3 * Main WordPress Formatting API.
5 * Handles many functions for formatting output.
11 * Replaces common plain text characters into formatted entities
15 * 'cause today's effort makes it worth tomorrow's "holiday" ...
19 * ’cause today’s effort makes it worth tomorrow’s “holiday” …
21 * Code within certain html blocks are skipped.
23 * Do not use this function before the {@see 'init'} action hook; everything will break.
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
37 * @param string $text The text to be formatted
38 * @param bool $reset Set to true for unit testing. Translated patterns will reset.
39 * @return string The string replaced with html entities
41 function wptexturize( $text, $reset = false ) {
42 global $wp_cockneyreplace, $shortcode_tags;
43 static $static_characters = null,
44 $static_replacements = null,
45 $dynamic_characters = null,
46 $dynamic_replacements = null,
47 $default_no_texturize_tags = null,
48 $default_no_texturize_shortcodes = null,
49 $run_texturize = true,
53 $opening_quote = null,
54 $closing_quote = null,
55 $opening_single_quote = null,
56 $closing_single_quote = null,
57 $open_q_flag = '<!--oq-->',
58 $open_sq_flag = '<!--osq-->',
59 $apos_flag = '<!--apos-->';
61 // If there's nothing to do, just stop.
62 if ( empty( $text ) || false === $run_texturize ) {
66 // Set up static variables. Run once only.
67 if ( $reset || ! isset( $static_characters ) ) {
69 * Filters whether to skip running wptexturize().
71 * Passing false to the filter will effectively short-circuit wptexturize().
72 * returning the original text passed to the function instead.
74 * The filter runs only once, the first time wptexturize() is called.
80 * @param bool $run_texturize Whether to short-circuit wptexturize().
82 $run_texturize = apply_filters( 'run_wptexturize', $run_texturize );
83 if ( false === $run_texturize ) {
87 /* translators: opening curly double quote */
88 $opening_quote = _x( '“', 'opening curly double quote' );
89 /* translators: closing curly double quote */
90 $closing_quote = _x( '”', 'closing curly double quote' );
92 /* translators: apostrophe, for example in 'cause or can't */
93 $apos = _x( '’', 'apostrophe' );
95 /* translators: prime, for example in 9' (nine feet) */
96 $prime = _x( '′', 'prime' );
97 /* translators: double prime, for example in 9" (nine inches) */
98 $double_prime = _x( '″', 'double prime' );
100 /* translators: opening curly single quote */
101 $opening_single_quote = _x( '‘', 'opening curly single quote' );
102 /* translators: closing curly single quote */
103 $closing_single_quote = _x( '’', 'closing curly single quote' );
105 /* translators: en dash */
106 $en_dash = _x( '–', 'en dash' );
107 /* translators: em dash */
108 $em_dash = _x( '—', 'em dash' );
110 $default_no_texturize_tags = array('pre', 'code', 'kbd', 'style', 'script', 'tt');
111 $default_no_texturize_shortcodes = array('code');
113 // if a plugin has provided an autocorrect array, use it
114 if ( isset($wp_cockneyreplace) ) {
115 $cockney = array_keys( $wp_cockneyreplace );
116 $cockneyreplace = array_values( $wp_cockneyreplace );
118 /* translators: This is a comma-separated list of words that defy the syntax of quotations in normal use,
119 * for example... 'We do not have enough words yet' ... is a typical quoted phrase. But when we write
120 * lines of code 'til we have enough of 'em, then we need to insert apostrophes instead of quotes.
122 $cockney = explode( ',', _x( "'tain't,'twere,'twas,'tis,'twill,'til,'bout,'nuff,'round,'cause,'em",
123 'Comma-separated list of words to texturize in your language' ) );
125 $cockneyreplace = explode( ',', _x( '’tain’t,’twere,’twas,’tis,’twill,’til,’bout,’nuff,’round,’cause,’em',
126 'Comma-separated list of replacement words in your language' ) );
129 $static_characters = array_merge( array( '...', '``', '\'\'', ' (tm)' ), $cockney );
130 $static_replacements = array_merge( array( '…', $opening_quote, $closing_quote, ' ™' ), $cockneyreplace );
133 // Pattern-based replacements of characters.
134 // Sort the remaining patterns into several arrays for performance tuning.
135 $dynamic_characters = array( 'apos' => array(), 'quote' => array(), 'dash' => array() );
136 $dynamic_replacements = array( 'apos' => array(), 'quote' => array(), 'dash' => array() );
138 $spaces = wp_spaces_regexp();
140 // '99' and '99" are ambiguous among other patterns; assume it's an abbreviated year at the end of a quotation.
141 if ( "'" !== $apos || "'" !== $closing_single_quote ) {
142 $dynamic[ '/\'(\d\d)\'(?=\Z|[.,:;!?)}\-\]]|>|' . $spaces . ')/' ] = $apos_flag . '$1' . $closing_single_quote;
144 if ( "'" !== $apos || '"' !== $closing_quote ) {
145 $dynamic[ '/\'(\d\d)"(?=\Z|[.,:;!?)}\-\]]|>|' . $spaces . ')/' ] = $apos_flag . '$1' . $closing_quote;
148 // '99 '99s '99's (apostrophe) But never '9 or '99% or '999 or '99.0.
149 if ( "'" !== $apos ) {
150 $dynamic[ '/\'(?=\d\d(?:\Z|(?![%\d]|[.,]\d)))/' ] = $apos_flag;
153 // Quoted Numbers like '0.42'
154 if ( "'" !== $opening_single_quote && "'" !== $closing_single_quote ) {
155 $dynamic[ '/(?<=\A|' . $spaces . ')\'(\d[.,\d]*)\'/' ] = $open_sq_flag . '$1' . $closing_single_quote;
158 // Single quote at start, or preceded by (, {, <, [, ", -, or spaces.
159 if ( "'" !== $opening_single_quote ) {
160 $dynamic[ '/(?<=\A|[([{"\-]|<|' . $spaces . ')\'/' ] = $open_sq_flag;
163 // Apostrophe in a word. No spaces, double apostrophes, or other punctuation.
164 if ( "'" !== $apos ) {
165 $dynamic[ '/(?<!' . $spaces . ')\'(?!\Z|[.,:;!?"\'(){}[\]\-]|&[lg]t;|' . $spaces . ')/' ] = $apos_flag;
168 $dynamic_characters['apos'] = array_keys( $dynamic );
169 $dynamic_replacements['apos'] = array_values( $dynamic );
172 // Quoted Numbers like "42"
173 if ( '"' !== $opening_quote && '"' !== $closing_quote ) {
174 $dynamic[ '/(?<=\A|' . $spaces . ')"(\d[.,\d]*)"/' ] = $open_q_flag . '$1' . $closing_quote;
177 // Double quote at start, or preceded by (, {, <, [, -, or spaces, and not followed by spaces.
178 if ( '"' !== $opening_quote ) {
179 $dynamic[ '/(?<=\A|[([{\-]|<|' . $spaces . ')"(?!' . $spaces . ')/' ] = $open_q_flag;
182 $dynamic_characters['quote'] = array_keys( $dynamic );
183 $dynamic_replacements['quote'] = array_values( $dynamic );
187 $dynamic[ '/---/' ] = $em_dash;
188 $dynamic[ '/(?<=^|' . $spaces . ')--(?=$|' . $spaces . ')/' ] = $em_dash;
189 $dynamic[ '/(?<!xn)--/' ] = $en_dash;
190 $dynamic[ '/(?<=^|' . $spaces . ')-(?=$|' . $spaces . ')/' ] = $en_dash;
192 $dynamic_characters['dash'] = array_keys( $dynamic );
193 $dynamic_replacements['dash'] = array_values( $dynamic );
196 // Must do this every time in case plugins use these filters in a context sensitive manner
198 * Filters the list of HTML elements not to texturize.
202 * @param array $default_no_texturize_tags An array of HTML element names.
204 $no_texturize_tags = apply_filters( 'no_texturize_tags', $default_no_texturize_tags );
206 * Filters the list of shortcodes not to texturize.
210 * @param array $default_no_texturize_shortcodes An array of shortcode names.
212 $no_texturize_shortcodes = apply_filters( 'no_texturize_shortcodes', $default_no_texturize_shortcodes );
214 $no_texturize_tags_stack = array();
215 $no_texturize_shortcodes_stack = array();
217 // Look for shortcodes and HTML elements.
219 preg_match_all( '@\[/?([^<>&/\[\]\x00-\x20=]++)@', $text, $matches );
220 $tagnames = array_intersect( array_keys( $shortcode_tags ), $matches[1] );
221 $found_shortcodes = ! empty( $tagnames );
222 $shortcode_regex = $found_shortcodes ? _get_wptexturize_shortcode_regex( $tagnames ) : '';
223 $regex = _get_wptexturize_split_regex( $shortcode_regex );
225 $textarr = preg_split( $regex, $text, -1, PREG_SPLIT_DELIM_CAPTURE | PREG_SPLIT_NO_EMPTY );
227 foreach ( $textarr as &$curl ) {
228 // Only call _wptexturize_pushpop_element if $curl is a delimiter.
230 if ( '<' === $first ) {
231 if ( '<!--' === substr( $curl, 0, 4 ) ) {
232 // This is an HTML comment delimiter.
235 // This is an HTML element delimiter.
237 // Replace each & with & unless it already looks like an entity.
238 $curl = preg_replace( '/&(?!#(?:\d+|x[a-f0-9]+);|[a-z1-4]{1,8};)/i', '&', $curl );
240 _wptexturize_pushpop_element( $curl, $no_texturize_tags_stack, $no_texturize_tags );
243 } elseif ( '' === trim( $curl ) ) {
244 // This is a newline between delimiters. Performance improves when we check this.
247 } elseif ( '[' === $first && $found_shortcodes && 1 === preg_match( '/^' . $shortcode_regex . '$/', $curl ) ) {
248 // This is a shortcode delimiter.
250 if ( '[[' !== substr( $curl, 0, 2 ) && ']]' !== substr( $curl, -2 ) ) {
251 // Looks like a normal shortcode.
252 _wptexturize_pushpop_element( $curl, $no_texturize_shortcodes_stack, $no_texturize_shortcodes );
254 // Looks like an escaped shortcode.
258 } elseif ( empty( $no_texturize_shortcodes_stack ) && empty( $no_texturize_tags_stack ) ) {
259 // This is neither a delimiter, nor is this content inside of no_texturize pairs. Do texturize.
261 $curl = str_replace( $static_characters, $static_replacements, $curl );
263 if ( false !== strpos( $curl, "'" ) ) {
264 $curl = preg_replace( $dynamic_characters['apos'], $dynamic_replacements['apos'], $curl );
265 $curl = wptexturize_primes( $curl, "'", $prime, $open_sq_flag, $closing_single_quote );
266 $curl = str_replace( $apos_flag, $apos, $curl );
267 $curl = str_replace( $open_sq_flag, $opening_single_quote, $curl );
269 if ( false !== strpos( $curl, '"' ) ) {
270 $curl = preg_replace( $dynamic_characters['quote'], $dynamic_replacements['quote'], $curl );
271 $curl = wptexturize_primes( $curl, '"', $double_prime, $open_q_flag, $closing_quote );
272 $curl = str_replace( $open_q_flag, $opening_quote, $curl );
274 if ( false !== strpos( $curl, '-' ) ) {
275 $curl = preg_replace( $dynamic_characters['dash'], $dynamic_replacements['dash'], $curl );
278 // 9x9 (times), but never 0x9999
279 if ( 1 === preg_match( '/(?<=\d)x\d/', $curl ) ) {
280 // Searching for a digit is 10 times more expensive than for the x, so we avoid doing this one!
281 $curl = preg_replace( '/\b(\d(?(?<=0)[\d\.,]+|[\d\.,]*))x(\d[\d\.,]*)\b/', '$1×$2', $curl );
284 // Replace each & with & unless it already looks like an entity.
285 $curl = preg_replace( '/&(?!#(?:\d+|x[a-f0-9]+);|[a-z1-4]{1,8};)/i', '&', $curl );
289 return implode( '', $textarr );
293 * Implements a logic tree to determine whether or not "7'." represents seven feet,
294 * then converts the special char into either a prime char or a closing quote char.
298 * @param string $haystack The plain text to be searched.
299 * @param string $needle The character to search for such as ' or ".
300 * @param string $prime The prime char to use for replacement.
301 * @param string $open_quote The opening quote char. Opening quote replacement must be
302 * accomplished already.
303 * @param string $close_quote The closing quote char to use for replacement.
304 * @return string The $haystack value after primes and quotes replacements.
306 function wptexturize_primes( $haystack, $needle, $prime, $open_quote, $close_quote ) {
307 $spaces = wp_spaces_regexp();
308 $flag = '<!--wp-prime-or-quote-->';
309 $quote_pattern = "/$needle(?=\\Z|[.,:;!?)}\\-\\]]|>|" . $spaces . ")/";
310 $prime_pattern = "/(?<=\\d)$needle/";
311 $flag_after_digit = "/(?<=\\d)$flag/";
312 $flag_no_digit = "/(?<!\\d)$flag/";
314 $sentences = explode( $open_quote, $haystack );
316 foreach ( $sentences as $key => &$sentence ) {
317 if ( false === strpos( $sentence, $needle ) ) {
319 } elseif ( 0 !== $key && 0 === substr_count( $sentence, $close_quote ) ) {
320 $sentence = preg_replace( $quote_pattern, $flag, $sentence, -1, $count );
322 // This sentence appears to have multiple closing quotes. Attempt Vulcan logic.
323 $sentence = preg_replace( $flag_no_digit, $close_quote, $sentence, -1, $count2 );
324 if ( 0 === $count2 ) {
325 // Try looking for a quote followed by a period.
326 $count2 = substr_count( $sentence, "$flag." );
328 // Assume the rightmost quote-period match is the end of quotation.
329 $pos = strrpos( $sentence, "$flag." );
331 // When all else fails, make the rightmost candidate a closing quote.
332 // This is most likely to be problematic in the context of bug #18549.
333 $pos = strrpos( $sentence, $flag );
335 $sentence = substr_replace( $sentence, $close_quote, $pos, strlen( $flag ) );
337 // Use conventional replacement on any remaining primes and quotes.
338 $sentence = preg_replace( $prime_pattern, $prime, $sentence );
339 $sentence = preg_replace( $flag_after_digit, $prime, $sentence );
340 $sentence = str_replace( $flag, $close_quote, $sentence );
341 } elseif ( 1 == $count ) {
342 // Found only one closing quote candidate, so give it priority over primes.
343 $sentence = str_replace( $flag, $close_quote, $sentence );
344 $sentence = preg_replace( $prime_pattern, $prime, $sentence );
346 // No closing quotes found. Just run primes pattern.
347 $sentence = preg_replace( $prime_pattern, $prime, $sentence );
350 $sentence = preg_replace( $prime_pattern, $prime, $sentence );
351 $sentence = preg_replace( $quote_pattern, $close_quote, $sentence );
353 if ( '"' == $needle && false !== strpos( $sentence, '"' ) ) {
354 $sentence = str_replace( '"', $close_quote, $sentence );
358 return implode( $open_quote, $sentences );
362 * Search for disabled element tags. Push element to stack on tag open and pop
365 * Assumes first char of $text is tag opening and last char is tag closing.
366 * Assumes second char of $text is optionally '/' to indicate closing as in </html>.
371 * @param string $text Text to check. Must be a tag like `<html>` or `[shortcode]`.
372 * @param array $stack List of open tag elements.
373 * @param array $disabled_elements The tag names to match against. Spaces are not allowed in tag names.
375 function _wptexturize_pushpop_element( $text, &$stack, $disabled_elements ) {
376 // Is it an opening tag or closing tag?
377 if ( isset( $text[1] ) && '/' !== $text[1] ) {
380 } elseif ( 0 == count( $stack ) ) {
381 // Stack is empty. Just stop.
384 $opening_tag = false;
388 // Parse out the tag name.
389 $space = strpos( $text, ' ' );
390 if ( false === $space ) {
393 $space -= $name_offset;
395 $tag = substr( $text, $name_offset, $space );
397 // Handle disabled tags.
398 if ( in_array( $tag, $disabled_elements ) ) {
399 if ( $opening_tag ) {
401 * This disables texturize until we find a closing tag of our type
402 * (e.g. <pre>) even if there was invalid nesting before that
404 * Example: in the case <pre>sadsadasd</code>"baba"</pre>
405 * "baba" won't be texturize
408 array_push( $stack, $tag );
409 } elseif ( end( $stack ) == $tag ) {
416 * Replaces double line-breaks with paragraph elements.
418 * A group of regex replaces used to identify text formatted with newlines and
419 * replace double line-breaks with HTML paragraph tags. The remaining line-breaks
420 * after conversion become <<br />> tags, unless $br is set to '0' or 'false'.
424 * @param string $pee The text which has to be formatted.
425 * @param bool $br Optional. If set, this will convert all remaining line-breaks
426 * after paragraphing. Default true.
427 * @return string Text which has been converted into correct paragraph tags.
429 function wpautop( $pee, $br = true ) {
432 if ( trim($pee) === '' )
435 // Just to make things a little easier, pad the end.
439 * Pre tags shouldn't be touched by autop.
440 * Replace pre tags with placeholders and bring them back after autop.
442 if ( strpos($pee, '<pre') !== false ) {
443 $pee_parts = explode( '</pre>', $pee );
444 $last_pee = array_pop($pee_parts);
448 foreach ( $pee_parts as $pee_part ) {
449 $start = strpos($pee_part, '<pre');
452 if ( $start === false ) {
457 $name = "<pre wp-pre-tag-$i></pre>";
458 $pre_tags[$name] = substr( $pee_part, $start ) . '</pre>';
460 $pee .= substr( $pee_part, 0, $start ) . $name;
466 // Change multiple <br>s into two line breaks, which will turn into paragraphs.
467 $pee = preg_replace('|<br\s*/?>\s*<br\s*/?>|', "\n\n", $pee);
469 $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)';
471 // Add a single line break above block-level opening tags.
472 $pee = preg_replace('!(<' . $allblocks . '[\s/>])!', "\n$1", $pee);
474 // Add a double line break below block-level closing tags.
475 $pee = preg_replace('!(</' . $allblocks . '>)!', "$1\n\n", $pee);
477 // Standardize newline characters to "\n".
478 $pee = str_replace(array("\r\n", "\r"), "\n", $pee);
480 // Find newlines in all elements and add placeholders.
481 $pee = wp_replace_in_html_tags( $pee, array( "\n" => " <!-- wpnl --> " ) );
483 // Collapse line breaks before and after <option> elements so they don't get autop'd.
484 if ( strpos( $pee, '<option' ) !== false ) {
485 $pee = preg_replace( '|\s*<option|', '<option', $pee );
486 $pee = preg_replace( '|</option>\s*|', '</option>', $pee );
490 * Collapse line breaks inside <object> elements, before <param> and <embed> elements
491 * so they don't get autop'd.
493 if ( strpos( $pee, '</object>' ) !== false ) {
494 $pee = preg_replace( '|(<object[^>]*>)\s*|', '$1', $pee );
495 $pee = preg_replace( '|\s*</object>|', '</object>', $pee );
496 $pee = preg_replace( '%\s*(</?(?:param|embed)[^>]*>)\s*%', '$1', $pee );
500 * Collapse line breaks inside <audio> and <video> elements,
501 * before and after <source> and <track> elements.
503 if ( strpos( $pee, '<source' ) !== false || strpos( $pee, '<track' ) !== false ) {
504 $pee = preg_replace( '%([<\[](?:audio|video)[^>\]]*[>\]])\s*%', '$1', $pee );
505 $pee = preg_replace( '%\s*([<\[]/(?:audio|video)[>\]])%', '$1', $pee );
506 $pee = preg_replace( '%\s*(<(?:source|track)[^>]*>)\s*%', '$1', $pee );
509 // Remove more than two contiguous line breaks.
510 $pee = preg_replace("/\n\n+/", "\n\n", $pee);
512 // Split up the contents into an array of strings, separated by double line breaks.
513 $pees = preg_split('/\n\s*\n/', $pee, -1, PREG_SPLIT_NO_EMPTY);
515 // Reset $pee prior to rebuilding.
518 // Rebuild the content as a string, wrapping every bit with a <p>.
519 foreach ( $pees as $tinkle ) {
520 $pee .= '<p>' . trim($tinkle, "\n") . "</p>\n";
523 // Under certain strange conditions it could create a P of entirely whitespace.
524 $pee = preg_replace('|<p>\s*</p>|', '', $pee);
526 // Add a closing <p> inside <div>, <address>, or <form> tag if missing.
527 $pee = preg_replace('!<p>([^<]+)</(div|address|form)>!', "<p>$1</p></$2>", $pee);
529 // If an opening or closing block element tag is wrapped in a <p>, unwrap it.
530 $pee = preg_replace('!<p>\s*(</?' . $allblocks . '[^>]*>)\s*</p>!', "$1", $pee);
532 // In some cases <li> may get wrapped in <p>, fix them.
533 $pee = preg_replace("|<p>(<li.+?)</p>|", "$1", $pee);
535 // If a <blockquote> is wrapped with a <p>, move it inside the <blockquote>.
536 $pee = preg_replace('|<p><blockquote([^>]*)>|i', "<blockquote$1><p>", $pee);
537 $pee = str_replace('</blockquote></p>', '</p></blockquote>', $pee);
539 // If an opening or closing block element tag is preceded by an opening <p> tag, remove it.
540 $pee = preg_replace('!<p>\s*(</?' . $allblocks . '[^>]*>)!', "$1", $pee);
542 // If an opening or closing block element tag is followed by a closing <p> tag, remove it.
543 $pee = preg_replace('!(</?' . $allblocks . '[^>]*>)\s*</p>!', "$1", $pee);
545 // Optionally insert line breaks.
547 // Replace newlines that shouldn't be touched with a placeholder.
548 $pee = preg_replace_callback('/<(script|style).*?<\/\\1>/s', '_autop_newline_preservation_helper', $pee);
551 $pee = str_replace( array( '<br>', '<br/>' ), '<br />', $pee );
553 // Replace any new line characters that aren't preceded by a <br /> with a <br />.
554 $pee = preg_replace('|(?<!<br />)\s*\n|', "<br />\n", $pee);
556 // Replace newline placeholders with newlines.
557 $pee = str_replace('<WPPreserveNewline />', "\n", $pee);
560 // If a <br /> tag is after an opening or closing block tag, remove it.
561 $pee = preg_replace('!(</?' . $allblocks . '[^>]*>)\s*<br />!', "$1", $pee);
563 // If a <br /> tag is before a subset of opening or closing block tags, remove it.
564 $pee = preg_replace('!<br />(\s*</?(?:p|li|div|dl|dd|dt|th|pre|td|ul|ol)[^>]*>)!', '$1', $pee);
565 $pee = preg_replace( "|\n</p>$|", '</p>', $pee );
567 // Replace placeholder <pre> tags with their original content.
568 if ( !empty($pre_tags) )
569 $pee = str_replace(array_keys($pre_tags), array_values($pre_tags), $pee);
571 // Restore newlines in all elements.
572 if ( false !== strpos( $pee, '<!-- wpnl -->' ) ) {
573 $pee = str_replace( array( ' <!-- wpnl --> ', '<!-- wpnl -->' ), "\n", $pee );
580 * Separate HTML elements and comments from the text.
584 * @param string $input The text which has to be formatted.
585 * @return array The formatted text.
587 function wp_html_split( $input ) {
588 return preg_split( get_html_split_regex(), $input, -1, PREG_SPLIT_DELIM_CAPTURE );
592 * Retrieve the regular expression for an HTML element.
596 * @return string The regular expression
598 function get_html_split_regex() {
601 if ( ! isset( $regex ) ) {
603 '!' // Start of comment, after the <.
604 . '(?:' // Unroll the loop: Consume everything until --> is found.
605 . '-(?!->)' // Dash not followed by end of comment.
606 . '[^\-]*+' // Consume non-dashes.
607 . ')*+' // Loop possessively.
608 . '(?:-->)?'; // End of comment. If not found, match all input.
611 '!\[CDATA\[' // Start of comment, after the <.
612 . '[^\]]*+' // Consume non-].
613 . '(?:' // Unroll the loop: Consume everything until ]]> is found.
614 . '](?!]>)' // One ] not followed by end of comment.
615 . '[^\]]*+' // Consume non-].
616 . ')*+' // Loop possessively.
617 . '(?:]]>)?'; // End of comment. If not found, match all input.
620 '(?=' // Is the element escaped?
625 . '(?(?=!-)' // If yes, which type?
632 '/(' // Capture the entire match.
633 . '<' // Find start of element.
634 . '(?' // Conditional expression follows.
635 . $escaped // Find end of escaped element.
636 . '|' // ... else ...
637 . '[^>]*>?' // Find end of normal element.
646 * Retrieve the combined regular expression for HTML and shortcodes.
650 * @internal This function will be removed in 4.5.0 per Shortcode API Roadmap.
653 * @param string $shortcode_regex The result from _get_wptexturize_shortcode_regex(). Optional.
654 * @return string The regular expression
656 function _get_wptexturize_split_regex( $shortcode_regex = '' ) {
659 if ( ! isset( $html_regex ) ) {
661 '!' // Start of comment, after the <.
662 . '(?:' // Unroll the loop: Consume everything until --> is found.
663 . '-(?!->)' // Dash not followed by end of comment.
664 . '[^\-]*+' // Consume non-dashes.
665 . ')*+' // Loop possessively.
666 . '(?:-->)?'; // End of comment. If not found, match all input.
668 $html_regex = // Needs replaced with wp_html_split() per Shortcode API Roadmap.
669 '<' // Find start of element.
670 . '(?(?=!--)' // Is this a comment?
671 . $comment_regex // Find end of comment.
673 . '[^>]*>?' // Find end of element. If not found, match all input.
677 if ( empty( $shortcode_regex ) ) {
678 $regex = '/(' . $html_regex . ')/';
680 $regex = '/(' . $html_regex . '|' . $shortcode_regex . ')/';
687 * Retrieve the regular expression for shortcodes.
691 * @internal This function will be removed in 4.5.0 per Shortcode API Roadmap.
694 * @param array $tagnames List of shortcodes to find.
695 * @return string The regular expression
697 function _get_wptexturize_shortcode_regex( $tagnames ) {
698 $tagregexp = join( '|', array_map( 'preg_quote', $tagnames ) );
699 $tagregexp = "(?:$tagregexp)(?=[\\s\\]\\/])"; // Excerpt of get_shortcode_regex().
701 '\[' // Find start of shortcode.
702 . '[\/\[]?' // Shortcodes may begin with [/ or [[
703 . $tagregexp // Only match registered shortcodes, because performance.
705 . '[^\[\]<>]+' // Shortcodes do not contain other shortcodes. Quantifier critical.
707 . '<[^\[\]>]*>' // HTML elements permitted. Prevents matching ] before >.
708 . ')*+' // Possessive critical.
709 . '\]' // Find end of shortcode.
710 . '\]?'; // Shortcodes may end with ]]
716 * Replace characters or phrases within HTML elements only.
720 * @param string $haystack The text which has to be formatted.
721 * @param array $replace_pairs In the form array('from' => 'to', ...).
722 * @return string The formatted text.
724 function wp_replace_in_html_tags( $haystack, $replace_pairs ) {
725 // Find all elements.
726 $textarr = wp_html_split( $haystack );
729 // Optimize when searching for one item.
730 if ( 1 === count( $replace_pairs ) ) {
731 // Extract $needle and $replace.
732 foreach ( $replace_pairs as $needle => $replace );
734 // Loop through delimiters (elements) only.
735 for ( $i = 1, $c = count( $textarr ); $i < $c; $i += 2 ) {
736 if ( false !== strpos( $textarr[$i], $needle ) ) {
737 $textarr[$i] = str_replace( $needle, $replace, $textarr[$i] );
742 // Extract all $needles.
743 $needles = array_keys( $replace_pairs );
745 // Loop through delimiters (elements) only.
746 for ( $i = 1, $c = count( $textarr ); $i < $c; $i += 2 ) {
747 foreach ( $needles as $needle ) {
748 if ( false !== strpos( $textarr[$i], $needle ) ) {
749 $textarr[$i] = strtr( $textarr[$i], $replace_pairs );
751 // After one strtr() break out of the foreach loop and look at next element.
759 $haystack = implode( $textarr );
766 * Newline preservation help function for wpautop
771 * @param array $matches preg_replace_callback matches array
774 function _autop_newline_preservation_helper( $matches ) {
775 return str_replace( "\n", "<WPPreserveNewline />", $matches[0] );
779 * Don't auto-p wrap shortcodes that stand alone
781 * Ensures that shortcodes are not wrapped in `<p>...</p>`.
785 * @global array $shortcode_tags
787 * @param string $pee The content.
788 * @return string The filtered content.
790 function shortcode_unautop( $pee ) {
791 global $shortcode_tags;
793 if ( empty( $shortcode_tags ) || !is_array( $shortcode_tags ) ) {
797 $tagregexp = join( '|', array_map( 'preg_quote', array_keys( $shortcode_tags ) ) );
798 $spaces = wp_spaces_regexp();
802 . '<p>' // Opening paragraph
803 . '(?:' . $spaces . ')*+' // Optional leading whitespace
804 . '(' // 1: The shortcode
805 . '\\[' // Opening bracket
806 . "($tagregexp)" // 2: Shortcode name
807 . '(?![\\w-])' // Not followed by word character or hyphen
808 // Unroll the loop: Inside the opening shortcode tag
809 . '[^\\]\\/]*' // Not a closing bracket or forward slash
811 . '\\/(?!\\])' // A forward slash not followed by a closing bracket
812 . '[^\\]\\/]*' // Not a closing bracket or forward slash
815 . '\\/\\]' // Self closing tag and closing bracket
817 . '\\]' // Closing bracket
818 . '(?:' // Unroll the loop: Optionally, anything between the opening and closing shortcode tags
819 . '[^\\[]*+' // Not an opening bracket
821 . '\\[(?!\\/\\2\\])' // An opening bracket not followed by the closing shortcode tag
822 . '[^\\[]*+' // Not an opening bracket
824 . '\\[\\/\\2\\]' // Closing shortcode tag
828 . '(?:' . $spaces . ')*+' // optional trailing whitespace
829 . '<\\/p>' // closing paragraph
832 return preg_replace( $pattern, '$1', $pee );
836 * Checks to see if a string is utf8 encoded.
838 * NOTE: This function checks for 5-Byte sequences, UTF8
839 * has Bytes Sequences with a maximum length of 4.
841 * @author bmorel at ssi dot fr (modified)
844 * @param string $str The string to be checked
845 * @return bool True if $str fits a UTF-8 model, false otherwise.
847 function seems_utf8( $str ) {
848 mbstring_binary_safe_encoding();
849 $length = strlen($str);
850 reset_mbstring_encoding();
851 for ($i=0; $i < $length; $i++) {
853 if ($c < 0x80) $n = 0; // 0bbbbbbb
854 elseif (($c & 0xE0) == 0xC0) $n=1; // 110bbbbb
855 elseif (($c & 0xF0) == 0xE0) $n=2; // 1110bbbb
856 elseif (($c & 0xF8) == 0xF0) $n=3; // 11110bbb
857 elseif (($c & 0xFC) == 0xF8) $n=4; // 111110bb
858 elseif (($c & 0xFE) == 0xFC) $n=5; // 1111110b
859 else return false; // Does not match any model
860 for ($j=0; $j<$n; $j++) { // n bytes matching 10bbbbbb follow ?
861 if ((++$i == $length) || ((ord($str[$i]) & 0xC0) != 0x80))
869 * Converts a number of special characters into their HTML entities.
871 * Specifically deals with: &, <, >, ", and '.
873 * $quote_style can be set to ENT_COMPAT to encode " to
874 * ", or ENT_QUOTES to do both. Default is ENT_NOQUOTES where no quotes are encoded.
879 * @staticvar string $_charset
881 * @param string $string The text which is to be encoded.
882 * @param int|string $quote_style Optional. Converts double quotes if set to ENT_COMPAT,
883 * both single and double if set to ENT_QUOTES or none if set to ENT_NOQUOTES.
884 * Also compatible with old values; converting single quotes if set to 'single',
885 * double if set to 'double' or both if otherwise set.
886 * Default is ENT_NOQUOTES.
887 * @param string $charset Optional. The character encoding of the string. Default is false.
888 * @param bool $double_encode Optional. Whether to encode existing html entities. Default is false.
889 * @return string The encoded text with HTML entities.
891 function _wp_specialchars( $string, $quote_style = ENT_NOQUOTES, $charset = false, $double_encode = false ) {
892 $string = (string) $string;
894 if ( 0 === strlen( $string ) )
897 // Don't bother if there are no specialchars - saves some processing
898 if ( ! preg_match( '/[&<>"\']/', $string ) )
901 // Account for the previous behaviour of the function when the $quote_style is not an accepted value
902 if ( empty( $quote_style ) )
903 $quote_style = ENT_NOQUOTES;
904 elseif ( ! in_array( $quote_style, array( 0, 2, 3, 'single', 'double' ), true ) )
905 $quote_style = ENT_QUOTES;
907 // Store the site charset as a static to avoid multiple calls to wp_load_alloptions()
909 static $_charset = null;
910 if ( ! isset( $_charset ) ) {
911 $alloptions = wp_load_alloptions();
912 $_charset = isset( $alloptions['blog_charset'] ) ? $alloptions['blog_charset'] : '';
914 $charset = $_charset;
917 if ( in_array( $charset, array( 'utf8', 'utf-8', 'UTF8' ) ) )
920 $_quote_style = $quote_style;
922 if ( $quote_style === 'double' ) {
923 $quote_style = ENT_COMPAT;
924 $_quote_style = ENT_COMPAT;
925 } elseif ( $quote_style === 'single' ) {
926 $quote_style = ENT_NOQUOTES;
929 if ( ! $double_encode ) {
930 // Guarantee every &entity; is valid, convert &garbage; into &garbage;
931 // This is required for PHP < 5.4.0 because ENT_HTML401 flag is unavailable.
932 $string = wp_kses_normalize_entities( $string );
935 $string = @htmlspecialchars( $string, $quote_style, $charset, $double_encode );
938 if ( 'single' === $_quote_style )
939 $string = str_replace( "'", ''', $string );
945 * Converts a number of HTML entities into their special characters.
947 * Specifically deals with: &, <, >, ", and '.
949 * $quote_style can be set to ENT_COMPAT to decode " entities,
950 * or ENT_QUOTES to do both " and '. Default is ENT_NOQUOTES where no quotes are decoded.
954 * @param string $string The text which is to be decoded.
955 * @param string|int $quote_style Optional. Converts double quotes if set to ENT_COMPAT,
956 * both single and double if set to ENT_QUOTES or
957 * none if set to ENT_NOQUOTES.
958 * Also compatible with old _wp_specialchars() values;
959 * converting single quotes if set to 'single',
960 * double if set to 'double' or both if otherwise set.
961 * Default is ENT_NOQUOTES.
962 * @return string The decoded text without HTML entities.
964 function wp_specialchars_decode( $string, $quote_style = ENT_NOQUOTES ) {
965 $string = (string) $string;
967 if ( 0 === strlen( $string ) ) {
971 // Don't bother if there are no entities - saves a lot of processing
972 if ( strpos( $string, '&' ) === false ) {
976 // Match the previous behaviour of _wp_specialchars() when the $quote_style is not an accepted value
977 if ( empty( $quote_style ) ) {
978 $quote_style = ENT_NOQUOTES;
979 } elseif ( !in_array( $quote_style, array( 0, 2, 3, 'single', 'double' ), true ) ) {
980 $quote_style = ENT_QUOTES;
983 // More complete than get_html_translation_table( HTML_SPECIALCHARS )
984 $single = array( ''' => '\'', ''' => '\'' );
985 $single_preg = array( '/�*39;/' => ''', '/�*27;/i' => ''' );
986 $double = array( '"' => '"', '"' => '"', '"' => '"' );
987 $double_preg = array( '/�*34;/' => '"', '/�*22;/i' => '"' );
988 $others = array( '<' => '<', '<' => '<', '>' => '>', '>' => '>', '&' => '&', '&' => '&', '&' => '&' );
989 $others_preg = array( '/�*60;/' => '<', '/�*62;/' => '>', '/�*38;/' => '&', '/�*26;/i' => '&' );
991 if ( $quote_style === ENT_QUOTES ) {
992 $translation = array_merge( $single, $double, $others );
993 $translation_preg = array_merge( $single_preg, $double_preg, $others_preg );
994 } elseif ( $quote_style === ENT_COMPAT || $quote_style === 'double' ) {
995 $translation = array_merge( $double, $others );
996 $translation_preg = array_merge( $double_preg, $others_preg );
997 } elseif ( $quote_style === 'single' ) {
998 $translation = array_merge( $single, $others );
999 $translation_preg = array_merge( $single_preg, $others_preg );
1000 } elseif ( $quote_style === ENT_NOQUOTES ) {
1001 $translation = $others;
1002 $translation_preg = $others_preg;
1005 // Remove zero padding on numeric entities
1006 $string = preg_replace( array_keys( $translation_preg ), array_values( $translation_preg ), $string );
1008 // Replace characters according to translation table
1009 return strtr( $string, $translation );
1013 * Checks for invalid UTF8 in a string.
1017 * @staticvar bool $is_utf8
1018 * @staticvar bool $utf8_pcre
1020 * @param string $string The text which is to be checked.
1021 * @param bool $strip Optional. Whether to attempt to strip out invalid UTF8. Default is false.
1022 * @return string The checked text.
1024 function wp_check_invalid_utf8( $string, $strip = false ) {
1025 $string = (string) $string;
1027 if ( 0 === strlen( $string ) ) {
1031 // Store the site charset as a static to avoid multiple calls to get_option()
1032 static $is_utf8 = null;
1033 if ( ! isset( $is_utf8 ) ) {
1034 $is_utf8 = in_array( get_option( 'blog_charset' ), array( 'utf8', 'utf-8', 'UTF8', 'UTF-8' ) );
1040 // Check for support for utf8 in the installed PCRE library once and store the result in a static
1041 static $utf8_pcre = null;
1042 if ( ! isset( $utf8_pcre ) ) {
1043 $utf8_pcre = @preg_match( '/^./u', 'a' );
1045 // We can't demand utf8 in the PCRE installation, so just return the string in those cases
1046 if ( !$utf8_pcre ) {
1050 // preg_match fails when it encounters invalid UTF8 in $string
1051 if ( 1 === @preg_match( '/^./us', $string ) ) {
1055 // Attempt to strip the bad chars if requested (not recommended)
1056 if ( $strip && function_exists( 'iconv' ) ) {
1057 return iconv( 'utf-8', 'utf-8', $string );
1064 * Encode the Unicode values to be used in the URI.
1068 * @param string $utf8_string
1069 * @param int $length Max length of the string
1070 * @return string String with Unicode encoded for URI.
1072 function utf8_uri_encode( $utf8_string, $length = 0 ) {
1076 $unicode_length = 0;
1078 mbstring_binary_safe_encoding();
1079 $string_length = strlen( $utf8_string );
1080 reset_mbstring_encoding();
1082 for ($i = 0; $i < $string_length; $i++ ) {
1084 $value = ord( $utf8_string[ $i ] );
1086 if ( $value < 128 ) {
1087 if ( $length && ( $unicode_length >= $length ) )
1089 $unicode .= chr($value);
1092 if ( count( $values ) == 0 ) {
1093 if ( $value < 224 ) {
1095 } elseif ( $value < 240 ) {
1104 if ( $length && ( $unicode_length + ($num_octets * 3) ) > $length )
1106 if ( count( $values ) == $num_octets ) {
1107 for ( $j = 0; $j < $num_octets; $j++ ) {
1108 $unicode .= '%' . dechex( $values[ $j ] );
1111 $unicode_length += $num_octets * 3;
1123 * Converts all accent characters to ASCII characters.
1125 * If there are no accent characters, then the string given is just returned.
1127 * **Accent characters converted:**
1131 * | Code | Glyph | Replacement | Description |
1132 * | -------- | ----- | ----------- | ------------------- |
1133 * | U+00A3 | £ | (empty) | British Pound sign |
1134 * | U+20AC | € | E | Euro sign |
1136 * Decompositions for Latin-1 Supplement:
1138 * | Code | Glyph | Replacement | Description |
1139 * | ------- | ----- | ----------- | -------------------------------------- |
1140 * | U+00AA | ª | a | Feminine ordinal indicator |
1141 * | U+00BA | º | o | Masculine ordinal indicator |
1142 * | U+00C0 | À | A | Latin capital letter A with grave |
1143 * | U+00C1 | Á | A | Latin capital letter A with acute |
1144 * | U+00C2 | Â | A | Latin capital letter A with circumflex |
1145 * | U+00C3 | Ã | A | Latin capital letter A with tilde |
1146 * | U+00C4 | Ä | A | Latin capital letter A with diaeresis |
1147 * | U+00C5 | Å | A | Latin capital letter A with ring above |
1148 * | U+00C6 | Æ | AE | Latin capital letter AE |
1149 * | U+00C7 | Ç | C | Latin capital letter C with cedilla |
1150 * | U+00C8 | È | E | Latin capital letter E with grave |
1151 * | U+00C9 | É | E | Latin capital letter E with acute |
1152 * | U+00CA | Ê | E | Latin capital letter E with circumflex |
1153 * | U+00CB | Ë | E | Latin capital letter E with diaeresis |
1154 * | U+00CC | Ì | I | Latin capital letter I with grave |
1155 * | U+00CD | Í | I | Latin capital letter I with acute |
1156 * | U+00CE | Î | I | Latin capital letter I with circumflex |
1157 * | U+00CF | Ï | I | Latin capital letter I with diaeresis |
1158 * | U+00D0 | Ð | D | Latin capital letter Eth |
1159 * | U+00D1 | Ñ | N | Latin capital letter N with tilde |
1160 * | U+00D2 | Ò | O | Latin capital letter O with grave |
1161 * | U+00D3 | Ó | O | Latin capital letter O with acute |
1162 * | U+00D4 | Ô | O | Latin capital letter O with circumflex |
1163 * | U+00D5 | Õ | O | Latin capital letter O with tilde |
1164 * | U+00D6 | Ö | O | Latin capital letter O with diaeresis |
1165 * | U+00D8 | Ø | O | Latin capital letter O with stroke |
1166 * | U+00D9 | Ù | U | Latin capital letter U with grave |
1167 * | U+00DA | Ú | U | Latin capital letter U with acute |
1168 * | U+00DB | Û | U | Latin capital letter U with circumflex |
1169 * | U+00DC | Ü | U | Latin capital letter U with diaeresis |
1170 * | U+00DD | Ý | Y | Latin capital letter Y with acute |
1171 * | U+00DE | Þ | TH | Latin capital letter Thorn |
1172 * | U+00DF | ß | s | Latin small letter sharp s |
1173 * | U+00E0 | à | a | Latin small letter a with grave |
1174 * | U+00E1 | á | a | Latin small letter a with acute |
1175 * | U+00E2 | â | a | Latin small letter a with circumflex |
1176 * | U+00E3 | ã | a | Latin small letter a with tilde |
1177 * | U+00E4 | ä | a | Latin small letter a with diaeresis |
1178 * | U+00E5 | å | a | Latin small letter a with ring above |
1179 * | U+00E6 | æ | ae | Latin small letter ae |
1180 * | U+00E7 | ç | c | Latin small letter c with cedilla |
1181 * | U+00E8 | è | e | Latin small letter e with grave |
1182 * | U+00E9 | é | e | Latin small letter e with acute |
1183 * | U+00EA | ê | e | Latin small letter e with circumflex |
1184 * | U+00EB | ë | e | Latin small letter e with diaeresis |
1185 * | U+00EC | ì | i | Latin small letter i with grave |
1186 * | U+00ED | í | i | Latin small letter i with acute |
1187 * | U+00EE | î | i | Latin small letter i with circumflex |
1188 * | U+00EF | ï | i | Latin small letter i with diaeresis |
1189 * | U+00F0 | ð | d | Latin small letter Eth |
1190 * | U+00F1 | ñ | n | Latin small letter n with tilde |
1191 * | U+00F2 | ò | o | Latin small letter o with grave |
1192 * | U+00F3 | ó | o | Latin small letter o with acute |
1193 * | U+00F4 | ô | o | Latin small letter o with circumflex |
1194 * | U+00F5 | õ | o | Latin small letter o with tilde |
1195 * | U+00F6 | ö | o | Latin small letter o with diaeresis |
1196 * | U+00F8 | ø | o | Latin small letter o with stroke |
1197 * | U+00F9 | ù | u | Latin small letter u with grave |
1198 * | U+00FA | ú | u | Latin small letter u with acute |
1199 * | U+00FB | û | u | Latin small letter u with circumflex |
1200 * | U+00FC | ü | u | Latin small letter u with diaeresis |
1201 * | U+00FD | ý | y | Latin small letter y with acute |
1202 * | U+00FE | þ | th | Latin small letter Thorn |
1203 * | U+00FF | ÿ | y | Latin small letter y with diaeresis |
1205 * Decompositions for Latin Extended-A:
1207 * | Code | Glyph | Replacement | Description |
1208 * | ------- | ----- | ----------- | ------------------------------------------------- |
1209 * | U+0100 | Ā | A | Latin capital letter A with macron |
1210 * | U+0101 | ā | a | Latin small letter a with macron |
1211 * | U+0102 | Ă | A | Latin capital letter A with breve |
1212 * | U+0103 | ă | a | Latin small letter a with breve |
1213 * | U+0104 | Ą | A | Latin capital letter A with ogonek |
1214 * | U+0105 | ą | a | Latin small letter a with ogonek |
1215 * | U+01006 | Ć | C | Latin capital letter C with acute |
1216 * | U+0107 | ć | c | Latin small letter c with acute |
1217 * | U+0108 | Ĉ | C | Latin capital letter C with circumflex |
1218 * | U+0109 | ĉ | c | Latin small letter c with circumflex |
1219 * | U+010A | Ċ | C | Latin capital letter C with dot above |
1220 * | U+010B | ċ | c | Latin small letter c with dot above |
1221 * | U+010C | Č | C | Latin capital letter C with caron |
1222 * | U+010D | č | c | Latin small letter c with caron |
1223 * | U+010E | Ď | D | Latin capital letter D with caron |
1224 * | U+010F | ď | d | Latin small letter d with caron |
1225 * | U+0110 | Đ | D | Latin capital letter D with stroke |
1226 * | U+0111 | đ | d | Latin small letter d with stroke |
1227 * | U+0112 | Ē | E | Latin capital letter E with macron |
1228 * | U+0113 | ē | e | Latin small letter e with macron |
1229 * | U+0114 | Ĕ | E | Latin capital letter E with breve |
1230 * | U+0115 | ĕ | e | Latin small letter e with breve |
1231 * | U+0116 | Ė | E | Latin capital letter E with dot above |
1232 * | U+0117 | ė | e | Latin small letter e with dot above |
1233 * | U+0118 | Ę | E | Latin capital letter E with ogonek |
1234 * | U+0119 | ę | e | Latin small letter e with ogonek |
1235 * | U+011A | Ě | E | Latin capital letter E with caron |
1236 * | U+011B | ě | e | Latin small letter e with caron |
1237 * | U+011C | Ĝ | G | Latin capital letter G with circumflex |
1238 * | U+011D | ĝ | g | Latin small letter g with circumflex |
1239 * | U+011E | Ğ | G | Latin capital letter G with breve |
1240 * | U+011F | ğ | g | Latin small letter g with breve |
1241 * | U+0120 | Ġ | G | Latin capital letter G with dot above |
1242 * | U+0121 | ġ | g | Latin small letter g with dot above |
1243 * | U+0122 | Ģ | G | Latin capital letter G with cedilla |
1244 * | U+0123 | ģ | g | Latin small letter g with cedilla |
1245 * | U+0124 | Ĥ | H | Latin capital letter H with circumflex |
1246 * | U+0125 | ĥ | h | Latin small letter h with circumflex |
1247 * | U+0126 | Ħ | H | Latin capital letter H with stroke |
1248 * | U+0127 | ħ | h | Latin small letter h with stroke |
1249 * | U+0128 | Ĩ | I | Latin capital letter I with tilde |
1250 * | U+0129 | ĩ | i | Latin small letter i with tilde |
1251 * | U+012A | Ī | I | Latin capital letter I with macron |
1252 * | U+012B | ī | i | Latin small letter i with macron |
1253 * | U+012C | Ĭ | I | Latin capital letter I with breve |
1254 * | U+012D | ĭ | i | Latin small letter i with breve |
1255 * | U+012E | Į | I | Latin capital letter I with ogonek |
1256 * | U+012F | į | i | Latin small letter i with ogonek |
1257 * | U+0130 | İ | I | Latin capital letter I with dot above |
1258 * | U+0131 | ı | i | Latin small letter dotless i |
1259 * | U+0132 | IJ | IJ | Latin capital ligature IJ |
1260 * | U+0133 | ij | ij | Latin small ligature ij |
1261 * | U+0134 | Ĵ | J | Latin capital letter J with circumflex |
1262 * | U+0135 | ĵ | j | Latin small letter j with circumflex |
1263 * | U+0136 | Ķ | K | Latin capital letter K with cedilla |
1264 * | U+0137 | ķ | k | Latin small letter k with cedilla |
1265 * | U+0138 | ĸ | k | Latin small letter Kra |
1266 * | U+0139 | Ĺ | L | Latin capital letter L with acute |
1267 * | U+013A | ĺ | l | Latin small letter l with acute |
1268 * | U+013B | Ļ | L | Latin capital letter L with cedilla |
1269 * | U+013C | ļ | l | Latin small letter l with cedilla |
1270 * | U+013D | Ľ | L | Latin capital letter L with caron |
1271 * | U+013E | ľ | l | Latin small letter l with caron |
1272 * | U+013F | Ŀ | L | Latin capital letter L with middle dot |
1273 * | U+0140 | ŀ | l | Latin small letter l with middle dot |
1274 * | U+0141 | Ł | L | Latin capital letter L with stroke |
1275 * | U+0142 | ł | l | Latin small letter l with stroke |
1276 * | U+0143 | Ń | N | Latin capital letter N with acute |
1277 * | U+0144 | ń | n | Latin small letter N with acute |
1278 * | U+0145 | Ņ | N | Latin capital letter N with cedilla |
1279 * | U+0146 | ņ | n | Latin small letter n with cedilla |
1280 * | U+0147 | Ň | N | Latin capital letter N with caron |
1281 * | U+0148 | ň | n | Latin small letter n with caron |
1282 * | U+0149 | ʼn | N | Latin small letter n preceded by apostrophe |
1283 * | U+014A | Ŋ | n | Latin capital letter Eng |
1284 * | U+014B | ŋ | N | Latin small letter Eng |
1285 * | U+014C | Ō | O | Latin capital letter O with macron |
1286 * | U+014D | ō | o | Latin small letter o with macron |
1287 * | U+014E | Ŏ | O | Latin capital letter O with breve |
1288 * | U+014F | ŏ | o | Latin small letter o with breve |
1289 * | U+0150 | Ő | O | Latin capital letter O with double acute |
1290 * | U+0151 | ő | o | Latin small letter o with double acute |
1291 * | U+0152 | Œ | OE | Latin capital ligature OE |
1292 * | U+0153 | œ | oe | Latin small ligature oe |
1293 * | U+0154 | Ŕ | R | Latin capital letter R with acute |
1294 * | U+0155 | ŕ | r | Latin small letter r with acute |
1295 * | U+0156 | Ŗ | R | Latin capital letter R with cedilla |
1296 * | U+0157 | ŗ | r | Latin small letter r with cedilla |
1297 * | U+0158 | Ř | R | Latin capital letter R with caron |
1298 * | U+0159 | ř | r | Latin small letter r with caron |
1299 * | U+015A | Ś | S | Latin capital letter S with acute |
1300 * | U+015B | ś | s | Latin small letter s with acute |
1301 * | U+015C | Ŝ | S | Latin capital letter S with circumflex |
1302 * | U+015D | ŝ | s | Latin small letter s with circumflex |
1303 * | U+015E | Ş | S | Latin capital letter S with cedilla |
1304 * | U+015F | ş | s | Latin small letter s with cedilla |
1305 * | U+0160 | Š | S | Latin capital letter S with caron |
1306 * | U+0161 | š | s | Latin small letter s with caron |
1307 * | U+0162 | Ţ | T | Latin capital letter T with cedilla |
1308 * | U+0163 | ţ | t | Latin small letter t with cedilla |
1309 * | U+0164 | Ť | T | Latin capital letter T with caron |
1310 * | U+0165 | ť | t | Latin small letter t with caron |
1311 * | U+0166 | Ŧ | T | Latin capital letter T with stroke |
1312 * | U+0167 | ŧ | t | Latin small letter t with stroke |
1313 * | U+0168 | Ũ | U | Latin capital letter U with tilde |
1314 * | U+0169 | ũ | u | Latin small letter u with tilde |
1315 * | U+016A | Ū | U | Latin capital letter U with macron |
1316 * | U+016B | ū | u | Latin small letter u with macron |
1317 * | U+016C | Ŭ | U | Latin capital letter U with breve |
1318 * | U+016D | ŭ | u | Latin small letter u with breve |
1319 * | U+016E | Ů | U | Latin capital letter U with ring above |
1320 * | U+016F | ů | u | Latin small letter u with ring above |
1321 * | U+0170 | Ű | U | Latin capital letter U with double acute |
1322 * | U+0171 | ű | u | Latin small letter u with double acute |
1323 * | U+0172 | Ų | U | Latin capital letter U with ogonek |
1324 * | U+0173 | ų | u | Latin small letter u with ogonek |
1325 * | U+0174 | Ŵ | W | Latin capital letter W with circumflex |
1326 * | U+0175 | ŵ | w | Latin small letter w with circumflex |
1327 * | U+0176 | Ŷ | Y | Latin capital letter Y with circumflex |
1328 * | U+0177 | ŷ | y | Latin small letter y with circumflex |
1329 * | U+0178 | Ÿ | Y | Latin capital letter Y with diaeresis |
1330 * | U+0179 | Ź | Z | Latin capital letter Z with acute |
1331 * | U+017A | ź | z | Latin small letter z with acute |
1332 * | U+017B | Ż | Z | Latin capital letter Z with dot above |
1333 * | U+017C | ż | z | Latin small letter z with dot above |
1334 * | U+017D | Ž | Z | Latin capital letter Z with caron |
1335 * | U+017E | ž | z | Latin small letter z with caron |
1336 * | U+017F | ſ | s | Latin small letter long s |
1337 * | U+01A0 | Ơ | O | Latin capital letter O with horn |
1338 * | U+01A1 | ơ | o | Latin small letter o with horn |
1339 * | U+01AF | Ư | U | Latin capital letter U with horn |
1340 * | U+01B0 | ư | u | Latin small letter u with horn |
1341 * | U+01CD | Ǎ | A | Latin capital letter A with caron |
1342 * | U+01CE | ǎ | a | Latin small letter a with caron |
1343 * | U+01CF | Ǐ | I | Latin capital letter I with caron |
1344 * | U+01D0 | ǐ | i | Latin small letter i with caron |
1345 * | U+01D1 | Ǒ | O | Latin capital letter O with caron |
1346 * | U+01D2 | ǒ | o | Latin small letter o with caron |
1347 * | U+01D3 | Ǔ | U | Latin capital letter U with caron |
1348 * | U+01D4 | ǔ | u | Latin small letter u with caron |
1349 * | U+01D5 | Ǖ | U | Latin capital letter U with diaeresis and macron |
1350 * | U+01D6 | ǖ | u | Latin small letter u with diaeresis and macron |
1351 * | U+01D7 | Ǘ | U | Latin capital letter U with diaeresis and acute |
1352 * | U+01D8 | ǘ | u | Latin small letter u with diaeresis and acute |
1353 * | U+01D9 | Ǚ | U | Latin capital letter U with diaeresis and caron |
1354 * | U+01DA | ǚ | u | Latin small letter u with diaeresis and caron |
1355 * | U+01DB | Ǜ | U | Latin capital letter U with diaeresis and grave |
1356 * | U+01DC | ǜ | u | Latin small letter u with diaeresis and grave |
1358 * Decompositions for Latin Extended-B:
1360 * | Code | Glyph | Replacement | Description |
1361 * | -------- | ----- | ----------- | ----------------------------------------- |
1362 * | U+0218 | Ș | S | Latin capital letter S with comma below |
1363 * | U+0219 | ș | s | Latin small letter s with comma below |
1364 * | U+021A | Ț | T | Latin capital letter T with comma below |
1365 * | U+021B | ț | t | Latin small letter t with comma below |
1367 * Vowels with diacritic (Chinese, Hanyu Pinyin):
1369 * | Code | Glyph | Replacement | Description |
1370 * | -------- | ----- | ----------- | ----------------------------------------------------- |
1371 * | U+0251 | ɑ | a | Latin small letter alpha |
1372 * | U+1EA0 | Ạ | A | Latin capital letter A with dot below |
1373 * | U+1EA1 | ạ | a | Latin small letter a with dot below |
1374 * | U+1EA2 | Ả | A | Latin capital letter A with hook above |
1375 * | U+1EA3 | ả | a | Latin small letter a with hook above |
1376 * | U+1EA4 | Ấ | A | Latin capital letter A with circumflex and acute |
1377 * | U+1EA5 | ấ | a | Latin small letter a with circumflex and acute |
1378 * | U+1EA6 | Ầ | A | Latin capital letter A with circumflex and grave |
1379 * | U+1EA7 | ầ | a | Latin small letter a with circumflex and grave |
1380 * | U+1EA8 | Ẩ | A | Latin capital letter A with circumflex and hook above |
1381 * | U+1EA9 | ẩ | a | Latin small letter a with circumflex and hook above |
1382 * | U+1EAA | Ẫ | A | Latin capital letter A with circumflex and tilde |
1383 * | U+1EAB | ẫ | a | Latin small letter a with circumflex and tilde |
1384 * | U+1EA6 | Ậ | A | Latin capital letter A with circumflex and dot below |
1385 * | U+1EAD | ậ | a | Latin small letter a with circumflex and dot below |
1386 * | U+1EAE | Ắ | A | Latin capital letter A with breve and acute |
1387 * | U+1EAF | ắ | a | Latin small letter a with breve and acute |
1388 * | U+1EB0 | Ằ | A | Latin capital letter A with breve and grave |
1389 * | U+1EB1 | ằ | a | Latin small letter a with breve and grave |
1390 * | U+1EB2 | Ẳ | A | Latin capital letter A with breve and hook above |
1391 * | U+1EB3 | ẳ | a | Latin small letter a with breve and hook above |
1392 * | U+1EB4 | Ẵ | A | Latin capital letter A with breve and tilde |
1393 * | U+1EB5 | ẵ | a | Latin small letter a with breve and tilde |
1394 * | U+1EB6 | Ặ | A | Latin capital letter A with breve and dot below |
1395 * | U+1EB7 | ặ | a | Latin small letter a with breve and dot below |
1396 * | U+1EB8 | Ẹ | E | Latin capital letter E with dot below |
1397 * | U+1EB9 | ẹ | e | Latin small letter e with dot below |
1398 * | U+1EBA | Ẻ | E | Latin capital letter E with hook above |
1399 * | U+1EBB | ẻ | e | Latin small letter e with hook above |
1400 * | U+1EBC | Ẽ | E | Latin capital letter E with tilde |
1401 * | U+1EBD | ẽ | e | Latin small letter e with tilde |
1402 * | U+1EBE | Ế | E | Latin capital letter E with circumflex and acute |
1403 * | U+1EBF | ế | e | Latin small letter e with circumflex and acute |
1404 * | U+1EC0 | Ề | E | Latin capital letter E with circumflex and grave |
1405 * | U+1EC1 | ề | e | Latin small letter e with circumflex and grave |
1406 * | U+1EC2 | Ể | E | Latin capital letter E with circumflex and hook above |
1407 * | U+1EC3 | ể | e | Latin small letter e with circumflex and hook above |
1408 * | U+1EC4 | Ễ | E | Latin capital letter E with circumflex and tilde |
1409 * | U+1EC5 | ễ | e | Latin small letter e with circumflex and tilde |
1410 * | U+1EC6 | Ệ | E | Latin capital letter E with circumflex and dot below |
1411 * | U+1EC7 | ệ | e | Latin small letter e with circumflex and dot below |
1412 * | U+1EC8 | Ỉ | I | Latin capital letter I with hook above |
1413 * | U+1EC9 | ỉ | i | Latin small letter i with hook above |
1414 * | U+1ECA | Ị | I | Latin capital letter I with dot below |
1415 * | U+1ECB | ị | i | Latin small letter i with dot below |
1416 * | U+1ECC | Ọ | O | Latin capital letter O with dot below |
1417 * | U+1ECD | ọ | o | Latin small letter o with dot below |
1418 * | U+1ECE | Ỏ | O | Latin capital letter O with hook above |
1419 * | U+1ECF | ỏ | o | Latin small letter o with hook above |
1420 * | U+1ED0 | Ố | O | Latin capital letter O with circumflex and acute |
1421 * | U+1ED1 | ố | o | Latin small letter o with circumflex and acute |
1422 * | U+1ED2 | Ồ | O | Latin capital letter O with circumflex and grave |
1423 * | U+1ED3 | ồ | o | Latin small letter o with circumflex and grave |
1424 * | U+1ED4 | Ổ | O | Latin capital letter O with circumflex and hook above |
1425 * | U+1ED5 | ổ | o | Latin small letter o with circumflex and hook above |
1426 * | U+1ED6 | Ỗ | O | Latin capital letter O with circumflex and tilde |
1427 * | U+1ED7 | ỗ | o | Latin small letter o with circumflex and tilde |
1428 * | U+1ED8 | Ộ | O | Latin capital letter O with circumflex and dot below |
1429 * | U+1ED9 | ộ | o | Latin small letter o with circumflex and dot below |
1430 * | U+1EDA | Ớ | O | Latin capital letter O with horn and acute |
1431 * | U+1EDB | ớ | o | Latin small letter o with horn and acute |
1432 * | U+1EDC | Ờ | O | Latin capital letter O with horn and grave |
1433 * | U+1EDD | ờ | o | Latin small letter o with horn and grave |
1434 * | U+1EDE | Ở | O | Latin capital letter O with horn and hook above |
1435 * | U+1EDF | ở | o | Latin small letter o with horn and hook above |
1436 * | U+1EE0 | Ỡ | O | Latin capital letter O with horn and tilde |
1437 * | U+1EE1 | ỡ | o | Latin small letter o with horn and tilde |
1438 * | U+1EE2 | Ợ | O | Latin capital letter O with horn and dot below |
1439 * | U+1EE3 | ợ | o | Latin small letter o with horn and dot below |
1440 * | U+1EE4 | Ụ | U | Latin capital letter U with dot below |
1441 * | U+1EE5 | ụ | u | Latin small letter u with dot below |
1442 * | U+1EE6 | Ủ | U | Latin capital letter U with hook above |
1443 * | U+1EE7 | ủ | u | Latin small letter u with hook above |
1444 * | U+1EE8 | Ứ | U | Latin capital letter U with horn and acute |
1445 * | U+1EE9 | ứ | u | Latin small letter u with horn and acute |
1446 * | U+1EEA | Ừ | U | Latin capital letter U with horn and grave |
1447 * | U+1EEB | ừ | u | Latin small letter u with horn and grave |
1448 * | U+1EEC | Ử | U | Latin capital letter U with horn and hook above |
1449 * | U+1EED | ử | u | Latin small letter u with horn and hook above |
1450 * | U+1EEE | Ữ | U | Latin capital letter U with horn and tilde |
1451 * | U+1EEF | ữ | u | Latin small letter u with horn and tilde |
1452 * | U+1EF0 | Ự | U | Latin capital letter U with horn and dot below |
1453 * | U+1EF1 | ự | u | Latin small letter u with horn and dot below |
1454 * | U+1EF2 | Ỳ | Y | Latin capital letter Y with grave |
1455 * | U+1EF3 | ỳ | y | Latin small letter y with grave |
1456 * | U+1EF4 | Ỵ | Y | Latin capital letter Y with dot below |
1457 * | U+1EF5 | ỵ | y | Latin small letter y with dot below |
1458 * | U+1EF6 | Ỷ | Y | Latin capital letter Y with hook above |
1459 * | U+1EF7 | ỷ | y | Latin small letter y with hook above |
1460 * | U+1EF8 | Ỹ | Y | Latin capital letter Y with tilde |
1461 * | U+1EF9 | ỹ | y | Latin small letter y with tilde |
1463 * German (`de_DE`), German formal (`de_DE_formal`), German (Switzerland) formal (`de_CH`),
1464 * and German (Switzerland) informal (`de_CH_informal`) locales:
1466 * | Code | Glyph | Replacement | Description |
1467 * | -------- | ----- | ----------- | --------------------------------------- |
1468 * | U+00C4 | Ä | Ae | Latin capital letter A with diaeresis |
1469 * | U+00E4 | ä | ae | Latin small letter a with diaeresis |
1470 * | U+00D6 | Ö | Oe | Latin capital letter O with diaeresis |
1471 * | U+00F6 | ö | oe | Latin small letter o with diaeresis |
1472 * | U+00DC | Ü | Ue | Latin capital letter U with diaeresis |
1473 * | U+00FC | ü | ue | Latin small letter u with diaeresis |
1474 * | U+00DF | ß | ss | Latin small letter sharp s |
1476 * Danish (`da_DK`) locale:
1478 * | Code | Glyph | Replacement | Description |
1479 * | -------- | ----- | ----------- | --------------------------------------- |
1480 * | U+00C6 | Æ | Ae | Latin capital letter AE |
1481 * | U+00E6 | æ | ae | Latin small letter ae |
1482 * | U+00D8 | Ø | Oe | Latin capital letter O with stroke |
1483 * | U+00F8 | ø | oe | Latin small letter o with stroke |
1484 * | U+00C5 | Å | Aa | Latin capital letter A with ring above |
1485 * | U+00E5 | å | aa | Latin small letter a with ring above |
1487 * Catalan (`ca`) locale:
1489 * | Code | Glyph | Replacement | Description |
1490 * | -------- | ----- | ----------- | --------------------------------------- |
1491 * | U+00B7 | l·l | ll | Flown dot (between two Ls) |
1494 * @since 4.6.0 Added locale support for `de_CH`, `de_CH_informal`, and `ca`.
1496 * @param string $string Text that might have accent characters
1497 * @return string Filtered string with replaced "nice" characters.
1499 function remove_accents( $string ) {
1500 if ( !preg_match('/[\x80-\xff]/', $string) )
1503 if (seems_utf8($string)) {
1505 // Decompositions for Latin-1 Supplement
1506 chr(194).chr(170) => 'a', chr(194).chr(186) => 'o',
1507 chr(195).chr(128) => 'A', chr(195).chr(129) => 'A',
1508 chr(195).chr(130) => 'A', chr(195).chr(131) => 'A',
1509 chr(195).chr(132) => 'A', chr(195).chr(133) => 'A',
1510 chr(195).chr(134) => 'AE',chr(195).chr(135) => 'C',
1511 chr(195).chr(136) => 'E', chr(195).chr(137) => 'E',
1512 chr(195).chr(138) => 'E', chr(195).chr(139) => 'E',
1513 chr(195).chr(140) => 'I', chr(195).chr(141) => 'I',
1514 chr(195).chr(142) => 'I', chr(195).chr(143) => 'I',
1515 chr(195).chr(144) => 'D', chr(195).chr(145) => 'N',
1516 chr(195).chr(146) => 'O', chr(195).chr(147) => 'O',
1517 chr(195).chr(148) => 'O', chr(195).chr(149) => 'O',
1518 chr(195).chr(150) => 'O', chr(195).chr(153) => 'U',
1519 chr(195).chr(154) => 'U', chr(195).chr(155) => 'U',
1520 chr(195).chr(156) => 'U', chr(195).chr(157) => 'Y',
1521 chr(195).chr(158) => 'TH',chr(195).chr(159) => 's',
1522 chr(195).chr(160) => 'a', chr(195).chr(161) => 'a',
1523 chr(195).chr(162) => 'a', chr(195).chr(163) => 'a',
1524 chr(195).chr(164) => 'a', chr(195).chr(165) => 'a',
1525 chr(195).chr(166) => 'ae',chr(195).chr(167) => 'c',
1526 chr(195).chr(168) => 'e', chr(195).chr(169) => 'e',
1527 chr(195).chr(170) => 'e', chr(195).chr(171) => 'e',
1528 chr(195).chr(172) => 'i', chr(195).chr(173) => 'i',
1529 chr(195).chr(174) => 'i', chr(195).chr(175) => 'i',
1530 chr(195).chr(176) => 'd', chr(195).chr(177) => 'n',
1531 chr(195).chr(178) => 'o', chr(195).chr(179) => 'o',
1532 chr(195).chr(180) => 'o', chr(195).chr(181) => 'o',
1533 chr(195).chr(182) => 'o', chr(195).chr(184) => 'o',
1534 chr(195).chr(185) => 'u', chr(195).chr(186) => 'u',
1535 chr(195).chr(187) => 'u', chr(195).chr(188) => 'u',
1536 chr(195).chr(189) => 'y', chr(195).chr(190) => 'th',
1537 chr(195).chr(191) => 'y', chr(195).chr(152) => 'O',
1538 // Decompositions for Latin Extended-A
1539 chr(196).chr(128) => 'A', chr(196).chr(129) => 'a',
1540 chr(196).chr(130) => 'A', chr(196).chr(131) => 'a',
1541 chr(196).chr(132) => 'A', chr(196).chr(133) => 'a',
1542 chr(196).chr(134) => 'C', chr(196).chr(135) => 'c',
1543 chr(196).chr(136) => 'C', chr(196).chr(137) => 'c',
1544 chr(196).chr(138) => 'C', chr(196).chr(139) => 'c',
1545 chr(196).chr(140) => 'C', chr(196).chr(141) => 'c',
1546 chr(196).chr(142) => 'D', chr(196).chr(143) => 'd',
1547 chr(196).chr(144) => 'D', chr(196).chr(145) => 'd',
1548 chr(196).chr(146) => 'E', chr(196).chr(147) => 'e',
1549 chr(196).chr(148) => 'E', chr(196).chr(149) => 'e',
1550 chr(196).chr(150) => 'E', chr(196).chr(151) => 'e',
1551 chr(196).chr(152) => 'E', chr(196).chr(153) => 'e',
1552 chr(196).chr(154) => 'E', chr(196).chr(155) => 'e',
1553 chr(196).chr(156) => 'G', chr(196).chr(157) => 'g',
1554 chr(196).chr(158) => 'G', chr(196).chr(159) => 'g',
1555 chr(196).chr(160) => 'G', chr(196).chr(161) => 'g',
1556 chr(196).chr(162) => 'G', chr(196).chr(163) => 'g',
1557 chr(196).chr(164) => 'H', chr(196).chr(165) => 'h',
1558 chr(196).chr(166) => 'H', chr(196).chr(167) => 'h',
1559 chr(196).chr(168) => 'I', chr(196).chr(169) => 'i',
1560 chr(196).chr(170) => 'I', chr(196).chr(171) => 'i',
1561 chr(196).chr(172) => 'I', chr(196).chr(173) => 'i',
1562 chr(196).chr(174) => 'I', chr(196).chr(175) => 'i',
1563 chr(196).chr(176) => 'I', chr(196).chr(177) => 'i',
1564 chr(196).chr(178) => 'IJ',chr(196).chr(179) => 'ij',
1565 chr(196).chr(180) => 'J', chr(196).chr(181) => 'j',
1566 chr(196).chr(182) => 'K', chr(196).chr(183) => 'k',
1567 chr(196).chr(184) => 'k', chr(196).chr(185) => 'L',
1568 chr(196).chr(186) => 'l', chr(196).chr(187) => 'L',
1569 chr(196).chr(188) => 'l', chr(196).chr(189) => 'L',
1570 chr(196).chr(190) => 'l', chr(196).chr(191) => 'L',
1571 chr(197).chr(128) => 'l', chr(197).chr(129) => 'L',
1572 chr(197).chr(130) => 'l', chr(197).chr(131) => 'N',
1573 chr(197).chr(132) => 'n', chr(197).chr(133) => 'N',
1574 chr(197).chr(134) => 'n', chr(197).chr(135) => 'N',
1575 chr(197).chr(136) => 'n', chr(197).chr(137) => 'N',
1576 chr(197).chr(138) => 'n', chr(197).chr(139) => 'N',
1577 chr(197).chr(140) => 'O', chr(197).chr(141) => 'o',
1578 chr(197).chr(142) => 'O', chr(197).chr(143) => 'o',
1579 chr(197).chr(144) => 'O', chr(197).chr(145) => 'o',
1580 chr(197).chr(146) => 'OE',chr(197).chr(147) => 'oe',
1581 chr(197).chr(148) => 'R',chr(197).chr(149) => 'r',
1582 chr(197).chr(150) => 'R',chr(197).chr(151) => 'r',
1583 chr(197).chr(152) => 'R',chr(197).chr(153) => 'r',
1584 chr(197).chr(154) => 'S',chr(197).chr(155) => 's',
1585 chr(197).chr(156) => 'S',chr(197).chr(157) => 's',
1586 chr(197).chr(158) => 'S',chr(197).chr(159) => 's',
1587 chr(197).chr(160) => 'S', chr(197).chr(161) => 's',
1588 chr(197).chr(162) => 'T', chr(197).chr(163) => 't',
1589 chr(197).chr(164) => 'T', chr(197).chr(165) => 't',
1590 chr(197).chr(166) => 'T', chr(197).chr(167) => 't',
1591 chr(197).chr(168) => 'U', chr(197).chr(169) => 'u',
1592 chr(197).chr(170) => 'U', chr(197).chr(171) => 'u',
1593 chr(197).chr(172) => 'U', chr(197).chr(173) => 'u',
1594 chr(197).chr(174) => 'U', chr(197).chr(175) => 'u',
1595 chr(197).chr(176) => 'U', chr(197).chr(177) => 'u',
1596 chr(197).chr(178) => 'U', chr(197).chr(179) => 'u',
1597 chr(197).chr(180) => 'W', chr(197).chr(181) => 'w',
1598 chr(197).chr(182) => 'Y', chr(197).chr(183) => 'y',
1599 chr(197).chr(184) => 'Y', chr(197).chr(185) => 'Z',
1600 chr(197).chr(186) => 'z', chr(197).chr(187) => 'Z',
1601 chr(197).chr(188) => 'z', chr(197).chr(189) => 'Z',
1602 chr(197).chr(190) => 'z', chr(197).chr(191) => 's',
1603 // Decompositions for Latin Extended-B
1604 chr(200).chr(152) => 'S', chr(200).chr(153) => 's',
1605 chr(200).chr(154) => 'T', chr(200).chr(155) => 't',
1607 chr(226).chr(130).chr(172) => 'E',
1609 chr(194).chr(163) => '',
1610 // Vowels with diacritic (Vietnamese)
1612 chr(198).chr(160) => 'O', chr(198).chr(161) => 'o',
1613 chr(198).chr(175) => 'U', chr(198).chr(176) => 'u',
1615 chr(225).chr(186).chr(166) => 'A', chr(225).chr(186).chr(167) => 'a',
1616 chr(225).chr(186).chr(176) => 'A', chr(225).chr(186).chr(177) => 'a',
1617 chr(225).chr(187).chr(128) => 'E', chr(225).chr(187).chr(129) => 'e',
1618 chr(225).chr(187).chr(146) => 'O', chr(225).chr(187).chr(147) => 'o',
1619 chr(225).chr(187).chr(156) => 'O', chr(225).chr(187).chr(157) => 'o',
1620 chr(225).chr(187).chr(170) => 'U', chr(225).chr(187).chr(171) => 'u',
1621 chr(225).chr(187).chr(178) => 'Y', chr(225).chr(187).chr(179) => 'y',
1623 chr(225).chr(186).chr(162) => 'A', chr(225).chr(186).chr(163) => 'a',
1624 chr(225).chr(186).chr(168) => 'A', chr(225).chr(186).chr(169) => 'a',
1625 chr(225).chr(186).chr(178) => 'A', chr(225).chr(186).chr(179) => 'a',
1626 chr(225).chr(186).chr(186) => 'E', chr(225).chr(186).chr(187) => 'e',
1627 chr(225).chr(187).chr(130) => 'E', chr(225).chr(187).chr(131) => 'e',
1628 chr(225).chr(187).chr(136) => 'I', chr(225).chr(187).chr(137) => 'i',
1629 chr(225).chr(187).chr(142) => 'O', chr(225).chr(187).chr(143) => 'o',
1630 chr(225).chr(187).chr(148) => 'O', chr(225).chr(187).chr(149) => 'o',
1631 chr(225).chr(187).chr(158) => 'O', chr(225).chr(187).chr(159) => 'o',
1632 chr(225).chr(187).chr(166) => 'U', chr(225).chr(187).chr(167) => 'u',
1633 chr(225).chr(187).chr(172) => 'U', chr(225).chr(187).chr(173) => 'u',
1634 chr(225).chr(187).chr(182) => 'Y', chr(225).chr(187).chr(183) => 'y',
1636 chr(225).chr(186).chr(170) => 'A', chr(225).chr(186).chr(171) => 'a',
1637 chr(225).chr(186).chr(180) => 'A', chr(225).chr(186).chr(181) => 'a',
1638 chr(225).chr(186).chr(188) => 'E', chr(225).chr(186).chr(189) => 'e',
1639 chr(225).chr(187).chr(132) => 'E', chr(225).chr(187).chr(133) => 'e',
1640 chr(225).chr(187).chr(150) => 'O', chr(225).chr(187).chr(151) => 'o',
1641 chr(225).chr(187).chr(160) => 'O', chr(225).chr(187).chr(161) => 'o',
1642 chr(225).chr(187).chr(174) => 'U', chr(225).chr(187).chr(175) => 'u',
1643 chr(225).chr(187).chr(184) => 'Y', chr(225).chr(187).chr(185) => 'y',
1645 chr(225).chr(186).chr(164) => 'A', chr(225).chr(186).chr(165) => 'a',
1646 chr(225).chr(186).chr(174) => 'A', chr(225).chr(186).chr(175) => 'a',
1647 chr(225).chr(186).chr(190) => 'E', chr(225).chr(186).chr(191) => 'e',
1648 chr(225).chr(187).chr(144) => 'O', chr(225).chr(187).chr(145) => 'o',
1649 chr(225).chr(187).chr(154) => 'O', chr(225).chr(187).chr(155) => 'o',
1650 chr(225).chr(187).chr(168) => 'U', chr(225).chr(187).chr(169) => 'u',
1652 chr(225).chr(186).chr(160) => 'A', chr(225).chr(186).chr(161) => 'a',
1653 chr(225).chr(186).chr(172) => 'A', chr(225).chr(186).chr(173) => 'a',
1654 chr(225).chr(186).chr(182) => 'A', chr(225).chr(186).chr(183) => 'a',
1655 chr(225).chr(186).chr(184) => 'E', chr(225).chr(186).chr(185) => 'e',
1656 chr(225).chr(187).chr(134) => 'E', chr(225).chr(187).chr(135) => 'e',
1657 chr(225).chr(187).chr(138) => 'I', chr(225).chr(187).chr(139) => 'i',
1658 chr(225).chr(187).chr(140) => 'O', chr(225).chr(187).chr(141) => 'o',
1659 chr(225).chr(187).chr(152) => 'O', chr(225).chr(187).chr(153) => 'o',
1660 chr(225).chr(187).chr(162) => 'O', chr(225).chr(187).chr(163) => 'o',
1661 chr(225).chr(187).chr(164) => 'U', chr(225).chr(187).chr(165) => 'u',
1662 chr(225).chr(187).chr(176) => 'U', chr(225).chr(187).chr(177) => 'u',
1663 chr(225).chr(187).chr(180) => 'Y', chr(225).chr(187).chr(181) => 'y',
1664 // Vowels with diacritic (Chinese, Hanyu Pinyin)
1665 chr(201).chr(145) => 'a',
1667 chr(199).chr(149) => 'U', chr(199).chr(150) => 'u',
1669 chr(199).chr(151) => 'U', chr(199).chr(152) => 'u',
1671 chr(199).chr(141) => 'A', chr(199).chr(142) => 'a',
1672 chr(199).chr(143) => 'I', chr(199).chr(144) => 'i',
1673 chr(199).chr(145) => 'O', chr(199).chr(146) => 'o',
1674 chr(199).chr(147) => 'U', chr(199).chr(148) => 'u',
1675 chr(199).chr(153) => 'U', chr(199).chr(154) => 'u',
1677 chr(199).chr(155) => 'U', chr(199).chr(156) => 'u',
1680 // Used for locale-specific rules
1681 $locale = get_locale();
1683 if ( 'de_DE' == $locale || 'de_DE_formal' == $locale || 'de_CH' == $locale || 'de_CH_informal' == $locale ) {
1684 $chars[ chr(195).chr(132) ] = 'Ae';
1685 $chars[ chr(195).chr(164) ] = 'ae';
1686 $chars[ chr(195).chr(150) ] = 'Oe';
1687 $chars[ chr(195).chr(182) ] = 'oe';
1688 $chars[ chr(195).chr(156) ] = 'Ue';
1689 $chars[ chr(195).chr(188) ] = 'ue';
1690 $chars[ chr(195).chr(159) ] = 'ss';
1691 } elseif ( 'da_DK' === $locale ) {
1692 $chars[ chr(195).chr(134) ] = 'Ae';
1693 $chars[ chr(195).chr(166) ] = 'ae';
1694 $chars[ chr(195).chr(152) ] = 'Oe';
1695 $chars[ chr(195).chr(184) ] = 'oe';
1696 $chars[ chr(195).chr(133) ] = 'Aa';
1697 $chars[ chr(195).chr(165) ] = 'aa';
1698 } elseif ( 'ca' === $locale ) {
1699 $chars[ chr(108).chr(194).chr(183).chr(108) ] = 'll';
1702 $string = strtr($string, $chars);
1705 // Assume ISO-8859-1 if not UTF-8
1706 $chars['in'] = chr(128).chr(131).chr(138).chr(142).chr(154).chr(158)
1707 .chr(159).chr(162).chr(165).chr(181).chr(192).chr(193).chr(194)
1708 .chr(195).chr(196).chr(197).chr(199).chr(200).chr(201).chr(202)
1709 .chr(203).chr(204).chr(205).chr(206).chr(207).chr(209).chr(210)
1710 .chr(211).chr(212).chr(213).chr(214).chr(216).chr(217).chr(218)
1711 .chr(219).chr(220).chr(221).chr(224).chr(225).chr(226).chr(227)
1712 .chr(228).chr(229).chr(231).chr(232).chr(233).chr(234).chr(235)
1713 .chr(236).chr(237).chr(238).chr(239).chr(241).chr(242).chr(243)
1714 .chr(244).chr(245).chr(246).chr(248).chr(249).chr(250).chr(251)
1715 .chr(252).chr(253).chr(255);
1717 $chars['out'] = "EfSZszYcYuAAAAAACEEEEIIIINOOOOOOUUUUYaaaaaaceeeeiiiinoooooouuuuyy";
1719 $string = strtr($string, $chars['in'], $chars['out']);
1720 $double_chars = array();
1721 $double_chars['in'] = array(chr(140), chr(156), chr(198), chr(208), chr(222), chr(223), chr(230), chr(240), chr(254));
1722 $double_chars['out'] = array('OE', 'oe', 'AE', 'DH', 'TH', 'ss', 'ae', 'dh', 'th');
1723 $string = str_replace($double_chars['in'], $double_chars['out'], $string);
1730 * Sanitizes a filename, replacing whitespace with dashes.
1732 * Removes special characters that are illegal in filenames on certain
1733 * operating systems and special characters requiring special escaping
1734 * to manipulate at the command line. Replaces spaces and consecutive
1735 * dashes with a single dash. Trims period, dash and underscore from beginning
1736 * and end of filename. It is not guaranteed that this function will return a
1737 * filename that is allowed to be uploaded.
1741 * @param string $filename The filename to be sanitized
1742 * @return string The sanitized filename
1744 function sanitize_file_name( $filename ) {
1745 $filename_raw = $filename;
1746 $special_chars = array("?", "[", "]", "/", "\\", "=", "<", ">", ":", ";", ",", "'", "\"", "&", "$", "#", "*", "(", ")", "|", "~", "`", "!", "{", "}", "%", "+", chr(0));
1748 * Filters the list of characters to remove from a filename.
1752 * @param array $special_chars Characters to remove.
1753 * @param string $filename_raw Filename as it was passed into sanitize_file_name().
1755 $special_chars = apply_filters( 'sanitize_file_name_chars', $special_chars, $filename_raw );
1756 $filename = preg_replace( "#\x{00a0}#siu", ' ', $filename );
1757 $filename = str_replace( $special_chars, '', $filename );
1758 $filename = str_replace( array( '%20', '+' ), '-', $filename );
1759 $filename = preg_replace( '/[\r\n\t -]+/', '-', $filename );
1760 $filename = trim( $filename, '.-_' );
1762 if ( false === strpos( $filename, '.' ) ) {
1763 $mime_types = wp_get_mime_types();
1764 $filetype = wp_check_filetype( 'test.' . $filename, $mime_types );
1765 if ( $filetype['ext'] === $filename ) {
1766 $filename = 'unnamed-file.' . $filetype['ext'];
1770 // Split the filename into a base and extension[s]
1771 $parts = explode('.', $filename);
1773 // Return if only one extension
1774 if ( count( $parts ) <= 2 ) {
1776 * Filters a sanitized filename string.
1780 * @param string $filename Sanitized filename.
1781 * @param string $filename_raw The filename prior to sanitization.
1783 return apply_filters( 'sanitize_file_name', $filename, $filename_raw );
1786 // Process multiple extensions
1787 $filename = array_shift($parts);
1788 $extension = array_pop($parts);
1789 $mimes = get_allowed_mime_types();
1792 * Loop over any intermediate extensions. Postfix them with a trailing underscore
1793 * if they are a 2 - 5 character long alpha string not in the extension whitelist.
1795 foreach ( (array) $parts as $part) {
1796 $filename .= '.' . $part;
1798 if ( preg_match("/^[a-zA-Z]{2,5}\d?$/", $part) ) {
1800 foreach ( $mimes as $ext_preg => $mime_match ) {
1801 $ext_preg = '!^(' . $ext_preg . ')$!i';
1802 if ( preg_match( $ext_preg, $part ) ) {
1811 $filename .= '.' . $extension;
1812 /** This filter is documented in wp-includes/formatting.php */
1813 return apply_filters('sanitize_file_name', $filename, $filename_raw);
1817 * Sanitizes a username, stripping out unsafe characters.
1819 * Removes tags, octets, entities, and if strict is enabled, will only keep
1820 * alphanumeric, _, space, ., -, @. After sanitizing, it passes the username,
1821 * raw username (the username in the parameter), and the value of $strict as
1822 * parameters for the {@see 'sanitize_user'} filter.
1826 * @param string $username The username to be sanitized.
1827 * @param bool $strict If set limits $username to specific characters. Default false.
1828 * @return string The sanitized username, after passing through filters.
1830 function sanitize_user( $username, $strict = false ) {
1831 $raw_username = $username;
1832 $username = wp_strip_all_tags( $username );
1833 $username = remove_accents( $username );
1835 $username = preg_replace( '|%([a-fA-F0-9][a-fA-F0-9])|', '', $username );
1836 $username = preg_replace( '/&.+?;/', '', $username ); // Kill entities
1838 // If strict, reduce to ASCII for max portability.
1840 $username = preg_replace( '|[^a-z0-9 _.\-@]|i', '', $username );
1842 $username = trim( $username );
1843 // Consolidate contiguous whitespace
1844 $username = preg_replace( '|\s+|', ' ', $username );
1847 * Filters a sanitized username string.
1851 * @param string $username Sanitized username.
1852 * @param string $raw_username The username prior to sanitization.
1853 * @param bool $strict Whether to limit the sanitization to specific characters. Default false.
1855 return apply_filters( 'sanitize_user', $username, $raw_username, $strict );
1859 * Sanitizes a string key.
1861 * Keys are used as internal identifiers. Lowercase alphanumeric characters, dashes and underscores are allowed.
1865 * @param string $key String key
1866 * @return string Sanitized key
1868 function sanitize_key( $key ) {
1870 $key = strtolower( $key );
1871 $key = preg_replace( '/[^a-z0-9_\-]/', '', $key );
1874 * Filters a sanitized key string.
1878 * @param string $key Sanitized key.
1879 * @param string $raw_key The key prior to sanitization.
1881 return apply_filters( 'sanitize_key', $key, $raw_key );
1885 * Sanitizes a title, or returns a fallback title.
1887 * Specifically, HTML and PHP tags are stripped. Further actions can be added
1888 * via the plugin API. If $title is empty and $fallback_title is set, the latter
1893 * @param string $title The string to be sanitized.
1894 * @param string $fallback_title Optional. A title to use if $title is empty.
1895 * @param string $context Optional. The operation for which the string is sanitized
1896 * @return string The sanitized string.
1898 function sanitize_title( $title, $fallback_title = '', $context = 'save' ) {
1899 $raw_title = $title;
1901 if ( 'save' == $context )
1902 $title = remove_accents($title);
1905 * Filters a sanitized title string.
1909 * @param string $title Sanitized title.
1910 * @param string $raw_title The title prior to sanitization.
1911 * @param string $context The context for which the title is being sanitized.
1913 $title = apply_filters( 'sanitize_title', $title, $raw_title, $context );
1915 if ( '' === $title || false === $title )
1916 $title = $fallback_title;
1922 * Sanitizes a title with the 'query' context.
1924 * Used for querying the database for a value from URL.
1928 * @param string $title The string to be sanitized.
1929 * @return string The sanitized string.
1931 function sanitize_title_for_query( $title ) {
1932 return sanitize_title( $title, '', 'query' );
1936 * Sanitizes a title, replacing whitespace and a few other characters with dashes.
1938 * Limits the output to alphanumeric characters, underscore (_) and dash (-).
1939 * Whitespace becomes a dash.
1943 * @param string $title The title to be sanitized.
1944 * @param string $raw_title Optional. Not used.
1945 * @param string $context Optional. The operation for which the string is sanitized.
1946 * @return string The sanitized title.
1948 function sanitize_title_with_dashes( $title, $raw_title = '', $context = 'display' ) {
1949 $title = strip_tags($title);
1950 // Preserve escaped octets.
1951 $title = preg_replace('|%([a-fA-F0-9][a-fA-F0-9])|', '---$1---', $title);
1952 // Remove percent signs that are not part of an octet.
1953 $title = str_replace('%', '', $title);
1955 $title = preg_replace('|---([a-fA-F0-9][a-fA-F0-9])---|', '%$1', $title);
1957 if (seems_utf8($title)) {
1958 if (function_exists('mb_strtolower')) {
1959 $title = mb_strtolower($title, 'UTF-8');
1961 $title = utf8_uri_encode($title, 200);
1964 $title = strtolower($title);
1966 if ( 'save' == $context ) {
1967 // Convert nbsp, ndash and mdash to hyphens
1968 $title = str_replace( array( '%c2%a0', '%e2%80%93', '%e2%80%94' ), '-', $title );
1969 // Convert nbsp, ndash and mdash HTML entities to hyphens
1970 $title = str_replace( array( ' ', ' ', '–', '–', '—', '—' ), '-', $title );
1972 // Strip these characters entirely
1973 $title = str_replace( array(
1977 '%c2%ab', '%c2%bb', '%e2%80%b9', '%e2%80%ba',
1979 '%e2%80%98', '%e2%80%99', '%e2%80%9c', '%e2%80%9d',
1980 '%e2%80%9a', '%e2%80%9b', '%e2%80%9e', '%e2%80%9f',
1981 // copy, reg, deg, hellip and trade
1982 '%c2%a9', '%c2%ae', '%c2%b0', '%e2%80%a6', '%e2%84%a2',
1984 '%c2%b4', '%cb%8a', '%cc%81', '%cd%81',
1985 // grave accent, macron, caron
1986 '%cc%80', '%cc%84', '%cc%8c',
1989 // Convert times to x
1990 $title = str_replace( '%c3%97', 'x', $title );
1993 $title = preg_replace('/&.+?;/', '', $title); // kill entities
1994 $title = str_replace('.', '-', $title);
1996 $title = preg_replace('/[^%a-z0-9 _-]/', '', $title);
1997 $title = preg_replace('/\s+/', '-', $title);
1998 $title = preg_replace('|-+|', '-', $title);
1999 $title = trim($title, '-');
2005 * Ensures a string is a valid SQL 'order by' clause.
2007 * Accepts one or more columns, with or without a sort order (ASC / DESC).
2008 * e.g. 'column_1', 'column_1, column_2', 'column_1 ASC, column_2 DESC' etc.
2010 * Also accepts 'RAND()'.
2014 * @param string $orderby Order by clause to be validated.
2015 * @return string|false Returns $orderby if valid, false otherwise.
2017 function sanitize_sql_orderby( $orderby ) {
2018 if ( preg_match( '/^\s*(([a-z0-9_]+|`[a-z0-9_]+`)(\s+(ASC|DESC))?\s*(,\s*(?=[a-z0-9_`])|$))+$/i', $orderby ) || preg_match( '/^\s*RAND\(\s*\)\s*$/i', $orderby ) ) {
2025 * Sanitizes an HTML classname to ensure it only contains valid characters.
2027 * Strips the string down to A-Z,a-z,0-9,_,-. If this results in an empty
2028 * string then it will return the alternative value supplied.
2030 * @todo Expand to support the full range of CDATA that a class attribute can contain.
2034 * @param string $class The classname to be sanitized
2035 * @param string $fallback Optional. The value to return if the sanitization ends up as an empty string.
2036 * Defaults to an empty string.
2037 * @return string The sanitized value
2039 function sanitize_html_class( $class, $fallback = '' ) {
2040 //Strip out any % encoded octets
2041 $sanitized = preg_replace( '|%[a-fA-F0-9][a-fA-F0-9]|', '', $class );
2043 //Limit to A-Z,a-z,0-9,_,-
2044 $sanitized = preg_replace( '/[^A-Za-z0-9_-]/', '', $sanitized );
2046 if ( '' == $sanitized && $fallback ) {
2047 return sanitize_html_class( $fallback );
2050 * Filters a sanitized HTML class string.
2054 * @param string $sanitized The sanitized HTML class.
2055 * @param string $class HTML class before sanitization.
2056 * @param string $fallback The fallback string.
2058 return apply_filters( 'sanitize_html_class', $sanitized, $class, $fallback );
2062 * Converts lone & characters into `&` (a.k.a. `&`)
2066 * @param string $content String of characters to be converted.
2067 * @param string $deprecated Not used.
2068 * @return string Converted string.
2070 function convert_chars( $content, $deprecated = '' ) {
2071 if ( ! empty( $deprecated ) ) {
2072 _deprecated_argument( __FUNCTION__, '0.71' );
2075 if ( strpos( $content, '&' ) !== false ) {
2076 $content = preg_replace( '/&([^#])(?![a-z1-4]{1,8};)/i', '&$1', $content );
2083 * Converts invalid Unicode references range to valid range.
2087 * @param string $content String with entities that need converting.
2088 * @return string Converted string.
2090 function convert_invalid_entities( $content ) {
2091 $wp_htmltranswinuni = array(
2092 '€' => '€', // the Euro sign
2094 '‚' => '‚', // these are Windows CP1252 specific characters
2095 'ƒ' => 'ƒ', // they would look weird on non-Windows browsers
2096 '„' => '„',
2097 '…' => '…',
2098 '†' => '†',
2099 '‡' => '‡',
2100 'ˆ' => 'ˆ',
2101 '‰' => '‰',
2102 'Š' => 'Š',
2103 '‹' => '‹',
2104 'Œ' => 'Œ',
2106 'Ž' => 'Ž',
2109 '‘' => '‘',
2110 '’' => '’',
2111 '“' => '“',
2112 '”' => '”',
2113 '•' => '•',
2114 '–' => '–',
2115 '—' => '—',
2116 '˜' => '˜',
2117 '™' => '™',
2118 'š' => 'š',
2119 '›' => '›',
2120 'œ' => 'œ',
2122 'ž' => 'ž',
2123 'Ÿ' => 'Ÿ'
2126 if ( strpos( $content, '' ) !== false ) {
2127 $content = strtr( $content, $wp_htmltranswinuni );
2134 * Balances tags if forced to, or if the 'use_balanceTags' option is set to true.
2138 * @param string $text Text to be balanced
2139 * @param bool $force If true, forces balancing, ignoring the value of the option. Default false.
2140 * @return string Balanced text
2142 function balanceTags( $text, $force = false ) {
2143 if ( $force || get_option('use_balanceTags') == 1 ) {
2144 return force_balance_tags( $text );
2151 * Balances tags of string using a modified stack.
2155 * @author Leonard Lin <leonard@acm.org>
2157 * @copyright November 4, 2001
2159 * @todo Make better - change loop condition to $text in 1.2
2160 * @internal Modified by Scott Reilly (coffee2code) 02 Aug 2004
2161 * 1.1 Fixed handling of append/stack pop order of end text
2162 * Added Cleaning Hooks
2165 * @param string $text Text to be balanced.
2166 * @return string Balanced text.
2168 function force_balance_tags( $text ) {
2169 $tagstack = array();
2173 // Known single-entity/self-closing tags
2174 $single_tags = array( 'area', 'base', 'basefont', 'br', 'col', 'command', 'embed', 'frame', 'hr', 'img', 'input', 'isindex', 'link', 'meta', 'param', 'source' );
2175 // Tags that can be immediately nested within themselves
2176 $nestable_tags = array( 'blockquote', 'div', 'object', 'q', 'span' );
2178 // WP bug fix for comments - in case you REALLY meant to type '< !--'
2179 $text = str_replace('< !--', '< !--', $text);
2180 // WP bug fix for LOVE <3 (and other situations with '<' before a number)
2181 $text = preg_replace('#<([0-9]{1})#', '<$1', $text);
2183 while ( preg_match("/<(\/?[\w:]*)\s*([^>]*)>/", $text, $regex) ) {
2184 $newtext .= $tagqueue;
2186 $i = strpos($text, $regex[0]);
2187 $l = strlen($regex[0]);
2189 // clear the shifter
2192 if ( isset($regex[1][0]) && '/' == $regex[1][0] ) { // End Tag
2193 $tag = strtolower(substr($regex[1],1));
2194 // if too many closing tags
2195 if ( $stacksize <= 0 ) {
2197 // or close to be safe $tag = '/' . $tag;
2199 // if stacktop value = tag close value then pop
2200 elseif ( $tagstack[$stacksize - 1] == $tag ) { // found closing tag
2201 $tag = '</' . $tag . '>'; // Close Tag
2203 array_pop( $tagstack );
2205 } else { // closing tag not at top, search for it
2206 for ( $j = $stacksize-1; $j >= 0; $j-- ) {
2207 if ( $tagstack[$j] == $tag ) {
2208 // add tag to tagqueue
2209 for ( $k = $stacksize-1; $k >= $j; $k--) {
2210 $tagqueue .= '</' . array_pop( $tagstack ) . '>';
2218 } else { // Begin Tag
2219 $tag = strtolower($regex[1]);
2223 // If it's an empty tag "< >", do nothing
2227 // ElseIf it presents itself as a self-closing tag...
2228 elseif ( substr( $regex[2], -1 ) == '/' ) {
2229 // ...but it isn't a known single-entity self-closing tag, then don't let it be treated as such and
2230 // immediately close it with a closing tag (the tag will encapsulate no text as a result)
2231 if ( ! in_array( $tag, $single_tags ) )
2232 $regex[2] = trim( substr( $regex[2], 0, -1 ) ) . "></$tag";
2234 // ElseIf it's a known single-entity tag but it doesn't close itself, do so
2235 elseif ( in_array($tag, $single_tags) ) {
2238 // Else it's not a single-entity tag
2240 // If the top of the stack is the same as the tag we want to push, close previous tag
2241 if ( $stacksize > 0 && !in_array($tag, $nestable_tags) && $tagstack[$stacksize - 1] == $tag ) {
2242 $tagqueue = '</' . array_pop( $tagstack ) . '>';
2245 $stacksize = array_push( $tagstack, $tag );
2249 $attributes = $regex[2];
2250 if ( ! empty( $attributes ) && $attributes[0] != '>' )
2251 $attributes = ' ' . $attributes;
2253 $tag = '<' . $tag . $attributes . '>';
2254 //If already queuing a close tag, then put this tag on, too
2255 if ( !empty($tagqueue) ) {
2260 $newtext .= substr($text, 0, $i) . $tag;
2261 $text = substr($text, $i + $l);
2265 $newtext .= $tagqueue;
2267 // Add Remaining text
2271 while( $x = array_pop($tagstack) )
2272 $newtext .= '</' . $x . '>'; // Add remaining tags to close
2274 // WP fix for the bug with HTML comments
2275 $newtext = str_replace("< !--","<!--",$newtext);
2276 $newtext = str_replace("< !--","< !--",$newtext);
2282 * Acts on text which is about to be edited.
2284 * The $content is run through esc_textarea(), which uses htmlspecialchars()
2285 * to convert special characters to HTML entities. If `$richedit` is set to true,
2286 * it is simply a holder for the {@see 'format_to_edit'} filter.
2289 * @since 4.4.0 The `$richedit` parameter was renamed to `$rich_text` for clarity.
2291 * @param string $content The text about to be edited.
2292 * @param bool $rich_text Optional. Whether `$content` should be considered rich text,
2293 * in which case it would not be passed through esc_textarea().
2295 * @return string The text after the filter (and possibly htmlspecialchars()) has been run.
2297 function format_to_edit( $content, $rich_text = false ) {
2299 * Filters the text to be formatted for editing.
2303 * @param string $content The text, prior to formatting for editing.
2305 $content = apply_filters( 'format_to_edit', $content );
2307 $content = esc_textarea( $content );
2312 * Add leading zeros when necessary.
2314 * If you set the threshold to '4' and the number is '10', then you will get
2315 * back '0010'. If you set the threshold to '4' and the number is '5000', then you
2316 * will get back '5000'.
2318 * Uses sprintf to append the amount of zeros based on the $threshold parameter
2319 * and the size of the number. If the number is large enough, then no zeros will
2324 * @param int $number Number to append zeros to if not greater than threshold.
2325 * @param int $threshold Digit places number needs to be to not have zeros added.
2326 * @return string Adds leading zeros to number if needed.
2328 function zeroise( $number, $threshold ) {
2329 return sprintf( '%0' . $threshold . 's', $number );
2333 * Adds backslashes before letters and before a number at the start of a string.
2337 * @param string $string Value to which backslashes will be added.
2338 * @return string String with backslashes inserted.
2340 function backslashit( $string ) {
2341 if ( isset( $string[0] ) && $string[0] >= '0' && $string[0] <= '9' )
2342 $string = '\\\\' . $string;
2343 return addcslashes( $string, 'A..Za..z' );
2347 * Appends a trailing slash.
2349 * Will remove trailing forward and backslashes if it exists already before adding
2350 * a trailing forward slash. This prevents double slashing a string or path.
2352 * The primary use of this is for paths and thus should be used for paths. It is
2353 * not restricted to paths and offers no specific path support.
2357 * @param string $string What to add the trailing slash to.
2358 * @return string String with trailing slash added.
2360 function trailingslashit( $string ) {
2361 return untrailingslashit( $string ) . '/';
2365 * Removes trailing forward slashes and backslashes if they exist.
2367 * The primary use of this is for paths and thus should be used for paths. It is
2368 * not restricted to paths and offers no specific path support.
2372 * @param string $string What to remove the trailing slashes from.
2373 * @return string String without the trailing slashes.
2375 function untrailingslashit( $string ) {
2376 return rtrim( $string, '/\\' );
2380 * Adds slashes to escape strings.
2382 * Slashes will first be removed if magic_quotes_gpc is set, see {@link
2383 * https://secure.php.net/magic_quotes} for more details.
2387 * @param string $gpc The string returned from HTTP request data.
2388 * @return string Returns a string escaped with slashes.
2390 function addslashes_gpc($gpc) {
2391 if ( get_magic_quotes_gpc() )
2392 $gpc = stripslashes($gpc);
2394 return wp_slash($gpc);
2398 * Navigates through an array, object, or scalar, and removes slashes from the values.
2402 * @param mixed $value The value to be stripped.
2403 * @return mixed Stripped value.
2405 function stripslashes_deep( $value ) {
2406 return map_deep( $value, 'stripslashes_from_strings_only' );
2410 * Callback function for `stripslashes_deep()` which strips slashes from strings.
2414 * @param mixed $value The array or string to be stripped.
2415 * @return mixed $value The stripped value.
2417 function stripslashes_from_strings_only( $value ) {
2418 return is_string( $value ) ? stripslashes( $value ) : $value;
2422 * Navigates through an array, object, or scalar, and encodes the values to be used in a URL.
2426 * @param mixed $value The array or string to be encoded.
2427 * @return mixed $value The encoded value.
2429 function urlencode_deep( $value ) {
2430 return map_deep( $value, 'urlencode' );
2434 * Navigates through an array, object, or scalar, and raw-encodes the values to be used in a URL.
2438 * @param mixed $value The array or string to be encoded.
2439 * @return mixed $value The encoded value.
2441 function rawurlencode_deep( $value ) {
2442 return map_deep( $value, 'rawurlencode' );
2446 * Navigates through an array, object, or scalar, and decodes URL-encoded values
2450 * @param mixed $value The array or string to be decoded.
2451 * @return mixed $value The decoded value.
2453 function urldecode_deep( $value ) {
2454 return map_deep( $value, 'urldecode' );
2458 * Converts email addresses characters to HTML entities to block spam bots.
2462 * @param string $email_address Email address.
2463 * @param int $hex_encoding Optional. Set to 1 to enable hex encoding.
2464 * @return string Converted email address.
2466 function antispambot( $email_address, $hex_encoding = 0 ) {
2467 $email_no_spam_address = '';
2468 for ( $i = 0, $len = strlen( $email_address ); $i < $len; $i++ ) {
2469 $j = rand( 0, 1 + $hex_encoding );
2471 $email_no_spam_address .= '&#' . ord( $email_address[$i] ) . ';';
2472 } elseif ( $j == 1 ) {
2473 $email_no_spam_address .= $email_address[$i];
2474 } elseif ( $j == 2 ) {
2475 $email_no_spam_address .= '%' . zeroise( dechex( ord( $email_address[$i] ) ), 2 );
2479 return str_replace( '@', '@', $email_no_spam_address );
2483 * Callback to convert URI match to HTML A element.
2485 * This function was backported from 2.5.0 to 2.3.2. Regex callback for make_clickable().
2490 * @param array $matches Single Regex Match.
2491 * @return string HTML A element with URI address.
2493 function _make_url_clickable_cb( $matches ) {
2496 if ( ')' == $matches[3] && strpos( $url, '(' ) ) {
2497 // If the trailing character is a closing parethesis, and the URL has an opening parenthesis in it, add the closing parenthesis to the URL.
2498 // Then we can let the parenthesis balancer do its thing below.
2499 $url .= $matches[3];
2502 $suffix = $matches[3];
2505 // Include parentheses in the URL only if paired
2506 while ( substr_count( $url, '(' ) < substr_count( $url, ')' ) ) {
2507 $suffix = strrchr( $url, ')' ) . $suffix;
2508 $url = substr( $url, 0, strrpos( $url, ')' ) );
2511 $url = esc_url($url);
2515 return $matches[1] . "<a href=\"$url\" rel=\"nofollow\">$url</a>" . $suffix;
2519 * Callback to convert URL match to HTML A element.
2521 * This function was backported from 2.5.0 to 2.3.2. Regex callback for make_clickable().
2526 * @param array $matches Single Regex Match.
2527 * @return string HTML A element with URL address.
2529 function _make_web_ftp_clickable_cb( $matches ) {
2531 $dest = $matches[2];
2532 $dest = 'http://' . $dest;
2534 // removed trailing [.,;:)] from URL
2535 if ( in_array( substr($dest, -1), array('.', ',', ';', ':', ')') ) === true ) {
2536 $ret = substr($dest, -1);
2537 $dest = substr($dest, 0, strlen($dest)-1);
2540 $dest = esc_url($dest);
2544 return $matches[1] . "<a href=\"$dest\" rel=\"nofollow\">$dest</a>$ret";
2548 * Callback to convert email address match to HTML A element.
2550 * This function was backported from 2.5.0 to 2.3.2. Regex callback for make_clickable().
2555 * @param array $matches Single Regex Match.
2556 * @return string HTML A element with email address.
2558 function _make_email_clickable_cb( $matches ) {
2559 $email = $matches[2] . '@' . $matches[3];
2560 return $matches[1] . "<a href=\"mailto:$email\">$email</a>";
2564 * Convert plaintext URI to HTML links.
2566 * Converts URI, www and ftp, and email addresses. Finishes by fixing links
2571 * @param string $text Content to convert URIs.
2572 * @return string Content with converted URIs.
2574 function make_clickable( $text ) {
2576 $textarr = preg_split( '/(<[^<>]+>)/', $text, -1, PREG_SPLIT_DELIM_CAPTURE ); // split out HTML tags
2577 $nested_code_pre = 0; // Keep track of how many levels link is nested inside <pre> or <code>
2578 foreach ( $textarr as $piece ) {
2580 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 ) )
2582 elseif ( $nested_code_pre && ( '</code>' === strtolower( $piece ) || '</pre>' === strtolower( $piece ) || '</script>' === strtolower( $piece ) || '</style>' === strtolower( $piece ) ) )
2585 if ( $nested_code_pre || empty( $piece ) || ( $piece[0] === '<' && ! preg_match( '|^<\s*[\w]{1,20}+://|', $piece ) ) ) {
2590 // Long strings might contain expensive edge cases ...
2591 if ( 10000 < strlen( $piece ) ) {
2593 foreach ( _split_str_by_whitespace( $piece, 2100 ) as $chunk ) { // 2100: Extra room for scheme and leading and trailing paretheses
2594 if ( 2101 < strlen( $chunk ) ) {
2595 $r .= $chunk; // Too big, no whitespace: bail.
2597 $r .= make_clickable( $chunk );
2601 $ret = " $piece "; // Pad with whitespace to simplify the regexes
2604 ([\\s(<.,;:!?]) # 1: Leading whitespace, or punctuation
2606 [\\w]{1,20}+:// # Scheme and hier-part prefix
2607 (?=\S{1,2000}\s) # Limit to URLs less than about 2000 characters long
2608 [\\w\\x80-\\xff#%\\~/@\\[\\]*(+=&$-]*+ # Non-punctuation URL character
2609 (?: # Unroll the Loop: Only allow puctuation URL character if followed by a non-punctuation URL character
2610 [\'.,;:!?)] # Punctuation URL character
2611 [\\w\\x80-\\xff#%\\~/@\\[\\]*(+=&$-]++ # Non-punctuation URL character
2614 (\)?) # 3: Trailing closing parenthesis (for parethesis balancing post processing)
2615 ~xS'; // The regex is a non-anchored pattern and does not have a single fixed starting character.
2616 // Tell PCRE to spend more time optimizing since, when used on a page load, it will probably be used several times.
2618 $ret = preg_replace_callback( $url_clickable, '_make_url_clickable_cb', $ret );
2620 $ret = preg_replace_callback( '#([\s>])((www|ftp)\.[\w\\x80-\\xff\#$%&~/.\-;:=,?@\[\]+]+)#is', '_make_web_ftp_clickable_cb', $ret );
2621 $ret = preg_replace_callback( '#([\s>])([.0-9a-z_+-]+)@(([0-9a-z-]+\.)+[0-9a-z]{2,})#i', '_make_email_clickable_cb', $ret );
2623 $ret = substr( $ret, 1, -1 ); // Remove our whitespace padding.
2628 // Cleanup of accidental links within links
2629 return preg_replace( '#(<a([ \r\n\t]+[^>]+?>|>))<a [^>]+?>([^>]+?)</a></a>#i', "$1$3</a>", $r );
2633 * Breaks a string into chunks by splitting at whitespace characters.
2634 * The length of each returned chunk is as close to the specified length goal as possible,
2635 * with the caveat that each chunk includes its trailing delimiter.
2636 * Chunks longer than the goal are guaranteed to not have any inner whitespace.
2638 * Joining the returned chunks with empty delimiters reconstructs the input string losslessly.
2640 * Input string must have no null characters (or eventual transformations on output chunks must not care about null characters)
2642 * _split_str_by_whitespace( "1234 67890 1234 67890a cd 1234 890 123456789 1234567890a 45678 1 3 5 7 90 ", 10 ) ==
2644 * 0 => '1234 67890 ', // 11 characters: Perfect split
2645 * 1 => '1234 ', // 5 characters: '1234 67890a' was too long
2646 * 2 => '67890a cd ', // 10 characters: '67890a cd 1234' was too long
2647 * 3 => '1234 890 ', // 11 characters: Perfect split
2648 * 4 => '123456789 ', // 10 characters: '123456789 1234567890a' was too long
2649 * 5 => '1234567890a ', // 12 characters: Too long, but no inner whitespace on which to split
2650 * 6 => ' 45678 ', // 11 characters: Perfect split
2651 * 7 => '1 3 5 7 90 ', // 11 characters: End of $string
2657 * @param string $string The string to split.
2658 * @param int $goal The desired chunk length.
2659 * @return array Numeric array of chunks.
2661 function _split_str_by_whitespace( $string, $goal ) {
2664 $string_nullspace = strtr( $string, "\r\n\t\v\f ", "\000\000\000\000\000\000" );
2666 while ( $goal < strlen( $string_nullspace ) ) {
2667 $pos = strrpos( substr( $string_nullspace, 0, $goal + 1 ), "\000" );
2669 if ( false === $pos ) {
2670 $pos = strpos( $string_nullspace, "\000", $goal + 1 );
2671 if ( false === $pos ) {
2676 $chunks[] = substr( $string, 0, $pos + 1 );
2677 $string = substr( $string, $pos + 1 );
2678 $string_nullspace = substr( $string_nullspace, $pos + 1 );
2682 $chunks[] = $string;
2689 * Adds rel nofollow string to all HTML A elements in content.
2693 * @param string $text Content that may contain HTML A elements.
2694 * @return string Converted content.
2696 function wp_rel_nofollow( $text ) {
2697 // This is a pre save filter, so text is already escaped.
2698 $text = stripslashes($text);
2699 $text = preg_replace_callback('|<a (.+?)>|i', 'wp_rel_nofollow_callback', $text);
2700 return wp_slash( $text );
2704 * Callback to add rel=nofollow string to HTML A element.
2706 * Will remove already existing rel="nofollow" and rel='nofollow' from the
2707 * string to prevent from invalidating (X)HTML.
2711 * @param array $matches Single Match
2712 * @return string HTML A Element with rel nofollow.
2714 function wp_rel_nofollow_callback( $matches ) {
2715 $text = $matches[1];
2716 $atts = shortcode_parse_atts( $matches[1] );
2719 if ( preg_match( '%href=["\'](' . preg_quote( set_url_scheme( home_url(), 'http' ) ) . ')%i', $text ) ||
2720 preg_match( '%href=["\'](' . preg_quote( set_url_scheme( home_url(), 'https' ) ) . ')%i', $text )
2725 if ( ! empty( $atts['rel'] ) ) {
2726 $parts = array_map( 'trim', explode( ' ', $atts['rel'] ) );
2727 if ( false === array_search( 'nofollow', $parts ) ) {
2728 $parts[] = 'nofollow';
2730 $rel = implode( ' ', $parts );
2731 unset( $atts['rel'] );
2734 foreach ( $atts as $name => $value ) {
2735 $html .= "{$name}=\"$value\" ";
2737 $text = trim( $html );
2739 return "<a $text rel=\"$rel\">";
2743 * Convert one smiley code to the icon graphic file equivalent.
2745 * Callback handler for convert_smilies().
2747 * Looks up one smiley code in the $wpsmiliestrans global array and returns an
2748 * `<img>` string for that smiley.
2752 * @global array $wpsmiliestrans
2754 * @param array $matches Single match. Smiley code to convert to image.
2755 * @return string Image string for smiley.
2757 function translate_smiley( $matches ) {
2758 global $wpsmiliestrans;
2760 if ( count( $matches ) == 0 )
2763 $smiley = trim( reset( $matches ) );
2764 $img = $wpsmiliestrans[ $smiley ];
2767 $ext = preg_match( '/\.([^.]+)$/', $img, $matches ) ? strtolower( $matches[1] ) : false;
2768 $image_exts = array( 'jpg', 'jpeg', 'jpe', 'gif', 'png' );
2770 // Don't convert smilies that aren't images - they're probably emoji.
2771 if ( ! in_array( $ext, $image_exts ) ) {
2776 * Filters the Smiley image URL before it's used in the image element.
2780 * @param string $smiley_url URL for the smiley image.
2781 * @param string $img Filename for the smiley image.
2782 * @param string $site_url Site URL, as returned by site_url().
2784 $src_url = apply_filters( 'smilies_src', includes_url( "images/smilies/$img" ), $img, site_url() );
2786 return sprintf( '<img src="%s" alt="%s" class="wp-smiley" style="height: 1em; max-height: 1em;" />', esc_url( $src_url ), esc_attr( $smiley ) );
2790 * Convert text equivalent of smilies to images.
2792 * Will only convert smilies if the option 'use_smilies' is true and the global
2793 * used in the function isn't empty.
2797 * @global string|array $wp_smiliessearch
2799 * @param string $text Content to convert smilies from text.
2800 * @return string Converted content with text smilies replaced with images.
2802 function convert_smilies( $text ) {
2803 global $wp_smiliessearch;
2805 if ( get_option( 'use_smilies' ) && ! empty( $wp_smiliessearch ) ) {
2806 // HTML loop taken from texturize function, could possible be consolidated
2807 $textarr = preg_split( '/(<.*>)/U', $text, -1, PREG_SPLIT_DELIM_CAPTURE ); // capture the tags as well as in between
2808 $stop = count( $textarr );// loop stuff
2810 // Ignore proessing of specific tags
2811 $tags_to_ignore = 'code|pre|style|script|textarea';
2812 $ignore_block_element = '';
2814 for ( $i = 0; $i < $stop; $i++ ) {
2815 $content = $textarr[$i];
2817 // If we're in an ignore block, wait until we find its closing tag
2818 if ( '' == $ignore_block_element && preg_match( '/^<(' . $tags_to_ignore . ')>/', $content, $matches ) ) {
2819 $ignore_block_element = $matches[1];
2822 // If it's not a tag and not in ignore block
2823 if ( '' == $ignore_block_element && strlen( $content ) > 0 && '<' != $content[0] ) {
2824 $content = preg_replace_callback( $wp_smiliessearch, 'translate_smiley', $content );
2827 // did we exit ignore block
2828 if ( '' != $ignore_block_element && '</' . $ignore_block_element . '>' == $content ) {
2829 $ignore_block_element = '';
2832 $output .= $content;
2835 // return default text.
2842 * Verifies that an email is valid.
2844 * Does not grok i18n domains. Not RFC compliant.
2848 * @param string $email Email address to verify.
2849 * @param bool $deprecated Deprecated.
2850 * @return string|bool Either false or the valid email address.
2852 function is_email( $email, $deprecated = false ) {
2853 if ( ! empty( $deprecated ) )
2854 _deprecated_argument( __FUNCTION__, '3.0.0' );
2856 // Test for the minimum length the email can be
2857 if ( strlen( $email ) < 3 ) {
2859 * Filters whether an email address is valid.
2861 * This filter is evaluated under several different contexts, such as 'email_too_short',
2862 * 'email_no_at', 'local_invalid_chars', 'domain_period_sequence', 'domain_period_limits',
2863 * 'domain_no_periods', 'sub_hyphen_limits', 'sub_invalid_chars', or no specific context.
2867 * @param bool $is_email Whether the email address has passed the is_email() checks. Default false.
2868 * @param string $email The email address being checked.
2869 * @param string $context Context under which the email was tested.
2871 return apply_filters( 'is_email', false, $email, 'email_too_short' );
2874 // Test for an @ character after the first position
2875 if ( strpos( $email, '@', 1 ) === false ) {
2876 /** This filter is documented in wp-includes/formatting.php */
2877 return apply_filters( 'is_email', false, $email, 'email_no_at' );
2880 // Split out the local and domain parts
2881 list( $local, $domain ) = explode( '@', $email, 2 );
2884 // Test for invalid characters
2885 if ( !preg_match( '/^[a-zA-Z0-9!#$%&\'*+\/=?^_`{|}~\.-]+$/', $local ) ) {
2886 /** This filter is documented in wp-includes/formatting.php */
2887 return apply_filters( 'is_email', false, $email, 'local_invalid_chars' );
2891 // Test for sequences of periods
2892 if ( preg_match( '/\.{2,}/', $domain ) ) {
2893 /** This filter is documented in wp-includes/formatting.php */
2894 return apply_filters( 'is_email', false, $email, 'domain_period_sequence' );
2897 // Test for leading and trailing periods and whitespace
2898 if ( trim( $domain, " \t\n\r\0\x0B." ) !== $domain ) {
2899 /** This filter is documented in wp-includes/formatting.php */
2900 return apply_filters( 'is_email', false, $email, 'domain_period_limits' );
2903 // Split the domain into subs
2904 $subs = explode( '.', $domain );
2906 // Assume the domain will have at least two subs
2907 if ( 2 > count( $subs ) ) {
2908 /** This filter is documented in wp-includes/formatting.php */
2909 return apply_filters( 'is_email', false, $email, 'domain_no_periods' );
2912 // Loop through each sub
2913 foreach ( $subs as $sub ) {
2914 // Test for leading and trailing hyphens and whitespace
2915 if ( trim( $sub, " \t\n\r\0\x0B-" ) !== $sub ) {
2916 /** This filter is documented in wp-includes/formatting.php */
2917 return apply_filters( 'is_email', false, $email, 'sub_hyphen_limits' );
2920 // Test for invalid characters
2921 if ( !preg_match('/^[a-z0-9-]+$/i', $sub ) ) {
2922 /** This filter is documented in wp-includes/formatting.php */
2923 return apply_filters( 'is_email', false, $email, 'sub_invalid_chars' );
2927 // Congratulations your email made it!
2928 /** This filter is documented in wp-includes/formatting.php */
2929 return apply_filters( 'is_email', $email, $email, null );
2933 * Convert to ASCII from email subjects.
2937 * @param string $string Subject line
2938 * @return string Converted string to ASCII
2940 function wp_iso_descrambler( $string ) {
2941 /* this may only work with iso-8859-1, I'm afraid */
2942 if (!preg_match('#\=\?(.+)\?Q\?(.+)\?\=#i', $string, $matches)) {
2945 $subject = str_replace('_', ' ', $matches[2]);
2946 return preg_replace_callback( '#\=([0-9a-f]{2})#i', '_wp_iso_convert', $subject );
2951 * Helper function to convert hex encoded chars to ASCII
2956 * @param array $match The preg_replace_callback matches array
2957 * @return string Converted chars
2959 function _wp_iso_convert( $match ) {
2960 return chr( hexdec( strtolower( $match[1] ) ) );
2964 * Returns a date in the GMT equivalent.
2966 * Requires and returns a date in the Y-m-d H:i:s format. If there is a
2967 * timezone_string available, the date is assumed to be in that timezone,
2968 * otherwise it simply subtracts the value of the 'gmt_offset' option. Return
2969 * format can be overridden using the $format parameter.
2973 * @param string $string The date to be converted.
2974 * @param string $format The format string for the returned date (default is Y-m-d H:i:s)
2975 * @return string GMT version of the date provided.
2977 function get_gmt_from_date( $string, $format = 'Y-m-d H:i:s' ) {
2978 $tz = get_option( 'timezone_string' );
2980 $datetime = date_create( $string, new DateTimeZone( $tz ) );
2981 if ( ! $datetime ) {
2982 return gmdate( $format, 0 );
2984 $datetime->setTimezone( new DateTimeZone( 'UTC' ) );
2985 $string_gmt = $datetime->format( $format );
2987 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 ) ) {
2988 $datetime = strtotime( $string );
2989 if ( false === $datetime ) {
2990 return gmdate( $format, 0 );
2992 return gmdate( $format, $datetime );
2994 $string_time = gmmktime( $matches[4], $matches[5], $matches[6], $matches[2], $matches[3], $matches[1] );
2995 $string_gmt = gmdate( $format, $string_time - get_option( 'gmt_offset' ) * HOUR_IN_SECONDS );
3001 * Converts a GMT date into the correct format for the blog.
3003 * Requires and returns a date in the Y-m-d H:i:s format. If there is a
3004 * timezone_string available, the returned date is in that timezone, otherwise
3005 * it simply adds the value of gmt_offset. Return format can be overridden
3006 * using the $format parameter
3010 * @param string $string The date to be converted.
3011 * @param string $format The format string for the returned date (default is Y-m-d H:i:s)
3012 * @return string Formatted date relative to the timezone / GMT offset.
3014 function get_date_from_gmt( $string, $format = 'Y-m-d H:i:s' ) {
3015 $tz = get_option( 'timezone_string' );
3017 $datetime = date_create( $string, new DateTimeZone( 'UTC' ) );
3019 return date( $format, 0 );
3020 $datetime->setTimezone( new DateTimeZone( $tz ) );
3021 $string_localtime = $datetime->format( $format );
3023 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) )
3024 return date( $format, 0 );
3025 $string_time = gmmktime( $matches[4], $matches[5], $matches[6], $matches[2], $matches[3], $matches[1] );
3026 $string_localtime = gmdate( $format, $string_time + get_option( 'gmt_offset' ) * HOUR_IN_SECONDS );
3028 return $string_localtime;
3032 * Computes an offset in seconds from an iso8601 timezone.
3036 * @param string $timezone Either 'Z' for 0 offset or '±hhmm'.
3037 * @return int|float The offset in seconds.
3039 function iso8601_timezone_to_offset( $timezone ) {
3040 // $timezone is either 'Z' or '[+|-]hhmm'
3041 if ($timezone == 'Z') {
3044 $sign = (substr($timezone, 0, 1) == '+') ? 1 : -1;
3045 $hours = intval(substr($timezone, 1, 2));
3046 $minutes = intval(substr($timezone, 3, 4)) / 60;
3047 $offset = $sign * HOUR_IN_SECONDS * ($hours + $minutes);
3053 * Converts an iso8601 date to MySQL DateTime format used by post_date[_gmt].
3057 * @param string $date_string Date and time in ISO 8601 format {@link https://en.wikipedia.org/wiki/ISO_8601}.
3058 * @param string $timezone Optional. If set to GMT returns the time minus gmt_offset. Default is 'user'.
3059 * @return string The date and time in MySQL DateTime format - Y-m-d H:i:s.
3061 function iso8601_to_datetime( $date_string, $timezone = 'user' ) {
3062 $timezone = strtolower($timezone);
3064 if ($timezone == 'gmt') {
3066 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, $date_bits);
3068 if (!empty($date_bits[7])) { // we have a timezone, so let's compute an offset
3069 $offset = iso8601_timezone_to_offset($date_bits[7]);
3070 } else { // we don't have a timezone, so we assume user local timezone (not server's!)
3071 $offset = HOUR_IN_SECONDS * get_option('gmt_offset');
3074 $timestamp = gmmktime($date_bits[4], $date_bits[5], $date_bits[6], $date_bits[2], $date_bits[3], $date_bits[1]);
3075 $timestamp -= $offset;
3077 return gmdate('Y-m-d H:i:s', $timestamp);
3079 } elseif ($timezone == 'user') {
3080 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);
3085 * Strips out all characters that are not allowable in an email.
3089 * @param string $email Email address to filter.
3090 * @return string Filtered email address.
3092 function sanitize_email( $email ) {
3093 // Test for the minimum length the email can be
3094 if ( strlen( $email ) < 3 ) {
3096 * Filters a sanitized email address.
3098 * This filter is evaluated under several contexts, including 'email_too_short',
3099 * 'email_no_at', 'local_invalid_chars', 'domain_period_sequence', 'domain_period_limits',
3100 * 'domain_no_periods', 'domain_no_valid_subs', or no context.
3104 * @param string $email The sanitized email address.
3105 * @param string $email The email address, as provided to sanitize_email().
3106 * @param string $message A message to pass to the user.
3108 return apply_filters( 'sanitize_email', '', $email, 'email_too_short' );
3111 // Test for an @ character after the first position
3112 if ( strpos( $email, '@', 1 ) === false ) {
3113 /** This filter is documented in wp-includes/formatting.php */
3114 return apply_filters( 'sanitize_email', '', $email, 'email_no_at' );
3117 // Split out the local and domain parts
3118 list( $local, $domain ) = explode( '@', $email, 2 );
3121 // Test for invalid characters
3122 $local = preg_replace( '/[^a-zA-Z0-9!#$%&\'*+\/=?^_`{|}~\.-]/', '', $local );
3123 if ( '' === $local ) {
3124 /** This filter is documented in wp-includes/formatting.php */
3125 return apply_filters( 'sanitize_email', '', $email, 'local_invalid_chars' );
3129 // Test for sequences of periods
3130 $domain = preg_replace( '/\.{2,}/', '', $domain );
3131 if ( '' === $domain ) {
3132 /** This filter is documented in wp-includes/formatting.php */
3133 return apply_filters( 'sanitize_email', '', $email, 'domain_period_sequence' );
3136 // Test for leading and trailing periods and whitespace
3137 $domain = trim( $domain, " \t\n\r\0\x0B." );
3138 if ( '' === $domain ) {
3139 /** This filter is documented in wp-includes/formatting.php */
3140 return apply_filters( 'sanitize_email', '', $email, 'domain_period_limits' );
3143 // Split the domain into subs
3144 $subs = explode( '.', $domain );
3146 // Assume the domain will have at least two subs
3147 if ( 2 > count( $subs ) ) {
3148 /** This filter is documented in wp-includes/formatting.php */
3149 return apply_filters( 'sanitize_email', '', $email, 'domain_no_periods' );
3152 // Create an array that will contain valid subs
3153 $new_subs = array();
3155 // Loop through each sub
3156 foreach ( $subs as $sub ) {
3157 // Test for leading and trailing hyphens
3158 $sub = trim( $sub, " \t\n\r\0\x0B-" );
3160 // Test for invalid characters
3161 $sub = preg_replace( '/[^a-z0-9-]+/i', '', $sub );
3163 // If there's anything left, add it to the valid subs
3164 if ( '' !== $sub ) {
3169 // If there aren't 2 or more valid subs
3170 if ( 2 > count( $new_subs ) ) {
3171 /** This filter is documented in wp-includes/formatting.php */
3172 return apply_filters( 'sanitize_email', '', $email, 'domain_no_valid_subs' );
3175 // Join valid subs into the new domain
3176 $domain = join( '.', $new_subs );
3178 // Put the email back together
3179 $email = $local . '@' . $domain;
3181 // Congratulations your email made it!
3182 /** This filter is documented in wp-includes/formatting.php */
3183 return apply_filters( 'sanitize_email', $email, $email, null );
3187 * Determines the difference between two timestamps.
3189 * The difference is returned in a human readable format such as "1 hour",
3190 * "5 mins", "2 days".
3194 * @param int $from Unix timestamp from which the difference begins.
3195 * @param int $to Optional. Unix timestamp to end the time difference. Default becomes time() if not set.
3196 * @return string Human readable time difference.
3198 function human_time_diff( $from, $to = '' ) {
3199 if ( empty( $to ) ) {
3203 $diff = (int) abs( $to - $from );
3205 if ( $diff < HOUR_IN_SECONDS ) {
3206 $mins = round( $diff / MINUTE_IN_SECONDS );
3209 /* translators: min=minute */
3210 $since = sprintf( _n( '%s min', '%s mins', $mins ), $mins );
3211 } elseif ( $diff < DAY_IN_SECONDS && $diff >= HOUR_IN_SECONDS ) {
3212 $hours = round( $diff / HOUR_IN_SECONDS );
3215 $since = sprintf( _n( '%s hour', '%s hours', $hours ), $hours );
3216 } elseif ( $diff < WEEK_IN_SECONDS && $diff >= DAY_IN_SECONDS ) {
3217 $days = round( $diff / DAY_IN_SECONDS );
3220 $since = sprintf( _n( '%s day', '%s days', $days ), $days );
3221 } elseif ( $diff < MONTH_IN_SECONDS && $diff >= WEEK_IN_SECONDS ) {
3222 $weeks = round( $diff / WEEK_IN_SECONDS );
3225 $since = sprintf( _n( '%s week', '%s weeks', $weeks ), $weeks );
3226 } elseif ( $diff < YEAR_IN_SECONDS && $diff >= MONTH_IN_SECONDS ) {
3227 $months = round( $diff / MONTH_IN_SECONDS );
3230 $since = sprintf( _n( '%s month', '%s months', $months ), $months );
3231 } elseif ( $diff >= YEAR_IN_SECONDS ) {
3232 $years = round( $diff / YEAR_IN_SECONDS );
3235 $since = sprintf( _n( '%s year', '%s years', $years ), $years );
3239 * Filters the human readable difference between two timestamps.
3243 * @param string $since The difference in human readable text.
3244 * @param int $diff The difference in seconds.
3245 * @param int $from Unix timestamp from which the difference begins.
3246 * @param int $to Unix timestamp to end the time difference.
3248 return apply_filters( 'human_time_diff', $since, $diff, $from, $to );
3252 * Generates an excerpt from the content, if needed.
3254 * The excerpt word amount will be 55 words and if the amount is greater than
3255 * that, then the string ' […]' will be appended to the excerpt. If the string
3256 * is less than 55 words, then the content will be returned as is.
3258 * The 55 word limit can be modified by plugins/themes using the {@see 'excerpt_length'} filter
3259 * The ' […]' string can be modified by plugins/themes using the {@see 'excerpt_more'} filter
3263 * @param string $text Optional. The excerpt. If set to empty, an excerpt is generated.
3264 * @return string The excerpt.
3266 function wp_trim_excerpt( $text = '' ) {
3267 $raw_excerpt = $text;
3268 if ( '' == $text ) {
3269 $text = get_the_content('');
3271 $text = strip_shortcodes( $text );
3273 /** This filter is documented in wp-includes/post-template.php */
3274 $text = apply_filters( 'the_content', $text );
3275 $text = str_replace(']]>', ']]>', $text);
3278 * Filters the number of words in an excerpt.
3282 * @param int $number The number of words. Default 55.
3284 $excerpt_length = apply_filters( 'excerpt_length', 55 );
3286 * Filters the string in the "more" link displayed after a trimmed excerpt.
3290 * @param string $more_string The string shown within the more link.
3292 $excerpt_more = apply_filters( 'excerpt_more', ' ' . '[…]' );
3293 $text = wp_trim_words( $text, $excerpt_length, $excerpt_more );
3296 * Filters the trimmed excerpt string.
3300 * @param string $text The trimmed text.
3301 * @param string $raw_excerpt The text prior to trimming.
3303 return apply_filters( 'wp_trim_excerpt', $text, $raw_excerpt );
3307 * Trims text to a certain number of words.
3309 * This function is localized. For languages that count 'words' by the individual
3310 * character (such as East Asian languages), the $num_words argument will apply
3311 * to the number of individual characters.
3315 * @param string $text Text to trim.
3316 * @param int $num_words Number of words. Default 55.
3317 * @param string $more Optional. What to append if $text needs to be trimmed. Default '…'.
3318 * @return string Trimmed text.
3320 function wp_trim_words( $text, $num_words = 55, $more = null ) {
3321 if ( null === $more ) {
3322 $more = __( '…' );
3325 $original_text = $text;
3326 $text = wp_strip_all_tags( $text );
3329 * translators: If your word count is based on single characters (e.g. East Asian characters),
3330 * enter 'characters_excluding_spaces' or 'characters_including_spaces'. Otherwise, enter 'words'.
3331 * Do not translate into your own language.
3333 if ( strpos( _x( 'words', 'Word count type. Do not translate!' ), 'characters' ) === 0 && preg_match( '/^utf\-?8$/i', get_option( 'blog_charset' ) ) ) {
3334 $text = trim( preg_replace( "/[\n\r\t ]+/", ' ', $text ), ' ' );
3335 preg_match_all( '/./u', $text, $words_array );
3336 $words_array = array_slice( $words_array[0], 0, $num_words + 1 );
3339 $words_array = preg_split( "/[\n\r\t ]+/", $text, $num_words + 1, PREG_SPLIT_NO_EMPTY );
3343 if ( count( $words_array ) > $num_words ) {
3344 array_pop( $words_array );
3345 $text = implode( $sep, $words_array );
3346 $text = $text . $more;
3348 $text = implode( $sep, $words_array );
3352 * Filters the text content after words have been trimmed.
3356 * @param string $text The trimmed text.
3357 * @param int $num_words The number of words to trim the text to. Default 5.
3358 * @param string $more An optional string to append to the end of the trimmed text, e.g. ….
3359 * @param string $original_text The text before it was trimmed.
3361 return apply_filters( 'wp_trim_words', $text, $num_words, $more, $original_text );
3365 * Converts named entities into numbered entities.
3369 * @param string $text The text within which entities will be converted.
3370 * @return string Text with converted entities.
3372 function ent2ncr( $text ) {
3375 * Filters text before named entities are converted into numbered entities.
3377 * A non-null string must be returned for the filter to be evaluated.
3381 * @param null $converted_text The text to be converted. Default null.
3382 * @param string $text The text prior to entity conversion.
3384 $filtered = apply_filters( 'pre_ent2ncr', null, $text );
3385 if ( null !== $filtered )
3389 '"' => '"',
3394 ' ' => ' ',
3395 '¡' => '¡',
3396 '¢' => '¢',
3397 '£' => '£',
3398 '¤' => '¤',
3399 '¥' => '¥',
3400 '¦' => '¦',
3401 '&brkbar;' => '¦',
3402 '§' => '§',
3403 '¨' => '¨',
3404 '¨' => '¨',
3405 '©' => '©',
3406 'ª' => 'ª',
3407 '«' => '«',
3408 '¬' => '¬',
3409 '­' => '­',
3410 '®' => '®',
3411 '¯' => '¯',
3412 '&hibar;' => '¯',
3413 '°' => '°',
3414 '±' => '±',
3415 '²' => '²',
3416 '³' => '³',
3417 '´' => '´',
3418 'µ' => 'µ',
3419 '¶' => '¶',
3420 '·' => '·',
3421 '¸' => '¸',
3422 '¹' => '¹',
3423 'º' => 'º',
3424 '»' => '»',
3425 '¼' => '¼',
3426 '½' => '½',
3427 '¾' => '¾',
3428 '¿' => '¿',
3429 'À' => 'À',
3430 'Á' => 'Á',
3431 'Â' => 'Â',
3432 'Ã' => 'Ã',
3433 'Ä' => 'Ä',
3434 'Å' => 'Å',
3435 'Æ' => 'Æ',
3436 'Ç' => 'Ç',
3437 'È' => 'È',
3438 'É' => 'É',
3439 'Ê' => 'Ê',
3440 'Ë' => 'Ë',
3441 'Ì' => 'Ì',
3442 'Í' => 'Í',
3443 'Î' => 'Î',
3444 'Ï' => 'Ï',
3445 'Ð' => 'Ð',
3446 'Ñ' => 'Ñ',
3447 'Ò' => 'Ò',
3448 'Ó' => 'Ó',
3449 'Ô' => 'Ô',
3450 'Õ' => 'Õ',
3451 'Ö' => 'Ö',
3452 '×' => '×',
3453 'Ø' => 'Ø',
3454 'Ù' => 'Ù',
3455 'Ú' => 'Ú',
3456 'Û' => 'Û',
3457 'Ü' => 'Ü',
3458 'Ý' => 'Ý',
3459 'Þ' => 'Þ',
3460 'ß' => 'ß',
3461 'à' => 'à',
3462 'á' => 'á',
3463 'â' => 'â',
3464 'ã' => 'ã',
3465 'ä' => 'ä',
3466 'å' => 'å',
3467 'æ' => 'æ',
3468 'ç' => 'ç',
3469 'è' => 'è',
3470 'é' => 'é',
3471 'ê' => 'ê',
3472 'ë' => 'ë',
3473 'ì' => 'ì',
3474 'í' => 'í',
3475 'î' => 'î',
3476 'ï' => 'ï',
3477 'ð' => 'ð',
3478 'ñ' => 'ñ',
3479 'ò' => 'ò',
3480 'ó' => 'ó',
3481 'ô' => 'ô',
3482 'õ' => 'õ',
3483 'ö' => 'ö',
3484 '÷' => '÷',
3485 'ø' => 'ø',
3486 'ù' => 'ù',
3487 'ú' => 'ú',
3488 'û' => 'û',
3489 'ü' => 'ü',
3490 'ý' => 'ý',
3491 'þ' => 'þ',
3492 'ÿ' => 'ÿ',
3493 'Œ' => 'Œ',
3494 'œ' => 'œ',
3495 'Š' => 'Š',
3496 'š' => 'š',
3497 'Ÿ' => 'Ÿ',
3498 'ƒ' => 'ƒ',
3499 'ˆ' => 'ˆ',
3500 '˜' => '˜',
3501 'Α' => 'Α',
3502 'Β' => 'Β',
3503 'Γ' => 'Γ',
3504 'Δ' => 'Δ',
3505 'Ε' => 'Ε',
3506 'Ζ' => 'Ζ',
3507 'Η' => 'Η',
3508 'Θ' => 'Θ',
3509 'Ι' => 'Ι',
3510 'Κ' => 'Κ',
3511 'Λ' => 'Λ',
3515 'Ο' => 'Ο',
3517 'Ρ' => 'Ρ',
3518 'Σ' => 'Σ',
3519 'Τ' => 'Τ',
3520 'Υ' => 'Υ',
3521 'Φ' => 'Φ',
3522 'Χ' => 'Χ',
3523 'Ψ' => 'Ψ',
3524 'Ω' => 'Ω',
3525 'α' => 'α',
3526 'β' => 'β',
3527 'γ' => 'γ',
3528 'δ' => 'δ',
3529 'ε' => 'ε',
3530 'ζ' => 'ζ',
3531 'η' => 'η',
3532 'θ' => 'θ',
3533 'ι' => 'ι',
3534 'κ' => 'κ',
3535 'λ' => 'λ',
3539 'ο' => 'ο',
3541 'ρ' => 'ρ',
3542 'ς' => 'ς',
3543 'σ' => 'σ',
3544 'τ' => 'τ',
3545 'υ' => 'υ',
3546 'φ' => 'φ',
3547 'χ' => 'χ',
3548 'ψ' => 'ψ',
3549 'ω' => 'ω',
3550 'ϑ' => 'ϑ',
3551 'ϒ' => 'ϒ',
3552 'ϖ' => 'ϖ',
3553 ' ' => ' ',
3554 ' ' => ' ',
3555 ' ' => ' ',
3556 '‌' => '‌',
3557 '‍' => '‍',
3558 '‎' => '‎',
3559 '‏' => '‏',
3560 '–' => '–',
3561 '—' => '—',
3562 '‘' => '‘',
3563 '’' => '’',
3564 '‚' => '‚',
3565 '“' => '“',
3566 '”' => '”',
3567 '„' => '„',
3568 '†' => '†',
3569 '‡' => '‡',
3570 '•' => '•',
3571 '…' => '…',
3572 '‰' => '‰',
3573 '′' => '′',
3574 '″' => '″',
3575 '‹' => '‹',
3576 '›' => '›',
3577 '‾' => '‾',
3578 '⁄' => '⁄',
3579 '€' => '€',
3580 'ℑ' => 'ℑ',
3581 '℘' => '℘',
3582 'ℜ' => 'ℜ',
3583 '™' => '™',
3584 'ℵ' => 'ℵ',
3585 '↵' => '↵',
3586 '⇐' => '⇐',
3587 '⇑' => '⇑',
3588 '⇒' => '⇒',
3589 '⇓' => '⇓',
3590 '⇔' => '⇔',
3591 '∀' => '∀',
3592 '∂' => '∂',
3593 '∃' => '∃',
3594 '∅' => '∅',
3595 '∇' => '∇',
3596 '∈' => '∈',
3597 '∉' => '∉',
3598 '∋' => '∋',
3599 '∏' => '∏',
3600 '∑' => '∑',
3601 '−' => '−',
3602 '∗' => '∗',
3603 '√' => '√',
3604 '∝' => '∝',
3605 '∞' => '∞',
3606 '∠' => '∠',
3607 '∧' => '∧',
3608 '∨' => '∨',
3609 '∩' => '∩',
3610 '∪' => '∪',
3611 '∫' => '∫',
3612 '∴' => '∴',
3613 '∼' => '∼',
3614 '≅' => '≅',
3615 '≈' => '≈',
3616 '≠' => '≠',
3617 '≡' => '≡',
3618 '≤' => '≤',
3619 '≥' => '≥',
3620 '⊂' => '⊂',
3621 '⊃' => '⊃',
3622 '⊄' => '⊄',
3623 '⊆' => '⊆',
3624 '⊇' => '⊇',
3625 '⊕' => '⊕',
3626 '⊗' => '⊗',
3627 '⊥' => '⊥',
3628 '⋅' => '⋅',
3629 '⌈' => '⌈',
3630 '⌉' => '⌉',
3631 '⌊' => '⌊',
3632 '⌋' => '⌋',
3633 '⟨' => '〈',
3634 '⟩' => '〉',
3635 '←' => '←',
3636 '↑' => '↑',
3637 '→' => '→',
3638 '↓' => '↓',
3639 '↔' => '↔',
3640 '◊' => '◊',
3641 '♠' => '♠',
3642 '♣' => '♣',
3643 '♥' => '♥',
3644 '♦' => '♦'
3647 return str_replace( array_keys($to_ncr), array_values($to_ncr), $text );
3651 * Formats text for the editor.
3653 * Generally the browsers treat everything inside a textarea as text, but
3654 * it is still a good idea to HTML entity encode `<`, `>` and `&` in the content.
3656 * The filter {@see 'format_for_editor'} is applied here. If `$text` is empty the
3657 * filter will be applied to an empty string.
3661 * @see _WP_Editors::editor()
3663 * @param string $text The text to be formatted.
3664 * @param string $default_editor The default editor for the current user.
3665 * It is usually either 'html' or 'tinymce'.
3666 * @return string The formatted text after filter is applied.
3668 function format_for_editor( $text, $default_editor = null ) {
3670 $text = htmlspecialchars( $text, ENT_NOQUOTES, get_option( 'blog_charset' ) );
3674 * Filters the text after it is formatted for the editor.
3678 * @param string $text The formatted text.
3679 * @param string $default_editor The default editor for the current user.
3680 * It is usually either 'html' or 'tinymce'.
3682 return apply_filters( 'format_for_editor', $text, $default_editor );
3686 * Perform a deep string replace operation to ensure the values in $search are no longer present
3688 * Repeats the replacement operation until it no longer replaces anything so as to remove "nested" values
3689 * e.g. $subject = '%0%0%0DDD', $search ='%0D', $result ='' rather than the '%0%0DD' that
3690 * str_replace would return
3695 * @param string|array $search The value being searched for, otherwise known as the needle.
3696 * An array may be used to designate multiple needles.
3697 * @param string $subject The string being searched and replaced on, otherwise known as the haystack.
3698 * @return string The string with the replaced svalues.
3700 function _deep_replace( $search, $subject ) {
3701 $subject = (string) $subject;
3705 $subject = str_replace( $search, '', $subject, $count );
3712 * Escapes data for use in a MySQL query.
3714 * Usually you should prepare queries using wpdb::prepare().
3715 * Sometimes, spot-escaping is required or useful. One example
3716 * is preparing an array for use in an IN clause.
3720 * @global wpdb $wpdb WordPress database abstraction object.
3722 * @param string|array $data Unescaped data
3723 * @return string|array Escaped data
3725 function esc_sql( $data ) {
3727 return $wpdb->_escape( $data );
3731 * Checks and cleans a URL.
3733 * A number of characters are removed from the URL. If the URL is for displaying
3734 * (the default behaviour) ampersands are also replaced. The {@see 'clean_url'} filter
3735 * is applied to the returned cleaned URL.
3739 * @param string $url The URL to be cleaned.
3740 * @param array $protocols Optional. An array of acceptable protocols.
3741 * Defaults to return value of wp_allowed_protocols()
3742 * @param string $_context Private. Use esc_url_raw() for database usage.
3743 * @return string The cleaned $url after the {@see 'clean_url'} filter is applied.
3745 function esc_url( $url, $protocols = null, $_context = 'display' ) {
3746 $original_url = $url;
3751 $url = str_replace( ' ', '%20', $url );
3752 $url = preg_replace('|[^a-z0-9-~+_.?#=!&;,/:%@$\|*\'()\[\]\\x80-\\xff]|i', '', $url);
3754 if ( '' === $url ) {
3758 if ( 0 !== stripos( $url, 'mailto:' ) ) {
3759 $strip = array('%0d', '%0a', '%0D', '%0A');
3760 $url = _deep_replace($strip, $url);
3763 $url = str_replace(';//', '://', $url);
3764 /* If the URL doesn't appear to contain a scheme, we
3765 * presume it needs http:// prepended (unless a relative
3766 * link starting with /, # or ? or a php file).
3768 if ( strpos($url, ':') === false && ! in_array( $url[0], array( '/', '#', '?' ) ) &&
3769 ! preg_match('/^[a-z0-9-]+?\.php/i', $url) )
3770 $url = 'http://' . $url;
3772 // Replace ampersands and single quotes only when displaying.
3773 if ( 'display' == $_context ) {
3774 $url = wp_kses_normalize_entities( $url );
3775 $url = str_replace( '&', '&', $url );
3776 $url = str_replace( "'", ''', $url );
3779 if ( ( false !== strpos( $url, '[' ) ) || ( false !== strpos( $url, ']' ) ) ) {
3781 $parsed = wp_parse_url( $url );
3784 if ( isset( $parsed['scheme'] ) ) {
3785 $front .= $parsed['scheme'] . '://';
3786 } elseif ( '/' === $url[0] ) {
3790 if ( isset( $parsed['user'] ) ) {
3791 $front .= $parsed['user'];
3794 if ( isset( $parsed['pass'] ) ) {
3795 $front .= ':' . $parsed['pass'];
3798 if ( isset( $parsed['user'] ) || isset( $parsed['pass'] ) ) {
3802 if ( isset( $parsed['host'] ) ) {
3803 $front .= $parsed['host'];
3806 if ( isset( $parsed['port'] ) ) {
3807 $front .= ':' . $parsed['port'];
3810 $end_dirty = str_replace( $front, '', $url );
3811 $end_clean = str_replace( array( '[', ']' ), array( '%5B', '%5D' ), $end_dirty );
3812 $url = str_replace( $end_dirty, $end_clean, $url );
3816 if ( '/' === $url[0] ) {
3817 $good_protocol_url = $url;
3819 if ( ! is_array( $protocols ) )
3820 $protocols = wp_allowed_protocols();
3821 $good_protocol_url = wp_kses_bad_protocol( $url, $protocols );
3822 if ( strtolower( $good_protocol_url ) != strtolower( $url ) )
3827 * Filters a string cleaned and escaped for output as a URL.
3831 * @param string $good_protocol_url The cleaned URL to be returned.
3832 * @param string $original_url The URL prior to cleaning.
3833 * @param string $_context If 'display', replace ampersands and single quotes only.
3835 return apply_filters( 'clean_url', $good_protocol_url, $original_url, $_context );
3839 * Performs esc_url() for database usage.
3843 * @param string $url The URL to be cleaned.
3844 * @param array $protocols An array of acceptable protocols.
3845 * @return string The cleaned URL.
3847 function esc_url_raw( $url, $protocols = null ) {
3848 return esc_url( $url, $protocols, 'db' );
3852 * Convert entities, while preserving already-encoded entities.
3854 * @link https://secure.php.net/htmlentities Borrowed from the PHP Manual user notes.
3858 * @param string $myHTML The text to be converted.
3859 * @return string Converted text.
3861 function htmlentities2( $myHTML ) {
3862 $translation_table = get_html_translation_table( HTML_ENTITIES, ENT_QUOTES );
3863 $translation_table[chr(38)] = '&';
3864 return preg_replace( "/&(?![A-Za-z]{0,4}\w{2,3};|#[0-9]{2,3};)/", "&", strtr($myHTML, $translation_table) );
3868 * Escape single quotes, htmlspecialchar " < > &, and fix line endings.
3870 * Escapes text strings for echoing in JS. It is intended to be used for inline JS
3871 * (in a tag attribute, for example onclick="..."). Note that the strings have to
3872 * be in single quotes. The {@see 'js_escape'} filter is also applied here.
3876 * @param string $text The text to be escaped.
3877 * @return string Escaped text.
3879 function esc_js( $text ) {
3880 $safe_text = wp_check_invalid_utf8( $text );
3881 $safe_text = _wp_specialchars( $safe_text, ENT_COMPAT );
3882 $safe_text = preg_replace( '/&#(x)?0*(?(1)27|39);?/i', "'", stripslashes( $safe_text ) );
3883 $safe_text = str_replace( "\r", '', $safe_text );
3884 $safe_text = str_replace( "\n", '\\n', addslashes( $safe_text ) );
3886 * Filters a string cleaned and escaped for output in JavaScript.
3888 * Text passed to esc_js() is stripped of invalid or special characters,
3889 * and properly slashed for output.
3893 * @param string $safe_text The text after it has been escaped.
3894 * @param string $text The text prior to being escaped.
3896 return apply_filters( 'js_escape', $safe_text, $text );
3900 * Escaping for HTML blocks.
3904 * @param string $text
3907 function esc_html( $text ) {
3908 $safe_text = wp_check_invalid_utf8( $text );
3909 $safe_text = _wp_specialchars( $safe_text, ENT_QUOTES );
3911 * Filters a string cleaned and escaped for output in HTML.
3913 * Text passed to esc_html() is stripped of invalid or special characters
3918 * @param string $safe_text The text after it has been escaped.
3919 * @param string $text The text prior to being escaped.
3921 return apply_filters( 'esc_html', $safe_text, $text );
3925 * Escaping for HTML attributes.
3929 * @param string $text
3932 function esc_attr( $text ) {
3933 $safe_text = wp_check_invalid_utf8( $text );
3934 $safe_text = _wp_specialchars( $safe_text, ENT_QUOTES );
3936 * Filters a string cleaned and escaped for output in an HTML attribute.
3938 * Text passed to esc_attr() is stripped of invalid or special characters
3943 * @param string $safe_text The text after it has been escaped.
3944 * @param string $text The text prior to being escaped.
3946 return apply_filters( 'attribute_escape', $safe_text, $text );
3950 * Escaping for textarea values.
3954 * @param string $text
3957 function esc_textarea( $text ) {
3958 $safe_text = htmlspecialchars( $text, ENT_QUOTES, get_option( 'blog_charset' ) );
3960 * Filters a string cleaned and escaped for output in a textarea element.
3964 * @param string $safe_text The text after it has been escaped.
3965 * @param string $text The text prior to being escaped.
3967 return apply_filters( 'esc_textarea', $safe_text, $text );
3971 * Escape an HTML tag name.
3975 * @param string $tag_name
3978 function tag_escape( $tag_name ) {
3979 $safe_tag = strtolower( preg_replace('/[^a-zA-Z0-9_:]/', '', $tag_name) );
3981 * Filters a string cleaned and escaped for output as an HTML tag.
3985 * @param string $safe_tag The tag name after it has been escaped.
3986 * @param string $tag_name The text before it was escaped.
3988 return apply_filters( 'tag_escape', $safe_tag, $tag_name );
3992 * Convert full URL paths to absolute paths.
3994 * Removes the http or https protocols and the domain. Keeps the path '/' at the
3995 * beginning, so it isn't a true relative link, but from the web root base.
3998 * @since 4.1.0 Support was added for relative URLs.
4000 * @param string $link Full URL path.
4001 * @return string Absolute path.
4003 function wp_make_link_relative( $link ) {
4004 return preg_replace( '|^(https?:)?//[^/]+(/?.*)|i', '$2', $link );
4008 * Sanitises various option values based on the nature of the option.
4010 * This is basically a switch statement which will pass $value through a number
4011 * of functions depending on the $option.
4015 * @global wpdb $wpdb WordPress database abstraction object.
4017 * @param string $option The name of the option.
4018 * @param string $value The unsanitised value.
4019 * @return string Sanitized value.
4021 function sanitize_option( $option, $value ) {
4024 $original_value = $value;
4027 switch ( $option ) {
4028 case 'admin_email' :
4029 case 'new_admin_email' :
4030 $value = $wpdb->strip_invalid_text_for_column( $wpdb->options, 'option_value', $value );
4031 if ( is_wp_error( $value ) ) {
4032 $error = $value->get_error_message();
4034 $value = sanitize_email( $value );
4035 if ( ! is_email( $value ) ) {
4036 $error = __( 'The email address entered did not appear to be a valid email address. Please enter a valid email address.' );
4041 case 'thumbnail_size_w':
4042 case 'thumbnail_size_h':
4043 case 'medium_size_w':
4044 case 'medium_size_h':
4045 case 'medium_large_size_w':
4046 case 'medium_large_size_h':
4047 case 'large_size_w':
4048 case 'large_size_h':
4049 case 'mailserver_port':
4050 case 'comment_max_links':
4051 case 'page_on_front':
4052 case 'page_for_posts':
4053 case 'rss_excerpt_length':
4054 case 'default_category':
4055 case 'default_email_category':
4056 case 'default_link_category':
4057 case 'close_comments_days_old':
4058 case 'comments_per_page':
4059 case 'thread_comments_depth':
4060 case 'users_can_register':
4061 case 'start_of_week':
4063 $value = absint( $value );
4066 case 'posts_per_page':
4067 case 'posts_per_rss':
4068 $value = (int) $value;
4069 if ( empty($value) )
4072 $value = abs($value);
4075 case 'default_ping_status':
4076 case 'default_comment_status':
4077 // Options that if not there have 0 value but need to be something like "closed"
4078 if ( $value == '0' || $value == '')
4082 case 'blogdescription':
4084 $value = $wpdb->strip_invalid_text_for_column( $wpdb->options, 'option_value', $value );
4085 if ( $value !== $original_value ) {
4086 $value = $wpdb->strip_invalid_text_for_column( $wpdb->options, 'option_value', wp_encode_emoji( $original_value ) );
4089 if ( is_wp_error( $value ) ) {
4090 $error = $value->get_error_message();
4092 $value = esc_html( $value );
4096 case 'blog_charset':
4097 $value = preg_replace('/[^a-zA-Z0-9_-]/', '', $value); // strips slashes
4101 // This is the value if the settings checkbox is not checked on POST. Don't rely on this.
4102 if ( null === $value )
4105 $value = intval( $value );
4110 case 'mailserver_url':
4111 case 'mailserver_login':
4112 case 'mailserver_pass':
4114 $value = $wpdb->strip_invalid_text_for_column( $wpdb->options, 'option_value', $value );
4115 if ( is_wp_error( $value ) ) {
4116 $error = $value->get_error_message();
4118 $value = strip_tags( $value );
4119 $value = wp_kses_data( $value );
4124 $value = explode( "\n", $value );
4125 $value = array_filter( array_map( 'trim', $value ) );
4126 $value = array_filter( array_map( 'esc_url_raw', $value ) );
4127 $value = implode( "\n", $value );
4131 $value = preg_replace('/[^0-9:.-]/', '', $value); // strips slashes
4135 $value = $wpdb->strip_invalid_text_for_column( $wpdb->options, 'option_value', $value );
4136 if ( is_wp_error( $value ) ) {
4137 $error = $value->get_error_message();
4139 if ( preg_match( '#http(s?)://(.+)#i', $value ) ) {
4140 $value = esc_url_raw( $value );
4142 $error = __( 'The WordPress address you entered did not appear to be a valid URL. Please enter a valid URL.' );
4148 $value = $wpdb->strip_invalid_text_for_column( $wpdb->options, 'option_value', $value );
4149 if ( is_wp_error( $value ) ) {
4150 $error = $value->get_error_message();
4152 if ( preg_match( '#http(s?)://(.+)#i', $value ) ) {
4153 $value = esc_url_raw( $value );
4155 $error = __( 'The Site address you entered did not appear to be a valid URL. Please enter a valid URL.' );
4161 $allowed = get_available_languages();
4162 if ( ! is_multisite() && defined( 'WPLANG' ) && '' !== WPLANG && 'en_US' !== WPLANG ) {
4163 $allowed[] = WPLANG;
4165 if ( ! in_array( $value, $allowed ) && ! empty( $value ) ) {
4166 $value = get_option( $option );
4170 case 'illegal_names':
4171 $value = $wpdb->strip_invalid_text_for_column( $wpdb->options, 'option_value', $value );
4172 if ( is_wp_error( $value ) ) {
4173 $error = $value->get_error_message();
4175 if ( ! is_array( $value ) )
4176 $value = explode( ' ', $value );
4178 $value = array_values( array_filter( array_map( 'trim', $value ) ) );
4185 case 'limited_email_domains':
4186 case 'banned_email_domains':
4187 $value = $wpdb->strip_invalid_text_for_column( $wpdb->options, 'option_value', $value );
4188 if ( is_wp_error( $value ) ) {
4189 $error = $value->get_error_message();
4191 if ( ! is_array( $value ) )
4192 $value = explode( "\n", $value );
4194 $domains = array_values( array_filter( array_map( 'trim', $value ) ) );
4197 foreach ( $domains as $domain ) {
4198 if ( ! preg_match( '/(--|\.\.)/', $domain ) && preg_match( '|^([a-zA-Z0-9-\.])+$|', $domain ) ) {
4207 case 'timezone_string':
4208 $allowed_zones = timezone_identifiers_list();
4209 if ( ! in_array( $value, $allowed_zones ) && ! empty( $value ) ) {
4210 $error = __( 'The timezone you have entered is not valid. Please select a valid timezone.' );
4214 case 'permalink_structure':
4215 case 'category_base':
4217 $value = $wpdb->strip_invalid_text_for_column( $wpdb->options, 'option_value', $value );
4218 if ( is_wp_error( $value ) ) {
4219 $error = $value->get_error_message();
4221 $value = esc_url_raw( $value );
4222 $value = str_replace( 'http://', '', $value );
4225 if ( 'permalink_structure' === $option && '' !== $value && ! preg_match( '/%[^\/%]+%/', $value ) ) {
4227 /* translators: %s: Codex URL */
4228 __( 'A structure tag is required when using custom permalinks. <a href="%s">Learn more</a>' ),
4229 __( 'https://codex.wordpress.org/Using_Permalinks#Choosing_your_permalink_structure' )
4234 case 'default_role' :
4235 if ( ! get_role( $value ) && get_role( 'subscriber' ) )
4236 $value = 'subscriber';
4239 case 'moderation_keys':
4240 case 'blacklist_keys':
4241 $value = $wpdb->strip_invalid_text_for_column( $wpdb->options, 'option_value', $value );
4242 if ( is_wp_error( $value ) ) {
4243 $error = $value->get_error_message();
4245 $value = explode( "\n", $value );
4246 $value = array_filter( array_map( 'trim', $value ) );
4247 $value = array_unique( $value );
4248 $value = implode( "\n", $value );
4253 if ( ! empty( $error ) ) {
4254 $value = get_option( $option );
4255 if ( function_exists( 'add_settings_error' ) ) {
4256 add_settings_error( $option, "invalid_{$option}", $error );
4261 * Filters an option value following sanitization.
4264 * @since 4.3.0 Added the `$original_value` parameter.
4266 * @param string $value The sanitized option value.
4267 * @param string $option The option name.
4268 * @param string $original_value The original value passed to the function.
4270 return apply_filters( "sanitize_option_{$option}", $value, $option, $original_value );
4274 * Maps a function to all non-iterable elements of an array or an object.
4276 * This is similar to `array_walk_recursive()` but acts upon objects too.
4280 * @param mixed $value The array, object, or scalar.
4281 * @param callable $callback The function to map onto $value.
4282 * @return mixed The value with the callback applied to all non-arrays and non-objects inside it.
4284 function map_deep( $value, $callback ) {
4285 if ( is_array( $value ) ) {
4286 foreach ( $value as $index => $item ) {
4287 $value[ $index ] = map_deep( $item, $callback );
4289 } elseif ( is_object( $value ) ) {
4290 $object_vars = get_object_vars( $value );
4291 foreach ( $object_vars as $property_name => $property_value ) {
4292 $value->$property_name = map_deep( $property_value, $callback );
4295 $value = call_user_func( $callback, $value );
4302 * Parses a string into variables to be stored in an array.
4304 * Uses {@link https://secure.php.net/parse_str parse_str()} and stripslashes if
4305 * {@link https://secure.php.net/magic_quotes magic_quotes_gpc} is on.
4309 * @param string $string The string to be parsed.
4310 * @param array $array Variables will be stored in this array.
4312 function wp_parse_str( $string, &$array ) {
4313 parse_str( $string, $array );
4314 if ( get_magic_quotes_gpc() )
4315 $array = stripslashes_deep( $array );
4317 * Filters the array of variables derived from a parsed string.
4321 * @param array $array The array populated with variables.
4323 $array = apply_filters( 'wp_parse_str', $array );
4327 * Convert lone less than signs.
4329 * KSES already converts lone greater than signs.
4333 * @param string $text Text to be converted.
4334 * @return string Converted text.
4336 function wp_pre_kses_less_than( $text ) {
4337 return preg_replace_callback('%<[^>]*?((?=<)|>|$)%', 'wp_pre_kses_less_than_callback', $text);
4341 * Callback function used by preg_replace.
4345 * @param array $matches Populated by matches to preg_replace.
4346 * @return string The text returned after esc_html if needed.
4348 function wp_pre_kses_less_than_callback( $matches ) {
4349 if ( false === strpos($matches[0], '>') )
4350 return esc_html($matches[0]);
4355 * WordPress implementation of PHP sprintf() with filters.
4358 * @link https://secure.php.net/sprintf
4360 * @param string $pattern The string which formatted args are inserted.
4361 * @param mixed $args ,... Arguments to be formatted into the $pattern string.
4362 * @return string The formatted string.
4364 function wp_sprintf( $pattern ) {
4365 $args = func_get_args();
4366 $len = strlen($pattern);
4370 while ( $len > $start ) {
4371 // Last character: append and break
4372 if ( strlen($pattern) - 1 == $start ) {
4373 $result .= substr($pattern, -1);
4377 // Literal %: append and continue
4378 if ( substr($pattern, $start, 2) == '%%' ) {
4384 // Get fragment before next %
4385 $end = strpos($pattern, '%', $start + 1);
4386 if ( false === $end )
4388 $fragment = substr($pattern, $start, $end - $start);
4390 // Fragment has a specifier
4391 if ( $pattern[$start] == '%' ) {
4392 // Find numbered arguments or take the next one in order
4393 if ( preg_match('/^%(\d+)\$/', $fragment, $matches) ) {
4394 $arg = isset($args[$matches[1]]) ? $args[$matches[1]] : '';
4395 $fragment = str_replace("%{$matches[1]}$", '%', $fragment);
4398 $arg = isset($args[$arg_index]) ? $args[$arg_index] : '';
4402 * Filters a fragment from the pattern passed to wp_sprintf().
4404 * If the fragment is unchanged, then sprintf() will be run on the fragment.
4408 * @param string $fragment A fragment from the pattern.
4409 * @param string $arg The argument.
4411 $_fragment = apply_filters( 'wp_sprintf', $fragment, $arg );
4412 if ( $_fragment != $fragment )
4413 $fragment = $_fragment;
4415 $fragment = sprintf($fragment, strval($arg) );
4418 // Append to result and move to next fragment
4419 $result .= $fragment;
4426 * Localize list items before the rest of the content.
4428 * The '%l' must be at the first characters can then contain the rest of the
4429 * content. The list items will have ', ', ', and', and ' and ' added depending
4430 * on the amount of list items in the $args parameter.
4434 * @param string $pattern Content containing '%l' at the beginning.
4435 * @param array $args List items to prepend to the content and replace '%l'.
4436 * @return string Localized list items and rest of the content.
4438 function wp_sprintf_l( $pattern, $args ) {
4440 if ( substr($pattern, 0, 2) != '%l' )
4443 // Nothing to work with
4448 * Filters the translated delimiters used by wp_sprintf_l().
4449 * Placeholders (%s) are included to assist translators and then
4450 * removed before the array of strings reaches the filter.
4452 * Please note: Ampersands and entities should be avoided here.
4456 * @param array $delimiters An array of translated delimiters.
4458 $l = apply_filters( 'wp_sprintf_l', array(
4459 /* translators: used to join items in a list with more than 2 items */
4460 'between' => sprintf( __('%s, %s'), '', '' ),
4461 /* translators: used to join last two items in a list with more than 2 times */
4462 'between_last_two' => sprintf( __('%s, and %s'), '', '' ),
4463 /* translators: used to join items in a list with only 2 items */
4464 'between_only_two' => sprintf( __('%s and %s'), '', '' ),
4467 $args = (array) $args;
4468 $result = array_shift($args);
4469 if ( count($args) == 1 )
4470 $result .= $l['between_only_two'] . array_shift($args);
4471 // Loop when more than two args
4474 $arg = array_shift($args);
4477 $result .= $l['between_last_two'] . $arg;
4479 $result .= $l['between'] . $arg;
4481 return $result . substr($pattern, 2);
4485 * Safely extracts not more than the first $count characters from html string.
4487 * UTF-8, tags and entities safe prefix extraction. Entities inside will *NOT*
4488 * be counted as one character. For example & will be counted as 4, < as
4493 * @param string $str String to get the excerpt from.
4494 * @param int $count Maximum number of characters to take.
4495 * @param string $more Optional. What to append if $str needs to be trimmed. Defaults to empty string.
4496 * @return string The excerpt.
4498 function wp_html_excerpt( $str, $count, $more = null ) {
4499 if ( null === $more )
4501 $str = wp_strip_all_tags( $str, true );
4502 $excerpt = mb_substr( $str, 0, $count );
4503 // remove part of an entity at the end
4504 $excerpt = preg_replace( '/&[^;\s]{0,6}$/', '', $excerpt );
4505 if ( $str != $excerpt )
4506 $excerpt = trim( $excerpt ) . $more;
4511 * Add a Base url to relative links in passed content.
4513 * By default it supports the 'src' and 'href' attributes. However this can be
4514 * changed via the 3rd param.
4518 * @global string $_links_add_base
4520 * @param string $content String to search for links in.
4521 * @param string $base The base URL to prefix to links.
4522 * @param array $attrs The attributes which should be processed.
4523 * @return string The processed content.
4525 function links_add_base_url( $content, $base, $attrs = array('src', 'href') ) {
4526 global $_links_add_base;
4527 $_links_add_base = $base;
4528 $attrs = implode('|', (array)$attrs);
4529 return preg_replace_callback( "!($attrs)=(['\"])(.+?)\\2!i", '_links_add_base', $content );
4533 * Callback to add a base url to relative links in passed content.
4538 * @global string $_links_add_base
4540 * @param string $m The matched link.
4541 * @return string The processed link.
4543 function _links_add_base( $m ) {
4544 global $_links_add_base;
4545 //1 = attribute name 2 = quotation mark 3 = URL
4546 return $m[1] . '=' . $m[2] .
4547 ( preg_match( '#^(\w{1,20}):#', $m[3], $protocol ) && in_array( $protocol[1], wp_allowed_protocols() ) ?
4549 WP_Http::make_absolute_url( $m[3], $_links_add_base )
4555 * Adds a Target attribute to all links in passed content.
4557 * This function by default only applies to `<a>` tags, however this can be
4558 * modified by the 3rd param.
4560 * *NOTE:* Any current target attributed will be stripped and replaced.
4564 * @global string $_links_add_target
4566 * @param string $content String to search for links in.
4567 * @param string $target The Target to add to the links.
4568 * @param array $tags An array of tags to apply to.
4569 * @return string The processed content.
4571 function links_add_target( $content, $target = '_blank', $tags = array('a') ) {
4572 global $_links_add_target;
4573 $_links_add_target = $target;
4574 $tags = implode('|', (array)$tags);
4575 return preg_replace_callback( "!<($tags)([^>]*)>!i", '_links_add_target', $content );
4579 * Callback to add a target attribute to all links in passed content.
4584 * @global string $_links_add_target
4586 * @param string $m The matched link.
4587 * @return string The processed link.
4589 function _links_add_target( $m ) {
4590 global $_links_add_target;
4592 $link = preg_replace('|( target=([\'"])(.*?)\2)|i', '', $m[2]);
4593 return '<' . $tag . $link . ' target="' . esc_attr( $_links_add_target ) . '">';
4597 * Normalize EOL characters and strip duplicate whitespace.
4601 * @param string $str The string to normalize.
4602 * @return string The normalized string.
4604 function normalize_whitespace( $str ) {
4605 $str = trim( $str );
4606 $str = str_replace( "\r", "\n", $str );
4607 $str = preg_replace( array( '/\n+/', '/[ \t]+/' ), array( "\n", ' ' ), $str );
4612 * Properly strip all HTML tags including script and style
4614 * This differs from strip_tags() because it removes the contents of
4615 * the `<script>` and `<style>` tags. E.g. `strip_tags( '<script>something</script>' )`
4616 * will return 'something'. wp_strip_all_tags will return ''
4620 * @param string $string String containing HTML tags
4621 * @param bool $remove_breaks Optional. Whether to remove left over line breaks and white space chars
4622 * @return string The processed string.
4624 function wp_strip_all_tags($string, $remove_breaks = false) {
4625 $string = preg_replace( '@<(script|style)[^>]*?>.*?</\\1>@si', '', $string );
4626 $string = strip_tags($string);
4628 if ( $remove_breaks )
4629 $string = preg_replace('/[\r\n\t ]+/', ' ', $string);
4631 return trim( $string );
4635 * Sanitizes a string from user input or from the database.
4637 * - Checks for invalid UTF-8,
4638 * - Converts single `<` characters to entities
4640 * - Removes line breaks, tabs, and extra whitespace
4645 * @see wp_check_invalid_utf8()
4646 * @see wp_strip_all_tags()
4648 * @param string $str String to sanitize.
4649 * @return string Sanitized string.
4651 function sanitize_text_field( $str ) {
4652 $filtered = wp_check_invalid_utf8( $str );
4654 if ( strpos($filtered, '<') !== false ) {
4655 $filtered = wp_pre_kses_less_than( $filtered );
4656 // This will strip extra whitespace for us.
4657 $filtered = wp_strip_all_tags( $filtered, true );
4659 $filtered = trim( preg_replace('/[\r\n\t ]+/', ' ', $filtered) );
4663 while ( preg_match('/%[a-f0-9]{2}/i', $filtered, $match) ) {
4664 $filtered = str_replace($match[0], '', $filtered);
4669 // Strip out the whitespace that may now exist after removing the octets.
4670 $filtered = trim( preg_replace('/ +/', ' ', $filtered) );
4674 * Filters a sanitized text field string.
4678 * @param string $filtered The sanitized string.
4679 * @param string $str The string prior to being sanitized.
4681 return apply_filters( 'sanitize_text_field', $filtered, $str );
4685 * i18n friendly version of basename()
4689 * @param string $path A path.
4690 * @param string $suffix If the filename ends in suffix this will also be cut off.
4693 function wp_basename( $path, $suffix = '' ) {
4694 return urldecode( basename( str_replace( array( '%2F', '%5C' ), '/', urlencode( $path ) ), $suffix ) );
4698 * Forever eliminate "Wordpress" from the planet (or at least the little bit we can influence).
4700 * Violating our coding standards for a good function name.
4704 * @staticvar string|false $dblq
4706 * @param string $text The text to be modified.
4707 * @return string The modified text.
4709 function capital_P_dangit( $text ) {
4710 // Simple replacement for titles
4711 $current_filter = current_filter();
4712 if ( 'the_title' === $current_filter || 'wp_title' === $current_filter )
4713 return str_replace( 'Wordpress', 'WordPress', $text );
4714 // Still here? Use the more judicious replacement
4715 static $dblq = false;
4716 if ( false === $dblq ) {
4717 $dblq = _x( '“', 'opening curly double quote' );
4720 array( ' Wordpress', '‘Wordpress', $dblq . 'Wordpress', '>Wordpress', '(Wordpress' ),
4721 array( ' WordPress', '‘WordPress', $dblq . 'WordPress', '>WordPress', '(WordPress' ),
4726 * Sanitize a mime type
4730 * @param string $mime_type Mime type
4731 * @return string Sanitized mime type
4733 function sanitize_mime_type( $mime_type ) {
4734 $sani_mime_type = preg_replace( '/[^-+*.a-zA-Z0-9\/]/', '', $mime_type );
4736 * Filters a mime type following sanitization.
4740 * @param string $sani_mime_type The sanitized mime type.
4741 * @param string $mime_type The mime type prior to sanitization.
4743 return apply_filters( 'sanitize_mime_type', $sani_mime_type, $mime_type );
4747 * Sanitize space or carriage return separated URLs that are used to send trackbacks.
4751 * @param string $to_ping Space or carriage return separated URLs
4752 * @return string URLs starting with the http or https protocol, separated by a carriage return.
4754 function sanitize_trackback_urls( $to_ping ) {
4755 $urls_to_ping = preg_split( '/[\r\n\t ]/', trim( $to_ping ), -1, PREG_SPLIT_NO_EMPTY );
4756 foreach ( $urls_to_ping as $k => $url ) {
4757 if ( !preg_match( '#^https?://.#i', $url ) )
4758 unset( $urls_to_ping[$k] );
4760 $urls_to_ping = array_map( 'esc_url_raw', $urls_to_ping );
4761 $urls_to_ping = implode( "\n", $urls_to_ping );
4763 * Filters a list of trackback URLs following sanitization.
4765 * The string returned here consists of a space or carriage return-delimited list
4766 * of trackback URLs.
4770 * @param string $urls_to_ping Sanitized space or carriage return separated URLs.
4771 * @param string $to_ping Space or carriage return separated URLs before sanitization.
4773 return apply_filters( 'sanitize_trackback_urls', $urls_to_ping, $to_ping );
4777 * Add slashes to a string or array of strings.
4779 * This should be used when preparing data for core API that expects slashed data.
4780 * This should not be used to escape data going directly into an SQL query.
4784 * @param string|array $value String or array of strings to slash.
4785 * @return string|array Slashed $value
4787 function wp_slash( $value ) {
4788 if ( is_array( $value ) ) {
4789 foreach ( $value as $k => $v ) {
4790 if ( is_array( $v ) ) {
4791 $value[$k] = wp_slash( $v );
4793 $value[$k] = addslashes( $v );
4797 $value = addslashes( $value );
4804 * Remove slashes from a string or array of strings.
4806 * This should be used to remove slashes from data passed to core API that
4807 * expects data to be unslashed.
4811 * @param string|array $value String or array of strings to unslash.
4812 * @return string|array Unslashed $value
4814 function wp_unslash( $value ) {
4815 return stripslashes_deep( $value );
4819 * Extract and return the first URL from passed content.
4823 * @param string $content A string which might contain a URL.
4824 * @return string|false The found URL.
4826 function get_url_in_content( $content ) {
4827 if ( empty( $content ) ) {
4831 if ( preg_match( '/<a\s[^>]*?href=([\'"])(.+?)\1/is', $content, $matches ) ) {
4832 return esc_url_raw( $matches[2] );
4839 * Returns the regexp for common whitespace characters.
4841 * By default, spaces include new lines, tabs, nbsp entities, and the UTF-8 nbsp.
4842 * This is designed to replace the PCRE \s sequence. In ticket #22692, that
4843 * sequence was found to be unreliable due to random inclusion of the A0 byte.
4847 * @staticvar string $spaces
4849 * @return string The spaces regexp.
4851 function wp_spaces_regexp() {
4852 static $spaces = '';
4854 if ( empty( $spaces ) ) {
4856 * Filters the regexp for common whitespace characters.
4858 * This string is substituted for the \s sequence as needed in regular
4859 * expressions. For websites not written in English, different characters
4860 * may represent whitespace. For websites not encoded in UTF-8, the 0xC2 0xA0
4861 * sequence may not be in use.
4865 * @param string $spaces Regexp pattern for matching common whitespace characters.
4867 $spaces = apply_filters( 'wp_spaces_regexp', '[\r\n\t ]|\xC2\xA0| ' );
4874 * Print the important emoji-related styles.
4878 * @staticvar bool $printed
4880 function print_emoji_styles() {
4881 static $printed = false;
4889 <style type="text/css">
4892 display: inline !important;
4893 border: none !important;
4894 box-shadow: none !important;
4895 height: 1em !important;
4896 width: 1em !important;
4897 margin: 0 .07em !important;
4898 vertical-align: -0.1em !important;
4899 background: none !important;
4900 padding: 0 !important;
4907 * Print the inline Emoji detection script if it is not already printed.
4910 * @staticvar bool $printed
4912 function print_emoji_detection_script() {
4913 static $printed = false;
4921 _print_emoji_detection_script();
4925 * Prints inline Emoji dection script
4931 * @global string $wp_version WordPress version string.
4933 function _print_emoji_detection_script() {
4938 * Filters the URL where emoji png images are hosted.
4942 * @param string The emoji base URL for png images.
4944 'baseUrl' => apply_filters( 'emoji_url', 'https://s.w.org/images/core/emoji/2/72x72/' ),
4947 * Filters the extension of the emoji png files.
4951 * @param string The emoji extension for png files. Default .png.
4953 'ext' => apply_filters( 'emoji_ext', '.png' ),
4956 * Filters the URL where emoji SVG images are hosted.
4960 * @param string The emoji base URL for svg images.
4962 'svgUrl' => apply_filters( 'emoji_svg_url', 'https://s.w.org/images/core/emoji/2/svg/' ),
4965 * Filters the extension of the emoji SVG files.
4969 * @param string The emoji extension for svg files. Default .svg.
4971 'svgExt' => apply_filters( 'emoji_svg_ext', '.svg' ),
4974 $version = 'ver=' . $wp_version;
4976 if ( SCRIPT_DEBUG ) {
4977 $settings['source'] = array(
4978 /** This filter is documented in wp-includes/class.wp-scripts.php */
4979 'wpemoji' => apply_filters( 'script_loader_src', includes_url( "js/wp-emoji.js?$version" ), 'wpemoji' ),
4980 /** This filter is documented in wp-includes/class.wp-scripts.php */
4981 'twemoji' => apply_filters( 'script_loader_src', includes_url( "js/twemoji.js?$version" ), 'twemoji' ),
4985 <script type="text/javascript">
4986 window._wpemojiSettings = <?php echo wp_json_encode( $settings ); ?>;
4987 <?php readfile( ABSPATH . WPINC . "/js/wp-emoji-loader.js" ); ?>
4991 $settings['source'] = array(
4992 /** This filter is documented in wp-includes/class.wp-scripts.php */
4993 'concatemoji' => apply_filters( 'script_loader_src', includes_url( "js/wp-emoji-release.min.js?$version" ), 'concatemoji' ),
4997 * If you're looking at a src version of this file, you'll see an "include"
4998 * statement below. This is used by the `grunt build` process to directly
4999 * include a minified version of wp-emoji-loader.js, instead of using the
5000 * readfile() method from above.
5002 * If you're looking at a build version of this file, you'll see a string of
5003 * minified JavaScript. If you need to debug it, please turn on SCRIPT_DEBUG
5004 * and edit wp-emoji-loader.js directly.
5007 <script type="text/javascript">
5008 window._wpemojiSettings = <?php echo wp_json_encode( $settings ); ?>;
5009 !function(a,b,c){function d(a){var c,d,e,f,g,h=b.createElement("canvas"),i=h.getContext&&h.getContext("2d"),j=String.fromCharCode;if(!i||!i.fillText)return!1;switch(i.textBaseline="top",i.font="600 32px Arial",a){case"flag":return i.fillText(j(55356,56806,55356,56826),0,0),!(h.toDataURL().length<3e3)&&(i.clearRect(0,0,h.width,h.height),i.fillText(j(55356,57331,65039,8205,55356,57096),0,0),c=h.toDataURL(),i.clearRect(0,0,h.width,h.height),i.fillText(j(55356,57331,55356,57096),0,0),d=h.toDataURL(),c!==d);case"diversity":return i.fillText(j(55356,57221),0,0),e=i.getImageData(16,16,1,1).data,f=e[0]+","+e[1]+","+e[2]+","+e[3],i.fillText(j(55356,57221,55356,57343),0,0),e=i.getImageData(16,16,1,1).data,g=e[0]+","+e[1]+","+e[2]+","+e[3],f!==g;case"simple":return i.fillText(j(55357,56835),0,0),0!==i.getImageData(16,16,1,1).data[0];case"unicode8":return i.fillText(j(55356,57135),0,0),0!==i.getImageData(16,16,1,1).data[0];case"unicode9":return i.fillText(j(55358,56631),0,0),0!==i.getImageData(16,16,1,1).data[0]}return!1}function e(a){var c=b.createElement("script");c.src=a,c.type="text/javascript",b.getElementsByTagName("head")[0].appendChild(c)}var f,g,h,i;for(i=Array("simple","flag","unicode8","diversity","unicode9"),c.supports={everything:!0,everythingExceptFlag:!0},h=0;h<i.length;h++)c.supports[i[h]]=d(i[h]),c.supports.everything=c.supports.everything&&c.supports[i[h]],"flag"!==i[h]&&(c.supports.everythingExceptFlag=c.supports.everythingExceptFlag&&c.supports[i[h]]);c.supports.everythingExceptFlag=c.supports.everythingExceptFlag&&!c.supports.flag,c.DOMReady=!1,c.readyCallback=function(){c.DOMReady=!0},c.supports.everything||(g=function(){c.readyCallback()},b.addEventListener?(b.addEventListener("DOMContentLoaded",g,!1),a.addEventListener("load",g,!1)):(a.attachEvent("onload",g),b.attachEvent("onreadystatechange",function(){"complete"===b.readyState&&c.readyCallback()})),f=c.source||{},f.concatemoji?e(f.concatemoji):f.wpemoji&&f.twemoji&&(e(f.twemoji),e(f.wpemoji)))}(window,document,window._wpemojiSettings);
5016 * Convert any 4 byte emoji in a string to their equivalent HTML entity.
5018 * Currently, only Unicode 7 emoji are supported. Skin tone modifiers are allowed,
5019 * all other Unicode 8 emoji will be added when the spec is finalised.
5021 * This allows us to store emoji in a DB using the utf8 character set.
5025 * @param string $content The content to encode.
5026 * @return string The encoded content.
5028 function wp_encode_emoji( $content ) {
5029 if ( function_exists( 'mb_convert_encoding' ) ) {
5031 \x23\xE2\x83\xA3 # Digits
5032 [\x30-\x39]\xE2\x83\xA3
5033 | \xF0\x9F[\x85-\x88][\xA6-\xBF] # Enclosed characters
5034 | \xF0\x9F[\x8C-\x97][\x80-\xBF] # Misc
5035 | \xF0\x9F\x98[\x80-\xBF] # Smilies
5036 | \xF0\x9F\x99[\x80-\x8F]
5037 | \xF0\x9F\x9A[\x80-\xBF] # Transport and map symbols
5041 if ( preg_match_all( $regex, $content, $matches ) ) {
5042 if ( ! empty( $matches[1] ) ) {
5043 foreach ( $matches[1] as $emoji ) {
5045 * UTF-32's hex encoding is the same as HTML's hex encoding.
5046 * So, by converting the emoji from UTF-8 to UTF-32, we magically
5047 * get the correct hex encoding.
5049 $unpacked = unpack( 'H*', mb_convert_encoding( $emoji, 'UTF-32', 'UTF-8' ) );
5050 if ( isset( $unpacked[1] ) ) {
5051 $entity = '&#x' . ltrim( $unpacked[1], '0' ) . ';';
5052 $content = str_replace( $emoji, $entity, $content );
5063 * Convert emoji to a static img element.
5067 * @param string $text The content to encode.
5068 * @return string The encoded content.
5070 function wp_staticize_emoji( $text ) {
5071 $text = wp_encode_emoji( $text );
5073 /** This filter is documented in wp-includes/formatting.php */
5074 $cdn_url = apply_filters( 'emoji_url', 'https://s.w.org/images/core/emoji/2/72x72/' );
5076 /** This filter is documented in wp-includes/formatting.php */
5077 $ext = apply_filters( 'emoji_ext', '.png' );
5081 * HTML loop taken from smiley function, which was taken from texturize function.
5082 * It'll never be consolidated.
5084 * First, capture the tags as well as in between.
5086 $textarr = preg_split( '/(<.*>)/U', $text, -1, PREG_SPLIT_DELIM_CAPTURE );
5087 $stop = count( $textarr );
5089 // Ignore processing of specific tags.
5090 $tags_to_ignore = 'code|pre|style|script|textarea';
5091 $ignore_block_element = '';
5093 for ( $i = 0; $i < $stop; $i++ ) {
5094 $content = $textarr[$i];
5096 // If we're in an ignore block, wait until we find its closing tag.
5097 if ( '' == $ignore_block_element && preg_match( '/^<(' . $tags_to_ignore . ')>/', $content, $matches ) ) {
5098 $ignore_block_element = $matches[1];
5101 // If it's not a tag and not in ignore block.
5102 if ( '' == $ignore_block_element && strlen( $content ) > 0 && '<' != $content[0] ) {
5104 if ( preg_match_all( '/(DZ(e[6-9a-f]|f[0-9a-f]);){2}/', $content, $matches ) ) {
5105 if ( ! empty( $matches[0] ) ) {
5106 foreach ( $matches[0] as $flag ) {
5107 $chars = str_replace( array( '&#x', ';'), '', $flag );
5109 list( $char1, $char2 ) = str_split( $chars, 5 );
5110 $entity = sprintf( '<img src="%s" alt="%s" class="wp-smiley" style="height: 1em; max-height: 1em;" />', $cdn_url . $char1 . '-' . $char2 . $ext, html_entity_decode( $flag ) );
5112 $content = str_replace( $flag, $entity, $content );
5117 // Loosely match the Emoji Unicode range.
5118 $regex = '/(&#x[2-3][0-9a-f]{3};|[1-6][0-9a-f]{2};)/';
5121 if ( preg_match_all( $regex, $content, $matches ) ) {
5122 if ( ! empty( $matches[1] ) ) {
5123 foreach ( $matches[1] as $emoji ) {
5124 $char = str_replace( array( '&#x', ';'), '', $emoji );
5125 $entity = sprintf( '<img src="%s" alt="%s" class="wp-smiley" style="height: 1em; max-height: 1em;" />', $cdn_url . $char . $ext, html_entity_decode( $emoji ) );
5127 $content = str_replace( $emoji, $entity, $content );
5133 // Did we exit ignore block.
5134 if ( '' != $ignore_block_element && '</' . $ignore_block_element . '>' == $content ) {
5135 $ignore_block_element = '';
5138 $output .= $content;
5145 * Convert emoji in emails into static images.
5149 * @param array $mail The email data array.
5150 * @return array The email data array, with emoji in the message staticized.
5152 function wp_staticize_emoji_for_email( $mail ) {
5153 if ( ! isset( $mail['message'] ) ) {
5158 * We can only transform the emoji into images if it's a text/html email.
5159 * To do that, here's a cut down version of the same process that happens
5160 * in wp_mail() - get the Content-Type from the headers, if there is one,
5161 * then pass it through the wp_mail_content_type filter, in case a plugin
5162 * is handling changing the Content-Type.
5165 if ( isset( $mail['headers'] ) ) {
5166 if ( is_array( $mail['headers'] ) ) {
5167 $headers = $mail['headers'];
5169 $headers = explode( "\n", str_replace( "\r\n", "\n", $mail['headers'] ) );
5173 foreach ( $headers as $header ) {
5174 if ( strpos($header, ':') === false ) {
5178 // Explode them out.
5179 list( $name, $content ) = explode( ':', trim( $header ), 2 );
5182 $name = trim( $name );
5183 $content = trim( $content );
5185 if ( 'content-type' === strtolower( $name ) ) {
5186 if ( strpos( $content, ';' ) !== false ) {
5187 list( $type, $charset ) = explode( ';', $content );
5188 $content_type = trim( $type );
5190 $content_type = trim( $content );
5196 // Set Content-Type if we don't have a content-type from the input headers.
5197 if ( ! isset( $content_type ) ) {
5198 $content_type = 'text/plain';
5201 /** This filter is documented in wp-includes/pluggable.php */
5202 $content_type = apply_filters( 'wp_mail_content_type', $content_type );
5204 if ( 'text/html' === $content_type ) {
5205 $mail['message'] = wp_staticize_emoji( $mail['message'] );
5212 * Shorten a URL, to be used as link text.
5215 * @since 4.4.0 Moved to wp-includes/formatting.php from wp-admin/includes/misc.php and added $length param.
5217 * @param string $url URL to shorten.
5218 * @param int $length Optional. Maximum length of the shortened URL. Default 35 characters.
5219 * @return string Shortened URL.
5221 function url_shorten( $url, $length = 35 ) {
5222 $stripped = str_replace( array( 'https://', 'http://', 'www.' ), '', $url );
5223 $short_url = untrailingslashit( $stripped );
5225 if ( strlen( $short_url ) > $length ) {
5226 $short_url = substr( $short_url, 0, $length - 3 ) . '…';
5232 * Sanitizes a hex color.
5234 * Returns either '', a 3 or 6 digit hex color (with #), or nothing.
5235 * For sanitizing values without a #, see sanitize_hex_color_no_hash().
5239 * @param string $color
5240 * @return string|void
5242 function sanitize_hex_color( $color ) {
5243 if ( '' === $color ) {
5247 // 3 or 6 hex digits, or the empty string.
5248 if ( preg_match('|^#([A-Fa-f0-9]{3}){1,2}$|', $color ) ) {
5254 * Sanitizes a hex color without a hash. Use sanitize_hex_color() when possible.
5256 * Saving hex colors without a hash puts the burden of adding the hash on the
5257 * UI, which makes it difficult to use or upgrade to other color types such as
5258 * rgba, hsl, rgb, and html color names.
5260 * Returns either '', a 3 or 6 digit hex color (without a #), or null.
5264 * @param string $color
5265 * @return string|null
5267 function sanitize_hex_color_no_hash( $color ) {
5268 $color = ltrim( $color, '#' );
5270 if ( '' === $color ) {
5274 return sanitize_hex_color( '#' . $color ) ? $color : null;
5278 * Ensures that any hex color is properly hashed.
5279 * Otherwise, returns value untouched.
5281 * This method should only be necessary if using sanitize_hex_color_no_hash().
5285 * @param string $color
5288 function maybe_hash_hex_color( $color ) {
5289 if ( $unhashed = sanitize_hex_color_no_hash( $color ) ) {
5290 return '#' . $unhashed;