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 $emailaddy Email address.
1487 * @param int $mailto Optional. Range from 0 to 1. Used for encoding.
1488 * @return string Converted email address.
1490 function antispambot($emailaddy, $mailto=0) {
1491 $emailNOSPAMaddy = '';
1492 srand ((float) microtime() * 1000000);
1493 for ($i = 0; $i < strlen($emailaddy); $i = $i + 1) {
1494 $j = floor(rand(0, 1+$mailto));
1496 $emailNOSPAMaddy .= '&#'.ord(substr($emailaddy,$i,1)).';';
1498 $emailNOSPAMaddy .= substr($emailaddy,$i,1);
1500 $emailNOSPAMaddy .= '%'.zeroise(dechex(ord(substr($emailaddy, $i, 1))), 2);
1503 $emailNOSPAMaddy = str_replace('@','@',$emailNOSPAMaddy);
1504 return $emailNOSPAMaddy;
1508 * Callback to convert URI match to HTML A element.
1510 * This function was backported from 2.5.0 to 2.3.2. Regex callback for {@link
1511 * make_clickable()}.
1516 * @param array $matches Single Regex Match.
1517 * @return string HTML A element with URI address.
1519 function _make_url_clickable_cb($matches) {
1522 if ( ')' == $matches[3] && strpos( $url, '(' ) ) {
1523 // If the trailing character is a closing parethesis, and the URL has an opening parenthesis in it, add the closing parenthesis to the URL.
1524 // Then we can let the parenthesis balancer do its thing below.
1525 $url .= $matches[3];
1528 $suffix = $matches[3];
1531 // Include parentheses in the URL only if paired
1532 while ( substr_count( $url, '(' ) < substr_count( $url, ')' ) ) {
1533 $suffix = strrchr( $url, ')' ) . $suffix;
1534 $url = substr( $url, 0, strrpos( $url, ')' ) );
1537 $url = esc_url($url);
1541 return $matches[1] . "<a href=\"$url\" rel=\"nofollow\">$url</a>" . $suffix;
1545 * Callback to convert URL match to HTML A element.
1547 * This function was backported from 2.5.0 to 2.3.2. Regex callback for {@link
1548 * make_clickable()}.
1553 * @param array $matches Single Regex Match.
1554 * @return string HTML A element with URL address.
1556 function _make_web_ftp_clickable_cb($matches) {
1558 $dest = $matches[2];
1559 $dest = 'http://' . $dest;
1560 $dest = esc_url($dest);
1564 // removed trailing [.,;:)] from URL
1565 if ( in_array( substr($dest, -1), array('.', ',', ';', ':', ')') ) === true ) {
1566 $ret = substr($dest, -1);
1567 $dest = substr($dest, 0, strlen($dest)-1);
1569 return $matches[1] . "<a href=\"$dest\" rel=\"nofollow\">$dest</a>$ret";
1573 * Callback to convert email address match to HTML A element.
1575 * This function was backported from 2.5.0 to 2.3.2. Regex callback for {@link
1576 * make_clickable()}.
1581 * @param array $matches Single Regex Match.
1582 * @return string HTML A element with email address.
1584 function _make_email_clickable_cb($matches) {
1585 $email = $matches[2] . '@' . $matches[3];
1586 return $matches[1] . "<a href=\"mailto:$email\">$email</a>";
1590 * Convert plaintext URI to HTML links.
1592 * Converts URI, www and ftp, and email addresses. Finishes by fixing links
1597 * @param string $text Content to convert URIs.
1598 * @return string Content with converted URIs.
1600 function make_clickable( $text ) {
1602 $textarr = preg_split( '/(<[^<>]+>)/', $text, -1, PREG_SPLIT_DELIM_CAPTURE ); // split out HTML tags
1603 foreach ( $textarr as $piece ) {
1604 if ( empty( $piece ) || ( $piece[0] == '<' && ! preg_match('|^<\s*[\w]{1,20}+://|', $piece) ) ) {
1609 // Long strings might contain expensive edge cases ...
1610 if ( 10000 < strlen( $piece ) ) {
1612 foreach ( _split_str_by_whitespace( $piece, 2100 ) as $chunk ) { // 2100: Extra room for scheme and leading and trailing paretheses
1613 if ( 2101 < strlen( $chunk ) ) {
1614 $r .= $chunk; // Too big, no whitespace: bail.
1616 $r .= make_clickable( $chunk );
1620 $ret = " $piece "; // Pad with whitespace to simplify the regexes
1623 ([\\s(<.,;:!?]) # 1: Leading whitespace, or punctuation
1625 [\\w]{1,20}+:// # Scheme and hier-part prefix
1626 (?=\S{1,2000}\s) # Limit to URLs less than about 2000 characters long
1627 [\\w\\x80-\\xff#%\\~/@\\[\\]*(+=&$-]*+ # Non-punctuation URL character
1628 (?: # Unroll the Loop: Only allow puctuation URL character if followed by a non-punctuation URL character
1629 [\'.,;:!?)] # Punctuation URL character
1630 [\\w\\x80-\\xff#%\\~/@\\[\\]*(+=&$-]++ # Non-punctuation URL character
1633 (\)?) # 3: Trailing closing parenthesis (for parethesis balancing post processing)
1634 ~xS'; // The regex is a non-anchored pattern and does not have a single fixed starting character.
1635 // Tell PCRE to spend more time optimizing since, when used on a page load, it will probably be used several times.
1637 $ret = preg_replace_callback( $url_clickable, '_make_url_clickable_cb', $ret );
1639 $ret = preg_replace_callback( '#([\s>])((www|ftp)\.[\w\\x80-\\xff\#$%&~/.\-;:=,?@\[\]+]+)#is', '_make_web_ftp_clickable_cb', $ret );
1640 $ret = preg_replace_callback( '#([\s>])([.0-9a-z_+-]+)@(([0-9a-z-]+\.)+[0-9a-z]{2,})#i', '_make_email_clickable_cb', $ret );
1642 $ret = substr( $ret, 1, -1 ); // Remove our whitespace padding.
1647 // Cleanup of accidental links within links
1648 $r = preg_replace( '#(<a( [^>]+?>|>))<a [^>]+?>([^>]+?)</a></a>#i', "$1$3</a>", $r );
1653 * Breaks a string into chunks by splitting at whitespace characters.
1654 * The length of each returned chunk is as close to the specified length goal as possible,
1655 * with the caveat that each chunk includes its trailing delimiter.
1656 * Chunks longer than the goal are guaranteed to not have any inner whitespace.
1658 * Joining the returned chunks with empty delimiters reconstructs the input string losslessly.
1660 * Input string must have no null characters (or eventual transformations on output chunks must not care about null characters)
1663 * _split_str_by_whitespace( "1234 67890 1234 67890a cd 1234 890 123456789 1234567890a 45678 1 3 5 7 90 ", 10 ) ==
1665 * 0 => '1234 67890 ', // 11 characters: Perfect split
1666 * 1 => '1234 ', // 5 characters: '1234 67890a' was too long
1667 * 2 => '67890a cd ', // 10 characters: '67890a cd 1234' was too long
1668 * 3 => '1234 890 ', // 11 characters: Perfect split
1669 * 4 => '123456789 ', // 10 characters: '123456789 1234567890a' was too long
1670 * 5 => '1234567890a ', // 12 characters: Too long, but no inner whitespace on which to split
1671 * 6 => ' 45678 ', // 11 characters: Perfect split
1672 * 7 => '1 3 5 7 9', // 9 characters: End of $string
1679 * @param string $string The string to split.
1680 * @param int $goal The desired chunk length.
1681 * @return array Numeric array of chunks.
1683 function _split_str_by_whitespace( $string, $goal ) {
1686 $string_nullspace = strtr( $string, "\r\n\t\v\f ", "\000\000\000\000\000\000" );
1688 while ( $goal < strlen( $string_nullspace ) ) {
1689 $pos = strrpos( substr( $string_nullspace, 0, $goal + 1 ), "\000" );
1691 if ( false === $pos ) {
1692 $pos = strpos( $string_nullspace, "\000", $goal + 1 );
1693 if ( false === $pos ) {
1698 $chunks[] = substr( $string, 0, $pos + 1 );
1699 $string = substr( $string, $pos + 1 );
1700 $string_nullspace = substr( $string_nullspace, $pos + 1 );
1704 $chunks[] = $string;
1711 * Adds rel nofollow string to all HTML A elements in content.
1715 * @param string $text Content that may contain HTML A elements.
1716 * @return string Converted content.
1718 function wp_rel_nofollow( $text ) {
1719 // This is a pre save filter, so text is already escaped.
1720 $text = stripslashes($text);
1721 $text = preg_replace_callback('|<a (.+?)>|i', 'wp_rel_nofollow_callback', $text);
1722 $text = wp_slash($text);
1727 * Callback to add rel=nofollow string to HTML A element.
1729 * Will remove already existing rel="nofollow" and rel='nofollow' from the
1730 * string to prevent from invalidating (X)HTML.
1734 * @param array $matches Single Match
1735 * @return string HTML A Element with rel nofollow.
1737 function wp_rel_nofollow_callback( $matches ) {
1738 $text = $matches[1];
1739 $text = str_replace(array(' rel="nofollow"', " rel='nofollow'"), '', $text);
1740 return "<a $text rel=\"nofollow\">";
1744 * Convert one smiley code to the icon graphic file equivalent.
1746 * Looks up one smiley code in the $wpsmiliestrans global array and returns an
1747 * <img> string for that smiley.
1749 * @global array $wpsmiliestrans
1752 * @param string $smiley Smiley code to convert to image.
1753 * @return string Image string for smiley.
1755 function translate_smiley($smiley) {
1756 global $wpsmiliestrans;
1758 if (count($smiley) == 0) {
1762 $smiley = trim(reset($smiley));
1763 $img = $wpsmiliestrans[$smiley];
1764 $smiley_masked = esc_attr($smiley);
1766 $srcurl = apply_filters('smilies_src', includes_url("images/smilies/$img"), $img, site_url());
1768 return " <img src='$srcurl' alt='$smiley_masked' class='wp-smiley' /> ";
1772 * Convert text equivalent of smilies to images.
1774 * Will only convert smilies if the option 'use_smilies' is true and the global
1775 * used in the function isn't empty.
1778 * @uses $wp_smiliessearch
1780 * @param string $text Content to convert smilies from text.
1781 * @return string Converted content with text smilies replaced with images.
1783 function convert_smilies($text) {
1784 global $wp_smiliessearch;
1786 if ( get_option('use_smilies') && !empty($wp_smiliessearch) ) {
1787 // HTML loop taken from texturize function, could possible be consolidated
1788 $textarr = preg_split("/(<.*>)/U", $text, -1, PREG_SPLIT_DELIM_CAPTURE); // capture the tags as well as in between
1789 $stop = count($textarr);// loop stuff
1790 for ($i = 0; $i < $stop; $i++) {
1791 $content = $textarr[$i];
1792 if ((strlen($content) > 0) && ('<' != $content[0])) { // If it's not a tag
1793 $content = preg_replace_callback($wp_smiliessearch, 'translate_smiley', $content);
1795 $output .= $content;
1798 // return default text.
1805 * Verifies that an email is valid.
1807 * Does not grok i18n domains. Not RFC compliant.
1811 * @param string $email Email address to verify.
1812 * @param boolean $deprecated Deprecated.
1813 * @return string|bool Either false or the valid email address.
1815 function is_email( $email, $deprecated = false ) {
1816 if ( ! empty( $deprecated ) )
1817 _deprecated_argument( __FUNCTION__, '3.0' );
1819 // Test for the minimum length the email can be
1820 if ( strlen( $email ) < 3 ) {
1821 return apply_filters( 'is_email', false, $email, 'email_too_short' );
1824 // Test for an @ character after the first position
1825 if ( strpos( $email, '@', 1 ) === false ) {
1826 return apply_filters( 'is_email', false, $email, 'email_no_at' );
1829 // Split out the local and domain parts
1830 list( $local, $domain ) = explode( '@', $email, 2 );
1833 // Test for invalid characters
1834 if ( !preg_match( '/^[a-zA-Z0-9!#$%&\'*+\/=?^_`{|}~\.-]+$/', $local ) ) {
1835 return apply_filters( 'is_email', false, $email, 'local_invalid_chars' );
1839 // Test for sequences of periods
1840 if ( preg_match( '/\.{2,}/', $domain ) ) {
1841 return apply_filters( 'is_email', false, $email, 'domain_period_sequence' );
1844 // Test for leading and trailing periods and whitespace
1845 if ( trim( $domain, " \t\n\r\0\x0B." ) !== $domain ) {
1846 return apply_filters( 'is_email', false, $email, 'domain_period_limits' );
1849 // Split the domain into subs
1850 $subs = explode( '.', $domain );
1852 // Assume the domain will have at least two subs
1853 if ( 2 > count( $subs ) ) {
1854 return apply_filters( 'is_email', false, $email, 'domain_no_periods' );
1857 // Loop through each sub
1858 foreach ( $subs as $sub ) {
1859 // Test for leading and trailing hyphens and whitespace
1860 if ( trim( $sub, " \t\n\r\0\x0B-" ) !== $sub ) {
1861 return apply_filters( 'is_email', false, $email, 'sub_hyphen_limits' );
1864 // Test for invalid characters
1865 if ( !preg_match('/^[a-z0-9-]+$/i', $sub ) ) {
1866 return apply_filters( 'is_email', false, $email, 'sub_invalid_chars' );
1870 // Congratulations your email made it!
1871 return apply_filters( 'is_email', $email, $email, null );
1875 * Convert to ASCII from email subjects.
1879 * @param string $string Subject line
1880 * @return string Converted string to ASCII
1882 function wp_iso_descrambler($string) {
1883 /* this may only work with iso-8859-1, I'm afraid */
1884 if (!preg_match('#\=\?(.+)\?Q\?(.+)\?\=#i', $string, $matches)) {
1887 $subject = str_replace('_', ' ', $matches[2]);
1888 $subject = preg_replace_callback('#\=([0-9a-f]{2})#i', '_wp_iso_convert', $subject);
1894 * Helper function to convert hex encoded chars to ASCII
1899 * @param array $match The preg_replace_callback matches array
1900 * @return array Converted chars
1902 function _wp_iso_convert( $match ) {
1903 return chr( hexdec( strtolower( $match[1] ) ) );
1907 * Returns a date in the GMT equivalent.
1909 * Requires and returns a date in the Y-m-d H:i:s format. If there is a
1910 * timezone_string available, the date is assumed to be in that timezone,
1911 * otherwise it simply subtracts the value of the 'gmt_offset' option. Return
1912 * format can be overridden using the $format parameter.
1916 * @uses get_option() to retrieve the value of 'gmt_offset'.
1917 * @param string $string The date to be converted.
1918 * @param string $format The format string for the returned date (default is Y-m-d H:i:s)
1919 * @return string GMT version of the date provided.
1921 function get_gmt_from_date( $string, $format = 'Y-m-d H:i:s' ) {
1922 $tz = get_option( 'timezone_string' );
1924 $datetime = date_create( $string, new DateTimeZone( $tz ) );
1926 return gmdate( $format, 0 );
1927 $datetime->setTimezone( new DateTimeZone( 'UTC' ) );
1928 $string_gmt = $datetime->format( $format );
1930 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 ) )
1931 return gmdate( $format, 0 );
1932 $string_time = gmmktime( $matches[4], $matches[5], $matches[6], $matches[2], $matches[3], $matches[1] );
1933 $string_gmt = gmdate( $format, $string_time - get_option( 'gmt_offset' ) * HOUR_IN_SECONDS );
1939 * Converts a GMT date into the correct format for the blog.
1941 * Requires and returns a date in the Y-m-d H:i:s format. If there is a
1942 * timezone_string available, the returned date is in that timezone, otherwise
1943 * it simply adds the value of gmt_offset. Return format can be overridden
1944 * using the $format parameter
1948 * @param string $string The date to be converted.
1949 * @param string $format The format string for the returned date (default is Y-m-d H:i:s)
1950 * @return string Formatted date relative to the timezone / GMT offset.
1952 function get_date_from_gmt( $string, $format = 'Y-m-d H:i:s' ) {
1953 $tz = get_option( 'timezone_string' );
1955 $datetime = date_create( $string, new DateTimeZone( 'UTC' ) );
1957 return date( $format, 0 );
1958 $datetime->setTimezone( new DateTimeZone( $tz ) );
1959 $string_localtime = $datetime->format( $format );
1961 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) )
1962 return date( $format, 0 );
1963 $string_time = gmmktime( $matches[4], $matches[5], $matches[6], $matches[2], $matches[3], $matches[1] );
1964 $string_localtime = gmdate( $format, $string_time + get_option( 'gmt_offset' ) * HOUR_IN_SECONDS );
1966 return $string_localtime;
1970 * Computes an offset in seconds from an iso8601 timezone.
1974 * @param string $timezone Either 'Z' for 0 offset or '±hhmm'.
1975 * @return int|float The offset in seconds.
1977 function iso8601_timezone_to_offset($timezone) {
1978 // $timezone is either 'Z' or '[+|-]hhmm'
1979 if ($timezone == 'Z') {
1982 $sign = (substr($timezone, 0, 1) == '+') ? 1 : -1;
1983 $hours = intval(substr($timezone, 1, 2));
1984 $minutes = intval(substr($timezone, 3, 4)) / 60;
1985 $offset = $sign * HOUR_IN_SECONDS * ($hours + $minutes);
1991 * Converts an iso8601 date to MySQL DateTime format used by post_date[_gmt].
1995 * @param string $date_string Date and time in ISO 8601 format {@link http://en.wikipedia.org/wiki/ISO_8601}.
1996 * @param string $timezone Optional. If set to GMT returns the time minus gmt_offset. Default is 'user'.
1997 * @return string The date and time in MySQL DateTime format - Y-m-d H:i:s.
1999 function iso8601_to_datetime($date_string, $timezone = 'user') {
2000 $timezone = strtolower($timezone);
2002 if ($timezone == 'gmt') {
2004 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, $date_bits);
2006 if (!empty($date_bits[7])) { // we have a timezone, so let's compute an offset
2007 $offset = iso8601_timezone_to_offset($date_bits[7]);
2008 } else { // we don't have a timezone, so we assume user local timezone (not server's!)
2009 $offset = HOUR_IN_SECONDS * get_option('gmt_offset');
2012 $timestamp = gmmktime($date_bits[4], $date_bits[5], $date_bits[6], $date_bits[2], $date_bits[3], $date_bits[1]);
2013 $timestamp -= $offset;
2015 return gmdate('Y-m-d H:i:s', $timestamp);
2017 } else if ($timezone == 'user') {
2018 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);
2023 * Adds a element attributes to open links in new windows.
2025 * Comment text in popup windows should be filtered through this. Right now it's
2026 * a moderately dumb function, ideally it would detect whether a target or rel
2027 * attribute was already there and adjust its actions accordingly.
2031 * @param string $text Content to replace links to open in a new window.
2032 * @return string Content that has filtered links.
2034 function popuplinks($text) {
2035 $text = preg_replace('/<a (.+?)>/i', "<a $1 target='_blank' rel='external'>", $text);
2040 * Strips out all characters that are not allowable in an email.
2044 * @param string $email Email address to filter.
2045 * @return string Filtered email address.
2047 function sanitize_email( $email ) {
2048 // Test for the minimum length the email can be
2049 if ( strlen( $email ) < 3 ) {
2050 return apply_filters( 'sanitize_email', '', $email, 'email_too_short' );
2053 // Test for an @ character after the first position
2054 if ( strpos( $email, '@', 1 ) === false ) {
2055 return apply_filters( 'sanitize_email', '', $email, 'email_no_at' );
2058 // Split out the local and domain parts
2059 list( $local, $domain ) = explode( '@', $email, 2 );
2062 // Test for invalid characters
2063 $local = preg_replace( '/[^a-zA-Z0-9!#$%&\'*+\/=?^_`{|}~\.-]/', '', $local );
2064 if ( '' === $local ) {
2065 return apply_filters( 'sanitize_email', '', $email, 'local_invalid_chars' );
2069 // Test for sequences of periods
2070 $domain = preg_replace( '/\.{2,}/', '', $domain );
2071 if ( '' === $domain ) {
2072 return apply_filters( 'sanitize_email', '', $email, 'domain_period_sequence' );
2075 // Test for leading and trailing periods and whitespace
2076 $domain = trim( $domain, " \t\n\r\0\x0B." );
2077 if ( '' === $domain ) {
2078 return apply_filters( 'sanitize_email', '', $email, 'domain_period_limits' );
2081 // Split the domain into subs
2082 $subs = explode( '.', $domain );
2084 // Assume the domain will have at least two subs
2085 if ( 2 > count( $subs ) ) {
2086 return apply_filters( 'sanitize_email', '', $email, 'domain_no_periods' );
2089 // Create an array that will contain valid subs
2090 $new_subs = array();
2092 // Loop through each sub
2093 foreach ( $subs as $sub ) {
2094 // Test for leading and trailing hyphens
2095 $sub = trim( $sub, " \t\n\r\0\x0B-" );
2097 // Test for invalid characters
2098 $sub = preg_replace( '/[^a-z0-9-]+/i', '', $sub );
2100 // If there's anything left, add it to the valid subs
2101 if ( '' !== $sub ) {
2106 // If there aren't 2 or more valid subs
2107 if ( 2 > count( $new_subs ) ) {
2108 return apply_filters( 'sanitize_email', '', $email, 'domain_no_valid_subs' );
2111 // Join valid subs into the new domain
2112 $domain = join( '.', $new_subs );
2114 // Put the email back together
2115 $email = $local . '@' . $domain;
2117 // Congratulations your email made it!
2118 return apply_filters( 'sanitize_email', $email, $email, null );
2122 * Determines the difference between two timestamps.
2124 * The difference is returned in a human readable format such as "1 hour",
2125 * "5 mins", "2 days".
2129 * @param int $from Unix timestamp from which the difference begins.
2130 * @param int $to Optional. Unix timestamp to end the time difference. Default becomes time() if not set.
2131 * @return string Human readable time difference.
2133 function human_time_diff( $from, $to = '' ) {
2137 $diff = (int) abs( $to - $from );
2139 if ( $diff < HOUR_IN_SECONDS ) {
2140 $mins = round( $diff / MINUTE_IN_SECONDS );
2143 /* translators: min=minute */
2144 $since = sprintf( _n( '%s min', '%s mins', $mins ), $mins );
2145 } elseif ( $diff < DAY_IN_SECONDS && $diff >= HOUR_IN_SECONDS ) {
2146 $hours = round( $diff / HOUR_IN_SECONDS );
2149 $since = sprintf( _n( '%s hour', '%s hours', $hours ), $hours );
2150 } elseif ( $diff < WEEK_IN_SECONDS && $diff >= DAY_IN_SECONDS ) {
2151 $days = round( $diff / DAY_IN_SECONDS );
2154 $since = sprintf( _n( '%s day', '%s days', $days ), $days );
2155 } elseif ( $diff < 30 * DAY_IN_SECONDS && $diff >= WEEK_IN_SECONDS ) {
2156 $weeks = round( $diff / WEEK_IN_SECONDS );
2159 $since = sprintf( _n( '%s week', '%s weeks', $weeks ), $weeks );
2160 } elseif ( $diff < YEAR_IN_SECONDS && $diff >= 30 * DAY_IN_SECONDS ) {
2161 $months = round( $diff / ( 30 * DAY_IN_SECONDS ) );
2164 $since = sprintf( _n( '%s month', '%s months', $months ), $months );
2165 } elseif ( $diff >= YEAR_IN_SECONDS ) {
2166 $years = round( $diff / YEAR_IN_SECONDS );
2169 $since = sprintf( _n( '%s year', '%s years', $years ), $years );
2176 * Generates an excerpt from the content, if needed.
2178 * The excerpt word amount will be 55 words and if the amount is greater than
2179 * that, then the string ' […]' will be appended to the excerpt. If the string
2180 * is less than 55 words, then the content will be returned as is.
2182 * The 55 word limit can be modified by plugins/themes using the excerpt_length filter
2183 * The ' […]' string can be modified by plugins/themes using the excerpt_more filter
2187 * @param string $text Optional. The excerpt. If set to empty, an excerpt is generated.
2188 * @return string The excerpt.
2190 function wp_trim_excerpt($text = '') {
2191 $raw_excerpt = $text;
2192 if ( '' == $text ) {
2193 $text = get_the_content('');
2195 $text = strip_shortcodes( $text );
2197 $text = apply_filters('the_content', $text);
2198 $text = str_replace(']]>', ']]>', $text);
2199 $excerpt_length = apply_filters('excerpt_length', 55);
2200 $excerpt_more = apply_filters('excerpt_more', ' ' . '[…]');
2201 $text = wp_trim_words( $text, $excerpt_length, $excerpt_more );
2203 return apply_filters('wp_trim_excerpt', $text, $raw_excerpt);
2207 * Trims text to a certain number of words.
2209 * This function is localized. For languages that count 'words' by the individual
2210 * character (such as East Asian languages), the $num_words argument will apply
2211 * to the number of individual characters.
2215 * @param string $text Text to trim.
2216 * @param int $num_words Number of words. Default 55.
2217 * @param string $more Optional. What to append if $text needs to be trimmed. Default '…'.
2218 * @return string Trimmed text.
2220 function wp_trim_words( $text, $num_words = 55, $more = null ) {
2221 if ( null === $more )
2222 $more = __( '…' );
2223 $original_text = $text;
2224 $text = wp_strip_all_tags( $text );
2225 /* translators: If your word count is based on single characters (East Asian characters),
2226 enter 'characters'. Otherwise, enter 'words'. Do not translate into your own language. */
2227 if ( 'characters' == _x( 'words', 'word count: words or characters?' ) && preg_match( '/^utf\-?8$/i', get_option( 'blog_charset' ) ) ) {
2228 $text = trim( preg_replace( "/[\n\r\t ]+/", ' ', $text ), ' ' );
2229 preg_match_all( '/./u', $text, $words_array );
2230 $words_array = array_slice( $words_array[0], 0, $num_words + 1 );
2233 $words_array = preg_split( "/[\n\r\t ]+/", $text, $num_words + 1, PREG_SPLIT_NO_EMPTY );
2236 if ( count( $words_array ) > $num_words ) {
2237 array_pop( $words_array );
2238 $text = implode( $sep, $words_array );
2239 $text = $text . $more;
2241 $text = implode( $sep, $words_array );
2243 return apply_filters( 'wp_trim_words', $text, $num_words, $more, $original_text );
2247 * Converts named entities into numbered entities.
2251 * @param string $text The text within which entities will be converted.
2252 * @return string Text with converted entities.
2254 function ent2ncr($text) {
2256 // Allow a plugin to short-circuit and override the mappings.
2257 $filtered = apply_filters( 'pre_ent2ncr', null, $text );
2258 if( null !== $filtered )
2262 '"' => '"',
2267 ' ' => ' ',
2268 '¡' => '¡',
2269 '¢' => '¢',
2270 '£' => '£',
2271 '¤' => '¤',
2272 '¥' => '¥',
2273 '¦' => '¦',
2274 '&brkbar;' => '¦',
2275 '§' => '§',
2276 '¨' => '¨',
2277 '¨' => '¨',
2278 '©' => '©',
2279 'ª' => 'ª',
2280 '«' => '«',
2281 '¬' => '¬',
2282 '­' => '­',
2283 '®' => '®',
2284 '¯' => '¯',
2285 '&hibar;' => '¯',
2286 '°' => '°',
2287 '±' => '±',
2288 '²' => '²',
2289 '³' => '³',
2290 '´' => '´',
2291 'µ' => 'µ',
2292 '¶' => '¶',
2293 '·' => '·',
2294 '¸' => '¸',
2295 '¹' => '¹',
2296 'º' => 'º',
2297 '»' => '»',
2298 '¼' => '¼',
2299 '½' => '½',
2300 '¾' => '¾',
2301 '¿' => '¿',
2302 'À' => 'À',
2303 'Á' => 'Á',
2304 'Â' => 'Â',
2305 'Ã' => 'Ã',
2306 'Ä' => 'Ä',
2307 'Å' => 'Å',
2308 'Æ' => 'Æ',
2309 'Ç' => 'Ç',
2310 'È' => 'È',
2311 'É' => 'É',
2312 'Ê' => 'Ê',
2313 'Ë' => 'Ë',
2314 'Ì' => 'Ì',
2315 'Í' => 'Í',
2316 'Î' => 'Î',
2317 'Ï' => 'Ï',
2318 'Ð' => 'Ð',
2319 'Ñ' => 'Ñ',
2320 'Ò' => 'Ò',
2321 'Ó' => 'Ó',
2322 'Ô' => 'Ô',
2323 'Õ' => 'Õ',
2324 'Ö' => 'Ö',
2325 '×' => '×',
2326 'Ø' => 'Ø',
2327 'Ù' => 'Ù',
2328 'Ú' => 'Ú',
2329 'Û' => 'Û',
2330 'Ü' => 'Ü',
2331 'Ý' => 'Ý',
2332 'Þ' => 'Þ',
2333 'ß' => 'ß',
2334 'à' => 'à',
2335 'á' => 'á',
2336 'â' => 'â',
2337 'ã' => 'ã',
2338 'ä' => 'ä',
2339 'å' => 'å',
2340 'æ' => 'æ',
2341 'ç' => 'ç',
2342 'è' => 'è',
2343 'é' => 'é',
2344 'ê' => 'ê',
2345 'ë' => 'ë',
2346 'ì' => 'ì',
2347 'í' => 'í',
2348 'î' => 'î',
2349 'ï' => 'ï',
2350 'ð' => 'ð',
2351 'ñ' => 'ñ',
2352 'ò' => 'ò',
2353 'ó' => 'ó',
2354 'ô' => 'ô',
2355 'õ' => 'õ',
2356 'ö' => 'ö',
2357 '÷' => '÷',
2358 'ø' => 'ø',
2359 'ù' => 'ù',
2360 'ú' => 'ú',
2361 'û' => 'û',
2362 'ü' => 'ü',
2363 'ý' => 'ý',
2364 'þ' => 'þ',
2365 'ÿ' => 'ÿ',
2366 'Œ' => 'Œ',
2367 'œ' => 'œ',
2368 'Š' => 'Š',
2369 'š' => 'š',
2370 'Ÿ' => 'Ÿ',
2371 'ƒ' => 'ƒ',
2372 'ˆ' => 'ˆ',
2373 '˜' => '˜',
2374 'Α' => 'Α',
2375 'Β' => 'Β',
2376 'Γ' => 'Γ',
2377 'Δ' => 'Δ',
2378 'Ε' => 'Ε',
2379 'Ζ' => 'Ζ',
2380 'Η' => 'Η',
2381 'Θ' => 'Θ',
2382 'Ι' => 'Ι',
2383 'Κ' => 'Κ',
2384 'Λ' => 'Λ',
2388 'Ο' => 'Ο',
2390 'Ρ' => 'Ρ',
2391 'Σ' => 'Σ',
2392 'Τ' => 'Τ',
2393 'Υ' => 'Υ',
2394 'Φ' => 'Φ',
2395 'Χ' => 'Χ',
2396 'Ψ' => 'Ψ',
2397 'Ω' => 'Ω',
2398 'α' => 'α',
2399 'β' => 'β',
2400 'γ' => 'γ',
2401 'δ' => 'δ',
2402 'ε' => 'ε',
2403 'ζ' => 'ζ',
2404 'η' => 'η',
2405 'θ' => 'θ',
2406 'ι' => 'ι',
2407 'κ' => 'κ',
2408 'λ' => 'λ',
2412 'ο' => 'ο',
2414 'ρ' => 'ρ',
2415 'ς' => 'ς',
2416 'σ' => 'σ',
2417 'τ' => 'τ',
2418 'υ' => 'υ',
2419 'φ' => 'φ',
2420 'χ' => 'χ',
2421 'ψ' => 'ψ',
2422 'ω' => 'ω',
2423 'ϑ' => 'ϑ',
2424 'ϒ' => 'ϒ',
2425 'ϖ' => 'ϖ',
2426 ' ' => ' ',
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 'ℑ' => 'ℑ',
2454 '℘' => '℘',
2455 'ℜ' => 'ℜ',
2456 '™' => '™',
2457 'ℵ' => 'ℵ',
2458 '↵' => '↵',
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 '♦' => '♦'
2520 return str_replace( array_keys($to_ncr), array_values($to_ncr), $text );
2524 * Formats text for the rich text editor.
2526 * The filter 'richedit_pre' is applied here. If $text is empty the filter will
2527 * be applied to an empty string.
2531 * @param string $text The text to be formatted.
2532 * @return string The formatted text after filter is applied.
2534 function wp_richedit_pre($text) {
2535 // Filtering a blank results in an annoying <br />\n
2536 if ( empty($text) ) return apply_filters('richedit_pre', '');
2538 $output = convert_chars($text);
2539 $output = wpautop($output);
2540 $output = htmlspecialchars($output, ENT_NOQUOTES, get_option( 'blog_charset' ) );
2542 return apply_filters('richedit_pre', $output);
2546 * Formats text for the HTML editor.
2548 * Unless $output is empty it will pass through htmlspecialchars before the
2549 * 'htmledit_pre' filter is applied.
2553 * @param string $output The text to be formatted.
2554 * @return string Formatted text after filter applied.
2556 function wp_htmledit_pre($output) {
2557 if ( !empty($output) )
2558 $output = htmlspecialchars($output, ENT_NOQUOTES, get_option( 'blog_charset' ) ); // convert only < > &
2560 return apply_filters('htmledit_pre', $output);
2564 * Perform a deep string replace operation to ensure the values in $search are no longer present
2566 * Repeats the replacement operation until it no longer replaces anything so as to remove "nested" values
2567 * e.g. $subject = '%0%0%0DDD', $search ='%0D', $result ='' rather than the '%0%0DD' that
2568 * str_replace would return
2573 * @param string|array $search
2574 * @param string $subject
2575 * @return string The processed string
2577 function _deep_replace( $search, $subject ) {
2579 $subject = (string) $subject;
2582 foreach ( (array) $search as $val ) {
2583 while ( strpos( $subject, $val ) !== false ) {
2585 $subject = str_replace( $val, '', $subject );
2594 * Escapes data for use in a MySQL query.
2596 * Usually you should prepare queries using wpdb::prepare().
2597 * Sometimes, spot-escaping is required or useful. One example
2598 * is preparing an array for use in an IN clause.
2601 * @param string $data Unescaped data
2602 * @return string Escaped data
2604 function esc_sql( $data ) {
2606 return $wpdb->_escape( $data );
2610 * Checks and cleans a URL.
2612 * A number of characters are removed from the URL. If the URL is for displaying
2613 * (the default behaviour) ampersands are also replaced. The 'clean_url' filter
2614 * is applied to the returned cleaned URL.
2617 * @uses wp_kses_bad_protocol() To only permit protocols in the URL set
2618 * via $protocols or the common ones set in the function.
2620 * @param string $url The URL to be cleaned.
2621 * @param array $protocols Optional. An array of acceptable protocols.
2622 * Defaults to 'http', 'https', 'ftp', 'ftps', 'mailto', 'news', 'irc', 'gopher', 'nntp', 'feed', 'telnet', 'mms', 'rtsp', 'svn' if not set.
2623 * @param string $_context Private. Use esc_url_raw() for database usage.
2624 * @return string The cleaned $url after the 'clean_url' filter is applied.
2626 function esc_url( $url, $protocols = null, $_context = 'display' ) {
2627 $original_url = $url;
2631 $url = preg_replace('|[^a-z0-9-~+_.?#=!&;,/:%@$\|*\'()\\x80-\\xff]|i', '', $url);
2632 $strip = array('%0d', '%0a', '%0D', '%0A');
2633 $url = _deep_replace($strip, $url);
2634 $url = str_replace(';//', '://', $url);
2635 /* If the URL doesn't appear to contain a scheme, we
2636 * presume it needs http:// appended (unless a relative
2637 * link starting with /, # or ? or a php file).
2639 if ( strpos($url, ':') === false && ! in_array( $url[0], array( '/', '#', '?' ) ) &&
2640 ! preg_match('/^[a-z0-9-]+?\.php/i', $url) )
2641 $url = 'http://' . $url;
2643 // Replace ampersands and single quotes only when displaying.
2644 if ( 'display' == $_context ) {
2645 $url = wp_kses_normalize_entities( $url );
2646 $url = str_replace( '&', '&', $url );
2647 $url = str_replace( "'", ''', $url );
2650 if ( '/' === $url[0] ) {
2651 $good_protocol_url = $url;
2653 if ( ! is_array( $protocols ) )
2654 $protocols = wp_allowed_protocols();
2655 $good_protocol_url = wp_kses_bad_protocol( $url, $protocols );
2656 if ( strtolower( $good_protocol_url ) != strtolower( $url ) )
2660 return apply_filters('clean_url', $good_protocol_url, $original_url, $_context);
2664 * Performs esc_url() for database usage.
2669 * @param string $url The URL to be cleaned.
2670 * @param array $protocols An array of acceptable protocols.
2671 * @return string The cleaned URL.
2673 function esc_url_raw( $url, $protocols = null ) {
2674 return esc_url( $url, $protocols, 'db' );
2678 * Convert entities, while preserving already-encoded entities.
2680 * @link http://www.php.net/htmlentities Borrowed from the PHP Manual user notes.
2684 * @param string $myHTML The text to be converted.
2685 * @return string Converted text.
2687 function htmlentities2($myHTML) {
2688 $translation_table = get_html_translation_table( HTML_ENTITIES, ENT_QUOTES );
2689 $translation_table[chr(38)] = '&';
2690 return preg_replace( "/&(?![A-Za-z]{0,4}\w{2,3};|#[0-9]{2,3};)/", "&", strtr($myHTML, $translation_table) );
2694 * Escape single quotes, htmlspecialchar " < > &, and fix line endings.
2696 * Escapes text strings for echoing in JS. It is intended to be used for inline JS
2697 * (in a tag attribute, for example onclick="..."). Note that the strings have to
2698 * be in single quotes. The filter 'js_escape' is also applied here.
2702 * @param string $text The text to be escaped.
2703 * @return string Escaped text.
2705 function esc_js( $text ) {
2706 $safe_text = wp_check_invalid_utf8( $text );
2707 $safe_text = _wp_specialchars( $safe_text, ENT_COMPAT );
2708 $safe_text = preg_replace( '/&#(x)?0*(?(1)27|39);?/i', "'", stripslashes( $safe_text ) );
2709 $safe_text = str_replace( "\r", '', $safe_text );
2710 $safe_text = str_replace( "\n", '\\n', addslashes( $safe_text ) );
2711 return apply_filters( 'js_escape', $safe_text, $text );
2715 * Escaping for HTML blocks.
2719 * @param string $text
2722 function esc_html( $text ) {
2723 $safe_text = wp_check_invalid_utf8( $text );
2724 $safe_text = _wp_specialchars( $safe_text, ENT_QUOTES );
2725 return apply_filters( 'esc_html', $safe_text, $text );
2729 * Escaping for HTML attributes.
2733 * @param string $text
2736 function esc_attr( $text ) {
2737 $safe_text = wp_check_invalid_utf8( $text );
2738 $safe_text = _wp_specialchars( $safe_text, ENT_QUOTES );
2739 return apply_filters( 'attribute_escape', $safe_text, $text );
2743 * Escaping for textarea values.
2747 * @param string $text
2750 function esc_textarea( $text ) {
2751 $safe_text = htmlspecialchars( $text, ENT_QUOTES, get_option( 'blog_charset' ) );
2752 return apply_filters( 'esc_textarea', $safe_text, $text );
2756 * Escape an HTML tag name.
2760 * @param string $tag_name
2763 function tag_escape($tag_name) {
2764 $safe_tag = strtolower( preg_replace('/[^a-zA-Z0-9_:]/', '', $tag_name) );
2765 return apply_filters('tag_escape', $safe_tag, $tag_name);
2769 * Escapes text for SQL LIKE special characters % and _.
2773 * @param string $text The text to be escaped.
2774 * @return string text, safe for inclusion in LIKE query.
2776 function like_escape($text) {
2777 return str_replace(array("%", "_"), array("\\%", "\\_"), $text);
2781 * Convert full URL paths to absolute paths.
2783 * Removes the http or https protocols and the domain. Keeps the path '/' at the
2784 * beginning, so it isn't a true relative link, but from the web root base.
2788 * @param string $link Full URL path.
2789 * @return string Absolute path.
2791 function wp_make_link_relative( $link ) {
2792 return preg_replace( '|https?://[^/]+(/.*)|i', '$1', $link );
2796 * Sanitises various option values based on the nature of the option.
2798 * This is basically a switch statement which will pass $value through a number
2799 * of functions depending on the $option.
2803 * @param string $option The name of the option.
2804 * @param string $value The unsanitised value.
2805 * @return string Sanitized value.
2807 function sanitize_option($option, $value) {
2809 switch ( $option ) {
2810 case 'admin_email' :
2811 case 'new_admin_email' :
2812 $value = sanitize_email( $value );
2813 if ( ! is_email( $value ) ) {
2814 $value = get_option( $option ); // Resets option to stored value in the case of failed sanitization
2815 if ( function_exists( 'add_settings_error' ) )
2816 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.' ) );
2820 case 'thumbnail_size_w':
2821 case 'thumbnail_size_h':
2822 case 'medium_size_w':
2823 case 'medium_size_h':
2824 case 'large_size_w':
2825 case 'large_size_h':
2826 case 'mailserver_port':
2827 case 'comment_max_links':
2828 case 'page_on_front':
2829 case 'page_for_posts':
2830 case 'rss_excerpt_length':
2831 case 'default_category':
2832 case 'default_email_category':
2833 case 'default_link_category':
2834 case 'close_comments_days_old':
2835 case 'comments_per_page':
2836 case 'thread_comments_depth':
2837 case 'users_can_register':
2838 case 'start_of_week':
2839 $value = absint( $value );
2842 case 'posts_per_page':
2843 case 'posts_per_rss':
2844 $value = (int) $value;
2845 if ( empty($value) )
2848 $value = abs($value);
2851 case 'default_ping_status':
2852 case 'default_comment_status':
2853 // Options that if not there have 0 value but need to be something like "closed"
2854 if ( $value == '0' || $value == '')
2858 case 'blogdescription':
2860 $value = wp_kses_post( $value );
2861 $value = esc_html( $value );
2864 case 'blog_charset':
2865 $value = preg_replace('/[^a-zA-Z0-9_-]/', '', $value); // strips slashes
2869 // This is the value if the settings checkbox is not checked on POST. Don't rely on this.
2870 if ( null === $value )
2873 $value = intval( $value );
2878 case 'mailserver_url':
2879 case 'mailserver_login':
2880 case 'mailserver_pass':
2882 $value = strip_tags( $value );
2883 $value = wp_kses_data( $value );
2887 $value = explode( "\n", $value );
2888 $value = array_filter( array_map( 'trim', $value ) );
2889 $value = array_filter( array_map( 'esc_url_raw', $value ) );
2890 $value = implode( "\n", $value );
2894 $value = preg_replace('/[^0-9:.-]/', '', $value); // strips slashes
2898 if ( (bool)preg_match( '#http(s?)://(.+)#i', $value) ) {
2899 $value = esc_url_raw($value);
2901 $value = get_option( $option ); // Resets option to stored value in the case of failed sanitization
2902 if ( function_exists('add_settings_error') )
2903 add_settings_error('siteurl', 'invalid_siteurl', __('The WordPress address you entered did not appear to be a valid URL. Please enter a valid URL.'));
2908 if ( (bool)preg_match( '#http(s?)://(.+)#i', $value) ) {
2909 $value = esc_url_raw($value);
2911 $value = get_option( $option ); // Resets option to stored value in the case of failed sanitization
2912 if ( function_exists('add_settings_error') )
2913 add_settings_error('home', 'invalid_home', __('The Site address you entered did not appear to be a valid URL. Please enter a valid URL.'));
2918 $allowed = get_available_languages();
2919 if ( ! in_array( $value, $allowed ) && ! empty( $value ) )
2920 $value = get_option( $option );
2923 case 'illegal_names':
2924 if ( ! is_array( $value ) )
2925 $value = explode( ' ', $value );
2927 $value = array_values( array_filter( array_map( 'trim', $value ) ) );
2933 case 'limited_email_domains':
2934 case 'banned_email_domains':
2935 if ( ! is_array( $value ) )
2936 $value = explode( "\n", $value );
2938 $domains = array_values( array_filter( array_map( 'trim', $value ) ) );
2941 foreach ( $domains as $domain ) {
2942 if ( ! preg_match( '/(--|\.\.)/', $domain ) && preg_match( '|^([a-zA-Z0-9-\.])+$|', $domain ) )
2949 case 'timezone_string':
2950 $allowed_zones = timezone_identifiers_list();
2951 if ( ! in_array( $value, $allowed_zones ) && ! empty( $value ) ) {
2952 $value = get_option( $option ); // Resets option to stored value in the case of failed sanitization
2953 if ( function_exists('add_settings_error') )
2954 add_settings_error('timezone_string', 'invalid_timezone_string', __('The timezone you have entered is not valid. Please select a valid timezone.') );
2958 case 'permalink_structure':
2959 case 'category_base':
2961 $value = esc_url_raw( $value );
2962 $value = str_replace( 'http://', '', $value );
2966 $value = apply_filters("sanitize_option_{$option}", $value, $option);
2972 * Parses a string into variables to be stored in an array.
2974 * Uses {@link http://www.php.net/parse_str parse_str()} and stripslashes if
2975 * {@link http://www.php.net/magic_quotes magic_quotes_gpc} is on.
2978 * @uses apply_filters() for the 'wp_parse_str' filter.
2980 * @param string $string The string to be parsed.
2981 * @param array $array Variables will be stored in this array.
2983 function wp_parse_str( $string, &$array ) {
2984 parse_str( $string, $array );
2985 if ( get_magic_quotes_gpc() )
2986 $array = stripslashes_deep( $array );
2987 $array = apply_filters( 'wp_parse_str', $array );
2991 * Convert lone less than signs.
2993 * KSES already converts lone greater than signs.
2995 * @uses wp_pre_kses_less_than_callback in the callback function.
2998 * @param string $text Text to be converted.
2999 * @return string Converted text.
3001 function wp_pre_kses_less_than( $text ) {
3002 return preg_replace_callback('%<[^>]*?((?=<)|>|$)%', 'wp_pre_kses_less_than_callback', $text);
3006 * Callback function used by preg_replace.
3008 * @uses esc_html to format the $matches text.
3011 * @param array $matches Populated by matches to preg_replace.
3012 * @return string The text returned after esc_html if needed.
3014 function wp_pre_kses_less_than_callback( $matches ) {
3015 if ( false === strpos($matches[0], '>') )
3016 return esc_html($matches[0]);
3021 * WordPress implementation of PHP sprintf() with filters.
3024 * @link http://www.php.net/sprintf
3026 * @param string $pattern The string which formatted args are inserted.
3027 * @param mixed $args,... Arguments to be formatted into the $pattern string.
3028 * @return string The formatted string.
3030 function wp_sprintf( $pattern ) {
3031 $args = func_get_args();
3032 $len = strlen($pattern);
3036 while ( $len > $start ) {
3037 // Last character: append and break
3038 if ( strlen($pattern) - 1 == $start ) {
3039 $result .= substr($pattern, -1);
3043 // Literal %: append and continue
3044 if ( substr($pattern, $start, 2) == '%%' ) {
3050 // Get fragment before next %
3051 $end = strpos($pattern, '%', $start + 1);
3052 if ( false === $end )
3054 $fragment = substr($pattern, $start, $end - $start);
3056 // Fragment has a specifier
3057 if ( $pattern[$start] == '%' ) {
3058 // Find numbered arguments or take the next one in order
3059 if ( preg_match('/^%(\d+)\$/', $fragment, $matches) ) {
3060 $arg = isset($args[$matches[1]]) ? $args[$matches[1]] : '';
3061 $fragment = str_replace("%{$matches[1]}$", '%', $fragment);
3064 $arg = isset($args[$arg_index]) ? $args[$arg_index] : '';
3067 // Apply filters OR sprintf
3068 $_fragment = apply_filters( 'wp_sprintf', $fragment, $arg );
3069 if ( $_fragment != $fragment )
3070 $fragment = $_fragment;
3072 $fragment = sprintf($fragment, strval($arg) );
3075 // Append to result and move to next fragment
3076 $result .= $fragment;
3083 * Localize list items before the rest of the content.
3085 * The '%l' must be at the first characters can then contain the rest of the
3086 * content. The list items will have ', ', ', and', and ' and ' added depending
3087 * on the amount of list items in the $args parameter.
3091 * @param string $pattern Content containing '%l' at the beginning.
3092 * @param array $args List items to prepend to the content and replace '%l'.
3093 * @return string Localized list items and rest of the content.
3095 function wp_sprintf_l($pattern, $args) {
3097 if ( substr($pattern, 0, 2) != '%l' )
3100 // Nothing to work with
3104 // Translate and filter the delimiter set (avoid ampersands and entities here)
3105 $l = apply_filters('wp_sprintf_l', array(
3106 /* translators: used between list items, there is a space after the comma */
3107 'between' => __(', '),
3108 /* translators: used between list items, there is a space after the and */
3109 'between_last_two' => __(', and '),
3110 /* translators: used between only two list items, there is a space after the and */
3111 'between_only_two' => __(' and '),
3114 $args = (array) $args;
3115 $result = array_shift($args);
3116 if ( count($args) == 1 )
3117 $result .= $l['between_only_two'] . array_shift($args);
3118 // Loop when more than two args
3121 $arg = array_shift($args);
3124 $result .= $l['between_last_two'] . $arg;
3126 $result .= $l['between'] . $arg;
3128 return $result . substr($pattern, 2);
3132 * Safely extracts not more than the first $count characters from html string.
3134 * UTF-8, tags and entities safe prefix extraction. Entities inside will *NOT*
3135 * be counted as one character. For example & will be counted as 4, < as
3140 * @param string $str String to get the excerpt from.
3141 * @param integer $count Maximum number of characters to take.
3142 * @param string $more Optional. What to append if $str needs to be trimmed. Defaults to empty string.
3143 * @return string The excerpt.
3145 function wp_html_excerpt( $str, $count, $more = null ) {
3146 if ( null === $more )
3148 $str = wp_strip_all_tags( $str, true );
3149 $excerpt = mb_substr( $str, 0, $count );
3150 // remove part of an entity at the end
3151 $excerpt = preg_replace( '/&[^;\s]{0,6}$/', '', $excerpt );
3152 if ( $str != $excerpt )
3153 $excerpt = trim( $excerpt ) . $more;
3158 * Add a Base url to relative links in passed content.
3160 * By default it supports the 'src' and 'href' attributes. However this can be
3161 * changed via the 3rd param.
3165 * @param string $content String to search for links in.
3166 * @param string $base The base URL to prefix to links.
3167 * @param array $attrs The attributes which should be processed.
3168 * @return string The processed content.
3170 function links_add_base_url( $content, $base, $attrs = array('src', 'href') ) {
3171 global $_links_add_base;
3172 $_links_add_base = $base;
3173 $attrs = implode('|', (array)$attrs);
3174 return preg_replace_callback( "!($attrs)=(['\"])(.+?)\\2!i", '_links_add_base', $content );
3178 * Callback to add a base url to relative links in passed content.
3183 * @param string $m The matched link.
3184 * @return string The processed link.
3186 function _links_add_base($m) {
3187 global $_links_add_base;
3188 //1 = attribute name 2 = quotation mark 3 = URL
3189 return $m[1] . '=' . $m[2] .
3190 ( preg_match( '#^(\w{1,20}):#', $m[3], $protocol ) && in_array( $protocol[1], wp_allowed_protocols() ) ?
3192 path_join( $_links_add_base, $m[3] ) )
3197 * Adds a Target attribute to all links in passed content.
3199 * This function by default only applies to <a> tags, however this can be
3200 * modified by the 3rd param.
3202 * <b>NOTE:</b> Any current target attributed will be stripped and replaced.
3206 * @param string $content String to search for links in.
3207 * @param string $target The Target to add to the links.
3208 * @param array $tags An array of tags to apply to.
3209 * @return string The processed content.
3211 function links_add_target( $content, $target = '_blank', $tags = array('a') ) {
3212 global $_links_add_target;
3213 $_links_add_target = $target;
3214 $tags = implode('|', (array)$tags);
3215 return preg_replace_callback( "!<($tags)(.+?)>!i", '_links_add_target', $content );
3219 * Callback to add a target attribute to all links in passed content.
3224 * @param string $m The matched link.
3225 * @return string The processed link.
3227 function _links_add_target( $m ) {
3228 global $_links_add_target;
3230 $link = preg_replace('|(target=([\'"])(.*?)\2)|i', '', $m[2]);
3231 return '<' . $tag . $link . ' target="' . esc_attr( $_links_add_target ) . '">';
3235 * Normalize EOL characters and strip duplicate whitespace.
3239 * @param string $str The string to normalize.
3240 * @return string The normalized string.
3242 function normalize_whitespace( $str ) {
3243 $str = trim( $str );
3244 $str = str_replace( "\r", "\n", $str );
3245 $str = preg_replace( array( '/\n+/', '/[ \t]+/' ), array( "\n", ' ' ), $str );
3250 * Properly strip all HTML tags including script and style
3254 * @param string $string String containing HTML tags
3255 * @param bool $remove_breaks optional Whether to remove left over line breaks and white space chars
3256 * @return string The processed string.
3258 function wp_strip_all_tags($string, $remove_breaks = false) {
3259 $string = preg_replace( '@<(script|style)[^>]*?>.*?</\\1>@si', '', $string );
3260 $string = strip_tags($string);
3262 if ( $remove_breaks )
3263 $string = preg_replace('/[\r\n\t ]+/', ' ', $string);
3265 return trim( $string );
3269 * Sanitize a string from user input or from the db
3271 * check for invalid UTF-8,
3272 * Convert single < characters to entity,
3274 * remove line breaks, tabs and extra white space,
3279 * @param string $str
3282 function sanitize_text_field($str) {
3283 $filtered = wp_check_invalid_utf8( $str );
3285 if ( strpos($filtered, '<') !== false ) {
3286 $filtered = wp_pre_kses_less_than( $filtered );
3287 // This will strip extra whitespace for us.
3288 $filtered = wp_strip_all_tags( $filtered, true );
3290 $filtered = trim( preg_replace('/[\r\n\t ]+/', ' ', $filtered) );
3294 while ( preg_match('/%[a-f0-9]{2}/i', $filtered, $match) ) {
3295 $filtered = str_replace($match[0], '', $filtered);
3300 // Strip out the whitespace that may now exist after removing the octets.
3301 $filtered = trim( preg_replace('/ +/', ' ', $filtered) );
3304 return apply_filters('sanitize_text_field', $filtered, $str);
3308 * i18n friendly version of basename()
3312 * @param string $path A path.
3313 * @param string $suffix If the filename ends in suffix this will also be cut off.
3316 function wp_basename( $path, $suffix = '' ) {
3317 return urldecode( basename( str_replace( array( '%2F', '%5C' ), '/', urlencode( $path ) ), $suffix ) );
3321 * Forever eliminate "Wordpress" from the planet (or at least the little bit we can influence).
3323 * Violating our coding standards for a good function name.
3327 function capital_P_dangit( $text ) {
3328 // Simple replacement for titles
3329 if ( 'the_title' === current_filter() )
3330 return str_replace( 'Wordpress', 'WordPress', $text );
3331 // Still here? Use the more judicious replacement
3332 static $dblq = false;
3333 if ( false === $dblq )
3334 $dblq = _x( '“', 'opening curly double quote' );
3336 array( ' Wordpress', '‘Wordpress', $dblq . 'Wordpress', '>Wordpress', '(Wordpress' ),
3337 array( ' WordPress', '‘WordPress', $dblq . 'WordPress', '>WordPress', '(WordPress' ),
3343 * Sanitize a mime type
3347 * @param string $mime_type Mime type
3348 * @return string Sanitized mime type
3350 function sanitize_mime_type( $mime_type ) {
3351 $sani_mime_type = preg_replace( '/[^-+*.a-zA-Z0-9\/]/', '', $mime_type );
3352 return apply_filters( 'sanitize_mime_type', $sani_mime_type, $mime_type );
3356 * Sanitize space or carriage return separated URLs that are used to send trackbacks.
3360 * @param string $to_ping Space or carriage return separated URLs
3361 * @return string URLs starting with the http or https protocol, separated by a carriage return.
3363 function sanitize_trackback_urls( $to_ping ) {
3364 $urls_to_ping = preg_split( '/[\r\n\t ]/', trim( $to_ping ), -1, PREG_SPLIT_NO_EMPTY );
3365 foreach ( $urls_to_ping as $k => $url ) {
3366 if ( !preg_match( '#^https?://.#i', $url ) )
3367 unset( $urls_to_ping[$k] );
3369 $urls_to_ping = array_map( 'esc_url_raw', $urls_to_ping );
3370 $urls_to_ping = implode( "\n", $urls_to_ping );
3371 return apply_filters( 'sanitize_trackback_urls', $urls_to_ping, $to_ping );
3375 * Add slashes to a string or array of strings.
3377 * This should be used when preparing data for core API that expects slashed data.
3378 * This should not be used to escape data going directly into an SQL query.
3382 * @param string|array $value String or array of strings to slash.
3383 * @return string|array Slashed $value
3385 function wp_slash( $value ) {
3386 if ( is_array( $value ) ) {
3387 foreach ( $value as $k => $v ) {
3388 if ( is_array( $v ) ) {
3389 $value[$k] = wp_slash( $v );
3391 $value[$k] = addslashes( $v );
3395 $value = addslashes( $value );
3402 * Remove slashes from a string or array of strings.
3404 * This should be used to remove slashes from data passed to core API that
3405 * expects data to be unslashed.
3409 * @param string|array $value String or array of strings to unslash.
3410 * @return string|array Unslashed $value
3412 function wp_unslash( $value ) {
3413 return stripslashes_deep( $value );
3417 * Extract and return the first URL from passed content.
3421 * @param string $content A string which might contain a URL.
3422 * @return string The found URL.
3424 function get_url_in_content( $content ) {
3425 if ( empty( $content ) )
3428 if ( preg_match( '/<a\s[^>]*?href=([\'"])(.+?)\1/is', $content, $matches ) )
3429 return esc_url_raw( $matches[2] );