Context Navigation

Back to Ticket #40135

Ticket #40135: formatting.php

File formatting.php, 285.8 KB (added by ayubi, 7 years ago)

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	*
15	* 'cause today's effort makes it worth tomorrow's "holiday" ...
16	*
17	* Becomes:
18	*
19	* ’cause today’s effort makes it worth tomorrow’s “holiday” …
20	*
21	* Code within certain html blocks are skipped.
22	*
23	* Do not use this function before the {@see 'init'} action hook; everything will break.
24	*
25	* @since 0.71
26	*
27	* @global array $wp_cockneyreplace Array of formatted entities for certain common phrases
28	* @global array $shortcode_tags
29	* @staticvar array $static_characters
30	* @staticvar array $static_replacements
31	* @staticvar array $dynamic_characters
32	* @staticvar array $dynamic_replacements
33	* @staticvar array $default_no_texturize_tags
34	* @staticvar array $default_no_texturize_shortcodes
35	* @staticvar bool $run_texturize
36	* @staticvar string $apos
37	* @staticvar string $prime
38	* @staticvar string $double_prime
39	* @staticvar string $opening_quote
40	* @staticvar string $closing_quote
41	* @staticvar string $opening_single_quote
42	* @staticvar string $closing_single_quote
43	* @staticvar string $open_q_flag
44	* @staticvar string $open_sq_flag
45	* @staticvar string $apos_flag
46	*
47	* @param string $text The text to be formatted
48	* @param bool $reset Set to true for unit testing. Translated patterns will reset.
49	* @return string The string replaced with html entities
50	*/
51	function wptexturize($text, $reset = false)
52	{
53	global $wp_cockneyreplace, $shortcode_tags;
54	static $static_characters = null,
55	$static_replacements = null,
56	$dynamic_characters = null,
57	$dynamic_replacements = null,
58	$default_no_texturize_tags = null,
59	$default_no_texturize_shortcodes = null,
60	$run_texturize = true,
61	$apos = null,
62	$prime = null,
63	$double_prime = null,
64	$opening_quote = null,
65	$closing_quote = null,
66	$opening_single_quote = null,
67	$closing_single_quote = null,
68	$open_q_flag = '<!--oq-->',
69	$open_sq_flag = '<!--osq-->',
70	$apos_flag = '<!--apos-->';
71
72	// If there's nothing to do, just stop.
73	if (empty($text) \|\| false === $run_texturize) {
74	return $text;
75	}
76
77	// Set up static variables. Run once only.
78	if ($reset \|\| ! isset($static_characters)) {
79	/**
80	* Filters whether to skip running wptexturize().
81	*
82	* Passing false to the filter will effectively short-circuit wptexturize().
83	* returning the original text passed to the function instead.
84	*
85	* The filter runs only once, the first time wptexturize() is called.
86	*
87	* @since 4.0.0
88	*
89	* @see wptexturize()
90	*
91	* @param bool $run_texturize Whether to short-circuit wptexturize().
92	*/
93	$run_texturize = apply_filters('run_wptexturize', $run_texturize);
94	if (false === $run_texturize) {
95	return $text;
96	}
97
98	/* translators: opening curly double quote */
99	$opening_quote = _x('“', 'opening curly double quote');
100	/* translators: closing curly double quote */
101	$closing_quote = _x('”', 'closing curly double quote');
102
103	/* translators: apostrophe, for example in 'cause or can't */
104	$apos = _x('’', 'apostrophe');
105
106	/* translators: prime, for example in 9' (nine feet) */
107	$prime = _x('′', 'prime');
108	/* translators: double prime, for example in 9" (nine inches) */
109	$double_prime = _x('″', 'double prime');
110
111	/* translators: opening curly single quote */
112	$opening_single_quote = _x('‘', 'opening curly single quote');
113	/* translators: closing curly single quote */
114	$closing_single_quote = _x('’', 'closing curly single quote');
115
116	/* translators: en dash */
117	$en_dash = _x('–', 'en dash');
118	/* translators: em dash */
119	$em_dash = _x('—', 'em dash');
120
121	$default_no_texturize_tags = array( 'pre', 'code', 'kbd', 'style', 'script', 'tt' );
122	$default_no_texturize_shortcodes = array( 'code' );
123
124	// if a plugin has provided an autocorrect array, use it
125	if (isset($wp_cockneyreplace)) {
126	$cockney = array_keys($wp_cockneyreplace);
127	$cockneyreplace = array_values($wp_cockneyreplace);
128	} else {
129	/* translators: This is a comma-separated list of words that defy the syntax of quotations in normal use,
130	* for example... 'We do not have enough words yet' ... is a typical quoted phrase. But when we write
131	* lines of code 'til we have enough of 'em, then we need to insert apostrophes instead of quotes.
132	*/
133	$cockney = explode(
134	',',
135	_x(
136	"'tain't,'twere,'twas,'tis,'twill,'til,'bout,'nuff,'round,'cause,'em",
137	'Comma-separated list of words to texturize in your language'
138	)
139	);
140
141	$cockneyreplace = explode(
142	',',
143	_x(
144	'’tain’t,’twere,’twas,’tis,’twill,’til,’bout,’nuff,’round,’cause,’em',
145	'Comma-separated list of replacement words in your language'
146	)
147	);
148	}
149
150	$static_characters = array_merge(array( '...', '``', '\'\'', ' (tm)' ), $cockney);
151	$static_replacements = array_merge(array( '…', $opening_quote, $closing_quote, ' ™' ), $cockneyreplace);
152
153	// Pattern-based replacements of characters.
154	// Sort the remaining patterns into several arrays for performance tuning.
155	$dynamic_characters = array(
156	'apos' => array(),
157	'quote' => array(),
158	'dash' => array(),
159	);
160	$dynamic_replacements = array(
161	'apos' => array(),
162	'quote' => array(),
163	'dash' => array(),
164	);
165	$dynamic = array();
166	$spaces = wp_spaces_regexp();
167
168	// '99' and '99" are ambiguous among other patterns; assume it's an abbreviated year at the end of a quotation.
169	if ("'" !== $apos \|\| "'" !== $closing_single_quote) {
170	$dynamic[ '/\'(\d\d)\'(?=\Z\|[.,:;!?)}\-\]]\|>\|' . $spaces . ')/' ] = $apos_flag . '$1' . $closing_single_quote;
171	}
172	if ("'" !== $apos \|\| '"' !== $closing_quote) {
173	$dynamic[ '/\'(\d\d)"(?=\Z\|[.,:;!?)}\-\]]\|>\|' . $spaces . ')/' ] = $apos_flag . '$1' . $closing_quote;
174	}
175
176	// '99 '99s '99's (apostrophe) But never '9 or '99% or '999 or '99.0.
177	if ("'" !== $apos) {
178	$dynamic['/\'(?=\d\d(?:\Z\|(?![%\d]\|[.,]\d)))/'] = $apos_flag;
179	}
180
181	// Quoted Numbers like '0.42'
182	if ("'" !== $opening_single_quote && "'" !== $closing_single_quote) {
183	$dynamic[ '/(?<=\A\|' . $spaces . ')\'(\d[.,\d]*)\'/' ] = $open_sq_flag . '$1' . $closing_single_quote;
184	}
185
186	// Single quote at start, or preceded by (, {, <, [, ", -, or spaces.
187	if ("'" !== $opening_single_quote) {
188	$dynamic[ '/(?<=\A\|[([{"\-]\|<\|' . $spaces . ')\'/' ] = $open_sq_flag;
189	}
190
191	// Apostrophe in a word. No spaces, double apostrophes, or other punctuation.
192	if ("'" !== $apos) {
193	$dynamic[ '/(?<!' . $spaces . ')\'(?!\Z\|[.,:;!?"\'(){}[\]\-]\|&[lg]t;\|' . $spaces . ')/' ] = $apos_flag;
194	}
195
196	$dynamic_characters['apos'] = array_keys($dynamic);
197	$dynamic_replacements['apos'] = array_values($dynamic);
198	$dynamic = array();
199
200	// Quoted Numbers like "42"
201	if ('"' !== $opening_quote && '"' !== $closing_quote) {
202	$dynamic[ '/(?<=\A\|' . $spaces . ')"(\d[.,\d]*)"/' ] = $open_q_flag . '$1' . $closing_quote;
203	}
204
205	// Double quote at start, or preceded by (, {, <, [, -, or spaces, and not followed by spaces.
206	if ('"' !== $opening_quote) {
207	$dynamic[ '/(?<=\A\|[([{\-]\|<\|' . $spaces . ')"(?!' . $spaces . ')/' ] = $open_q_flag;
208	}
209
210	$dynamic_characters['quote'] = array_keys($dynamic);
211	$dynamic_replacements['quote'] = array_values($dynamic);
212	$dynamic = array();
213
214	// Dashes and spaces
215	$dynamic['/---/'] = $em_dash;
216	$dynamic[ '/(?<=^\|' . $spaces . ')--(?=$\|' . $spaces . ')/' ] = $em_dash;
217	$dynamic['/(?<!xn)--/'] = $en_dash;
218	$dynamic[ '/(?<=^\|' . $spaces . ')-(?=$\|' . $spaces . ')/' ] = $en_dash;
219
220	$dynamic_characters['dash'] = array_keys($dynamic);
221	$dynamic_replacements['dash'] = array_values($dynamic);
222	}
223
224	// Must do this every time in case plugins use these filters in a context sensitive manner
225	/**
226	* Filters the list of HTML elements not to texturize.
227	*
228	* @since 2.8.0
229	*
230	* @param array $default_no_texturize_tags An array of HTML element names.
231	*/
232	$no_texturize_tags = apply_filters('no_texturize_tags', $default_no_texturize_tags);
233	/**
234	* Filters the list of shortcodes not to texturize.
235	*
236	* @since 2.8.0
237	*
238	* @param array $default_no_texturize_shortcodes An array of shortcode names.
239	*/
240	$no_texturize_shortcodes = apply_filters('no_texturize_shortcodes', $default_no_texturize_shortcodes);
241
242	$no_texturize_tags_stack = array();
243	$no_texturize_shortcodes_stack = array();
244
245	// Look for shortcodes and HTML elements.
246
247	preg_match_all('@\[/?([^<>&/\[\]\x00-\x20=]++)@', $text, $matches);
248	$tagnames = array_intersect(array_keys($shortcode_tags), $matches[1]);
249	$found_shortcodes = ! empty($tagnames);
250	$shortcode_regex = $found_shortcodes ? _get_wptexturize_shortcode_regex($tagnames) : '';
251	$regex = _get_wptexturize_split_regex($shortcode_regex);
252
253	$textarr = preg_split($regex, $text, -1, PREG_SPLIT_DELIM_CAPTURE \| PREG_SPLIT_NO_EMPTY);
254
255	foreach ($textarr as &$curl) {
256	// Only call _wptexturize_pushpop_element if $curl is a delimiter.
257	$first = $curl[0];
258	if ('<' === $first) {
259	if ('<!--' === substr($curl, 0, 4)) {
260	// This is an HTML comment delimiter.
261	continue;
262	} else {
263	// This is an HTML element delimiter.
264
265	// Replace each & with & unless it already looks like an entity.
266	$curl = preg_replace('/&(?!#(?:\d+\|x[a-f0-9]+);\|[a-z1-4]{1,8};)/i', '&', $curl);
267
268	_wptexturize_pushpop_element($curl, $no_texturize_tags_stack, $no_texturize_tags);
269	}
270	} elseif ('' === trim($curl)) {
271	// This is a newline between delimiters. Performance improves when we check this.
272	continue;
273	} elseif ('[' === $first && $found_shortcodes && 1 === preg_match('/^' . $shortcode_regex . '$/', $curl)) {
274	// This is a shortcode delimiter.
275
276	if ('[[' !== substr($curl, 0, 2) && ']]' !== substr($curl, -2)) {
277	// Looks like a normal shortcode.
278	_wptexturize_pushpop_element($curl, $no_texturize_shortcodes_stack, $no_texturize_shortcodes);
279	} else {
280	// Looks like an escaped shortcode.
281	continue;
282	}
283	} elseif (empty($no_texturize_shortcodes_stack) && empty($no_texturize_tags_stack)) {
284	// This is neither a delimiter, nor is this content inside of no_texturize pairs. Do texturize.
285
286	$curl = str_replace($static_characters, $static_replacements, $curl);
287
288	if (false !== strpos($curl, "'")) {
289	$curl = preg_replace($dynamic_characters['apos'], $dynamic_replacements['apos'], $curl);
290	$curl = wptexturize_primes($curl, "'", $prime, $open_sq_flag, $closing_single_quote);
291	$curl = str_replace($apos_flag, $apos, $curl);
292	$curl = str_replace($open_sq_flag, $opening_single_quote, $curl);
293	}
294	if (false !== strpos($curl, '"')) {
295	$curl = preg_replace($dynamic_characters['quote'], $dynamic_replacements['quote'], $curl);
296	$curl = wptexturize_primes($curl, '"', $double_prime, $open_q_flag, $closing_quote);
297	$curl = str_replace($open_q_flag, $opening_quote, $curl);
298	}
299	if (false !== strpos($curl, '-')) {
300	$curl = preg_replace($dynamic_characters['dash'], $dynamic_replacements['dash'], $curl);
301	}
302
303	// 9x9 (times), but never 0x9999
304	if (1 === preg_match('/(?<=\d)x\d/', $curl)) {
305	// Searching for a digit is 10 times more expensive than for the x, so we avoid doing this one!
306	$curl = preg_replace('/\b(\d(?(?<=0)[\d\.,]+\|[\d\.,]))x(\d[\d\.,])\b/', '$1×$2', $curl);
307	}
308
309	// Replace each & with & unless it already looks like an entity.
310	$curl = preg_replace('/&(?!#(?:\d+\|x[a-f0-9]+);\|[a-z1-4]{1,8};)/i', '&', $curl);
311	}
312	}
313
314	return implode('', $textarr);
315	}
316
317	/**
318	* Implements a logic tree to determine whether or not "7'." represents seven feet,
319	* then converts the special char into either a prime char or a closing quote char.
320	*
321	* @since 4.3.0
322	*
323	* @param string $haystack The plain text to be searched.
324	* @param string $needle The character to search for such as ' or ".
325	* @param string $prime The prime char to use for replacement.
326	* @param string $open_quote The opening quote char. Opening quote replacement must be
327	* accomplished already.
328	* @param string $close_quote The closing quote char to use for replacement.
329	* @return string The $haystack value after primes and quotes replacements.
330	*/
331	function wptexturize_primes($haystack, $needle, $prime, $open_quote, $close_quote)
332	{
333	$spaces = wp_spaces_regexp();
334	$flag = '<!--wp-prime-or-quote-->';
335	$quote_pattern = "/$needle(?=\\Z\|[.,:;!?)}\\-\\]]\|>\|" . $spaces . ')/';
336	$prime_pattern = "/(?<=\\d)$needle/";
337	$flag_after_digit = "/(?<=\\d)$flag/";
338	$flag_no_digit = "/(?<!\\d)$flag/";
339
340	$sentences = explode($open_quote, $haystack);
341
342	foreach ($sentences as $key => &$sentence) {
343	if (false === strpos($sentence, $needle)) {
344	continue;
345	} elseif (0 !== $key && 0 === substr_count($sentence, $close_quote)) {
346	$sentence = preg_replace($quote_pattern, $flag, $sentence, -1, $count);
347	if ($count > 1) {
348	// This sentence appears to have multiple closing quotes. Attempt Vulcan logic.
349	$sentence = preg_replace($flag_no_digit, $close_quote, $sentence, -1, $count2);
350	if (0 === $count2) {
351	// Try looking for a quote followed by a period.
352	$count2 = substr_count($sentence, "$flag.");
353	if ($count2 > 0) {
354	// Assume the rightmost quote-period match is the end of quotation.
355	$pos = strrpos($sentence, "$flag.");
356	} else {
357	// When all else fails, make the rightmost candidate a closing quote.
358	// This is most likely to be problematic in the context of bug #18549.
359	$pos = strrpos($sentence, $flag);
360	}
361	$sentence = substr_replace($sentence, $close_quote, $pos, strlen($flag));
362	}
363	// Use conventional replacement on any remaining primes and quotes.
364	$sentence = preg_replace($prime_pattern, $prime, $sentence);
365	$sentence = preg_replace($flag_after_digit, $prime, $sentence);
366	$sentence = str_replace($flag, $close_quote, $sentence);
367	} elseif (1 == $count) {
368	// Found only one closing quote candidate, so give it priority over primes.
369	$sentence = str_replace($flag, $close_quote, $sentence);
370	$sentence = preg_replace($prime_pattern, $prime, $sentence);
371	} else {
372	// No closing quotes found. Just run primes pattern.
373	$sentence = preg_replace($prime_pattern, $prime, $sentence);
374	}
375	} else {
376	$sentence = preg_replace($prime_pattern, $prime, $sentence);
377	$sentence = preg_replace($quote_pattern, $close_quote, $sentence);
378	}
379	if ('"' == $needle && false !== strpos($sentence, '"')) {
380	$sentence = str_replace('"', $close_quote, $sentence);
381	}
382	}
383
384	return implode($open_quote, $sentences);
385	}
386
387	/**
388	* Search for disabled element tags. Push element to stack on tag open and pop
389	* on tag close.
390	*
391	* Assumes first char of $text is tag opening and last char is tag closing.
392	* Assumes second char of $text is optionally '/' to indicate closing as in </html>.
393	*
394	* @since 2.9.0
395	* @access private
396	*
397	* @param string $text Text to check. Must be a tag like `<html>` or `[shortcode]`.
398	* @param array $stack List of open tag elements.
399	* @param array $disabled_elements The tag names to match against. Spaces are not allowed in tag names.
400	*/
401	function _wptexturize_pushpop_element($text, &$stack, $disabled_elements)
402	{
403	// Is it an opening tag or closing tag?
404	if (isset($text[1]) && '/' !== $text[1]) {
405	$opening_tag = true;
406	$name_offset = 1;
407	} elseif (0 == count($stack)) {
408	// Stack is empty. Just stop.
409	return;
410	} else {
411	$opening_tag = false;
412	$name_offset = 2;
413	}
414
415	// Parse out the tag name.
416	$space = strpos($text, ' ');
417	if (false === $space) {
418	$space = -1;
419	} else {
420	$space -= $name_offset;
421	}
422	$tag = substr($text, $name_offset, $space);
423
424	// Handle disabled tags.
425	if (in_array($tag, $disabled_elements)) {
426	if ($opening_tag) {
427	/*
428	* This disables texturize until we find a closing tag of our type
429	* (e.g. <pre>) even if there was invalid nesting before that
430	*
431	* Example: in the case <pre>sadsadasd</code>"baba"</pre>
432	* "baba" won't be texturize
433	*/
434
435	array_push($stack, $tag);
436	} elseif (end($stack) == $tag) {
437	array_pop($stack);
438	}
439	}
440	}
441
442	/**
443	* Replaces double line-breaks with paragraph elements.
444	*
445	* A group of regex replaces used to identify text formatted with newlines and
446	* replace double line-breaks with HTML paragraph tags. The remaining line-breaks
447	* after conversion become <<br />> tags, unless $br is set to '0' or 'false'.
448	*
449	* @since 0.71
450	*
451	* @param string $pee The text which has to be formatted.
452	* @param bool $br Optional. If set, this will convert all remaining line-breaks
453	* after paragraphing. Default true.
454	* @return string Text which has been converted into correct paragraph tags.
455	*/
456	function wpautop($pee, $br = true)
457	{
458	$pre_tags = array();
459
460	if (trim($pee) === '') {
461	return '';
462	}
463
464	// Just to make things a little easier, pad the end.
465	$pee = $pee . "\n";
466
467	/*
468	* Pre tags shouldn't be touched by autop.
469	* Replace pre tags with placeholders and bring them back after autop.
470	*/
471	if (strpos($pee, '<pre') !== false) {
472	$pee_parts = explode('</pre>', $pee);
473	$last_pee = array_pop($pee_parts);
474	$pee = '';
475	$i = 0;
476
477	foreach ($pee_parts as $pee_part) {
478	$start = strpos($pee_part, '<pre');
479
480	// Malformed html?
481	if ($start === false) {
482	$pee .= $pee_part;
483	continue;
484	}
485
486	$name = "<pre wp-pre-tag-$i></pre>";
487	$pre_tags[ $name ] = substr($pee_part, $start) . '</pre>';
488
489	$pee .= substr($pee_part, 0, $start) . $name;
490	$i++;
491	}
492
493	$pee .= $last_pee;
494	}
495	// Change multiple <br>s into two line breaks, which will turn into paragraphs.
496	$pee = preg_replace('\|<br\s/?>\s<br\s*/?>\|', "\n\n", $pee);
497
498	$allblocks = '(?:table\|thead\|tfoot\|caption\|col\|colgroup\|tbody\|tr\|td\|th\|div\|dl\|dd\|dt\|ul\|ol\|li\|pre\|form\|map\|area\|blockquote\|address\|math\|style\|p\|h[1-6]\|hr\|fieldset\|legend\|section\|article\|aside\|hgroup\|header\|footer\|nav\|figure\|figcaption\|details\|menu\|summary)';
499
500	// Add a double line break above block-level opening tags.
501	$pee = preg_replace('!(<' . $allblocks . '[\s/>])!', "\n\n$1", $pee);
502
503	// Add a double line break below block-level closing tags.
504	$pee = preg_replace('!(</' . $allblocks . '>)!', "$1\n\n", $pee);
505
506	// Standardize newline characters to "\n".
507	$pee = str_replace(array( "\r\n", "\r" ), "\n", $pee);
508
509	// Find newlines in all elements and add placeholders.
510	$pee = wp_replace_in_html_tags($pee, array( "\n" => ' <!-- wpnl --> ' ));
511
512	// Collapse line breaks before and after <option> elements so they don't get autop'd.
513	if (strpos($pee, '<option') !== false) {
514	$pee = preg_replace('\|\s*<option\|', '<option', $pee);
515	$pee = preg_replace('\|</option>\s*\|', '</option>', $pee);
516	}
517
518	/*
519	* Collapse line breaks inside <object> elements, before <param> and <embed> elements
520	* so they don't get autop'd.
521	*/
522	if (strpos($pee, '</object>') !== false) {
523	$pee = preg_replace('\|(<object[^>]>)\s\|', '$1', $pee);
524	$pee = preg_replace('\|\s*</object>\|', '</object>', $pee);
525	$pee = preg_replace('%\s(</?(?:param\|embed)[^>]>)\s*%', '$1', $pee);
526	}
527
528	/*
529	* Collapse line breaks inside <audio> and <video> elements,
530	* before and after <source> and <track> elements.
531	*/
532	if (strpos($pee, '<source') !== false \|\| strpos($pee, '<track') !== false) {
533	$pee = preg_replace('%([<\[](?:audio\|video)[^>\]][>\]])\s%', '$1', $pee);
534	$pee = preg_replace('%\s*([<\[]/(?:audio\|video)[>\]])%', '$1', $pee);
535	$pee = preg_replace('%\s(<(?:source\|track)[^>]>)\s*%', '$1', $pee);
536	}
537
538	// Collapse line breaks before and after <figcaption> elements.
539	if (strpos($pee, '<figcaption') !== false) {
540	$pee = preg_replace('\|\s(<figcaption[^>]>)\|', '$1', $pee);
541	$pee = preg_replace('\|</figcaption>\s*\|', '</figcaption>', $pee);
542	}
543
544	// Remove more than two contiguous line breaks.
545	$pee = preg_replace("/\n\n+/", "\n\n", $pee);
546
547	// Split up the contents into an array of strings, separated by double line breaks.
548	$pees = preg_split('/\n\s*\n/', $pee, -1, PREG_SPLIT_NO_EMPTY);
549
550	// Reset $pee prior to rebuilding.
551	$pee = '';
552
553	// Rebuild the content as a string, wrapping every bit with a <p>.
554	foreach ($pees as $tinkle) {
555	$pee .= '<p>' . trim($tinkle, "\n") . "</p>\n";
556	}
557
558	// Under certain strange conditions it could create a P of entirely whitespace.
559	$pee = preg_replace('\|<p>\s*</p>\|', '', $pee);
560
561	// Add a closing <p> inside <div>, <address>, or <form> tag if missing.
562	$pee = preg_replace('!<p>([^<]+)</(div\|address\|form)>!', '<p>$1</p></$2>', $pee);
563
564	// If an opening or closing block element tag is wrapped in a <p>, unwrap it.
565	$pee = preg_replace('!<p>\s(</?' . $allblocks . '[^>]>)\s*</p>!', '$1', $pee);
566
567	// In some cases <li> may get wrapped in <p>, fix them.
568	$pee = preg_replace('\|<p>(<li.+?)</p>\|', '$1', $pee);
569
570	// If a <blockquote> is wrapped with a <p>, move it inside the <blockquote>.
571	$pee = preg_replace('\|<p><blockquote([^>]*)>\|i', '<blockquote$1><p>', $pee);
572	$pee = str_replace('</blockquote></p>', '</p></blockquote>', $pee);
573
574	$pee = preg_replace('/(img\s)?(^">\|<\/p>)/', "", $pee);
575
576	// If an opening or closing block element tag is preceded by an opening <p> tag, remove it.
577	$pee = preg_replace('!<p>\s(</?' . $allblocks . '[^>]>)!', '$1', $pee);
578
579	// If an opening or closing block element tag is followed by a closing <p> tag, remove it.
580	$pee = preg_replace('!(</?' . $allblocks . '[^>]>)\s</p>!', '$1', $pee);
581
582	// Optionally insert line breaks.
583	if ($br) {
584	// Replace newlines that shouldn't be touched with a placeholder.
585	$pee = preg_replace_callback('/<(script\|style).*?<\/\\1>/s', '_autop_newline_preservation_helper', $pee);
586
587	// Normalize <br>
588	$pee = str_replace(array( '<br>', '<br/>' ), '<br />', $pee);
589
590	// Replace any new line characters that aren't preceded by a <br /> with a <br />.
591	$pee = preg_replace('\|(?<!<br />)\s*\n\|', "<br />\n", $pee);
592
593	// Replace newline placeholders with newlines.
594	$pee = str_replace('<WPPreserveNewline />', "\n", $pee);
595	}
596
597	// If a <br /> tag is after an opening or closing block tag, remove it.
598	$pee = preg_replace('!(</?' . $allblocks . '[^>]>)\s<br />!', '$1', $pee);
599
600	// If a <br /> tag is before a subset of opening or closing block tags, remove it.
601	$pee = preg_replace('!<br />(\s</?(?:p\|li\|div\|dl\|dd\|dt\|th\|pre\|td\|ul\|ol)[^>]>)!', '$1', $pee);
602	$pee = preg_replace("\|\n</p>$\|", '</p>', $pee);
603
604	// Replace placeholder <pre> tags with their original content.
605	if (! empty($pre_tags)) {
606	$pee = str_replace(array_keys($pre_tags), array_values($pre_tags), $pee);
607	}
608
609	// Restore newlines in all elements.
610	if (false !== strpos($pee, '<!-- wpnl -->')) {
611	$pee = str_replace(array( ' <!-- wpnl --> ', '<!-- wpnl -->' ), "\n", $pee);
612	}
613
614	return $pee;
615	}
616
617	/**
618	* Separate HTML elements and comments from the text.
619	*
620	* @since 4.2.4
621	*
622	* @param string $input The text which has to be formatted.
623	* @return array The formatted text.
624	*/
625	function wp_html_split($input)
626	{
627	return preg_split(get_html_split_regex(), $input, -1, PREG_SPLIT_DELIM_CAPTURE);
628	}
629
630	/**
631	* Retrieve the regular expression for an HTML element.
632	*
633	* @since 4.4.0
634	*
635	* @staticvar string $regex
636	*
637	* @return string The regular expression
638	*/
639	function get_html_split_regex()
640	{
641	static $regex;
642
643	if (! isset($regex)) {
644	// phpcs:disable Squiz.Strings.ConcatenationSpacing.PaddingFound -- don't remove regex indentation
645	$comments =
646	'!' // Start of comment, after the <.
647	. '(?:' // Unroll the loop: Consume everything until --> is found.
648	. '-(?!->)' // Dash not followed by end of comment.
649	. '[^\-]*+' // Consume non-dashes.
650	. ')*+' // Loop possessively.
651	. '(?:-->)?'; // End of comment. If not found, match all input.
652
653	$cdata =
654	'!\[CDATA\[' // Start of comment, after the <.
655	. '[^\]]*+' // Consume non-].
656	. '(?:' // Unroll the loop: Consume everything until ]]> is found.
657	. '](?!]>)' // One ] not followed by end of comment.
658	. '[^\]]*+' // Consume non-].
659	. ')*+' // Loop possessively.
660	. '(?:]]>)?'; // End of comment. If not found, match all input.
661
662	$escaped =
663	'(?=' // Is the element escaped?
664	. '!--'
665	. '\|'
666	. '!\[CDATA\['
667	. ')'
668	. '(?(?=!-)' // If yes, which type?
669	. $comments
670	. '\|'
671	. $cdata
672	. ')';
673
674	$regex =
675	'/(' // Capture the entire match.
676	. '<' // Find start of element.
677	. '(?' // Conditional expression follows.
678	. $escaped // Find end of escaped element.
679	. '\|' // ... else ...
680	. '[^>]*>?' // Find end of normal element.
681	. ')'
682	. ')/';
683	// phpcs:enable
684	}
685
686	return $regex;
687	}
688
689	/**
690	* Retrieve the combined regular expression for HTML and shortcodes.
691	*
692	* @access private
693	* @ignore
694	* @internal This function will be removed in 4.5.0 per Shortcode API Roadmap.
695	* @since 4.4.0
696	*
697	* @staticvar string $html_regex
698	*
699	* @param string $shortcode_regex The result from _get_wptexturize_shortcode_regex(). Optional.
700	* @return string The regular expression
701	*/
702	function _get_wptexturize_split_regex($shortcode_regex = '')
703	{
704	static $html_regex;
705
706	if (! isset($html_regex)) {
707	// phpcs:disable Squiz.Strings.ConcatenationSpacing.PaddingFound -- don't remove regex indentation
708	$comment_regex =
709	'!' // Start of comment, after the <.
710	. '(?:' // Unroll the loop: Consume everything until --> is found.
711	. '-(?!->)' // Dash not followed by end of comment.
712	. '[^\-]*+' // Consume non-dashes.
713	. ')*+' // Loop possessively.
714	. '(?:-->)?'; // End of comment. If not found, match all input.
715
716	$html_regex = // Needs replaced with wp_html_split() per Shortcode API Roadmap.
717	'<' // Find start of element.
718	. '(?(?=!--)' // Is this a comment?
719	. $comment_regex // Find end of comment.
720	. '\|'
721	. '[^>]*>?' // Find end of element. If not found, match all input.
722	. ')';
723	// phpcs:enable
724	}
725
726	if (empty($shortcode_regex)) {
727	$regex = '/(' . $html_regex . ')/';
728	} else {
729	$regex = '/(' . $html_regex . '\|' . $shortcode_regex . ')/';
730	}
731
732	return $regex;
733	}
734
735	/**
736	* Retrieve the regular expression for shortcodes.
737	*
738	* @access private
739	* @ignore
740	* @internal This function will be removed in 4.5.0 per Shortcode API Roadmap.
741	* @since 4.4.0
742	*
743	* @param array $tagnames List of shortcodes to find.
744	* @return string The regular expression
745	*/
746	function _get_wptexturize_shortcode_regex($tagnames)
747	{
748	$tagregexp = join('\|', array_map('preg_quote', $tagnames));
749	$tagregexp = "(?:$tagregexp)(?=[\\s\\]\\/])"; // Excerpt of get_shortcode_regex().
750	// phpcs:disable Squiz.Strings.ConcatenationSpacing.PaddingFound -- don't remove regex indentation
751	$regex =
752	'\[' // Find start of shortcode.
753	. '[\/\[]?' // Shortcodes may begin with [/ or [[
754	. $tagregexp // Only match registered shortcodes, because performance.
755	. '(?:'
756	. '[^\[\]<>]+' // Shortcodes do not contain other shortcodes. Quantifier critical.
757	. '\|'
758	. '<[^\[\]>]*>' // HTML elements permitted. Prevents matching ] before >.
759	. ')*+' // Possessive critical.
760	. '\]' // Find end of shortcode.
761	. '\]?'; // Shortcodes may end with ]]
762	// phpcs:enable
763
764	return $regex;
765	}
766
767	/**
768	* Replace characters or phrases within HTML elements only.
769	*
770	* @since 4.2.3
771	*
772	* @param string $haystack The text which has to be formatted.
773	* @param array $replace_pairs In the form array('from' => 'to', ...).
774	* @return string The formatted text.
775	*/
776	function wp_replace_in_html_tags($haystack, $replace_pairs)
777	{
778	// Find all elements.
779	$textarr = wp_html_split($haystack);
780	$changed = false;
781
782	// Optimize when searching for one item.
783	if (1 === count($replace_pairs)) {
784	// Extract $needle and $replace.
785	foreach ($replace_pairs as $needle => $replace) {
786	}
787
788	// Loop through delimiters (elements) only.
789	for ($i = 1, $c = count($textarr); $i < $c; $i += 2) {
790	if (false !== strpos($textarr[ $i ], $needle)) {
791	$textarr[ $i ] = str_replace($needle, $replace, $textarr[ $i ]);
792	$changed = true;
793	}
794	}
795	} else {
796	// Extract all $needles.
797	$needles = array_keys($replace_pairs);
798
799	// Loop through delimiters (elements) only.
800	for ($i = 1, $c = count($textarr); $i < $c; $i += 2) {
801	foreach ($needles as $needle) {
802	if (false !== strpos($textarr[ $i ], $needle)) {
803	$textarr[ $i ] = strtr($textarr[ $i ], $replace_pairs);
804	$changed = true;
805	// After one strtr() break out of the foreach loop and look at next element.
806	break;
807	}
808	}
809	}
810	}
811
812	if ($changed) {
813	$haystack = implode($textarr);
814	}
815
816	return $haystack;
817	}
818
819	/**
820	* Newline preservation help function for wpautop
821	*
822	* @since 3.1.0
823	* @access private
824	*
825	* @param array $matches preg_replace_callback matches array
826	* @return string
827	*/
828	function _autop_newline_preservation_helper($matches)
829	{
830	return str_replace("\n", '<WPPreserveNewline />', $matches[0]);
831	}
832
833	/**
834	* Don't auto-p wrap shortcodes that stand alone
835	*
836	* Ensures that shortcodes are not wrapped in `<p>...</p>`.
837	*
838	* @since 2.9.0
839	*
840	* @global array $shortcode_tags
841	*
842	* @param string $pee The content.
843	* @return string The filtered content.
844	*/
845	function shortcode_unautop($pee)
846	{
847	global $shortcode_tags;
848
849	if (empty($shortcode_tags) \|\| ! is_array($shortcode_tags)) {
850	return $pee;
851	}
852
853	$tagregexp = join('\|', array_map('preg_quote', array_keys($shortcode_tags)));
854	$spaces = wp_spaces_regexp();
855
856	// phpcs:disable Squiz.Strings.ConcatenationSpacing.PaddingFound -- don't remove regex indentation
857	$pattern =
858	'/'
859	. '<p>' // Opening paragraph
860	. '(?:' . $spaces . ')*+' // Optional leading whitespace
861	. '(' // 1: The shortcode
862	. '\\[' // Opening bracket
863	. "($tagregexp)" // 2: Shortcode name
864	. '(?![\\w-])' // Not followed by word character or hyphen
865	// Unroll the loop: Inside the opening shortcode tag
866	. '[^\\]\\/]*' // Not a closing bracket or forward slash
867	. '(?:'
868	. '\\/(?!\\])' // A forward slash not followed by a closing bracket
869	. '[^\\]\\/]*' // Not a closing bracket or forward slash
870	. ')*?'
871	. '(?:'
872	. '\\/\\]' // Self closing tag and closing bracket
873	. '\|'
874	. '\\]' // Closing bracket
875	. '(?:' // Unroll the loop: Optionally, anything between the opening and closing shortcode tags
876	. '[^\\[]*+' // Not an opening bracket
877	. '(?:'
878	. '\\[(?!\\/\\2\\])' // An opening bracket not followed by the closing shortcode tag
879	. '[^\\[]*+' // Not an opening bracket
880	. ')*+'
881	. '\\[\\/\\2\\]' // Closing shortcode tag
882	. ')?'
883	. ')'
884	. ')'
885	. '(?:' . $spaces . ')*+' // optional trailing whitespace
886	. '<\\/p>' // closing paragraph
887	. '/';
888	// phpcs:enable
889
890	return preg_replace($pattern, '$1', $pee);
891	}
892
893	/**
894	* Checks to see if a string is utf8 encoded.
895	*
896	* NOTE: This function checks for 5-Byte sequences, UTF8
897	* has Bytes Sequences with a maximum length of 4.
898	*
899	* @author bmorel at ssi dot fr (modified)
900	* @since 1.2.1
901	*
902	* @param string $str The string to be checked
903	* @return bool True if $str fits a UTF-8 model, false otherwise.
904	*/
905	function seems_utf8($str)
906	{
907	mbstring_binary_safe_encoding();
908	$length = strlen($str);
909	reset_mbstring_encoding();
910	for ($i = 0; $i < $length; $i++) {
911	$c = ord($str[ $i ]);
912	if ($c < 0x80) {
913	$n = 0; // 0bbbbbbb
914	} elseif (( $c & 0xE0 ) == 0xC0) {
915	$n = 1; // 110bbbbb
916	} elseif (( $c & 0xF0 ) == 0xE0) {
917	$n = 2; // 1110bbbb
918	} elseif (( $c & 0xF8 ) == 0xF0) {
919	$n = 3; // 11110bbb
920	} elseif (( $c & 0xFC ) == 0xF8) {
921	$n = 4; // 111110bb
922	} elseif (( $c & 0xFE ) == 0xFC) {
923	$n = 5; // 1111110b
924	} else {
925	return false; // Does not match any model
926	}
927	for ($j = 0; $j < $n; $j++) { // n bytes matching 10bbbbbb follow ?
928	if (( ++$i == $length ) \|\| ( ( ord($str[ $i ]) & 0xC0 ) != 0x80 )) {
929	return false;
930	}
931	}
932	}
933	return true;
934	}
935
936	/**
937	* Converts a number of special characters into their HTML entities.
938	*
939	* Specifically deals with: &, <, >, ", and '.
940	*
941	* $quote_style can be set to ENT_COMPAT to encode " to
942	* ", or ENT_QUOTES to do both. Default is ENT_NOQUOTES where no quotes are encoded.
943	*
944	* @since 1.2.2
945	* @access private
946	*
947	* @staticvar string $_charset
948	*
949	* @param string $string The text which is to be encoded.
950	* @param int\|string $quote_style Optional. Converts double quotes if set to ENT_COMPAT,
951	* both single and double if set to ENT_QUOTES or none if set to ENT_NOQUOTES.
952	* Also compatible with old values; converting single quotes if set to 'single',
953	* double if set to 'double' or both if otherwise set.
954	* Default is ENT_NOQUOTES.
955	* @param string $charset Optional. The character encoding of the string. Default is false.
956	* @param bool $double_encode Optional. Whether to encode existing html entities. Default is false.
957	* @return string The encoded text with HTML entities.
958	*/
959	function _wp_specialchars($string, $quote_style = ENT_NOQUOTES, $charset = false, $double_encode = false)
960	{
961	$string = (string) $string;
962
963	if (0 === strlen($string)) {
964	return '';
965	}
966
967	// Don't bother if there are no specialchars - saves some processing
968	if (! preg_match('/[&<>"\']/', $string)) {
969	return $string;
970	}
971
972	// Account for the previous behaviour of the function when the $quote_style is not an accepted value
973	if (empty($quote_style)) {
974	$quote_style = ENT_NOQUOTES;
975	} elseif (! in_array($quote_style, array( 0, 2, 3, 'single', 'double' ), true)) {
976	$quote_style = ENT_QUOTES;
977	}
978
979	// Store the site charset as a static to avoid multiple calls to wp_load_alloptions()
980	if (! $charset) {
981	static $_charset = null;
982	if (! isset($_charset)) {
983	$alloptions = wp_load_alloptions();
984	$_charset = isset($alloptions['blog_charset']) ? $alloptions['blog_charset'] : '';
985	}
986	$charset = $_charset;
987	}
988
989	if (in_array($charset, array( 'utf8', 'utf-8', 'UTF8' ))) {
990	$charset = 'UTF-8';
991	}
992
993	$_quote_style = $quote_style;
994
995	if ($quote_style === 'double') {
996	$quote_style = ENT_COMPAT;
997	$_quote_style = ENT_COMPAT;
998	} elseif ($quote_style === 'single') {
999	$quote_style = ENT_NOQUOTES;
1000	}
1001
1002	if (! $double_encode) {
1003	// Guarantee every &entity; is valid, convert &garbage; into &garbage;
1004	// This is required for PHP < 5.4.0 because ENT_HTML401 flag is unavailable.
1005	$string = wp_kses_normalize_entities($string);
1006	}
1007
1008	$string = @htmlspecialchars($string, $quote_style, $charset, $double_encode);
1009
1010	// Back-compat.
1011	if ('single' === $_quote_style) {
1012	$string = str_replace("'", ''', $string);
1013	}
1014
1015	return $string;
1016	}
1017
1018	/**
1019	* Converts a number of HTML entities into their special characters.
1020	*
1021	* Specifically deals with: &, <, >, ", and '.
1022	*
1023	* $quote_style can be set to ENT_COMPAT to decode " entities,
1024	* or ENT_QUOTES to do both " and '. Default is ENT_NOQUOTES where no quotes are decoded.
1025	*
1026	* @since 2.8.0
1027	*
1028	* @param string $string The text which is to be decoded.
1029	* @param string\|int $quote_style Optional. Converts double quotes if set to ENT_COMPAT,
1030	* both single and double if set to ENT_QUOTES or
1031	* none if set to ENT_NOQUOTES.
1032	* Also compatible with old _wp_specialchars() values;
1033	* converting single quotes if set to 'single',
1034	* double if set to 'double' or both if otherwise set.
1035	* Default is ENT_NOQUOTES.
1036	* @return string The decoded text without HTML entities.
1037	*/
1038	function wp_specialchars_decode($string, $quote_style = ENT_NOQUOTES)
1039	{
1040	$string = (string) $string;
1041
1042	if (0 === strlen($string)) {
1043	return '';
1044	}
1045
1046	// Don't bother if there are no entities - saves a lot of processing
1047	if (strpos($string, '&') === false) {
1048	return $string;
1049	}
1050
1051	// Match the previous behaviour of _wp_specialchars() when the $quote_style is not an accepted value
1052	if (empty($quote_style)) {
1053	$quote_style = ENT_NOQUOTES;
1054	} elseif (! in_array($quote_style, array( 0, 2, 3, 'single', 'double' ), true)) {
1055	$quote_style = ENT_QUOTES;
1056	}
1057
1058	// More complete than get_html_translation_table( HTML_SPECIALCHARS )
1059	$single = array(
1060	''' => '\'',
1061	''' => '\'',
1062	);
1063	$single_preg = array(
1064	'/&#0*39;/' => ''',
1065	'/&#x0*27;/i' => ''',
1066	);
1067	$double = array(
1068	'"' => '"',
1069	'"' => '"',
1070	'"' => '"',
1071	);
1072	$double_preg = array(
1073	'/&#0*34;/' => '"',
1074	'/&#x0*22;/i' => '"',
1075	);
1076	$others = array(
1077	'<' => '<',
1078	'<' => '<',
1079	'>' => '>',
1080	'>' => '>',
1081	'&' => '&',
1082	'&' => '&',
1083	'&' => '&',
1084	);
1085	$others_preg = array(
1086	'/&#0*60;/' => '<',
1087	'/&#0*62;/' => '>',
1088	'/&#0*38;/' => '&',
1089	'/&#x0*26;/i' => '&',
1090	);
1091
1092	if ($quote_style === ENT_QUOTES) {
1093	$translation = array_merge($single, $double, $others);
1094	$translation_preg = array_merge($single_preg, $double_preg, $others_preg);
1095	} elseif ($quote_style === ENT_COMPAT \|\| $quote_style === 'double') {
1096	$translation = array_merge($double, $others);
1097	$translation_preg = array_merge($double_preg, $others_preg);
1098	} elseif ($quote_style === 'single') {
1099	$translation = array_merge($single, $others);
1100	$translation_preg = array_merge($single_preg, $others_preg);
1101	} elseif ($quote_style === ENT_NOQUOTES) {
1102	$translation = $others;
1103	$translation_preg = $others_preg;
1104	}
1105
1106	// Remove zero padding on numeric entities
1107	$string = preg_replace(array_keys($translation_preg), array_values($translation_preg), $string);
1108
1109	// Replace characters according to translation table
1110	return strtr($string, $translation);
1111	}
1112
1113	/**
1114	* Checks for invalid UTF8 in a string.
1115	*
1116	* @since 2.8.0
1117	*
1118	* @staticvar bool $is_utf8
1119	* @staticvar bool $utf8_pcre
1120	*
1121	* @param string $string The text which is to be checked.
1122	* @param bool $strip Optional. Whether to attempt to strip out invalid UTF8. Default is false.
1123	* @return string The checked text.
1124	*/
1125	function wp_check_invalid_utf8($string, $strip = false)
1126	{
1127	$string = (string) $string;
1128
1129	if (0 === strlen($string)) {
1130	return '';
1131	}
1132
1133	// Store the site charset as a static to avoid multiple calls to get_option()
1134	static $is_utf8 = null;
1135	if (! isset($is_utf8)) {
1136	$is_utf8 = in_array(get_option('blog_charset'), array( 'utf8', 'utf-8', 'UTF8', 'UTF-8' ));
1137	}
1138	if (! $is_utf8) {
1139	return $string;
1140	}
1141
1142	// Check for support for utf8 in the installed PCRE library once and store the result in a static
1143	static $utf8_pcre = null;
1144	if (! isset($utf8_pcre)) {
1145	$utf8_pcre = @preg_match('/^./u', 'a');
1146	}
1147	// We can't demand utf8 in the PCRE installation, so just return the string in those cases
1148	if (! $utf8_pcre) {
1149	return $string;
1150	}
1151
1152	// preg_match fails when it encounters invalid UTF8 in $string
1153	if (1 === @preg_match('/^./us', $string)) {
1154	return $string;
1155	}
1156
1157	// Attempt to strip the bad chars if requested (not recommended)
1158	if ($strip && function_exists('iconv')) {
1159	return iconv('utf-8', 'utf-8', $string);
1160	}
1161
1162	return '';
1163	}
1164
1165	/**
1166	* Encode the Unicode values to be used in the URI.
1167	*
1168	* @since 1.5.0
1169	*
1170	* @param string $utf8_string
1171	* @param int $length Max length of the string
1172	* @return string String with Unicode encoded for URI.
1173	*/
1174	function utf8_uri_encode($utf8_string, $length = 0)
1175	{
1176	$unicode = '';
1177	$values = array();
1178	$num_octets = 1;
1179	$unicode_length = 0;
1180
1181	mbstring_binary_safe_encoding();
1182	$string_length = strlen($utf8_string);
1183	reset_mbstring_encoding();
1184
1185	for ($i = 0; $i < $string_length; $i++) {
1186	$value = ord($utf8_string[ $i ]);
1187
1188	if ($value < 128) {
1189	if ($length && ( $unicode_length >= $length )) {
1190	break;
1191	}
1192	$unicode .= chr($value);
1193	$unicode_length++;
1194	} else {
1195	if (count($values) == 0) {
1196	if ($value < 224) {
1197	$num_octets = 2;
1198	} elseif ($value < 240) {
1199	$num_octets = 3;
1200	} else {
1201	$num_octets = 4;
1202	}
1203	}
1204
1205	$values[] = $value;
1206
1207	if ($length && ( $unicode_length + ( $num_octets * 3 ) ) > $length) {
1208	break;
1209	}
1210	if (count($values) == $num_octets) {
1211	for ($j = 0; $j < $num_octets; $j++) {
1212	$unicode .= '%' . dechex($values[ $j ]);
1213	}
1214
1215	$unicode_length += $num_octets * 3;
1216
1217	$values = array();
1218	$num_octets = 1;
1219	}
1220	}
1221	}
1222
1223	return $unicode;
1224	}
1225
1226	/**
1227	* Converts all accent characters to ASCII characters.
1228	*
1229	* If there are no accent characters, then the string given is just returned.
1230	*
1231	* Accent characters converted:
1232	*
1233	* Currency signs:
1234	*
1235	* \| Code \| Glyph \| Replacement \| Description \|
1236	* \| -------- \| ----- \| ----------- \| ------------------- \|
1237	* \| U+00A3 \| £ \| (empty) \| British Pound sign \|
1238	* \| U+20AC \| € \| E \| Euro sign \|
1239	*
1240	* Decompositions for Latin-1 Supplement:
1241	*
1242	* \| Code \| Glyph \| Replacement \| Description \|
1243	* \| ------- \| ----- \| ----------- \| -------------------------------------- \|
1244	* \| U+00AA \| ª \| a \| Feminine ordinal indicator \|
1245	* \| U+00BA \| º \| o \| Masculine ordinal indicator \|
1246	* \| U+00C0 \| À \| A \| Latin capital letter A with grave \|
1247	* \| U+00C1 \| Á \| A \| Latin capital letter A with acute \|
1248	* \| U+00C2 \| Â \| A \| Latin capital letter A with circumflex \|
1249	* \| U+00C3 \| Ã \| A \| Latin capital letter A with tilde \|
1250	* \| U+00C4 \| Ä \| A \| Latin capital letter A with diaeresis \|
1251	* \| U+00C5 \| Å \| A \| Latin capital letter A with ring above \|
1252	* \| U+00C6 \| Æ \| AE \| Latin capital letter AE \|
1253	* \| U+00C7 \| Ç \| C \| Latin capital letter C with cedilla \|
1254	* \| U+00C8 \| È \| E \| Latin capital letter E with grave \|
1255	* \| U+00C9 \| É \| E \| Latin capital letter E with acute \|
1256	* \| U+00CA \| Ê \| E \| Latin capital letter E with circumflex \|
1257	* \| U+00CB \| Ë \| E \| Latin capital letter E with diaeresis \|
1258	* \| U+00CC \| Ì \| I \| Latin capital letter I with grave \|
1259	* \| U+00CD \| Í \| I \| Latin capital letter I with acute \|
1260	* \| U+00CE \| Î \| I \| Latin capital letter I with circumflex \|
1261	* \| U+00CF \| Ï \| I \| Latin capital letter I with diaeresis \|
1262	* \| U+00D0 \| Ð \| D \| Latin capital letter Eth \|
1263	* \| U+00D1 \| Ñ \| N \| Latin capital letter N with tilde \|
1264	* \| U+00D2 \| Ò \| O \| Latin capital letter O with grave \|
1265	* \| U+00D3 \| Ó \| O \| Latin capital letter O with acute \|
1266	* \| U+00D4 \| Ô \| O \| Latin capital letter O with circumflex \|
1267	* \| U+00D5 \| Õ \| O \| Latin capital letter O with tilde \|
1268	* \| U+00D6 \| Ö \| O \| Latin capital letter O with diaeresis \|
1269	* \| U+00D8 \| Ø \| O \| Latin capital letter O with stroke \|
1270	* \| U+00D9 \| Ù \| U \| Latin capital letter U with grave \|
1271	* \| U+00DA \| Ú \| U \| Latin capital letter U with acute \|
1272	* \| U+00DB \| Û \| U \| Latin capital letter U with circumflex \|
1273	* \| U+00DC \| Ü \| U \| Latin capital letter U with diaeresis \|
1274	* \| U+00DD \| Ý \| Y \| Latin capital letter Y with acute \|
1275	* \| U+00DE \| Þ \| TH \| Latin capital letter Thorn \|
1276	* \| U+00DF \| ß \| s \| Latin small letter sharp s \|
1277	* \| U+00E0 \| à \| a \| Latin small letter a with grave \|
1278	* \| U+00E1 \| á \| a \| Latin small letter a with acute \|
1279	* \| U+00E2 \| â \| a \| Latin small letter a with circumflex \|
1280	* \| U+00E3 \| ã \| a \| Latin small letter a with tilde \|
1281	* \| U+00E4 \| ä \| a \| Latin small letter a with diaeresis \|
1282	* \| U+00E5 \| å \| a \| Latin small letter a with ring above \|
1283	* \| U+00E6 \| æ \| ae \| Latin small letter ae \|
1284	* \| U+00E7 \| ç \| c \| Latin small letter c with cedilla \|
1285	* \| U+00E8 \| è \| e \| Latin small letter e with grave \|
1286	* \| U+00E9 \| é \| e \| Latin small letter e with acute \|
1287	* \| U+00EA \| ê \| e \| Latin small letter e with circumflex \|
1288	* \| U+00EB \| ë \| e \| Latin small letter e with diaeresis \|
1289	* \| U+00EC \| ì \| i \| Latin small letter i with grave \|
1290	* \| U+00ED \| í \| i \| Latin small letter i with acute \|
1291	* \| U+00EE \| î \| i \| Latin small letter i with circumflex \|
1292	* \| U+00EF \| ï \| i \| Latin small letter i with diaeresis \|
1293	* \| U+00F0 \| ð \| d \| Latin small letter Eth \|
1294	* \| U+00F1 \| ñ \| n \| Latin small letter n with tilde \|
1295	* \| U+00F2 \| ò \| o \| Latin small letter o with grave \|
1296	* \| U+00F3 \| ó \| o \| Latin small letter o with acute \|
1297	* \| U+00F4 \| ô \| o \| Latin small letter o with circumflex \|
1298	* \| U+00F5 \| õ \| o \| Latin small letter o with tilde \|
1299	* \| U+00F6 \| ö \| o \| Latin small letter o with diaeresis \|
1300	* \| U+00F8 \| ø \| o \| Latin small letter o with stroke \|
1301	* \| U+00F9 \| ù \| u \| Latin small letter u with grave \|
1302	* \| U+00FA \| ú \| u \| Latin small letter u with acute \|
1303	* \| U+00FB \| û \| u \| Latin small letter u with circumflex \|
1304	* \| U+00FC \| ü \| u \| Latin small letter u with diaeresis \|
1305	* \| U+00FD \| ý \| y \| Latin small letter y with acute \|
1306	* \| U+00FE \| þ \| th \| Latin small letter Thorn \|
1307	* \| U+00FF \| ÿ \| y \| Latin small letter y with diaeresis \|
1308	*
1309	* Decompositions for Latin Extended-A:
1310	*
1311	* \| Code \| Glyph \| Replacement \| Description \|
1312	* \| ------- \| ----- \| ----------- \| ------------------------------------------------- \|
1313	* \| U+0100 \| Ā \| A \| Latin capital letter A with macron \|
1314	* \| U+0101 \| ā \| a \| Latin small letter a with macron \|
1315	* \| U+0102 \| Ă \| A \| Latin capital letter A with breve \|
1316	* \| U+0103 \| ă \| a \| Latin small letter a with breve \|
1317	* \| U+0104 \| Ą \| A \| Latin capital letter A with ogonek \|
1318	* \| U+0105 \| ą \| a \| Latin small letter a with ogonek \|
1319	* \| U+01006 \| Ć \| C \| Latin capital letter C with acute \|
1320	* \| U+0107 \| ć \| c \| Latin small letter c with acute \|
1321	* \| U+0108 \| Ĉ \| C \| Latin capital letter C with circumflex \|
1322	* \| U+0109 \| ĉ \| c \| Latin small letter c with circumflex \|
1323	* \| U+010A \| Ċ \| C \| Latin capital letter C with dot above \|
1324	* \| U+010B \| ċ \| c \| Latin small letter c with dot above \|
1325	* \| U+010C \| Č \| C \| Latin capital letter C with caron \|
1326	* \| U+010D \| č \| c \| Latin small letter c with caron \|
1327	* \| U+010E \| Ď \| D \| Latin capital letter D with caron \|
1328	* \| U+010F \| ď \| d \| Latin small letter d with caron \|
1329	* \| U+0110 \| Đ \| D \| Latin capital letter D with stroke \|
1330	* \| U+0111 \| đ \| d \| Latin small letter d with stroke \|
1331	* \| U+0112 \| Ē \| E \| Latin capital letter E with macron \|
1332	* \| U+0113 \| ē \| e \| Latin small letter e with macron \|
1333	* \| U+0114 \| Ĕ \| E \| Latin capital letter E with breve \|
1334	* \| U+0115 \| ĕ \| e \| Latin small letter e with breve \|
1335	* \| U+0116 \| Ė \| E \| Latin capital letter E with dot above \|
1336	* \| U+0117 \| ė \| e \| Latin small letter e with dot above \|
1337	* \| U+0118 \| Ę \| E \| Latin capital letter E with ogonek \|
1338	* \| U+0119 \| ę \| e \| Latin small letter e with ogonek \|
1339	* \| U+011A \| Ě \| E \| Latin capital letter E with caron \|
1340	* \| U+011B \| ě \| e \| Latin small letter e with caron \|
1341	* \| U+011C \| Ĝ \| G \| Latin capital letter G with circumflex \|
1342	* \| U+011D \| ĝ \| g \| Latin small letter g with circumflex \|
1343	* \| U+011E \| Ğ \| G \| Latin capital letter G with breve \|
1344	* \| U+011F \| ğ \| g \| Latin small letter g with breve \|
1345	* \| U+0120 \| Ġ \| G \| Latin capital letter G with dot above \|
1346	* \| U+0121 \| ġ \| g \| Latin small letter g with dot above \|
1347	* \| U+0122 \| Ģ \| G \| Latin capital letter G with cedilla \|
1348	* \| U+0123 \| ģ \| g \| Latin small letter g with cedilla \|
1349	* \| U+0124 \| Ĥ \| H \| Latin capital letter H with circumflex \|
1350	* \| U+0125 \| ĥ \| h \| Latin small letter h with circumflex \|
1351	* \| U+0126 \| Ħ \| H \| Latin capital letter H with stroke \|
1352	* \| U+0127 \| ħ \| h \| Latin small letter h with stroke \|
1353	* \| U+0128 \| Ĩ \| I \| Latin capital letter I with tilde \|
1354	* \| U+0129 \| ĩ \| i \| Latin small letter i with tilde \|
1355	* \| U+012A \| Ī \| I \| Latin capital letter I with macron \|
1356	* \| U+012B \| ī \| i \| Latin small letter i with macron \|
1357	* \| U+012C \| Ĭ \| I \| Latin capital letter I with breve \|
1358	* \| U+012D \| ĭ \| i \| Latin small letter i with breve \|
1359	* \| U+012E \| Į \| I \| Latin capital letter I with ogonek \|
1360	* \| U+012F \| į \| i \| Latin small letter i with ogonek \|
1361	* \| U+0130 \| İ \| I \| Latin capital letter I with dot above \|
1362	* \| U+0131 \| ı \| i \| Latin small letter dotless i \|
1363	* \| U+0132 \| Ĳ \| IJ \| Latin capital ligature IJ \|
1364	* \| U+0133 \| ĳ \| ij \| Latin small ligature ij \|
1365	* \| U+0134 \| Ĵ \| J \| Latin capital letter J with circumflex \|
1366	* \| U+0135 \| ĵ \| j \| Latin small letter j with circumflex \|
1367	* \| U+0136 \| Ķ \| K \| Latin capital letter K with cedilla \|
1368	* \| U+0137 \| ķ \| k \| Latin small letter k with cedilla \|
1369	* \| U+0138 \| ĸ \| k \| Latin small letter Kra \|
1370	* \| U+0139 \| Ĺ \| L \| Latin capital letter L with acute \|
1371	* \| U+013A \| ĺ \| l \| Latin small letter l with acute \|
1372	* \| U+013B \| Ļ \| L \| Latin capital letter L with cedilla \|
1373	* \| U+013C \| ļ \| l \| Latin small letter l with cedilla \|
1374	* \| U+013D \| Ľ \| L \| Latin capital letter L with caron \|
1375	* \| U+013E \| ľ \| l \| Latin small letter l with caron \|
1376	* \| U+013F \| Ŀ \| L \| Latin capital letter L with middle dot \|
1377	* \| U+0140 \| ŀ \| l \| Latin small letter l with middle dot \|
1378	* \| U+0141 \| Ł \| L \| Latin capital letter L with stroke \|
1379	* \| U+0142 \| ł \| l \| Latin small letter l with stroke \|
1380	* \| U+0143 \| Ń \| N \| Latin capital letter N with acute \|
1381	* \| U+0144 \| ń \| n \| Latin small letter N with acute \|
1382	* \| U+0145 \| Ņ \| N \| Latin capital letter N with cedilla \|
1383	* \| U+0146 \| ņ \| n \| Latin small letter n with cedilla \|
1384	* \| U+0147 \| Ň \| N \| Latin capital letter N with caron \|
1385	* \| U+0148 \| ň \| n \| Latin small letter n with caron \|
1386	* \| U+0149 \| ŉ \| n \| Latin small letter n preceded by apostrophe \|
1387	* \| U+014A \| Ŋ \| N \| Latin capital letter Eng \|
1388	* \| U+014B \| ŋ \| n \| Latin small letter Eng \|
1389	* \| U+014C \| Ō \| O \| Latin capital letter O with macron \|
1390	* \| U+014D \| ō \| o \| Latin small letter o with macron \|
1391	* \| U+014E \| Ŏ \| O \| Latin capital letter O with breve \|
1392	* \| U+014F \| ŏ \| o \| Latin small letter o with breve \|
1393	* \| U+0150 \| Ő \| O \| Latin capital letter O with double acute \|
1394	* \| U+0151 \| ő \| o \| Latin small letter o with double acute \|
1395	* \| U+0152 \| Œ \| OE \| Latin capital ligature OE \|
1396	* \| U+0153 \| œ \| oe \| Latin small ligature oe \|
1397	* \| U+0154 \| Ŕ \| R \| Latin capital letter R with acute \|
1398	* \| U+0155 \| ŕ \| r \| Latin small letter r with acute \|
1399	* \| U+0156 \| Ŗ \| R \| Latin capital letter R with cedilla \|
1400	* \| U+0157 \| ŗ \| r \| Latin small letter r with cedilla \|
1401	* \| U+0158 \| Ř \| R \| Latin capital letter R with caron \|
1402	* \| U+0159 \| ř \| r \| Latin small letter r with caron \|
1403	* \| U+015A \| Ś \| S \| Latin capital letter S with acute \|
1404	* \| U+015B \| ś \| s \| Latin small letter s with acute \|
1405	* \| U+015C \| Ŝ \| S \| Latin capital letter S with circumflex \|
1406	* \| U+015D \| ŝ \| s \| Latin small letter s with circumflex \|
1407	* \| U+015E \| Ş \| S \| Latin capital letter S with cedilla \|
1408	* \| U+015F \| ş \| s \| Latin small letter s with cedilla \|
1409	* \| U+0160 \| Š \| S \| Latin capital letter S with caron \|
1410	* \| U+0161 \| š \| s \| Latin small letter s with caron \|
1411	* \| U+0162 \| Ţ \| T \| Latin capital letter T with cedilla \|
1412	* \| U+0163 \| ţ \| t \| Latin small letter t with cedilla \|
1413	* \| U+0164 \| Ť \| T \| Latin capital letter T with caron \|
1414	* \| U+0165 \| ť \| t \| Latin small letter t with caron \|
1415	* \| U+0166 \| Ŧ \| T \| Latin capital letter T with stroke \|
1416	* \| U+0167 \| ŧ \| t \| Latin small letter t with stroke \|
1417	* \| U+0168 \| Ũ \| U \| Latin capital letter U with tilde \|
1418	* \| U+0169 \| ũ \| u \| Latin small letter u with tilde \|
1419	* \| U+016A \| Ū \| U \| Latin capital letter U with macron \|
1420	* \| U+016B \| ū \| u \| Latin small letter u with macron \|
1421	* \| U+016C \| Ŭ \| U \| Latin capital letter U with breve \|
1422	* \| U+016D \| ŭ \| u \| Latin small letter u with breve \|
1423	* \| U+016E \| Ů \| U \| Latin capital letter U with ring above \|
1424	* \| U+016F \| ů \| u \| Latin small letter u with ring above \|
1425	* \| U+0170 \| Ű \| U \| Latin capital letter U with double acute \|
1426	* \| U+0171 \| ű \| u \| Latin small letter u with double acute \|
1427	* \| U+0172 \| Ų \| U \| Latin capital letter U with ogonek \|
1428	* \| U+0173 \| ų \| u \| Latin small letter u with ogonek \|
1429	* \| U+0174 \| Ŵ \| W \| Latin capital letter W with circumflex \|
1430	* \| U+0175 \| ŵ \| w \| Latin small letter w with circumflex \|
1431	* \| U+0176 \| Ŷ \| Y \| Latin capital letter Y with circumflex \|
1432	* \| U+0177 \| ŷ \| y \| Latin small letter y with circumflex \|
1433	* \| U+0178 \| Ÿ \| Y \| Latin capital letter Y with diaeresis \|
1434	* \| U+0179 \| Ź \| Z \| Latin capital letter Z with acute \|
1435	* \| U+017A \| ź \| z \| Latin small letter z with acute \|
1436	* \| U+017B \| Ż \| Z \| Latin capital letter Z with dot above \|
1437	* \| U+017C \| ż \| z \| Latin small letter z with dot above \|
1438	* \| U+017D \| Ž \| Z \| Latin capital letter Z with caron \|
1439	* \| U+017E \| ž \| z \| Latin small letter z with caron \|
1440	* \| U+017F \| ſ \| s \| Latin small letter long s \|
1441	* \| U+01A0 \| Ơ \| O \| Latin capital letter O with horn \|
1442	* \| U+01A1 \| ơ \| o \| Latin small letter o with horn \|
1443	* \| U+01AF \| Ư \| U \| Latin capital letter U with horn \|
1444	* \| U+01B0 \| ư \| u \| Latin small letter u with horn \|
1445	* \| U+01CD \| Ǎ \| A \| Latin capital letter A with caron \|
1446	* \| U+01CE \| ǎ \| a \| Latin small letter a with caron \|
1447	* \| U+01CF \| Ǐ \| I \| Latin capital letter I with caron \|
1448	* \| U+01D0 \| ǐ \| i \| Latin small letter i with caron \|
1449	* \| U+01D1 \| Ǒ \| O \| Latin capital letter O with caron \|
1450	* \| U+01D2 \| ǒ \| o \| Latin small letter o with caron \|
1451	* \| U+01D3 \| Ǔ \| U \| Latin capital letter U with caron \|
1452	* \| U+01D4 \| ǔ \| u \| Latin small letter u with caron \|
1453	* \| U+01D5 \| Ǖ \| U \| Latin capital letter U with diaeresis and macron \|
1454	* \| U+01D6 \| ǖ \| u \| Latin small letter u with diaeresis and macron \|
1455	* \| U+01D7 \| Ǘ \| U \| Latin capital letter U with diaeresis and acute \|
1456	* \| U+01D8 \| ǘ \| u \| Latin small letter u with diaeresis and acute \|
1457	* \| U+01D9 \| Ǚ \| U \| Latin capital letter U with diaeresis and caron \|
1458	* \| U+01DA \| ǚ \| u \| Latin small letter u with diaeresis and caron \|
1459	* \| U+01DB \| Ǜ \| U \| Latin capital letter U with diaeresis and grave \|
1460	* \| U+01DC \| ǜ \| u \| Latin small letter u with diaeresis and grave \|
1461	*
1462	* Decompositions for Latin Extended-B:
1463	*
1464	* \| Code \| Glyph \| Replacement \| Description \|
1465	* \| -------- \| ----- \| ----------- \| ----------------------------------------- \|
1466	* \| U+0218 \| Ș \| S \| Latin capital letter S with comma below \|
1467	* \| U+0219 \| ș \| s \| Latin small letter s with comma below \|
1468	* \| U+021A \| Ț \| T \| Latin capital letter T with comma below \|
1469	* \| U+021B \| ț \| t \| Latin small letter t with comma below \|
1470	*
1471	* Vowels with diacritic (Chinese, Hanyu Pinyin):
1472	*
1473	* \| Code \| Glyph \| Replacement \| Description \|
1474	* \| -------- \| ----- \| ----------- \| ----------------------------------------------------- \|
1475	* \| U+0251 \| ɑ \| a \| Latin small letter alpha \|
1476	* \| U+1EA0 \| Ạ \| A \| Latin capital letter A with dot below \|
1477	* \| U+1EA1 \| ạ \| a \| Latin small letter a with dot below \|
1478	* \| U+1EA2 \| Ả \| A \| Latin capital letter A with hook above \|
1479	* \| U+1EA3 \| ả \| a \| Latin small letter a with hook above \|
1480	* \| U+1EA4 \| Ấ \| A \| Latin capital letter A with circumflex and acute \|
1481	* \| U+1EA5 \| ấ \| a \| Latin small letter a with circumflex and acute \|
1482	* \| U+1EA6 \| Ầ \| A \| Latin capital letter A with circumflex and grave \|
1483	* \| U+1EA7 \| ầ \| a \| Latin small letter a with circumflex and grave \|
1484	* \| U+1EA8 \| Ẩ \| A \| Latin capital letter A with circumflex and hook above \|
1485	* \| U+1EA9 \| ẩ \| a \| Latin small letter a with circumflex and hook above \|
1486	* \| U+1EAA \| Ẫ \| A \| Latin capital letter A with circumflex and tilde \|
1487	* \| U+1EAB \| ẫ \| a \| Latin small letter a with circumflex and tilde \|
1488	* \| U+1EA6 \| Ậ \| A \| Latin capital letter A with circumflex and dot below \|
1489	* \| U+1EAD \| ậ \| a \| Latin small letter a with circumflex and dot below \|
1490	* \| U+1EAE \| Ắ \| A \| Latin capital letter A with breve and acute \|
1491	* \| U+1EAF \| ắ \| a \| Latin small letter a with breve and acute \|
1492	* \| U+1EB0 \| Ằ \| A \| Latin capital letter A with breve and grave \|
1493	* \| U+1EB1 \| ằ \| a \| Latin small letter a with breve and grave \|
1494	* \| U+1EB2 \| Ẳ \| A \| Latin capital letter A with breve and hook above \|
1495	* \| U+1EB3 \| ẳ \| a \| Latin small letter a with breve and hook above \|
1496	* \| U+1EB4 \| Ẵ \| A \| Latin capital letter A with breve and tilde \|
1497	* \| U+1EB5 \| ẵ \| a \| Latin small letter a with breve and tilde \|
1498	* \| U+1EB6 \| Ặ \| A \| Latin capital letter A with breve and dot below \|
1499	* \| U+1EB7 \| ặ \| a \| Latin small letter a with breve and dot below \|
1500	* \| U+1EB8 \| Ẹ \| E \| Latin capital letter E with dot below \|
1501	* \| U+1EB9 \| ẹ \| e \| Latin small letter e with dot below \|
1502	* \| U+1EBA \| Ẻ \| E \| Latin capital letter E with hook above \|
1503	* \| U+1EBB \| ẻ \| e \| Latin small letter e with hook above \|
1504	* \| U+1EBC \| Ẽ \| E \| Latin capital letter E with tilde \|
1505	* \| U+1EBD \| ẽ \| e \| Latin small letter e with tilde \|
1506	* \| U+1EBE \| Ế \| E \| Latin capital letter E with circumflex and acute \|
1507	* \| U+1EBF \| ế \| e \| Latin small letter e with circumflex and acute \|
1508	* \| U+1EC0 \| Ề \| E \| Latin capital letter E with circumflex and grave \|
1509	* \| U+1EC1 \| ề \| e \| Latin small letter e with circumflex and grave \|
1510	* \| U+1EC2 \| Ể \| E \| Latin capital letter E with circumflex and hook above \|
1511	* \| U+1EC3 \| ể \| e \| Latin small letter e with circumflex and hook above \|
1512	* \| U+1EC4 \| Ễ \| E \| Latin capital letter E with circumflex and tilde \|
1513	* \| U+1EC5 \| ễ \| e \| Latin small letter e with circumflex and tilde \|
1514	* \| U+1EC6 \| Ệ \| E \| Latin capital letter E with circumflex and dot below \|
1515	* \| U+1EC7 \| ệ \| e \| Latin small letter e with circumflex and dot below \|
1516	* \| U+1EC8 \| Ỉ \| I \| Latin capital letter I with hook above \|
1517	* \| U+1EC9 \| ỉ \| i \| Latin small letter i with hook above \|
1518	* \| U+1ECA \| Ị \| I \| Latin capital letter I with dot below \|
1519	* \| U+1ECB \| ị \| i \| Latin small letter i with dot below \|
1520	* \| U+1ECC \| Ọ \| O \| Latin capital letter O with dot below \|
1521	* \| U+1ECD \| ọ \| o \| Latin small letter o with dot below \|
1522	* \| U+1ECE \| Ỏ \| O \| Latin capital letter O with hook above \|
1523	* \| U+1ECF \| ỏ \| o \| Latin small letter o with hook above \|
1524	* \| U+1ED0 \| Ố \| O \| Latin capital letter O with circumflex and acute \|
1525	* \| U+1ED1 \| ố \| o \| Latin small letter o with circumflex and acute \|
1526	* \| U+1ED2 \| Ồ \| O \| Latin capital letter O with circumflex and grave \|
1527	* \| U+1ED3 \| ồ \| o \| Latin small letter o with circumflex and grave \|
1528	* \| U+1ED4 \| Ổ \| O \| Latin capital letter O with circumflex and hook above \|
1529	* \| U+1ED5 \| ổ \| o \| Latin small letter o with circumflex and hook above \|
1530	* \| U+1ED6 \| Ỗ \| O \| Latin capital letter O with circumflex and tilde \|
1531	* \| U+1ED7 \| ỗ \| o \| Latin small letter o with circumflex and tilde \|
1532	* \| U+1ED8 \| Ộ \| O \| Latin capital letter O with circumflex and dot below \|
1533	* \| U+1ED9 \| ộ \| o \| Latin small letter o with circumflex and dot below \|
1534	* \| U+1EDA \| Ớ \| O \| Latin capital letter O with horn and acute \|
1535	* \| U+1EDB \| ớ \| o \| Latin small letter o with horn and acute \|
1536	* \| U+1EDC \| Ờ \| O \| Latin capital letter O with horn and grave \|
1537	* \| U+1EDD \| ờ \| o \| Latin small letter o with horn and grave \|
1538	* \| U+1EDE \| Ở \| O \| Latin capital letter O with horn and hook above \|
1539	* \| U+1EDF \| ở \| o \| Latin small letter o with horn and hook above \|
1540	* \| U+1EE0 \| Ỡ \| O \| Latin capital letter O with horn and tilde \|
1541	* \| U+1EE1 \| ỡ \| o \| Latin small letter o with horn and tilde \|
1542	* \| U+1EE2 \| Ợ \| O \| Latin capital letter O with horn and dot below \|
1543	* \| U+1EE3 \| ợ \| o \| Latin small letter o with horn and dot below \|
1544	* \| U+1EE4 \| Ụ \| U \| Latin capital letter U with dot below \|
1545	* \| U+1EE5 \| ụ \| u \| Latin small letter u with dot below \|
1546	* \| U+1EE6 \| Ủ \| U \| Latin capital letter U with hook above \|
1547	* \| U+1EE7 \| ủ \| u \| Latin small letter u with hook above \|
1548	* \| U+1EE8 \| Ứ \| U \| Latin capital letter U with horn and acute \|
1549	* \| U+1EE9 \| ứ \| u \| Latin small letter u with horn and acute \|
1550	* \| U+1EEA \| Ừ \| U \| Latin capital letter U with horn and grave \|
1551	* \| U+1EEB \| ừ \| u \| Latin small letter u with horn and grave \|
1552	* \| U+1EEC \| Ử \| U \| Latin capital letter U with horn and hook above \|
1553	* \| U+1EED \| ử \| u \| Latin small letter u with horn and hook above \|
1554	* \| U+1EEE \| Ữ \| U \| Latin capital letter U with horn and tilde \|
1555	* \| U+1EEF \| ữ \| u \| Latin small letter u with horn and tilde \|
1556	* \| U+1EF0 \| Ự \| U \| Latin capital letter U with horn and dot below \|
1557	* \| U+1EF1 \| ự \| u \| Latin small letter u with horn and dot below \|
1558	* \| U+1EF2 \| Ỳ \| Y \| Latin capital letter Y with grave \|
1559	* \| U+1EF3 \| ỳ \| y \| Latin small letter y with grave \|
1560	* \| U+1EF4 \| Ỵ \| Y \| Latin capital letter Y with dot below \|
1561	* \| U+1EF5 \| ỵ \| y \| Latin small letter y with dot below \|
1562	* \| U+1EF6 \| Ỷ \| Y \| Latin capital letter Y with hook above \|
1563	* \| U+1EF7 \| ỷ \| y \| Latin small letter y with hook above \|
1564	* \| U+1EF8 \| Ỹ \| Y \| Latin capital letter Y with tilde \|
1565	* \| U+1EF9 \| ỹ \| y \| Latin small letter y with tilde \|
1566	*
1567	* German (`de_DE`), German formal (`de_DE_formal`), German (Switzerland) formal (`de_CH`),
1568	* and German (Switzerland) informal (`de_CH_informal`) locales:
1569	*
1570	* \| Code \| Glyph \| Replacement \| Description \|
1571	* \| -------- \| ----- \| ----------- \| --------------------------------------- \|
1572	* \| U+00C4 \| Ä \| Ae \| Latin capital letter A with diaeresis \|
1573	* \| U+00E4 \| ä \| ae \| Latin small letter a with diaeresis \|
1574	* \| U+00D6 \| Ö \| Oe \| Latin capital letter O with diaeresis \|
1575	* \| U+00F6 \| ö \| oe \| Latin small letter o with diaeresis \|
1576	* \| U+00DC \| Ü \| Ue \| Latin capital letter U with diaeresis \|
1577	* \| U+00FC \| ü \| ue \| Latin small letter u with diaeresis \|
1578	* \| U+00DF \| ß \| ss \| Latin small letter sharp s \|
1579	*
1580	* Danish (`da_DK`) locale:
1581	*
1582	* \| Code \| Glyph \| Replacement \| Description \|
1583	* \| -------- \| ----- \| ----------- \| --------------------------------------- \|
1584	* \| U+00C6 \| Æ \| Ae \| Latin capital letter AE \|
1585	* \| U+00E6 \| æ \| ae \| Latin small letter ae \|
1586	* \| U+00D8 \| Ø \| Oe \| Latin capital letter O with stroke \|
1587	* \| U+00F8 \| ø \| oe \| Latin small letter o with stroke \|
1588	* \| U+00C5 \| Å \| Aa \| Latin capital letter A with ring above \|
1589	* \| U+00E5 \| å \| aa \| Latin small letter a with ring above \|
1590	*
1591	* Catalan (`ca`) locale:
1592	*
1593	* \| Code \| Glyph \| Replacement \| Description \|
1594	* \| -------- \| ----- \| ----------- \| --------------------------------------- \|
1595	* \| U+00B7 \| l·l \| ll \| Flown dot (between two Ls) \|
1596	*
1597	* Serbian (`sr_RS`) and Bosnian (`bs_BA`) locales:
1598	*
1599	* \| Code \| Glyph \| Replacement \| Description \|
1600	* \| -------- \| ----- \| ----------- \| --------------------------------------- \|
1601	* \| U+0110 \| Đ \| DJ \| Latin capital letter D with stroke \|
1602	* \| U+0111 \| đ \| dj \| Latin small letter d with stroke \|
1603	*
1604	* @since 1.2.1
1605	* @since 4.6.0 Added locale support for `de_CH`, `de_CH_informal`, and `ca`.
1606	* @since 4.7.0 Added locale support for `sr_RS`.
1607	* @since 4.8.0 Added locale support for `bs_BA`.
1608	*
1609	* @param string $string Text that might have accent characters
1610	* @return string Filtered string with replaced "nice" characters.
1611	*/
1612	function remove_accents($string)
1613	{
1614	if (! preg_match('/[\x80-\xff]/', $string)) {
1615	return $string;
1616	}
1617
1618	if (seems_utf8($string)) {
1619	$chars = array(
1620	// Decompositions for Latin-1 Supplement
1621	'ª' => 'a',
1622	'º' => 'o',
1623	'À' => 'A',
1624	'Á' => 'A',
1625	'Â' => 'A',
1626	'Ã' => 'A',
1627	'Ä' => 'A',
1628	'Å' => 'A',
1629	'Æ' => 'AE',
1630	'Ç' => 'C',
1631	'È' => 'E',
1632	'É' => 'E',
1633	'Ê' => 'E',
1634	'Ë' => 'E',
1635	'Ì' => 'I',
1636	'Í' => 'I',
1637	'Î' => 'I',
1638	'Ï' => 'I',
1639	'Ð' => 'D',
1640	'Ñ' => 'N',
1641	'Ò' => 'O',
1642	'Ó' => 'O',
1643	'Ô' => 'O',
1644	'Õ' => 'O',
1645	'Ö' => 'O',
1646	'Ù' => 'U',
1647	'Ú' => 'U',
1648	'Û' => 'U',
1649	'Ü' => 'U',
1650	'Ý' => 'Y',
1651	'Þ' => 'TH',
1652	'ß' => 's',
1653	'à' => 'a',
1654	'á' => 'a',
1655	'â' => 'a',
1656	'ã' => 'a',
1657	'ä' => 'a',
1658	'å' => 'a',
1659	'æ' => 'ae',
1660	'ç' => 'c',
1661	'è' => 'e',
1662	'é' => 'e',
1663	'ê' => 'e',
1664	'ë' => 'e',
1665	'ì' => 'i',
1666	'í' => 'i',
1667	'î' => 'i',
1668	'ï' => 'i',
1669	'ð' => 'd',
1670	'ñ' => 'n',
1671	'ò' => 'o',
1672	'ó' => 'o',
1673	'ô' => 'o',
1674	'õ' => 'o',
1675	'ö' => 'o',
1676	'ø' => 'o',
1677	'ù' => 'u',
1678	'ú' => 'u',
1679	'û' => 'u',
1680	'ü' => 'u',
1681	'ý' => 'y',
1682	'þ' => 'th',
1683	'ÿ' => 'y',
1684	'Ø' => 'O',
1685	// Decompositions for Latin Extended-A
1686	'Ā' => 'A',
1687	'ā' => 'a',
1688	'Ă' => 'A',
1689	'ă' => 'a',
1690	'Ą' => 'A',
1691	'ą' => 'a',
1692	'Ć' => 'C',
1693	'ć' => 'c',
1694	'Ĉ' => 'C',
1695	'ĉ' => 'c',
1696	'Ċ' => 'C',
1697	'ċ' => 'c',
1698	'Č' => 'C',
1699	'č' => 'c',
1700	'Ď' => 'D',
1701	'ď' => 'd',
1702	'Đ' => 'D',
1703	'đ' => 'd',
1704	'Ē' => 'E',
1705	'ē' => 'e',
1706	'Ĕ' => 'E',
1707	'ĕ' => 'e',
1708	'Ė' => 'E',
1709	'ė' => 'e',
1710	'Ę' => 'E',
1711	'ę' => 'e',
1712	'Ě' => 'E',
1713	'ě' => 'e',
1714	'Ĝ' => 'G',
1715	'ĝ' => 'g',
1716	'Ğ' => 'G',
1717	'ğ' => 'g',
1718	'Ġ' => 'G',
1719	'ġ' => 'g',
1720	'Ģ' => 'G',
1721	'ģ' => 'g',
1722	'Ĥ' => 'H',
1723	'ĥ' => 'h',
1724	'Ħ' => 'H',
1725	'ħ' => 'h',
1726	'Ĩ' => 'I',
1727	'ĩ' => 'i',
1728	'Ī' => 'I',
1729	'ī' => 'i',
1730	'Ĭ' => 'I',
1731	'ĭ' => 'i',
1732	'Į' => 'I',
1733	'į' => 'i',
1734	'İ' => 'I',
1735	'ı' => 'i',
1736	'Ĳ' => 'IJ',
1737	'ĳ' => 'ij',
1738	'Ĵ' => 'J',
1739	'ĵ' => 'j',
1740	'Ķ' => 'K',
1741	'ķ' => 'k',
1742	'ĸ' => 'k',
1743	'Ĺ' => 'L',
1744	'ĺ' => 'l',
1745	'Ļ' => 'L',
1746	'ļ' => 'l',
1747	'Ľ' => 'L',
1748	'ľ' => 'l',
1749	'Ŀ' => 'L',
1750	'ŀ' => 'l',
1751	'Ł' => 'L',
1752	'ł' => 'l',
1753	'Ń' => 'N',
1754	'ń' => 'n',
1755	'Ņ' => 'N',
1756	'ņ' => 'n',
1757	'Ň' => 'N',
1758	'ň' => 'n',
1759	'ŉ' => 'n',
1760	'Ŋ' => 'N',
1761	'ŋ' => 'n',
1762	'Ō' => 'O',
1763	'ō' => 'o',
1764	'Ŏ' => 'O',
1765	'ŏ' => 'o',
1766	'Ő' => 'O',
1767	'ő' => 'o',
1768	'Œ' => 'OE',
1769	'œ' => 'oe',
1770	'Ŕ' => 'R',
1771	'ŕ' => 'r',
1772	'Ŗ' => 'R',
1773	'ŗ' => 'r',
1774	'Ř' => 'R',
1775	'ř' => 'r',
1776	'Ś' => 'S',
1777	'ś' => 's',
1778	'Ŝ' => 'S',
1779	'ŝ' => 's',
1780	'Ş' => 'S',
1781	'ş' => 's',
1782	'Š' => 'S',
1783	'š' => 's',
1784	'Ţ' => 'T',
1785	'ţ' => 't',
1786	'Ť' => 'T',
1787	'ť' => 't',
1788	'Ŧ' => 'T',
1789	'ŧ' => 't',
1790	'Ũ' => 'U',
1791	'ũ' => 'u',
1792	'Ū' => 'U',
1793	'ū' => 'u',
1794	'Ŭ' => 'U',
1795	'ŭ' => 'u',
1796	'Ů' => 'U',
1797	'ů' => 'u',
1798	'Ű' => 'U',
1799	'ű' => 'u',
1800	'Ų' => 'U',
1801	'ų' => 'u',
1802	'Ŵ' => 'W',
1803	'ŵ' => 'w',
1804	'Ŷ' => 'Y',
1805	'ŷ' => 'y',
1806	'Ÿ' => 'Y',
1807	'Ź' => 'Z',
1808	'ź' => 'z',
1809	'Ż' => 'Z',
1810	'ż' => 'z',
1811	'Ž' => 'Z',
1812	'ž' => 'z',
1813	'ſ' => 's',
1814	// Decompositions for Latin Extended-B
1815	'Ș' => 'S',
1816	'ș' => 's',
1817	'Ț' => 'T',
1818	'ț' => 't',
1819	// Euro Sign
1820	'€' => 'E',
1821	// GBP (Pound) Sign
1822	'£' => '',
1823	// Vowels with diacritic (Vietnamese)
1824	// unmarked
1825	'Ơ' => 'O',
1826	'ơ' => 'o',
1827	'Ư' => 'U',
1828	'ư' => 'u',
1829	// grave accent
1830	'Ầ' => 'A',
1831	'ầ' => 'a',
1832	'Ằ' => 'A',
1833	'ằ' => 'a',
1834	'Ề' => 'E',
1835	'ề' => 'e',
1836	'Ồ' => 'O',
1837	'ồ' => 'o',
1838	'Ờ' => 'O',
1839	'ờ' => 'o',
1840	'Ừ' => 'U',
1841	'ừ' => 'u',
1842	'Ỳ' => 'Y',
1843	'ỳ' => 'y',
1844	// hook
1845	'Ả' => 'A',
1846	'ả' => 'a',
1847	'Ẩ' => 'A',
1848	'ẩ' => 'a',
1849	'Ẳ' => 'A',
1850	'ẳ' => 'a',
1851	'Ẻ' => 'E',
1852	'ẻ' => 'e',
1853	'Ể' => 'E',
1854	'ể' => 'e',
1855	'Ỉ' => 'I',
1856	'ỉ' => 'i',
1857	'Ỏ' => 'O',
1858	'ỏ' => 'o',
1859	'Ổ' => 'O',
1860	'ổ' => 'o',
1861	'Ở' => 'O',
1862	'ở' => 'o',
1863	'Ủ' => 'U',
1864	'ủ' => 'u',
1865	'Ử' => 'U',
1866	'ử' => 'u',
1867	'Ỷ' => 'Y',
1868	'ỷ' => 'y',
1869	// tilde
1870	'Ẫ' => 'A',
1871	'ẫ' => 'a',
1872	'Ẵ' => 'A',
1873	'ẵ' => 'a',
1874	'Ẽ' => 'E',
1875	'ẽ' => 'e',
1876	'Ễ' => 'E',
1877	'ễ' => 'e',
1878	'Ỗ' => 'O',
1879	'ỗ' => 'o',
1880	'Ỡ' => 'O',
1881	'ỡ' => 'o',
1882	'Ữ' => 'U',
1883	'ữ' => 'u',
1884	'Ỹ' => 'Y',
1885	'ỹ' => 'y',
1886	// acute accent
1887	'Ấ' => 'A',
1888	'ấ' => 'a',
1889	'Ắ' => 'A',
1890	'ắ' => 'a',
1891	'Ế' => 'E',
1892	'ế' => 'e',
1893	'Ố' => 'O',
1894	'ố' => 'o',
1895	'Ớ' => 'O',
1896	'ớ' => 'o',
1897	'Ứ' => 'U',
1898	'ứ' => 'u',
1899	// dot below
1900	'Ạ' => 'A',
1901	'ạ' => 'a',
1902	'Ậ' => 'A',
1903	'ậ' => 'a',
1904	'Ặ' => 'A',
1905	'ặ' => 'a',
1906	'Ẹ' => 'E',
1907	'ẹ' => 'e',
1908	'Ệ' => 'E',
1909	'ệ' => 'e',
1910	'Ị' => 'I',
1911	'ị' => 'i',
1912	'Ọ' => 'O',
1913	'ọ' => 'o',
1914	'Ộ' => 'O',
1915	'ộ' => 'o',
1916	'Ợ' => 'O',
1917	'ợ' => 'o',
1918	'Ụ' => 'U',
1919	'ụ' => 'u',
1920	'Ự' => 'U',
1921	'ự' => 'u',
1922	'Ỵ' => 'Y',
1923	'ỵ' => 'y',
1924	// Vowels with diacritic (Chinese, Hanyu Pinyin)
1925	'ɑ' => 'a',
1926	// macron
1927	'Ǖ' => 'U',
1928	'ǖ' => 'u',
1929	// acute accent
1930	'Ǘ' => 'U',
1931	'ǘ' => 'u',
1932	// caron
1933	'Ǎ' => 'A',
1934	'ǎ' => 'a',
1935	'Ǐ' => 'I',
1936	'ǐ' => 'i',
1937	'Ǒ' => 'O',
1938	'ǒ' => 'o',
1939	'Ǔ' => 'U',
1940	'ǔ' => 'u',
1941	'Ǚ' => 'U',
1942	'ǚ' => 'u',
1943	// grave accent
1944	'Ǜ' => 'U',
1945	'ǜ' => 'u',
1946	);
1947
1948	// Used for locale-specific rules
1949	$locale = get_locale();
1950
1951	if ('de_DE' == $locale \|\| 'de_DE_formal' == $locale \|\| 'de_CH' == $locale \|\| 'de_CH_informal' == $locale) {
1952	$chars['Ä'] = 'Ae';
1953	$chars['ä'] = 'ae';
1954	$chars['Ö'] = 'Oe';
1955	$chars['ö'] = 'oe';
1956	$chars['Ü'] = 'Ue';
1957	$chars['ü'] = 'ue';
1958	$chars['ß'] = 'ss';
1959	} elseif ('da_DK' === $locale) {
1960	$chars['Æ'] = 'Ae';
1961	$chars['æ'] = 'ae';
1962	$chars['Ø'] = 'Oe';
1963	$chars['ø'] = 'oe';
1964	$chars['Å'] = 'Aa';
1965	$chars['å'] = 'aa';
1966	} elseif ('ca' === $locale) {
1967	$chars['l·l'] = 'll';
1968	} elseif ('sr_RS' === $locale \|\| 'bs_BA' === $locale) {
1969	$chars['Đ'] = 'DJ';
1970	$chars['đ'] = 'dj';
1971	}
1972
1973	$string = strtr($string, $chars);
1974	} else {
1975	$chars = array();
1976	// Assume ISO-8859-1 if not UTF-8
1977	$chars['in'] = "\x80\x83\x8a\x8e\x9a\x9e"
1978	. "\x9f\xa2\xa5\xb5\xc0\xc1\xc2"
1979	. "\xc3\xc4\xc5\xc7\xc8\xc9\xca"
1980	. "\xcb\xcc\xcd\xce\xcf\xd1\xd2"
1981	. "\xd3\xd4\xd5\xd6\xd8\xd9\xda"
1982	. "\xdb\xdc\xdd\xe0\xe1\xe2\xe3"
1983	. "\xe4\xe5\xe7\xe8\xe9\xea\xeb"
1984	. "\xec\xed\xee\xef\xf1\xf2\xf3"
1985	. "\xf4\xf5\xf6\xf8\xf9\xfa\xfb"
1986	. "\xfc\xfd\xff";
1987
1988	$chars['out'] = 'EfSZszYcYuAAAAAACEEEEIIIINOOOOOOUUUUYaaaaaaceeeeiiiinoooooouuuuyy';
1989
1990	$string = strtr($string, $chars['in'], $chars['out']);
1991	$double_chars = array();
1992	$double_chars['in'] = array( "\x8c", "\x9c", "\xc6", "\xd0", "\xde", "\xdf", "\xe6", "\xf0", "\xfe" );
1993	$double_chars['out'] = array( 'OE', 'oe', 'AE', 'DH', 'TH', 'ss', 'ae', 'dh', 'th' );
1994	$string = str_replace($double_chars['in'], $double_chars['out'], $string);
1995	}
1996
1997	return $string;
1998	}
1999
2000	/**
2001	* Sanitizes a filename, replacing whitespace with dashes.
2002	*
2003	* Removes special characters that are illegal in filenames on certain
2004	* operating systems and special characters requiring special escaping
2005	* to manipulate at the command line. Replaces spaces and consecutive
2006	* dashes with a single dash. Trims period, dash and underscore from beginning
2007	* and end of filename. It is not guaranteed that this function will return a
2008	* filename that is allowed to be uploaded.
2009	*
2010	* @since 2.1.0
2011	*
2012	* @param string $filename The filename to be sanitized
2013	* @return string The sanitized filename
2014	*/
2015	function sanitize_file_name($filename)
2016	{
2017	$filename_raw = $filename;
2018	$special_chars = array( '?', '[', ']', '/', '\\', '=', '<', '>', ':', ';', ',', "'", '"', '&', '$', '#', '*', '(', ')', '\|', '~', '`', '!', '{', '}', '%', '+', chr(0) );
2019	/**
2020	* Filters the list of characters to remove from a filename.
2021	*
2022	* @since 2.8.0
2023	*
2024	* @param array $special_chars Characters to remove.
2025	* @param string $filename_raw Filename as it was passed into sanitize_file_name().
2026	*/
2027	$special_chars = apply_filters('sanitize_file_name_chars', $special_chars, $filename_raw);
2028	$filename = preg_replace("#\x{00a0}#siu", ' ', $filename);
2029	$filename = str_replace($special_chars, '', $filename);
2030	$filename = str_replace(array( '%20', '+' ), '-', $filename);
2031	$filename = preg_replace('/[\r\n\t -]+/', '-', $filename);
2032	$filename = trim($filename, '.-_');
2033
2034	if (false === strpos($filename, '.')) {
2035	$mime_types = wp_get_mime_types();
2036	$filetype = wp_check_filetype('test.' . $filename, $mime_types);
2037	if ($filetype['ext'] === $filename) {
2038	$filename = 'unnamed-file.' . $filetype['ext'];
2039	}
2040	}
2041
2042	// Split the filename into a base and extension[s]
2043	$parts = explode('.', $filename);
2044
2045	// Return if only one extension
2046	if (count($parts) <= 2) {
2047	/**
2048	* Filters a sanitized filename string.
2049	*
2050	* @since 2.8.0
2051	*
2052	* @param string $filename Sanitized filename.
2053	* @param string $filename_raw The filename prior to sanitization.
2054	*/
2055	return apply_filters('sanitize_file_name', $filename, $filename_raw);
2056	}
2057
2058	// Process multiple extensions
2059	$filename = array_shift($parts);
2060	$extension = array_pop($parts);
2061	$mimes = get_allowed_mime_types();
2062
2063	/*
2064	* Loop over any intermediate extensions. Postfix them with a trailing underscore
2065	* if they are a 2 - 5 character long alpha string not in the extension whitelist.
2066	*/
2067	foreach ((array) $parts as $part) {
2068	$filename .= '.' . $part;
2069
2070	if (preg_match('/^[a-zA-Z]{2,5}\d?$/', $part)) {
2071	$allowed = false;
2072	foreach ($mimes as $ext_preg => $mime_match) {
2073	$ext_preg = '!^(' . $ext_preg . ')$!i';
2074	if (preg_match($ext_preg, $part)) {
2075	$allowed = true;
2076	break;
2077	}
2078	}
2079	if (! $allowed) {
2080	$filename .= '_';
2081	}
2082	}
2083	}
2084	$filename .= '.' . $extension;
2085	/** This filter is documented in wp-includes/formatting.php */
2086	return apply_filters('sanitize_file_name', $filename, $filename_raw);
2087	}
2088
2089	/**
2090	* Sanitizes a username, stripping out unsafe characters.
2091	*
2092	* Removes tags, octets, entities, and if strict is enabled, will only keep
2093	* alphanumeric, _, space, ., -, @. After sanitizing, it passes the username,
2094	* raw username (the username in the parameter), and the value of $strict as
2095	* parameters for the {@see 'sanitize_user'} filter.
2096	*
2097	* @since 2.0.0
2098	*
2099	* @param string $username The username to be sanitized.
2100	* @param bool $strict If set limits $username to specific characters. Default false.
2101	* @return string The sanitized username, after passing through filters.
2102	*/
2103	function sanitize_user($username, $strict = false)
2104	{
2105	$raw_username = $username;
2106	$username = wp_strip_all_tags($username);
2107	$username = remove_accents($username);
2108	// Kill octets
2109	$username = preg_replace('\|%([a-fA-F0-9][a-fA-F0-9])\|', '', $username);
2110	$username = preg_replace('/&.+?;/', '', $username); // Kill entities
2111
2112	// If strict, reduce to ASCII for max portability.
2113	if ($strict) {
2114	$username = preg_replace('\|[^a-z0-9 _.\-@]\|i', '', $username);
2115	}
2116
2117	$username = trim($username);
2118	// Consolidate contiguous whitespace
2119	$username = preg_replace('\|\s+\|', ' ', $username);
2120
2121	/**
2122	* Filters a sanitized username string.
2123	*
2124	* @since 2.0.1
2125	*
2126	* @param string $username Sanitized username.
2127	* @param string $raw_username The username prior to sanitization.
2128	* @param bool $strict Whether to limit the sanitization to specific characters. Default false.
2129	*/
2130	return apply_filters('sanitize_user', $username, $raw_username, $strict);
2131	}
2132
2133	/**
2134	* Sanitizes a string key.
2135	*
2136	* Keys are used as internal identifiers. Lowercase alphanumeric characters, dashes and underscores are allowed.
2137	*
2138	* @since 3.0.0
2139	*
2140	* @param string $key String key
2141	* @return string Sanitized key
2142	*/
2143	function sanitize_key($key)
2144	{
2145	$raw_key = $key;
2146	$key = strtolower($key);
2147	$key = preg_replace('/[^a-z0-9_\-]/', '', $key);
2148
2149	/**
2150	* Filters a sanitized key string.
2151	*
2152	* @since 3.0.0
2153	*
2154	* @param string $key Sanitized key.
2155	* @param string $raw_key The key prior to sanitization.
2156	*/
2157	return apply_filters('sanitize_key', $key, $raw_key);
2158	}
2159
2160	/**
2161	* Sanitizes a title, or returns a fallback title.
2162	*
2163	* Specifically, HTML and PHP tags are stripped. Further actions can be added
2164	* via the plugin API. If $title is empty and $fallback_title is set, the latter
2165	* will be used.
2166	*
2167	* @since 1.0.0
2168	*
2169	* @param string $title The string to be sanitized.
2170	* @param string $fallback_title Optional. A title to use if $title is empty.
2171	* @param string $context Optional. The operation for which the string is sanitized
2172	* @return string The sanitized string.
2173	*/
2174	function sanitize_title($title, $fallback_title = '', $context = 'save')
2175	{
2176	$raw_title = $title;
2177
2178	if ('save' == $context) {
2179	$title = remove_accents($title);
2180	}
2181
2182	/**
2183	* Filters a sanitized title string.
2184	*
2185	* @since 1.2.0
2186	*
2187	* @param string $title Sanitized title.
2188	* @param string $raw_title The title prior to sanitization.
2189	* @param string $context The context for which the title is being sanitized.
2190	*/
2191	$title = apply_filters('sanitize_title', $title, $raw_title, $context);
2192
2193	if ('' === $title \|\| false === $title) {
2194	$title = $fallback_title;
2195	}
2196
2197	return $title;
2198	}
2199
2200	/**
2201	* Sanitizes a title with the 'query' context.
2202	*
2203	* Used for querying the database for a value from URL.
2204	*
2205	* @since 3.1.0
2206	*
2207	* @param string $title The string to be sanitized.
2208	* @return string The sanitized string.
2209	*/
2210	function sanitize_title_for_query($title)
2211	{
2212	return sanitize_title($title, '', 'query');
2213	}
2214
2215	/**
2216	* Sanitizes a title, replacing whitespace and a few other characters with dashes.
2217	*
2218	* Limits the output to alphanumeric characters, underscore (_) and dash (-).
2219	* Whitespace becomes a dash.
2220	*
2221	* @since 1.2.0
2222	*
2223	* @param string $title The title to be sanitized.
2224	* @param string $raw_title Optional. Not used.
2225	* @param string $context Optional. The operation for which the string is sanitized.
2226	* @return string The sanitized title.
2227	*/
2228	function sanitize_title_with_dashes($title, $raw_title = '', $context = 'display')
2229	{
2230	$title = strip_tags($title);
2231	// Preserve escaped octets.
2232	$title = preg_replace('\|%([a-fA-F0-9][a-fA-F0-9])\|', '---$1---', $title);
2233	// Remove percent signs that are not part of an octet.
2234	$title = str_replace('%', '', $title);
2235	// Restore octets.
2236	$title = preg_replace('\|---([a-fA-F0-9][a-fA-F0-9])---\|', '%$1', $title);
2237
2238	if (seems_utf8($title)) {
2239	if (function_exists('mb_strtolower')) {
2240	$title = mb_strtolower($title, 'UTF-8');
2241	}
2242	$title = utf8_uri_encode($title, 200);
2243	}
2244
2245	$title = strtolower($title);
2246
2247	if ('save' == $context) {
2248	// Convert nbsp, ndash and mdash to hyphens
2249	$title = str_replace(array( '%c2%a0', '%e2%80%93', '%e2%80%94' ), '-', $title);
2250	// Convert nbsp, ndash and mdash HTML entities to hyphens
2251	$title = str_replace(array( ' ', ' ', '–', '–', '—', '—' ), '-', $title);
2252	// Convert forward slash to hyphen
2253	$title = str_replace('/', '-', $title);
2254
2255	// Strip these characters entirely
2256	$title = str_replace(
2257	array(
2258	// iexcl and iquest
2259	'%c2%a1',
2260	'%c2%bf',
2261	// angle quotes
2262	'%c2%ab',
2263	'%c2%bb',
2264	'%e2%80%b9',
2265	'%e2%80%ba',
2266	// curly quotes
2267	'%e2%80%98',
2268	'%e2%80%99',
2269	'%e2%80%9c',
2270	'%e2%80%9d',
2271	'%e2%80%9a',
2272	'%e2%80%9b',
2273	'%e2%80%9e',
2274	'%e2%80%9f',
2275	// copy, reg, deg, hellip and trade
2276	'%c2%a9',
2277	'%c2%ae',
2278	'%c2%b0',
2279	'%e2%80%a6',
2280	'%e2%84%a2',
2281	// acute accents
2282	'%c2%b4',
2283	'%cb%8a',
2284	'%cc%81',
2285	'%cd%81',
2286	// grave accent, macron, caron
2287	'%cc%80',
2288	'%cc%84',
2289	'%cc%8c',
2290	),
2291	'',
2292	$title
2293	);
2294
2295	// Convert times to x
2296	$title = str_replace('%c3%97', 'x', $title);
2297	}
2298
2299	$title = preg_replace('/&.+?;/', '', $title); // kill entities
2300	$title = str_replace('.', '-', $title);
2301
2302	$title = preg_replace('/[^%a-z0-9 _-]/', '', $title);
2303	$title = preg_replace('/\s+/', '-', $title);
2304	$title = preg_replace('\|-+\|', '-', $title);
2305	$title = trim($title, '-');
2306
2307	return $title;
2308	}
2309
2310	/**
2311	* Ensures a string is a valid SQL 'order by' clause.
2312	*
2313	* Accepts one or more columns, with or without a sort order (ASC / DESC).
2314	* e.g. 'column_1', 'column_1, column_2', 'column_1 ASC, column_2 DESC' etc.
2315	*
2316	* Also accepts 'RAND()'.
2317	*
2318	* @since 2.5.1
2319	*
2320	* @param string $orderby Order by clause to be validated.
2321	* @return string\|false Returns $orderby if valid, false otherwise.
2322	*/
2323	function sanitize_sql_orderby($orderby)
2324	{
2325	if (preg_match('/^\s(([a-z0-9_]+\|`[a-z0-9_]+`)(\s+(ASC\|DESC))?\s(,\s(?=[a-z0-9_`])\|$))+$/i', $orderby) \|\| preg_match('/^\sRAND$\s$\s$/i', $orderby)) {
2326	return $orderby;
2327	}
2328	return false;
2329	}
2330
2331	/**
2332	* Sanitizes an HTML classname to ensure it only contains valid characters.
2333	*
2334	* Strips the string down to A-Z,a-z,0-9,_,-. If this results in an empty
2335	* string then it will return the alternative value supplied.
2336	*
2337	* @todo Expand to support the full range of CDATA that a class attribute can contain.
2338	*
2339	* @since 2.8.0
2340	*
2341	* @param string $class The classname to be sanitized
2342	* @param string $fallback Optional. The value to return if the sanitization ends up as an empty string.
2343	* Defaults to an empty string.
2344	* @return string The sanitized value
2345	*/
2346	function sanitize_html_class($class, $fallback = '')
2347	{
2348	//Strip out any % encoded octets
2349	$sanitized = preg_replace('\|%[a-fA-F0-9][a-fA-F0-9]\|', '', $class);
2350
2351	//Limit to A-Z,a-z,0-9,_,-
2352	$sanitized = preg_replace('/[^A-Za-z0-9_-]/', '', $sanitized);
2353
2354	if ('' == $sanitized && $fallback) {
2355	return sanitize_html_class($fallback);
2356	}
2357	/**
2358	* Filters a sanitized HTML class string.
2359	*
2360	* @since 2.8.0
2361	*
2362	* @param string $sanitized The sanitized HTML class.
2363	* @param string $class HTML class before sanitization.
2364	* @param string $fallback The fallback string.
2365	*/
2366	return apply_filters('sanitize_html_class', $sanitized, $class, $fallback);
2367	}
2368
2369	/**
2370	* Converts lone & characters into `&` (a.k.a. `&`)
2371	*
2372	* @since 0.71
2373	*
2374	* @param string $content String of characters to be converted.
2375	* @param string $deprecated Not used.
2376	* @return string Converted string.
2377	*/
2378	function convert_chars($content, $deprecated = '')
2379	{
2380	if (! empty($deprecated)) {
2381	_deprecated_argument(__FUNCTION__, '0.71');
2382	}
2383
2384	if (strpos($content, '&') !== false) {
2385	$content = preg_replace('/&([^#])(?![a-z1-4]{1,8};)/i', '&$1', $content);
2386	}
2387
2388	return $content;
2389	}
2390
2391	/**
2392	* Converts invalid Unicode references range to valid range.
2393	*
2394	* @since 4.3.0
2395	*
2396	* @param string $content String with entities that need converting.
2397	* @return string Converted string.
2398	*/
2399	function convert_invalid_entities($content)
2400	{
2401	$wp_htmltranswinuni = array(
2402	'' => '€', // the Euro sign
2403	'' => '',
2404	'' => '‚', // these are Windows CP1252 specific characters
2405	'' => 'ƒ', // they would look weird on non-Windows browsers
2406	'' => '„',
2407	'' => '…',
2408	'' => '†',
2409	'' => '‡',
2410	'' => 'ˆ',
2411	'' => '‰',
2412	'' => 'Š',
2413	'' => '‹',
2414	'' => 'Œ',
2415	'' => '',
2416	'' => 'Ž',
2417	'' => '',
2418	'' => '',
2419	'' => '‘',
2420	'' => '’',
2421	'' => '“',
2422	'' => '”',
2423	'' => '•',
2424	'' => '–',
2425	'' => '—',
2426	'' => '˜',
2427	'' => '™',
2428	'' => 'š',
2429	'' => '›',
2430	'' => 'œ',
2431	'' => '',
2432	'' => 'ž',
2433	'' => 'Ÿ',
2434	);
2435
2436	if (strpos($content, '&#1') !== false) {
2437	$content = strtr($content, $wp_htmltranswinuni);
2438	}
2439
2440	return $content;
2441	}
2442
2443	/**
2444	* Balances tags if forced to, or if the 'use_balanceTags' option is set to true.
2445	*
2446	* @since 0.71
2447	*
2448	* @param string $text Text to be balanced
2449	* @param bool $force If true, forces balancing, ignoring the value of the option. Default false.
2450	* @return string Balanced text
2451	*/
2452	function balanceTags($text, $force = false)
2453	{
2454	if ($force \|\| get_option('use_balanceTags') == 1) {
2455	return force_balance_tags($text);
2456	} else {
2457	return $text;
2458	}
2459	}
2460
2461	/**
2462	* Balances tags of string using a modified stack.
2463	*
2464	* @since 2.0.4
2465	*
2466	* @author Leonard Lin <leonard@acm.org>
2467	* @license GPL
2468	* @copyright November 4, 2001
2469	* @version 1.1
2470	* @todo Make better - change loop condition to $text in 1.2
2471	* @internal Modified by Scott Reilly (coffee2code) 02 Aug 2004
2472	* 1.1 Fixed handling of append/stack pop order of end text
2473	* Added Cleaning Hooks
2474	* 1.0 First Version
2475	*
2476	* @param string $text Text to be balanced.
2477	* @return string Balanced text.
2478	*/
2479	function force_balance_tags($text)
2480	{
2481	$tagstack = array();
2482	$stacksize = 0;
2483	$tagqueue = '';
2484	$newtext = '';
2485	// Known single-entity/self-closing tags
2486	$single_tags = array( 'area', 'base', 'basefont', 'br', 'col', 'command', 'embed', 'frame', 'hr', 'img', 'input', 'isindex', 'link', 'meta', 'param', 'source' );
2487	// Tags that can be immediately nested within themselves
2488	$nestable_tags = array( 'blockquote', 'div', 'object', 'q', 'span' );
2489
2490	// WP bug fix for comments - in case you REALLY meant to type '< !--'
2491	$text = str_replace('< !--', '< !--', $text);
2492	// WP bug fix for LOVE <3 (and other situations with '<' before a number)
2493	$text = preg_replace('#<([0-9]{1})#', '<$1', $text);
2494
2495	while (preg_match('/<(\/?[\w:])\s([^>]*)>/', $text, $regex)) {
2496	$newtext .= $tagqueue;
2497
2498	$i = strpos($text, $regex[0]);
2499	$l = strlen($regex[0]);
2500
2501	// clear the shifter
2502	$tagqueue = '';
2503	// Pop or Push
2504	if (isset($regex[1][0]) && '/' == $regex[1][0]) { // End Tag
2505	$tag = strtolower(substr($regex[1], 1));
2506	// if too many closing tags
2507	if ($stacksize <= 0) {
2508	$tag = '';
2509	// or close to be safe $tag = '/' . $tag;
2510	} // if stacktop value = tag close value then pop
2511	elseif ($tagstack[ $stacksize - 1 ] == $tag) { // found closing tag
2512	$tag = '</' . $tag . '>'; // Close Tag
2513	// Pop
2514	array_pop($tagstack);
2515	$stacksize--;
2516	} else { // closing tag not at top, search for it
2517	for ($j = $stacksize - 1; $j >= 0; $j--) {
2518	if ($tagstack[ $j ] == $tag) {
2519	// add tag to tagqueue
2520	for ($k = $stacksize - 1; $k >= $j; $k--) {
2521	$tagqueue .= '</' . array_pop($tagstack) . '>';
2522	$stacksize--;
2523	}
2524	break;
2525	}
2526	}
2527	$tag = '';
2528	}
2529	} else { // Begin Tag
2530	$tag = strtolower($regex[1]);
2531
2532	// Tag Cleaning
2533
2534	// If it's an empty tag "< >", do nothing
2535	if ('' == $tag) {
2536	// do nothing
2537	} // ElseIf it presents itself as a self-closing tag...
2538	elseif (substr($regex[2], -1) == '/') {
2539	// ...but it isn't a known single-entity self-closing tag, then don't let it be treated as such and
2540	// immediately close it with a closing tag (the tag will encapsulate no text as a result)
2541	if (! in_array($tag, $single_tags)) {
2542	$regex[2] = trim(substr($regex[2], 0, -1)) . "></$tag";
2543	}
2544	} // ElseIf it's a known single-entity tag but it doesn't close itself, do so
2545	elseif (in_array($tag, $single_tags)) {
2546	$regex[2] .= '/';
2547	} // Else it's not a single-entity tag
2548	else {
2549	// If the top of the stack is the same as the tag we want to push, close previous tag
2550	if ($stacksize > 0 && ! in_array($tag, $nestable_tags) && $tagstack[ $stacksize - 1 ] == $tag) {
2551	$tagqueue = '</' . array_pop($tagstack) . '>';
2552	$stacksize--;
2553	}
2554	$stacksize = array_push($tagstack, $tag);
2555	}
2556
2557	// Attributes
2558	$attributes = $regex[2];
2559	if (! empty($attributes) && $attributes[0] != '>') {
2560	$attributes = ' ' . $attributes;
2561	}
2562
2563	$tag = '<' . $tag . $attributes . '>';
2564	//If already queuing a close tag, then put this tag on, too
2565	if (! empty($tagqueue)) {
2566	$tagqueue .= $tag;
2567	$tag = '';
2568	}
2569	}
2570	$newtext .= substr($text, 0, $i) . $tag;
2571	$text = substr($text, $i + $l);
2572	}
2573
2574	// Clear Tag Queue
2575	$newtext .= $tagqueue;
2576
2577	// Add Remaining text
2578	$newtext .= $text;
2579
2580	// Empty Stack
2581	while ($x = array_pop($tagstack)) {
2582	$newtext .= '</' . $x . '>'; // Add remaining tags to close
2583	}
2584
2585	// WP fix for the bug with HTML comments
2586	$newtext = str_replace('< !--', '<!--', $newtext);
2587	$newtext = str_replace('< !--', '< !--', $newtext);
2588
2589	return $newtext;
2590	}
2591
2592	/**
2593	* Acts on text which is about to be edited.
2594	*
2595	* The $content is run through esc_textarea(), which uses htmlspecialchars()
2596	* to convert special characters to HTML entities. If `$richedit` is set to true,
2597	* it is simply a holder for the {@see 'format_to_edit'} filter.
2598	*
2599	* @since 0.71
2600	* @since 4.4.0 The `$richedit` parameter was renamed to `$rich_text` for clarity.
2601	*
2602	* @param string $content The text about to be edited.
2603	* @param bool $rich_text Optional. Whether `$content` should be considered rich text,
2604	* in which case it would not be passed through esc_textarea().
2605	* Default false.
2606	* @return string The text after the filter (and possibly htmlspecialchars()) has been run.
2607	*/
2608	function format_to_edit($content, $rich_text = false)
2609	{
2610	/**
2611	* Filters the text to be formatted for editing.
2612	*
2613	* @since 1.2.0
2614	*
2615	* @param string $content The text, prior to formatting for editing.
2616	*/
2617	$content = apply_filters('format_to_edit', $content);
2618	if (! $rich_text) {
2619	$content = esc_textarea($content);
2620	}
2621	return $content;
2622	}
2623
2624	/**
2625	* Add leading zeros when necessary.
2626	*
2627	* If you set the threshold to '4' and the number is '10', then you will get
2628	* back '0010'. If you set the threshold to '4' and the number is '5000', then you
2629	* will get back '5000'.
2630	*
2631	* Uses sprintf to append the amount of zeros based on the $threshold parameter
2632	* and the size of the number. If the number is large enough, then no zeros will
2633	* be appended.
2634	*
2635	* @since 0.71
2636	*
2637	* @param int $number Number to append zeros to if not greater than threshold.
2638	* @param int $threshold Digit places number needs to be to not have zeros added.
2639	* @return string Adds leading zeros to number if needed.
2640	*/
2641	function zeroise($number, $threshold)
2642	{
2643	return sprintf('%0' . $threshold . 's', $number);
2644	}
2645
2646	/**
2647	* Adds backslashes before letters and before a number at the start of a string.
2648	*
2649	* @since 0.71
2650	*
2651	* @param string $string Value to which backslashes will be added.
2652	* @return string String with backslashes inserted.
2653	*/
2654	function backslashit($string)
2655	{
2656	if (isset($string[0]) && $string[0] >= '0' && $string[0] <= '9') {
2657	$string = '\\\\' . $string;
2658	}
2659	return addcslashes($string, 'A..Za..z');
2660	}
2661
2662	/**
2663	* Appends a trailing slash.
2664	*
2665	* Will remove trailing forward and backslashes if it exists already before adding
2666	* a trailing forward slash. This prevents double slashing a string or path.
2667	*
2668	* The primary use of this is for paths and thus should be used for paths. It is
2669	* not restricted to paths and offers no specific path support.
2670	*
2671	* @since 1.2.0
2672	*
2673	* @param string $string What to add the trailing slash to.
2674	* @return string String with trailing slash added.
2675	*/
2676	function trailingslashit($string)
2677	{
2678	return untrailingslashit($string) . '/';
2679	}
2680
2681	/**
2682	* Removes trailing forward slashes and backslashes if they exist.
2683	*
2684	* The primary use of this is for paths and thus should be used for paths. It is
2685	* not restricted to paths and offers no specific path support.
2686	*
2687	* @since 2.2.0
2688	*
2689	* @param string $string What to remove the trailing slashes from.
2690	* @return string String without the trailing slashes.
2691	*/
2692	function untrailingslashit($string)
2693	{
2694	return rtrim($string, '/\\');
2695	}
2696
2697	/**
2698	* Adds slashes to escape strings.
2699	*
2700	* Slashes will first be removed if magic_quotes_gpc is set, see {@link
2701	* https://secure.php.net/magic_quotes} for more details.
2702	*
2703	* @since 0.71
2704	*
2705	* @param string $gpc The string returned from HTTP request data.
2706	* @return string Returns a string escaped with slashes.
2707	*/
2708	function addslashes_gpc($gpc)
2709	{
2710	if (get_magic_quotes_gpc()) {
2711	$gpc = stripslashes($gpc);
2712	}
2713
2714	return wp_slash($gpc);
2715	}
2716
2717	/**
2718	* Navigates through an array, object, or scalar, and removes slashes from the values.
2719	*
2720	* @since 2.0.0
2721	*
2722	* @param mixed $value The value to be stripped.
2723	* @return mixed Stripped value.
2724	*/
2725	function stripslashes_deep($value)
2726	{
2727	return map_deep($value, 'stripslashes_from_strings_only');
2728	}
2729
2730	/**
2731	* Callback function for `stripslashes_deep()` which strips slashes from strings.
2732	*
2733	* @since 4.4.0
2734	*
2735	* @param mixed $value The array or string to be stripped.
2736	* @return mixed $value The stripped value.
2737	*/
2738	function stripslashes_from_strings_only($value)
2739	{
2740	return is_string($value) ? stripslashes($value) : $value;
2741	}
2742
2743	/**
2744	* Navigates through an array, object, or scalar, and encodes the values to be used in a URL.
2745	*
2746	* @since 2.2.0
2747	*
2748	* @param mixed $value The array or string to be encoded.
2749	* @return mixed $value The encoded value.
2750	*/
2751	function urlencode_deep($value)
2752	{
2753	return map_deep($value, 'urlencode');
2754	}
2755
2756	/**
2757	* Navigates through an array, object, or scalar, and raw-encodes the values to be used in a URL.
2758	*
2759	* @since 3.4.0
2760	*
2761	* @param mixed $value The array or string to be encoded.
2762	* @return mixed $value The encoded value.
2763	*/
2764	function rawurlencode_deep($value)
2765	{
2766	return map_deep($value, 'rawurlencode');
2767	}
2768
2769	/**
2770	* Navigates through an array, object, or scalar, and decodes URL-encoded values
2771	*
2772	* @since 4.4.0
2773	*
2774	* @param mixed $value The array or string to be decoded.
2775	* @return mixed $value The decoded value.
2776	*/
2777	function urldecode_deep($value)
2778	{
2779	return map_deep($value, 'urldecode');
2780	}
2781
2782	/**
2783	* Converts email addresses characters to HTML entities to block spam bots.
2784	*
2785	* @since 0.71
2786	*
2787	* @param string $email_address Email address.
2788	* @param int $hex_encoding Optional. Set to 1 to enable hex encoding.
2789	* @return string Converted email address.
2790	*/
2791	function antispambot($email_address, $hex_encoding = 0)
2792	{
2793	$email_no_spam_address = '';
2794	for ($i = 0, $len = strlen($email_address); $i < $len; $i++) {
2795	$j = rand(0, 1 + $hex_encoding);
2796	if ($j == 0) {
2797	$email_no_spam_address .= '&#' . ord($email_address[ $i ]) . ';';
2798	} elseif ($j == 1) {
2799	$email_no_spam_address .= $email_address[ $i ];
2800	} elseif ($j == 2) {
2801	$email_no_spam_address .= '%' . zeroise(dechex(ord($email_address[ $i ])), 2);
2802	}
2803	}
2804
2805	return str_replace('@', '@', $email_no_spam_address);
2806	}
2807
2808	/**
2809	* Callback to convert URI match to HTML A element.
2810	*
2811	* This function was backported from 2.5.0 to 2.3.2. Regex callback for make_clickable().
2812	*
2813	* @since 2.3.2
2814	* @access private
2815	*
2816	* @param array $matches Single Regex Match.
2817	* @return string HTML A element with URI address.
2818	*/
2819	function _make_url_clickable_cb($matches)
2820	{
2821	$url = $matches[2];
2822
2823	if (')' == $matches[3] && strpos($url, '(')) {
2824	// If the trailing character is a closing parethesis, and the URL has an opening parenthesis in it, add the closing parenthesis to the URL.
2825	// Then we can let the parenthesis balancer do its thing below.
2826	$url .= $matches[3];
2827	$suffix = '';
2828	} else {
2829	$suffix = $matches[3];
2830	}
2831
2832	// Include parentheses in the URL only if paired
2833	while (substr_count($url, '(') < substr_count($url, ')')) {
2834	$suffix = strrchr($url, ')') . $suffix;
2835	$url = substr($url, 0, strrpos($url, ')'));
2836	}
2837
2838	$url = esc_url($url);
2839	if (empty($url)) {
2840	return $matches[0];
2841	}
2842
2843	return $matches[1] . "<a href=\"$url\" rel=\"nofollow\">$url</a>" . $suffix;
2844	}
2845
2846	/**
2847	* Callback to convert URL match to HTML A element.
2848	*
2849	* This function was backported from 2.5.0 to 2.3.2. Regex callback for make_clickable().
2850	*
2851	* @since 2.3.2
2852	* @access private
2853	*
2854	* @param array $matches Single Regex Match.
2855	* @return string HTML A element with URL address.
2856	*/
2857	function _make_web_ftp_clickable_cb($matches)
2858	{
2859	$ret = '';
2860	$dest = $matches[2];
2861	$dest = 'http://' . $dest;
2862
2863	// removed trailing [.,;:)] from URL
2864	if (in_array(substr($dest, -1), array( '.', ',', ';', ':', ')' )) === true) {
2865	$ret = substr($dest, -1);
2866	$dest = substr($dest, 0, strlen($dest) - 1);
2867	}
2868
2869	$dest = esc_url($dest);
2870	if (empty($dest)) {
2871	return $matches[0];
2872	}
2873
2874	return $matches[1] . "<a href=\"$dest\" rel=\"nofollow\">$dest</a>$ret";
2875	}
2876
2877	/**
2878	* Callback to convert email address match to HTML A element.
2879	*
2880	* This function was backported from 2.5.0 to 2.3.2. Regex callback for make_clickable().
2881	*
2882	* @since 2.3.2
2883	* @access private
2884	*
2885	* @param array $matches Single Regex Match.
2886	* @return string HTML A element with email address.
2887	*/
2888	function _make_email_clickable_cb($matches)
2889	{
2890	$email = $matches[2] . '@' . $matches[3];
2891	return $matches[1] . "<a href=\"mailto:$email\">$email</a>";
2892	}
2893
2894	/**
2895	* Convert plaintext URI to HTML links.
2896	*
2897	* Converts URI, www and ftp, and email addresses. Finishes by fixing links
2898	* within links.
2899	*
2900	* @since 0.71
2901	*
2902	* @param string $text Content to convert URIs.
2903	* @return string Content with converted URIs.
2904	*/
2905	function make_clickable($text)
2906	{
2907	$r = '';
2908	$textarr = preg_split('/(<[^<>]+>)/', $text, -1, PREG_SPLIT_DELIM_CAPTURE); // split out HTML tags
2909	$nested_code_pre = 0; // Keep track of how many levels link is nested inside <pre> or <code>
2910	foreach ($textarr as $piece) {
2911	if (preg_match('\|^<code[\s>]\|i', $piece) \|\| preg_match('\|^<pre[\s>]\|i', $piece) \|\| preg_match('\|^<script[\s>]\|i', $piece) \|\| preg_match('\|^<style[\s>]\|i', $piece)) {
2912	$nested_code_pre++;
2913	} elseif ($nested_code_pre && ( '</code>' === strtolower($piece) \|\| '</pre>' === strtolower($piece) \|\| '</script>' === strtolower($piece) \|\| '</style>' === strtolower($piece) )) {
2914	$nested_code_pre--;
2915	}
2916
2917	if ($nested_code_pre \|\| empty($piece) \|\| ( $piece[0] === '<' && ! preg_match('\|^<\s*[\w]{1,20}+://\|', $piece) )) {
2918	$r .= $piece;
2919	continue;
2920	}
2921
2922	// Long strings might contain expensive edge cases ...
2923	if (10000 < strlen($piece)) {
2924	// ... break it up
2925	foreach (_split_str_by_whitespace($piece, 2100) as $chunk) { // 2100: Extra room for scheme and leading and trailing paretheses
2926	if (2101 < strlen($chunk)) {
2927	$r .= $chunk; // Too big, no whitespace: bail.
2928	} else {
2929	$r .= make_clickable($chunk);
2930	}
2931	}
2932	} else {
2933	$ret = " $piece "; // Pad with whitespace to simplify the regexes
2934
2935	$url_clickable = '~
2936	([\\s(<.,;:!?]) # 1: Leading whitespace, or punctuation
2937	( # 2: URL
2938	[\\w]{1,20}+:// # Scheme and hier-part prefix
2939	(?=\S{1,2000}\s) # Limit to URLs less than about 2000 characters long
2940	[\\w\\x80-\\xff#%\\~/@\\[\\](+=&$-]+ # Non-punctuation URL character
2941	(?: # Unroll the Loop: Only allow puctuation URL character if followed by a non-punctuation URL character
2942	[\'.,;:!?)] # Punctuation URL character
2943	[\\w\\x80-\\xff#%\\~/@\\[\\]*(+=&$-]++ # Non-punctuation URL character
2944	)*
2945	)
2946	(\)?) # 3: Trailing closing parenthesis (for parethesis balancing post processing)
2947	~xS'; // The regex is a non-anchored pattern and does not have a single fixed starting character.
2948	// Tell PCRE to spend more time optimizing since, when used on a page load, it will probably be used several times.
2949
2950	$ret = preg_replace_callback($url_clickable, '_make_url_clickable_cb', $ret);
2951
2952	$ret = preg_replace_callback('#([\s>])((www\|ftp)\.[\w\\x80-\\xff\#$%&~/.\-;:=,?@\[\]+]+)#is', '_make_web_ftp_clickable_cb', $ret);
2953	$ret = preg_replace_callback('#([\s>])([.0-9a-z_+-]+)@(([0-9a-z-]+\.)+[0-9a-z]{2,})#i', '_make_email_clickable_cb', $ret);
2954
2955	$ret = substr($ret, 1, -1); // Remove our whitespace padding.
2956	$r .= $ret;
2957	}
2958	}
2959
2960	// Cleanup of accidental links within links
2961	return preg_replace('#(<a([ \r\n\t]+[^>]+?>\|>))<a [^>]+?>([^>]+?)</a></a>#i', '$1$3</a>', $r);
2962	}
2963
2964	/**
2965	* Breaks a string into chunks by splitting at whitespace characters.
2966	* The length of each returned chunk is as close to the specified length goal as possible,
2967	* with the caveat that each chunk includes its trailing delimiter.
2968	* Chunks longer than the goal are guaranteed to not have any inner whitespace.
2969	*
2970	* Joining the returned chunks with empty delimiters reconstructs the input string losslessly.
2971	*
2972	* Input string must have no null characters (or eventual transformations on output chunks must not care about null characters)
2973	*
2974	* _split_str_by_whitespace( "1234 67890 1234 67890a cd 1234 890 123456789 1234567890a 45678 1 3 5 7 90 ", 10 ) ==
2975	* array (
2976	* 0 => '1234 67890 ', // 11 characters: Perfect split
2977	* 1 => '1234 ', // 5 characters: '1234 67890a' was too long
2978	* 2 => '67890a cd ', // 10 characters: '67890a cd 1234' was too long
2979	* 3 => '1234 890 ', // 11 characters: Perfect split
2980	* 4 => '123456789 ', // 10 characters: '123456789 1234567890a' was too long
2981	* 5 => '1234567890a ', // 12 characters: Too long, but no inner whitespace on which to split
2982	* 6 => ' 45678 ', // 11 characters: Perfect split
2983	* 7 => '1 3 5 7 90 ', // 11 characters: End of $string
2984	* );
2985	*
2986	* @since 3.4.0
2987	* @access private
2988	*
2989	* @param string $string The string to split.
2990	* @param int $goal The desired chunk length.
2991	* @return array Numeric array of chunks.
2992	*/
2993	function _split_str_by_whitespace($string, $goal)
2994	{
2995	$chunks = array();
2996
2997	$string_nullspace = strtr($string, "\r\n\t\v\f ", "\000\000\000\000\000\000");
2998
2999	while ($goal < strlen($string_nullspace)) {
3000	$pos = strrpos(substr($string_nullspace, 0, $goal + 1), "\000");
3001
3002	if (false === $pos) {
3003	$pos = strpos($string_nullspace, "\000", $goal + 1);
3004	if (false === $pos) {
3005	break;
3006	}
3007	}
3008
3009	$chunks[] = substr($string, 0, $pos + 1);
3010	$string = substr($string, $pos + 1);
3011	$string_nullspace = substr($string_nullspace, $pos + 1);
3012	}
3013
3014	if ($string) {
3015	$chunks[] = $string;
3016	}
3017
3018	return $chunks;
3019	}
3020
3021	/**
3022	* Adds rel nofollow string to all HTML A elements in content.
3023	*
3024	* @since 1.5.0
3025	*
3026	* @param string $text Content that may contain HTML A elements.
3027	* @return string Converted content.
3028	*/
3029	function wp_rel_nofollow($text)
3030	{
3031	// This is a pre save filter, so text is already escaped.
3032	$text = stripslashes($text);
3033	$text = preg_replace_callback('\|<a (.+?)>\|i', 'wp_rel_nofollow_callback', $text);
3034	return wp_slash($text);
3035	}
3036
3037	/**
3038	* Callback to add rel=nofollow string to HTML A element.
3039	*
3040	* Will remove already existing rel="nofollow" and rel='nofollow' from the
3041	* string to prevent from invalidating (X)HTML.
3042	*
3043	* @since 2.3.0
3044	*
3045	* @param array $matches Single Match
3046	* @return string HTML A Element with rel nofollow.
3047	*/
3048	function wp_rel_nofollow_callback($matches)
3049	{
3050	$text = $matches[1];
3051	$atts = shortcode_parse_atts($matches[1]);
3052	$rel = 'nofollow';
3053
3054	if (preg_match('%href=["\'](' . preg_quote(set_url_scheme(home_url(), 'http')) . ')%i', $text) \|\|
3055	preg_match('%href=["\'](' . preg_quote(set_url_scheme(home_url(), 'https')) . ')%i', $text) ) {
3056	return "<a $text>";
3057	}
3058
3059	if (! empty($atts['rel'])) {
3060	$parts = array_map('trim', explode(' ', $atts['rel']));
3061	if (false === array_search('nofollow', $parts)) {
3062	$parts[] = 'nofollow';
3063	}
3064	$rel = implode(' ', $parts);
3065	unset($atts['rel']);
3066
3067	$html = '';
3068	foreach ($atts as $name => $value) {
3069	$html .= "{$name}=\"$value\" ";
3070	}
3071	$text = trim($html);
3072	}
3073	return "<a $text rel=\"$rel\">";
3074	}
3075
3076	/**
3077	* Adds rel noreferrer and noopener to all HTML A elements that have a target.
3078	*
3079	* @param string $text Content that may contain HTML A elements.
3080	* @return string Converted content.
3081	*/
3082	function wp_targeted_link_rel($text)
3083	{
3084	// Don't run (more expensive) regex if no links with targets.
3085	if (stripos($text, 'target') !== false && stripos($text, '<a ') !== false) {
3086	$text = preg_replace_callback('\|<a\s([^>]target\s=[^>]*)>\|i', 'wp_targeted_link_rel_callback', $text);
3087	}
3088
3089	return $text;
3090	}
3091
3092	/**
3093	* Callback to add rel="noreferrer noopener" string to HTML A element.
3094	*
3095	* Will not duplicate existing noreferrer and noopener values
3096	* to prevent from invalidating the HTML.
3097	*
3098	* @param array $matches Single Match
3099	* @return string HTML A Element with rel noreferrer noopener in addition to any existing values
3100	*/
3101	function wp_targeted_link_rel_callback($matches)
3102	{
3103	$link_html = $matches[1];
3104	$rel_match = array();
3105
3106	/**
3107	* Filters the rel values that are added to links with `target` attribute.
3108	*
3109	* @since 5.0.0
3110	*
3111	* @param string The rel values.
3112	* @param string $link_html The matched content of the link tag including all HTML attributes.
3113	*/
3114	$rel = apply_filters('wp_targeted_link_rel', 'noopener noreferrer', $link_html);
3115
3116	// Value with delimiters, spaces around are optional.
3117	$attr_regex = '\|rel\s=\s?(\\\\{0,1}["\'])(.*?)\\1\|i';
3118	preg_match($attr_regex, $link_html, $rel_match);
3119
3120	if (empty($rel_match[0])) {
3121	// No delimiters, try with a single value and spaces, because `rel = va"lue` is totally fine...
3122	$attr_regex = '\|rel\s=(\s)([^\s]*)\|i';
3123	preg_match($attr_regex, $link_html, $rel_match);
3124	}
3125
3126	if (! empty($rel_match[0])) {
3127	$parts = preg_split('\|\s+\|', strtolower($rel_match[2]));
3128	$parts = array_map('esc_attr', $parts);
3129	$needed = explode(' ', $rel);
3130	$parts = array_unique(array_merge($parts, $needed));
3131	$delimiter = trim($rel_match[1]) ? $rel_match[1] : '"';
3132	$rel = 'rel=' . $delimiter . trim(implode(' ', $parts)) . $delimiter;
3133	$link_html = str_replace($rel_match[0], $rel, $link_html);
3134	} else {
3135	$link_html .= " rel=\"$rel\"";
3136	}
3137
3138	return "<a $link_html>";
3139	}
3140
3141	/**
3142	* Convert one smiley code to the icon graphic file equivalent.
3143	*
3144	* Callback handler for convert_smilies().
3145	*
3146	* Looks up one smiley code in the $wpsmiliestrans global array and returns an
3147	* `<img>` string for that smiley.
3148	*
3149	* @since 2.8.0
3150	*
3151	* @global array $wpsmiliestrans
3152	*
3153	* @param array $matches Single match. Smiley code to convert to image.
3154	* @return string Image string for smiley.
3155	*/
3156	function translate_smiley($matches)
3157	{
3158	global $wpsmiliestrans;
3159
3160	if (count($matches) == 0) {
3161	return '';
3162	}
3163
3164	$smiley = trim(reset($matches));
3165	$img = $wpsmiliestrans[ $smiley ];
3166
3167	$matches = array();
3168	$ext = preg_match('/\.([^.]+)$/', $img, $matches) ? strtolower($matches[1]) : false;
3169	$image_exts = array( 'jpg', 'jpeg', 'jpe', 'gif', 'png' );
3170
3171	// Don't convert smilies that aren't images - they're probably emoji.
3172	if (! in_array($ext, $image_exts)) {
3173	return $img;
3174	}
3175
3176	/**
3177	* Filters the Smiley image URL before it's used in the image element.
3178	*
3179	* @since 2.9.0
3180	*
3181	* @param string $smiley_url URL for the smiley image.
3182	* @param string $img Filename for the smiley image.
3183	* @param string $site_url Site URL, as returned by site_url().
3184	*/
3185	$src_url = apply_filters('smilies_src', includes_url("images/smilies/$img"), $img, site_url());
3186
3187	return sprintf('<img src="%s" alt="%s" class="wp-smiley" style="height: 1em; max-height: 1em;" />', esc_url($src_url), esc_attr($smiley));
3188	}
3189
3190	/**
3191	* Convert text equivalent of smilies to images.
3192	*
3193	* Will only convert smilies if the option 'use_smilies' is true and the global
3194	* used in the function isn't empty.
3195	*
3196	* @since 0.71
3197	*
3198	* @global string\|array $wp_smiliessearch
3199	*
3200	* @param string $text Content to convert smilies from text.
3201	* @return string Converted content with text smilies replaced with images.
3202	*/
3203	function convert_smilies($text)
3204	{
3205	global $wp_smiliessearch;
3206	$output = '';
3207	if (get_option('use_smilies') && ! empty($wp_smiliessearch)) {
3208	// HTML loop taken from texturize function, could possible be consolidated
3209	$textarr = preg_split('/(<.*>)/U', $text, -1, PREG_SPLIT_DELIM_CAPTURE); // capture the tags as well as in between
3210	$stop = count($textarr);// loop stuff
3211
3212	// Ignore proessing of specific tags
3213	$tags_to_ignore = 'code\|pre\|style\|script\|textarea';
3214	$ignore_block_element = '';
3215
3216	for ($i = 0; $i < $stop; $i++) {
3217	$content = $textarr[ $i ];
3218
3219	// If we're in an ignore block, wait until we find its closing tag
3220	if ('' == $ignore_block_element && preg_match('/^<(' . $tags_to_ignore . ')>/', $content, $matches)) {
3221	$ignore_block_element = $matches[1];
3222	}
3223
3224	// If it's not a tag and not in ignore block
3225	if ('' == $ignore_block_element && strlen($content) > 0 && '<' != $content[0]) {
3226	$content = preg_replace_callback($wp_smiliessearch, 'translate_smiley', $content);
3227	}
3228
3229	// did we exit ignore block
3230	if ('' != $ignore_block_element && '</' . $ignore_block_element . '>' == $content) {
3231	$ignore_block_element = '';
3232	}
3233
3234	$output .= $content;
3235	}
3236	} else {
3237	// return default text.
3238	$output = $text;
3239	}
3240	return $output;
3241	}
3242
3243	/**
3244	* Verifies that an email is valid.
3245	*
3246	* Does not grok i18n domains. Not RFC compliant.
3247	*
3248	* @since 0.71
3249	*
3250	* @param string $email Email address to verify.
3251	* @param bool $deprecated Deprecated.
3252	* @return string\|bool Either false or the valid email address.
3253	*/
3254	function is_email($email, $deprecated = false)
3255	{
3256	if (! empty($deprecated)) {
3257	_deprecated_argument(__FUNCTION__, '3.0.0');
3258	}
3259
3260	// Test for the minimum length the email can be
3261	if (strlen($email) < 6) {
3262	/**
3263	* Filters whether an email address is valid.
3264	*
3265	* This filter is evaluated under several different contexts, such as 'email_too_short',
3266	* 'email_no_at', 'local_invalid_chars', 'domain_period_sequence', 'domain_period_limits',
3267	* 'domain_no_periods', 'sub_hyphen_limits', 'sub_invalid_chars', or no specific context.
3268	*
3269	* @since 2.8.0
3270	*
3271	* @param bool $is_email Whether the email address has passed the is_email() checks. Default false.
3272	* @param string $email The email address being checked.
3273	* @param string $context Context under which the email was tested.
3274	*/
3275	return apply_filters('is_email', false, $email, 'email_too_short');
3276	}
3277
3278	// Test for an @ character after the first position
3279	if (strpos($email, '@', 1) === false) {
3280	/** This filter is documented in wp-includes/formatting.php */
3281	return apply_filters('is_email', false, $email, 'email_no_at');
3282	}
3283
3284	// Split out the local and domain parts
3285	list( $local, $domain ) = explode('@', $email, 2);
3286
3287	// LOCAL PART
3288	// Test for invalid characters
3289	if (! preg_match('/^[a-zA-Z0-9!#$%&\'*+\/=?^_`{\|}~\.-]+$/', $local)) {
3290	/** This filter is documented in wp-includes/formatting.php */
3291	return apply_filters('is_email', false, $email, 'local_invalid_chars');
3292	}
3293
3294	// DOMAIN PART
3295	// Test for sequences of periods
3296	if (preg_match('/\.{2,}/', $domain)) {
3297	/** This filter is documented in wp-includes/formatting.php */
3298	return apply_filters('is_email', false, $email, 'domain_period_sequence');
3299	}
3300
3301	// Test for leading and trailing periods and whitespace
3302	if (trim($domain, " \t\n\r\0\x0B.") !== $domain) {
3303	/** This filter is documented in wp-includes/formatting.php */
3304	return apply_filters('is_email', false, $email, 'domain_period_limits');
3305	}
3306
3307	// Split the domain into subs
3308	$subs = explode('.', $domain);
3309
3310	// Assume the domain will have at least two subs
3311	if (2 > count($subs)) {
3312	/** This filter is documented in wp-includes/formatting.php */
3313	return apply_filters('is_email', false, $email, 'domain_no_periods');
3314	}
3315
3316	// Loop through each sub
3317	foreach ($subs as $sub) {
3318	// Test for leading and trailing hyphens and whitespace
3319	if (trim($sub, " \t\n\r\0\x0B-") !== $sub) {
3320	/** This filter is documented in wp-includes/formatting.php */
3321	return apply_filters('is_email', false, $email, 'sub_hyphen_limits');
3322	}
3323
3324	// Test for invalid characters
3325	if (! preg_match('/^[a-z0-9-]+$/i', $sub)) {
3326	/** This filter is documented in wp-includes/formatting.php */
3327	return apply_filters('is_email', false, $email, 'sub_invalid_chars');
3328	}
3329	}
3330
3331	// Congratulations your email made it!
3332	/** This filter is documented in wp-includes/formatting.php */
3333	return apply_filters('is_email', $email, $email, null);
3334	}
3335
3336	/**
3337	* Convert to ASCII from email subjects.
3338	*
3339	* @since 1.2.0
3340	*
3341	* @param string $string Subject line
3342	* @return string Converted string to ASCII
3343	*/
3344	function wp_iso_descrambler($string)
3345	{
3346	/* this may only work with iso-8859-1, I'm afraid */
3347	if (! preg_match('#\=\?(.+)\?Q\?(.+)\?\=#i', $string, $matches)) {
3348	return $string;
3349	} else {
3350	$subject = str_replace('_', ' ', $matches[2]);
3351	return preg_replace_callback('#\=([0-9a-f]{2})#i', '_wp_iso_convert', $subject);
3352	}
3353	}
3354
3355	/**
3356	* Helper function to convert hex encoded chars to ASCII
3357	*
3358	* @since 3.1.0
3359	* @access private
3360	*
3361	* @param array $match The preg_replace_callback matches array
3362	* @return string Converted chars
3363	*/
3364	function _wp_iso_convert($match)
3365	{
3366	return chr(hexdec(strtolower($match[1])));
3367	}
3368
3369	/**
3370	* Returns a date in the GMT equivalent.
3371	*
3372	* Requires and returns a date in the Y-m-d H:i:s format. If there is a
3373	* timezone_string available, the date is assumed to be in that timezone,
3374	* otherwise it simply subtracts the value of the 'gmt_offset' option. Return
3375	* format can be overridden using the $format parameter.
3376	*
3377	* @since 1.2.0
3378	*
3379	* @param string $string The date to be converted.
3380	* @param string $format The format string for the returned date (default is Y-m-d H:i:s)
3381	* @return string GMT version of the date provided.
3382	*/
3383	function get_gmt_from_date($string, $format = 'Y-m-d H:i:s')
3384	{
3385	$tz = get_option('timezone_string');
3386	if ($tz) {
3387	$datetime = date_create($string, new DateTimeZone($tz));
3388	if (! $datetime) {
3389	return gmdate($format, 0);
3390	}
3391	$datetime->setTimezone(new DateTimeZone('UTC'));
3392	$string_gmt = $datetime->format($format);
3393	} else {
3394	if (! 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)) {
3395	$datetime = strtotime($string);
3396	if (false === $datetime) {
3397	return gmdate($format, 0);
3398	}
3399	return gmdate($format, $datetime);
3400	}
3401	$string_time = gmmktime($matches[4], $matches[5], $matches[6], $matches[2], $matches[3], $matches[1]);
3402	$string_gmt = gmdate($format, $string_time - get_option('gmt_offset') * HOUR_IN_SECONDS);
3403	}
3404	return $string_gmt;
3405	}
3406
3407	/**
3408	* Converts a GMT date into the correct format for the blog.
3409	*
3410	* Requires and returns a date in the Y-m-d H:i:s format. If there is a
3411	* timezone_string available, the returned date is in that timezone, otherwise
3412	* it simply adds the value of gmt_offset. Return format can be overridden
3413	* using the $format parameter
3414	*
3415	* @since 1.2.0
3416	*
3417	* @param string $string The date to be converted.
3418	* @param string $format The format string for the returned date (default is Y-m-d H:i:s)
3419	* @return string Formatted date relative to the timezone / GMT offset.
3420	*/
3421	function get_date_from_gmt($string, $format = 'Y-m-d H:i:s')
3422	{
3423	$tz = get_option('timezone_string');
3424	if ($tz) {
3425	$datetime = date_create($string, new DateTimeZone('UTC'));
3426	if (! $datetime) {
3427	return date($format, 0);
3428	}
3429	$datetime->setTimezone(new DateTimeZone($tz));
3430	$string_localtime = $datetime->format($format);
3431	} else {
3432	if (! 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, $matches)) {
3433	return date($format, 0);
3434	}
3435	$string_time = gmmktime($matches[4], $matches[5], $matches[6], $matches[2], $matches[3], $matches[1]);
3436	$string_localtime = gmdate($format, $string_time + get_option('gmt_offset') * HOUR_IN_SECONDS);
3437	}
3438	return $string_localtime;
3439	}
3440
3441	/**
3442	* Computes an offset in seconds from an iso8601 timezone.
3443	*
3444	* @since 1.5.0
3445	*
3446	* @param string $timezone Either 'Z' for 0 offset or '±hhmm'.
3447	* @return int\|float The offset in seconds.
3448	*/
3449	function iso8601_timezone_to_offset($timezone)
3450	{
3451	// $timezone is either 'Z' or '[+\|-]hhmm'
3452	if ($timezone == 'Z') {
3453	$offset = 0;
3454	} else {
3455	$sign = ( substr($timezone, 0, 1) == '+' ) ? 1 : -1;
3456	$hours = intval(substr($timezone, 1, 2));
3457	$minutes = intval(substr($timezone, 3, 4)) / 60;
3458	$offset = $sign * HOUR_IN_SECONDS * ( $hours + $minutes );
3459	}
3460	return $offset;
3461	}
3462
3463	/**
3464	* Converts an iso8601 date to MySQL DateTime format used by post_date[_gmt].
3465	*
3466	* @since 1.5.0
3467	*
3468	* @param string $date_string Date and time in ISO 8601 format {@link https://en.wikipedia.org/wiki/ISO_8601}.
3469	* @param string $timezone Optional. If set to GMT returns the time minus gmt_offset. Default is 'user'.
3470	* @return string The date and time in MySQL DateTime format - Y-m-d H:i:s.
3471	*/
3472	function iso8601_to_datetime($date_string, $timezone = 'user')
3473	{
3474	$timezone = strtolower($timezone);
3475
3476	if ($timezone == 'gmt') {
3477	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, $date_bits);
3478
3479	if (! empty($date_bits[7])) { // we have a timezone, so let's compute an offset
3480	$offset = iso8601_timezone_to_offset($date_bits[7]);
3481	} else { // we don't have a timezone, so we assume user local timezone (not server's!)
3482	$offset = HOUR_IN_SECONDS * get_option('gmt_offset');
3483	}
3484
3485	$timestamp = gmmktime($date_bits[4], $date_bits[5], $date_bits[6], $date_bits[2], $date_bits[3], $date_bits[1]);
3486	$timestamp -= $offset;
3487
3488	return gmdate('Y-m-d H:i:s', $timestamp);
3489	} elseif ($timezone == 'user') {
3490	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);
3491	}
3492	}
3493
3494	/**
3495	* Strips out all characters that are not allowable in an email.
3496	*
3497	* @since 1.5.0
3498	*
3499	* @param string $email Email address to filter.
3500	* @return string Filtered email address.
3501	*/
3502	function sanitize_email($email)
3503	{
3504	// Test for the minimum length the email can be
3505	if (strlen($email) < 6) {
3506	/**
3507	* Filters a sanitized email address.
3508	*
3509	* This filter is evaluated under several contexts, including 'email_too_short',
3510	* 'email_no_at', 'local_invalid_chars', 'domain_period_sequence', 'domain_period_limits',
3511	* 'domain_no_periods', 'domain_no_valid_subs', or no context.
3512	*
3513	* @since 2.8.0
3514	*
3515	* @param string $email The sanitized email address.
3516	* @param string $email The email address, as provided to sanitize_email().
3517	* @param string $message A message to pass to the user.
3518	*/
3519	return apply_filters('sanitize_email', '', $email, 'email_too_short');
3520	}
3521
3522	// Test for an @ character after the first position
3523	if (strpos($email, '@', 1) === false) {
3524	/** This filter is documented in wp-includes/formatting.php */
3525	return apply_filters('sanitize_email', '', $email, 'email_no_at');
3526	}
3527
3528	// Split out the local and domain parts
3529	list( $local, $domain ) = explode('@', $email, 2);
3530
3531	// LOCAL PART
3532	// Test for invalid characters
3533	$local = preg_replace('/[^a-zA-Z0-9!#$%&\'*+\/=?^_`{\|}~\.-]/', '', $local);
3534	if ('' === $local) {
3535	/** This filter is documented in wp-includes/formatting.php */
3536	return apply_filters('sanitize_email', '', $email, 'local_invalid_chars');
3537	}
3538
3539	// DOMAIN PART
3540	// Test for sequences of periods
3541	$domain = preg_replace('/\.{2,}/', '', $domain);
3542	if ('' === $domain) {
3543	/** This filter is documented in wp-includes/formatting.php */
3544	return apply_filters('sanitize_email', '', $email, 'domain_period_sequence');
3545	}
3546
3547	// Test for leading and trailing periods and whitespace
3548	$domain = trim($domain, " \t\n\r\0\x0B.");
3549	if ('' === $domain) {
3550	/** This filter is documented in wp-includes/formatting.php */
3551	return apply_filters('sanitize_email', '', $email, 'domain_period_limits');
3552	}
3553
3554	// Split the domain into subs
3555	$subs = explode('.', $domain);
3556
3557	// Assume the domain will have at least two subs
3558	if (2 > count($subs)) {
3559	/** This filter is documented in wp-includes/formatting.php */
3560	return apply_filters('sanitize_email', '', $email, 'domain_no_periods');
3561	}
3562
3563	// Create an array that will contain valid subs
3564	$new_subs = array();
3565
3566	// Loop through each sub
3567	foreach ($subs as $sub) {
3568	// Test for leading and trailing hyphens
3569	$sub = trim($sub, " \t\n\r\0\x0B-");
3570
3571	// Test for invalid characters
3572	$sub = preg_replace('/[^a-z0-9-]+/i', '', $sub);
3573
3574	// If there's anything left, add it to the valid subs
3575	if ('' !== $sub) {
3576	$new_subs[] = $sub;
3577	}
3578	}
3579
3580	// If there aren't 2 or more valid subs
3581	if (2 > count($new_subs)) {
3582	/** This filter is documented in wp-includes/formatting.php */
3583	return apply_filters('sanitize_email', '', $email, 'domain_no_valid_subs');
3584	}
3585
3586	// Join valid subs into the new domain
3587	$domain = join('.', $new_subs);
3588
3589	// Put the email back together
3590	$email = $local . '@' . $domain;
3591
3592	// Congratulations your email made it!
3593	/** This filter is documented in wp-includes/formatting.php */
3594	return apply_filters('sanitize_email', $email, $email, null);
3595	}
3596
3597	/**
3598	* Determines the difference between two timestamps.
3599	*
3600	* The difference is returned in a human readable format such as "1 hour",
3601	* "5 mins", "2 days".
3602	*
3603	* @since 1.5.0
3604	*
3605	* @param int $from Unix timestamp from which the difference begins.
3606	* @param int $to Optional. Unix timestamp to end the time difference. Default becomes time() if not set.
3607	* @return string Human readable time difference.
3608	*/
3609	function human_time_diff($from, $to = '')
3610	{
3611	if (empty($to)) {
3612	$to = time();
3613	}
3614
3615	$diff = (int) abs($to - $from);
3616
3617	if ($diff < HOUR_IN_SECONDS) {
3618	$mins = round($diff / MINUTE_IN_SECONDS);
3619	if ($mins <= 1) {
3620	$mins = 1;
3621	}
3622	/* translators: Time difference between two dates, in minutes (min=minute). 1: Number of minutes */
3623	$since = sprintf(_n('%s min', '%s mins', $mins), $mins);
3624	} elseif ($diff < DAY_IN_SECONDS && $diff >= HOUR_IN_SECONDS) {
3625	$hours = round($diff / HOUR_IN_SECONDS);
3626	if ($hours <= 1) {
3627	$hours = 1;
3628	}
3629	/* translators: Time difference between two dates, in hours. 1: Number of hours */
3630	$since = sprintf(_n('%s hour', '%s hours', $hours), $hours);
3631	} elseif ($diff < WEEK_IN_SECONDS && $diff >= DAY_IN_SECONDS) {
3632	$days = round($diff / DAY_IN_SECONDS);
3633	if ($days <= 1) {
3634	$days = 1;
3635	}
3636	/* translators: Time difference between two dates, in days. 1: Number of days */
3637	$since = sprintf(_n('%s day', '%s days', $days), $days);
3638	} elseif ($diff < MONTH_IN_SECONDS && $diff >= WEEK_IN_SECONDS) {
3639	$weeks = round($diff / WEEK_IN_SECONDS);
3640	if ($weeks <= 1) {
3641	$weeks = 1;
3642	}
3643	/* translators: Time difference between two dates, in weeks. 1: Number of weeks */
3644	$since = sprintf(_n('%s week', '%s weeks', $weeks), $weeks);
3645	} elseif ($diff < YEAR_IN_SECONDS && $diff >= MONTH_IN_SECONDS) {
3646	$months = round($diff / MONTH_IN_SECONDS);
3647	if ($months <= 1) {
3648	$months = 1;
3649	}
3650	/* translators: Time difference between two dates, in months. 1: Number of months */
3651	$since = sprintf(_n('%s month', '%s months', $months), $months);
3652	} elseif ($diff >= YEAR_IN_SECONDS) {
3653	$years = round($diff / YEAR_IN_SECONDS);
3654	if ($years <= 1) {
3655	$years = 1;
3656	}
3657	/* translators: Time difference between two dates, in years. 1: Number of years */
3658	$since = sprintf(_n('%s year', '%s years', $years), $years);
3659	}
3660
3661	/**
3662	* Filters the human readable difference between two timestamps.
3663	*
3664	* @since 4.0.0
3665	*
3666	* @param string $since The difference in human readable text.
3667	* @param int $diff The difference in seconds.
3668	* @param int $from Unix timestamp from which the difference begins.
3669	* @param int $to Unix timestamp to end the time difference.
3670	*/
3671	return apply_filters('human_time_diff', $since, $diff, $from, $to);
3672	}
3673
3674	/**
3675	* Generates an excerpt from the content, if needed.
3676	*
3677	* The excerpt word amount will be 55 words and if the amount is greater than
3678	* that, then the string ' […]' will be appended to the excerpt. If the string
3679	* is less than 55 words, then the content will be returned as is.
3680	*
3681	* The 55 word limit can be modified by plugins/themes using the {@see 'excerpt_length'} filter
3682	* The ' […]' string can be modified by plugins/themes using the {@see 'excerpt_more'} filter
3683	*
3684	* @since 1.5.0
3685	*
3686	* @param string $text Optional. The excerpt. If set to empty, an excerpt is generated.
3687	* @return string The excerpt.
3688	*/
3689	function wp_trim_excerpt($text = '')
3690	{
3691	$raw_excerpt = $text;
3692	if ('' == $text) {
3693	$text = get_the_content('');
3694
3695	$text = strip_shortcodes($text);
3696
3697	/** This filter is documented in wp-includes/post-template.php */
3698	$text = apply_filters('the_content', $text);
3699	$text = str_replace(']]>', ']]>', $text);
3700
3701	/**
3702	* Filters the number of words in an excerpt.
3703	*
3704	* @since 2.7.0
3705	*
3706	* @param int $number The number of words. Default 55.
3707	*/
3708	$excerpt_length = apply_filters('excerpt_length', 55);
3709	/**
3710	* Filters the string in the "more" link displayed after a trimmed excerpt.
3711	*
3712	* @since 2.9.0
3713	*
3714	* @param string $more_string The string shown within the more link.
3715	*/
3716	$excerpt_more = apply_filters('excerpt_more', ' ' . '[…]');
3717	$text = wp_trim_words($text, $excerpt_length, $excerpt_more);
3718	}
3719	/**
3720	* Filters the trimmed excerpt string.
3721	*
3722	* @since 2.8.0
3723	*
3724	* @param string $text The trimmed text.
3725	* @param string $raw_excerpt The text prior to trimming.
3726	*/
3727	return apply_filters('wp_trim_excerpt', $text, $raw_excerpt);
3728	}
3729
3730	/**
3731	* Trims text to a certain number of words.
3732	*
3733	* This function is localized. For languages that count 'words' by the individual
3734	* character (such as East Asian languages), the $num_words argument will apply
3735	* to the number of individual characters.
3736	*
3737	* @since 3.3.0
3738	*
3739	* @param string $text Text to trim.
3740	* @param int $num_words Number of words. Default 55.
3741	* @param string $more Optional. What to append if $text needs to be trimmed. Default '…'.
3742	* @return string Trimmed text.
3743	*/
3744	function wp_trim_words($text, $num_words = 55, $more = null)
3745	{
3746	if (null === $more) {
3747	$more = __('…');
3748	}
3749
3750	$original_text = $text;
3751	$text = wp_strip_all_tags($text);
3752
3753	/*
3754	* translators: If your word count is based on single characters (e.g. East Asian characters),
3755	* enter 'characters_excluding_spaces' or 'characters_including_spaces'. Otherwise, enter 'words'.
3756	* Do not translate into your own language.
3757	*/
3758	if (strpos(_x('words', 'Word count type. Do not translate!'), 'characters') === 0 && preg_match('/^utf\-?8$/i', get_option('blog_charset'))) {
3759	$text = trim(preg_replace("/[\n\r\t ]+/", ' ', $text), ' ');
3760	preg_match_all('/./u', $text, $words_array);
3761	$words_array = array_slice($words_array[0], 0, $num_words + 1);
3762	$sep = '';
3763	} else {
3764	$words_array = preg_split("/[\n\r\t ]+/", $text, $num_words + 1, PREG_SPLIT_NO_EMPTY);
3765	$sep = ' ';
3766	}
3767
3768	if (count($words_array) > $num_words) {
3769	array_pop($words_array);
3770	$text = implode($sep, $words_array);
3771	$text = $text . $more;
3772	} else {
3773	$text = implode($sep, $words_array);
3774	}
3775
3776	/**
3777	* Filters the text content after words have been trimmed.
3778	*
3779	* @since 3.3.0
3780	*
3781	* @param string $text The trimmed text.
3782	* @param int $num_words The number of words to trim the text to. Default 55.
3783	* @param string $more An optional string to append to the end of the trimmed text, e.g. ….
3784	* @param string $original_text The text before it was trimmed.
3785	*/
3786	return apply_filters('wp_trim_words', $text, $num_words, $more, $original_text);
3787	}
3788
3789	/**
3790	* Converts named entities into numbered entities.
3791	*
3792	* @since 1.5.1
3793	*
3794	* @param string $text The text within which entities will be converted.
3795	* @return string Text with converted entities.
3796	*/
3797	function ent2ncr($text)
3798	{
3799
3800	/**
3801	* Filters text before named entities are converted into numbered entities.
3802	*
3803	* A non-null string must be returned for the filter to be evaluated.
3804	*
3805	* @since 3.3.0
3806	*
3807	* @param null $converted_text The text to be converted. Default null.
3808	* @param string $text The text prior to entity conversion.
3809	*/
3810	$filtered = apply_filters('pre_ent2ncr', null, $text);
3811	if (null !== $filtered) {
3812	return $filtered;
3813	}
3814
3815	$to_ncr = array(
3816	'"' => '"',
3817	'&' => '&',
3818	'<' => '<',
3819	'>' => '>',
3820	'\|' => '\|',
3821	' ' => ' ',
3822	'¡' => '¡',
3823	'¢' => '¢',
3824	'£' => '£',
3825	'¤' => '¤',
3826	'¥' => '¥',
3827	'¦' => '¦',
3828	'&brkbar;' => '¦',
3829	'§' => '§',
3830	'¨' => '¨',
3831	'&die;' => '¨',
3832	'©' => '©',
3833	'ª' => 'ª',
3834	'«' => '«',
3835	'¬' => '¬',
3836	'' => '',
3837	'®' => '®',
3838	'¯' => '¯',
3839	'&hibar;' => '¯',
3840	'°' => '°',
3841	'±' => '±',
3842	'²' => '²',
3843	'³' => '³',
3844	'´' => '´',
3845	'µ' => 'µ',
3846	'¶' => '¶',
3847	'·' => '·',
3848	'¸' => '¸',
3849	'¹' => '¹',
3850	'º' => 'º',
3851	'»' => '»',
3852	'¼' => '¼',
3853	'½' => '½',
3854	'¾' => '¾',
3855	'¿' => '¿',
3856	'À' => 'À',
3857	'Á' => 'Á',
3858	'Â' => 'Â',
3859	'Ã' => 'Ã',
3860	'Ä' => 'Ä',
3861	'Å' => 'Å',
3862	'Æ' => 'Æ',
3863	'Ç' => 'Ç',
3864	'È' => 'È',
3865	'É' => 'É',
3866	'Ê' => 'Ê',
3867	'Ë' => 'Ë',
3868	'Ì' => 'Ì',
3869	'Í' => 'Í',
3870	'Î' => 'Î',
3871	'Ï' => 'Ï',
3872	'Ð' => 'Ð',
3873	'Ñ' => 'Ñ',
3874	'Ò' => 'Ò',
3875	'Ó' => 'Ó',
3876	'Ô' => 'Ô',
3877	'Õ' => 'Õ',
3878	'Ö' => 'Ö',
3879	'×' => '×',
3880	'Ø' => 'Ø',
3881	'Ù' => 'Ù',
3882	'Ú' => 'Ú',
3883	'Û' => 'Û',
3884	'Ü' => 'Ü',
3885	'Ý' => 'Ý',
3886	'Þ' => 'Þ',
3887	'ß' => 'ß',
3888	'à' => 'à',
3889	'á' => 'á',
3890	'â' => 'â',
3891	'ã' => 'ã',
3892	'ä' => 'ä',
3893	'å' => 'å',
3894	'æ' => 'æ',
3895	'ç' => 'ç',
3896	'è' => 'è',
3897	'é' => 'é',
3898	'ê' => 'ê',
3899	'ë' => 'ë',
3900	'ì' => 'ì',
3901	'í' => 'í',
3902	'î' => 'î',
3903	'ï' => 'ï',
3904	'ð' => 'ð',
3905	'ñ' => 'ñ',
3906	'ò' => 'ò',
3907	'ó' => 'ó',
3908	'ô' => 'ô',
3909	'õ' => 'õ',
3910	'ö' => 'ö',
3911	'÷' => '÷',
3912	'ø' => 'ø',
3913	'ù' => 'ù',
3914	'ú' => 'ú',
3915	'û' => 'û',
3916	'ü' => 'ü',
3917	'ý' => 'ý',
3918	'þ' => 'þ',
3919	'ÿ' => 'ÿ',
3920	'&OElig;' => 'Œ',
3921	'&oelig;' => 'œ',
3922	'&Scaron;' => 'Š',
3923	'&scaron;' => 'š',
3924	'&Yuml;' => 'Ÿ',
3925	'&fnof;' => 'ƒ',
3926	'&circ;' => 'ˆ',
3927	'&tilde;' => '˜',
3928	'Α' => 'Α',
3929	'Β' => 'Β',
3930	'Γ' => 'Γ',
3931	'Δ' => 'Δ',
3932	'Ε' => 'Ε',
3933	'Ζ' => 'Ζ',
3934	'Η' => 'Η',
3935	'Θ' => 'Θ',
3936	'Ι' => 'Ι',
3937	'Κ' => 'Κ',
3938	'Λ' => 'Λ',
3939	'Μ' => 'Μ',
3940	'Ν' => 'Ν',
3941	'Ξ' => 'Ξ',
3942	'Ο' => 'Ο',
3943	'Π' => 'Π',
3944	'Ρ' => 'Ρ',
3945	'Σ' => 'Σ',
3946	'Τ' => 'Τ',
3947	'Υ' => 'Υ',
3948	'Φ' => 'Φ',
3949	'Χ' => 'Χ',
3950	'Ψ' => 'Ψ',
3951	'Ω' => 'Ω',
3952	'α' => 'α',
3953	'β' => 'β',
3954	'γ' => 'γ',
3955	'δ' => 'δ',
3956	'ε' => 'ε',
3957	'ζ' => 'ζ',
3958	'η' => 'η',
3959	'θ' => 'θ',
3960	'ι' => 'ι',
3961	'κ' => 'κ',
3962	'λ' => 'λ',
3963	'μ' => 'μ',
3964	'ν' => 'ν',
3965	'ξ' => 'ξ',
3966	'ο' => 'ο',
3967	'π' => 'π',
3968	'ρ' => 'ρ',
3969	'&sigmaf;' => 'ς',
3970	'σ' => 'σ',
3971	'τ' => 'τ',
3972	'υ' => 'υ',
3973	'φ' => 'φ',
3974	'χ' => 'χ',
3975	'ψ' => 'ψ',
3976	'ω' => 'ω',
3977	'&thetasym;' => 'ϑ',
3978	'&upsih;' => 'ϒ',
3979	'ϖ' => 'ϖ',
3980	'&ensp;' => ' ',
3981	'&emsp;' => ' ',
3982	' ' => ' ',
3983	'&zwnj;' => '‌',
3984	'&zwj;' => '‍',
3985	'&lrm;' => '‎',
3986	'&rlm;' => '‏',
3987	'–' => '–',
3988	'—' => '—',
3989	'‘' => '‘',
3990	'’' => '’',
3991	'&sbquo;' => '‚',
3992	'“' => '“',
3993	'”' => '”',
3994	'&bdquo;' => '„',
3995	'&dagger;' => '†',
3996	'&Dagger;' => '‡',
3997	'•' => '•',
3998	'…' => '…',
3999	'&permil;' => '‰',
4000	'′' => '′',
4001	'″' => '″',
4002	'&lsaquo;' => '‹',
4003	'&rsaquo;' => '›',
4004	'&oline;' => '‾',
4005	'&frasl;' => '⁄',
4006	'€' => '€',
4007	'&image;' => 'ℑ',
4008	'&weierp;' => '℘',
4009	'&real;' => 'ℜ',
4010	'™' => '™',
4011	'&alefsym;' => 'ℵ',
4012	'&crarr;' => '↵',
4013	'⇐' => '⇐',
4014	'&uArr;' => '⇑',
4015	'⇒' => '⇒',
4016	'&dArr;' => '⇓',
4017	'⇔' => '⇔',
4018	'∀' => '∀',
4019	'∂' => '∂',
4020	'∃' => '∃',
4021	'∅' => '∅',
4022	'∇' => '∇',
4023	'∈' => '∈',
4024	'∉' => '∉',
4025	'&ni;' => '∋',
4026	'∏' => '∏',
4027	'∑' => '∑',
4028	'−' => '−',
4029	'&lowast;' => '∗',
4030	'√' => '√',
4031	'&prop;' => '∝',
4032	'∞' => '∞',
4033	'&ang;' => '∠',
4034	'&and;' => '∧',
4035	'&or;' => '∨',
4036	'∩' => '∩',
4037	'∪' => '∪',
4038	'∫' => '∫',
4039	'&there4;' => '∴',
4040	'&sim;' => '∼',
4041	'&cong;' => '≅',
4042	'≈' => '≈',
4043	'≠' => '≠',
4044	'&equiv;' => '≡',
4045	'≤' => '≤',
4046	'≥' => '≥',
4047	'⊂' => '⊂',
4048	'⊃' => '⊃',
4049	'&nsub;' => '⊄',
4050	'&sube;' => '⊆',
4051	'&supe;' => '⊇',
4052	'&oplus;' => '⊕',
4053	'&otimes;' => '⊗',
4054	'&perp;' => '⊥',
4055	'⋅' => '⋅',
4056	'&lceil;' => '⌈',
4057	'&rceil;' => '⌉',
4058	'&lfloor;' => '⌊',
4059	'&rfloor;' => '⌋',
4060	'&lang;' => '〈',
4061	'&rang;' => '〉',
4062	'←' => '←',
4063	'↑' => '↑',
4064	'→' => '→',
4065	'↓' => '↓',
4066	'↔' => '↔',
4067	'&loz;' => '◊',
4068	'&spades;' => '♠',
4069	'&clubs;' => '♣',
4070	'&hearts;' => '♥',
4071	'&diams;' => '♦',
4072	);
4073
4074	return str_replace(array_keys($to_ncr), array_values($to_ncr), $text);
4075	}
4076
4077	/**
4078	* Formats text for the editor.
4079	*
4080	* Generally the browsers treat everything inside a textarea as text, but
4081	* it is still a good idea to HTML entity encode `<`, `>` and `&` in the content.
4082	*
4083	* The filter {@see 'format_for_editor'} is applied here. If `$text` is empty the
4084	* filter will be applied to an empty string.
4085	*
4086	* @since 4.3.0
4087	*
4088	* @see _WP_Editors::editor()
4089	*
4090	* @param string $text The text to be formatted.
4091	* @param string $default_editor The default editor for the current user.
4092	* It is usually either 'html' or 'tinymce'.
4093	* @return string The formatted text after filter is applied.
4094	*/
4095	function format_for_editor($text, $default_editor = null)
4096	{
4097	if ($text) {
4098	$text = htmlspecialchars($text, ENT_NOQUOTES, get_option('blog_charset'));
4099	}
4100
4101	/**
4102	* Filters the text after it is formatted for the editor.
4103	*
4104	* @since 4.3.0
4105	*
4106	* @param string $text The formatted text.
4107	* @param string $default_editor The default editor for the current user.
4108	* It is usually either 'html' or 'tinymce'.
4109	*/
4110	return apply_filters('format_for_editor', $text, $default_editor);
4111	}
4112
4113	/**
4114	* Perform a deep string replace operation to ensure the values in $search are no longer present
4115	*
4116	* Repeats the replacement operation until it no longer replaces anything so as to remove "nested" values
4117	* e.g. $subject = '%0%0%0DDD', $search ='%0D', $result ='' rather than the '%0%0DD' that
4118	* str_replace would return
4119	*
4120	* @since 2.8.1
4121	* @access private
4122	*
4123	* @param string\|array $search The value being searched for, otherwise known as the needle.
4124	* An array may be used to designate multiple needles.
4125	* @param string $subject The string being searched and replaced on, otherwise known as the haystack.
4126	* @return string The string with the replaced values.
4127	*/
4128	function _deep_replace($search, $subject)
4129	{
4130	$subject = (string) $subject;
4131
4132	$count = 1;
4133	while ($count) {
4134	$subject = str_replace($search, '', $subject, $count);
4135	}
4136
4137	return $subject;
4138	}
4139
4140	/**
4141	* Escapes data for use in a MySQL query.
4142	*
4143	* Usually you should prepare queries using wpdb::prepare().
4144	* Sometimes, spot-escaping is required or useful. One example
4145	* is preparing an array for use in an IN clause.
4146	*
4147	* NOTE: Since 4.8.3, '%' characters will be replaced with a placeholder string,
4148	* this prevents certain SQLi attacks from taking place. This change in behaviour
4149	* may cause issues for code that expects the return value of esc_sql() to be useable
4150	* for other purposes.
4151	*
4152	* @since 2.8.0
4153	*
4154	* @global wpdb $wpdb WordPress database abstraction object.
4155	*
4156	* @param string\|array $data Unescaped data
4157	* @return string\|array Escaped data
4158	*/
4159	function esc_sql($data)
4160	{
4161	global $wpdb;
4162	return $wpdb->_escape($data);
4163	}
4164
4165	/**
4166	* Checks and cleans a URL.
4167	*
4168	* A number of characters are removed from the URL. If the URL is for displaying
4169	* (the default behaviour) ampersands are also replaced. The {@see 'clean_url'} filter
4170	* is applied to the returned cleaned URL.
4171	*
4172	* @since 2.8.0
4173	*
4174	* @param string $url The URL to be cleaned.
4175	* @param array $protocols Optional. An array of acceptable protocols.
4176	* Defaults to return value of wp_allowed_protocols()
4177	* @param string $_context Private. Use esc_url_raw() for database usage.
4178	* @return string The cleaned $url after the {@see 'clean_url'} filter is applied.
4179	*/
4180	function esc_url($url, $protocols = null, $_context = 'display')
4181	{
4182	$original_url = $url;
4183
4184	if ('' == $url) {
4185	return $url;
4186	}
4187
4188	$url = str_replace(' ', '%20', $url);
4189	$url = preg_replace('\|[^a-z0-9-~+_.?#=!&;,/:%@$\\|*\'()\[\]\\x80-\\xff]\|i', '', $url);
4190
4191	if ('' === $url) {
4192	return $url;
4193	}
4194
4195	if (0 !== stripos($url, 'mailto:')) {
4196	$strip = array( '%0d', '%0a', '%0D', '%0A' );
4197	$url = _deep_replace($strip, $url);
4198	}
4199
4200	$url = str_replace(';//', '://', $url);
4201	/* If the URL doesn't appear to contain a scheme, we
4202	* presume it needs http:// prepended (unless a relative
4203	* link starting with /, # or ? or a php file).
4204	*/
4205	if (strpos($url, ':') === false && ! in_array($url[0], array( '/', '#', '?' )) &&
4206	! preg_match('/^[a-z0-9-]+?\.php/i', $url) ) {
4207	$url = 'http://' . $url;
4208	}
4209
4210	// Replace ampersands and single quotes only when displaying.
4211	if ('display' == $_context) {
4212	$url = wp_kses_normalize_entities($url);
4213	$url = str_replace('&', '&', $url);
4214	$url = str_replace("'", ''', $url);
4215	}
4216
4217	if (( false !== strpos($url, '[') ) \|\| ( false !== strpos($url, ']') )) {
4218	$parsed = wp_parse_url($url);
4219	$front = '';
4220
4221	if (isset($parsed['scheme'])) {
4222	$front .= $parsed['scheme'] . '://';
4223	} elseif ('/' === $url[0]) {
4224	$front .= '//';
4225	}
4226
4227	if (isset($parsed['user'])) {
4228	$front .= $parsed['user'];
4229	}
4230
4231	if (isset($parsed['pass'])) {
4232	$front .= ':' . $parsed['pass'];
4233	}
4234
4235	if (isset($parsed['user']) \|\| isset($parsed['pass'])) {
4236	$front .= '@';
4237	}
4238
4239	if (isset($parsed['host'])) {
4240	$front .= $parsed['host'];
4241	}
4242
4243	if (isset($parsed['port'])) {
4244	$front .= ':' . $parsed['port'];
4245	}
4246
4247	$end_dirty = str_replace($front, '', $url);
4248	$end_clean = str_replace(array( '[', ']' ), array( '%5B', '%5D' ), $end_dirty);
4249	$url = str_replace($end_dirty, $end_clean, $url);
4250	}
4251
4252	if ('/' === $url[0]) {
4253	$good_protocol_url = $url;
4254	} else {
4255	if (! is_array($protocols)) {
4256	$protocols = wp_allowed_protocols();
4257	}
4258	$good_protocol_url = wp_kses_bad_protocol($url, $protocols);
4259	if (strtolower($good_protocol_url) != strtolower($url)) {
4260	return '';
4261	}
4262	}
4263
4264	/**
4265	* Filters a string cleaned and escaped for output as a URL.
4266	*
4267	* @since 2.3.0
4268	*
4269	* @param string $good_protocol_url The cleaned URL to be returned.
4270	* @param string $original_url The URL prior to cleaning.
4271	* @param string $_context If 'display', replace ampersands and single quotes only.
4272	*/
4273	return apply_filters('clean_url', $good_protocol_url, $original_url, $_context);
4274	}
4275
4276	/**
4277	* Performs esc_url() for database usage.
4278	*
4279	* @since 2.8.0
4280	*
4281	* @param string $url The URL to be cleaned.
4282	* @param array $protocols An array of acceptable protocols.
4283	* @return string The cleaned URL.
4284	*/
4285	function esc_url_raw($url, $protocols = null)
4286	{
4287	return esc_url($url, $protocols, 'db');
4288	}
4289
4290	/**
4291	* Convert entities, while preserving already-encoded entities.
4292	*
4293	* @link https://secure.php.net/htmlentities Borrowed from the PHP Manual user notes.
4294	*
4295	* @since 1.2.2
4296	*
4297	* @param string $myHTML The text to be converted.
4298	* @return string Converted text.
4299	*/
4300	function htmlentities2($myHTML)
4301	{
4302	$translation_table = get_html_translation_table(HTML_ENTITIES, ENT_QUOTES);
4303	$translation_table[ chr(38) ] = '&';
4304	return preg_replace('/&(?![A-Za-z]{0,4}\w{2,3};\|#[0-9]{2,3};)/', '&', strtr($myHTML, $translation_table));
4305	}
4306
4307	/**
4308	* Escape single quotes, htmlspecialchar " < > &, and fix line endings.
4309	*
4310	* Escapes text strings for echoing in JS. It is intended to be used for inline JS
4311	* (in a tag attribute, for example onclick="..."). Note that the strings have to
4312	* be in single quotes. The {@see 'js_escape'} filter is also applied here.
4313	*
4314	* @since 2.8.0
4315	*
4316	* @param string $text The text to be escaped.
4317	* @return string Escaped text.
4318	*/
4319	function esc_js($text)
4320	{
4321	$safe_text = wp_check_invalid_utf8($text);
4322	$safe_text = _wp_specialchars($safe_text, ENT_COMPAT);
4323	$safe_text = preg_replace('/&#(x)?0*(?(1)27\|39);?/i', "'", stripslashes($safe_text));
4324	$safe_text = str_replace("\r", '', $safe_text);
4325	$safe_text = str_replace("\n", '\\n', addslashes($safe_text));
4326	/**
4327	* Filters a string cleaned and escaped for output in JavaScript.
4328	*
4329	* Text passed to esc_js() is stripped of invalid or special characters,
4330	* and properly slashed for output.
4331	*
4332	* @since 2.0.6
4333	*
4334	* @param string $safe_text The text after it has been escaped.
4335	* @param string $text The text prior to being escaped.
4336	*/
4337	return apply_filters('js_escape', $safe_text, $text);
4338	}
4339
4340	/**
4341	* Escaping for HTML blocks.
4342	*
4343	* @since 2.8.0
4344	*
4345	* @param string $text
4346	* @return string
4347	*/
4348	function esc_html($text)
4349	{
4350	$safe_text = wp_check_invalid_utf8($text);
4351	$safe_text = _wp_specialchars($safe_text, ENT_QUOTES);
4352	/**
4353	* Filters a string cleaned and escaped for output in HTML.
4354	*
4355	* Text passed to esc_html() is stripped of invalid or special characters
4356	* before output.
4357	*
4358	* @since 2.8.0
4359	*
4360	* @param string $safe_text The text after it has been escaped.
4361	* @param string $text The text prior to being escaped.
4362	*/
4363	return apply_filters('esc_html', $safe_text, $text);
4364	}
4365
4366	/**
4367	* Escaping for HTML attributes.
4368	*
4369	* @since 2.8.0
4370	*
4371	* @param string $text
4372	* @return string
4373	*/
4374	function esc_attr($text)
4375	{
4376	$safe_text = wp_check_invalid_utf8($text);
4377	$safe_text = _wp_specialchars($safe_text, ENT_QUOTES);
4378	/**
4379	* Filters a string cleaned and escaped for output in an HTML attribute.
4380	*
4381	* Text passed to esc_attr() is stripped of invalid or special characters
4382	* before output.
4383	*
4384	* @since 2.0.6
4385	*
4386	* @param string $safe_text The text after it has been escaped.
4387	* @param string $text The text prior to being escaped.
4388	*/
4389	return apply_filters('attribute_escape', $safe_text, $text);
4390	}
4391
4392	/**
4393	* Escaping for textarea values.
4394	*
4395	* @since 3.1.0
4396	*
4397	* @param string $text
4398	* @return string
4399	*/
4400	function esc_textarea($text)
4401	{
4402	$safe_text = htmlspecialchars($text, ENT_QUOTES, get_option('blog_charset'));
4403	/**
4404	* Filters a string cleaned and escaped for output in a textarea element.
4405	*
4406	* @since 3.1.0
4407	*
4408	* @param string $safe_text The text after it has been escaped.
4409	* @param string $text The text prior to being escaped.
4410	*/
4411	return apply_filters('esc_textarea', $safe_text, $text);
4412	}
4413
4414	/**
4415	* Escape an HTML tag name.
4416	*
4417	* @since 2.5.0
4418	*
4419	* @param string $tag_name
4420	* @return string
4421	*/
4422	function tag_escape($tag_name)
4423	{
4424	$safe_tag = strtolower(preg_replace('/[^a-zA-Z0-9_:]/', '', $tag_name));
4425	/**
4426	* Filters a string cleaned and escaped for output as an HTML tag.
4427	*
4428	* @since 2.8.0
4429	*
4430	* @param string $safe_tag The tag name after it has been escaped.
4431	* @param string $tag_name The text before it was escaped.
4432	*/
4433	return apply_filters('tag_escape', $safe_tag, $tag_name);
4434	}
4435
4436	/**
4437	* Convert full URL paths to absolute paths.
4438	*
4439	* Removes the http or https protocols and the domain. Keeps the path '/' at the
4440	* beginning, so it isn't a true relative link, but from the web root base.
4441	*
4442	* @since 2.1.0
4443	* @since 4.1.0 Support was added for relative URLs.
4444	*
4445	* @param string $link Full URL path.
4446	* @return string Absolute path.
4447	*/
4448	function wp_make_link_relative($link)
4449	{
4450	return preg_replace('\|^(https?:)?//[^/]+(/?.*)\|i', '$2', $link);
4451	}
4452
4453	/**
4454	* Sanitises various option values based on the nature of the option.
4455	*
4456	* This is basically a switch statement which will pass $value through a number
4457	* of functions depending on the $option.
4458	*
4459	* @since 2.0.5
4460	*
4461	* @global wpdb $wpdb WordPress database abstraction object.
4462	*
4463	* @param string $option The name of the option.
4464	* @param string $value The unsanitised value.
4465	* @return string Sanitized value.
4466	*/
4467	function sanitize_option($option, $value)
4468	{
4469	global $wpdb;
4470
4471	$original_value = $value;
4472	$error = '';
4473
4474	switch ($option) {
4475	case 'admin_email':
4476	case 'new_admin_email':
4477	$value = $wpdb->strip_invalid_text_for_column($wpdb->options, 'option_value', $value);
4478	if (is_wp_error($value)) {
4479	$error = $value->get_error_message();
4480	} else {
4481	$value = sanitize_email($value);
4482	if (! is_email($value)) {
4483	$error = __('The email address entered did not appear to be a valid email address. Please enter a valid email address.');
4484	}
4485	}
4486	break;
4487
4488	case 'thumbnail_size_w':
4489	case 'thumbnail_size_h':
4490	case 'medium_size_w':
4491	case 'medium_size_h':
4492	case 'medium_large_size_w':
4493	case 'medium_large_size_h':
4494	case 'large_size_w':
4495	case 'large_size_h':
4496	case 'mailserver_port':
4497	case 'comment_max_links':
4498	case 'page_on_front':
4499	case 'page_for_posts':
4500	case 'rss_excerpt_length':
4501	case 'default_category':
4502	case 'default_email_category':
4503	case 'default_link_category':
4504	case 'close_comments_days_old':
4505	case 'comments_per_page':
4506	case 'thread_comments_depth':
4507	case 'users_can_register':
4508	case 'start_of_week':
4509	case 'site_icon':
4510	$value = absint($value);
4511	break;
4512
4513	case 'posts_per_page':
4514	case 'posts_per_rss':
4515	$value = (int) $value;
4516	if (empty($value)) {
4517	$value = 1;
4518	}
4519	if ($value < -1) {
4520	$value = abs($value);
4521	}
4522	break;
4523
4524	case 'default_ping_status':
4525	case 'default_comment_status':
4526	// Options that if not there have 0 value but need to be something like "closed"
4527	if ($value == '0' \|\| $value == '') {
4528	$value = 'closed';
4529	}
4530	break;
4531
4532	case 'blogdescription':
4533	case 'blogname':
4534	$value = $wpdb->strip_invalid_text_for_column($wpdb->options, 'option_value', $value);
4535	if ($value !== $original_value) {
4536	$value = $wpdb->strip_invalid_text_for_column($wpdb->options, 'option_value', wp_encode_emoji($original_value));
4537	}
4538
4539	if (is_wp_error($value)) {
4540	$error = $value->get_error_message();
4541	} else {
4542	$value = esc_html($value);
4543	}
4544	break;
4545
4546	case 'blog_charset':
4547	$value = preg_replace('/[^a-zA-Z0-9_-]/', '', $value); // strips slashes
4548	break;
4549
4550	case 'blog_public':
4551	// This is the value if the settings checkbox is not checked on POST. Don't rely on this.
4552	if (null === $value) {
4553	$value = 1;
4554	} else {
4555	$value = intval($value);
4556	}
4557	break;
4558
4559	case 'date_format':
4560	case 'time_format':
4561	case 'mailserver_url':
4562	case 'mailserver_login':
4563	case 'mailserver_pass':
4564	case 'upload_path':
4565	$value = $wpdb->strip_invalid_text_for_column($wpdb->options, 'option_value', $value);
4566	if (is_wp_error($value)) {
4567	$error = $value->get_error_message();
4568	} else {
4569	$value = strip_tags($value);
4570	$value = wp_kses_data($value);
4571	}
4572	break;
4573
4574	case 'ping_sites':
4575	$value = explode("\n", $value);
4576	$value = array_filter(array_map('trim', $value));
4577	$value = array_filter(array_map('esc_url_raw', $value));
4578	$value = implode("\n", $value);
4579	break;
4580
4581	case 'gmt_offset':
4582	$value = preg_replace('/[^0-9:.-]/', '', $value); // strips slashes
4583	break;
4584
4585	case 'siteurl':
4586	$value = $wpdb->strip_invalid_text_for_column($wpdb->options, 'option_value', $value);
4587	if (is_wp_error($value)) {
4588	$error = $value->get_error_message();
4589	} else {
4590	if (preg_match('#http(s?)://(.+)#i', $value)) {
4591	$value = esc_url_raw($value);
4592	} else {
4593	$error = __('The WordPress address you entered did not appear to be a valid URL. Please enter a valid URL.');
4594	}
4595	}
4596	break;
4597
4598	case 'home':
4599	$value = $wpdb->strip_invalid_text_for_column($wpdb->options, 'option_value', $value);
4600	if (is_wp_error($value)) {
4601	$error = $value->get_error_message();
4602	} else {
4603	if (preg_match('#http(s?)://(.+)#i', $value)) {
4604	$value = esc_url_raw($value);
4605	} else {
4606	$error = __('The Site address you entered did not appear to be a valid URL. Please enter a valid URL.');
4607	}
4608	}
4609	break;
4610
4611	case 'WPLANG':
4612	$allowed = get_available_languages();
4613	if (! is_multisite() && defined('WPLANG') && '' !== WPLANG && 'en_US' !== WPLANG) {
4614	$allowed[] = WPLANG;
4615	}
4616	if (! in_array($value, $allowed) && ! empty($value)) {
4617	$value = get_option($option);
4618	}
4619	break;
4620
4621	case 'illegal_names':
4622	$value = $wpdb->strip_invalid_text_for_column($wpdb->options, 'option_value', $value);
4623	if (is_wp_error($value)) {
4624	$error = $value->get_error_message();
4625	} else {
4626	if (! is_array($value)) {
4627	$value = explode(' ', $value);
4628	}
4629
4630	$value = array_values(array_filter(array_map('trim', $value)));
4631
4632	if (! $value) {
4633	$value = '';
4634	}
4635	}
4636	break;
4637
4638	case 'limited_email_domains':
4639	case 'banned_email_domains':
4640	$value = $wpdb->strip_invalid_text_for_column($wpdb->options, 'option_value', $value);
4641	if (is_wp_error($value)) {
4642	$error = $value->get_error_message();
4643	} else {
4644	if (! is_array($value)) {
4645	$value = explode("\n", $value);
4646	}
4647
4648	$domains = array_values(array_filter(array_map('trim', $value)));
4649	$value = array();
4650
4651	foreach ($domains as $domain) {
4652	if (! preg_match('/(--\|\.\.)/', $domain) && preg_match('\|^([a-zA-Z0-9-\.])+$\|', $domain)) {
4653	$value[] = $domain;
4654	}
4655	}
4656	if (! $value) {
4657	$value = '';
4658	}
4659	}
4660	break;
4661
4662	case 'timezone_string':
4663	$allowed_zones = timezone_identifiers_list();
4664	if (! in_array($value, $allowed_zones) && ! empty($value)) {
4665	$error = __('The timezone you have entered is not valid. Please select a valid timezone.');
4666	}
4667	break;
4668
4669	case 'permalink_structure':
4670	case 'category_base':
4671	case 'tag_base':
4672	$value = $wpdb->strip_invalid_text_for_column($wpdb->options, 'option_value', $value);
4673	if (is_wp_error($value)) {
4674	$error = $value->get_error_message();
4675	} else {
4676	$value = esc_url_raw($value);
4677	$value = str_replace('http://', '', $value);
4678	}
4679
4680	if ('permalink_structure' === $option && '' !== $value && ! preg_match('/%[^\/%]+%/', $value)) {
4681	$error = sprintf(
4682	/* translators: %s: Codex URL */
4683	__('A structure tag is required when using custom permalinks. <a href="%s">Learn more</a>'),
4684	__('https://codex.wordpress.org/Using_Permalinks#Choosing_your_permalink_structure')
4685	);
4686	}
4687	break;
4688
4689	case 'default_role':
4690	if (! get_role($value) && get_role('subscriber')) {
4691	$value = 'subscriber';
4692	}
4693	break;
4694
4695	case 'moderation_keys':
4696	case 'blacklist_keys':
4697	$value = $wpdb->strip_invalid_text_for_column($wpdb->options, 'option_value', $value);
4698	if (is_wp_error($value)) {
4699	$error = $value->get_error_message();
4700	} else {
4701	$value = explode("\n", $value);
4702	$value = array_filter(array_map('trim', $value));
4703	$value = array_unique($value);
4704	$value = implode("\n", $value);
4705	}
4706	break;
4707	}
4708
4709	if (! empty($error)) {
4710	$value = get_option($option);
4711	if (function_exists('add_settings_error')) {
4712	add_settings_error($option, "invalid_{$option}", $error);
4713	}
4714	}
4715
4716	/**
4717	* Filters an option value following sanitization.
4718	*
4719	* @since 2.3.0
4720	* @since 4.3.0 Added the `$original_value` parameter.
4721	*
4722	* @param string $value The sanitized option value.
4723	* @param string $option The option name.
4724	* @param string $original_value The original value passed to the function.
4725	*/
4726	return apply_filters("sanitize_option_{$option}", $value, $option, $original_value);
4727	}
4728
4729	/**
4730	* Maps a function to all non-iterable elements of an array or an object.
4731	*
4732	* This is similar to `array_walk_recursive()` but acts upon objects too.
4733	*
4734	* @since 4.4.0
4735	*
4736	* @param mixed $value The array, object, or scalar.
4737	* @param callable $callback The function to map onto $value.
4738	* @return mixed The value with the callback applied to all non-arrays and non-objects inside it.
4739	*/
4740	function map_deep($value, $callback)
4741	{
4742	if (is_array($value)) {
4743	foreach ($value as $index => $item) {
4744	$value[ $index ] = map_deep($item, $callback);
4745	}
4746	} elseif (is_object($value)) {
4747	$object_vars = get_object_vars($value);
4748	foreach ($object_vars as $property_name => $property_value) {
4749	$value->$property_name = map_deep($property_value, $callback);
4750	}
4751	} else {
4752	$value = call_user_func($callback, $value);
4753	}
4754
4755	return $value;
4756	}
4757
4758	/**
4759	* Parses a string into variables to be stored in an array.
4760	*
4761	* Uses {@link https://secure.php.net/parse_str parse_str()} and stripslashes if
4762	* {@link https://secure.php.net/magic_quotes magic_quotes_gpc} is on.
4763	*
4764	* @since 2.2.1
4765	*
4766	* @param string $string The string to be parsed.
4767	* @param array $array Variables will be stored in this array.
4768	*/
4769	function wp_parse_str($string, &$array)
4770	{
4771	parse_str($string, $array);
4772	if (get_magic_quotes_gpc()) {
4773	$array = stripslashes_deep($array);
4774	}
4775	/**
4776	* Filters the array of variables derived from a parsed string.
4777	*
4778	* @since 2.3.0
4779	*
4780	* @param array $array The array populated with variables.
4781	*/
4782	$array = apply_filters('wp_parse_str', $array);
4783	}
4784
4785	/**
4786	* Convert lone less than signs.
4787	*
4788	* KSES already converts lone greater than signs.
4789	*
4790	* @since 2.3.0
4791	*
4792	* @param string $text Text to be converted.
4793	* @return string Converted text.
4794	*/
4795	function wp_pre_kses_less_than($text)
4796	{
4797	return preg_replace_callback('%<[^>]*?((?=<)\|>\|$)%', 'wp_pre_kses_less_than_callback', $text);
4798	}
4799
4800	/**
4801	* Callback function used by preg_replace.
4802	*
4803	* @since 2.3.0
4804	*
4805	* @param array $matches Populated by matches to preg_replace.
4806	* @return string The text returned after esc_html if needed.
4807	*/
4808	function wp_pre_kses_less_than_callback($matches)
4809	{
4810	if (false === strpos($matches[0], '>')) {
4811	return esc_html($matches[0]);
4812	}
4813	return $matches[0];
4814	}
4815
4816	/**
4817	* WordPress implementation of PHP sprintf() with filters.
4818	*
4819	* @since 2.5.0
4820	* @link https://secure.php.net/sprintf
4821	*
4822	* @param string $pattern The string which formatted args are inserted.
4823	* @param mixed $args ,... Arguments to be formatted into the $pattern string.
4824	* @return string The formatted string.
4825	*/
4826	function wp_sprintf($pattern)
4827	{
4828	$args = func_get_args();
4829	$len = strlen($pattern);
4830	$start = 0;
4831	$result = '';
4832	$arg_index = 0;
4833	while ($len > $start) {
4834	// Last character: append and break
4835	if (strlen($pattern) - 1 == $start) {
4836	$result .= substr($pattern, -1);
4837	break;
4838	}
4839
4840	// Literal %: append and continue
4841	if (substr($pattern, $start, 2) == '%%') {
4842	$start += 2;
4843	$result .= '%';
4844	continue;
4845	}
4846
4847	// Get fragment before next %
4848	$end = strpos($pattern, '%', $start + 1);
4849	if (false === $end) {
4850	$end = $len;
4851	}
4852	$fragment = substr($pattern, $start, $end - $start);
4853
4854	// Fragment has a specifier
4855	if ($pattern[ $start ] == '%') {
4856	// Find numbered arguments or take the next one in order
4857	if (preg_match('/^%(\d+)\$/', $fragment, $matches)) {
4858	$arg = isset($args[ $matches[1] ]) ? $args[ $matches[1] ] : '';
4859	$fragment = str_replace("%{$matches[1]}$", '%', $fragment);
4860	} else {
4861	++$arg_index;
4862	$arg = isset($args[ $arg_index ]) ? $args[ $arg_index ] : '';
4863	}
4864
4865	/**
4866	* Filters a fragment from the pattern passed to wp_sprintf().
4867	*
4868	* If the fragment is unchanged, then sprintf() will be run on the fragment.
4869	*
4870	* @since 2.5.0
4871	*
4872	* @param string $fragment A fragment from the pattern.
4873	* @param string $arg The argument.
4874	*/
4875	$_fragment = apply_filters('wp_sprintf', $fragment, $arg);
4876	if ($_fragment != $fragment) {
4877	$fragment = $_fragment;
4878	} else {
4879	$fragment = sprintf($fragment, strval($arg));
4880	}
4881	}
4882
4883	// Append to result and move to next fragment
4884	$result .= $fragment;
4885	$start = $end;
4886	}
4887	return $result;
4888	}
4889
4890	/**
4891	* Localize list items before the rest of the content.
4892	*
4893	* The '%l' must be at the first characters can then contain the rest of the
4894	* content. The list items will have ', ', ', and', and ' and ' added depending
4895	* on the amount of list items in the $args parameter.
4896	*
4897	* @since 2.5.0
4898	*
4899	* @param string $pattern Content containing '%l' at the beginning.
4900	* @param array $args List items to prepend to the content and replace '%l'.
4901	* @return string Localized list items and rest of the content.
4902	*/
4903	function wp_sprintf_l($pattern, $args)
4904	{
4905	// Not a match
4906	if (substr($pattern, 0, 2) != '%l') {
4907	return $pattern;
4908	}
4909
4910	// Nothing to work with
4911	if (empty($args)) {
4912	return '';
4913	}
4914
4915	/**
4916	* Filters the translated delimiters used by wp_sprintf_l().
4917	* Placeholders (%s) are included to assist translators and then
4918	* removed before the array of strings reaches the filter.
4919	*
4920	* Please note: Ampersands and entities should be avoided here.
4921	*
4922	* @since 2.5.0
4923	*
4924	* @param array $delimiters An array of translated delimiters.
4925	*/
4926	$l = apply_filters(
4927	'wp_sprintf_l',
4928	array(
4929	/* translators: used to join items in a list with more than 2 items */
4930	'between' => sprintf(__('%1$s, %2$s'), '', ''),
4931	/* translators: used to join last two items in a list with more than 2 times */
4932	'between_last_two' => sprintf(__('%1$s, and %2$s'), '', ''),
4933	/* translators: used to join items in a list with only 2 items */
4934	'between_only_two' => sprintf(__('%1$s and %2$s'), '', ''),
4935	)
4936	);
4937
4938	$args = (array) $args;
4939	$result = array_shift($args);
4940	if (count($args) == 1) {
4941	$result .= $l['between_only_two'] . array_shift($args);
4942	}
4943	// Loop when more than two args
4944	$i = count($args);
4945	while ($i) {
4946	$arg = array_shift($args);
4947	$i--;
4948	if (0 == $i) {
4949	$result .= $l['between_last_two'] . $arg;
4950	} else {
4951	$result .= $l['between'] . $arg;
4952	}
4953	}
4954	return $result . substr($pattern, 2);
4955	}
4956
4957	/**
4958	* Safely extracts not more than the first $count characters from html string.
4959	*
4960	* UTF-8, tags and entities safe prefix extraction. Entities inside will NOT
4961	* be counted as one character. For example & will be counted as 4, < as
4962	* 3, etc.
4963	*
4964	* @since 2.5.0
4965	*
4966	* @param string $str String to get the excerpt from.
4967	* @param int $count Maximum number of characters to take.
4968	* @param string $more Optional. What to append if $str needs to be trimmed. Defaults to empty string.
4969	* @return string The excerpt.
4970	*/
4971	function wp_html_excerpt($str, $count, $more = null)
4972	{
4973	if (null === $more) {
4974	$more = '';
4975	}
4976	$str = wp_strip_all_tags($str, true);
4977	$excerpt = mb_substr($str, 0, $count);
4978	// remove part of an entity at the end
4979	$excerpt = preg_replace('/&[^;\s]{0,6}$/', '', $excerpt);
4980	if ($str != $excerpt) {
4981	$excerpt = trim($excerpt) . $more;
4982	}
4983	return $excerpt;
4984	}
4985
4986	/**
4987	* Add a Base url to relative links in passed content.
4988	*
4989	* By default it supports the 'src' and 'href' attributes. However this can be
4990	* changed via the 3rd param.
4991	*
4992	* @since 2.7.0
4993	*
4994	* @global string $_links_add_base
4995	*
4996	* @param string $content String to search for links in.
4997	* @param string $base The base URL to prefix to links.
4998	* @param array $attrs The attributes which should be processed.
4999	* @return string The processed content.
5000	*/
5001	function links_add_base_url($content, $base, $attrs = array( 'src', 'href' ))
5002	{
5003	global $_links_add_base;
5004	$_links_add_base = $base;
5005	$attrs = implode('\|', (array) $attrs);
5006	return preg_replace_callback("!($attrs)=(['\"])(.+?)\\2!i", '_links_add_base', $content);
5007	}
5008
5009	/**
5010	* Callback to add a base url to relative links in passed content.
5011	*
5012	* @since 2.7.0
5013	* @access private
5014	*
5015	* @global string $_links_add_base
5016	*
5017	* @param string $m The matched link.
5018	* @return string The processed link.
5019	*/
5020	function _links_add_base($m)
5021	{
5022	global $_links_add_base;
5023	//1 = attribute name 2 = quotation mark 3 = URL
5024	return $m[1] . '=' . $m[2] .
5025	( preg_match('#^(\w{1,20}):#', $m[3], $protocol) && in_array($protocol[1], wp_allowed_protocols()) ?
5026	$m[3] :
5027	WP_Http::make_absolute_url($m[3], $_links_add_base)
5028	)
5029	. $m[2];
5030	}
5031
5032	/**
5033	* Adds a Target attribute to all links in passed content.
5034	*
5035	* This function by default only applies to `<a>` tags, however this can be
5036	* modified by the 3rd param.
5037	*
5038	* NOTE: Any current target attributed will be stripped and replaced.
5039	*
5040	* @since 2.7.0
5041	*
5042	* @global string $_links_add_target
5043	*
5044	* @param string $content String to search for links in.
5045	* @param string $target The Target to add to the links.
5046	* @param array $tags An array of tags to apply to.
5047	* @return string The processed content.
5048	*/
5049	function links_add_target($content, $target = '_blank', $tags = array( 'a' ))
5050	{
5051	global $_links_add_target;
5052	$_links_add_target = $target;
5053	$tags = implode('\|', (array) $tags);
5054	return preg_replace_callback("!<($tags)([^>]*)>!i", '_links_add_target', $content);
5055	}
5056
5057	/**
5058	* Callback to add a target attribute to all links in passed content.
5059	*
5060	* @since 2.7.0
5061	* @access private
5062	*
5063	* @global string $_links_add_target
5064	*
5065	* @param string $m The matched link.
5066	* @return string The processed link.
5067	*/
5068	function _links_add_target($m)
5069	{
5070	global $_links_add_target;
5071	$tag = $m[1];
5072	$link = preg_replace('\|( target=([\'"])(.*?)\2)\|i', '', $m[2]);
5073	return '<' . $tag . $link . ' target="' . esc_attr($_links_add_target) . '">';
5074	}
5075
5076	/**
5077	* Normalize EOL characters and strip duplicate whitespace.
5078	*
5079	* @since 2.7.0
5080	*
5081	* @param string $str The string to normalize.
5082	* @return string The normalized string.
5083	*/
5084	function normalize_whitespace($str)
5085	{
5086	$str = trim($str);
5087	$str = str_replace("\r", "\n", $str);
5088	$str = preg_replace(array( '/\n+/', '/[ \t]+/' ), array( "\n", ' ' ), $str);
5089	return $str;
5090	}
5091
5092	/**
5093	* Properly strip all HTML tags including script and style
5094	*
5095	* This differs from strip_tags() because it removes the contents of
5096	* the `<script>` and `<style>` tags. E.g. `strip_tags( '<script>something</script>' )`
5097	* will return 'something'. wp_strip_all_tags will return ''
5098	*
5099	* @since 2.9.0
5100	*
5101	* @param string $string String containing HTML tags
5102	* @param bool $remove_breaks Optional. Whether to remove left over line breaks and white space chars
5103	* @return string The processed string.
5104	*/
5105	function wp_strip_all_tags($string, $remove_breaks = false)
5106	{
5107	$string = preg_replace('@<(script\|style)[^>]?>.?</\\1>@si', '', $string);
5108	$string = strip_tags($string);
5109
5110	if ($remove_breaks) {
5111	$string = preg_replace('/[\r\n\t ]+/', ' ', $string);
5112	}
5113
5114	return trim($string);
5115	}
5116
5117	/**
5118	* Sanitizes a string from user input or from the database.
5119	*
5120	* - Checks for invalid UTF-8,
5121	* - Converts single `<` characters to entities
5122	* - Strips all tags
5123	* - Removes line breaks, tabs, and extra whitespace
5124	* - Strips octets
5125	*
5126	* @since 2.9.0
5127	*
5128	* @see sanitize_textarea_field()
5129	* @see wp_check_invalid_utf8()
5130	* @see wp_strip_all_tags()
5131	*
5132	* @param string $str String to sanitize.
5133	* @return string Sanitized string.
5134	*/
5135	function sanitize_text_field($str)
5136	{
5137	$filtered = _sanitize_text_fields($str, false);
5138
5139	/**
5140	* Filters a sanitized text field string.
5141	*
5142	* @since 2.9.0
5143	*
5144	* @param string $filtered The sanitized string.
5145	* @param string $str The string prior to being sanitized.
5146	*/
5147	return apply_filters('sanitize_text_field', $filtered, $str);
5148	}
5149
5150	/**
5151	* Sanitizes a multiline string from user input or from the database.
5152	*
5153	* The function is like sanitize_text_field(), but preserves
5154	* new lines (\n) and other whitespace, which are legitimate
5155	* input in textarea elements.
5156	*
5157	* @see sanitize_text_field()
5158	*
5159	* @since 4.7.0
5160	*
5161	* @param string $str String to sanitize.
5162	* @return string Sanitized string.
5163	*/
5164	function sanitize_textarea_field($str)
5165	{
5166	$filtered = _sanitize_text_fields($str, true);
5167
5168	/**
5169	* Filters a sanitized textarea field string.
5170	*
5171	* @since 4.7.0
5172	*
5173	* @param string $filtered The sanitized string.
5174	* @param string $str The string prior to being sanitized.
5175	*/
5176	return apply_filters('sanitize_textarea_field', $filtered, $str);
5177	}
5178
5179	/**
5180	* Internal helper function to sanitize a string from user input or from the db
5181	*
5182	* @since 4.7.0
5183	* @access private
5184	*
5185	* @param string $str String to sanitize.
5186	* @param bool $keep_newlines optional Whether to keep newlines. Default: false.
5187	* @return string Sanitized string.
5188	*/
5189	function _sanitize_text_fields($str, $keep_newlines = false)
5190	{
5191	$filtered = wp_check_invalid_utf8($str);
5192
5193	if (strpos($filtered, '<') !== false) {
5194	$filtered = wp_pre_kses_less_than($filtered);
5195	// This will strip extra whitespace for us.
5196	$filtered = wp_strip_all_tags($filtered, false);
5197
5198	// Use html entities in a special case to make sure no later
5199	// newline stripping stage could lead to a functional tag
5200	$filtered = str_replace("<\n", "<\n", $filtered);
5201	}
5202
5203	if (! $keep_newlines) {
5204	$filtered = preg_replace('/[\r\n\t ]+/', ' ', $filtered);
5205	}
5206	$filtered = trim($filtered);
5207
5208	$found = false;
5209	while (preg_match('/%[a-f0-9]{2}/i', $filtered, $match

Make WordPress Core

Context Navigation

Ticket #40135: formatting.php