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.
24 * @uses $wp_cockneyreplace Array of formatted entities for certain common phrases
26 * @param string $text The text to be formatted
27 * @return string The string replaced with html entities
29 function wptexturize($text) {
30 global $wp_cockneyreplace;
31 static $static_characters, $static_replacements, $dynamic_characters, $dynamic_replacements,
32 $default_no_texturize_tags, $default_no_texturize_shortcodes;
34 // No need to set up these static variables more than once
35 if ( ! isset( $static_characters ) ) {
36 /* translators: opening curly double quote */
37 $opening_quote = _x( '“', 'opening curly double quote' );
38 /* translators: closing curly double quote */
39 $closing_quote = _x( '”', 'closing curly double quote' );
41 /* translators: apostrophe, for example in 'cause or can't */
42 $apos = _x( '’', 'apostrophe' );
44 /* translators: prime, for example in 9' (nine feet) */
45 $prime = _x( '′', 'prime' );
46 /* translators: double prime, for example in 9" (nine inches) */
47 $double_prime = _x( '″', 'double prime' );
49 /* translators: opening curly single quote */
50 $opening_single_quote = _x( '‘', 'opening curly single quote' );
51 /* translators: closing curly single quote */
52 $closing_single_quote = _x( '’', 'closing curly single quote' );
54 /* translators: en dash */
55 $en_dash = _x( '–', 'en dash' );
56 /* translators: em dash */
57 $em_dash = _x( '—', 'em dash' );
59 $default_no_texturize_tags = array('pre', 'code', 'kbd', 'style', 'script', 'tt');
60 $default_no_texturize_shortcodes = array('code');
62 // if a plugin has provided an autocorrect array, use it
63 if ( isset($wp_cockneyreplace) ) {
64 $cockney = array_keys($wp_cockneyreplace);
65 $cockneyreplace = array_values($wp_cockneyreplace);
66 } elseif ( "'" != $apos ) { // Only bother if we're doing a replacement.
67 $cockney = array( "'tain't", "'twere", "'twas", "'tis", "'twill", "'til", "'bout", "'nuff", "'round", "'cause" );
68 $cockneyreplace = array( $apos . "tain" . $apos . "t", $apos . "twere", $apos . "twas", $apos . "tis", $apos . "twill", $apos . "til", $apos . "bout", $apos . "nuff", $apos . "round", $apos . "cause" );
70 $cockney = $cockneyreplace = array();
73 $static_characters = array_merge( array( '---', ' -- ', '--', ' - ', 'xn–', '...', '``', '\'\'', ' (tm)' ), $cockney );
74 $static_replacements = array_merge( array( $em_dash, ' ' . $em_dash . ' ', $en_dash, ' ' . $en_dash . ' ', 'xn--', '…', $opening_quote, $closing_quote, ' ™' ), $cockneyreplace );
78 $dynamic[ '/\'(\d\d(?:’|\')?s)/' ] = $apos . '$1'; // '99's
79 $dynamic[ '/\'(\d)/' ] = $apos . '$1'; // '99
81 if ( "'" != $opening_single_quote )
82 $dynamic[ '/(\s|\A|[([{<]|")\'/' ] = '$1' . $opening_single_quote; // opening single quote, even after (, {, <, [
83 if ( '"' != $double_prime )
84 $dynamic[ '/(\d)"/' ] = '$1' . $double_prime; // 9" (double prime)
86 $dynamic[ '/(\d)\'/' ] = '$1' . $prime; // 9' (prime)
88 $dynamic[ '/(\S)\'([^\'\s])/' ] = '$1' . $apos . '$2'; // apostrophe in a word
89 if ( '"' != $opening_quote )
90 $dynamic[ '/(\s|\A|[([{<])"(?!\s)/' ] = '$1' . $opening_quote . '$2'; // opening double quote, even after (, {, <, [
91 if ( '"' != $closing_quote )
92 $dynamic[ '/"(\s|\S|\Z)/' ] = $closing_quote . '$1'; // closing double quote
93 if ( "'" != $closing_single_quote )
94 $dynamic[ '/\'([\s.]|\Z)/' ] = $closing_single_quote . '$1'; // closing single quote
96 $dynamic[ '/\b(\d+)x(\d+)\b/' ] = '$1×$2'; // 9x9 (times)
98 $dynamic_characters = array_keys( $dynamic );
99 $dynamic_replacements = array_values( $dynamic );
102 // Transform into regexp sub-expression used in _wptexturize_pushpop_element
103 // Must do this every time in case plugins use these filters in a context sensitive manner
104 $no_texturize_tags = '(' . implode('|', apply_filters('no_texturize_tags', $default_no_texturize_tags) ) . ')';
105 $no_texturize_shortcodes = '(' . implode('|', apply_filters('no_texturize_shortcodes', $default_no_texturize_shortcodes) ) . ')';
107 $no_texturize_tags_stack = array();
108 $no_texturize_shortcodes_stack = array();
110 $textarr = preg_split('/(<.*>|\[.*\])/Us', $text, -1, PREG_SPLIT_DELIM_CAPTURE);
112 foreach ( $textarr as &$curl ) {
113 if ( empty( $curl ) )
116 // Only call _wptexturize_pushpop_element if first char is correct tag opening
118 if ( '<' === $first ) {
119 _wptexturize_pushpop_element($curl, $no_texturize_tags_stack, $no_texturize_tags, '<', '>');
120 } elseif ( '[' === $first ) {
121 _wptexturize_pushpop_element($curl, $no_texturize_shortcodes_stack, $no_texturize_shortcodes, '[', ']');
122 } elseif ( empty($no_texturize_shortcodes_stack) && empty($no_texturize_tags_stack) ) {
123 // This is not a tag, nor is the texturization disabled static strings
124 $curl = str_replace($static_characters, $static_replacements, $curl);
125 // regular expressions
126 $curl = preg_replace($dynamic_characters, $dynamic_replacements, $curl);
128 $curl = preg_replace('/&([^#])(?![a-zA-Z1-4]{1,8};)/', '&$1', $curl);
130 return implode( '', $textarr );
134 * Search for disabled element tags. Push element to stack on tag open and pop
135 * on tag close. Assumes first character of $text is tag opening.
140 * @param string $text Text to check. First character is assumed to be $opening
141 * @param array $stack Array used as stack of opened tag elements
142 * @param string $disabled_elements Tags to match against formatted as regexp sub-expression
143 * @param string $opening Tag opening character, assumed to be 1 character long
144 * @param string $closing Tag closing character
146 function _wptexturize_pushpop_element($text, &$stack, $disabled_elements, $opening = '<', $closing = '>') {
147 // Check if it is a closing tag -- otherwise assume opening tag
148 if (strncmp($opening . '/', $text, 2)) {
149 // Opening? Check $text+1 against disabled elements
150 if (preg_match('/^' . $disabled_elements . '\b/', substr($text, 1), $matches)) {
152 * This disables texturize until we find a closing tag of our type
153 * (e.g. <pre>) even if there was invalid nesting before that
155 * Example: in the case <pre>sadsadasd</code>"baba"</pre>
156 * "baba" won't be texturize
159 array_push($stack, $matches[1]);
162 // Closing? Check $text+2 against disabled elements
163 $c = preg_quote($closing, '/');
164 if (preg_match('/^' . $disabled_elements . $c . '/', substr($text, 2), $matches)) {
165 $last = array_pop($stack);
167 // Make sure it matches the opening tag
168 if ($last != $matches[1])
169 array_push($stack, $last);
175 * Replaces double line-breaks with paragraph elements.
177 * A group of regex replaces used to identify text formatted with newlines and
178 * replace double line-breaks with HTML paragraph tags. The remaining
179 * line-breaks after conversion become <<br />> tags, unless $br is set to '0'
184 * @param string $pee The text which has to be formatted.
185 * @param bool $br Optional. If set, this will convert all remaining line-breaks after paragraphing. Default true.
186 * @return string Text which has been converted into correct paragraph tags.
188 function wpautop($pee, $br = true) {
191 if ( trim($pee) === '' )
194 $pee = $pee . "\n"; // just to make things a little easier, pad the end
196 if ( strpos($pee, '<pre') !== false ) {
197 $pee_parts = explode( '</pre>', $pee );
198 $last_pee = array_pop($pee_parts);
202 foreach ( $pee_parts as $pee_part ) {
203 $start = strpos($pee_part, '<pre');
206 if ( $start === false ) {
211 $name = "<pre wp-pre-tag-$i></pre>";
212 $pre_tags[$name] = substr( $pee_part, $start ) . '</pre>';
214 $pee .= substr( $pee_part, 0, $start ) . $name;
221 $pee = preg_replace('|<br />\s*<br />|', "\n\n", $pee);
222 // Space things out a little
223 $allblocks = '(?:table|thead|tfoot|caption|col|colgroup|tbody|tr|td|th|div|dl|dd|dt|ul|ol|li|pre|select|option|form|map|area|blockquote|address|math|style|p|h[1-6]|hr|fieldset|noscript|legend|section|article|aside|hgroup|header|footer|nav|figure|figcaption|details|menu|summary)';
224 $pee = preg_replace('!(<' . $allblocks . '[^>]*>)!', "\n$1", $pee);
225 $pee = preg_replace('!(</' . $allblocks . '>)!', "$1\n\n", $pee);
226 $pee = str_replace(array("\r\n", "\r"), "\n", $pee); // cross-platform newlines
227 if ( strpos($pee, '<object') !== false ) {
228 $pee = preg_replace('|\s*<param([^>]*)>\s*|', "<param$1>", $pee); // no pee inside object/embed
229 $pee = preg_replace('|\s*</embed>\s*|', '</embed>', $pee);
231 $pee = preg_replace("/\n\n+/", "\n\n", $pee); // take care of duplicates
232 // make paragraphs, including one at the end
233 $pees = preg_split('/\n\s*\n/', $pee, -1, PREG_SPLIT_NO_EMPTY);
235 foreach ( $pees as $tinkle )
236 $pee .= '<p>' . trim($tinkle, "\n") . "</p>\n";
237 $pee = preg_replace('|<p>\s*</p>|', '', $pee); // under certain strange conditions it could create a P of entirely whitespace
238 $pee = preg_replace('!<p>([^<]+)</(div|address|form)>!', "<p>$1</p></$2>", $pee);
239 $pee = preg_replace('!<p>\s*(</?' . $allblocks . '[^>]*>)\s*</p>!', "$1", $pee); // don't pee all over a tag
240 $pee = preg_replace("|<p>(<li.+?)</p>|", "$1", $pee); // problem with nested lists
241 $pee = preg_replace('|<p><blockquote([^>]*)>|i', "<blockquote$1><p>", $pee);
242 $pee = str_replace('</blockquote></p>', '</p></blockquote>', $pee);
243 $pee = preg_replace('!<p>\s*(</?' . $allblocks . '[^>]*>)!', "$1", $pee);
244 $pee = preg_replace('!(</?' . $allblocks . '[^>]*>)\s*</p>!', "$1", $pee);
246 $pee = preg_replace_callback('/<(script|style).*?<\/\\1>/s', '_autop_newline_preservation_helper', $pee);
247 $pee = preg_replace('|(?<!<br />)\s*\n|', "<br />\n", $pee); // optionally make line breaks
248 $pee = str_replace('<WPPreserveNewline />', "\n", $pee);
250 $pee = preg_replace('!(</?' . $allblocks . '[^>]*>)\s*<br />!', "$1", $pee);
251 $pee = preg_replace('!<br />(\s*</?(?:p|li|div|dl|dd|dt|th|pre|td|ul|ol)[^>]*>)!', '$1', $pee);
252 $pee = preg_replace( "|\n</p>$|", '</p>', $pee );
254 if ( !empty($pre_tags) )
255 $pee = str_replace(array_keys($pre_tags), array_values($pre_tags), $pee);
261 * Newline preservation help function for wpautop
266 * @param array $matches preg_replace_callback matches array
269 function _autop_newline_preservation_helper( $matches ) {
270 return str_replace("\n", "<WPPreserveNewline />", $matches[0]);
274 * Don't auto-p wrap shortcodes that stand alone
276 * Ensures that shortcodes are not wrapped in <<p>>...<</p>>.
280 * @param string $pee The content.
281 * @return string The filtered content.
283 function shortcode_unautop( $pee ) {
284 global $shortcode_tags;
286 if ( empty( $shortcode_tags ) || !is_array( $shortcode_tags ) ) {
290 $tagregexp = join( '|', array_map( 'preg_quote', array_keys( $shortcode_tags ) ) );
294 . '<p>' // Opening paragraph
295 . '\\s*+' // Optional leading whitespace
296 . '(' // 1: The shortcode
297 . '\\[' // Opening bracket
298 . "($tagregexp)" // 2: Shortcode name
299 . '(?![\\w-])' // Not followed by word character or hyphen
300 // Unroll the loop: Inside the opening shortcode tag
301 . '[^\\]\\/]*' // Not a closing bracket or forward slash
303 . '\\/(?!\\])' // A forward slash not followed by a closing bracket
304 . '[^\\]\\/]*' // Not a closing bracket or forward slash
307 . '\\/\\]' // Self closing tag and closing bracket
309 . '\\]' // Closing bracket
310 . '(?:' // Unroll the loop: Optionally, anything between the opening and closing shortcode tags
311 . '[^\\[]*+' // Not an opening bracket
313 . '\\[(?!\\/\\2\\])' // An opening bracket not followed by the closing shortcode tag
314 . '[^\\[]*+' // Not an opening bracket
316 . '\\[\\/\\2\\]' // Closing shortcode tag
320 . '\\s*+' // optional trailing whitespace
321 . '<\\/p>' // closing paragraph
324 return preg_replace( $pattern, '$1', $pee );
328 * Checks to see if a string is utf8 encoded.
330 * NOTE: This function checks for 5-Byte sequences, UTF8
331 * has Bytes Sequences with a maximum length of 4.
333 * @author bmorel at ssi dot fr (modified)
336 * @param string $str The string to be checked
337 * @return bool True if $str fits a UTF-8 model, false otherwise.
339 function seems_utf8($str) {
340 $length = strlen($str);
341 for ($i=0; $i < $length; $i++) {
343 if ($c < 0x80) $n = 0; # 0bbbbbbb
344 elseif (($c & 0xE0) == 0xC0) $n=1; # 110bbbbb
345 elseif (($c & 0xF0) == 0xE0) $n=2; # 1110bbbb
346 elseif (($c & 0xF8) == 0xF0) $n=3; # 11110bbb
347 elseif (($c & 0xFC) == 0xF8) $n=4; # 111110bb
348 elseif (($c & 0xFE) == 0xFC) $n=5; # 1111110b
349 else return false; # Does not match any model
350 for ($j=0; $j<$n; $j++) { # n bytes matching 10bbbbbb follow ?
351 if ((++$i == $length) || ((ord($str[$i]) & 0xC0) != 0x80))
359 * Converts a number of special characters into their HTML entities.
361 * Specifically deals with: &, <, >, ", and '.
363 * $quote_style can be set to ENT_COMPAT to encode " to
364 * ", or ENT_QUOTES to do both. Default is ENT_NOQUOTES where no quotes are encoded.
369 * @param string $string The text which is to be encoded.
370 * @param mixed $quote_style Optional. Converts double quotes if set to ENT_COMPAT, both single and double if set to ENT_QUOTES or none if set to ENT_NOQUOTES. Also compatible with old values; converting single quotes if set to 'single', double if set to 'double' or both if otherwise set. Default is ENT_NOQUOTES.
371 * @param string $charset Optional. The character encoding of the string. Default is false.
372 * @param boolean $double_encode Optional. Whether to encode existing html entities. Default is false.
373 * @return string The encoded text with HTML entities.
375 function _wp_specialchars( $string, $quote_style = ENT_NOQUOTES, $charset = false, $double_encode = false ) {
376 $string = (string) $string;
378 if ( 0 === strlen( $string ) )
381 // Don't bother if there are no specialchars - saves some processing
382 if ( ! preg_match( '/[&<>"\']/', $string ) )
385 // Account for the previous behaviour of the function when the $quote_style is not an accepted value
386 if ( empty( $quote_style ) )
387 $quote_style = ENT_NOQUOTES;
388 elseif ( ! in_array( $quote_style, array( 0, 2, 3, 'single', 'double' ), true ) )
389 $quote_style = ENT_QUOTES;
391 // Store the site charset as a static to avoid multiple calls to wp_load_alloptions()
394 if ( ! isset( $_charset ) ) {
395 $alloptions = wp_load_alloptions();
396 $_charset = isset( $alloptions['blog_charset'] ) ? $alloptions['blog_charset'] : '';
398 $charset = $_charset;
401 if ( in_array( $charset, array( 'utf8', 'utf-8', 'UTF8' ) ) )
404 $_quote_style = $quote_style;
406 if ( $quote_style === 'double' ) {
407 $quote_style = ENT_COMPAT;
408 $_quote_style = ENT_COMPAT;
409 } elseif ( $quote_style === 'single' ) {
410 $quote_style = ENT_NOQUOTES;
413 // Handle double encoding ourselves
414 if ( $double_encode ) {
415 $string = @htmlspecialchars( $string, $quote_style, $charset );
417 // Decode & into &
418 $string = wp_specialchars_decode( $string, $_quote_style );
420 // Guarantee every &entity; is valid or re-encode the &
421 $string = wp_kses_normalize_entities( $string );
423 // Now re-encode everything except &entity;
424 $string = preg_split( '/(&#?x?[0-9a-z]+;)/i', $string, -1, PREG_SPLIT_DELIM_CAPTURE );
426 for ( $i = 0; $i < count( $string ); $i += 2 )
427 $string[$i] = @htmlspecialchars( $string[$i], $quote_style, $charset );
429 $string = implode( '', $string );
432 // Backwards compatibility
433 if ( 'single' === $_quote_style )
434 $string = str_replace( "'", ''', $string );
440 * Converts a number of HTML entities into their special characters.
442 * Specifically deals with: &, <, >, ", and '.
444 * $quote_style can be set to ENT_COMPAT to decode " entities,
445 * or ENT_QUOTES to do both " and '. Default is ENT_NOQUOTES where no quotes are decoded.
449 * @param string $string The text which is to be decoded.
450 * @param mixed $quote_style Optional. Converts double quotes if set to ENT_COMPAT, both single and double if set to ENT_QUOTES or none if set to ENT_NOQUOTES. Also compatible with old _wp_specialchars() values; converting single quotes if set to 'single', double if set to 'double' or both if otherwise set. Default is ENT_NOQUOTES.
451 * @return string The decoded text without HTML entities.
453 function wp_specialchars_decode( $string, $quote_style = ENT_NOQUOTES ) {
454 $string = (string) $string;
456 if ( 0 === strlen( $string ) ) {
460 // Don't bother if there are no entities - saves a lot of processing
461 if ( strpos( $string, '&' ) === false ) {
465 // Match the previous behaviour of _wp_specialchars() when the $quote_style is not an accepted value
466 if ( empty( $quote_style ) ) {
467 $quote_style = ENT_NOQUOTES;
468 } elseif ( !in_array( $quote_style, array( 0, 2, 3, 'single', 'double' ), true ) ) {
469 $quote_style = ENT_QUOTES;
472 // More complete than get_html_translation_table( HTML_SPECIALCHARS )
473 $single = array( ''' => '\'', ''' => '\'' );
474 $single_preg = array( '/�*39;/' => ''', '/�*27;/i' => ''' );
475 $double = array( '"' => '"', '"' => '"', '"' => '"' );
476 $double_preg = array( '/�*34;/' => '"', '/�*22;/i' => '"' );
477 $others = array( '<' => '<', '<' => '<', '>' => '>', '>' => '>', '&' => '&', '&' => '&', '&' => '&' );
478 $others_preg = array( '/�*60;/' => '<', '/�*62;/' => '>', '/�*38;/' => '&', '/�*26;/i' => '&' );
480 if ( $quote_style === ENT_QUOTES ) {
481 $translation = array_merge( $single, $double, $others );
482 $translation_preg = array_merge( $single_preg, $double_preg, $others_preg );
483 } elseif ( $quote_style === ENT_COMPAT || $quote_style === 'double' ) {
484 $translation = array_merge( $double, $others );
485 $translation_preg = array_merge( $double_preg, $others_preg );
486 } elseif ( $quote_style === 'single' ) {
487 $translation = array_merge( $single, $others );
488 $translation_preg = array_merge( $single_preg, $others_preg );
489 } elseif ( $quote_style === ENT_NOQUOTES ) {
490 $translation = $others;
491 $translation_preg = $others_preg;
494 // Remove zero padding on numeric entities
495 $string = preg_replace( array_keys( $translation_preg ), array_values( $translation_preg ), $string );
497 // Replace characters according to translation table
498 return strtr( $string, $translation );
502 * Checks for invalid UTF8 in a string.
506 * @param string $string The text which is to be checked.
507 * @param boolean $strip Optional. Whether to attempt to strip out invalid UTF8. Default is false.
508 * @return string The checked text.
510 function wp_check_invalid_utf8( $string, $strip = false ) {
511 $string = (string) $string;
513 if ( 0 === strlen( $string ) ) {
517 // Store the site charset as a static to avoid multiple calls to get_option()
519 if ( !isset( $is_utf8 ) ) {
520 $is_utf8 = in_array( get_option( 'blog_charset' ), array( 'utf8', 'utf-8', 'UTF8', 'UTF-8' ) );
526 // Check for support for utf8 in the installed PCRE library once and store the result in a static
528 if ( !isset( $utf8_pcre ) ) {
529 $utf8_pcre = @preg_match( '/^./u', 'a' );
531 // We can't demand utf8 in the PCRE installation, so just return the string in those cases
536 // preg_match fails when it encounters invalid UTF8 in $string
537 if ( 1 === @preg_match( '/^./us', $string ) ) {
541 // Attempt to strip the bad chars if requested (not recommended)
542 if ( $strip && function_exists( 'iconv' ) ) {
543 return iconv( 'utf-8', 'utf-8', $string );
550 * Encode the Unicode values to be used in the URI.
554 * @param string $utf8_string
555 * @param int $length Max length of the string
556 * @return string String with Unicode encoded for URI.
558 function utf8_uri_encode( $utf8_string, $length = 0 ) {
564 $string_length = strlen( $utf8_string );
565 for ($i = 0; $i < $string_length; $i++ ) {
567 $value = ord( $utf8_string[ $i ] );
569 if ( $value < 128 ) {
570 if ( $length && ( $unicode_length >= $length ) )
572 $unicode .= chr($value);
575 if ( count( $values ) == 0 ) $num_octets = ( $value < 224 ) ? 2 : 3;
579 if ( $length && ( $unicode_length + ($num_octets * 3) ) > $length )
581 if ( count( $values ) == $num_octets ) {
582 if ($num_octets == 3) {
583 $unicode .= '%' . dechex($values[0]) . '%' . dechex($values[1]) . '%' . dechex($values[2]);
584 $unicode_length += 9;
586 $unicode .= '%' . dechex($values[0]) . '%' . dechex($values[1]);
587 $unicode_length += 6;
600 * Converts all accent characters to ASCII characters.
602 * If there are no accent characters, then the string given is just returned.
606 * @param string $string Text that might have accent characters
607 * @return string Filtered string with replaced "nice" characters.
609 function remove_accents($string) {
610 if ( !preg_match('/[\x80-\xff]/', $string) )
613 if (seems_utf8($string)) {
615 // Decompositions for Latin-1 Supplement
616 chr(194).chr(170) => 'a', chr(194).chr(186) => 'o',
617 chr(195).chr(128) => 'A', chr(195).chr(129) => 'A',
618 chr(195).chr(130) => 'A', chr(195).chr(131) => 'A',
619 chr(195).chr(132) => 'A', chr(195).chr(133) => 'A',
620 chr(195).chr(134) => 'AE',chr(195).chr(135) => 'C',
621 chr(195).chr(136) => 'E', chr(195).chr(137) => 'E',
622 chr(195).chr(138) => 'E', chr(195).chr(139) => 'E',
623 chr(195).chr(140) => 'I', chr(195).chr(141) => 'I',
624 chr(195).chr(142) => 'I', chr(195).chr(143) => 'I',
625 chr(195).chr(144) => 'D', chr(195).chr(145) => 'N',
626 chr(195).chr(146) => 'O', chr(195).chr(147) => 'O',
627 chr(195).chr(148) => 'O', chr(195).chr(149) => 'O',
628 chr(195).chr(150) => 'O', chr(195).chr(153) => 'U',
629 chr(195).chr(154) => 'U', chr(195).chr(155) => 'U',
630 chr(195).chr(156) => 'U', chr(195).chr(157) => 'Y',
631 chr(195).chr(158) => 'TH',chr(195).chr(159) => 's',
632 chr(195).chr(160) => 'a', chr(195).chr(161) => 'a',
633 chr(195).chr(162) => 'a', chr(195).chr(163) => 'a',
634 chr(195).chr(164) => 'a', chr(195).chr(165) => 'a',
635 chr(195).chr(166) => 'ae',chr(195).chr(167) => 'c',
636 chr(195).chr(168) => 'e', chr(195).chr(169) => 'e',
637 chr(195).chr(170) => 'e', chr(195).chr(171) => 'e',
638 chr(195).chr(172) => 'i', chr(195).chr(173) => 'i',
639 chr(195).chr(174) => 'i', chr(195).chr(175) => 'i',
640 chr(195).chr(176) => 'd', chr(195).chr(177) => 'n',
641 chr(195).chr(178) => 'o', chr(195).chr(179) => 'o',
642 chr(195).chr(180) => 'o', chr(195).chr(181) => 'o',
643 chr(195).chr(182) => 'o', chr(195).chr(184) => 'o',
644 chr(195).chr(185) => 'u', chr(195).chr(186) => 'u',
645 chr(195).chr(187) => 'u', chr(195).chr(188) => 'u',
646 chr(195).chr(189) => 'y', chr(195).chr(190) => 'th',
647 chr(195).chr(191) => 'y', chr(195).chr(152) => 'O',
648 // Decompositions for Latin Extended-A
649 chr(196).chr(128) => 'A', chr(196).chr(129) => 'a',
650 chr(196).chr(130) => 'A', chr(196).chr(131) => 'a',
651 chr(196).chr(132) => 'A', chr(196).chr(133) => 'a',
652 chr(196).chr(134) => 'C', chr(196).chr(135) => 'c',
653 chr(196).chr(136) => 'C', chr(196).chr(137) => 'c',
654 chr(196).chr(138) => 'C', chr(196).chr(139) => 'c',
655 chr(196).chr(140) => 'C', chr(196).chr(141) => 'c',
656 chr(196).chr(142) => 'D', chr(196).chr(143) => 'd',
657 chr(196).chr(144) => 'D', chr(196).chr(145) => 'd',
658 chr(196).chr(146) => 'E', chr(196).chr(147) => 'e',
659 chr(196).chr(148) => 'E', chr(196).chr(149) => 'e',
660 chr(196).chr(150) => 'E', chr(196).chr(151) => 'e',
661 chr(196).chr(152) => 'E', chr(196).chr(153) => 'e',
662 chr(196).chr(154) => 'E', chr(196).chr(155) => 'e',
663 chr(196).chr(156) => 'G', chr(196).chr(157) => 'g',
664 chr(196).chr(158) => 'G', chr(196).chr(159) => 'g',
665 chr(196).chr(160) => 'G', chr(196).chr(161) => 'g',
666 chr(196).chr(162) => 'G', chr(196).chr(163) => 'g',
667 chr(196).chr(164) => 'H', chr(196).chr(165) => 'h',
668 chr(196).chr(166) => 'H', chr(196).chr(167) => 'h',
669 chr(196).chr(168) => 'I', chr(196).chr(169) => 'i',
670 chr(196).chr(170) => 'I', chr(196).chr(171) => 'i',
671 chr(196).chr(172) => 'I', chr(196).chr(173) => 'i',
672 chr(196).chr(174) => 'I', chr(196).chr(175) => 'i',
673 chr(196).chr(176) => 'I', chr(196).chr(177) => 'i',
674 chr(196).chr(178) => 'IJ',chr(196).chr(179) => 'ij',
675 chr(196).chr(180) => 'J', chr(196).chr(181) => 'j',
676 chr(196).chr(182) => 'K', chr(196).chr(183) => 'k',
677 chr(196).chr(184) => 'k', chr(196).chr(185) => 'L',
678 chr(196).chr(186) => 'l', chr(196).chr(187) => 'L',
679 chr(196).chr(188) => 'l', chr(196).chr(189) => 'L',
680 chr(196).chr(190) => 'l', chr(196).chr(191) => 'L',
681 chr(197).chr(128) => 'l', chr(197).chr(129) => 'L',
682 chr(197).chr(130) => 'l', chr(197).chr(131) => 'N',
683 chr(197).chr(132) => 'n', chr(197).chr(133) => 'N',
684 chr(197).chr(134) => 'n', chr(197).chr(135) => 'N',
685 chr(197).chr(136) => 'n', chr(197).chr(137) => 'N',
686 chr(197).chr(138) => 'n', chr(197).chr(139) => 'N',
687 chr(197).chr(140) => 'O', chr(197).chr(141) => 'o',
688 chr(197).chr(142) => 'O', chr(197).chr(143) => 'o',
689 chr(197).chr(144) => 'O', chr(197).chr(145) => 'o',
690 chr(197).chr(146) => 'OE',chr(197).chr(147) => 'oe',
691 chr(197).chr(148) => 'R',chr(197).chr(149) => 'r',
692 chr(197).chr(150) => 'R',chr(197).chr(151) => 'r',
693 chr(197).chr(152) => 'R',chr(197).chr(153) => 'r',
694 chr(197).chr(154) => 'S',chr(197).chr(155) => 's',
695 chr(197).chr(156) => 'S',chr(197).chr(157) => 's',
696 chr(197).chr(158) => 'S',chr(197).chr(159) => 's',
697 chr(197).chr(160) => 'S', chr(197).chr(161) => 's',
698 chr(197).chr(162) => 'T', chr(197).chr(163) => 't',
699 chr(197).chr(164) => 'T', chr(197).chr(165) => 't',
700 chr(197).chr(166) => 'T', chr(197).chr(167) => 't',
701 chr(197).chr(168) => 'U', chr(197).chr(169) => 'u',
702 chr(197).chr(170) => 'U', chr(197).chr(171) => 'u',
703 chr(197).chr(172) => 'U', chr(197).chr(173) => 'u',
704 chr(197).chr(174) => 'U', chr(197).chr(175) => 'u',
705 chr(197).chr(176) => 'U', chr(197).chr(177) => 'u',
706 chr(197).chr(178) => 'U', chr(197).chr(179) => 'u',
707 chr(197).chr(180) => 'W', chr(197).chr(181) => 'w',
708 chr(197).chr(182) => 'Y', chr(197).chr(183) => 'y',
709 chr(197).chr(184) => 'Y', chr(197).chr(185) => 'Z',
710 chr(197).chr(186) => 'z', chr(197).chr(187) => 'Z',
711 chr(197).chr(188) => 'z', chr(197).chr(189) => 'Z',
712 chr(197).chr(190) => 'z', chr(197).chr(191) => 's',
713 // Decompositions for Latin Extended-B
714 chr(200).chr(152) => 'S', chr(200).chr(153) => 's',
715 chr(200).chr(154) => 'T', chr(200).chr(155) => 't',
717 chr(226).chr(130).chr(172) => 'E',
719 chr(194).chr(163) => '',
720 // Vowels with diacritic (Vietnamese)
722 chr(198).chr(160) => 'O', chr(198).chr(161) => 'o',
723 chr(198).chr(175) => 'U', chr(198).chr(176) => 'u',
725 chr(225).chr(186).chr(166) => 'A', chr(225).chr(186).chr(167) => 'a',
726 chr(225).chr(186).chr(176) => 'A', chr(225).chr(186).chr(177) => 'a',
727 chr(225).chr(187).chr(128) => 'E', chr(225).chr(187).chr(129) => 'e',
728 chr(225).chr(187).chr(146) => 'O', chr(225).chr(187).chr(147) => 'o',
729 chr(225).chr(187).chr(156) => 'O', chr(225).chr(187).chr(157) => 'o',
730 chr(225).chr(187).chr(170) => 'U', chr(225).chr(187).chr(171) => 'u',
731 chr(225).chr(187).chr(178) => 'Y', chr(225).chr(187).chr(179) => 'y',
733 chr(225).chr(186).chr(162) => 'A', chr(225).chr(186).chr(163) => 'a',
734 chr(225).chr(186).chr(168) => 'A', chr(225).chr(186).chr(169) => 'a',
735 chr(225).chr(186).chr(178) => 'A', chr(225).chr(186).chr(179) => 'a',
736 chr(225).chr(186).chr(186) => 'E', chr(225).chr(186).chr(187) => 'e',
737 chr(225).chr(187).chr(130) => 'E', chr(225).chr(187).chr(131) => 'e',
738 chr(225).chr(187).chr(136) => 'I', chr(225).chr(187).chr(137) => 'i',
739 chr(225).chr(187).chr(142) => 'O', chr(225).chr(187).chr(143) => 'o',
740 chr(225).chr(187).chr(148) => 'O', chr(225).chr(187).chr(149) => 'o',
741 chr(225).chr(187).chr(158) => 'O', chr(225).chr(187).chr(159) => 'o',
742 chr(225).chr(187).chr(166) => 'U', chr(225).chr(187).chr(167) => 'u',
743 chr(225).chr(187).chr(172) => 'U', chr(225).chr(187).chr(173) => 'u',
744 chr(225).chr(187).chr(182) => 'Y', chr(225).chr(187).chr(183) => 'y',
746 chr(225).chr(186).chr(170) => 'A', chr(225).chr(186).chr(171) => 'a',
747 chr(225).chr(186).chr(180) => 'A', chr(225).chr(186).chr(181) => 'a',
748 chr(225).chr(186).chr(188) => 'E', chr(225).chr(186).chr(189) => 'e',
749 chr(225).chr(187).chr(132) => 'E', chr(225).chr(187).chr(133) => 'e',
750 chr(225).chr(187).chr(150) => 'O', chr(225).chr(187).chr(151) => 'o',
751 chr(225).chr(187).chr(160) => 'O', chr(225).chr(187).chr(161) => 'o',
752 chr(225).chr(187).chr(174) => 'U', chr(225).chr(187).chr(175) => 'u',
753 chr(225).chr(187).chr(184) => 'Y', chr(225).chr(187).chr(185) => 'y',
755 chr(225).chr(186).chr(164) => 'A', chr(225).chr(186).chr(165) => 'a',
756 chr(225).chr(186).chr(174) => 'A', chr(225).chr(186).chr(175) => 'a',
757 chr(225).chr(186).chr(190) => 'E', chr(225).chr(186).chr(191) => 'e',
758 chr(225).chr(187).chr(144) => 'O', chr(225).chr(187).chr(145) => 'o',
759 chr(225).chr(187).chr(154) => 'O', chr(225).chr(187).chr(155) => 'o',
760 chr(225).chr(187).chr(168) => 'U', chr(225).chr(187).chr(169) => 'u',
762 chr(225).chr(186).chr(160) => 'A', chr(225).chr(186).chr(161) => 'a',
763 chr(225).chr(186).chr(172) => 'A', chr(225).chr(186).chr(173) => 'a',
764 chr(225).chr(186).chr(182) => 'A', chr(225).chr(186).chr(183) => 'a',
765 chr(225).chr(186).chr(184) => 'E', chr(225).chr(186).chr(185) => 'e',
766 chr(225).chr(187).chr(134) => 'E', chr(225).chr(187).chr(135) => 'e',
767 chr(225).chr(187).chr(138) => 'I', chr(225).chr(187).chr(139) => 'i',
768 chr(225).chr(187).chr(140) => 'O', chr(225).chr(187).chr(141) => 'o',
769 chr(225).chr(187).chr(152) => 'O', chr(225).chr(187).chr(153) => 'o',
770 chr(225).chr(187).chr(162) => 'O', chr(225).chr(187).chr(163) => 'o',
771 chr(225).chr(187).chr(164) => 'U', chr(225).chr(187).chr(165) => 'u',
772 chr(225).chr(187).chr(176) => 'U', chr(225).chr(187).chr(177) => 'u',
773 chr(225).chr(187).chr(180) => 'Y', chr(225).chr(187).chr(181) => 'y',
774 // Vowels with diacritic (Chinese, Hanyu Pinyin)
775 chr(201).chr(145) => 'a',
777 chr(199).chr(149) => 'U', chr(199).chr(150) => 'u',
779 chr(199).chr(151) => 'U', chr(199).chr(152) => 'u',
781 chr(199).chr(141) => 'A', chr(199).chr(142) => 'a',
782 chr(199).chr(143) => 'I', chr(199).chr(144) => 'i',
783 chr(199).chr(145) => 'O', chr(199).chr(146) => 'o',
784 chr(199).chr(147) => 'U', chr(199).chr(148) => 'u',
785 chr(199).chr(153) => 'U', chr(199).chr(154) => 'u',
787 chr(199).chr(155) => 'U', chr(199).chr(156) => 'u',
790 // Used for locale-specific rules
791 $locale = get_locale();
793 if ( 'de_DE' == $locale ) {
794 $chars[ chr(195).chr(132) ] = 'Ae';
795 $chars[ chr(195).chr(164) ] = 'ae';
796 $chars[ chr(195).chr(150) ] = 'Oe';
797 $chars[ chr(195).chr(182) ] = 'oe';
798 $chars[ chr(195).chr(156) ] = 'Ue';
799 $chars[ chr(195).chr(188) ] = 'ue';
800 $chars[ chr(195).chr(159) ] = 'ss';
803 $string = strtr($string, $chars);
805 // Assume ISO-8859-1 if not UTF-8
806 $chars['in'] = chr(128).chr(131).chr(138).chr(142).chr(154).chr(158)
807 .chr(159).chr(162).chr(165).chr(181).chr(192).chr(193).chr(194)
808 .chr(195).chr(196).chr(197).chr(199).chr(200).chr(201).chr(202)
809 .chr(203).chr(204).chr(205).chr(206).chr(207).chr(209).chr(210)
810 .chr(211).chr(212).chr(213).chr(214).chr(216).chr(217).chr(218)
811 .chr(219).chr(220).chr(221).chr(224).chr(225).chr(226).chr(227)
812 .chr(228).chr(229).chr(231).chr(232).chr(233).chr(234).chr(235)
813 .chr(236).chr(237).chr(238).chr(239).chr(241).chr(242).chr(243)
814 .chr(244).chr(245).chr(246).chr(248).chr(249).chr(250).chr(251)
815 .chr(252).chr(253).chr(255);
817 $chars['out'] = "EfSZszYcYuAAAAAACEEEEIIIINOOOOOOUUUUYaaaaaaceeeeiiiinoooooouuuuyy";
819 $string = strtr($string, $chars['in'], $chars['out']);
820 $double_chars['in'] = array(chr(140), chr(156), chr(198), chr(208), chr(222), chr(223), chr(230), chr(240), chr(254));
821 $double_chars['out'] = array('OE', 'oe', 'AE', 'DH', 'TH', 'ss', 'ae', 'dh', 'th');
822 $string = str_replace($double_chars['in'], $double_chars['out'], $string);
829 * Sanitizes a filename, replacing whitespace with dashes.
831 * Removes special characters that are illegal in filenames on certain
832 * operating systems and special characters requiring special escaping
833 * to manipulate at the command line. Replaces spaces and consecutive
834 * dashes with a single dash. Trims period, dash and underscore from beginning
835 * and end of filename.
839 * @param string $filename The filename to be sanitized
840 * @return string The sanitized filename
842 function sanitize_file_name( $filename ) {
843 $filename_raw = $filename;
844 $special_chars = array("?", "[", "]", "/", "\\", "=", "<", ">", ":", ";", ",", "'", "\"", "&", "$", "#", "*", "(", ")", "|", "~", "`", "!", "{", "}", chr(0));
845 $special_chars = apply_filters('sanitize_file_name_chars', $special_chars, $filename_raw);
846 $filename = str_replace($special_chars, '', $filename);
847 $filename = preg_replace('/[\s-]+/', '-', $filename);
848 $filename = trim($filename, '.-_');
850 // Split the filename into a base and extension[s]
851 $parts = explode('.', $filename);
853 // Return if only one extension
854 if ( count($parts) <= 2 )
855 return apply_filters('sanitize_file_name', $filename, $filename_raw);
857 // Process multiple extensions
858 $filename = array_shift($parts);
859 $extension = array_pop($parts);
860 $mimes = get_allowed_mime_types();
862 // Loop over any intermediate extensions. Munge them with a trailing underscore if they are a 2 - 5 character
863 // long alpha string not in the extension whitelist.
864 foreach ( (array) $parts as $part) {
865 $filename .= '.' . $part;
867 if ( preg_match("/^[a-zA-Z]{2,5}\d?$/", $part) ) {
869 foreach ( $mimes as $ext_preg => $mime_match ) {
870 $ext_preg = '!^(' . $ext_preg . ')$!i';
871 if ( preg_match( $ext_preg, $part ) ) {
880 $filename .= '.' . $extension;
882 return apply_filters('sanitize_file_name', $filename, $filename_raw);
886 * Sanitizes a username, stripping out unsafe characters.
888 * Removes tags, octets, entities, and if strict is enabled, will only keep
889 * alphanumeric, _, space, ., -, @. After sanitizing, it passes the username,
890 * raw username (the username in the parameter), and the value of $strict as
891 * parameters for the 'sanitize_user' filter.
894 * @uses apply_filters() Calls 'sanitize_user' hook on username, raw username,
895 * and $strict parameter.
897 * @param string $username The username to be sanitized.
898 * @param bool $strict If set limits $username to specific characters. Default false.
899 * @return string The sanitized username, after passing through filters.
901 function sanitize_user( $username, $strict = false ) {
902 $raw_username = $username;
903 $username = wp_strip_all_tags( $username );
904 $username = remove_accents( $username );
906 $username = preg_replace( '|%([a-fA-F0-9][a-fA-F0-9])|', '', $username );
907 $username = preg_replace( '/&.+?;/', '', $username ); // Kill entities
909 // If strict, reduce to ASCII for max portability.
911 $username = preg_replace( '|[^a-z0-9 _.\-@]|i', '', $username );
913 $username = trim( $username );
914 // Consolidate contiguous whitespace
915 $username = preg_replace( '|\s+|', ' ', $username );
917 return apply_filters( 'sanitize_user', $username, $raw_username, $strict );
921 * Sanitizes a string key.
923 * Keys are used as internal identifiers. Lowercase alphanumeric characters, dashes and underscores are allowed.
927 * @param string $key String key
928 * @return string Sanitized key
930 function sanitize_key( $key ) {
932 $key = strtolower( $key );
933 $key = preg_replace( '/[^a-z0-9_\-]/', '', $key );
934 return apply_filters( 'sanitize_key', $key, $raw_key );
938 * Sanitizes a title, or returns a fallback title.
940 * Specifically, HTML and PHP tags are stripped. Further actions can be added
941 * via the plugin API. If $title is empty and $fallback_title is set, the latter
946 * @param string $title The string to be sanitized.
947 * @param string $fallback_title Optional. A title to use if $title is empty.
948 * @param string $context Optional. The operation for which the string is sanitized
949 * @return string The sanitized string.
951 function sanitize_title( $title, $fallback_title = '', $context = 'save' ) {
954 if ( 'save' == $context )
955 $title = remove_accents($title);
957 $title = apply_filters('sanitize_title', $title, $raw_title, $context);
959 if ( '' === $title || false === $title )
960 $title = $fallback_title;
966 * Sanitizes a title with the 'query' context.
968 * Used for querying the database for a value from URL.
971 * @uses sanitize_title()
973 * @param string $title The string to be sanitized.
974 * @return string The sanitized string.
976 function sanitize_title_for_query( $title ) {
977 return sanitize_title( $title, '', 'query' );
981 * Sanitizes a title, replacing whitespace and a few other characters with dashes.
983 * Limits the output to alphanumeric characters, underscore (_) and dash (-).
984 * Whitespace becomes a dash.
988 * @param string $title The title to be sanitized.
989 * @param string $raw_title Optional. Not used.
990 * @param string $context Optional. The operation for which the string is sanitized.
991 * @return string The sanitized title.
993 function sanitize_title_with_dashes( $title, $raw_title = '', $context = 'display' ) {
994 $title = strip_tags($title);
995 // Preserve escaped octets.
996 $title = preg_replace('|%([a-fA-F0-9][a-fA-F0-9])|', '---$1---', $title);
997 // Remove percent signs that are not part of an octet.
998 $title = str_replace('%', '', $title);
1000 $title = preg_replace('|---([a-fA-F0-9][a-fA-F0-9])---|', '%$1', $title);
1002 if (seems_utf8($title)) {
1003 if (function_exists('mb_strtolower')) {
1004 $title = mb_strtolower($title, 'UTF-8');
1006 $title = utf8_uri_encode($title, 200);
1009 $title = strtolower($title);
1010 $title = preg_replace('/&.+?;/', '', $title); // kill entities
1011 $title = str_replace('.', '-', $title);
1013 if ( 'save' == $context ) {
1014 // Convert nbsp, ndash and mdash to hyphens
1015 $title = str_replace( array( '%c2%a0', '%e2%80%93', '%e2%80%94' ), '-', $title );
1017 // Strip these characters entirely
1018 $title = str_replace( array(
1022 '%c2%ab', '%c2%bb', '%e2%80%b9', '%e2%80%ba',
1024 '%e2%80%98', '%e2%80%99', '%e2%80%9c', '%e2%80%9d',
1025 '%e2%80%9a', '%e2%80%9b', '%e2%80%9e', '%e2%80%9f',
1026 // copy, reg, deg, hellip and trade
1027 '%c2%a9', '%c2%ae', '%c2%b0', '%e2%80%a6', '%e2%84%a2',
1029 '%c2%b4', '%cb%8a', '%cc%81', '%cd%81',
1030 // grave accent, macron, caron
1031 '%cc%80', '%cc%84', '%cc%8c',
1034 // Convert times to x
1035 $title = str_replace( '%c3%97', 'x', $title );
1038 $title = preg_replace('/[^%a-z0-9 _-]/', '', $title);
1039 $title = preg_replace('/\s+/', '-', $title);
1040 $title = preg_replace('|-+|', '-', $title);
1041 $title = trim($title, '-');
1047 * Ensures a string is a valid SQL order by clause.
1049 * Accepts one or more columns, with or without ASC/DESC, and also accepts
1054 * @param string $orderby Order by string to be checked.
1055 * @return string|bool Returns the order by clause if it is a match, false otherwise.
1057 function sanitize_sql_orderby( $orderby ){
1058 preg_match('/^\s*([a-z0-9_]+(\s+(ASC|DESC))?(\s*,\s*|\s*$))+|^\s*RAND\(\s*\)\s*$/i', $orderby, $obmatches);
1065 * Sanitizes an HTML classname to ensure it only contains valid characters.
1067 * Strips the string down to A-Z,a-z,0-9,_,-. If this results in an empty
1068 * string then it will return the alternative value supplied.
1070 * @todo Expand to support the full range of CDATA that a class attribute can contain.
1074 * @param string $class The classname to be sanitized
1075 * @param string $fallback Optional. The value to return if the sanitization end's up as an empty string.
1076 * Defaults to an empty string.
1077 * @return string The sanitized value
1079 function sanitize_html_class( $class, $fallback = '' ) {
1080 //Strip out any % encoded octets
1081 $sanitized = preg_replace( '|%[a-fA-F0-9][a-fA-F0-9]|', '', $class );
1083 //Limit to A-Z,a-z,0-9,_,-
1084 $sanitized = preg_replace( '/[^A-Za-z0-9_-]/', '', $sanitized );
1086 if ( '' == $sanitized )
1087 $sanitized = $fallback;
1089 return apply_filters( 'sanitize_html_class', $sanitized, $class, $fallback );
1093 * Converts a number of characters from a string.
1095 * Metadata tags <<title>> and <<category>> are removed, <<br>> and <<hr>> are
1096 * converted into correct XHTML and Unicode characters are converted to the
1101 * @param string $content String of characters to be converted.
1102 * @param string $deprecated Not used.
1103 * @return string Converted string.
1105 function convert_chars($content, $deprecated = '') {
1106 if ( !empty( $deprecated ) )
1107 _deprecated_argument( __FUNCTION__, '0.71' );
1109 // Translation of invalid Unicode references range to valid range
1110 $wp_htmltranswinuni = array(
1111 '€' => '€', // the Euro sign
1113 '‚' => '‚', // these are Windows CP1252 specific characters
1114 'ƒ' => 'ƒ', // they would look weird on non-Windows browsers
1115 '„' => '„',
1116 '…' => '…',
1117 '†' => '†',
1118 '‡' => '‡',
1119 'ˆ' => 'ˆ',
1120 '‰' => '‰',
1121 'Š' => 'Š',
1122 '‹' => '‹',
1123 'Œ' => 'Œ',
1125 'Ž' => 'Ž',
1128 '‘' => '‘',
1129 '’' => '’',
1130 '“' => '“',
1131 '”' => '”',
1132 '•' => '•',
1133 '–' => '–',
1134 '—' => '—',
1135 '˜' => '˜',
1136 '™' => '™',
1137 'š' => 'š',
1138 '›' => '›',
1139 'œ' => 'œ',
1141 'ž' => 'ž',
1142 'Ÿ' => 'Ÿ'
1145 // Remove metadata tags
1146 $content = preg_replace('/<title>(.+?)<\/title>/','',$content);
1147 $content = preg_replace('/<category>(.+?)<\/category>/','',$content);
1149 // Converts lone & characters into & (a.k.a. &)
1150 $content = preg_replace('/&([^#])(?![a-z1-4]{1,8};)/i', '&$1', $content);
1153 $content = strtr($content, $wp_htmltranswinuni);
1155 // Just a little XHTML help
1156 $content = str_replace('<br>', '<br />', $content);
1157 $content = str_replace('<hr>', '<hr />', $content);
1163 * Balances tags if forced to, or if the 'use_balanceTags' option is set to true.
1167 * @param string $text Text to be balanced
1168 * @param bool $force If true, forces balancing, ignoring the value of the option. Default false.
1169 * @return string Balanced text
1171 function balanceTags( $text, $force = false ) {
1172 if ( $force || get_option('use_balanceTags') == 1 )
1173 return force_balance_tags( $text );
1179 * Balances tags of string using a modified stack.
1183 * @author Leonard Lin <leonard@acm.org>
1185 * @copyright November 4, 2001
1187 * @todo Make better - change loop condition to $text in 1.2
1188 * @internal Modified by Scott Reilly (coffee2code) 02 Aug 2004
1189 * 1.1 Fixed handling of append/stack pop order of end text
1190 * Added Cleaning Hooks
1193 * @param string $text Text to be balanced.
1194 * @return string Balanced text.
1196 function force_balance_tags( $text ) {
1197 $tagstack = array();
1201 // Known single-entity/self-closing tags
1202 $single_tags = array( 'area', 'base', 'basefont', 'br', 'col', 'command', 'embed', 'frame', 'hr', 'img', 'input', 'isindex', 'link', 'meta', 'param', 'source' );
1203 // Tags that can be immediately nested within themselves
1204 $nestable_tags = array( 'blockquote', 'div', 'object', 'q', 'span' );
1206 // WP bug fix for comments - in case you REALLY meant to type '< !--'
1207 $text = str_replace('< !--', '< !--', $text);
1208 // WP bug fix for LOVE <3 (and other situations with '<' before a number)
1209 $text = preg_replace('#<([0-9]{1})#', '<$1', $text);
1211 while ( preg_match("/<(\/?[\w:]*)\s*([^>]*)>/", $text, $regex) ) {
1212 $newtext .= $tagqueue;
1214 $i = strpos($text, $regex[0]);
1215 $l = strlen($regex[0]);
1217 // clear the shifter
1220 if ( isset($regex[1][0]) && '/' == $regex[1][0] ) { // End Tag
1221 $tag = strtolower(substr($regex[1],1));
1222 // if too many closing tags
1223 if( $stacksize <= 0 ) {
1225 // or close to be safe $tag = '/' . $tag;
1227 // if stacktop value = tag close value then pop
1228 else if ( $tagstack[$stacksize - 1] == $tag ) { // found closing tag
1229 $tag = '</' . $tag . '>'; // Close Tag
1231 array_pop( $tagstack );
1233 } else { // closing tag not at top, search for it
1234 for ( $j = $stacksize-1; $j >= 0; $j-- ) {
1235 if ( $tagstack[$j] == $tag ) {
1236 // add tag to tagqueue
1237 for ( $k = $stacksize-1; $k >= $j; $k--) {
1238 $tagqueue .= '</' . array_pop( $tagstack ) . '>';
1246 } else { // Begin Tag
1247 $tag = strtolower($regex[1]);
1251 // If it's an empty tag "< >", do nothing
1255 // ElseIf it presents itself as a self-closing tag...
1256 elseif ( substr( $regex[2], -1 ) == '/' ) {
1257 // ...but it isn't a known single-entity self-closing tag, then don't let it be treated as such and
1258 // immediately close it with a closing tag (the tag will encapsulate no text as a result)
1259 if ( ! in_array( $tag, $single_tags ) )
1260 $regex[2] = trim( substr( $regex[2], 0, -1 ) ) . "></$tag";
1262 // ElseIf it's a known single-entity tag but it doesn't close itself, do so
1263 elseif ( in_array($tag, $single_tags) ) {
1266 // Else it's not a single-entity tag
1268 // If the top of the stack is the same as the tag we want to push, close previous tag
1269 if ( $stacksize > 0 && !in_array($tag, $nestable_tags) && $tagstack[$stacksize - 1] == $tag ) {
1270 $tagqueue = '</' . array_pop( $tagstack ) . '>';
1273 $stacksize = array_push( $tagstack, $tag );
1277 $attributes = $regex[2];
1278 if( ! empty( $attributes ) && $attributes[0] != '>' )
1279 $attributes = ' ' . $attributes;
1281 $tag = '<' . $tag . $attributes . '>';
1282 //If already queuing a close tag, then put this tag on, too
1283 if ( !empty($tagqueue) ) {
1288 $newtext .= substr($text, 0, $i) . $tag;
1289 $text = substr($text, $i + $l);
1293 $newtext .= $tagqueue;
1295 // Add Remaining text
1299 while( $x = array_pop($tagstack) )
1300 $newtext .= '</' . $x . '>'; // Add remaining tags to close
1302 // WP fix for the bug with HTML comments
1303 $newtext = str_replace("< !--","<!--",$newtext);
1304 $newtext = str_replace("< !--","< !--",$newtext);
1310 * Acts on text which is about to be edited.
1312 * The $content is run through esc_textarea(), which uses htmlspecialchars()
1313 * to convert special characters to HTML entities. If $richedit is set to true,
1314 * it is simply a holder for the 'format_to_edit' filter.
1318 * @param string $content The text about to be edited.
1319 * @param bool $richedit Whether the $content should not pass through htmlspecialchars(). Default false (meaning it will be passed).
1320 * @return string The text after the filter (and possibly htmlspecialchars()) has been run.
1322 function format_to_edit( $content, $richedit = false ) {
1323 $content = apply_filters( 'format_to_edit', $content );
1325 $content = esc_textarea( $content );
1330 * Holder for the 'format_to_post' filter.
1334 * @param string $content The text to pass through the filter.
1335 * @return string Text returned from the 'format_to_post' filter.
1337 function format_to_post($content) {
1338 $content = apply_filters('format_to_post', $content);
1343 * Add leading zeros when necessary.
1345 * If you set the threshold to '4' and the number is '10', then you will get
1346 * back '0010'. If you set the threshold to '4' and the number is '5000', then you
1347 * will get back '5000'.
1349 * Uses sprintf to append the amount of zeros based on the $threshold parameter
1350 * and the size of the number. If the number is large enough, then no zeros will
1355 * @param mixed $number Number to append zeros to if not greater than threshold.
1356 * @param int $threshold Digit places number needs to be to not have zeros added.
1357 * @return string Adds leading zeros to number if needed.
1359 function zeroise($number, $threshold) {
1360 return sprintf('%0'.$threshold.'s', $number);
1364 * Adds backslashes before letters and before a number at the start of a string.
1368 * @param string $string Value to which backslashes will be added.
1369 * @return string String with backslashes inserted.
1371 function backslashit($string) {
1372 if ( isset( $string[0] ) && $string[0] >= '0' && $string[0] <= '9' )
1373 $string = '\\\\' . $string;
1374 return addcslashes( $string, 'A..Za..z' );
1378 * Appends a trailing slash.
1380 * Will remove trailing slash if it exists already before adding a trailing
1381 * slash. This prevents double slashing a string or path.
1383 * The primary use of this is for paths and thus should be used for paths. It is
1384 * not restricted to paths and offers no specific path support.
1387 * @uses untrailingslashit() Unslashes string if it was slashed already.
1389 * @param string $string What to add the trailing slash to.
1390 * @return string String with trailing slash added.
1392 function trailingslashit($string) {
1393 return untrailingslashit($string) . '/';
1397 * Removes trailing slash if it exists.
1399 * The primary use of this is for paths and thus should be used for paths. It is
1400 * not restricted to paths and offers no specific path support.
1404 * @param string $string What to remove the trailing slash from.
1405 * @return string String without the trailing slash.
1407 function untrailingslashit($string) {
1408 return rtrim($string, '/');
1412 * Adds slashes to escape strings.
1414 * Slashes will first be removed if magic_quotes_gpc is set, see {@link
1415 * http://www.php.net/magic_quotes} for more details.
1419 * @param string $gpc The string returned from HTTP request data.
1420 * @return string Returns a string escaped with slashes.
1422 function addslashes_gpc($gpc) {
1423 if ( get_magic_quotes_gpc() )
1424 $gpc = stripslashes($gpc);
1426 return wp_slash($gpc);
1430 * Navigates through an array and removes slashes from the values.
1432 * If an array is passed, the array_map() function causes a callback to pass the
1433 * value back to the function. The slashes from this value will removed.
1437 * @param mixed $value The value to be stripped.
1438 * @return mixed Stripped value.
1440 function stripslashes_deep($value) {
1441 if ( is_array($value) ) {
1442 $value = array_map('stripslashes_deep', $value);
1443 } elseif ( is_object($value) ) {
1444 $vars = get_object_vars( $value );
1445 foreach ($vars as $key=>$data) {
1446 $value->{$key} = stripslashes_deep( $data );
1448 } elseif ( is_string( $value ) ) {
1449 $value = stripslashes($value);
1456 * Navigates through an array and encodes the values to be used in a URL.
1461 * @param array|string $value The array or string to be encoded.
1462 * @return array|string $value The encoded array (or string from the callback).
1464 function urlencode_deep($value) {
1465 $value = is_array($value) ? array_map('urlencode_deep', $value) : urlencode($value);
1470 * Navigates through an array and raw encodes the values to be used in a URL.
1474 * @param array|string $value The array or string to be encoded.
1475 * @return array|string $value The encoded array (or string from the callback).
1477 function rawurlencode_deep( $value ) {
1478 return is_array( $value ) ? array_map( 'rawurlencode_deep', $value ) : rawurlencode( $value );
1482 * Converts email addresses characters to HTML entities to block spam bots.
1486 * @param string $email_address Email address.
1487 * @param int $hex_encoding Optional. Set to 1 to enable hex encoding.
1488 * @return string Converted email address.
1490 function antispambot( $email_address, $hex_encoding = 0 ) {
1491 $email_no_spam_address = '';
1492 for ( $i = 0; $i < strlen( $email_address ); $i++ ) {
1493 $j = rand( 0, 1 + $hex_encoding );
1495 $email_no_spam_address .= '&#' . ord( $email_address[$i] ) . ';';
1496 } elseif ( $j == 1 ) {
1497 $email_no_spam_address .= $email_address[$i];
1498 } elseif ( $j == 2 ) {
1499 $email_no_spam_address .= '%' . zeroise( dechex( ord( $email_address[$i] ) ), 2 );
1503 $email_no_spam_address = str_replace( '@', '@', $email_no_spam_address );
1505 return $email_no_spam_address;
1509 * Callback to convert URI match to HTML A element.
1511 * This function was backported from 2.5.0 to 2.3.2. Regex callback for {@link
1512 * make_clickable()}.
1517 * @param array $matches Single Regex Match.
1518 * @return string HTML A element with URI address.
1520 function _make_url_clickable_cb($matches) {
1523 if ( ')' == $matches[3] && strpos( $url, '(' ) ) {
1524 // If the trailing character is a closing parethesis, and the URL has an opening parenthesis in it, add the closing parenthesis to the URL.
1525 // Then we can let the parenthesis balancer do its thing below.
1526 $url .= $matches[3];
1529 $suffix = $matches[3];
1532 // Include parentheses in the URL only if paired
1533 while ( substr_count( $url, '(' ) < substr_count( $url, ')' ) ) {
1534 $suffix = strrchr( $url, ')' ) . $suffix;
1535 $url = substr( $url, 0, strrpos( $url, ')' ) );
1538 $url = esc_url($url);
1542 return $matches[1] . "<a href=\"$url\" rel=\"nofollow\">$url</a>" . $suffix;
1546 * Callback to convert URL match to HTML A element.
1548 * This function was backported from 2.5.0 to 2.3.2. Regex callback for {@link
1549 * make_clickable()}.
1554 * @param array $matches Single Regex Match.
1555 * @return string HTML A element with URL address.
1557 function _make_web_ftp_clickable_cb($matches) {
1559 $dest = $matches[2];
1560 $dest = 'http://' . $dest;
1561 $dest = esc_url($dest);
1565 // removed trailing [.,;:)] from URL
1566 if ( in_array( substr($dest, -1), array('.', ',', ';', ':', ')') ) === true ) {
1567 $ret = substr($dest, -1);
1568 $dest = substr($dest, 0, strlen($dest)-1);
1570 return $matches[1] . "<a href=\"$dest\" rel=\"nofollow\">$dest</a>$ret";
1574 * Callback to convert email address match to HTML A element.
1576 * This function was backported from 2.5.0 to 2.3.2. Regex callback for {@link
1577 * make_clickable()}.
1582 * @param array $matches Single Regex Match.
1583 * @return string HTML A element with email address.
1585 function _make_email_clickable_cb($matches) {
1586 $email = $matches[2] . '@' . $matches[3];
1587 return $matches[1] . "<a href=\"mailto:$email\">$email</a>";
1591 * Convert plaintext URI to HTML links.
1593 * Converts URI, www and ftp, and email addresses. Finishes by fixing links
1598 * @param string $text Content to convert URIs.
1599 * @return string Content with converted URIs.
1601 function make_clickable( $text ) {
1603 $textarr = preg_split( '/(<[^<>]+>)/', $text, -1, PREG_SPLIT_DELIM_CAPTURE ); // split out HTML tags
1604 foreach ( $textarr as $piece ) {
1605 if ( empty( $piece ) || ( $piece[0] == '<' && ! preg_match('|^<\s*[\w]{1,20}+://|', $piece) ) ) {
1610 // Long strings might contain expensive edge cases ...
1611 if ( 10000 < strlen( $piece ) ) {
1613 foreach ( _split_str_by_whitespace( $piece, 2100 ) as $chunk ) { // 2100: Extra room for scheme and leading and trailing paretheses
1614 if ( 2101 < strlen( $chunk ) ) {
1615 $r .= $chunk; // Too big, no whitespace: bail.
1617 $r .= make_clickable( $chunk );
1621 $ret = " $piece "; // Pad with whitespace to simplify the regexes
1624 ([\\s(<.,;:!?]) # 1: Leading whitespace, or punctuation
1626 [\\w]{1,20}+:// # Scheme and hier-part prefix
1627 (?=\S{1,2000}\s) # Limit to URLs less than about 2000 characters long
1628 [\\w\\x80-\\xff#%\\~/@\\[\\]*(+=&$-]*+ # Non-punctuation URL character
1629 (?: # Unroll the Loop: Only allow puctuation URL character if followed by a non-punctuation URL character
1630 [\'.,;:!?)] # Punctuation URL character
1631 [\\w\\x80-\\xff#%\\~/@\\[\\]*(+=&$-]++ # Non-punctuation URL character
1634 (\)?) # 3: Trailing closing parenthesis (for parethesis balancing post processing)
1635 ~xS'; // The regex is a non-anchored pattern and does not have a single fixed starting character.
1636 // Tell PCRE to spend more time optimizing since, when used on a page load, it will probably be used several times.
1638 $ret = preg_replace_callback( $url_clickable, '_make_url_clickable_cb', $ret );
1640 $ret = preg_replace_callback( '#([\s>])((www|ftp)\.[\w\\x80-\\xff\#$%&~/.\-;:=,?@\[\]+]+)#is', '_make_web_ftp_clickable_cb', $ret );
1641 $ret = preg_replace_callback( '#([\s>])([.0-9a-z_+-]+)@(([0-9a-z-]+\.)+[0-9a-z]{2,})#i', '_make_email_clickable_cb', $ret );
1643 $ret = substr( $ret, 1, -1 ); // Remove our whitespace padding.
1648 // Cleanup of accidental links within links
1649 $r = preg_replace( '#(<a( [^>]+?>|>))<a [^>]+?>([^>]+?)</a></a>#i', "$1$3</a>", $r );
1654 * Breaks a string into chunks by splitting at whitespace characters.
1655 * The length of each returned chunk is as close to the specified length goal as possible,
1656 * with the caveat that each chunk includes its trailing delimiter.
1657 * Chunks longer than the goal are guaranteed to not have any inner whitespace.
1659 * Joining the returned chunks with empty delimiters reconstructs the input string losslessly.
1661 * Input string must have no null characters (or eventual transformations on output chunks must not care about null characters)
1664 * _split_str_by_whitespace( "1234 67890 1234 67890a cd 1234 890 123456789 1234567890a 45678 1 3 5 7 90 ", 10 ) ==
1666 * 0 => '1234 67890 ', // 11 characters: Perfect split
1667 * 1 => '1234 ', // 5 characters: '1234 67890a' was too long
1668 * 2 => '67890a cd ', // 10 characters: '67890a cd 1234' was too long
1669 * 3 => '1234 890 ', // 11 characters: Perfect split
1670 * 4 => '123456789 ', // 10 characters: '123456789 1234567890a' was too long
1671 * 5 => '1234567890a ', // 12 characters: Too long, but no inner whitespace on which to split
1672 * 6 => ' 45678 ', // 11 characters: Perfect split
1673 * 7 => '1 3 5 7 9', // 9 characters: End of $string
1680 * @param string $string The string to split.
1681 * @param int $goal The desired chunk length.
1682 * @return array Numeric array of chunks.
1684 function _split_str_by_whitespace( $string, $goal ) {
1687 $string_nullspace = strtr( $string, "\r\n\t\v\f ", "\000\000\000\000\000\000" );
1689 while ( $goal < strlen( $string_nullspace ) ) {
1690 $pos = strrpos( substr( $string_nullspace, 0, $goal + 1 ), "\000" );
1692 if ( false === $pos ) {
1693 $pos = strpos( $string_nullspace, "\000", $goal + 1 );
1694 if ( false === $pos ) {
1699 $chunks[] = substr( $string, 0, $pos + 1 );
1700 $string = substr( $string, $pos + 1 );
1701 $string_nullspace = substr( $string_nullspace, $pos + 1 );
1705 $chunks[] = $string;
1712 * Adds rel nofollow string to all HTML A elements in content.
1716 * @param string $text Content that may contain HTML A elements.
1717 * @return string Converted content.
1719 function wp_rel_nofollow( $text ) {
1720 // This is a pre save filter, so text is already escaped.
1721 $text = stripslashes($text);
1722 $text = preg_replace_callback('|<a (.+?)>|i', 'wp_rel_nofollow_callback', $text);
1723 $text = wp_slash($text);
1728 * Callback to add rel=nofollow string to HTML A element.
1730 * Will remove already existing rel="nofollow" and rel='nofollow' from the
1731 * string to prevent from invalidating (X)HTML.
1735 * @param array $matches Single Match
1736 * @return string HTML A Element with rel nofollow.
1738 function wp_rel_nofollow_callback( $matches ) {
1739 $text = $matches[1];
1740 $text = str_replace(array(' rel="nofollow"', " rel='nofollow'"), '', $text);
1741 return "<a $text rel=\"nofollow\">";
1745 * Convert one smiley code to the icon graphic file equivalent.
1747 * Callback handler for {@link convert_smilies()}.
1748 * Looks up one smiley code in the $wpsmiliestrans global array and returns an
1749 * <img> string for that smiley.
1751 * @global array $wpsmiliestrans
1754 * @param array $matches Single match. Smiley code to convert to image.
1755 * @return string Image string for smiley.
1757 function translate_smiley( $matches ) {
1758 global $wpsmiliestrans;
1760 if ( count( $matches ) == 0 )
1763 $smiley = trim( reset( $matches ) );
1764 $img = $wpsmiliestrans[ $smiley ];
1765 $smiley_masked = esc_attr( $smiley );
1767 $src_url = apply_filters( 'smilies_src', includes_url( "images/smilies/$img" ), $img, site_url() );
1769 return " <img src='$src_url' alt='$smiley_masked' class='wp-smiley' /> ";
1773 * Convert text equivalent of smilies to images.
1775 * Will only convert smilies if the option 'use_smilies' is true and the global
1776 * used in the function isn't empty.
1779 * @uses $wp_smiliessearch
1781 * @param string $text Content to convert smilies from text.
1782 * @return string Converted content with text smilies replaced with images.
1784 function convert_smilies($text) {
1785 global $wp_smiliessearch;
1787 if ( get_option('use_smilies') && !empty($wp_smiliessearch) ) {
1788 // HTML loop taken from texturize function, could possible be consolidated
1789 $textarr = preg_split("/(<.*>)/U", $text, -1, PREG_SPLIT_DELIM_CAPTURE); // capture the tags as well as in between
1790 $stop = count($textarr);// loop stuff
1791 for ($i = 0; $i < $stop; $i++) {
1792 $content = $textarr[$i];
1793 if ((strlen($content) > 0) && ('<' != $content[0])) { // If it's not a tag
1794 $content = preg_replace_callback($wp_smiliessearch, 'translate_smiley', $content);
1796 $output .= $content;
1799 // return default text.
1806 * Verifies that an email is valid.
1808 * Does not grok i18n domains. Not RFC compliant.
1812 * @param string $email Email address to verify.
1813 * @param boolean $deprecated Deprecated.
1814 * @return string|bool Either false or the valid email address.
1816 function is_email( $email, $deprecated = false ) {
1817 if ( ! empty( $deprecated ) )
1818 _deprecated_argument( __FUNCTION__, '3.0' );
1820 // Test for the minimum length the email can be
1821 if ( strlen( $email ) < 3 ) {
1822 return apply_filters( 'is_email', false, $email, 'email_too_short' );
1825 // Test for an @ character after the first position
1826 if ( strpos( $email, '@', 1 ) === false ) {
1827 return apply_filters( 'is_email', false, $email, 'email_no_at' );
1830 // Split out the local and domain parts
1831 list( $local, $domain ) = explode( '@', $email, 2 );
1834 // Test for invalid characters
1835 if ( !preg_match( '/^[a-zA-Z0-9!#$%&\'*+\/=?^_`{|}~\.-]+$/', $local ) ) {
1836 return apply_filters( 'is_email', false, $email, 'local_invalid_chars' );
1840 // Test for sequences of periods
1841 if ( preg_match( '/\.{2,}/', $domain ) ) {
1842 return apply_filters( 'is_email', false, $email, 'domain_period_sequence' );
1845 // Test for leading and trailing periods and whitespace
1846 if ( trim( $domain, " \t\n\r\0\x0B." ) !== $domain ) {
1847 return apply_filters( 'is_email', false, $email, 'domain_period_limits' );
1850 // Split the domain into subs
1851 $subs = explode( '.', $domain );
1853 // Assume the domain will have at least two subs
1854 if ( 2 > count( $subs ) ) {
1855 return apply_filters( 'is_email', false, $email, 'domain_no_periods' );
1858 // Loop through each sub
1859 foreach ( $subs as $sub ) {
1860 // Test for leading and trailing hyphens and whitespace
1861 if ( trim( $sub, " \t\n\r\0\x0B-" ) !== $sub ) {
1862 return apply_filters( 'is_email', false, $email, 'sub_hyphen_limits' );
1865 // Test for invalid characters
1866 if ( !preg_match('/^[a-z0-9-]+$/i', $sub ) ) {
1867 return apply_filters( 'is_email', false, $email, 'sub_invalid_chars' );
1871 // Congratulations your email made it!
1872 return apply_filters( 'is_email', $email, $email, null );
1876 * Convert to ASCII from email subjects.
1880 * @param string $string Subject line
1881 * @return string Converted string to ASCII
1883 function wp_iso_descrambler($string) {
1884 /* this may only work with iso-8859-1, I'm afraid */
1885 if (!preg_match('#\=\?(.+)\?Q\?(.+)\?\=#i', $string, $matches)) {
1888 $subject = str_replace('_', ' ', $matches[2]);
1889 $subject = preg_replace_callback('#\=([0-9a-f]{2})#i', '_wp_iso_convert', $subject);
1895 * Helper function to convert hex encoded chars to ASCII
1900 * @param array $match The preg_replace_callback matches array
1901 * @return array Converted chars
1903 function _wp_iso_convert( $match ) {
1904 return chr( hexdec( strtolower( $match[1] ) ) );
1908 * Returns a date in the GMT equivalent.
1910 * Requires and returns a date in the Y-m-d H:i:s format. If there is a
1911 * timezone_string available, the date is assumed to be in that timezone,
1912 * otherwise it simply subtracts the value of the 'gmt_offset' option. Return
1913 * format can be overridden using the $format parameter.
1917 * @uses get_option() to retrieve the value of 'gmt_offset'.
1918 * @param string $string The date to be converted.
1919 * @param string $format The format string for the returned date (default is Y-m-d H:i:s)
1920 * @return string GMT version of the date provided.
1922 function get_gmt_from_date( $string, $format = 'Y-m-d H:i:s' ) {
1923 $tz = get_option( 'timezone_string' );
1925 $datetime = date_create( $string, new DateTimeZone( $tz ) );
1927 return gmdate( $format, 0 );
1928 $datetime->setTimezone( new DateTimeZone( 'UTC' ) );
1929 $string_gmt = $datetime->format( $format );
1931 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 ) )
1932 return gmdate( $format, 0 );
1933 $string_time = gmmktime( $matches[4], $matches[5], $matches[6], $matches[2], $matches[3], $matches[1] );
1934 $string_gmt = gmdate( $format, $string_time - get_option( 'gmt_offset' ) * HOUR_IN_SECONDS );
1940 * Converts a GMT date into the correct format for the blog.
1942 * Requires and returns a date in the Y-m-d H:i:s format. If there is a
1943 * timezone_string available, the returned date is in that timezone, otherwise
1944 * it simply adds the value of gmt_offset. Return format can be overridden
1945 * using the $format parameter
1949 * @param string $string The date to be converted.
1950 * @param string $format The format string for the returned date (default is Y-m-d H:i:s)
1951 * @return string Formatted date relative to the timezone / GMT offset.
1953 function get_date_from_gmt( $string, $format = 'Y-m-d H:i:s' ) {
1954 $tz = get_option( 'timezone_string' );
1956 $datetime = date_create( $string, new DateTimeZone( 'UTC' ) );
1958 return date( $format, 0 );
1959 $datetime->setTimezone( new DateTimeZone( $tz ) );
1960 $string_localtime = $datetime->format( $format );
1962 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) )
1963 return date( $format, 0 );
1964 $string_time = gmmktime( $matches[4], $matches[5], $matches[6], $matches[2], $matches[3], $matches[1] );
1965 $string_localtime = gmdate( $format, $string_time + get_option( 'gmt_offset' ) * HOUR_IN_SECONDS );
1967 return $string_localtime;
1971 * Computes an offset in seconds from an iso8601 timezone.
1975 * @param string $timezone Either 'Z' for 0 offset or '±hhmm'.
1976 * @return int|float The offset in seconds.
1978 function iso8601_timezone_to_offset($timezone) {
1979 // $timezone is either 'Z' or '[+|-]hhmm'
1980 if ($timezone == 'Z') {
1983 $sign = (substr($timezone, 0, 1) == '+') ? 1 : -1;
1984 $hours = intval(substr($timezone, 1, 2));
1985 $minutes = intval(substr($timezone, 3, 4)) / 60;
1986 $offset = $sign * HOUR_IN_SECONDS * ($hours + $minutes);
1992 * Converts an iso8601 date to MySQL DateTime format used by post_date[_gmt].
1996 * @param string $date_string Date and time in ISO 8601 format {@link http://en.wikipedia.org/wiki/ISO_8601}.
1997 * @param string $timezone Optional. If set to GMT returns the time minus gmt_offset. Default is 'user'.
1998 * @return string The date and time in MySQL DateTime format - Y-m-d H:i:s.
2000 function iso8601_to_datetime($date_string, $timezone = 'user') {
2001 $timezone = strtolower($timezone);
2003 if ($timezone == 'gmt') {
2005 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, $date_bits);
2007 if (!empty($date_bits[7])) { // we have a timezone, so let's compute an offset
2008 $offset = iso8601_timezone_to_offset($date_bits[7]);
2009 } else { // we don't have a timezone, so we assume user local timezone (not server's!)
2010 $offset = HOUR_IN_SECONDS * get_option('gmt_offset');
2013 $timestamp = gmmktime($date_bits[4], $date_bits[5], $date_bits[6], $date_bits[2], $date_bits[3], $date_bits[1]);
2014 $timestamp -= $offset;
2016 return gmdate('Y-m-d H:i:s', $timestamp);
2018 } else if ($timezone == 'user') {
2019 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);
2024 * Adds a element attributes to open links in new windows.
2026 * Comment text in popup windows should be filtered through this. Right now it's
2027 * a moderately dumb function, ideally it would detect whether a target or rel
2028 * attribute was already there and adjust its actions accordingly.
2032 * @param string $text Content to replace links to open in a new window.
2033 * @return string Content that has filtered links.
2035 function popuplinks($text) {
2036 $text = preg_replace('/<a (.+?)>/i', "<a $1 target='_blank' rel='external'>", $text);
2041 * Strips out all characters that are not allowable in an email.
2045 * @param string $email Email address to filter.
2046 * @return string Filtered email address.
2048 function sanitize_email( $email ) {
2049 // Test for the minimum length the email can be
2050 if ( strlen( $email ) < 3 ) {
2051 return apply_filters( 'sanitize_email', '', $email, 'email_too_short' );
2054 // Test for an @ character after the first position
2055 if ( strpos( $email, '@', 1 ) === false ) {
2056 return apply_filters( 'sanitize_email', '', $email, 'email_no_at' );
2059 // Split out the local and domain parts
2060 list( $local, $domain ) = explode( '@', $email, 2 );
2063 // Test for invalid characters
2064 $local = preg_replace( '/[^a-zA-Z0-9!#$%&\'*+\/=?^_`{|}~\.-]/', '', $local );
2065 if ( '' === $local ) {
2066 return apply_filters( 'sanitize_email', '', $email, 'local_invalid_chars' );
2070 // Test for sequences of periods
2071 $domain = preg_replace( '/\.{2,}/', '', $domain );
2072 if ( '' === $domain ) {
2073 return apply_filters( 'sanitize_email', '', $email, 'domain_period_sequence' );
2076 // Test for leading and trailing periods and whitespace
2077 $domain = trim( $domain, " \t\n\r\0\x0B." );
2078 if ( '' === $domain ) {
2079 return apply_filters( 'sanitize_email', '', $email, 'domain_period_limits' );
2082 // Split the domain into subs
2083 $subs = explode( '.', $domain );
2085 // Assume the domain will have at least two subs
2086 if ( 2 > count( $subs ) ) {
2087 return apply_filters( 'sanitize_email', '', $email, 'domain_no_periods' );
2090 // Create an array that will contain valid subs
2091 $new_subs = array();
2093 // Loop through each sub
2094 foreach ( $subs as $sub ) {
2095 // Test for leading and trailing hyphens
2096 $sub = trim( $sub, " \t\n\r\0\x0B-" );
2098 // Test for invalid characters
2099 $sub = preg_replace( '/[^a-z0-9-]+/i', '', $sub );
2101 // If there's anything left, add it to the valid subs
2102 if ( '' !== $sub ) {
2107 // If there aren't 2 or more valid subs
2108 if ( 2 > count( $new_subs ) ) {
2109 return apply_filters( 'sanitize_email', '', $email, 'domain_no_valid_subs' );
2112 // Join valid subs into the new domain
2113 $domain = join( '.', $new_subs );
2115 // Put the email back together
2116 $email = $local . '@' . $domain;
2118 // Congratulations your email made it!
2119 return apply_filters( 'sanitize_email', $email, $email, null );
2123 * Determines the difference between two timestamps.
2125 * The difference is returned in a human readable format such as "1 hour",
2126 * "5 mins", "2 days".
2130 * @param int $from Unix timestamp from which the difference begins.
2131 * @param int $to Optional. Unix timestamp to end the time difference. Default becomes time() if not set.
2132 * @return string Human readable time difference.
2134 function human_time_diff( $from, $to = '' ) {
2138 $diff = (int) abs( $to - $from );
2140 if ( $diff < HOUR_IN_SECONDS ) {
2141 $mins = round( $diff / MINUTE_IN_SECONDS );
2144 /* translators: min=minute */
2145 $since = sprintf( _n( '%s min', '%s mins', $mins ), $mins );
2146 } elseif ( $diff < DAY_IN_SECONDS && $diff >= HOUR_IN_SECONDS ) {
2147 $hours = round( $diff / HOUR_IN_SECONDS );
2150 $since = sprintf( _n( '%s hour', '%s hours', $hours ), $hours );
2151 } elseif ( $diff < WEEK_IN_SECONDS && $diff >= DAY_IN_SECONDS ) {
2152 $days = round( $diff / DAY_IN_SECONDS );
2155 $since = sprintf( _n( '%s day', '%s days', $days ), $days );
2156 } elseif ( $diff < 30 * DAY_IN_SECONDS && $diff >= WEEK_IN_SECONDS ) {
2157 $weeks = round( $diff / WEEK_IN_SECONDS );
2160 $since = sprintf( _n( '%s week', '%s weeks', $weeks ), $weeks );
2161 } elseif ( $diff < YEAR_IN_SECONDS && $diff >= 30 * DAY_IN_SECONDS ) {
2162 $months = round( $diff / ( 30 * DAY_IN_SECONDS ) );
2165 $since = sprintf( _n( '%s month', '%s months', $months ), $months );
2166 } elseif ( $diff >= YEAR_IN_SECONDS ) {
2167 $years = round( $diff / YEAR_IN_SECONDS );
2170 $since = sprintf( _n( '%s year', '%s years', $years ), $years );
2177 * Generates an excerpt from the content, if needed.
2179 * The excerpt word amount will be 55 words and if the amount is greater than
2180 * that, then the string ' […]' will be appended to the excerpt. If the string
2181 * is less than 55 words, then the content will be returned as is.
2183 * The 55 word limit can be modified by plugins/themes using the excerpt_length filter
2184 * The ' […]' string can be modified by plugins/themes using the excerpt_more filter
2188 * @param string $text Optional. The excerpt. If set to empty, an excerpt is generated.
2189 * @return string The excerpt.
2191 function wp_trim_excerpt($text = '') {
2192 $raw_excerpt = $text;
2193 if ( '' == $text ) {
2194 $text = get_the_content('');
2196 $text = strip_shortcodes( $text );
2198 $text = apply_filters('the_content', $text);
2199 $text = str_replace(']]>', ']]>', $text);
2200 $excerpt_length = apply_filters('excerpt_length', 55);
2201 $excerpt_more = apply_filters('excerpt_more', ' ' . '[…]');
2202 $text = wp_trim_words( $text, $excerpt_length, $excerpt_more );
2204 return apply_filters('wp_trim_excerpt', $text, $raw_excerpt);
2208 * Trims text to a certain number of words.
2210 * This function is localized. For languages that count 'words' by the individual
2211 * character (such as East Asian languages), the $num_words argument will apply
2212 * to the number of individual characters.
2216 * @param string $text Text to trim.
2217 * @param int $num_words Number of words. Default 55.
2218 * @param string $more Optional. What to append if $text needs to be trimmed. Default '…'.
2219 * @return string Trimmed text.
2221 function wp_trim_words( $text, $num_words = 55, $more = null ) {
2222 if ( null === $more )
2223 $more = __( '…' );
2224 $original_text = $text;
2225 $text = wp_strip_all_tags( $text );
2226 /* translators: If your word count is based on single characters (East Asian characters),
2227 enter 'characters'. Otherwise, enter 'words'. Do not translate into your own language. */
2228 if ( 'characters' == _x( 'words', 'word count: words or characters?' ) && preg_match( '/^utf\-?8$/i', get_option( 'blog_charset' ) ) ) {
2229 $text = trim( preg_replace( "/[\n\r\t ]+/", ' ', $text ), ' ' );
2230 preg_match_all( '/./u', $text, $words_array );
2231 $words_array = array_slice( $words_array[0], 0, $num_words + 1 );
2234 $words_array = preg_split( "/[\n\r\t ]+/", $text, $num_words + 1, PREG_SPLIT_NO_EMPTY );
2237 if ( count( $words_array ) > $num_words ) {
2238 array_pop( $words_array );
2239 $text = implode( $sep, $words_array );
2240 $text = $text . $more;
2242 $text = implode( $sep, $words_array );
2244 return apply_filters( 'wp_trim_words', $text, $num_words, $more, $original_text );
2248 * Converts named entities into numbered entities.
2252 * @param string $text The text within which entities will be converted.
2253 * @return string Text with converted entities.
2255 function ent2ncr($text) {
2257 // Allow a plugin to short-circuit and override the mappings.
2258 $filtered = apply_filters( 'pre_ent2ncr', null, $text );
2259 if( null !== $filtered )
2263 '"' => '"',
2268 ' ' => ' ',
2269 '¡' => '¡',
2270 '¢' => '¢',
2271 '£' => '£',
2272 '¤' => '¤',
2273 '¥' => '¥',
2274 '¦' => '¦',
2275 '&brkbar;' => '¦',
2276 '§' => '§',
2277 '¨' => '¨',
2278 '¨' => '¨',
2279 '©' => '©',
2280 'ª' => 'ª',
2281 '«' => '«',
2282 '¬' => '¬',
2283 '­' => '­',
2284 '®' => '®',
2285 '¯' => '¯',
2286 '&hibar;' => '¯',
2287 '°' => '°',
2288 '±' => '±',
2289 '²' => '²',
2290 '³' => '³',
2291 '´' => '´',
2292 'µ' => 'µ',
2293 '¶' => '¶',
2294 '·' => '·',
2295 '¸' => '¸',
2296 '¹' => '¹',
2297 'º' => 'º',
2298 '»' => '»',
2299 '¼' => '¼',
2300 '½' => '½',
2301 '¾' => '¾',
2302 '¿' => '¿',
2303 'À' => 'À',
2304 'Á' => 'Á',
2305 'Â' => 'Â',
2306 'Ã' => 'Ã',
2307 'Ä' => 'Ä',
2308 'Å' => 'Å',
2309 'Æ' => 'Æ',
2310 'Ç' => 'Ç',
2311 'È' => 'È',
2312 'É' => 'É',
2313 'Ê' => 'Ê',
2314 'Ë' => 'Ë',
2315 'Ì' => 'Ì',
2316 'Í' => 'Í',
2317 'Î' => 'Î',
2318 'Ï' => 'Ï',
2319 'Ð' => 'Ð',
2320 'Ñ' => 'Ñ',
2321 'Ò' => 'Ò',
2322 'Ó' => 'Ó',
2323 'Ô' => 'Ô',
2324 'Õ' => 'Õ',
2325 'Ö' => 'Ö',
2326 '×' => '×',
2327 'Ø' => 'Ø',
2328 'Ù' => 'Ù',
2329 'Ú' => 'Ú',
2330 'Û' => 'Û',
2331 'Ü' => 'Ü',
2332 'Ý' => 'Ý',
2333 'Þ' => 'Þ',
2334 'ß' => 'ß',
2335 'à' => 'à',
2336 'á' => 'á',
2337 'â' => 'â',
2338 'ã' => 'ã',
2339 'ä' => 'ä',
2340 'å' => 'å',
2341 'æ' => 'æ',
2342 'ç' => 'ç',
2343 'è' => 'è',
2344 'é' => 'é',
2345 'ê' => 'ê',
2346 'ë' => 'ë',
2347 'ì' => 'ì',
2348 'í' => 'í',
2349 'î' => 'î',
2350 'ï' => 'ï',
2351 'ð' => 'ð',
2352 'ñ' => 'ñ',
2353 'ò' => 'ò',
2354 'ó' => 'ó',
2355 'ô' => 'ô',
2356 'õ' => 'õ',
2357 'ö' => 'ö',
2358 '÷' => '÷',
2359 'ø' => 'ø',
2360 'ù' => 'ù',
2361 'ú' => 'ú',
2362 'û' => 'û',
2363 'ü' => 'ü',
2364 'ý' => 'ý',
2365 'þ' => 'þ',
2366 'ÿ' => 'ÿ',
2367 'Œ' => 'Œ',
2368 'œ' => 'œ',
2369 'Š' => 'Š',
2370 'š' => 'š',
2371 'Ÿ' => 'Ÿ',
2372 'ƒ' => 'ƒ',
2373 'ˆ' => 'ˆ',
2374 '˜' => '˜',
2375 'Α' => 'Α',
2376 'Β' => 'Β',
2377 'Γ' => 'Γ',
2378 'Δ' => 'Δ',
2379 'Ε' => 'Ε',
2380 'Ζ' => 'Ζ',
2381 'Η' => 'Η',
2382 'Θ' => 'Θ',
2383 'Ι' => 'Ι',
2384 'Κ' => 'Κ',
2385 'Λ' => 'Λ',
2389 'Ο' => 'Ο',
2391 'Ρ' => 'Ρ',
2392 'Σ' => 'Σ',
2393 'Τ' => 'Τ',
2394 'Υ' => 'Υ',
2395 'Φ' => 'Φ',
2396 'Χ' => 'Χ',
2397 'Ψ' => 'Ψ',
2398 'Ω' => 'Ω',
2399 'α' => 'α',
2400 'β' => 'β',
2401 'γ' => 'γ',
2402 'δ' => 'δ',
2403 'ε' => 'ε',
2404 'ζ' => 'ζ',
2405 'η' => 'η',
2406 'θ' => 'θ',
2407 'ι' => 'ι',
2408 'κ' => 'κ',
2409 'λ' => 'λ',
2413 'ο' => 'ο',
2415 'ρ' => 'ρ',
2416 'ς' => 'ς',
2417 'σ' => 'σ',
2418 'τ' => 'τ',
2419 'υ' => 'υ',
2420 'φ' => 'φ',
2421 'χ' => 'χ',
2422 'ψ' => 'ψ',
2423 'ω' => 'ω',
2424 'ϑ' => 'ϑ',
2425 'ϒ' => 'ϒ',
2426 'ϖ' => 'ϖ',
2427 ' ' => ' ',
2428 ' ' => ' ',
2429 ' ' => ' ',
2430 '‌' => '‌',
2431 '‍' => '‍',
2432 '‎' => '‎',
2433 '‏' => '‏',
2434 '–' => '–',
2435 '—' => '—',
2436 '‘' => '‘',
2437 '’' => '’',
2438 '‚' => '‚',
2439 '“' => '“',
2440 '”' => '”',
2441 '„' => '„',
2442 '†' => '†',
2443 '‡' => '‡',
2444 '•' => '•',
2445 '…' => '…',
2446 '‰' => '‰',
2447 '′' => '′',
2448 '″' => '″',
2449 '‹' => '‹',
2450 '›' => '›',
2451 '‾' => '‾',
2452 '⁄' => '⁄',
2453 '€' => '€',
2454 'ℑ' => 'ℑ',
2455 '℘' => '℘',
2456 'ℜ' => 'ℜ',
2457 '™' => '™',
2458 'ℵ' => 'ℵ',
2459 '↵' => '↵',
2460 '⇐' => '⇐',
2461 '⇑' => '⇑',
2462 '⇒' => '⇒',
2463 '⇓' => '⇓',
2464 '⇔' => '⇔',
2465 '∀' => '∀',
2466 '∂' => '∂',
2467 '∃' => '∃',
2468 '∅' => '∅',
2469 '∇' => '∇',
2470 '∈' => '∈',
2471 '∉' => '∉',
2472 '∋' => '∋',
2473 '∏' => '∏',
2474 '∑' => '∑',
2475 '−' => '−',
2476 '∗' => '∗',
2477 '√' => '√',
2478 '∝' => '∝',
2479 '∞' => '∞',
2480 '∠' => '∠',
2481 '∧' => '∧',
2482 '∨' => '∨',
2483 '∩' => '∩',
2484 '∪' => '∪',
2485 '∫' => '∫',
2486 '∴' => '∴',
2487 '∼' => '∼',
2488 '≅' => '≅',
2489 '≈' => '≈',
2490 '≠' => '≠',
2491 '≡' => '≡',
2492 '≤' => '≤',
2493 '≥' => '≥',
2494 '⊂' => '⊂',
2495 '⊃' => '⊃',
2496 '⊄' => '⊄',
2497 '⊆' => '⊆',
2498 '⊇' => '⊇',
2499 '⊕' => '⊕',
2500 '⊗' => '⊗',
2501 '⊥' => '⊥',
2502 '⋅' => '⋅',
2503 '⌈' => '⌈',
2504 '⌉' => '⌉',
2505 '⌊' => '⌊',
2506 '⌋' => '⌋',
2507 '⟨' => '〈',
2508 '⟩' => '〉',
2509 '←' => '←',
2510 '↑' => '↑',
2511 '→' => '→',
2512 '↓' => '↓',
2513 '↔' => '↔',
2514 '◊' => '◊',
2515 '♠' => '♠',
2516 '♣' => '♣',
2517 '♥' => '♥',
2518 '♦' => '♦'
2521 return str_replace( array_keys($to_ncr), array_values($to_ncr), $text );
2525 * Formats text for the rich text editor.
2527 * The filter 'richedit_pre' is applied here. If $text is empty the filter will
2528 * be applied to an empty string.
2532 * @param string $text The text to be formatted.
2533 * @return string The formatted text after filter is applied.
2535 function wp_richedit_pre($text) {
2536 // Filtering a blank results in an annoying <br />\n
2537 if ( empty($text) ) return apply_filters('richedit_pre', '');
2539 $output = convert_chars($text);
2540 $output = wpautop($output);
2541 $output = htmlspecialchars($output, ENT_NOQUOTES, get_option( 'blog_charset' ) );
2543 return apply_filters('richedit_pre', $output);
2547 * Formats text for the HTML editor.
2549 * Unless $output is empty it will pass through htmlspecialchars before the
2550 * 'htmledit_pre' filter is applied.
2554 * @param string $output The text to be formatted.
2555 * @return string Formatted text after filter applied.
2557 function wp_htmledit_pre($output) {
2558 if ( !empty($output) )
2559 $output = htmlspecialchars($output, ENT_NOQUOTES, get_option( 'blog_charset' ) ); // convert only < > &
2561 return apply_filters('htmledit_pre', $output);
2565 * Perform a deep string replace operation to ensure the values in $search are no longer present
2567 * Repeats the replacement operation until it no longer replaces anything so as to remove "nested" values
2568 * e.g. $subject = '%0%0%0DDD', $search ='%0D', $result ='' rather than the '%0%0DD' that
2569 * str_replace would return
2574 * @param string|array $search The value being searched for, otherwise known as the needle. An array may be used to designate multiple needles.
2575 * @param string $subject The string being searched and replaced on, otherwise known as the haystack.
2576 * @return string The string with the replaced svalues.
2578 function _deep_replace( $search, $subject ) {
2579 $subject = (string) $subject;
2583 $subject = str_replace( $search, '', $subject, $count );
2590 * Escapes data for use in a MySQL query.
2592 * Usually you should prepare queries using wpdb::prepare().
2593 * Sometimes, spot-escaping is required or useful. One example
2594 * is preparing an array for use in an IN clause.
2597 * @param string|array $data Unescaped data
2598 * @return string|array Escaped data
2600 function esc_sql( $data ) {
2602 return $wpdb->_escape( $data );
2606 * Checks and cleans a URL.
2608 * A number of characters are removed from the URL. If the URL is for displaying
2609 * (the default behaviour) ampersands are also replaced. The 'clean_url' filter
2610 * is applied to the returned cleaned URL.
2613 * @uses wp_kses_bad_protocol() To only permit protocols in the URL set
2614 * via $protocols or the common ones set in the function.
2616 * @param string $url The URL to be cleaned.
2617 * @param array $protocols Optional. An array of acceptable protocols.
2618 * Defaults to 'http', 'https', 'ftp', 'ftps', 'mailto', 'news', 'irc', 'gopher', 'nntp', 'feed', 'telnet', 'mms', 'rtsp', 'svn' if not set.
2619 * @param string $_context Private. Use esc_url_raw() for database usage.
2620 * @return string The cleaned $url after the 'clean_url' filter is applied.
2622 function esc_url( $url, $protocols = null, $_context = 'display' ) {
2623 $original_url = $url;
2627 $url = preg_replace('|[^a-z0-9-~+_.?#=!&;,/:%@$\|*\'()\\x80-\\xff]|i', '', $url);
2628 $strip = array('%0d', '%0a', '%0D', '%0A');
2629 $url = _deep_replace($strip, $url);
2630 $url = str_replace(';//', '://', $url);
2631 /* If the URL doesn't appear to contain a scheme, we
2632 * presume it needs http:// appended (unless a relative
2633 * link starting with /, # or ? or a php file).
2635 if ( strpos($url, ':') === false && ! in_array( $url[0], array( '/', '#', '?' ) ) &&
2636 ! preg_match('/^[a-z0-9-]+?\.php/i', $url) )
2637 $url = 'http://' . $url;
2639 // Replace ampersands and single quotes only when displaying.
2640 if ( 'display' == $_context ) {
2641 $url = wp_kses_normalize_entities( $url );
2642 $url = str_replace( '&', '&', $url );
2643 $url = str_replace( "'", ''', $url );
2646 if ( '/' === $url[0] ) {
2647 $good_protocol_url = $url;
2649 if ( ! is_array( $protocols ) )
2650 $protocols = wp_allowed_protocols();
2651 $good_protocol_url = wp_kses_bad_protocol( $url, $protocols );
2652 if ( strtolower( $good_protocol_url ) != strtolower( $url ) )
2656 return apply_filters('clean_url', $good_protocol_url, $original_url, $_context);
2660 * Performs esc_url() for database usage.
2665 * @param string $url The URL to be cleaned.
2666 * @param array $protocols An array of acceptable protocols.
2667 * @return string The cleaned URL.
2669 function esc_url_raw( $url, $protocols = null ) {
2670 return esc_url( $url, $protocols, 'db' );
2674 * Convert entities, while preserving already-encoded entities.
2676 * @link http://www.php.net/htmlentities Borrowed from the PHP Manual user notes.
2680 * @param string $myHTML The text to be converted.
2681 * @return string Converted text.
2683 function htmlentities2($myHTML) {
2684 $translation_table = get_html_translation_table( HTML_ENTITIES, ENT_QUOTES );
2685 $translation_table[chr(38)] = '&';
2686 return preg_replace( "/&(?![A-Za-z]{0,4}\w{2,3};|#[0-9]{2,3};)/", "&", strtr($myHTML, $translation_table) );
2690 * Escape single quotes, htmlspecialchar " < > &, and fix line endings.
2692 * Escapes text strings for echoing in JS. It is intended to be used for inline JS
2693 * (in a tag attribute, for example onclick="..."). Note that the strings have to
2694 * be in single quotes. The filter 'js_escape' is also applied here.
2698 * @param string $text The text to be escaped.
2699 * @return string Escaped text.
2701 function esc_js( $text ) {
2702 $safe_text = wp_check_invalid_utf8( $text );
2703 $safe_text = _wp_specialchars( $safe_text, ENT_COMPAT );
2704 $safe_text = preg_replace( '/&#(x)?0*(?(1)27|39);?/i', "'", stripslashes( $safe_text ) );
2705 $safe_text = str_replace( "\r", '', $safe_text );
2706 $safe_text = str_replace( "\n", '\\n', addslashes( $safe_text ) );
2707 return apply_filters( 'js_escape', $safe_text, $text );
2711 * Escaping for HTML blocks.
2715 * @param string $text
2718 function esc_html( $text ) {
2719 $safe_text = wp_check_invalid_utf8( $text );
2720 $safe_text = _wp_specialchars( $safe_text, ENT_QUOTES );
2721 return apply_filters( 'esc_html', $safe_text, $text );
2725 * Escaping for HTML attributes.
2729 * @param string $text
2732 function esc_attr( $text ) {
2733 $safe_text = wp_check_invalid_utf8( $text );
2734 $safe_text = _wp_specialchars( $safe_text, ENT_QUOTES );
2735 return apply_filters( 'attribute_escape', $safe_text, $text );
2739 * Escaping for textarea values.
2743 * @param string $text
2746 function esc_textarea( $text ) {
2747 $safe_text = htmlspecialchars( $text, ENT_QUOTES, get_option( 'blog_charset' ) );
2748 return apply_filters( 'esc_textarea', $safe_text, $text );
2752 * Escape an HTML tag name.
2756 * @param string $tag_name
2759 function tag_escape($tag_name) {
2760 $safe_tag = strtolower( preg_replace('/[^a-zA-Z0-9_:]/', '', $tag_name) );
2761 return apply_filters('tag_escape', $safe_tag, $tag_name);
2765 * Escapes text for SQL LIKE special characters % and _.
2769 * @param string $text The text to be escaped.
2770 * @return string text, safe for inclusion in LIKE query.
2772 function like_escape($text) {
2773 return str_replace(array("%", "_"), array("\\%", "\\_"), $text);
2777 * Convert full URL paths to absolute paths.
2779 * Removes the http or https protocols and the domain. Keeps the path '/' at the
2780 * beginning, so it isn't a true relative link, but from the web root base.
2784 * @param string $link Full URL path.
2785 * @return string Absolute path.
2787 function wp_make_link_relative( $link ) {
2788 return preg_replace( '|https?://[^/]+(/.*)|i', '$1', $link );
2792 * Sanitises various option values based on the nature of the option.
2794 * This is basically a switch statement which will pass $value through a number
2795 * of functions depending on the $option.
2799 * @param string $option The name of the option.
2800 * @param string $value The unsanitised value.
2801 * @return string Sanitized value.
2803 function sanitize_option($option, $value) {
2805 switch ( $option ) {
2806 case 'admin_email' :
2807 case 'new_admin_email' :
2808 $value = sanitize_email( $value );
2809 if ( ! is_email( $value ) ) {
2810 $value = get_option( $option ); // Resets option to stored value in the case of failed sanitization
2811 if ( function_exists( 'add_settings_error' ) )
2812 add_settings_error( $option, 'invalid_admin_email', __( 'The email address entered did not appear to be a valid email address. Please enter a valid email address.' ) );
2816 case 'thumbnail_size_w':
2817 case 'thumbnail_size_h':
2818 case 'medium_size_w':
2819 case 'medium_size_h':
2820 case 'large_size_w':
2821 case 'large_size_h':
2822 case 'mailserver_port':
2823 case 'comment_max_links':
2824 case 'page_on_front':
2825 case 'page_for_posts':
2826 case 'rss_excerpt_length':
2827 case 'default_category':
2828 case 'default_email_category':
2829 case 'default_link_category':
2830 case 'close_comments_days_old':
2831 case 'comments_per_page':
2832 case 'thread_comments_depth':
2833 case 'users_can_register':
2834 case 'start_of_week':
2835 $value = absint( $value );
2838 case 'posts_per_page':
2839 case 'posts_per_rss':
2840 $value = (int) $value;
2841 if ( empty($value) )
2844 $value = abs($value);
2847 case 'default_ping_status':
2848 case 'default_comment_status':
2849 // Options that if not there have 0 value but need to be something like "closed"
2850 if ( $value == '0' || $value == '')
2854 case 'blogdescription':
2856 $value = wp_kses_post( $value );
2857 $value = esc_html( $value );
2860 case 'blog_charset':
2861 $value = preg_replace('/[^a-zA-Z0-9_-]/', '', $value); // strips slashes
2865 // This is the value if the settings checkbox is not checked on POST. Don't rely on this.
2866 if ( null === $value )
2869 $value = intval( $value );
2874 case 'mailserver_url':
2875 case 'mailserver_login':
2876 case 'mailserver_pass':
2878 $value = strip_tags( $value );
2879 $value = wp_kses_data( $value );
2883 $value = explode( "\n", $value );
2884 $value = array_filter( array_map( 'trim', $value ) );
2885 $value = array_filter( array_map( 'esc_url_raw', $value ) );
2886 $value = implode( "\n", $value );
2890 $value = preg_replace('/[^0-9:.-]/', '', $value); // strips slashes
2894 if ( (bool)preg_match( '#http(s?)://(.+)#i', $value) ) {
2895 $value = esc_url_raw($value);
2897 $value = get_option( $option ); // Resets option to stored value in the case of failed sanitization
2898 if ( function_exists('add_settings_error') )
2899 add_settings_error('siteurl', 'invalid_siteurl', __('The WordPress address you entered did not appear to be a valid URL. Please enter a valid URL.'));
2904 if ( (bool)preg_match( '#http(s?)://(.+)#i', $value) ) {
2905 $value = esc_url_raw($value);
2907 $value = get_option( $option ); // Resets option to stored value in the case of failed sanitization
2908 if ( function_exists('add_settings_error') )
2909 add_settings_error('home', 'invalid_home', __('The Site address you entered did not appear to be a valid URL. Please enter a valid URL.'));
2914 $allowed = get_available_languages();
2915 if ( ! in_array( $value, $allowed ) && ! empty( $value ) )
2916 $value = get_option( $option );
2919 case 'illegal_names':
2920 if ( ! is_array( $value ) )
2921 $value = explode( ' ', $value );
2923 $value = array_values( array_filter( array_map( 'trim', $value ) ) );
2929 case 'limited_email_domains':
2930 case 'banned_email_domains':
2931 if ( ! is_array( $value ) )
2932 $value = explode( "\n", $value );
2934 $domains = array_values( array_filter( array_map( 'trim', $value ) ) );
2937 foreach ( $domains as $domain ) {
2938 if ( ! preg_match( '/(--|\.\.)/', $domain ) && preg_match( '|^([a-zA-Z0-9-\.])+$|', $domain ) )
2945 case 'timezone_string':
2946 $allowed_zones = timezone_identifiers_list();
2947 if ( ! in_array( $value, $allowed_zones ) && ! empty( $value ) ) {
2948 $value = get_option( $option ); // Resets option to stored value in the case of failed sanitization
2949 if ( function_exists('add_settings_error') )
2950 add_settings_error('timezone_string', 'invalid_timezone_string', __('The timezone you have entered is not valid. Please select a valid timezone.') );
2954 case 'permalink_structure':
2955 case 'category_base':
2957 $value = esc_url_raw( $value );
2958 $value = str_replace( 'http://', '', $value );
2961 case 'default_role' :
2962 if ( ! get_role( $value ) && get_role( 'subscriber' ) )
2963 $value = 'subscriber';
2967 $value = apply_filters("sanitize_option_{$option}", $value, $option);
2973 * Parses a string into variables to be stored in an array.
2975 * Uses {@link http://www.php.net/parse_str parse_str()} and stripslashes if
2976 * {@link http://www.php.net/magic_quotes magic_quotes_gpc} is on.
2979 * @uses apply_filters() for the 'wp_parse_str' filter.
2981 * @param string $string The string to be parsed.
2982 * @param array $array Variables will be stored in this array.
2984 function wp_parse_str( $string, &$array ) {
2985 parse_str( $string, $array );
2986 if ( get_magic_quotes_gpc() )
2987 $array = stripslashes_deep( $array );
2988 $array = apply_filters( 'wp_parse_str', $array );
2992 * Convert lone less than signs.
2994 * KSES already converts lone greater than signs.
2996 * @uses wp_pre_kses_less_than_callback in the callback function.
2999 * @param string $text Text to be converted.
3000 * @return string Converted text.
3002 function wp_pre_kses_less_than( $text ) {
3003 return preg_replace_callback('%<[^>]*?((?=<)|>|$)%', 'wp_pre_kses_less_than_callback', $text);
3007 * Callback function used by preg_replace.
3009 * @uses esc_html to format the $matches text.
3012 * @param array $matches Populated by matches to preg_replace.
3013 * @return string The text returned after esc_html if needed.
3015 function wp_pre_kses_less_than_callback( $matches ) {
3016 if ( false === strpos($matches[0], '>') )
3017 return esc_html($matches[0]);
3022 * WordPress implementation of PHP sprintf() with filters.
3025 * @link http://www.php.net/sprintf
3027 * @param string $pattern The string which formatted args are inserted.
3028 * @param mixed $args,... Arguments to be formatted into the $pattern string.
3029 * @return string The formatted string.
3031 function wp_sprintf( $pattern ) {
3032 $args = func_get_args();
3033 $len = strlen($pattern);
3037 while ( $len > $start ) {
3038 // Last character: append and break
3039 if ( strlen($pattern) - 1 == $start ) {
3040 $result .= substr($pattern, -1);
3044 // Literal %: append and continue
3045 if ( substr($pattern, $start, 2) == '%%' ) {
3051 // Get fragment before next %
3052 $end = strpos($pattern, '%', $start + 1);
3053 if ( false === $end )
3055 $fragment = substr($pattern, $start, $end - $start);
3057 // Fragment has a specifier
3058 if ( $pattern[$start] == '%' ) {
3059 // Find numbered arguments or take the next one in order
3060 if ( preg_match('/^%(\d+)\$/', $fragment, $matches) ) {
3061 $arg = isset($args[$matches[1]]) ? $args[$matches[1]] : '';
3062 $fragment = str_replace("%{$matches[1]}$", '%', $fragment);
3065 $arg = isset($args[$arg_index]) ? $args[$arg_index] : '';
3068 // Apply filters OR sprintf
3069 $_fragment = apply_filters( 'wp_sprintf', $fragment, $arg );
3070 if ( $_fragment != $fragment )
3071 $fragment = $_fragment;
3073 $fragment = sprintf($fragment, strval($arg) );
3076 // Append to result and move to next fragment
3077 $result .= $fragment;
3084 * Localize list items before the rest of the content.
3086 * The '%l' must be at the first characters can then contain the rest of the
3087 * content. The list items will have ', ', ', and', and ' and ' added depending
3088 * on the amount of list items in the $args parameter.
3092 * @param string $pattern Content containing '%l' at the beginning.
3093 * @param array $args List items to prepend to the content and replace '%l'.
3094 * @return string Localized list items and rest of the content.
3096 function wp_sprintf_l($pattern, $args) {
3098 if ( substr($pattern, 0, 2) != '%l' )
3101 // Nothing to work with
3105 // Translate and filter the delimiter set (avoid ampersands and entities here)
3106 $l = apply_filters('wp_sprintf_l', array(
3107 /* translators: used between list items, there is a space after the comma */
3108 'between' => __(', '),
3109 /* translators: used between list items, there is a space after the and */
3110 'between_last_two' => __(', and '),
3111 /* translators: used between only two list items, there is a space after the and */
3112 'between_only_two' => __(' and '),
3115 $args = (array) $args;
3116 $result = array_shift($args);
3117 if ( count($args) == 1 )
3118 $result .= $l['between_only_two'] . array_shift($args);
3119 // Loop when more than two args
3122 $arg = array_shift($args);
3125 $result .= $l['between_last_two'] . $arg;
3127 $result .= $l['between'] . $arg;
3129 return $result . substr($pattern, 2);
3133 * Safely extracts not more than the first $count characters from html string.
3135 * UTF-8, tags and entities safe prefix extraction. Entities inside will *NOT*
3136 * be counted as one character. For example & will be counted as 4, < as
3141 * @param string $str String to get the excerpt from.
3142 * @param integer $count Maximum number of characters to take.
3143 * @param string $more Optional. What to append if $str needs to be trimmed. Defaults to empty string.
3144 * @return string The excerpt.
3146 function wp_html_excerpt( $str, $count, $more = null ) {
3147 if ( null === $more )
3149 $str = wp_strip_all_tags( $str, true );
3150 $excerpt = mb_substr( $str, 0, $count );
3151 // remove part of an entity at the end
3152 $excerpt = preg_replace( '/&[^;\s]{0,6}$/', '', $excerpt );
3153 if ( $str != $excerpt )
3154 $excerpt = trim( $excerpt ) . $more;
3159 * Add a Base url to relative links in passed content.
3161 * By default it supports the 'src' and 'href' attributes. However this can be
3162 * changed via the 3rd param.
3166 * @param string $content String to search for links in.
3167 * @param string $base The base URL to prefix to links.
3168 * @param array $attrs The attributes which should be processed.
3169 * @return string The processed content.
3171 function links_add_base_url( $content, $base, $attrs = array('src', 'href') ) {
3172 global $_links_add_base;
3173 $_links_add_base = $base;
3174 $attrs = implode('|', (array)$attrs);
3175 return preg_replace_callback( "!($attrs)=(['\"])(.+?)\\2!i", '_links_add_base', $content );
3179 * Callback to add a base url to relative links in passed content.
3184 * @param string $m The matched link.
3185 * @return string The processed link.
3187 function _links_add_base($m) {
3188 global $_links_add_base;
3189 //1 = attribute name 2 = quotation mark 3 = URL
3190 return $m[1] . '=' . $m[2] .
3191 ( preg_match( '#^(\w{1,20}):#', $m[3], $protocol ) && in_array( $protocol[1], wp_allowed_protocols() ) ?
3193 path_join( $_links_add_base, $m[3] ) )
3198 * Adds a Target attribute to all links in passed content.
3200 * This function by default only applies to <a> tags, however this can be
3201 * modified by the 3rd param.
3203 * <b>NOTE:</b> Any current target attributed will be stripped and replaced.
3207 * @param string $content String to search for links in.
3208 * @param string $target The Target to add to the links.
3209 * @param array $tags An array of tags to apply to.
3210 * @return string The processed content.
3212 function links_add_target( $content, $target = '_blank', $tags = array('a') ) {
3213 global $_links_add_target;
3214 $_links_add_target = $target;
3215 $tags = implode('|', (array)$tags);
3216 return preg_replace_callback( "!<($tags)(.+?)>!i", '_links_add_target', $content );
3220 * Callback to add a target attribute to all links in passed content.
3225 * @param string $m The matched link.
3226 * @return string The processed link.
3228 function _links_add_target( $m ) {
3229 global $_links_add_target;
3231 $link = preg_replace('|(target=([\'"])(.*?)\2)|i', '', $m[2]);
3232 return '<' . $tag . $link . ' target="' . esc_attr( $_links_add_target ) . '">';
3236 * Normalize EOL characters and strip duplicate whitespace.
3240 * @param string $str The string to normalize.
3241 * @return string The normalized string.
3243 function normalize_whitespace( $str ) {
3244 $str = trim( $str );
3245 $str = str_replace( "\r", "\n", $str );
3246 $str = preg_replace( array( '/\n+/', '/[ \t]+/' ), array( "\n", ' ' ), $str );
3251 * Properly strip all HTML tags including script and style
3255 * @param string $string String containing HTML tags
3256 * @param bool $remove_breaks optional Whether to remove left over line breaks and white space chars
3257 * @return string The processed string.
3259 function wp_strip_all_tags($string, $remove_breaks = false) {
3260 $string = preg_replace( '@<(script|style)[^>]*?>.*?</\\1>@si', '', $string );
3261 $string = strip_tags($string);
3263 if ( $remove_breaks )
3264 $string = preg_replace('/[\r\n\t ]+/', ' ', $string);
3266 return trim( $string );
3270 * Sanitize a string from user input or from the db
3272 * check for invalid UTF-8,
3273 * Convert single < characters to entity,
3275 * remove line breaks, tabs and extra white space,
3280 * @param string $str
3283 function sanitize_text_field($str) {
3284 $filtered = wp_check_invalid_utf8( $str );
3286 if ( strpos($filtered, '<') !== false ) {
3287 $filtered = wp_pre_kses_less_than( $filtered );
3288 // This will strip extra whitespace for us.
3289 $filtered = wp_strip_all_tags( $filtered, true );
3291 $filtered = trim( preg_replace('/[\r\n\t ]+/', ' ', $filtered) );
3295 while ( preg_match('/%[a-f0-9]{2}/i', $filtered, $match) ) {
3296 $filtered = str_replace($match[0], '', $filtered);
3301 // Strip out the whitespace that may now exist after removing the octets.
3302 $filtered = trim( preg_replace('/ +/', ' ', $filtered) );
3305 return apply_filters('sanitize_text_field', $filtered, $str);
3309 * i18n friendly version of basename()
3313 * @param string $path A path.
3314 * @param string $suffix If the filename ends in suffix this will also be cut off.
3317 function wp_basename( $path, $suffix = '' ) {
3318 return urldecode( basename( str_replace( array( '%2F', '%5C' ), '/', urlencode( $path ) ), $suffix ) );
3322 * Forever eliminate "Wordpress" from the planet (or at least the little bit we can influence).
3324 * Violating our coding standards for a good function name.
3328 function capital_P_dangit( $text ) {
3329 // Simple replacement for titles
3330 if ( 'the_title' === current_filter() )
3331 return str_replace( 'Wordpress', 'WordPress', $text );
3332 // Still here? Use the more judicious replacement
3333 static $dblq = false;
3334 if ( false === $dblq )
3335 $dblq = _x( '“', 'opening curly double quote' );
3337 array( ' Wordpress', '‘Wordpress', $dblq . 'Wordpress', '>Wordpress', '(Wordpress' ),
3338 array( ' WordPress', '‘WordPress', $dblq . 'WordPress', '>WordPress', '(WordPress' ),
3344 * Sanitize a mime type
3348 * @param string $mime_type Mime type
3349 * @return string Sanitized mime type
3351 function sanitize_mime_type( $mime_type ) {
3352 $sani_mime_type = preg_replace( '/[^-+*.a-zA-Z0-9\/]/', '', $mime_type );
3353 return apply_filters( 'sanitize_mime_type', $sani_mime_type, $mime_type );
3357 * Sanitize space or carriage return separated URLs that are used to send trackbacks.
3361 * @param string $to_ping Space or carriage return separated URLs
3362 * @return string URLs starting with the http or https protocol, separated by a carriage return.
3364 function sanitize_trackback_urls( $to_ping ) {
3365 $urls_to_ping = preg_split( '/[\r\n\t ]/', trim( $to_ping ), -1, PREG_SPLIT_NO_EMPTY );
3366 foreach ( $urls_to_ping as $k => $url ) {
3367 if ( !preg_match( '#^https?://.#i', $url ) )
3368 unset( $urls_to_ping[$k] );
3370 $urls_to_ping = array_map( 'esc_url_raw', $urls_to_ping );
3371 $urls_to_ping = implode( "\n", $urls_to_ping );
3372 return apply_filters( 'sanitize_trackback_urls', $urls_to_ping, $to_ping );
3376 * Add slashes to a string or array of strings.
3378 * This should be used when preparing data for core API that expects slashed data.
3379 * This should not be used to escape data going directly into an SQL query.
3383 * @param string|array $value String or array of strings to slash.
3384 * @return string|array Slashed $value
3386 function wp_slash( $value ) {
3387 if ( is_array( $value ) ) {
3388 foreach ( $value as $k => $v ) {
3389 if ( is_array( $v ) ) {
3390 $value[$k] = wp_slash( $v );
3392 $value[$k] = addslashes( $v );
3396 $value = addslashes( $value );
3403 * Remove slashes from a string or array of strings.
3405 * This should be used to remove slashes from data passed to core API that
3406 * expects data to be unslashed.
3410 * @param string|array $value String or array of strings to unslash.
3411 * @return string|array Unslashed $value
3413 function wp_unslash( $value ) {
3414 return stripslashes_deep( $value );
3418 * Extract and return the first URL from passed content.
3422 * @param string $content A string which might contain a URL.
3423 * @return string The found URL.
3425 function get_url_in_content( $content ) {
3426 if ( empty( $content ) )
3429 if ( preg_match( '/<a\s[^>]*?href=([\'"])(.+?)\1/is', $content, $matches ) )
3430 return esc_url_raw( $matches[2] );