(197).chr(138) => 'n', chr(197).chr(139) => 'N',
355 chr(197).chr(140) => 'O', chr(197).chr(141) => 'o',
356 chr(197).chr(142) => 'O', chr(197).chr(143) => 'o',
357 chr(197).chr(144) => 'O', chr(197).chr(145) => 'o',
358 chr(197).chr(146) => 'OE',chr(197).chr(147) => 'oe',
359 chr(197).chr(148) => 'R',chr(197).chr(149) => 'r',
360 chr(197).chr(150) => 'R',chr(197).chr(151) => 'r',
361 chr(197).chr(152) => 'R',chr(197).chr(153) => 'r',
362 chr(197).chr(154) => 'S',chr(197).chr(155) => 's',
363 chr(197).chr(156) => 'S',chr(197).chr(157) => 's',
364 chr(197).chr(158) => 'S',chr(197).chr(159) => 's',
365 chr(197).chr(160) => 'S', chr(197).chr(161) => 's',
366 chr(197).chr(162) => 'T', chr(197).chr(163) => 't',
367 chr(197).chr(164) => 'T', chr(197).chr(165) => 't',
368 chr(197).chr(166) => 'T', chr(197).chr(167) => 't',
369 chr(197).chr(168) => 'U', chr(197).chr(169) => 'u',
370 chr(197).chr(170) => 'U', chr(197).chr(171) => 'u',
371 chr(197).chr(172) => 'U', chr(197).chr(173) => 'u',
372 chr(197).chr(174) => 'U', chr(197).chr(175) => 'u',
373 chr(197).chr(176) => 'U', chr(197).chr(177) => 'u',
374 chr(197).chr(178) => 'U', chr(197).chr(179) => 'u',
375 chr(197).chr(180) => 'W', chr(197).chr(181) => 'w',
376 chr(197).chr(182) => 'Y', chr(197).chr(183) => 'y',
377 chr(197).chr(184) => 'Y', chr(197).chr(185) => 'Z',
378 chr(197).chr(186) => 'z', chr(197).chr(187) => 'Z',
379 chr(197).chr(188) => 'z', chr(197).chr(189) => 'Z',
380 chr(197).chr(190) => 'z', chr(197).chr(191) => 's',
381 // Euro Sign
382 chr(226).chr(130).chr(172) => 'E',
383 // GBP (Pound) Sign
384 chr(194).chr(163) => '');
385
386 $string = strtr($string, $chars);
387 } else {
388 // Assume ISO-8859-1 if not UTF-8
389 $chars['in'] = chr(128).chr(131).chr(138).chr(142).chr(154).chr(158)
390 .chr(159).chr(162).chr(165).chr(181).chr(192).chr(193).chr(194)
391 .chr(195).chr(196).chr(197).chr(199).chr(200).chr(201).chr(202)
392 .chr(203).chr(204).chr(205).chr(206).chr(207).chr(209).chr(210)
393 .chr(211).chr(212).chr(213).chr(214).chr(216).chr(217).chr(218)
394 .chr(219).chr(220).chr(221).chr(224).chr(225).chr(226).chr(227)
395 .chr(228).chr(229).chr(231).chr(232).chr(233).chr(234).chr(235)
396 .chr(236).chr(237).chr(238).chr(239).chr(241).chr(242).chr(243)
397 .chr(244).chr(245).chr(246).chr(248).chr(249).chr(250).chr(251)
398 .chr(252).chr(253).chr(255);
399
400 $chars['out'] = "EfSZszYcYuAAAAAACEEEEIIIINOOOOOOUUUUYaaaaaaceeeeiiiinoooooouuuuyy";
401
402 $string = strtr($string, $chars['in'], $chars['out']);
403 $double_chars['in'] = array(chr(140), chr(156), chr(198), chr(208), chr(222), chr(223), chr(230), chr(240), chr(254));
404 $double_chars['out'] = array('OE', 'oe', 'AE', 'DH', 'TH', 'ss', 'ae', 'dh', 'th');
405 $string = str_replace($double_chars['in'], $double_chars['out'], $string);
406 }
407
408 return $string;
409}
410
411/**
412 * Filters certain characters from the file name.
413 *
414 * Turns all strings to lowercase removing most characters except alphanumeric
415 * with spaces, dashes and periods. All spaces and underscores are converted to
416 * dashes. Multiple dashes are converted to a single dash. Finally, if the file
417 * name ends with a dash, it is removed.
418 *
419 * @since 2.1.0
420 *
421 * @param string $name The file name
422 * @return string Sanitized file name
423 */
424function sanitize_file_name( $name ) { // Like sanitize_title, but with periods
425 $name = strtolower( $name );
426 $name = preg_replace('/&.+?;/', '', $name); // kill entities
427 $name = str_replace( '_', '-', $name );
428 $name = preg_replace('/[^a-z0-9\s-.]/', '', $name);
429 $name = preg_replace('/\s+/', '-', $name);
430 $name = preg_replace('|-+|', '-', $name);
431 $name = trim($name, '-');
432 return $name;
433}
434
435/**
436 * Sanitize username stripping out unsafe characters.
437 *
438 * If $strict is true, only alphanumeric characters (as well as _, space, ., -,
439 * @) are returned.
440 * Removes tags, octets, entities, and if strict is enabled, will remove all
441 * non-ASCII characters. After sanitizing, it passes the username, raw username
442 * (the username in the parameter), and the strict parameter as parameters for
443 * the filter.
444 *
445 * @since 2.0.0
446 * @uses apply_filters() Calls 'sanitize_user' hook on username, raw username,
447 * and $strict parameter.
448 *
449 * @param string $username The username to be sanitized.
450 * @param bool $strict If set limits $username to specific characters. Default false.
451 * @return string The sanitized username, after passing through filters.
452 */
453function sanitize_user( $username, $strict = false ) {
454 $raw_username = $username;
455 $username = strip_tags($username);
456 // Kill octets
457 $username = preg_replace('|%([a-fA-F0-9][a-fA-F0-9])|', '', $username);
458 $username = preg_replace('/&.+?;/', '', $username); // Kill entities
459
460 // If strict, reduce to ASCII for max portability.
461 if ( $strict )
462 $username = preg_replace('|[^a-z0-9 _.\-@]|i', '', $username);
463
464 // Consolidate contiguous whitespace
465 $username = preg_replace('|\s+|', ' ', $username);
466
467 return apply_filters('sanitize_user', $username, $raw_username, $strict);
468}
469
470/**
471 * Sanitizes title or use fallback title.
472 *
473 * Specifically, HTML and PHP tags are stripped. Further actions can be added
474 * via the plugin API. If $title is empty and $fallback_title is set, the latter
475 * will be used.
476 *
477 * @since 1.0.0
478 *
479 * @param string $title The string to be sanitized.
480 * @param string $fallback_title Optional. A title to use if $title is empty.
481 * @return string The sanitized string.
482 */
483function sanitize_title($title, $fallback_title = '') {
484 $title = strip_tags($title);
485 $title = apply_filters('sanitize_title', $title);
486
487 if ( '' === $title || false === $title )
488 $title = $fallback_title;
489
490 return $title;
491}
492
493/**
494 * Sanitizes title, replacing whitespace with dashes.
495 *
496 * Limits the output to alphanumeric characters, underscore (_) and dash (-).
497 * Whitespace becomes a dash.
498 *
499 * @since 1.2.0
500 *
501 * @param string $title The title to be sanitized.
502 * @return string The sanitized title.
503 */
504function sanitize_title_with_dashes($title) {
505 $title = strip_tags($title);
506 // Preserve escaped octets.
507 $title = preg_replace('|%([a-fA-F0-9][a-fA-F0-9])|', '---$1---', $title);
508 // Remove percent signs that are not part of an octet.
509 $title = str_replace('%', '', $title);
510 // Restore octets.
511 $title = preg_replace('|---([a-fA-F0-9][a-fA-F0-9])---|', '%$1', $title);
512
513 $title = remove_accents($title);
514 if (seems_utf8($title)) {
515 if (function_exists('mb_strtolower')) {
516 $title = mb_strtolower($title, 'UTF-8');
517 }
518 $title = utf8_uri_encode($title, 200);
519 }
520
521 $title = strtolower($title);
522 $title = preg_replace('/&.+?;/', '', $title); // kill entities
523 $title = preg_replace('/[^%a-z0-9 _-]/', '', $title);
524 $title = preg_replace('/\s+/', '-', $title);
525 $title = preg_replace('|-+|', '-', $title);
526 $title = trim($title, '-');
527
528 return $title;
529}
530
531/**
532 * Ensures a string is a valid SQL order by clause.
533 *
534 * Accepts one or more columns, with or without ASC/DESC, and also accepts
535 * RAND().
536 *
537 * @since 2.5.1
538 *
539 * @param string $orderby Order by string to be checked.
540 * @return string|false Returns the order by clause if it is a match, false otherwise.
541 */
542function sanitize_sql_orderby( $orderby ){
543 preg_match('/^\s*([a-z0-9_]+(\s+(ASC|DESC))?(\s*,\s*|\s*$))+|^\s*RAND\(\s*\)\s*$/i', $orderby, $obmatches);
544 if ( !$obmatches )
545 return false;
546 return $orderby;
547}
548
549/**
550 * Converts a number of characters from a string.
551 *
552 * Metadata tags <<title>> and <<category>> are removed, <<br>> and <<hr>> are
553 * converted into correct XHTML and Unicode characters are converted to the
554 * valid range.
555 *
556 * @since 0.71
557 *
558 * @param string $content String of characters to be converted.
559 * @param string $deprecated Not used.
560 * @return string Converted string.
561 */
562function convert_chars($content, $deprecated = '') {
563 // Translation of invalid Unicode references range to valid range
564 $wp_htmltranswinuni = array(
565 '&#128;' => '&#8364;', // the Euro sign
566 '&#129;' => '',
567 '&#130;' => '&#8218;', // these are Windows CP1252 specific characters
568 '&#131;' => '&#402;', // they would look weird on non-Windows browsers
569 '&#132;' => '&#8222;',
570 '&#133;' => '&#8230;',
571 '&#134;' => '&#8224;',
572 '&#135;' => '&#8225;',
573 '&#136;' => '&#710;',
574 '&#137;' => '&#8240;',
575 '&#138;' => '&#352;',
576 '&#139;' => '&#8249;',
577 '&#140;' => '&#338;',
578 '&#141;' => '',
579 '&#142;' => '&#382;',
580 '&#143;' => '',
581 '&#144;' => '',
582 '&#145;' => '&#8216;',
583 '&#146;' => '&#8217;',
584 '&#147;' => '&#8220;',
585 '&#148;' => '&#8221;',
586 '&#149;' => '&#8226;',
587 '&#150;' => '&#8211;',
588 '&#151;' => '&#8212;',
589 '&#152;' => '&#732;',
590 '&#153;' => '&#8482;',
591 '&#154;' => '&#353;',
592 '&#155;' => '&#8250;',
593 '&#156;' => '&#339;',
594 '&#157;' => '',
595 '&#158;' => '',
596 '&#159;' => '&#376;'
597 );
598
599 // Remove metadata tags
600 $content = preg_replace('/<title>(.+?)<\/title>/','',$content);
601 $content = preg_replace('/<category>(.+?)<\/category>/','',$content);
602
603 // Converts lone & characters into &#38; (a.k.a. &amp;)
604 $content = preg_replace('/&([^#])(?![a-z1-4]{1,8};)/i', '&#038;$1', $content);
605
606 // Fix Word pasting
607 $content = strtr($content, $wp_htmltranswinuni);
608
609 // Just a little XHTML help
610 $content = str_replace('<br>', '<br />', $content);
611 $content = str_replace('<hr>', '<hr />', $content);
612
613 return $content;
614}
615
616/**
617 * Fixes javascript bugs in browsers.
618 *
619 * Converts unicode characters to HTML numbered entities.
620 *
621 * @since 1.5.0
622 * @uses $is_macIE
623 * @uses $is_winIE
624 *
625 * @param string $text Text to be made safe.
626 * @return string Fixed text.
627 */
628function funky_javascript_fix($text) {
629 // Fixes for browsers' javascript bugs
630 global $is_macIE, $is_winIE;
631
632 /** @todo use preg_replace_callback() instead */
633 if ( $is_winIE || $is_macIE )
634 $text = preg_replace("/\%u([0-9A-F]{4,4})/e", "'&#'.base_convert('\\1',16,10).';'", $text);
635
636 return $text;
637}
638
639/**
640 * Will only balance the tags if forced to and the option is set to balance tags.
641 *
642 * The option 'use_balanceTags' is used for whether the tags will be balanced.
643 * Both the $force parameter and 'use_balanceTags' option will have to be true
644 * before the tags will be balanced.
645 *
646 * @since 0.71
647 *
648 * @param string $text Text to be balanced
649 * @param bool $force Forces balancing, ignoring the value of the option. Default false.
650 * @return string Balanced text
651 */
652function balanceTags( $text, $force = false ) {
653 if ( !$force && get_option('use_balanceTags') == 0 )
654 return $text;
655 return force_balance_tags( $text );
656}
657
658/**
659 * Balances tags of string using a modified stack.
660 *
661 * @since 2.0.4
662 *
663 * @author Leonard Lin <leonard@acm.org>
664 * @license GPL v2.0
665 * @copyright November 4, 2001
666 * @version 1.1
667 * @todo Make better - change loop condition to $text in 1.2
668 * @internal Modified by Scott Reilly (coffee2code) 02 Aug 2004
669 * 1.1 Fixed handling of append/stack pop order of end text
670 * Added Cleaning Hooks
671 * 1.0 First Version
672 *
673 * @param string $text Text to be balanced.
674 * @return string Balanced text.
675 */
676function force_balance_tags( $text ) {
677 $tagstack = array(); $stacksize = 0; $tagqueue = ''; $newtext = '';
678 $single_tags = array('br', 'hr', 'img', 'input'); //Known single-entity/self-closing tags
679 $nestable_tags = array('blockquote', 'div', 'span'); //Tags that can be immediately nested within themselves
680
681 # WP bug fix for comments - in case you REALLY meant to type '< !--'
682 $text = str_replace('< !--', '< !--', $text);
683 # WP bug fix for LOVE <3 (and other situations with '<' before a number)
684 $text = preg_replace('#<([0-9]{1})#', '&lt;$1', $text);
685
686 while (preg_match("/<(\/?\w*)\s*([^>]*)>/",$text,$regex)) {
687 $newtext .= $tagqueue;
688
689 $i = strpos($text,$regex[0]);
690 $l = strlen($regex[0]);
691
692 // clear the shifter
693 $tagqueue = '';
694 // Pop or Push
695 if ($regex[1][0] == "/") { // End Tag
696 $tag = strtolower(substr($regex[1],1));
697 // if too many closing tags
698 if($stacksize <= 0) {
699 $tag = '';
700 //or close to be safe $tag = '/' . $tag;
701 }
702 // if stacktop value = tag close value then pop
703 else if ($tagstack[$stacksize - 1] == $tag) { // found closing tag
704 $tag = '</' . $tag . '>'; // Close Tag
705 // Pop
706 array_pop ($tagstack);
707 $stacksize--;
708 } else { // closing tag not at top, search for it
709 for ($j=$stacksize-1;$j>=0;$j--) {
710 if ($tagstack[$j] == $tag) {
711 // add tag to tagqueue
712 for ($k=$stacksize-1;$k>=$j;$k--){
713 $tagqueue .= '</' . array_pop ($tagstack) . '>';
714 $stacksize--;
715 }
716 break;
717 }
718 }
719 $tag = '';
720 }
721 } else { // Begin Tag
722 $tag = strtolower($regex[1]);
723
724 // Tag Cleaning
725
726 // If self-closing or '', don't do anything.
727 if((substr($regex[2],-1) == '/') || ($tag == '')) {
728 }
729 // ElseIf it's a known single-entity tag but it doesn't close itself, do so
730 elseif ( in_array($tag, $single_tags) ) {
731 $regex[2] .= '/';
732 } else { // Push the tag onto the stack
733 // If the top of the stack is the same as the tag we want to push, close previous tag
734 if (($stacksize > 0) && !in_array($tag, $nestable_tags) && ($tagstack[$stacksize - 1] == $tag)) {
735 $tagqueue = '</' . array_pop ($tagstack) . '>';
736 $stacksize--;
737 }
738 $stacksize = array_push ($tagstack, $tag);
739 }
740
741 // Attributes
742 $attributes = $regex[2];
743 if($attributes) {
744 $attributes = ' '.$attributes;
745 }
746 $tag = '<'.$tag.$attributes.'>';
747 //If already queuing a close tag, then put this tag on, too
748 if ($tagqueue) {
749 $tagqueue .= $tag;
750 $tag = '';
751 }
752 }
753 $newtext .= substr($text,0,$i) . $tag;
754 $text = substr($text,$i+$l);
755 }
756
757 // Clear Tag Queue
758 $newtext .= $tagqueue;
759
760 // Add Remaining text
761 $newtext .= $text;
762
763 // Empty Stack
764 while($x = array_pop($tagstack)) {
765 $newtext .= '</' . $x . '>'; // Add remaining tags to close
766 }
767
768 // WP fix for the bug with HTML comments
769 $newtext = str_replace("< !--","<!--",$newtext);
770 $newtext = str_replace("< !--","< !--",$newtext);
771
772 return $newtext;
773}
774
775/**
776 * Acts on text which is about to be edited.
777 *
778 * Holder for the 'format_to_edit' filter.
779 *
780 * @since 0.71
781 *
782 * @param string $content The text about to be edited.
783 * @return string The text after the filter and htmlspecialchars() has been run.
784 */
785function format_to_edit($content) {
786 $content = apply_filters('format_to_edit', $content);
787 return htmlspecialchars($content);
788}
789
790/**
791 * Holder for the 'format_to_post' filter.
792 *
793 * @since 0.71
794 *
795 * @param string $content The text to pass through the filter.
796 * @return string Text returned from the 'format_to_post' filter.
797 */
798function format_to_post($content) {
799 $content = apply_filters('format_to_post', $content);
800 return $content;
801}
802
803/**
804 * Add leading zeros when necessary.
805 *
806 * If you set the threshold to '4' and the number is '10', then you will get
807 * back '0010'. If you set the number to '4' and the number is '5000', then you
808 * will get back '5000'.
809 *
810 * Uses sprintf to append the amount of zeros based on the $threshold parameter
811 * and the size of the number. If the number is large enough, then no zeros will
812 * be appended.
813 *
814 * @since 0.71
815 *
816 * @param mixed $number Number to append zeros to if not greater than threshold.
817 * @param int $threshold Digit places number needs to be to not have zeros added.
818 * @return string Adds leading zeros to number if needed.
819 */
820function zeroise($number, $threshold) {
821 return sprintf('%0'.$threshold.'s', $number);
822}
823
824/**
825 * Adds backslashes before letters and before a number at the start of a string.
826 *
827 * @since 0.71
828 *
829 * @param string $string Value to which backslashes will be added.
830 * @return string String with backslashes inserted.
831 */
832function backslashit($string) {
833 $string = preg_replace('/^([0-9])/', '\\\\\\\\\1', $string);
834 $string = preg_replace('/([a-z])/i', '\\\\\1', $string);
835 return $string;
836}
837
838/**
839 * Appends a trailing slash.
840 *
841 * Will remove trailing slash if it exists already before adding a trailing
842 * slash. This prevents double slashing a string or path.
843 *
844 * The primary use of this is for paths and thus should be used for paths. It is
845 * not restricted to paths and offers no specific path support.
846 *
847 * @since 1.2.0
848 * @uses untrailingslashit() Unslashes string if it was slashed already.
849 *
850 * @param string $string What to add the trailing slash to.
851 * @return string String with trailing slash added.
852 */
853function trailingslashit($string) {
854 return untrailingslashit($string) . '/';
855}
856
857/**
858 * Removes trailing slash if it exists.
859 *
860 * The primary use of this is for paths and thus should be used for paths. It is
861 * not restricted to paths and offers no specific path support.
862 *
863 * @since 2.2.0
864 *
865 * @param string $string What to remove the trailing slash from.
866 * @return string String without the trailing slash.
867 */
868function untrailingslashit($string) {
869 return rtrim($string, '/');
870}
871
872/**
873 * Adds slashes to escape strings.
874 *
875 * Slashes will first be removed if magic_quotes_gpc is set, see {@link
876 * http://www.php.net/magic_quotes} for more details.
877 *
878 * @since 0.71
879 *
880 * @param string $gpc The string returned from HTTP request data.
881 * @return string Returns a string escaped with slashes.
882 */
883function addslashes_gpc($gpc) {
884 global $wpdb;
885
886 if (get_magic_quotes_gpc()) {
887 $gpc = stripslashes($gpc);
888 }
889
890 return $wpdb->escape($gpc);
891}
892
893/**
894 * Navigates through an array and removes slashes from the values.
895 *
896 * If an array is passed, the array_map() function causes a callback to pass the
897 * value back to the function. The slashes from this value will removed.
898 *
899 * @since 2.0.0
900 *
901 * @param array|string $value The array or string to be striped.
902 * @return array|string Stripped array (or string in the callback).
903 */
904function stripslashes_deep($value) {
905 $value = is_array($value) ? array_map('stripslashes_deep', $value) : stripslashes($value);
906 return $value;
907}
908
909/**
910 * Navigates through an array and encodes the values to be used in a URL.
911 *
912 * Uses a callback to pass the value of the array back to the function as a
913 * string.
914 *
915 * @since 2.2.0
916 *
917 * @param array|string $value The array or string to be encoded.
918 * @return array|string $value The encoded array (or string from the callback).
919 */
920function urlencode_deep($value) {
921 $value = is_array($value) ? array_map('urlencode_deep', $value) : urlencode($value);
922 return $value;
923}
924
925/**
926 * Converts email addresses characters to HTML entities to block spam bots.
927 *
928 * @since 0.71
929 *
930 * @param string $emailaddy Email address.
931 * @param int $mailto Optional. Range from 0 to 1. Used for encoding.
932 * @return string Converted email address.
933 */
934function antispambot($emailaddy, $mailto=0) {
935 $emailNOSPAMaddy = '';
936 srand ((float) microtime() * 1000000);
937 for ($i = 0; $i < strlen($emailaddy); $i = $i + 1) {
938 $j = floor(rand(0, 1+$mailto));
939 if ($j==0) {
940 $emailNOSPAMaddy .= '&#'.ord(substr($emailaddy,$i,1)).';';
941 } elseif ($j==1) {
942 $emailNOSPAMaddy .= substr($emailaddy,$i,1);
943 } elseif ($j==2) {
944 $emailNOSPAMaddy .= '%'.zeroise(dechex(ord(substr($emailaddy, $i, 1))), 2);
945 }
946 }
947 $emailNOSPAMaddy = str_replace('@','&#64;',$emailNOSPAMaddy);
948 return $emailNOSPAMaddy;
949}
950
951/**
952 * Callback to convert URI match to HTML A element.
953 *
954 * This function was backported from 2.5.0 to 2.3.2. Regex callback for {@link
955 * make_clickable()}.
956 *
957 * @since 2.3.2
958 * @access private
959 *
960 * @param array $matches Single Regex Match.
961 * @return string HTML A element with URI address.
962 */
963function _make_url_clickable_cb($matches) {
964 $ret = '';
965 $url = $matches[2];
966 $url = clean_url($url);
967 if ( empty($url) )
968 return $matches[0];
969 // removed trailing [.,;:] from URL
970 if ( in_array(substr($url, -1), array('.', ',', ';', ':')) === true ) {
971 $ret = substr($url, -1);
972 $url = substr($url, 0, strlen($url)-1);
973 }
974 return $matches[1] . "<a href=\"$url\" rel=\"nofollow\">$url</a>" . $ret;
975}
976
977/**
978 * Callback to convert URL match to HTML A element.
979 *
980 * This function was backported from 2.5.0 to 2.3.2. Regex callback for {@link
981 * make_clickable()}.
982 *
983 * @since 2.3.2
984 * @access private
985 *
986 * @param array $matches Single Regex Match.
987 * @return string HTML A element with URL address.
988 */
989function _make_web_ftp_clickable_cb($matches) {
990 $ret = '';
991 $dest = $matches[2];
992 $dest = 'http://' . $dest;
993 $dest = clean_url($dest);
994 if ( empty($dest) )
995 return $matches[0];
996 // removed trailing [,;:] from URL
997 if ( in_array(substr($dest, -1), array('.', ',', ';', ':')) === true ) {
998 $ret = substr($dest, -1);
999 $dest = substr($dest, 0, strlen($dest)-1);
1000 }
1001 return $matches[1] . "<a href=\"$dest\" rel=\"nofollow\">$dest</a>" . $ret;
1002}
1003
1004/**
1005 * Callback to convert email address match to HTML A element.
1006 *
1007 * This function was backported from 2.5.0 to 2.3.2. Regex callback for {@link
1008 * make_clickable()}.
1009 *
1010 * @since 2.3.2
1011 * @access private
1012 *
1013 * @param array $matches Single Regex Match.
1014 * @return string HTML A element with email address.
1015 */
1016function _make_email_clickable_cb($matches) {
1017 $email = $matches[2] . '@' . $matches[3];
1018 return $matches[1] . "<a href=\"mailto:$email\">$email</a>";
1019}
1020
1021/**
1022 * Convert plaintext URI to HTML links.
1023 *
1024 * Converts URI, www and ftp, and email addresses. Finishes by fixing links
1025 * within links.
1026 *
1027 * @since 0.71
1028 *
1029 * @param string $ret Content to convert URIs.
1030 * @return string Content with converted URIs.
1031 */
1032function make_clickable($ret) {
1033 $ret = ' ' . $ret;
1034 // in testing, using arrays here was found to be faster
1035 $ret = preg_replace_callback('#([\s>])([\w]+?://[\w\\x80-\\xff\#$%&~/.\-;:=,?@\[\]+]*)#is', '_make_url_clickable_cb', $ret);
1036 $ret = preg_replace_callback('#([\s>])((www|ftp)\.[\w\\x80-\\xff\#$%&~/.\-;:=,?@\[\]+]*)#is', '_make_web_ftp_clickable_cb', $ret);
1037 $ret = preg_replace_callback('#([\s>])([.0-9a-z_+-]+)@(([0-9a-z-]+\.)+[0-9a-z]{2,})#i', '_make_email_clickable_cb', $ret);
1038 // this one is not in an array because we need it to run last, for cleanup of accidental links within links
1039 $ret = preg_replace("#(<a( [^>]+?>|>))<a [^>]+?>([^>]+?)</a></a>#i", "$1$3</a>", $ret);
1040 $ret = trim($ret);
1041 return $ret;
1042}
1043
1044/**
1045 * Adds rel nofollow string to all HTML A elements in content.
1046 *
1047 * @since 1.5.0
1048 *
1049 * @param string $text Content that may contain HTML A elements.
1050 * @return string Converted content.
1051 */
1052function wp_rel_nofollow( $text ) {
1053 global $wpdb;
1054 // This is a pre save filter, so text is already escaped.
1055 $text = stripslashes($text);
1056 $text = preg_replace_callback('|<a (.+?)>|i', 'wp_rel_nofollow_callback', $text);
1057 $text = $wpdb->escape($text);
1058 return $text;
1059}
1060
1061/**
1062 * Callback to used to add rel=nofollow string to HTML A element.
1063 *
1064 * Will remove already existing rel="nofollow" and rel='nofollow' from the
1065 * string to prevent from invalidating (X)HTML.
1066 *
1067 * @since 2.3.0
1068 *
1069 * @param array $matches Single Match
1070 * @return string HTML A Element with rel nofollow.
1071 */
1072function wp_rel_nofollow_callback( $matches ) {
1073 $text = $matches[1];
1074 $text = str_replace(array(' rel="nofollow"', " rel='nofollow'"), '', $text);
1075 return "<a $text rel=\"nofollow\">";
1076}
1077
1078/**
1079 * Convert text equivalent of smilies to images.
1080 *
1081 * Will only convert smilies if the option 'use_smilies' is true and the globals
1082 * used in the function aren't empty.
1083 *
1084 * @since 0.71
1085 * @uses $wp_smiliessearch, $wp_smiliesreplace Smiley replacement arrays.
1086 *
1087 * @param string $text Content to convert smilies from text.
1088 * @return string Converted content with text smilies replaced with images.
1089 */
1090function convert_smilies($text) {
1091 global $wp_smiliessearch, $wp_smiliesreplace;
1092 $output = '';
1093 if ( get_option('use_smilies') && !empty($wp_smiliessearch) && !empty($wp_smiliesreplace) ) {
1094 // HTML loop taken from texturize function, could possible be consolidated
1095 $textarr = preg_split("/(<.*>)/U", $text, -1, PREG_SPLIT_DELIM_CAPTURE); // capture the tags as well as in between
1096 $stop = count($textarr);// loop stuff
1097 for ($i = 0; $i < $stop; $i++) {
1098 $content = $textarr[$i];
1099 if ((strlen($content) > 0) && ('<' != $content{0})) { // If it's not a tag
1100 $content = preg_replace($wp_smiliessearch, $wp_smiliesreplace, $content);
1101 }
1102 $output .= $content;
1103 }
1104 } else {
1105 // return default text.
1106 $output = $text;
1107 }
1108 return $output;
1109}
1110
1111/**
1112 * Checks to see if the text is a valid email address.
1113 *
1114 * @since 0.71
1115 *
1116 * @param string $user_email The email address to be checked.
1117 * @return bool Returns true if valid, otherwise false.
1118 */
1119function is_email($user_email) {
1120 $chars = "/^([a-z0-9+_]|\\-|\\.)+@(([a-z0-9_]|\\-)+\\.)+[a-z]{2,6}\$/i";
1121 if (strpos($user_email, '@') !== false && strpos($user_email, '.') !== false) {
1122 if (preg_match($chars, $user_email)) {
1123 return true;
1124 } else {
1125 return false;
1126 }
1127 } else {
1128 return false;
1129 }
1130}
1131
1132/**
1133 * Convert to ASCII from email subjects.
1134 *
1135 * @since 1.2.0
1136 * @usedby wp_mail() handles charsets in email subjects
1137 *
1138 * @param string $string Subject line
1139 * @return string Converted string to ASCII
1140 */
1141function wp_iso_descrambler($string) {
1142 /* this may only work with iso-8859-1, I'm afraid */
1143 if (!preg_match('#\=\?(.+)\?Q\?(.+)\?\=#i', $string, $matches)) {
1144 return $string;
1145 } else {
1146 $subject = str_replace('_', ' ', $matches[2]);
1147 /** @todo use preg_replace_callback() */
1148 $subject = preg_replace('#\=([0-9a-f]{2})#ei', "chr(hexdec(strtolower('$1')))", $subject);
1149 return $subject;
1150 }
1151}
1152
1153/**
1154 * Returns a date in the GMT equivalent.
1155 *
1156 * Requires and returns a date in the Y-m-d H:i:s format. Simply subtracts the
1157 * value of gmt_offset.
1158 *
1159 * @since 1.2.0
1160 *
1161 * @param string $string The date to be converted.
1162 * @return string GMT version of the date provided.
1163 */
1164function get_gmt_from_date($string) {
1165 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);
1166 $string_time = gmmktime($matches[4], $matches[5], $matches[6], $matches[2], $matches[3], $matches[1]);
1167 $string_gmt = gmdate('Y-m-d H:i:s', $string_time - get_option('gmt_offset') * 3600);
1168 return $string_gmt;
1169}
1170
1171/**
1172 * Converts a GMT date into the correct format for the blog.
1173 *
1174 * Requires and returns in the Y-m-d H:i:s format. Simply adds the value of
1175 * gmt_offset.
1176 *
1177 * @since 1.2.0
1178 *
1179 * @param string $string The date to be converted.
1180 * @return string Formatted date relative to the GMT offset.
1181 */
1182function get_date_from_gmt($string) {
1183 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);
1184 $string_time = gmmktime($matches[4], $matches[5], $matches[6], $matches[2], $matches[3], $matches[1]);
1185 $string_localtime = gmdate('Y-m-d H:i:s', $string_time + get_option('gmt_offset')*3600);
1186 return $string_localtime;
1187}
1188
1189/**
1190 * Computes an offset in seconds from an iso8601 timezone.
1191 *
1192 * @since 1.5.0
1193 *
1194 * @param string $timezone Either 'Z' for 0 offset or 'hhmm'.
1195 * @return int|float The offset in seconds.
1196 */
1197function iso8601_timezone_to_offset($timezone) {
1198 // $timezone is either 'Z' or '[+|-]hhmm'
1199 if ($timezone == 'Z') {
1200 $offset = 0;
1201 } else {
1202 $sign = (substr($timezone, 0, 1) == '+') ? 1 : -1;
1203 $hours = intval(substr($timezone, 1, 2));
1204 $minutes = intval(substr($timezone, 3, 4)) / 60;
1205 $offset = $sign * 3600 * ($hours + $minutes);
1206 }
1207 return $offset;
1208}
1209
1210/**
1211 * Converts an iso8601 date to MySQL DateTime format used by post_date[_gmt].
1212 *
1213 * @since 1.5.0
1214 *
1215 * @param string $date_string Date and time in ISO 8601 format {@link http://en.wikipedia.org/wiki/ISO_8601}.
1216 * @param string $timezone Optional. If set to GMT returns the time minus gmt_offset. Default is 'user'.
1217 * @return string The date and time in MySQL DateTime format - Y-m-d H:i:s.
1218 */
1219function iso8601_to_datetime($date_string, $timezone = 'user') {
1220 $timezone = strtolower($timezone);
1221
1222 if ($timezone == 'gmt') {
1223
1224 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, $date_bits);
1225
1226 if (!empty($date_bits[7])) { // we have a timezone, so let's compute an offset
1227 $offset = iso8601_timezone_to_offset($date_bits[7]);
1228 } else { // we don't have a timezone, so we assume user local timezone (not server's!)
1229 $offset = 3600 * get_option('gmt_offset');
1230 }
1231
1232 $timestamp = gmmktime($date_bits[4], $date_bits[5], $date_bits[6], $date_bits[2], $date_bits[3], $date_bits[1]);
1233 $timestamp -= $offset;
1234
1235 return gmdate('Y-m-d H:i:s', $timestamp);
1236
1237 } else if ($timezone == 'user') {
1238 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);
1239 }
1240}
1241
1242/**
1243 * Adds a element attributes to open links in new windows.
1244 *
1245 * Comment text in popup windows should be filtered through this. Right now it's
1246 * a moderately dumb function, ideally it would detect whether a target or rel
1247 * attribute was already there and adjust its actions accordingly.
1248 *
1249 * @since 0.71
1250 *
1251 * @param string $text Content to replace links to open in a new window.
1252 * @return string Content that has filtered links.
1253 */
1254function popuplinks($text) {
1255 $text = preg_replace('/<a (.+?)>/i', "<a $1 target='_blank' rel='external'>", $text);
1256 return $text;
1257}
1258
1259/**
1260 * Strips out all characters that are not allowable in an email.
1261 *
1262 * @since 1.5.0
1263 *
1264 * @param string $email Email address to filter.
1265 * @return string Filtered email address.
1266 */
1267function sanitize_email($email) {
1268 return preg_replace('/[^a-z0-9+_.@-]/i', '', $email);
1269}
1270
1271/**
1272 * Determines the difference between two timestamps.
1273 *
1274 * The difference is returned in a human readable format such as "1 hour",
1275 * "5 mins", "2 days".
1276 *
1277 * @since 1.5.0
1278 *
1279 * @param int $from Unix timestamp from which the difference begins.
1280 * @param int $to Optional. Unix timestamp to end the time difference. Default becomes time() if not set.
1281 * @return string Human readable time difference.
1282 */
1283function human_time_diff( $from, $to = '' ) {
1284 if ( empty($to) )
1285 $to = time();
1286 $diff = (int) abs($to - $from);
1287 if ($diff <= 3600) {
1288 $mins = round($diff / 60);
1289 if ($mins <= 1) {
1290 $mins = 1;
1291 }
1292 $since = sprintf(__ngettext('%s min', '%s mins', $mins), $mins);
1293 } else if (($diff <= 86400) && ($diff > 3600)) {
1294 $hours = round($diff / 3600);
1295 if ($hours <= 1) {
1296 $hours = 1;
1297 }
1298 $since = sprintf(__ngettext('%s hour', '%s hours', $hours), $hours);
1299 } elseif ($diff >= 86400) {
1300 $days = round($diff / 86400);
1301 if ($days <= 1) {
1302 $days = 1;
1303 }
1304 $since = sprintf(__ngettext('%s day', '%s days', $days), $days);
1305 }
1306 return $since;
1307}
1308
1309/**
1310 * Generates an excerpt from the content, if needed.
1311 *
1312 * The excerpt word amount will be 55 words and if the amount is greater than
1313 * that, then the string '[...]' will be appended to the excerpt. If the string
1314 * is less than 55 words, then the content will be returned as is.
1315 *
1316 * @since 1.5.0
1317 *
1318 * @param string $text The exerpt. If set to empty an excerpt is generated.
1319 * @return string The excerpt.
1320 */
1321function wp_trim_excerpt($text) {
1322 if ( '' == $text ) {
1323 $text = get_the_content('');
1324
1325 $text = strip_shortcodes( $text );
1326
1327 $text = apply_filters('the_content', $text);
1328 $text = str_replace(']]>', ']]&gt;', $text);
1329 $text = strip_tags($text);
1330 $excerpt_length = apply_filters('excerpt_length', 55);
1331 $words = explode(' ', $text, $excerpt_length + 1);
1332 if (count($words) > $excerpt_length) {
1333 array_pop($words);
1334 array_push($words, '[...]');
1335 $text = implode(' ', $words);
1336 }
1337 }
1338 return $text;
1339}
1340
1341/**
1342 * Converts named entities into numbered entities.
1343 *
1344 * @since 1.5.1
1345 *
1346 * @param string $text The text within which entities will be converted.
1347 * @return string Text with converted entities.
1348 */
1349function ent2ncr($text) {
1350 $to_ncr = array(
1351 '&quot;' => '&#34;',
1352 '&amp;' => '&#38;',
1353 '&frasl;' => '&#47;',
1354 '&lt;' => '&#60;',
1355 '&gt;' => '&#62;',
1356 '|' => '&#124;',
1357 '&nbsp;' => '&#160;',
1358 '&iexcl;' => '&#161;',
1359 '&cent;' => '&#162;',
1360 '&pound;' => '&#163;',
1361 '&curren;' => '&#164;',
1362 '&yen;' => '&#165;',
1363 '&brvbar;' => '&#166;',
1364 '&brkbar;' => '&#166;',
1365 '&sect;' => '&#167;',
1366 '&uml;' => '&#168;',
1367 '&die;' => '&#168;',
1368 '&copy;' => '&#169;',
1369 '&ordf;' => '&#170;',
1370 '&laquo;' => '&#171;',
1371 '&not;' => '&#172;',
1372 '&shy;' => '&#173;',
1373 '&reg;' => '&#174;',
1374 '&macr;' => '&#175;',
1375 '&hibar;' => '&#175;',
1376 '&deg;' => '&#176;',
1377 '&plusmn;' => '&#177;',
1378 '&sup2;' => '&#178;',
1379 '&sup3;' => '&#179;',
1380 '&acute;' => '&#180;',
1381 '&micro;' => '&#181;',
1382 '&para;' => '&#182;',
1383 '&middot;' => '&#183;',
1384 '&cedil;' => '&#184;',
1385 '&sup1;' => '&#185;',
1386 '&ordm;' => '&#186;',
1387 '&raquo;' => '&#187;',
1388 '&frac14;' => '&#188;',
1389 '&frac12;' => '&#189;',
1390 '&frac34;' => '&#190;',
1391 '&iquest;' => '&#191;',
1392 '&Agrave;' => '&#192;',
1393 '&Aacute;' => '&#193;',
1394 '&Acirc;' => '&#194;',
1395 '&Atilde;' => '&#195;',
1396 '&Auml;' => '&#196;',
1397 '&Aring;' => '&#197;',
1398 '&AElig;' => '&#198;',
1399 '&Ccedil;' => '&#199;',
1400 '&Egrave;' => '&#200;',
1401 '&Eacute;' => '&#201;',
1402 '&Ecirc;' => '&#202;',
1403 '&Euml;' => '&#203;',
1404 '&Igrave;' => '&#204;',
1405 '&Iacute;' => '&#205;',
1406 '&Icirc;' => '&#206;',
1407 '&Iuml;' => '&#207;',
1408 '&ETH;' => '&#208;',
1409 '&Ntilde;' => '&#209;',
1410 '&Ograve;' => '&#210;',
1411 '&Oacute;' => '&#211;',
1412 '&Ocirc;' => '&#212;',
1413 '&Otilde;' => '&#213;',
1414 '&Ouml;' => '&#214;',
1415 '&times;' => '&#215;',
1416 '&Oslash;' => '&#216;',
1417 '&Ugrave;' => '&#217;',
1418 '&Uacute;' => '&#218;',
1419 '&Ucirc;' => '&#219;',
1420 '&Uuml;' => '&#220;',
1421 '&Yacute;' => '&#221;',
1422 '&THORN;' => '&#222;',
1423 '&szlig;' => '&#223;',
1424 '&agrave;' => '&#224;',
1425 '&aacute;' => '&#225;',
1426 '&acirc;' => '&#226;',
1427 '&atilde;' => '&#227;',
1428 '&auml;' => '&#228;',
1429 '&aring;' => '&#229;',
1430 '&aelig;' => '&#230;',
1431 '&ccedil;' => '&#231;',
1432 '&egrave;' => '&#232;',
1433 '&eacute;' => '&#233;',
1434 '&ecirc;' => '&#234;',
1435 '&euml;' => '&#235;',
1436 '&igrave;' => '&#236;',
1437 '&iacute;' => '&#237;',
1438 '&icirc;' => '&#238;',
1439 '&iuml;' => '&#239;',
1440 '&eth;' => '&#240;',
1441 '&ntilde;' => '&#241;',
1442 '&ograve;' => '&#242;',
1443 '&oacute;' => '&#243;',
1444 '&ocirc;' => '&#244;',
1445 '&otilde;' => '&#245;',
1446 '&ouml;' => '&#246;',
1447 '&divide;' => '&#247;',
1448 '&oslash;' => '&#248;',
1449 '&ugrave;' => '&#249;',
1450 '&uacute;' => '&#250;',
1451 '&ucirc;' => '&#251;',
1452 '&uuml;' => '&#252;',
1453 '&yacute;' => '&#253;',
1454 '&thorn;' => '&#254;',
1455 '&yuml;' => '&#255;',
1456 '&OElig;' => '&#338;',
1457 '&oelig;' => '&#339;',
1458 '&Scaron;' => '&#352;',
1459 '&scaron;' => '&#353;',
1460 '&Yuml;' => '&#376;',
1461 '&fnof;' => '&#402;',
1462 '&circ;' => '&#710;',
1463 '&tilde;' => '&#732;',
1464 '&Alpha;' => '&#913;',
1465 '&Beta;' => '&#914;',
1466 '&Gamma;' => '&#915;',
1467 '&Delta;' => '&#916;',
1468 '&Epsilon;' => '&#917;',
1469 '&Zeta;' => '&#918;',
1470 '&Eta;' => '&#919;',
1471 '&Theta;' => '&#920;',
1472 '&Iota;' => '&#921;',
1473 '&Kappa;' => '&#922;',
1474 '&Lambda;' => '&#923;',
1475 '&Mu;' => '&#924;',
1476 '&Nu;' => '&#925;',
1477 '&Xi;' => '&#926;',
1478 '&Omicron;' => '&#927;',
1479 '&Pi;' => '&#928;',
1480 '&Rho;' => '&#929;',
1481 '&Sigma;' => '&#931;',
1482 '&Tau;' => '&#932;',
1483 '&Upsilon;' => '&#933;',
1484 '&Phi;' => '&#934;',
1485 '&Chi;' => '&#935;',
1486 '&Psi;' => '&#936;',
1487 '&Omega;' => '&#937;',
1488 '&alpha;' => '&#945;',
1489 '&beta;' => '&#946;',
1490 '&gamma;' => '&#947;',
1491 '&delta;' => '&#948;',
1492 '&epsilon;' => '&#949;',
1493 '&zeta;' => '&#950;',
1494 '&eta;' => '&#951;',
1495 '&theta;' => '&#952;',
1496 '&iota;' => '&#953;',
1497 '&kappa;' => '&#954;',
1498 '&lambda;' => '&#955;',
1499 '&mu;' => '&#956;',
1500 '&nu;' => '&#957;',
1501 '&xi;' => '&#958;',
1502 '&omicron;' => '&#959;',
1503 '&pi;' => '&#960;',
1504 '&rho;' => '&#961;',
1505 '&sigmaf;' => '&#962;',
1506 '&sigma;' => '&#963;',
1507 '&tau;' => '&#964;',
1508 '&upsilon;' => '&#965;',
1509 '&phi;' => '&#966;',
1510 '&chi;' => '&#967;',
1511 '&psi;' => '&#968;',
1512 '&omega;' => '&#969;',
1513 '&thetasym;' => '&#977;',
1514 '&upsih;' => '&#978;',
1515 '&piv;' => '&#982;',
1516 '&ensp;' => '&#8194;',
1517 '&emsp;' => '&#8195;',
1518 '&thinsp;' => '&#8201;',
1519 '&zwnj;' => '&#8204;',
1520 '&zwj;' => '&#8205;',
1521 '&lrm;' => '&#8206;',
1522 '&rlm;' => '&#8207;',
1523 '&ndash;' => '&#8211;',
1524 '&mdash;' => '&#8212;',
1525 '&lsquo;' => '&#8216;',
1526 '&rsquo;' => '&#8217;',
1527 '&sbquo;' => '&#8218;',
1528 '&ldquo;' => '&#8220;',
1529 '&rdquo;' => '&#8221;',
1530 '&bdquo;' => '&#8222;',
1531 '&dagger;' => '&#8224;',
1532 '&Dagger;' => '&#8225;',
1533 '&bull;' => '&#8226;',
1534 '&hellip;' => '&#8230;',
1535 '&permil;' => '&#8240;',
1536 '&prime;' => '&#8242;',
1537 '&Prime;' => '&#8243;',
1538 '&lsaquo;' => '&#8249;',
1539 '&rsaquo;' => '&#8250;',
1540 '&oline;' => '&#8254;',
1541 '&frasl;' => '&#8260;',
1542 '&euro;' => '&#8364;',
1543 '&image;' => '&#8465;',
1544 '&weierp;' => '&#8472;',
1545 '&real;' => '&#8476;',
1546 '&trade;' => '&#8482;',
1547 '&alefsym;' => '&#8501;',
1548 '&crarr;' => '&#8629;',
1549 '&lArr;' => '&#8656;',
1550 '&uArr;' => '&#8657;',
1551 '&rArr;' => '&#8658;',
1552 '&dArr;' => '&#8659;',
1553 '&hArr;' => '&#8660;',
1554 '&forall;' => '&#8704;',
1555 '&part;' => '&#8706;',
1556 '&exist;' => '&#8707;',
1557 '&empty;' => '&#8709;',
1558 '&nabla;' => '&#8711;',
1559 '&isin;' => '&#8712;',
1560 '&notin;' => '&#8713;',
1561 '&ni;' => '&#8715;',
1562 '&prod;' => '&#8719;',
1563 '&sum;' => '&#8721;',
1564 '&minus;' => '&#8722;',
1565 '&lowast;' => '&#8727;',
1566 '&radic;' => '&#8730;',
1567 '&prop;' => '&#8733;',
1568 '&infin;' => '&#8734;',
1569 '&ang;' => '&#8736;',
1570 '&and;' => '&#8743;',
1571 '&or;' => '&#8744;',
1572 '&cap;' => '&#8745;',
1573 '&cup;' => '&#8746;',
1574 '&int;' => '&#8747;',
1575 '&there4;' => '&#8756;',
1576 '&sim;' => '&#8764;',
1577 '&cong;' => '&#8773;',
1578 '&asymp;' => '&#8776;',
1579 '&ne;' => '&#8800;',
1580 '&equiv;' => '&#8801;',
1581 '&le;' => '&#8804;',
1582 '&ge;' => '&#8805;',
1583 '&sub;' => '&#8834;',
1584 '&sup;' => '&#8835;',
1585 '&nsub;' => '&#8836;',
1586 '&sube;' => '&#8838;',
1587 '&supe;' => '&#8839;',
1588 '&oplus;' => '&#8853;',
1589 '&otimes;' => '&#8855;',
1590 '&perp;' => '&#8869;',
1591 '&sdot;' => '&#8901;',
1592 '&lceil;' => '&#8968;',
1593 '&rceil;' => '&#8969;',
1594 '&lfloor;' => '&#8970;',
1595 '&rfloor;' => '&#8971;',
1596 '&lang;' => '&#9001;',
1597 '&rang;' => '&#9002;',
1598 '&larr;' => '&#8592;',
1599 '&uarr;' => '&#8593;',
1600 '&rarr;' => '&#8594;',
1601 '&darr;' => '&#8595;',
1602 '&harr;' => '&#8596;',
1603 '&loz;' => '&#9674;',
1604 '&spades;' => '&#9824;',
1605 '&clubs;' => '&#9827;',
1606 '&hearts;' => '&#9829;',
1607 '&diams;' => '&#9830;'
1608 );
1609
1610 return str_replace( array_keys($to_ncr), array_values($to_ncr), $text );
1611}
1612
1613/**
1614 * Formats text for the HTML editor.
1615 *
1616 * Unless $output is empty it will pass through htmlspecialchars before the
1617 * 'htmledit_pre' filter is applied.
1618 *
1619 * @since 2.5.0
1620 *
1621 * @param string $output The text to be formatted.
1622 * @return string Formatted text after filter applied.
1623 */
1624function wp_htmledit_pre($output) {
1625 if ( !empty($output) )
1626 $output = htmlspecialchars($output, ENT_NOQUOTES); // convert only < > &
1627
1628 return apply_filters('htmledit_pre', $output);
1629}
1630
1631/**
1632 * Checks and cleans a URL.
1633 *
1634 * A number of characters are removed from the URL. If the URL is for displaying
1635 * (the default behaviour) amperstands are also replaced. The 'clean_url' filter
1636 * is applied to the returned cleaned URL.
1637 *
1638 * @since 1.2.0
1639 * @uses wp_kses_bad_protocol() To only permit protocols in the URL set
1640 * via $protocols or the common ones set in the function.
1641 *
1642 * @param string $url The URL to be cleaned.
1643 * @param array $protocols Optional. An array of acceptable protocols.
1644 * Defaults to 'http', 'https', 'ftp', 'ftps', 'mailto', 'news', 'irc', 'gopher', 'nntp', 'feed', 'telnet' if not set.
1645 * @param string $context Optional. How the URL will be used. Default is 'display'.
1646 * @return string The cleaned $url after the 'cleaned_url' filter is applied.
1647 */
1648function clean_url( $url, $protocols = null, $context = 'display' ) {
1649 $original_url = $url;
1650
1651 if ('' == $url) return $url;
1652 $url = preg_replace('|[^a-z0-9-~+_.?#=!&;,/:%@$*\'()\\x80-\\xff]|i', '', $url);
1653 $strip = array('%0d', '%0a');
1654 $url = str_replace($strip, '', $url);
1655 $url = str_replace(';//', '://', $url);
1656 /* If the URL doesn't appear to contain a scheme, we
1657 * presume it needs http:// appended (unless a relative
1658 * link starting with / or a php file).
1659 */
1660 if ( strpos($url, ':') === false &&
1661 substr( $url, 0, 1 ) != '/' && !preg_match('/^[a-z0-9-]+?\.php/i', $url) )
1662 $url = 'http://' . $url;
1663
1664 // Replace ampersands and single quotes only when displaying.
1665 if ( 'display' == $context ) {
1666 $url = preg_replace('/&([^#])(?![a-z]{2,8};)/', '&#038;$1', $url);
1667 $url = str_replace( "'", '&#039;', $url );
1668 }
1669
1670 if ( !is_array($protocols) )
1671 $protocols = array('http', 'https', 'ftp', 'ftps', 'mailto', 'news', 'irc', 'gopher', 'nntp', 'feed', 'telnet');
1672 if ( wp_kses_bad_protocol( $url, $protocols ) != $url )
1673 return '';
1674
1675 return apply_filters('clean_url', $url, $original_url, $context);
1676}
1677
1678/**
1679 * Performs clean_url() for database usage.
1680 *
1681 * @see clean_url()
1682 *
1683 * @since 2.3.1
1684 *
1685 * @param string $url The URL to be cleaned.
1686 * @param array $protocols An array of acceptable protocols.
1687 * @return string The cleaned URL.
1688 */
1689function sanitize_url( $url, $protocols = null ) {
1690 return clean_url( $url, $protocols, 'db' );
1691}
1692
1693/**
1694 * Convert entities, while preserving already-encoded entities.
1695 *
1696 * @link http://www.php.net/htmlentities Borrowed from the PHP Manual user notes.
1697 *
1698 * @since 1.2.2
1699 *
1700 * @param string $myHTML The text to be converted.
1701 * @return string Converted text.
1702 */
1703function htmlentities2($myHTML) {
1704 $translation_table = get_html_translation_table( HTML_ENTITIES, ENT_QUOTES );
1705 $translation_table[chr(38)] = '&';
1706 return preg_replace( "/&(?![A-Za-z]{0,4}\w{2,3};|#[0-9]{2,3};)/", "&amp;", strtr($myHTML, $translation_table) );
1707}
1708
1709/**
1710 * Escape single quotes, specialchar double quotes, and fix line endings.
1711 *
1712 * The filter 'js_escape' is also applied here.
1713 *
1714 * @since 2.0.4
1715 *
1716 * @param string $text The text to be escaped.
1717 * @return string Escaped text.
1718 */
1719function js_escape($text) {
1720 $safe_text = wp_specialchars($text, 'double');
1721 $safe_text = preg_replace('/&#(x)?0*(?(1)27|39);?/i', "'", stripslashes($safe_text));
1722 $safe_text = preg_replace("/\r?\n/", "\\n", addslashes($safe_text));
1723 return apply_filters('js_escape', $safe_text, $text);
1724}
1725
1726/**
1727 * Escaping for HTML attributes.
1728 *
1729 * @since 2.0.6
1730 *
1731 * @param string $text
1732 * @return string
1733 */
1734function attribute_escape($text) {
1735 $safe_text = wp_specialchars($text, true);
1736 return apply_filters('attribute_escape', $safe_text, $text);
1737}
1738
1739/**
1740 * Escape a HTML tag name.
1741 *
1742 * @since 2.5.0
1743 *
1744 * @param string $tag_name
1745 * @return string
1746 */
1747function tag_escape($tag_name) {
1748 $safe_tag = strtolower( preg_replace('[^a-zA-Z_:]', '', $tag_name) );
1749 return apply_filters('tag_escape', $safe_tag, $tag_name);
1750}
1751
1752/**
1753 * Escapes text for SQL LIKE special characters % and _.
1754 *
1755 * @since 2.5.0
1756 *
1757 * @param string $text The text to be escaped.
1758 * @return string text, safe for inclusion in LIKE query.
1759 */
1760function like_escape($text) {
1761 return str_replace(array("%", "_"), array("\\%", "\\_"), $text);
1762}
1763
1764/**
1765 * Convert full URL paths to absolute paths.
1766 *
1767 * Removes the http or https protocols and the domain. Keeps the path '/' at the
1768 * beginning, so it isn't a true relative link, but from the web root base.
1769 *
1770 * @since 2.1.0
1771 *
1772 * @param string $link Full URL path.
1773 * @return string Absolute path.
1774 */
1775function wp_make_link_relative( $link ) {
1776 return preg_replace( '|https?://[^/]+(/.*)|i', '$1', $link );
1777}
1778
1779/**
1780 * Sanitises various option values based on the nature of the option.
1781 *
1782 * This is basically a switch statement which will pass $value through a number
1783 * of functions depending on the $option.
1784 *
1785 * @since 2.0.5
1786 *
1787 * @param string $option The name of the option.
1788 * @param string $value The unsanitised value.
1789 * @return string Sanitized value.
1790 */
1791function sanitize_option($option, $value) {
1792
1793 switch ($option) {
1794 case 'admin_email':
1795 $value = sanitize_email($value);
1796 break;
1797
1798 case 'thumbnail_size_w':
1799 case 'thumbnail_size_h':
1800 case 'medium_size_w':
1801 case 'medium_size_h':
1802 case 'large_size_w':
1803 case 'large_size_h':
1804 case 'default_post_edit_rows':
1805 case 'mailserver_port':
1806 case 'comment_max_links':
1807 case 'page_on_front':
1808 case 'rss_excerpt_length':
1809 case 'default_category':
1810 case 'default_email_category':
1811 case 'default_link_category':
1812 case 'close_comments_days_old':
1813 case 'comments_per_page':
1814 case 'thread_comments_depth':
1815 $value = abs((int) $value);
1816 break;
1817
1818 case 'posts_per_page':
1819 case 'posts_per_rss':
1820 $value = (int) $value;
1821 if ( empty($value) ) $value = 1;
1822 if ( $value < -1 ) $value = abs($value);
1823 break;
1824
1825 case 'default_ping_status':
1826 case 'default_comment_status':
1827 // Options that if not there have 0 value but need to be something like "closed"
1828 if ( $value == '0' || $value == '')
1829 $value = 'closed';
1830 break;
1831
1832 case 'blogdescription':
1833 case 'blogname':
1834 $value = addslashes($value);
1835 $value = wp_filter_post_kses( $value ); // calls stripslashes then addslashes
1836 $value = stripslashes($value);
1837 $value = wp_specialchars( $value );
1838 break;
1839
1840 case 'blog_charset':
1841 $value = preg_replace('/[^a-zA-Z0-9_-]/', '', $value); // strips slashes
1842 break;
1843
1844 case 'date_format':
1845 case 'time_format':
1846 case 'mailserver_url':
1847 case 'mailserver_login':
1848 case 'mailserver_pass':
1849 case 'ping_sites':
1850 case 'upload_path':
1851 $value = strip_tags($value);
1852 $value = addslashes($value);
1853 $value = wp_filter_kses($value); // calls stripslashes then addslashes
1854 $value = stripslashes($value);
1855 break;
1856
1857 case 'gmt_offset':
1858 $value = preg_replace('/[^0-9:.-]/', '', $value); // strips slashes
1859 break;
1860
1861 case 'siteurl':
1862 case 'home':
1863 $value = stripslashes($value);
1864 $value = clean_url($value);
1865 break;
1866 default :
1867 $value = apply_filters("sanitize_option_{$option}", $value, $option);
1868 break;
1869 }
1870
1871 return $value;
1872}
1873
1874/**
1875 * Parses a string into variables to be stored in an array.
1876 *
1877 * Uses {@link http://www.php.net/parse_str parse_str()} and stripslashes if
1878 * {@link http://www.php.net/magic_quotes magic_quotes_gpc} is on.
1879 *
1880 * @since 2.2.1
1881 * @uses apply_filters() for the 'wp_parse_str' filter.
1882 *
1883 * @param string $string The string to be parsed.
1884 * @param array $array Variables will be stored in this array.
1885 */
1886function wp_parse_str( $string, &$array ) {
1887 parse_str( $string, $array );
1888 if ( get_magic_quotes_gpc() )
1889 $array = stripslashes_deep( $array );
1890 $array = apply_filters( 'wp_parse_str', $array );
1891}
1892
1893/**
1894 * Convert lone less than signs.
1895 *
1896 * KSES already converts lone greater than signs.
1897 *
1898 * @uses wp_pre_kses_less_than_callback in the callback function.
1899 * @since 2.3.0
1900 *
1901 * @param string $text Text to be converted.
1902 * @return string Converted text.
1903 */
1904function wp_pre_kses_less_than( $text ) {
1905 return preg_replace_callback('%<[^>]*?((?=<)|>|$)%', 'wp_pre_kses_less_than_callback', $text);
1906}
1907
1908/**
1909 * Callback function used by preg_replace.
1910 *
1911 * @uses wp_specialchars to format the $matches text.
1912 * @since 2.3.0
1913 *
1914 * @param array $matches Populated by matches to preg_replace.
1915 * @return string The text returned after wp_specialchars if needed.
1916 */
1917function wp_pre_kses_less_than_callback( $matches ) {
1918 if ( false === strpos($matches[0], '>') )
1919 return wp_specialchars($matches[0]);
1920 return $matches[0];
1921}
1922
1923/**
1924 * WordPress implementation of PHP sprintf() with filters.
1925 *
1926 * @since 2.5.0
1927 * @link http://www.php.net/sprintf
1928 *
1929 * @param string $pattern The string which formatted args are inserted.
1930 * @param mixed $args,... Arguments to be formatted into the $pattern string.
1931 * @return string The formatted string.
1932 */
1933function wp_sprintf( $pattern ) {
1934 $args = func_get_args( );
1935 $len = strlen($pattern);
1936 $start = 0;
1937 $result = '';
1938 $arg_index = 0;
1939 while ( $len > $start ) {
1940 // Last character: append and break
1941 if ( strlen($pattern) - 1 == $start ) {
1942 $result .= substr($pattern, -1);
1943 break;
1944 }
1945
1946 // Literal %: append and continue
1947 if ( substr($pattern, $start, 2) == '%%' ) {
1948 $start += 2;
1949 $result .= '%';
1950 continue;
1951 }
1952
1953 // Get fragment before next %
1954 $end = strpos($pattern, '%', $start + 1);
1955 if ( false === $end )
1956 $end = $len;
1957 $fragment = substr($pattern, $start, $end - $start);
1958
1959 // Fragment has a specifier
1960 if ( $pattern{$start} == '%' ) {
1961 // Find numbered arguments or take the next one in order
1962 if ( preg_match('/^%(\d+)\$/', $fragment, $matches) ) {
1963 $arg = isset($args[$matches[1]]) ? $args[$matches[1]] : '';
1964 $fragment = str_replace("%{$matches[1]}$", '%', $fragment);
1965 } else {
1966 ++$arg_index;
1967 $arg = isset($args[$arg_index]) ? $args[$arg_index] : '';
1968 }
1969
1970 // Apply filters OR sprintf
1971 $_fragment = apply_filters( 'wp_sprintf', $fragment, $arg );
1972 if ( $_fragment != $fragment )
1973 $fragment = $_fragment;
1974 else
1975 $fragment = sprintf($fragment, strval($arg) );
1976 }
1977
1978 // Append to result and move to next fragment
1979 $result .= $fragment;
1980 $start = $end;
1981 }
1982 return $result;
1983}
1984
1985/**
1986 * Localize list items before the rest of the content.
1987 *
1988 * The '%l' must be at the first characters can then contain the rest of the
1989 * content. The list items will have ', ', ', and', and ' and ' added depending
1990 * on the amount of list items in the $args parameter.
1991 *
1992 * @since 2.5.0
1993 *
1994 * @param string $pattern Content containing '%l' at the beginning.
1995 * @param array $args List items to prepend to the content and replace '%l'.
1996 * @return string Localized list items and rest of the content.
1997 */
1998function wp_sprintf_l($pattern, $args) {
1999 // Not a match
2000 if ( substr($pattern, 0, 2) != '%l' )
2001 return $pattern;
2002
2003 // Nothing to work with
2004 if ( empty($args) )
2005 return '';
2006
2007 // Translate and filter the delimiter set (avoid ampersands and entities here)
2008 $l = apply_filters('wp_sprintf_l', array(
2009 'between' => _c(', |between list items'),
2010 'between_last_two' => _c(', and |between last two list items'),
2011 'between_only_two' => _c(' and |between only two list items'),
2012 ));
2013
2014 $args = (array) $args;
2015 $result = array_shift($args);
2016 if ( count($args) == 1 )
2017 $result .= $l['between_only_two'] . array_shift($args);
2018 // Loop when more than two args
2019 $i = count($args);
2020 while ( $i ) {
2021 $arg = array_shift($args);
2022 $i--;
2023 if ( $i == 1 )
2024 $result .= $l['between_last_two'] . $arg;
2025 else
2026 $result .= $l['between'] . $arg;
2027 }
2028 return $result . substr($pattern, 2);
2029}
2030
2031/**
2032 * Safely extracts not more than the first $count characters from html string.
2033 *
2034 * UTF-8, tags and entities safe prefix extraction. Entities inside will *NOT*
2035 * be counted as one character. For example &amp; will be counted as 4, &lt; as
2036 * 3, etc.
2037 *
2038 * @since 2.5.0
2039 *
2040 * @param integer $str String to get the excerpt from.
2041 * @param integer $count Maximum number of characters to take.
2042 * @return string The excerpt.
2043 */
2044function wp_html_excerpt( $str, $count ) {
2045 $str = strip_tags( $str );
2046 $str = mb_strcut( $str, 0, $count );
2047 // remove part of an entity at the end
2048 $str = preg_replace( '/&[^;\s]{0,6}$/', '', $str );
2049 return $str;
2050}
2051
2052/**
2053 * Add a Base url to relative links in passed content.
2054 *
2055 * By default it supports the 'src' and 'href' attributes. However this can be
2056 * changed via the 3rd param.
2057 *
2058 * @since 2.7.0
2059 *
2060 * @param string $content String to search for links in.
2061 * @param string $base The base URL to prefix to links.
2062 * @param array $attrs The attributes which should be processed.
2063 * @return string The processed content.
2064 */
2065function links_add_base_url( $content, $base, $attrs = array('src', 'href') ) {
2066 $attrs = implode('|', (array)$attrs);
2067 return preg_replace_callback("!($attrs)=(['\"])(.+?)\\2!i",
2068 create_function('$m', 'return _links_add_base($m, "' . $base . '");'),
2069 $content);
2070}
2071
2072/**
2073 * Callback to add a base url to relative links in passed content.
2074 *
2075 * @since 2.7.0
2076 * @access private
2077 *
2078 * @param string $m The matched link.
2079 * @param string $base The base URL to prefix to links.
2080 * @return string The processed link.
2081 */
2082function _links_add_base($m, $base) {
2083 //1 = attribute name 2 = quotation mark 3 = URL
2084 return $m[1] . '=' . $m[2] .
2085 (strpos($m[3], 'http://') === false ?
2086 path_join($base, $m[3]) :
2087 $m[3])
2088 . $m[2];
2089}
2090
2091/**
2092 * Adds a Target attribute to all links in passed content.
2093 *
2094 * This function by default only applies to <a> tags, however this can be
2095 * modified by the 3rd param.
2096 *
2097 * <b>NOTE:</b> Any current target attributed will be striped and replaced.
2098 *
2099 * @since 2.7.0
2100 *
2101 * @param string $content String to search for links in.
2102 * @param string $target The Target to add to the links.
2103 * @param array $tags An array of tags to apply to.
2104 * @return string The processed content.
2105 */
2106function links_add_target( $content, $target = '_blank', $tags = array('a') ) {
2107 $tags = implode('|', (array)$tags);
2108 return preg_replace_callback("!<($tags)(.+?)>!i",
2109 create_function('$m', 'return _links_add_target($m, "' . $target . '");'),
2110 $content);
2111}
2112/**
2113 * Callback to add a target attribute to all links in passed content.
2114 *
2115 * @since 2.7.0
2116 * @access private
2117 *
2118 * @param string $m The matched link.
2119 * @param string $target The Target to add to the links.
2120 * @return string The processed link.
2121 */
2122function _links_add_target( $m, $target ) {
2123 $tag = $m[1];
2124 $link = preg_replace('|(target=[\'"](.*?)[\'"])|i', '', $m[2]);
2125 return '<' . $tag . $link . ' target="' . $target . '">';
2126}
2127
2128// normalize EOL characters and strip duplicate whitespace
2129function normalize_whitespace( $str ) {
2130 $str = trim($str);
2131 $str = str_replace("\r", "\n", $str);
2132 $str = preg_replace( array( '/\n+/', '/[ \t]+/' ), array( "\n", ' ' ), $str );
2133 return $str;
2134}
2135
2136?>