formatting.php

Revision 1805, 82.6 kB (checked in by donncha, 4 days ago)
WP 2.8 branch merge, part 1

Line
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	* ’cause today’s effort makes it worth tomorrow’s “holiday”…
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 $text The text to be formatted
27	* @return string The string replaced with html entities
28	*/
29	function wptexturize($text) {
30	global $wp_cockneyreplace;
31	$output = '';
32	$curl = '';
33	$textarr = preg_split('/(<.>\|\[.\])/Us', $text, -1, PREG_SPLIT_DELIM_CAPTURE);
34	$stop = count($textarr);
35
36	/* translators: opening curly quote */
37	$opening_quote = _x('“', 'opening curly quote');
38	/* translators: closing curly quote */
39	$closing_quote = _x('”', 'closing curly quote');
40
41	$no_texturize_tags = apply_filters('no_texturize_tags', array('pre', 'code', 'kbd', 'style', 'script', 'tt'));
42	$no_texturize_shortcodes = apply_filters('no_texturize_shortcodes', array('code'));
43	$no_texturize_tags_stack = array();
44	$no_texturize_shortcodes_stack = array();
45
46	// if a plugin has provided an autocorrect array, use it
47	if ( isset($wp_cockneyreplace) ) {
48	$cockney = array_keys($wp_cockneyreplace);
49	$cockneyreplace = array_values($wp_cockneyreplace);
50	} else {
51	$cockney = array("'tain't","'twere","'twas","'tis","'twill","'til","'bout","'nuff","'round","'cause");
52	$cockneyreplace = array("’tain’t","’twere","’twas","’tis","’twill","’til","’bout","’nuff","’round","’cause");
53	}
54
55	$static_characters = array_merge(array('---', ' -- ', '--', ' - ', 'xn–', '...', '``', '\'s', '\'\'', ' (tm)'), $cockney);
56	$static_replacements = array_merge(array('—', ' — ', '–', ' – ', 'xn--', '…', $opening_quote, '’s', $closing_quote, ' ™'), $cockneyreplace);
57
58	$dynamic_characters = array('/\'(\d\d(?:’\|\')?s)/', '/(\s\|\A\|")\'/', '/(\d+)"/', '/(\d+)\'/', '/(\S)\'([^\'\s])/', '/(\s\|\A)"(?!\s)/', '/"(\s\|\S\|\Z)/', '/\'([\s.]\|\Z)/', '/(\d+)x(\d+)/');
59	$dynamic_replacements = array('’$1','$1‘', '$1″', '$1′', '$1’$2', '$1' . $opening_quote . '$2', $closing_quote . '$1', '’$1', '$1×$2');
60
61	for ( $i = 0; $i < $stop; $i++ ) {
62	$curl = $textarr[$i];
63
64	if ( !empty($curl) && '<' != $curl{0} && '[' != $curl{0}
65	&& empty($no_texturize_shortcodes_stack) && empty($no_texturize_tags_stack)) { // If it's not a tag
66	// static strings
67	$curl = str_replace($static_characters, $static_replacements, $curl);
68	// regular expressions
69	$curl = preg_replace($dynamic_characters, $dynamic_replacements, $curl);
70	} else {
71	wptexturize_pushpop_element($curl, $no_texturize_tags_stack, $no_texturize_tags, '<', '>');
72	wptexturize_pushpop_element($curl, $no_texturize_shortcodes_stack, $no_texturize_shortcodes, '[', ']');
73	}
74
75	$curl = preg_replace('/&([^#])(?![a-zA-Z1-4]{1,8};)/', '&$1', $curl);
76	$output .= $curl;
77	}
78
79	return $output;
80	}
81
82	function wptexturize_pushpop_element($text, &$stack, $disabled_elements, $opening = '<', $closing = '>') {
83	$o = preg_quote($opening, '/');
84	$c = preg_quote($closing, '/');
85	foreach($disabled_elements as $element) {
86	if (preg_match('/^'.$o.$element.'\b/', $text)) array_push($stack, $element);
87	if (preg_match('/^'.$o.'\/'.$element.$c.'/', $text)) {
88	$last = array_pop($stack);
89	// disable texturize until we find a closing tag of our type (e.g. <pre>)
90	// even if there was invalid nesting before that
91	// Example: in the case <pre>sadsadasd</code>"baba"</pre> "baba" won't be texturized
92	if ($last != $element) array_push($stack, $last);
93	}
94	}
95	}
96
97	/**
98	* Accepts matches array from preg_replace_callback in wpautop() or a string.
99	*
100	* Ensures that the contents of a <<pre>>...<</pre>> HTML block are not
101	* converted into paragraphs or line-breaks.
102	*
103	* @since 1.2.0
104	*
105	* @param array\|string $matches The array or string
106	* @return string The pre block without paragraph/line-break conversion.
107	*/
108	function clean_pre($matches) {
109	if ( is_array($matches) )
110	$text = $matches[1] . $matches[2] . "</pre>";
111	else
112	$text = $matches;
113
114	$text = str_replace('<br />', '', $text);
115	$text = str_replace('<p>', "\n", $text);
116	$text = str_replace('</p>', '', $text);
117
118	return $text;
119	}
120
121	/**
122	* Replaces double line-breaks with paragraph elements.
123	*
124	* A group of regex replaces used to identify text formatted with newlines and
125	* replace double line-breaks with HTML paragraph tags. The remaining
126	* line-breaks after conversion become <<br />> tags, unless $br is set to '0'
127	* or 'false'.
128	*
129	* @since 0.71
130	*
131	* @param string $pee The text which has to be formatted.
132	* @param int\|bool $br Optional. If set, this will convert all remaining line-breaks after paragraphing. Default true.
133	* @return string Text which has been converted into correct paragraph tags.
134	*/
135	function wpautop($pee, $br = 1) {
136	if ( trim($pee) === '' )
137	return '';
138	$pee = $pee . "\n"; // just to make things a little easier, pad the end
139	$pee = preg_replace('\|<br />\s*<br />\|', "\n\n", $pee);
140	// Space things out a little
141	$allblocks = '(?:table\|thead\|tfoot\|caption\|col\|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)';
142	$pee = preg_replace('!(<' . $allblocks . '[^>]*>)!', "\n$1", $pee);
143	$pee = preg_replace('!(</' . $allblocks . '>)!', "$1\n\n", $pee);
144	$pee = str_replace(array("\r\n", "\r"), "\n", $pee); // cross-platform newlines
145	if ( strpos($pee, '<object') !== false ) {
146	$pee = preg_replace('\|\s<param([^>])>\s*\|', "<param$1>", $pee); // no pee inside object/embed
147	$pee = preg_replace('\|\s</embed>\s\|', '</embed>', $pee);
148	}
149	$pee = preg_replace("/\n\n+/", "\n\n", $pee); // take care of duplicates
150	// make paragraphs, including one at the end
151	$pees = preg_split('/\n\s*\n/', $pee, -1, PREG_SPLIT_NO_EMPTY);
152	$pee = '';
153	foreach ( $pees as $tinkle )
154	$pee .= '<p>' . trim($tinkle, "\n") . "</p>\n";
155	$pee = preg_replace('\|<p>\s*</p>\|', '', $pee); // under certain strange conditions it could create a P of entirely whitespace
156	$pee = preg_replace('!<p>([^<]+)</(div\|address\|form)>!', "<p>$1</p></$2>", $pee);
157	$pee = preg_replace('!<p>\s(</?' . $allblocks . '[^>]>)\s*</p>!', "$1", $pee); // don't pee all over a tag
158	$pee = preg_replace("\|<p>(<li.+?)</p>\|", "$1", $pee); // problem with nested lists
159	$pee = preg_replace('\|<p><blockquote([^>]*)>\|i', "<blockquote$1><p>", $pee);
160	$pee = str_replace('</blockquote></p>', '</p></blockquote>', $pee);
161	$pee = preg_replace('!<p>\s(</?' . $allblocks . '[^>]>)!', "$1", $pee);
162	$pee = preg_replace('!(</?' . $allblocks . '[^>]>)\s</p>!', "$1", $pee);
163	if ($br) {
164	$pee = preg_replace_callback('/<(script\|style).*?<\/\\1>/s', create_function('$matches', 'return str_replace("\n", "<WPPreserveNewline />", $matches[0]);'), $pee);
165	$pee = preg_replace('\|(?<!<br />)\s*\n\|', "<br />\n", $pee); // optionally make line breaks
166	$pee = str_replace('<WPPreserveNewline />', "\n", $pee);
167	}
168	$pee = preg_replace('!(</?' . $allblocks . '[^>]>)\s<br />!', "$1", $pee);
169	$pee = preg_replace('!<br />(\s</?(?:p\|li\|div\|dl\|dd\|dt\|th\|pre\|td\|ul\|ol)[^>]>)!', '$1', $pee);
170	if (strpos($pee, '<pre') !== false)
171	$pee = preg_replace_callback('!(<pre[^>]>)(.?)</pre>!is', 'clean_pre', $pee );
172	$pee = preg_replace( "\|\n</p>$\|", '</p>', $pee );
173	$pee = preg_replace('/<p>\s?(' . get_shortcode_regex() . ')\s<\/p>/s', '$1', $pee); // don't auto-p wrap shortcodes that stand alone
174
175	return $pee;
176	}
177
178	/**
179	* Checks to see if a string is utf8 encoded.
180	*
181	* NOTE: This function checks for 5-Byte sequences, UTF8
182	* has Bytes Sequences with a maximum length of 4.
183	*
184	* @author bmorel at ssi dot fr (modified)
185	* @since 1.2.1
186	*
187	* @param string $str The string to be checked
188	* @return bool True if $str fits a UTF-8 model, false otherwise.
189	*/
190	function seems_utf8($str) {
191	$length = strlen($str);
192	for ($i=0; $i < $length; $i++) {
193	$c = ord($str[$i]);
194	if ($c < 0x80) $n = 0; # 0bbbbbbb
195	elseif (($c & 0xE0) == 0xC0) $n=1; # 110bbbbb
196	elseif (($c & 0xF0) == 0xE0) $n=2; # 1110bbbb
197	elseif (($c & 0xF8) == 0xF0) $n=3; # 11110bbb
198	elseif (($c & 0xFC) == 0xF8) $n=4; # 111110bb
199	elseif (($c & 0xFE) == 0xFC) $n=5; # 1111110b
200	else return false; # Does not match any model
201	for ($j=0; $j<$n; $j++) { # n bytes matching 10bbbbbb follow ?
202	if ((++$i == $length) \|\| ((ord($str[$i]) & 0xC0) != 0x80))
203	return false;
204	}
205	}
206	return true;
207	}
208
209	/**
210	* Converts a number of special characters into their HTML entities.
211	*
212	* Specifically deals with: &, <, >, ", and '.
213	*
214	* $quote_style can be set to ENT_COMPAT to encode " to
215	* ", or ENT_QUOTES to do both. Default is ENT_NOQUOTES where no quotes are encoded.
216	*
217	* @since 1.2.2
218	*
219	* @param string $string The text which is to be encoded.
220	* @param mixed $quote_style Optional. Converts double quotes if set to ENT_COMPAT, both single and double if set to ENT_QUOTES or none if set to ENT_NOQUOTES. Also compatible with old values; converting single quotes if set to 'single', double if set to 'double' or both if otherwise set. Default is ENT_NOQUOTES.
221	* @param string $charset Optional. The character encoding of the string. Default is false.
222	* @param boolean $double_encode Optional. Whether or not to encode existing html entities. Default is false.
223	* @return string The encoded text with HTML entities.
224	*/
225	function _wp_specialchars( $string, $quote_style = ENT_NOQUOTES, $charset = false, $double_encode = false ) {
226	$string = (string) $string;
227
228	if ( 0 === strlen( $string ) ) {
229	return '';
230	}
231
232	// Don't bother if there are no specialchars - saves some processing
233	if ( !preg_match( '/[&<>"\']/', $string ) ) {
234	return $string;
235	}
236
237	// Account for the previous behaviour of the function when the $quote_style is not an accepted value
238	if ( empty( $quote_style ) ) {
239	$quote_style = ENT_NOQUOTES;
240	} elseif ( !in_array( $quote_style, array( 0, 2, 3, 'single', 'double' ), true ) ) {
241	$quote_style = ENT_QUOTES;
242	}
243
244	// Store the site charset as a static to avoid multiple calls to wp_load_alloptions()
245	if ( !$charset ) {
246	static $_charset;
247	if ( !isset( $_charset ) ) {
248	$alloptions = wp_load_alloptions();
249	$_charset = isset( $alloptions['blog_charset'] ) ? $alloptions['blog_charset'] : '';
250	}
251	$charset = $_charset;
252	}
253	if ( in_array( $charset, array( 'utf8', 'utf-8', 'UTF8' ) ) ) {
254	$charset = 'UTF-8';
255	}
256
257	$_quote_style = $quote_style;
258
259	if ( $quote_style === 'double' ) {
260	$quote_style = ENT_COMPAT;
261	$_quote_style = ENT_COMPAT;
262	} elseif ( $quote_style === 'single' ) {
263	$quote_style = ENT_NOQUOTES;
264	}
265
266	// Handle double encoding ourselves
267	if ( !$double_encode ) {
268	$string = wp_specialchars_decode( $string, $_quote_style );
269	$string = preg_replace( '/&(#?x?[0-9a-z]+);/i', '\|wp_entity\|$1\|/wp_entity\|', $string );
270	}
271
272	$string = @htmlspecialchars( $string, $quote_style, $charset );
273
274	// Handle double encoding ourselves
275	if ( !$double_encode ) {
276	$string = str_replace( array( '\|wp_entity\|', '\|/wp_entity\|' ), array( '&', ';' ), $string );
277	}
278
279	// Backwards compatibility
280	if ( 'single' === $_quote_style ) {
281	$string = str_replace( "'", ''', $string );
282	}
283
284	return $string;
285	}
286
287	/**
288	* Converts a number of HTML entities into their special characters.
289	*
290	* Specifically deals with: &, <, >, ", and '.
291	*
292	* $quote_style can be set to ENT_COMPAT to decode " entities,
293	* or ENT_QUOTES to do both " and '. Default is ENT_NOQUOTES where no quotes are decoded.
294	*
295	* @since 2.8
296	*
297	* @param string $string The text which is to be decoded.
298	* @param mixed $quote_style Optional. Converts double quotes if set to ENT_COMPAT, both single and double if set to ENT_QUOTES or none if set to ENT_NOQUOTES. Also compatible with old _wp_specialchars() values; converting single quotes if set to 'single', double if set to 'double' or both if otherwise set. Default is ENT_NOQUOTES.
299	* @return string The decoded text without HTML entities.
300	*/
301	function wp_specialchars_decode( $string, $quote_style = ENT_NOQUOTES ) {
302	$string = (string) $string;
303
304	if ( 0 === strlen( $string ) ) {
305	return '';
306	}
307
308	// Don't bother if there are no entities - saves a lot of processing
309	if ( strpos( $string, '&' ) === false ) {
310	return $string;
311	}
312
313	// Match the previous behaviour of _wp_specialchars() when the $quote_style is not an accepted value
314	if ( empty( $quote_style ) ) {
315	$quote_style = ENT_NOQUOTES;
316	} elseif ( !in_array( $quote_style, array( 0, 2, 3, 'single', 'double' ), true ) ) {
317	$quote_style = ENT_QUOTES;
318	}
319
320	// More complete than get_html_translation_table( HTML_SPECIALCHARS )
321	$single = array( ''' => '\'', ''' => '\'' );
322	$single_preg = array( '/&#039;/' => ''', '/&#x027;/i' => ''' );
323	$double = array( '"' => '"', '"' => '"', '"' => '"' );
324	$double_preg = array( '/&#034;/' => '"', '/&#x022;/i' => '"' );
325	$others = array( '<' => '<', '<' => '<', '>' => '>', '>' => '>', '&' => '&', '&' => '&', '&' => '&' );
326	$others_preg = array( '/&#060;/' => '<', '/&#062;/' => '>', '/&#038;/' => '&', '/&#x026;/i' => '&' );
327
328	if ( $quote_style === ENT_QUOTES ) {
329	$translation = array_merge( $single, $double, $others );
330	$translation_preg = array_merge( $single_preg, $double_preg, $others_preg );
331	} elseif ( $quote_style === ENT_COMPAT \|\| $quote_style === 'double' ) {
332	$translation = array_merge( $double, $others );
333	$translation_preg = array_merge( $double_preg, $others_preg );
334	} elseif ( $quote_style === 'single' ) {
335	$translation = array_merge( $single, $others );
336	$translation_preg = array_merge( $single_preg, $others_preg );
337	} elseif ( $quote_style === ENT_NOQUOTES ) {
338	$translation = $others;
339	$translation_preg = $others_preg;
340	}
341
342	// Remove zero padding on numeric entities
343	$string = preg_replace( array_keys( $translation_preg ), array_values( $translation_preg ), $string );
344
345	// Replace characters according to translation table
346	return strtr( $string, $translation );
347	}
348
349	/**
350	* Checks for invalid UTF8 in a string.
351	*
352	* @since 2.8
353	*
354	* @param string $string The text which is to be checked.
355	* @param boolean $strip Optional. Whether to attempt to strip out invalid UTF8. Default is false.
356	* @return string The checked text.
357	*/
358	function wp_check_invalid_utf8( $string, $strip = false ) {
359	$string = (string) $string;
360
361	if ( 0 === strlen( $string ) ) {
362	return '';
363	}
364
365	// Store the site charset as a static to avoid multiple calls to get_option()
366	static $is_utf8;
367	if ( !isset( $is_utf8 ) ) {
368	$is_utf8 = in_array( get_option( 'blog_charset' ), array( 'utf8', 'utf-8', 'UTF8', 'UTF-8' ) );
369	}
370	if ( !$is_utf8 ) {
371	return $string;
372	}
373
374	// Check for support for utf8 in the installed PCRE library once and store the result in a static
375	static $utf8_pcre;
376	if ( !isset( $utf8_pcre ) ) {
377	$utf8_pcre = @preg_match( '/^./u', 'a' );
378	}
379	// We can't demand utf8 in the PCRE installation, so just return the string in those cases
380	if ( !$utf8_pcre ) {
381	return $string;
382	}
383
384	// preg_match fails when it encounters invalid UTF8 in $string
385	if ( 1 === @preg_match( '/^./us', $string ) ) {
386	return $string;
387	}
388
389	// Attempt to strip the bad chars if requested (not recommended)
390	if ( $strip && function_exists( 'iconv' ) ) {
391	return iconv( 'utf-8', 'utf-8', $string );
392	}
393
394	return '';
395	}
396
397	/**
398	* Encode the Unicode values to be used in the URI.
399	*
400	* @since 1.5.0
401	*
402	* @param string $utf8_string
403	* @param int $length Max length of the string
404	* @return string String with Unicode encoded for URI.
405	*/
406	function utf8_uri_encode( $utf8_string, $length = 0 ) {
407	$unicode = '';
408	$values = array();
409	$num_octets = 1;
410	$unicode_length = 0;
411
412	$string_length = strlen( $utf8_string );
413	for ($i = 0; $i < $string_length; $i++ ) {
414
415	$value = ord( $utf8_string[ $i ] );
416
417	if ( $value < 128 ) {
418	if ( $length && ( $unicode_length >= $length ) )
419	break;
420	$unicode .= chr($value);
421	$unicode_length++;
422	} else {
423	if ( count( $values ) == 0 ) $num_octets = ( $value < 224 ) ? 2 : 3;
424
425	$values[] = $value;
426
427	if ( $length && ( $unicode_length + ($num_octets * 3) ) > $length )
428	break;
429	if ( count( $values ) == $num_octets ) {
430	if ($num_octets == 3) {
431	$unicode .= '%' . dechex($values[0]) . '%' . dechex($values[1]) . '%' . dechex($values[2]);
432	$unicode_length += 9;
433	} else {
434	$unicode .= '%' . dechex($values[0]) . '%' . dechex($values[1]);
435	$unicode_length += 6;
436	}
437
438	$values = array();
439	$num_octets = 1;
440	}
441	}
442	}
443
444	return $unicode;
445	}
446
447	/**
448	* Converts all accent characters to ASCII characters.
449	*
450	* If there are no accent characters, then the string given is just returned.
451	*
452	* @since 1.2.1
453	*
454	* @param string $string Text that might have accent characters
455	* @return string Filtered string with replaced "nice" characters.
456	*/
457	function remove_accents($string) {
458	if ( !preg_match('/[\x80-\xff]/', $string) )
459	return $string;
460
461	if (seems_utf8($string)) {
462	$chars = array(
463	// Decompositions for Latin-1 Supplement
464	chr(195).chr(128) => 'A', chr(195).chr(129) => 'A',
465	chr(195).chr(130) => 'A', chr(195).chr(131) => 'A',
466	chr(195).chr(132) => 'A', chr(195).chr(133) => 'A',
467	chr(195).chr(135) => 'C', chr(195).chr(136) => 'E',
468	chr(195).chr(137) => 'E', chr(195).chr(138) => 'E',
469	chr(195).chr(139) => 'E', chr(195).chr(140) => 'I',
470	chr(195).chr(141) => 'I', chr(195).chr(142) => 'I',
471	chr(195).chr(143) => 'I', chr(195).chr(145) => 'N',
472	chr(195).chr(146) => 'O', chr(195).chr(147) => 'O',
473	chr(195).chr(148) => 'O', chr(195).chr(149) => 'O',
474	chr(195).chr(150) => 'O', chr(195).chr(153) => 'U',
475	chr(195).chr(154) => 'U', chr(195).chr(155) => 'U',
476	chr(195).chr(156) => 'U', chr(195).chr(157) => 'Y',
477	chr(195).chr(159) => 's', chr(195).chr(160) => 'a',
478	chr(195).chr(161) => 'a', chr(195).chr(162) => 'a',
479	chr(195).chr(163) => 'a', chr(195).chr(164) => 'a',
480	chr(195).chr(165) => 'a', chr(195).chr(167) => 'c',
481	chr(195).chr(168) => 'e', chr(195).chr(169) => 'e',
482	chr(195).chr(170) => 'e', chr(195).chr(171) => 'e',
483	chr(195).chr(172) => 'i', chr(195).chr(173) => 'i',
484	chr(195).chr(174) => 'i', chr(195).chr(175) => 'i',
485	chr(195).chr(177) => 'n', chr(195).chr(178) => 'o',
486	chr(195).chr(179) => 'o', chr(195).chr(180) => 'o',
487	chr(195).chr(181) => 'o', chr(195).chr(182) => 'o',
488	chr(195).chr(182) => 'o', chr(195).chr(185) => 'u',
489	chr(195).chr(186) => 'u', chr(195).chr(187) => 'u',
490	chr(195).chr(188) => 'u', chr(195).chr(189) => 'y',
491	chr(195).chr(191) => 'y',
492	// Decompositions for Latin Extended-A
493	chr(196).chr(128) => 'A', chr(196).chr(129) => 'a',
494	chr(196).chr(130) => 'A', chr(196).chr(131) => 'a',
495	chr(196).chr(132) => 'A', chr(196).chr(133) => 'a',
496	chr(196).chr(134) => 'C', chr(196).chr(135) => 'c',
497	chr(196).chr(136) => 'C', chr(196).chr(137) => 'c',
498	chr(196).chr(138) => 'C', chr(196).chr(139) => 'c',
499	chr(196).chr(140) => 'C', chr(196).chr(141) => 'c',
500	chr(196).chr(142) => 'D', chr(196).chr(143) => 'd',
501	chr(196).chr(144) => 'D', chr(196).chr(145) => 'd',
502	chr(196).chr(146) => 'E', chr(196).chr(147) => 'e',
503	chr(196).chr(148) => 'E', chr(196).chr(149) => 'e',
504	chr(196).chr(150) => 'E', chr(196).chr(151) => 'e',
505	chr(196).chr(152) => 'E', chr(196).chr(153) => 'e',
506	chr(196).chr(154) => 'E', chr(196).chr(155) => 'e',
507	chr(196).chr(156) => 'G', chr(196).chr(157) => 'g',
508	chr(196).chr(158) => 'G', chr(196).chr(159) => 'g',
509	chr(196).chr(160) => 'G', chr(196).chr(161) => 'g',
510	chr(196).chr(162) => 'G', chr(196).chr(163) => 'g',
511	chr(196).chr(164) => 'H', chr(196).chr(165) => 'h',
512	chr(196).chr(166) => 'H', chr(196).chr(167) => 'h',
513	chr(196).chr(168) => 'I', chr(196).chr(169) => 'i',
514	chr(196).chr(170) => 'I', chr(196).chr(171) => 'i',
515	chr(196).chr(172) => 'I', chr(196).chr(173) => 'i',
516	chr(196).chr(174) => 'I', chr(196).chr(175) => 'i',
517	chr(196).chr(176) => 'I', chr(196).chr(177) => 'i',
518	chr(196).chr(178) => 'IJ',chr(196).chr(179) => 'ij',
519	chr(196).chr(180) => 'J', chr(196).chr(181) => 'j',
520	chr(196).chr(182) => 'K', chr(196).chr(183) => 'k',
521	chr(196).chr(184) => 'k', chr(196).chr(185) => 'L',
522	chr(196).chr(186) => 'l', chr(196).chr(187) => 'L',
523	chr(196).chr(188) => 'l', chr(196).chr(189) => 'L',
524	chr(196).chr(190) => 'l', chr(196).chr(191) => 'L',
525	chr(197).chr(128) => 'l', chr(197).chr(129) => 'L',
526	chr(197).chr(130) => 'l', chr(197).chr(131) => 'N',
527	chr(197).chr(132) => 'n', chr(197).chr(133) => 'N',
528	chr(197).chr(134) => 'n', chr(197).chr(135) => 'N',
529	chr(197).chr(136) => 'n', chr(197).chr(137) => 'N',
530	chr(197).chr(138) => 'n', chr(197).chr(139) => 'N',
531	chr(197).chr(140) => 'O', chr(197).chr(141) => 'o',
532	chr(197).chr(142) => 'O', chr(197).chr(143) => 'o',
533	chr(197).chr(144) => 'O', chr(197).chr(145) => 'o',
534	chr(197).chr(146) => 'OE',chr(197).chr(147) => 'oe',
535	chr(197).chr(148) => 'R',chr(197).chr(149) => 'r',
536	chr(197).chr(150) => 'R',chr(197).chr(151) => 'r',
537	chr(197).chr(152) => 'R',chr(197).chr(153) => 'r',
538	chr(197).chr(154) => 'S',chr(197).chr(155) => 's',
539	chr(197).chr(156) => 'S',chr(197).chr(157) => 's',
540	chr(197).chr(158) => 'S',chr(197).chr(159) => 's',
541	chr(197).chr(160) => 'S', chr(197).chr(161) => 's',
542	chr(197).chr(162) => 'T', chr(197).chr(163) => 't',
543	chr(197).chr(164) => 'T', chr(197).chr(165) => 't',
544	chr(197).chr(166) => 'T', chr(197).chr(167) => 't',
545	chr(197).chr(168) => 'U', chr(197).chr(169) => 'u',
546	chr(197).chr(170) => 'U', chr(197).chr(171) => 'u',
547	chr(197).chr(172) => 'U', chr(197).chr(173) => 'u',
548	chr(197).chr(174) => 'U', chr(197).chr(175) => 'u',
549	chr(197).chr(176) => 'U', chr(197).chr(177) => 'u',
550	chr(197).chr(178) => 'U', chr(197).chr(179) => 'u',
551	chr(197).chr(180) => 'W', chr(197).chr(181) => 'w',
552	chr(197).chr(182) => 'Y', chr(197).chr(183) => 'y',
553	chr(197).chr(184) => 'Y', chr(197).chr(185) => 'Z',
554	chr(197).chr(186) => 'z', chr(197).chr(187) => 'Z',
555	chr(197).chr(188) => 'z', chr(197).chr(189) => 'Z',
556	chr(197).chr(190) => 'z', chr(197).chr(191) => 's',
557	// Euro Sign
558	chr(226).chr(130).chr(172) => 'E',
559	// GBP (Pound) Sign
560	chr(194).chr(163) => '');
561
562	$string = strtr($string, $chars);
563	} else {
564	// Assume ISO-8859-1 if not UTF-8
565	$chars['in'] = chr(128).chr(131).chr(138).chr(142).chr(154).chr(158)
566	.chr(159).chr(162).chr(165).chr(181).chr(192).chr(193).chr(194)
567	.chr(195).chr(196).chr(197).chr(199).chr(200).chr(201).chr(202)
568	.chr(203).chr(204).chr(205).chr(206).chr(207).chr(209).chr(210)
569	.chr(211).chr(212).chr(213).chr(214).chr(216).chr(217).chr(218)
570	.chr(219).chr(220).chr(221).chr(224).chr(225).chr(226).chr(227)
571	.chr(228).chr(229).chr(231).chr(232).chr(233).chr(234).chr(235)
572	.chr(236).chr(237).chr(238).chr(239).chr(241).chr(242).chr(243)
573	.chr(244).chr(245).chr(246).chr(248).chr(249).chr(250).chr(251)
574	.chr(252).chr(253).chr(255);
575
576	$chars['out'] = "EfSZszYcYuAAAAAACEEEEIIIINOOOOOOUUUUYaaaaaaceeeeiiiinoooooouuuuyy";
577
578	$string = strtr($string, $chars['in'], $chars['out']);
579	$double_chars['in'] = array(chr(140), chr(156), chr(198), chr(208), chr(222), chr(223), chr(230), chr(240), chr(254));
580	$double_chars['out'] = array('OE', 'oe', 'AE', 'DH', 'TH', 'ss', 'ae', 'dh', 'th');
581	$string = str_replace($double_chars['in'], $double_chars['out'], $string);
582	}
583
584	return $string;
585	}
586
587	/**
588	* Sanitizes a filename replacing whitespace with dashes
589	*
590	* Removes special characters that are illegal in filenames on certain
591	* operating systems and special characters requiring special escaping
592	* to manipulate at the command line. Replaces spaces and consecutive
593	* dashes with a single dash. Trim period, dash and underscore from beginning
594	* and end of filename.
595	*
596	* @since 2.1.0
597	*
598	* @param string $filename The filename to be sanitized
599	* @return string The sanitized filename
600	*/
601	function sanitize_file_name( $filename ) {
602	$filename_raw = $filename;
603	$special_chars = array("?", "[", "]", "/", "\\", "=", "<", ">", ":", ";", ",", "'", "\"", "&", "$", "#", "*", "(", ")", "\|", "~", "`", "!", "{", "}");
604	$special_chars = apply_filters('sanitize_file_name_chars', $special_chars, $filename_raw);
605	$filename = str_replace($special_chars, '', $filename);
606	$filename = preg_replace('/[\s-]+/', '-', $filename);
607	$filename = trim($filename, '.-_');
608	return apply_filters('sanitize_file_name', $filename, $filename_raw);
609	}
610
611	/**
612	* Sanitize username stripping out unsafe characters.
613	*
614	* If $strict is true, only alphanumeric characters (as well as _, space, ., -,
615	* @) are returned.
616	* Removes tags, octets, entities, and if strict is enabled, will remove all
617	* non-ASCII characters. After sanitizing, it passes the username, raw username
618	* (the username in the parameter), and the strict parameter as parameters for
619	* the filter.
620	*
621	* @since 2.0.0
622	* @uses apply_filters() Calls 'sanitize_user' hook on username, raw username,
623	* and $strict parameter.
624	*
625	* @param string $username The username to be sanitized.
626	* @param bool $strict If set limits $username to specific characters. Default false.
627	* @return string The sanitized username, after passing through filters.
628	*/
629	function sanitize_user( $username, $strict = false ) {
630	$raw_username = $username;
631	$username = strip_tags($username);
632	// Kill octets
633	$username = preg_replace('\|%([a-fA-F0-9][a-fA-F0-9])\|', '', $username);
634	$username = preg_replace('/&.+?;/', '', $username); // Kill entities
635
636	// If strict, reduce to ASCII for max portability.
637	if ( $strict )
638	$username = preg_replace('\|[^a-z0-9 _.\-@]\|i', '', $username);
639
640	// Consolidate contiguous whitespace
641	$username = preg_replace('\|\s+\|', ' ', $username);
642
643	return apply_filters('sanitize_user', $username, $raw_username, $strict);
644	}
645
646	/**
647	* Sanitizes title or use fallback title.
648	*
649	* Specifically, HTML and PHP tags are stripped. Further actions can be added
650	* via the plugin API. If $title is empty and $fallback_title is set, the latter
651	* will be used.
652	*
653	* @since 1.0.0
654	*
655	* @param string $title The string to be sanitized.
656	* @param string $fallback_title Optional. A title to use if $title is empty.
657	* @return string The sanitized string.
658	*/
659	function sanitize_title($title, $fallback_title = '') {
660	$raw_title = $title;
661	$title = strip_tags($title);
662	$title = apply_filters('sanitize_title', $title, $raw_title);
663
664	if ( '' === $title \|\| false === $title )
665	$title = $fallback_title;
666
667	return $title;
668	}
669
670	/**
671	* Sanitizes title, replacing whitespace with dashes.
672	*
673	* Limits the output to alphanumeric characters, underscore (_) and dash (-).
674	* Whitespace becomes a dash.
675	*
676	* @since 1.2.0
677	*
678	* @param string $title The title to be sanitized.
679	* @return string The sanitized title.
680	*/
681	function sanitize_title_with_dashes($title) {
682	$title = strip_tags($title);
683	// Preserve escaped octets.
684	$title = preg_replace('\|%([a-fA-F0-9][a-fA-F0-9])\|', '---$1---', $title);
685	// Remove percent signs that are not part of an octet.
686	$title = str_replace('%', '', $title);
687	// Restore octets.
688	$title = preg_replace('\|---([a-fA-F0-9][a-fA-F0-9])---\|', '%$1', $title);
689
690	$title = remove_accents($title);
691	if (seems_utf8($title)) {
692	if (function_exists('mb_strtolower')) {
693	$title = mb_strtolower($title, 'UTF-8');
694	}
695	$title = utf8_uri_encode($title, 200);
696	}
697
698	$title = strtolower($title);
699	$title = preg_replace('/&.+?;/', '', $title); // kill entities
700	$title = str_replace('.', '-', $title);
701	$title = preg_replace('/[^%a-z0-9 _-]/', '', $title);
702	$title = preg_replace('/\s+/', '-', $title);
703	$title = preg_replace('\|-+\|', '-', $title);
704	$title = trim($title, '-');
705
706	return $title;
707	}
708
709	/**
710	* Ensures a string is a valid SQL order by clause.
711	*
712	* Accepts one or more columns, with or without ASC/DESC, and also accepts
713	* RAND().
714	*
715	* @since 2.5.1
716	*
717	* @param string $orderby Order by string to be checked.
718	* @return string\|false Returns the order by clause if it is a match, false otherwise.
719	*/
720	function sanitize_sql_orderby( $orderby ){
721	preg_match('/^\s([a-z0-9_]+(\s+(ASC\|DESC))?(\s,\s\|\s$))+\|^\sRAND$\s$\s*$/i', $orderby, $obmatches);
722	if ( !$obmatches )
723	return false;
724	return $orderby;
725	}
726
727	/**
728	* Santizes a html classname to ensure it only contains valid characters
729	*
730	* Strips the string down to A-Z,a-z,0-9,'-' if this results in an empty
731	* string then it will return the alternative value supplied.
732	*
733	* @todo Expand to support the full range of CDATA that a class attribute can contain.
734	*
735	* @since 2.8.0
736	*
737	* @param string $class The classname to be sanitized
738	* @param string $fallback The value to return if the sanitization end's up as an empty string.
739	* @return string The sanitized value
740	*/
741	function sanitize_html_class($class, $fallback){
742	//Strip out any % encoded octets
743	$sanitized = preg_replace('\|%[a-fA-F0-9][a-fA-F0-9]\|', '', $class);
744
745	//Limit to A-Z,a-z,0-9,'-'
746	$sanitized = preg_replace('/[^A-Za-z0-9-]/', '', $sanitized);
747
748	if ('' == $sanitized)
749	$sanitized = $fallback;
750
751	return apply_filters('sanitize_html_class',$sanitized, $class, $fallback);
752	}
753
754	/**
755	* Converts a number of characters from a string.
756	*
757	* Metadata tags <<title>> and <<category>> are removed, <<br>> and <<hr>> are
758	* converted into correct XHTML and Unicode characters are converted to the
759	* valid range.
760	*
761	* @since 0.71
762	*
763	* @param string $content String of characters to be converted.
764	* @param string $deprecated Not used.
765	* @return string Converted string.
766	*/
767	function convert_chars($content, $deprecated = '') {
768	// Translation of invalid Unicode references range to valid range
769	$wp_htmltranswinuni = array(
770	'' => '€', // the Euro sign
771	'' => '',
772	'' => '‚', // these are Windows CP1252 specific characters
773	'' => 'ƒ', // they would look weird on non-Windows browsers
774	'' => '„',
775	'' => '…',
776	'' => '†',
777	'' => '‡',
778	'' => 'ˆ',
779	'' => '‰',
780	'' => 'Š',
781	'' => '‹',
782	'' => 'Œ',
783	'' => '',
784	'' => 'ž',
785	'' => '',
786	'' => '',
787	'' => '‘',
788	'' => '’',
789	'' => '“',
790	'' => '”',
791	'' => '•',
792	'' => '–',
793	'' => '—',
794	'' => '˜',
795	'' => '™',
796	'' => 'š',
797	'' => '›',
798	'' => 'œ',
799	'' => '',
800	'' => '',
801	'' => 'Ÿ'
802	);
803
804	// Remove metadata tags
805	$content = preg_replace('/<title>(.+?)<\/title>/','',$content);
806	$content = preg_replace('/<category>(.+?)<\/category>/','',$content);
807
808	// Converts lone & characters into & (a.k.a. &)
809	$content = preg_replace('/&([^#])(?![a-z1-4]{1,8};)/i', '&$1', $content);
810
811	// Fix Word pasting
812	$content = strtr($content, $wp_htmltranswinuni);
813
814	// Just a little XHTML help
815	$content = str_replace('<br>', '<br />', $content);
816	$content = str_replace('<hr>', '<hr />', $content);
817
818	return $content;
819	}
820
821	/**
822	* Callback used to change %uXXXX to &#YYY; syntax
823	*
824	* @since 2.8?
825	*
826	* @param array $matches Single Match
827	* @return string An HTML entity
828	*/
829	function funky_javascript_callback($matches) {
830	return "&#".base_convert($matches[1],16,10).";";
831	}
832
833	/**
834	* Fixes javascript bugs in browsers.
835	*
836	* Converts unicode characters to HTML numbered entities.
837	*
838	* @since 1.5.0
839	* @uses $is_macIE
840	* @uses $is_winIE
841	*
842	* @param string $text Text to be made safe.
843	* @return string Fixed text.
844	*/
845	function funky_javascript_fix($text) {
846	// Fixes for browsers' javascript bugs
847	global $is_macIE, $is_winIE;
848
849	if ( $is_winIE \|\| $is_macIE )
850	$text = preg_replace_callback("/\%u([0-9A-F]{4,4})/",
851	"funky_javascript_callback",
852	$text);
853
854	return $text;
855	}
856
857	/**
858	* Will only balance the tags if forced to and the option is set to balance tags.
859	*
860	* The option 'use_balanceTags' is used for whether the tags will be balanced.
861	* Both the $force parameter and 'use_balanceTags' option will have to be true
862	* before the tags will be balanced.
863	*
864	* @since 0.71
865	*
866	* @param string $text Text to be balanced
867	* @param bool $force Forces balancing, ignoring the value of the option. Default false.
868	* @return string Balanced text
869	*/
870	function balanceTags( $text, $force = false ) {
871	if ( !$force && get_option('use_balanceTags') == 0 )
872	return $text;
873	return force_balance_tags( $text );
874	}
875
876	/**
877	* Balances tags of string using a modified stack.
878	*
879	* @since 2.0.4
880	*
881	* @author Leonard Lin <leonard@acm.org>
882	* @license GPL v2.0
883	* @copyright November 4, 2001
884	* @version 1.1
885	* @todo Make better - change loop condition to $text in 1.2
886	* @internal Modified by Scott Reilly (coffee2code) 02 Aug 2004
887	* 1.1 Fixed handling of append/stack pop order of end text
888	* Added Cleaning Hooks
889	* 1.0 First Version
890	*
891	* @param string $text Text to be balanced.
892	* @return string Balanced text.
893	*/
894	function force_balance_tags( $text ) {
895	$tagstack = array(); $stacksize = 0; $tagqueue = ''; $newtext = '';
896	$single_tags = array('br', 'hr', 'img', 'input'); //Known single-entity/self-closing tags
897	$nestable_tags = array('blockquote', 'div', 'span'); //Tags that can be immediately nested within themselves
898
899	# WP bug fix for comments - in case you REALLY meant to type '< !--'
900	$text = str_replace('< !--', '< !--', $text);
901	# WP bug fix for LOVE <3 (and other situations with '<' before a number)
902	$text = preg_replace('#<([0-9]{1})#', '<$1', $text);
903
904	while (preg_match("/<(\/?\w)\s([^>]*)>/",$text,$regex)) {
905	$newtext .= $tagqueue;
906
907	$i = strpos($text,$regex[0]);
908	$l = strlen($regex[0]);
909
910	// clear the shifter
911	$tagqueue = '';
912	// Pop or Push
913	if ( isset($regex[1][0]) && '/' == $regex[1][0] ) { // End Tag
914	$tag = strtolower(substr($regex[1],1));
915	// if too many closing tags
916	if($stacksize <= 0) {
917	$tag = '';
918	//or close to be safe $tag = '/' . $tag;
919	}
920	// if stacktop value = tag close value then pop
921	else if ($tagstack[$stacksize - 1] == $tag) { // found closing tag
922	$tag = '</' . $tag . '>'; // Close Tag
923	// Pop
924	array_pop ($tagstack);
925	$stacksize--;
926	} else { // closing tag not at top, search for it
927	for ($j=$stacksize-1;$j>=0;$j--) {
928	if ($tagstack[$j] == $tag) {
929	// add tag to tagqueue
930	for ($k=$stacksize-1;$k>=$j;$k--){
931	$tagqueue .= '</' . array_pop ($tagstack) . '>';
932	$stacksize--;
933	}
934	break;
935	}
936	}
937	$tag = '';
938	}
939	} else { // Begin Tag
940	$tag = strtolower($regex[1]);
941
942	// Tag Cleaning
943
944	// If self-closing or '', don't do anything.
945	if((substr($regex[2],-1) == '/') \|\| ($tag == '')) {
946	}
947	// ElseIf it's a known single-entity tag but it doesn't close itself, do so
948	elseif ( in_array($tag, $single_tags) ) {
949	$regex[2] .= '/';
950	} else { // Push the tag onto the stack
951	// If the top of the stack is the same as the tag we want to push, close previous tag
952	if (($stacksize > 0) && !in_array($tag, $nestable_tags) && ($tagstack[$stacksize - 1] == $tag)) {
953	$tagqueue = '</' . array_pop ($tagstack) . '>';
954	$stacksize--;
955	}
956	$stacksize = array_push ($tagstack, $tag);
957	}
958
959	// Attributes
960	$attributes = $regex[2];
961	if($attributes) {
962	$attributes = ' '.$attributes;
963	}
964	$tag = '<'.$tag.$attributes.'>';
965	//If already queuing a close tag, then put this tag on, too
966	if ($tagqueue) {
967	$tagqueue .= $tag;
968	$tag = '';
969	}
970	}
971	$newtext .= substr($text,0,$i) . $tag;
972	$text = substr($text,$i+$l);
973	}
974
975	// Clear Tag Queue
976	$newtext .= $tagqueue;
977
978	// Add Remaining text
979	$newtext .= $text;
980
981	// Empty Stack
982	while($x = array_pop($tagstack)) {
983	$newtext .= '</' . $x . '>'; // Add remaining tags to close
984	}
985
986	// WP fix for the bug with HTML comments
987	$newtext = str_replace("< !--","<!--",$newtext);
988	$newtext = str_replace("< !--","< !--",$newtext);
989
990	return $newtext;
991	}
992
993	/**
994	* Acts on text which is about to be edited.
995	*
996	* Unless $richedit is set, it is simply a holder for the 'format_to_edit'
997	* filter. If $richedit is set true htmlspecialchars() will be run on the
998	* content, converting special characters to HTMl entities.
999	*
1000	* @since 0.71
1001	*
1002	* @param string $content The text about to be edited.
1003	* @param bool $richedit Whether or not the $content should pass through htmlspecialchars(). Default false.
1004	* @return string The text after the filter (and possibly htmlspecialchars()) has been run.
1005	*/
1006	function format_to_edit($content, $richedit = false) {
1007	$content = apply_filters('format_to_edit', $content);
1008	if (! $richedit )
1009	$content = htmlspecialchars($content);
1010	return $content;
1011	}
1012
1013	/**
1014	* Holder for the 'format_to_post' filter.
1015	*
1016	* @since 0.71
1017	*
1018	* @param string $content The text to pass through the filter.
1019	* @return string Text returned from the 'format_to_post' filter.
1020	*/
1021	function format_to_post($content) {
1022	$content = apply_filters('format_to_post', $content);
1023	return $content;
1024	}
1025
1026	/**
1027	* Add leading zeros when necessary.
1028	*
1029	* If you set the threshold to '4' and the number is '10', then you will get
1030	* back '0010'. If you set the number to '4' and the number is '5000', then you
1031	* will get back '5000'.
1032	*
1033	* Uses sprintf to append the amount of zeros based on the $threshold parameter
1034	* and the size of the number. If the number is large enough, then no zeros will
1035	* be appended.
1036	*
1037	* @since 0.71
1038	*
1039	* @param mixed $number Number to append zeros to if not greater than threshold.
1040	* @param int $threshold Digit places number needs to be to not have zeros added.
1041	* @return string Adds leading zeros to number if needed.
1042	*/
1043	function zeroise($number, $threshold) {
1044	return sprintf('%0'.$threshold.'s', $number);
1045	}
1046
1047	/**
1048	* Adds backslashes before letters and before a number at the start of a string.
1049	*
1050	* @since 0.71
1051	*
1052	* @param string $string Value to which backslashes will be added.
1053	* @return string String with backslashes inserted.
1054	*/
1055	function backslashit($string) {
1056	$string = preg_replace('/^([0-9])/', '\\\\\\\\\1', $string);
1057	$string = preg_replace('/([a-z])/i', '\\\\\1', $string);
1058	return $string;
1059	}
1060
1061	/**
1062	* Appends a trailing slash.
1063	*
1064	* Will remove trailing slash if it exists already before adding a trailing
1065	* slash. This prevents double slashing a string or path.
1066	*
1067	* The primary use of this is for paths and thus should be used for paths. It is
1068	* not restricted to paths and offers no specific path support.
1069	*
1070	* @since 1.2.0
1071	* @uses untrailingslashit() Unslashes string if it was slashed already.
1072	*
1073	* @param string $string What to add the trailing slash to.
1074	* @return string String with trailing slash added.
1075	*/
1076	function trailingslashit($string) {
1077	return untrailingslashit($string) . '/';
1078	}
1079
1080	/**
1081	* Removes trailing slash if it exists.
1082	*
1083	* The primary use of this is for paths and thus should be used for paths. It is
1084	* not restricted to paths and offers no specific path support.
1085	*
1086	* @since 2.2.0
1087	*
1088	* @param string $string What to remove the trailing slash from.
1089	* @return string String without the trailing slash.
1090	*/
1091	function untrailingslashit($string) {
1092	return rtrim($string, '/');
1093	}
1094
1095	/**
1096	* Adds slashes to escape strings.
1097	*
1098	* Slashes will first be removed if magic_quotes_gpc is set, see {@link
1099	* http://www.php.net/magic_quotes} for more details.
1100	*
1101	* @since 0.71
1102	*
1103	* @param string $gpc The string returned from HTTP request data.
1104	* @return string Returns a string escaped with slashes.
1105	*/
1106	function addslashes_gpc($gpc) {
1107	global $wpdb;
1108
1109	if (get_magic_quotes_gpc()) {
1110	$gpc = stripslashes($gpc);
1111	}
1112
1113	return $wpdb->escape($gpc);
1114	}
1115
1116	/**
1117	* Navigates through an array and removes slashes from the values.
1118	*
1119	* If an array is passed, the array_map() function causes a callback to pass the
1120	* value back to the function. The slashes from this value will removed.
1121	*
1122	* @since 2.0.0
1123	*
1124	* @param array\|string $value The array or string to be striped.
1125	* @return array\|string Stripped array (or string in the callback).
1126	*/
1127	function stripslashes_deep($value) {
1128	$value = is_array($value) ? array_map('stripslashes_deep', $value) : stripslashes($value);
1129	return $value;
1130	}
1131
1132	/**
1133	* Navigates through an array and encodes the values to be used in a URL.
1134	*
1135	* Uses a callback to pass the value of the array back to the function as a
1136	* string.
1137	*
1138	* @since 2.2.0
1139	*
1140	* @param array\|string $value The array or string to be encoded.
1141	* @return array\|string $value The encoded array (or string from the callback).
1142	*/
1143	function urlencode_deep($value) {
1144	$value = is_array($value) ? array_map('urlencode_deep', $value) : urlencode($value);
1145	return $value;
1146	}
1147
1148	/**
1149	* Converts email addresses characters to HTML entities to block spam bots.
1150	*
1151	* @since 0.71
1152	*
1153	* @param string $emailaddy Email address.
1154	* @param int $mailto Optional. Range from 0 to 1. Used for encoding.
1155	* @return string Converted email address.
1156	*/
1157	function antispambot($emailaddy, $mailto=0) {
1158	$emailNOSPAMaddy = '';
1159	srand ((float) microtime() * 1000000);
1160	for ($i = 0; $i < strlen($emailaddy); $i = $i + 1) {
1161	$j = floor(rand(0, 1+$mailto));
1162	if ($j==0) {
1163	$emailNOSPAMaddy .= '&#'.ord(substr($emailaddy,$i,1)).';';
1164	} elseif ($j==1) {
1165	$emailNOSPAMaddy .= substr($emailaddy,$i,1);
1166	} elseif ($j==2) {
1167	$emailNOSPAMaddy .= '%'.zeroise(dechex(ord(substr($emailaddy, $i, 1))), 2);
1168	}
1169	}
1170	$emailNOSPAMaddy = str_replace('@','@',$emailNOSPAMaddy);
1171	return $emailNOSPAMaddy;
1172	}
1173
1174	/**
1175	* Callback to convert URI match to HTML A element.
1176	*
1177	* This function was backported from 2.5.0 to 2.3.2. Regex callback for {@link
1178	* make_clickable()}.
1179	*
1180	* @since 2.3.2
1181	* @access private
1182	*
1183	* @param array $matches Single Regex Match.
1184	* @return string HTML A element with URI address.
1185	*/
1186	function _make_url_clickable_cb($matches) {
1187	$url = $matches[2];
1188	$url = esc_url($url);
1189	if ( empty($url) )
1190	return $matches[0];
1191	return $matches[1] . "<a href=\"$url\" rel=\"nofollow\">$url</a>";
1192	}
1193
1194	/**
1195	* Callback to convert URL match to HTML A element.
1196	*
1197	* This function was backported from 2.5.0 to 2.3.2. Regex callback for {@link
1198	* make_clickable()}.
1199	*
1200	* @since 2.3.2
1201	* @access private
1202	*
1203	* @param array $matches Single Regex Match.
1204	* @return string HTML A element with URL address.
1205	*/
1206	function _make_web_ftp_clickable_cb($matches) {
1207	$ret = '';
1208	$dest = $matches[2];
1209	$dest = 'http://' . $dest;
1210	$dest = esc_url($dest);
1211	if ( empty($dest) )
1212	return $matches[0];
1213	// removed trailing [,;:] from URL
1214	if ( in_array(substr($dest, -1), array('.', ',', ';', ':')) === true ) {
1215	$ret = substr($dest, -1);
1216	$dest = substr($dest, 0, strlen($dest)-1);
1217	}
1218	return $matches[1] . "<a href=\"$dest\" rel=\"nofollow\">$dest</a>" . $ret;
1219	}
1220
1221	/**
1222	* Callback to convert email address match to HTML A element.
1223	*
1224	* This function was backported from 2.5.0 to 2.3.2. Regex callback for {@link
1225	* make_clickable()}.
1226	*
1227	* @since 2.3.2
1228	* @access private
1229	*
1230	* @param array $matches Single Regex Match.
1231	* @return string HTML A element with email address.
1232	*/
1233	function _make_email_clickable_cb($matches) {
1234	$email = $matches[2] . '@' . $matches[3];
1235	return $matches[1] . "<a href=\"mailto:$email\">$email</a>";
1236	}
1237
1238	/**
1239	* Convert plaintext URI to HTML links.
1240	*
1241	* Converts URI, www and ftp, and email addresses. Finishes by fixing links
1242	* within links.
1243	*
1244	* @since 0.71
1245	*
1246	* @param string $ret Content to convert URIs.
1247	* @return string Content with converted URIs.
1248	*/
1249	function make_clickable($ret) {
1250	$ret = ' ' . $ret;
1251	// in testing, using arrays here was found to be faster
1252	$ret = preg_replace_callback('#(?<=[\s>])($)?([\w]+?://(?:[\w\\x80-\\xff\#$%&~/\-=?@\[\](+]\|[.,;:](?![\s<])\|(?(1)$(?![\s<])\|\)))+)#is', '_make_url_clickable_cb', $ret);
1253	$ret = preg_replace_callback('#([\s>])((www\|ftp)\.[\w\\x80-\\xff\#$%&~/.\-;:=,?@\[\]+]+)#is', '_make_web_ftp_clickable_cb', $ret);
1254	$ret = preg_replace_callback('#([\s>])([.0-9a-z_+-]+)@(([0-9a-z-]+\.)+[0-9a-z]{2,})#i', '_make_email_clickable_cb', $ret);
1255	// this one is not in an array because we need it to run last, for cleanup of accidental links within links
1256	$ret = preg_replace("#(<a( [^>]+?>\|>))<a [^>]+?>([^>]+?)</a></a>#i", "$1$3</a>", $ret);
1257	$ret = trim($ret);
1258	return $ret;
1259	}
1260
1261	/**
1262	* Adds rel nofollow string to all HTML A elements in content.
1263	*
1264	* @since 1.5.0
1265	*
1266	* @param string $text Content that may contain HTML A elements.
1267	* @return string Converted content.
1268	*/
1269	function wp_rel_nofollow( $text ) {
1270	global $wpdb;
1271	// This is a pre save filter, so text is already escaped.
1272	$text = stripslashes($text);
1273	$text = preg_replace_callback('\|<a (.+?)>\|i', 'wp_rel_nofollow_callback', $text);
1274	$text = $wpdb->escape($text);
1275	return $text;
1276	}
1277
1278	/**
1279	* Callback to used to add rel=nofollow string to HTML A element.
1280	*
1281	* Will remove already existing rel="nofollow" and rel='nofollow' from the
1282	* string to prevent from invalidating (X)HTML.
1283	*
1284	* @since 2.3.0
1285	*
1286	* @param array $matches Single Match
1287	* @return string HTML A Element with rel nofollow.
1288	*/
1289	function wp_rel_nofollow_callback( $matches ) {
1290	$text = $matches[1];
1291	$text = str_replace(array(' rel="nofollow"', " rel='nofollow'"), '', $text);
1292	return "<a $text rel=\"nofollow\">";
1293	}
1294
1295
1296	/**
1297	* Convert one smiley code to the icon graphic file equivalent.
1298	*
1299	* Looks up one smiley code in the $wpsmiliestrans global array and returns an
1300	* <img> string for that smiley.
1301	*
1302	* @global array $wpsmiliestrans
1303	* @since 2.8.0
1304	*
1305	* @param string $smiley Smiley code to convert to image.
1306	* @return string Image string for smiley.
1307	*/
1308	function translate_smiley($smiley) {
1309	global $wpsmiliestrans;
1310
1311	if (count($smiley) == 0) {
1312	return '';
1313	}
1314
1315	$siteurl = get_option( 'siteurl' );
1316
1317	$smiley = trim(reset($smiley));
1318	$img = $wpsmiliestrans[$smiley];
1319	$smiley_masked = esc_attr($smiley);
1320
1321	return " <img src='$siteurl/wp-includes/images/smilies/$img' alt='$smiley_masked' class='wp-smiley' /> ";
1322	}
1323
1324
1325	/**
1326	* Convert text equivalent of smilies to images.
1327	*
1328	* Will only convert smilies if the option 'use_smilies' is true and the global
1329	* used in the function isn't empty.
1330	*
1331	* @since 0.71
1332	* @uses $wp_smiliessearch
1333	*
1334	* @param string $text Content to convert smilies from text.
1335	* @return string Converted content with text smilies replaced with images.
1336	*/
1337	function convert_smilies($text) {
1338	global $wp_smiliessearch;
1339	$output = '';
1340	if ( get_option('use_smilies') && !empty($wp_smiliessearch) ) {
1341	// HTML loop taken from texturize function, could possible be consolidated
1342	$textarr = preg_split("/(<.*>)/U", $text, -1, PREG_SPLIT_DELIM_CAPTURE); // capture the tags as well as in between
1343	$stop = count($textarr);// loop stuff
1344	for ($i = 0; $i < $stop; $i++) {
1345	$content = $textarr[$i];
1346	if ((strlen($content) > 0) && ('<' != $content{0})) { // If it's not a tag
1347	$content = preg_replace_callback($wp_smiliessearch, 'translate_smiley', $content);
1348	}
1349	$output .= $content;
1350	}
1351	} else {
1352	// return default text.
1353	$output = $text;
1354	}
1355	return $output;
1356	}
1357
1358	/**
1359	* Verifies that an email is valid.
1360	*
1361	* Does not grok i18n domains. Not RFC compliant.
1362	*
1363	* @since 0.71
1364	*
1365	* @param string $email Email address to verify.
1366	* @param boolean $check_dns Whether to check the DNS for the domain using checkdnsrr().
1367	* @return string\|bool Either false or the valid email address.
1368	*/
1369	function is_email( $email, $check_dns = false ) {
1370	// Test for the minimum length the email can be
1371	if ( strlen( $email ) < 3 ) {
1372	return apply_filters( 'is_email', false, $email, 'email_too_short' );
1373	}
1374
1375	// Test for an @ character after the first position
1376	if ( strpos( $email, '@', 1 ) === false ) {
1377	return apply_filters( 'is_email', false, $email, 'email_no_at' );
1378	}
1379
1380	// Split out the local and domain parts
1381	list( $local, $domain ) = explode( '@', $email, 2 );
1382
1383	// LOCAL PART
1384	// Test for invalid characters
1385	if ( !preg_match( '/^[a-zA-Z0-9!#$%&\'*+\/=?^_`{\|}~\.-]+$/', $local ) ) {
1386	return apply_filters( 'is_email', false, $email, 'local_invalid_chars' );
1387	}
1388
1389	// DOMAIN PART
1390	// Test for sequences of periods
1391	if ( preg_match( '/\.{2,}/', $domain ) ) {
1392	return apply_filters( 'is_email', false, $email, 'domain_period_sequence' );
1393	}
1394
1395	// Test for leading and trailing periods and whitespace
1396	if ( trim( $domain, " \t\n\r\0\x0B." ) !== $domain ) {
1397	return apply_filters( 'is_email', false, $email, 'domain_period_limits' );
1398	}
1399
1400	// Split the domain into subs
1401	$subs = explode( '.', $domain );
1402
1403	// Assume the domain will have at least two subs
1404	if ( 2 > count( $subs ) ) {
1405	return apply_filters( 'is_email', false, $email, 'domain_no_periods' );
1406	}
1407
1408	// Loop through each sub
1409	foreach ( $subs as $sub ) {
1410	// Test for leading and trailing hyphens and whitespace
1411	if ( trim( $sub, " \t\n\r\0\x0B-" ) !== $sub ) {
1412	return apply_filters( 'is_email', false, $email, 'sub_hyphen_limits' );
1413	}
1414
1415	// Test for invalid characters
1416	if ( !preg_match('/^[a-z0-9-]+$/i', $sub ) ) {
1417	return apply_filters( 'is_email', false, $email, 'sub_invalid_chars' );
1418	}
1419	}
1420
1421	// DNS
1422	// Check the domain has a valid MX and A resource record
1423	if ( $check_dns && function_exists( 'checkdnsrr' ) && !( checkdnsrr( $domain . '.', 'MX' ) \|\| checkdnsrr( $domain . '.', 'A' ) ) ) {
1424	return apply_filters( 'is_email', false, $email, 'dns_no_rr' );
1425	}
1426
1427	// Congratulations your email made it!
1428	return apply_filters( 'is_email', $email, $email, null );
1429	}
1430
1431	/**
1432	* Convert to ASCII from email subjects.
1433	*
1434	* @since 1.2.0
1435	* @usedby wp_mail() handles charsets in email subjects
1436	*
1437	* @param string $string Subject line
1438	* @return string Converted string to ASCII
1439	*/
1440	function wp_iso_descrambler($string) {
1441	/* this may only work with iso-8859-1, I'm afraid */
1442	if (!preg_match('#\=\?(.+)\?Q\?(.+)\?\=#i', $string, $matches)) {
1443	return $string;
1444	} else {
1445	$subject = str_replace('_', ' ', $matches[2]);
1446	$subject = preg_replace_callback('#\=([0-9a-f]{2})#i', create_function('$match', 'return chr(hexdec(strtolower($match[1])));'), $subject);
1447	return $subject;
1448	}
1449	}
1450
1451	/**
1452	* Returns a date in the GMT equivalent.
1453	*
1454	* Requires and returns a date in the Y-m-d H:i:s format. Simply subtracts the
1455	* value of the 'gmt_offset' option.
1456	*
1457	* @since 1.2.0
1458	*
1459	* @uses get_option() to retrieve the the value of 'gmt_offset'.
1460	* @param string $string The date to be converted.
1461	* @return string GMT version of the date provided.
1462	*/
1463	function get_gmt_from_date($string) {
1464	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);
1465	$string_time = gmmktime($matches[4], $matches[5], $matches[6], $matches[2], $matches[3], $matches[1]);
1466	$string_gmt = gmdate('Y-m-d H:i:s', $string_time - get_option('gmt_offset') * 3600);
1467	return $string_gmt;
1468	}
1469
1470	/**
1471	* Converts a GMT date into the correct format for the blog.
1472	*
1473	* Requires and returns in the Y-m-d H:i:s format. Simply adds the value of
1474	* gmt_offset.
1475	*
1476	* @since 1.2.0
1477	*
1478	* @param string $string The date to be converted.
1479	* @return string Formatted date relative to the GMT offset.
1480	*/
1481	function get_date_from_gmt($string) {
1482	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);
1483	$string_time = gmmktime($matches[4], $matches[5], $matches[6], $matches[2], $matches[3], $matches[1]);
1484	$string_localtime = gmdate('Y-m-d H:i:s', $string_time + get_option('gmt_offset')*3600);
1485	return $string_localtime;
1486	}
1487
1488	/**
1489	* Computes an offset in seconds from an iso8601 timezone.
1490	*
1491	* @since 1.5.0
1492	*
1493	* @param string $timezone Either 'Z' for 0 offset or '±hhmm'.
1494	* @return int\|float The offset in seconds.
1495	*/
1496	function iso8601_timezone_to_offset($timezone) {
1497	// $timezone is either 'Z' or '[+\|-]hhmm'
1498	if ($timezone == 'Z') {
1499	$offset = 0;
1500	} else {
1501	$sign = (substr($timezone, 0, 1) == '+') ? 1 : -1;
1502	$hours = intval(substr($timezone, 1, 2));
1503	$minutes = intval(substr($timezone, 3, 4)) / 60;
1504	$offset = $sign * 3600 * ($hours + $minutes);
1505	}
1506	return $offset;
1507	}
1508
1509	/**
1510	* Converts an iso8601 date to MySQL DateTime format used by post_date[_gmt].
1511	*
1512	* @since 1.5.0
1513	*
1514	* @param string $date_string Date and time in ISO 8601 format {@link http://en.wikipedia.org/wiki/ISO_8601}.
1515	* @param string $timezone Optional. If set to GMT returns the time minus gmt_offset. Default is 'user'.
1516	* @return string The date and time in MySQL DateTime format - Y-m-d H:i:s.
1517	*/
1518	function iso8601_to_datetime($date_string, $timezone = 'user') {
1519	$timezone = strtolower($timezone);
1520
1521	if ($timezone == 'gmt') {
1522
1523	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, $date_bits);
1524
1525	if (!empty($date_bits[7])) { // we have a timezone, so let's compute an offset
1526	$offset = iso8601_timezone_to_offset($date_bits[7]);
1527	} else { // we don't have a timezone, so we assume user local timezone (not server's!)
1528	$offset = 3600 * get_option('gmt_offset');
1529	}
1530
1531	$timestamp = gmmktime($date_bits[4], $date_bits[5], $date_bits[6], $date_bits[2], $date_bits[3], $date_bits[1]);
1532	$timestamp -= $offset;
1533
1534	return gmdate('Y-m-d H:i:s', $timestamp);
1535
1536	} else if ($timezone == 'user') {
1537	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);
1538	}
1539	}
1540
1541	/**
1542	* Adds a element attributes to open links in new windows.
1543	*
1544	* Comment text in popup windows should be filtered through this. Right now it's
1545	* a moderately dumb function, ideally it would detect whether a target or rel
1546	* attribute was already there and adjust its actions accordingly.
1547	*
1548	* @since 0.71
1549	*
1550	* @param string $text Content to replace links to open in a new window.
1551	* @return string Content that has filtered links.
1552	*/
1553	function popuplinks($text) {
1554	$text = preg_replace('/<a (.+?)>/i', "<a $1 target='_blank' rel='external'>", $text);
1555	return $text;
1556	}
1557
1558	/**
1559	* Strips out all characters that are not allowable in an email.
1560	*
1561	* @since 1.5.0
1562	*
1563	* @param string $email Email address to filter.
1564	* @return string Filtered email address.
1565	*/
1566	function sanitize_email( $email ) {
1567	// Test for the minimum length the email can be
1568	if ( strlen( $email ) < 3 ) {
1569	return apply_filters( 'sanitize_email', '', $email, 'email_too_short' );
1570	}
1571
1572	// Test for an @ character after the first position
1573	if ( strpos( $email, '@', 1 ) === false ) {
1574	return apply_filters( 'sanitize_email', '', $email, 'email_no_at' );
1575	}
1576
1577	// Split out the local and domain parts
1578	list( $local, $domain ) = explode( '@', $email, 2 );
1579
1580	// LOCAL PART
1581	// Test for invalid characters
1582	$local = preg_replace( '/[^a-zA-Z0-9!#$%&\'*+\/=?^_`{\|}~\.-]/', '', $local );
1583	if ( '' === $local ) {
1584	return apply_filters( 'sanitize_email', '', $email, 'local_invalid_chars' );
1585	}
1586
1587	// DOMAIN PART
1588	// Test for sequences of periods
1589	$domain = preg_replace( '/\.{2,}/', '', $domain );
1590	if ( '' === $domain ) {
1591	return apply_filters( 'sanitize_email', '', $email, 'domain_period_sequence' );
1592	}
1593
1594	// Test for leading and trailing periods and whitespace
1595	$domain = trim( $domain, " \t\n\r\0\x0B." );
1596	if ( '' === $domain ) {
1597	return apply_filters( 'sanitize_email', '', $email, 'domain_period_limits' );
1598	}
1599
1600	// Split the domain into subs
1601	$subs = explode( '.', $domain );
1602
1603	// Assume the domain will have at least two subs
1604	if ( 2 > count( $subs ) ) {
1605	return apply_filters( 'sanitize_email', '', $email, 'domain_no_periods' );
1606	}
1607
1608	// Create an array that will contain valid subs
1609	$new_subs = array();
1610
1611	// Loop through each sub
1612	foreach ( $subs as $sub ) {
1613	// Test for leading and trailing hyphens
1614	$sub = trim( $sub, " \t\n\r\0\x0B-" );
1615
1616	// Test for invalid characters
1617	$sub = preg_replace( '/^[^a-z0-9-]+$/i', '', $sub );
1618
1619	// If there's anything left, add it to the valid subs
1620	if ( '' !== $sub ) {
1621	$new_subs[] = $sub;
1622	}
1623	}
1624
1625	// If there aren't 2 or more valid subs
1626	if ( 2 > count( $new_subs ) ) {
1627	return apply_filters( 'sanitize_email', '', $email, 'domain_no_valid_subs' );
1628	}
1629
1630	// Join valid subs into the new domain
1631	$domain = join( '.', $new_subs );
1632
1633	// Put the email back together
1634	$email = $local . '@' . $domain;
1635
1636	// Congratulations your email made it!
1637	return apply_filters( 'sanitize_email', $email, $email, null );
1638	}
1639
1640	/**
1641	* Determines the difference between two timestamps.
1642	*
1643	* The difference is returned in a human readable format such as "1 hour",
1644	* "5 mins", "2 days".
1645	*
1646	* @since 1.5.0
1647	*
1648	* @param int $from Unix timestamp from which the difference begins.
1649	* @param int $to Optional. Unix timestamp to end the time difference. Default becomes time() if not set.
1650	* @return string Human readable time difference.
1651	*/
1652	function human_time_diff( $from, $to = '' ) {
1653	if ( empty($to) )
1654	$to = time();
1655	$diff = (int) abs($to - $from);
1656	if ($diff <= 3600) {
1657	$mins = round($diff / 60);
1658	if ($mins <= 1) {
1659	$mins = 1;
1660	}
1661	$since = sprintf(_n('%s min', '%s mins', $mins), $mins);
1662	} else if (($diff <= 86400) && ($diff > 3600)) {
1663	$hours = round($diff / 3600);
1664	if ($hours <= 1) {
1665	$hours = 1;
1666	}
1667	$since = sprintf(_n('%s hour', '%s hours', $hours), $hours);
1668	} elseif ($diff >= 86400) {
1669	$days = round($diff / 86400);
1670	if ($days <= 1) {
1671	$days = 1;
1672	}
1673	$since = sprintf(_n('%s day', '%s days', $days), $days);
1674	}
1675	return $since;
1676	}
1677
1678	/**
1679	* Generates an excerpt from the content, if needed.
1680	*
1681	* The excerpt word amount will be 55 words and if the amount is greater than
1682	* that, then the string '[...]' will be appended to the excerpt. If the string
1683	* is less than 55 words, then the content will be returned as is.
1684	*
1685	* @since 1.5.0
1686	*
1687	* @param string $text The exerpt. If set to empty an excerpt is generated.
1688	* @return string The excerpt.
1689	*/
1690	function wp_trim_excerpt($text) {
1691	$raw_excerpt = $text;
1692	if ( '' == $text ) {
1693	$text = get_the_content('');
1694
1695	$text = strip_shortcodes( $text );
1696
1697	$text = apply_filters('the_content', $text);
1698	$text = str_replace(']]>', ']]>', $text);
1699	$text = strip_tags($text);
1700	$excerpt_length = apply_filters('excerpt_length', 55);
1701	$words = explode(' ', $text, $excerpt_length + 1);
1702	if (count($words) > $excerpt_length) {
1703	array_pop($words);
1704	array_push($words, '[...]');
1705	$text = implode(' ', $words);
1706	}
1707	}
1708	return apply_filters('wp_trim_excerpt', $text, $raw_excerpt);
1709	}
1710
1711	/**
1712	* Converts named entities into numbered entities.
1713	*
1714	* @since 1.5.1
1715	*
1716	* @param string $text The text within which entities will be converted.
1717	* @return string Text with converted entities.
1718	*/
1719	function ent2ncr($text) {
1720	$to_ncr = array(
1721	'"' => '"',
1722	'&' => '&',
1723	'&frasl;' => '/',
1724	'<' => '<',
1725	'>' => '>',
1726	'\|' => '\|',
1727	' ' => ' ',
1728	'¡' => '¡',
1729	'¢' => '¢',
1730	'£' => '£',
1731	'¤' => '¤',
1732	'¥' => '¥',
1733	'¦' => '¦',
1734	'&brkbar;' => '¦',
1735	'§' => '§',
1736	'¨' => '¨',
1737	'&die;' => '¨',
1738	'©' => '©',
1739	'ª' => 'ª',
1740	'«' => '«',
1741	'¬' => '¬',
1742	'' => '',
1743	'®' => '®',
1744	'¯' => '¯',
1745	'&hibar;' => '¯',
1746	'°' => '°',
1747	'±' => '±',
1748	'²' => '²',
1749	'³' => '³',
1750	'´' => '´',
1751	'µ' => 'µ',
1752	'¶' => '¶',
1753	'·' => '·',
1754	'¸' => '¸',
1755	'¹' => '¹',
1756	'º' => 'º',
1757	'»' => '»',
1758	'¼' => '¼',
1759	'½' => '½',
1760	'¾' => '¾',
1761	'¿' => '¿',
1762	'À' => 'À',
1763	'Á' => 'Á',
1764	'Â' => 'Â',
1765	'Ã' => 'Ã',
1766	'Ä' => 'Ä',
1767	'Å' => 'Å',
1768	'Æ' => 'Æ',
1769	'Ç' => 'Ç',
1770	'È' => 'È',
1771	'É' => 'É',
1772	'Ê' => 'Ê',
1773	'Ë' => 'Ë',
1774	'Ì' => 'Ì',
1775	'Í' => 'Í',
1776	'Î' => 'Î',
1777	'Ï' => 'Ï',
1778	'Ð' => 'Ð',
1779	'Ñ' => 'Ñ',
1780	'Ò' => 'Ò',
1781	'Ó' => 'Ó',
1782	'Ô' => 'Ô',
1783	'Õ' => 'Õ',
1784	'Ö' => 'Ö',
1785	'×' => '×',
1786	'Ø' => 'Ø',
1787	'Ù' => 'Ù',
1788	'Ú' => 'Ú',
1789	'Û' => 'Û',
1790	'Ü' => 'Ü',
1791	'Ý' => 'Ý',
1792	'Þ' => 'Þ',
1793	'ß' => 'ß',
1794	'à' => 'à',
1795	'á' => 'á',
1796	'â' => 'â',
1797	'ã' => 'ã',
1798	'ä' => 'ä',
1799	'å' => 'å',
1800	'æ' => 'æ',
1801	'ç' => 'ç',
1802	'è' => 'è',
1803	'é' => 'é',
1804	'ê' => 'ê',
1805	'ë' => 'ë',
1806	'ì' => 'ì',
1807	'í' => 'í',
1808	'î' => 'î',
1809	'ï' => 'ï',
1810	'ð' => 'ð',
1811	'ñ' => 'ñ',
1812	'ò' => 'ò',
1813	'ó' => 'ó',
1814	'ô' => 'ô',
1815	'õ' => 'õ',
1816	'ö' => 'ö',
1817	'÷' => '÷',
1818	'ø' => 'ø',
1819	'ù' => 'ù',
1820	'ú' => 'ú',
1821	'û' => 'û',
1822	'ü' => 'ü',
1823	'ý' => 'ý',
1824	'þ' => 'þ',
1825	'ÿ' => 'ÿ',
1826	'&OElig;' => 'Œ',
1827	'&oelig;' => 'œ',
1828	'&Scaron;' => 'Š',
1829	'&scaron;' => 'š',
1830	'&Yuml;' => 'Ÿ',
1831	'&fnof;' => 'ƒ',
1832	'&circ;' => 'ˆ',
1833	'&tilde;' => '˜',
1834	'Α' => 'Α',
1835	'Β' => 'Β',
1836	'Γ' => 'Γ',
1837	'Δ' => 'Δ',
1838	'Ε' => 'Ε',
1839	'Ζ' => 'Ζ',
1840	'Η' => 'Η',
1841	'Θ' => 'Θ',
1842	'Ι' => 'Ι',
1843	'Κ' => 'Κ',
1844	'Λ' => 'Λ',
1845	'Μ' => 'Μ',
1846	'Ν' => 'Ν',
1847	'Ξ' => 'Ξ',
1848	'Ο' => 'Ο',
1849	'Π' => 'Π',
1850	'Ρ' => 'Ρ',
1851	'Σ' => 'Σ',
1852	'Τ' => 'Τ',
1853	'Υ' => 'Υ',
1854	'Φ' => 'Φ',
1855	'Χ' => 'Χ',
1856	'Ψ' => 'Ψ',
1857	'Ω' => 'Ω',
1858	'α' => 'α',
1859	'β' => 'β',
1860	'γ' => 'γ',
1861	'δ' => 'δ',
1862	'ε' => 'ε',
1863	'ζ' => 'ζ',
1864	'η' => 'η',
1865	'θ' => 'θ',
1866	'ι' => 'ι',
1867	'κ' => 'κ',
1868	'λ' => 'λ',
1869	'μ' => 'μ',
1870	'ν' => 'ν',
1871	'ξ' => 'ξ',
1872	'ο' => 'ο',
1873	'π' => 'π',
1874	'ρ' => 'ρ',
1875	'&sigmaf;' => 'ς',
1876	'σ' => 'σ',
1877	'τ' => 'τ',
1878	'υ' => 'υ',
1879	'φ' => 'φ',
1880	'χ' => 'χ',
1881	'ψ' => 'ψ',
1882	'ω' => 'ω',
1883	'&thetasym;' => 'ϑ',
1884	'&upsih;'