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|samp|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
265 * @param array $matches preg_replace_callback matches array
268 function _autop_newline_preservation_helper( $matches ) {
269 return str_replace("\n", "<WPPreserveNewline />", $matches[0]);
273 * Don't auto-p wrap shortcodes that stand alone
275 * Ensures that shortcodes are not wrapped in <<p>>...<</p>>.
279 * @param string $pee The content.
280 * @return string The filtered content.
282 function shortcode_unautop( $pee ) {
283 global $shortcode_tags;
285 if ( empty( $shortcode_tags ) || !is_array( $shortcode_tags ) ) {
289 $tagregexp = join( '|', array_map( 'preg_quote', array_keys( $shortcode_tags ) ) );
293 . '<p>' // Opening paragraph
294 . '\\s*+' // Optional leading whitespace
295 . '(' // 1: The shortcode
296 . '\\[' // Opening bracket
297 . "($tagregexp)" // 2: Shortcode name
298 . '(?![\\w-])' // Not followed by word character or hyphen
299 // Unroll the loop: Inside the opening shortcode tag
300 . '[^\\]\\/]*' // Not a closing bracket or forward slash
302 . '\\/(?!\\])' // A forward slash not followed by a closing bracket
303 . '[^\\]\\/]*' // Not a closing bracket or forward slash
306 . '\\/\\]' // Self closing tag and closing bracket
308 . '\\]' // Closing bracket
309 . '(?:' // Unroll the loop: Optionally, anything between the opening and closing shortcode tags
310 . '[^\\[]*+' // Not an opening bracket
312 . '\\[(?!\\/\\2\\])' // An opening bracket not followed by the closing shortcode tag
313 . '[^\\[]*+' // Not an opening bracket
315 . '\\[\\/\\2\\]' // Closing shortcode tag
319 . '\\s*+' // optional trailing whitespace
320 . '<\\/p>' // closing paragraph
323 return preg_replace( $pattern, '$1', $pee );
327 * Checks to see if a string is utf8 encoded.
329 * NOTE: This function checks for 5-Byte sequences, UTF8
330 * has Bytes Sequences with a maximum length of 4.
332 * @author bmorel at ssi dot fr (modified)
335 * @param string $str The string to be checked
336 * @return bool True if $str fits a UTF-8 model, false otherwise.
338 function seems_utf8($str) {
339 $length = strlen($str);
340 for ($i=0; $i < $length; $i++) {
342 if ($c < 0x80) $n = 0; # 0bbbbbbb
343 elseif (($c & 0xE0) == 0xC0) $n=1; # 110bbbbb
344 elseif (($c & 0xF0) == 0xE0) $n=2; # 1110bbbb
345 elseif (($c & 0xF8) == 0xF0) $n=3; # 11110bbb
346 elseif (($c & 0xFC) == 0xF8) $n=4; # 111110bb
347 elseif (($c & 0xFE) == 0xFC) $n=5; # 1111110b
348 else return false; # Does not match any model
349 for ($j=0; $j<$n; $j++) { # n bytes matching 10bbbbbb follow ?
350 if ((++$i == $length) || ((ord($str[$i]) & 0xC0) != 0x80))
358 * Converts a number of special characters into their HTML entities.
360 * Specifically deals with: &, <, >, ", and '.
362 * $quote_style can be set to ENT_COMPAT to encode " to
363 * ", or ENT_QUOTES to do both. Default is ENT_NOQUOTES where no quotes are encoded.
367 * @param string $string The text which is to be encoded.
368 * @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.
369 * @param string $charset Optional. The character encoding of the string. Default is false.
370 * @param boolean $double_encode Optional. Whether to encode existing html entities. Default is false.
371 * @return string The encoded text with HTML entities.
373 function _wp_specialchars( $string, $quote_style = ENT_NOQUOTES, $charset = false, $double_encode = false ) {
374 $string = (string) $string;
376 if ( 0 === strlen( $string ) )
379 // Don't bother if there are no specialchars - saves some processing
380 if ( ! preg_match( '/[&<>"\']/', $string ) )
383 // Account for the previous behaviour of the function when the $quote_style is not an accepted value
384 if ( empty( $quote_style ) )
385 $quote_style = ENT_NOQUOTES;
386 elseif ( ! in_array( $quote_style, array( 0, 2, 3, 'single', 'double' ), true ) )
387 $quote_style = ENT_QUOTES;
389 // Store the site charset as a static to avoid multiple calls to wp_load_alloptions()
392 if ( ! isset( $_charset ) ) {
393 $alloptions = wp_load_alloptions();
394 $_charset = isset( $alloptions['blog_charset'] ) ? $alloptions['blog_charset'] : '';
396 $charset = $_charset;
399 if ( in_array( $charset, array( 'utf8', 'utf-8', 'UTF8' ) ) )
402 $_quote_style = $quote_style;
404 if ( $quote_style === 'double' ) {
405 $quote_style = ENT_COMPAT;
406 $_quote_style = ENT_COMPAT;
407 } elseif ( $quote_style === 'single' ) {
408 $quote_style = ENT_NOQUOTES;
411 // Handle double encoding ourselves
412 if ( $double_encode ) {
413 $string = @htmlspecialchars( $string, $quote_style, $charset );
415 // Decode & into &
416 $string = wp_specialchars_decode( $string, $_quote_style );
418 // Guarantee every &entity; is valid or re-encode the &
419 $string = wp_kses_normalize_entities( $string );
421 // Now re-encode everything except &entity;
422 $string = preg_split( '/(&#?x?[0-9a-z]+;)/i', $string, -1, PREG_SPLIT_DELIM_CAPTURE );
424 for ( $i = 0; $i < count( $string ); $i += 2 )
425 $string[$i] = @htmlspecialchars( $string[$i], $quote_style, $charset );
427 $string = implode( '', $string );
430 // Backwards compatibility
431 if ( 'single' === $_quote_style )
432 $string = str_replace( "'", ''', $string );
438 * Converts a number of HTML entities into their special characters.
440 * Specifically deals with: &, <, >, ", and '.
442 * $quote_style can be set to ENT_COMPAT to decode " entities,
443 * or ENT_QUOTES to do both " and '. Default is ENT_NOQUOTES where no quotes are decoded.
447 * @param string $string The text which is to be decoded.
448 * @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.
449 * @return string The decoded text without HTML entities.
451 function wp_specialchars_decode( $string, $quote_style = ENT_NOQUOTES ) {
452 $string = (string) $string;
454 if ( 0 === strlen( $string ) ) {
458 // Don't bother if there are no entities - saves a lot of processing
459 if ( strpos( $string, '&' ) === false ) {
463 // Match the previous behaviour of _wp_specialchars() when the $quote_style is not an accepted value
464 if ( empty( $quote_style ) ) {
465 $quote_style = ENT_NOQUOTES;
466 } elseif ( !in_array( $quote_style, array( 0, 2, 3, 'single', 'double' ), true ) ) {
467 $quote_style = ENT_QUOTES;
470 // More complete than get_html_translation_table( HTML_SPECIALCHARS )
471 $single = array( ''' => '\'', ''' => '\'' );
472 $single_preg = array( '/�*39;/' => ''', '/�*27;/i' => ''' );
473 $double = array( '"' => '"', '"' => '"', '"' => '"' );
474 $double_preg = array( '/�*34;/' => '"', '/�*22;/i' => '"' );
475 $others = array( '<' => '<', '<' => '<', '>' => '>', '>' => '>', '&' => '&', '&' => '&', '&' => '&' );
476 $others_preg = array( '/�*60;/' => '<', '/�*62;/' => '>', '/�*38;/' => '&', '/�*26;/i' => '&' );
478 if ( $quote_style === ENT_QUOTES ) {
479 $translation = array_merge( $single, $double, $others );
480 $translation_preg = array_merge( $single_preg, $double_preg, $others_preg );
481 } elseif ( $quote_style === ENT_COMPAT || $quote_style === 'double' ) {
482 $translation = array_merge( $double, $others );
483 $translation_preg = array_merge( $double_preg, $others_preg );
484 } elseif ( $quote_style === 'single' ) {
485 $translation = array_merge( $single, $others );
486 $translation_preg = array_merge( $single_preg, $others_preg );
487 } elseif ( $quote_style === ENT_NOQUOTES ) {
488 $translation = $others;
489 $translation_preg = $others_preg;
492 // Remove zero padding on numeric entities
493 $string = preg_replace( array_keys( $translation_preg ), array_values( $translation_preg ), $string );
495 // Replace characters according to translation table
496 return strtr( $string, $translation );
500 * Checks for invalid UTF8 in a string.
504 * @param string $string The text which is to be checked.
505 * @param boolean $strip Optional. Whether to attempt to strip out invalid UTF8. Default is false.
506 * @return string The checked text.
508 function wp_check_invalid_utf8( $string, $strip = false ) {
509 $string = (string) $string;
511 if ( 0 === strlen( $string ) ) {
515 // Store the site charset as a static to avoid multiple calls to get_option()
517 if ( !isset( $is_utf8 ) ) {
518 $is_utf8 = in_array( get_option( 'blog_charset' ), array( 'utf8', 'utf-8', 'UTF8', 'UTF-8' ) );
524 // Check for support for utf8 in the installed PCRE library once and store the result in a static
526 if ( !isset( $utf8_pcre ) ) {
527 $utf8_pcre = @preg_match( '/^./u', 'a' );
529 // We can't demand utf8 in the PCRE installation, so just return the string in those cases
534 // preg_match fails when it encounters invalid UTF8 in $string
535 if ( 1 === @preg_match( '/^./us', $string ) ) {
539 // Attempt to strip the bad chars if requested (not recommended)
540 if ( $strip && function_exists( 'iconv' ) ) {
541 return iconv( 'utf-8', 'utf-8', $string );
548 * Encode the Unicode values to be used in the URI.
552 * @param string $utf8_string
553 * @param int $length Max length of the string
554 * @return string String with Unicode encoded for URI.
556 function utf8_uri_encode( $utf8_string, $length = 0 ) {
562 $string_length = strlen( $utf8_string );
563 for ($i = 0; $i < $string_length; $i++ ) {
565 $value = ord( $utf8_string[ $i ] );
567 if ( $value < 128 ) {
568 if ( $length && ( $unicode_length >= $length ) )
570 $unicode .= chr($value);
573 if ( count( $values ) == 0 ) $num_octets = ( $value < 224 ) ? 2 : 3;
577 if ( $length && ( $unicode_length + ($num_octets * 3) ) > $length )
579 if ( count( $values ) == $num_octets ) {
580 if ($num_octets == 3) {
581 $unicode .= '%' . dechex($values[0]) . '%' . dechex($values[1]) . '%' . dechex($values[2]);
582 $unicode_length += 9;
584 $unicode .= '%' . dechex($values[0]) . '%' . dechex($values[1]);
585 $unicode_length += 6;
598 * Converts all accent characters to ASCII characters.
600 * If there are no accent characters, then the string given is just returned.
604 * @param string $string Text that might have accent characters
605 * @return string Filtered string with replaced "nice" characters.
607 function remove_accents($string) {
608 if ( !preg_match('/[\x80-\xff]/', $string) )
611 if (seems_utf8($string)) {
613 // Decompositions for Latin-1 Supplement
614 chr(194).chr(170) => 'a', chr(194).chr(186) => 'o',
615 chr(195).chr(128) => 'A', chr(195).chr(129) => 'A',
616 chr(195).chr(130) => 'A', chr(195).chr(131) => 'A',
617 chr(195).chr(132) => 'A', chr(195).chr(133) => 'A',
618 chr(195).chr(134) => 'AE',chr(195).chr(135) => 'C',
619 chr(195).chr(136) => 'E', chr(195).chr(137) => 'E',
620 chr(195).chr(138) => 'E', chr(195).chr(139) => 'E',
621 chr(195).chr(140) => 'I', chr(195).chr(141) => 'I',
622 chr(195).chr(142) => 'I', chr(195).chr(143) => 'I',
623 chr(195).chr(144) => 'D', chr(195).chr(145) => 'N',
624 chr(195).chr(146) => 'O', chr(195).chr(147) => 'O',
625 chr(195).chr(148) => 'O', chr(195).chr(149) => 'O',
626 chr(195).chr(150) => 'O', chr(195).chr(153) => 'U',
627 chr(195).chr(154) => 'U', chr(195).chr(155) => 'U',
628 chr(195).chr(156) => 'U', chr(195).chr(157) => 'Y',
629 chr(195).chr(158) => 'TH',chr(195).chr(159) => 's',
630 chr(195).chr(160) => 'a', chr(195).chr(161) => 'a',
631 chr(195).chr(162) => 'a', chr(195).chr(163) => 'a',
632 chr(195).chr(164) => 'a', chr(195).chr(165) => 'a',
633 chr(195).chr(166) => 'ae',chr(195).chr(167) => 'c',
634 chr(195).chr(168) => 'e', chr(195).chr(169) => 'e',
635 chr(195).chr(170) => 'e', chr(195).chr(171) => 'e',
636 chr(195).chr(172) => 'i', chr(195).chr(173) => 'i',
637 chr(195).chr(174) => 'i', chr(195).chr(175) => 'i',
638 chr(195).chr(176) => 'd', chr(195).chr(177) => 'n',
639 chr(195).chr(178) => 'o', chr(195).chr(179) => 'o',
640 chr(195).chr(180) => 'o', chr(195).chr(181) => 'o',
641 chr(195).chr(182) => 'o', chr(195).chr(184) => 'o',
642 chr(195).chr(185) => 'u', chr(195).chr(186) => 'u',
643 chr(195).chr(187) => 'u', chr(195).chr(188) => 'u',
644 chr(195).chr(189) => 'y', chr(195).chr(190) => 'th',
645 chr(195).chr(191) => 'y', chr(195).chr(152) => 'O',
646 // Decompositions for Latin Extended-A
647 chr(196).chr(128) => 'A', chr(196).chr(129) => 'a',
648 chr(196).chr(130) => 'A', chr(196).chr(131) => 'a',
649 chr(196).chr(132) => 'A', chr(196).chr(133) => 'a',
650 chr(196).chr(134) => 'C', chr(196).chr(135) => 'c',
651 chr(196).chr(136) => 'C', chr(196).chr(137) => 'c',
652 chr(196).chr(138) => 'C', chr(196).chr(139) => 'c',
653 chr(196).chr(140) => 'C', chr(196).chr(141) => 'c',
654 chr(196).chr(142) => 'D', chr(196).chr(143) => 'd',
655 chr(196).chr(144) => 'D', chr(196).chr(145) => 'd',
656 chr(196).chr(146) => 'E', chr(196).chr(147) => 'e',
657 chr(196).chr(148) => 'E', chr(196).chr(149) => 'e',
658 chr(196).chr(150) => 'E', chr(196).chr(151) => 'e',
659 chr(196).chr(152) => 'E', chr(196).chr(153) => 'e',
660 chr(196).chr(154) => 'E', chr(196).chr(155) => 'e',
661 chr(196).chr(156) => 'G', chr(196).chr(157) => 'g',
662 chr(196).chr(158) => 'G', chr(196).chr(159) => 'g',
663 chr(196).chr(160) => 'G', chr(196).chr(161) => 'g',
664 chr(196).chr(162) => 'G', chr(196).chr(163) => 'g',
665 chr(196).chr(164) => 'H', chr(196).chr(165) => 'h',
666 chr(196).chr(166) => 'H', chr(196).chr(167) => 'h',
667 chr(196).chr(168) => 'I', chr(196).chr(169) => 'i',
668 chr(196).chr(170) => 'I', chr(196).chr(171) => 'i',
669 chr(196).chr(172) => 'I', chr(196).chr(173) => 'i',
670 chr(196).chr(174) => 'I', chr(196).chr(175) => 'i',
671 chr(196).chr(176) => 'I', chr(196).chr(177) => 'i',
672 chr(196).chr(178) => 'IJ',chr(196).chr(179) => 'ij',
673 chr(196).chr(180) => 'J', chr(196).chr(181) => 'j',
674 chr(196).chr(182) => 'K', chr(196).chr(183) => 'k',
675 chr(196).chr(184) => 'k', chr(196).chr(185) => 'L',
676 chr(196).chr(186) => 'l', chr(196).chr(187) => 'L',
677 chr(196).chr(188) => 'l', chr(196).chr(189) => 'L',
678 chr(196).chr(190) => 'l', chr(196).chr(191) => 'L',
679 chr(197).chr(128) => 'l', chr(197).chr(129) => 'L',
680 chr(197).chr(130) => 'l', chr(197).chr(131) => 'N',
681 chr(197).chr(132) => 'n', chr(197).chr(133) => 'N',
682 chr(197).chr(134) => 'n', chr(197).chr(135) => 'N',
683 chr(197).chr(136) => 'n', chr(197).chr(137) => 'N',
684 chr(197).chr(138) => 'n', chr(197).chr(139) => 'N',
685 chr(197).chr(140) => 'O', chr(197).chr(141) => 'o',
686 chr(197).chr(142) => 'O', chr(197).chr(143) => 'o',
687 chr(197).chr(144) => 'O', chr(197).chr(145) => 'o',
688 chr(197).chr(146) => 'OE',chr(197).chr(147) => 'oe',
689 chr(197).chr(148) => 'R',chr(197).chr(149) => 'r',
690 chr(197).chr(150) => 'R',chr(197).chr(151) => 'r',
691 chr(197).chr(152) => 'R',chr(197).chr(153) => 'r',
692 chr(197).chr(154) => 'S',chr(197).chr(155) => 's',
693 chr(197).chr(156) => 'S',chr(197).chr(157) => 's',
694 chr(197).chr(158) => 'S',chr(197).chr(159) => 's',
695 chr(197).chr(160) => 'S', chr(197).chr(161) => 's',
696 chr(197).chr(162) => 'T', chr(197).chr(163) => 't',
697 chr(197).chr(164) => 'T', chr(197).chr(165) => 't',
698 chr(197).chr(166) => 'T', chr(197).chr(167) => 't',
699 chr(197).chr(168) => 'U', chr(197).chr(169) => 'u',
700 chr(197).chr(170) => 'U', chr(197).chr(171) => 'u',
701 chr(197).chr(172) => 'U', chr(197).chr(173) => 'u',
702 chr(197).chr(174) => 'U', chr(197).chr(175) => 'u',
703 chr(197).chr(176) => 'U', chr(197).chr(177) => 'u',
704 chr(197).chr(178) => 'U', chr(197).chr(179) => 'u',
705 chr(197).chr(180) => 'W', chr(197).chr(181) => 'w',
706 chr(197).chr(182) => 'Y', chr(197).chr(183) => 'y',
707 chr(197).chr(184) => 'Y', chr(197).chr(185) => 'Z',
708 chr(197).chr(186) => 'z', chr(197).chr(187) => 'Z',
709 chr(197).chr(188) => 'z', chr(197).chr(189) => 'Z',
710 chr(197).chr(190) => 'z', chr(197).chr(191) => 's',
711 // Decompositions for Latin Extended-B
712 chr(200).chr(152) => 'S', chr(200).chr(153) => 's',
713 chr(200).chr(154) => 'T', chr(200).chr(155) => 't',
715 chr(226).chr(130).chr(172) => 'E',
717 chr(194).chr(163) => '',
718 // Vowels with diacritic (Vietnamese)
720 chr(198).chr(160) => 'O', chr(198).chr(161) => 'o',
721 chr(198).chr(175) => 'U', chr(198).chr(176) => 'u',
723 chr(225).chr(186).chr(166) => 'A', chr(225).chr(186).chr(167) => 'a',
724 chr(225).chr(186).chr(176) => 'A', chr(225).chr(186).chr(177) => 'a',
725 chr(225).chr(187).chr(128) => 'E', chr(225).chr(187).chr(129) => 'e',
726 chr(225).chr(187).chr(146) => 'O', chr(225).chr(187).chr(147) => 'o',
727 chr(225).chr(187).chr(156) => 'O', chr(225).chr(187).chr(157) => 'o',
728 chr(225).chr(187).chr(170) => 'U', chr(225).chr(187).chr(171) => 'u',
729 chr(225).chr(187).chr(178) => 'Y', chr(225).chr(187).chr(179) => 'y',
731 chr(225).chr(186).chr(162) => 'A', chr(225).chr(186).chr(163) => 'a',
732 chr(225).chr(186).chr(168) => 'A', chr(225).chr(186).chr(169) => 'a',
733 chr(225).chr(186).chr(178) => 'A', chr(225).chr(186).chr(179) => 'a',
734 chr(225).chr(186).chr(186) => 'E', chr(225).chr(186).chr(187) => 'e',
735 chr(225).chr(187).chr(130) => 'E', chr(225).chr(187).chr(131) => 'e',
736 chr(225).chr(187).chr(136) => 'I', chr(225).chr(187).chr(137) => 'i',
737 chr(225).chr(187).chr(142) => 'O', chr(225).chr(187).chr(143) => 'o',
738 chr(225).chr(187).chr(148) => 'O', chr(225).chr(187).chr(149) => 'o',
739 chr(225).chr(187).chr(158) => 'O', chr(225).chr(187).chr(159) => 'o',
740 chr(225).chr(187).chr(166) => 'U', chr(225).chr(187).chr(167) => 'u',
741 chr(225).chr(187).chr(172) => 'U', chr(225).chr(187).chr(173) => 'u',
742 chr(225).chr(187).chr(182) => 'Y', chr(225).chr(187).chr(183) => 'y',
744 chr(225).chr(186).chr(170) => 'A', chr(225).chr(186).chr(171) => 'a',
745 chr(225).chr(186).chr(180) => 'A', chr(225).chr(186).chr(181) => 'a',
746 chr(225).chr(186).chr(188) => 'E', chr(225).chr(186).chr(189) => 'e',
747 chr(225).chr(187).chr(132) => 'E', chr(225).chr(187).chr(133) => 'e',
748 chr(225).chr(187).chr(150) => 'O', chr(225).chr(187).chr(151) => 'o',
749 chr(225).chr(187).chr(160) => 'O', chr(225).chr(187).chr(161) => 'o',
750 chr(225).chr(187).chr(174) => 'U', chr(225).chr(187).chr(175) => 'u',
751 chr(225).chr(187).chr(184) => 'Y', chr(225).chr(187).chr(185) => 'y',
753 chr(225).chr(186).chr(164) => 'A', chr(225).chr(186).chr(165) => 'a',
754 chr(225).chr(186).chr(174) => 'A', chr(225).chr(186).chr(175) => 'a',
755 chr(225).chr(186).chr(190) => 'E', chr(225).chr(186).chr(191) => 'e',
756 chr(225).chr(187).chr(144) => 'O', chr(225).chr(187).chr(145) => 'o',
757 chr(225).chr(187).chr(154) => 'O', chr(225).chr(187).chr(155) => 'o',
758 chr(225).chr(187).chr(168) => 'U', chr(225).chr(187).chr(169) => 'u',
760 chr(225).chr(186).chr(160) => 'A', chr(225).chr(186).chr(161) => 'a',
761 chr(225).chr(186).chr(172) => 'A', chr(225).chr(186).chr(173) => 'a',
762 chr(225).chr(186).chr(182) => 'A', chr(225).chr(186).chr(183) => 'a',
763 chr(225).chr(186).chr(184) => 'E', chr(225).chr(186).chr(185) => 'e',
764 chr(225).chr(187).chr(134) => 'E', chr(225).chr(187).chr(135) => 'e',
765 chr(225).chr(187).chr(138) => 'I', chr(225).chr(187).chr(139) => 'i',
766 chr(225).chr(187).chr(140) => 'O', chr(225).chr(187).chr(141) => 'o',
767 chr(225).chr(187).chr(152) => 'O', chr(225).chr(187).chr(153) => 'o',
768 chr(225).chr(187).chr(162) => 'O', chr(225).chr(187).chr(163) => 'o',
769 chr(225).chr(187).chr(164) => 'U', chr(225).chr(187).chr(165) => 'u',
770 chr(225).chr(187).chr(176) => 'U', chr(225).chr(187).chr(177) => 'u',
771 chr(225).chr(187).chr(180) => 'Y', chr(225).chr(187).chr(181) => 'y',
772 // Vowels with diacritic (Chinese, Hanyu Pinyin)
773 chr(201).chr(145) => 'a',
775 chr(199).chr(149) => 'U', chr(199).chr(150) => 'u',
777 chr(199).chr(151) => 'U', chr(199).chr(152) => 'u',
779 chr(199).chr(141) => 'A', chr(199).chr(142) => 'a',
780 chr(199).chr(143) => 'I', chr(199).chr(144) => 'i',
781 chr(199).chr(145) => 'O', chr(199).chr(146) => 'o',
782 chr(199).chr(147) => 'U', chr(199).chr(148) => 'u',
783 chr(199).chr(153) => 'U', chr(199).chr(154) => 'u',
785 chr(199).chr(155) => 'U', chr(199).chr(156) => 'u',
788 $string = strtr($string, $chars);
790 // Assume ISO-8859-1 if not UTF-8
791 $chars['in'] = chr(128).chr(131).chr(138).chr(142).chr(154).chr(158)
792 .chr(159).chr(162).chr(165).chr(181).chr(192).chr(193).chr(194)
793 .chr(195).chr(196).chr(197).chr(199).chr(200).chr(201).chr(202)
794 .chr(203).chr(204).chr(205).chr(206).chr(207).chr(209).chr(210)
795 .chr(211).chr(212).chr(213).chr(214).chr(216).chr(217).chr(218)
796 .chr(219).chr(220).chr(221).chr(224).chr(225).chr(226).chr(227)
797 .chr(228).chr(229).chr(231).chr(232).chr(233).chr(234).chr(235)
798 .chr(236).chr(237).chr(238).chr(239).chr(241).chr(242).chr(243)
799 .chr(244).chr(245).chr(246).chr(248).chr(249).chr(250).chr(251)
800 .chr(252).chr(253).chr(255);
802 $chars['out'] = "EfSZszYcYuAAAAAACEEEEIIIINOOOOOOUUUUYaaaaaaceeeeiiiinoooooouuuuyy";
804 $string = strtr($string, $chars['in'], $chars['out']);
805 $double_chars['in'] = array(chr(140), chr(156), chr(198), chr(208), chr(222), chr(223), chr(230), chr(240), chr(254));
806 $double_chars['out'] = array('OE', 'oe', 'AE', 'DH', 'TH', 'ss', 'ae', 'dh', 'th');
807 $string = str_replace($double_chars['in'], $double_chars['out'], $string);
814 * Sanitizes a filename replacing whitespace with dashes
816 * Removes special characters that are illegal in filenames on certain
817 * operating systems and special characters requiring special escaping
818 * to manipulate at the command line. Replaces spaces and consecutive
819 * dashes with a single dash. Trim period, dash and underscore from beginning
820 * and end of filename.
824 * @param string $filename The filename to be sanitized
825 * @return string The sanitized filename
827 function sanitize_file_name( $filename ) {
828 $filename_raw = $filename;
829 $special_chars = array("?", "[", "]", "/", "\\", "=", "<", ">", ":", ";", ",", "'", "\"", "&", "$", "#", "*", "(", ")", "|", "~", "`", "!", "{", "}", chr(0));
830 $special_chars = apply_filters('sanitize_file_name_chars', $special_chars, $filename_raw);
831 $filename = str_replace($special_chars, '', $filename);
832 $filename = preg_replace('/[\s-]+/', '-', $filename);
833 $filename = trim($filename, '.-_');
835 // Split the filename into a base and extension[s]
836 $parts = explode('.', $filename);
838 // Return if only one extension
839 if ( count($parts) <= 2 )
840 return apply_filters('sanitize_file_name', $filename, $filename_raw);
842 // Process multiple extensions
843 $filename = array_shift($parts);
844 $extension = array_pop($parts);
845 $mimes = get_allowed_mime_types();
847 // Loop over any intermediate extensions. Munge them with a trailing underscore if they are a 2 - 5 character
848 // long alpha string not in the extension whitelist.
849 foreach ( (array) $parts as $part) {
850 $filename .= '.' . $part;
852 if ( preg_match("/^[a-zA-Z]{2,5}\d?$/", $part) ) {
854 foreach ( $mimes as $ext_preg => $mime_match ) {
855 $ext_preg = '!^(' . $ext_preg . ')$!i';
856 if ( preg_match( $ext_preg, $part ) ) {
865 $filename .= '.' . $extension;
867 return apply_filters('sanitize_file_name', $filename, $filename_raw);
871 * Sanitize username stripping out unsafe characters.
873 * Removes tags, octets, entities, and if strict is enabled, will only keep
874 * alphanumeric, _, space, ., -, @. After sanitizing, it passes the username,
875 * raw username (the username in the parameter), and the value of $strict as
876 * parameters for the 'sanitize_user' filter.
879 * @uses apply_filters() Calls 'sanitize_user' hook on username, raw username,
880 * and $strict parameter.
882 * @param string $username The username to be sanitized.
883 * @param bool $strict If set limits $username to specific characters. Default false.
884 * @return string The sanitized username, after passing through filters.
886 function sanitize_user( $username, $strict = false ) {
887 $raw_username = $username;
888 $username = wp_strip_all_tags( $username );
889 $username = remove_accents( $username );
891 $username = preg_replace( '|%([a-fA-F0-9][a-fA-F0-9])|', '', $username );
892 $username = preg_replace( '/&.+?;/', '', $username ); // Kill entities
894 // If strict, reduce to ASCII for max portability.
896 $username = preg_replace( '|[^a-z0-9 _.\-@]|i', '', $username );
898 $username = trim( $username );
899 // Consolidate contiguous whitespace
900 $username = preg_replace( '|\s+|', ' ', $username );
902 return apply_filters( 'sanitize_user', $username, $raw_username, $strict );
906 * Sanitize a string key.
908 * Keys are used as internal identifiers. Lowercase alphanumeric characters, dashes and underscores are allowed.
912 * @param string $key String key
913 * @return string Sanitized key
915 function sanitize_key( $key ) {
917 $key = strtolower( $key );
918 $key = preg_replace( '/[^a-z0-9_\-]/', '', $key );
919 return apply_filters( 'sanitize_key', $key, $raw_key );
923 * Sanitizes title or use fallback title.
925 * Specifically, HTML and PHP tags are stripped. Further actions can be added
926 * via the plugin API. If $title is empty and $fallback_title is set, the latter
931 * @param string $title The string to be sanitized.
932 * @param string $fallback_title Optional. A title to use if $title is empty.
933 * @param string $context Optional. The operation for which the string is sanitized
934 * @return string The sanitized string.
936 function sanitize_title($title, $fallback_title = '', $context = 'save') {
939 if ( 'save' == $context )
940 $title = remove_accents($title);
942 $title = apply_filters('sanitize_title', $title, $raw_title, $context);
944 if ( '' === $title || false === $title )
945 $title = $fallback_title;
950 function sanitize_title_for_query($title) {
951 return sanitize_title($title, '', 'query');
955 * Sanitizes title, replacing whitespace and a few other characters with dashes.
957 * Limits the output to alphanumeric characters, underscore (_) and dash (-).
958 * Whitespace becomes a dash.
962 * @param string $title The title to be sanitized.
963 * @param string $raw_title Optional. Not used.
964 * @param string $context Optional. The operation for which the string is sanitized.
965 * @return string The sanitized title.
967 function sanitize_title_with_dashes($title, $raw_title = '', $context = 'display') {
968 $title = strip_tags($title);
969 // Preserve escaped octets.
970 $title = preg_replace('|%([a-fA-F0-9][a-fA-F0-9])|', '---$1---', $title);
971 // Remove percent signs that are not part of an octet.
972 $title = str_replace('%', '', $title);
974 $title = preg_replace('|---([a-fA-F0-9][a-fA-F0-9])---|', '%$1', $title);
976 if (seems_utf8($title)) {
977 if (function_exists('mb_strtolower')) {
978 $title = mb_strtolower($title, 'UTF-8');
980 $title = utf8_uri_encode($title, 200);
983 $title = strtolower($title);
984 $title = preg_replace('/&.+?;/', '', $title); // kill entities
985 $title = str_replace('.', '-', $title);
987 if ( 'save' == $context ) {
988 // Convert nbsp, ndash and mdash to hyphens
989 $title = str_replace( array( '%c2%a0', '%e2%80%93', '%e2%80%94' ), '-', $title );
991 // Strip these characters entirely
992 $title = str_replace( array(
996 '%c2%ab', '%c2%bb', '%e2%80%b9', '%e2%80%ba',
998 '%e2%80%98', '%e2%80%99', '%e2%80%9c', '%e2%80%9d',
999 '%e2%80%9a', '%e2%80%9b', '%e2%80%9e', '%e2%80%9f',
1000 // copy, reg, deg, hellip and trade
1001 '%c2%a9', '%c2%ae', '%c2%b0', '%e2%80%a6', '%e2%84%a2',
1002 // grave accent, acute accent, macron, caron
1003 '%cc%80', '%cc%81', '%cc%84', '%cc%8c',
1006 // Convert times to x
1007 $title = str_replace( '%c3%97', 'x', $title );
1010 $title = preg_replace('/[^%a-z0-9 _-]/', '', $title);
1011 $title = preg_replace('/\s+/', '-', $title);
1012 $title = preg_replace('|-+|', '-', $title);
1013 $title = trim($title, '-');
1019 * Ensures a string is a valid SQL order by clause.
1021 * Accepts one or more columns, with or without ASC/DESC, and also accepts
1026 * @param string $orderby Order by string to be checked.
1027 * @return string|bool Returns the order by clause if it is a match, false otherwise.
1029 function sanitize_sql_orderby( $orderby ){
1030 preg_match('/^\s*([a-z0-9_]+(\s+(ASC|DESC))?(\s*,\s*|\s*$))+|^\s*RAND\(\s*\)\s*$/i', $orderby, $obmatches);
1037 * Santizes a html classname to ensure it only contains valid characters
1039 * Strips the string down to A-Z,a-z,0-9,_,-. If this results in an empty
1040 * string then it will return the alternative value supplied.
1042 * @todo Expand to support the full range of CDATA that a class attribute can contain.
1046 * @param string $class The classname to be sanitized
1047 * @param string $fallback Optional. The value to return if the sanitization end's up as an empty string.
1048 * Defaults to an empty string.
1049 * @return string The sanitized value
1051 function sanitize_html_class( $class, $fallback = '' ) {
1052 //Strip out any % encoded octets
1053 $sanitized = preg_replace( '|%[a-fA-F0-9][a-fA-F0-9]|', '', $class );
1055 //Limit to A-Z,a-z,0-9,_,-
1056 $sanitized = preg_replace( '/[^A-Za-z0-9_-]/', '', $sanitized );
1058 if ( '' == $sanitized )
1059 $sanitized = $fallback;
1061 return apply_filters( 'sanitize_html_class', $sanitized, $class, $fallback );
1065 * Converts a number of characters from a string.
1067 * Metadata tags <<title>> and <<category>> are removed, <<br>> and <<hr>> are
1068 * converted into correct XHTML and Unicode characters are converted to the
1073 * @param string $content String of characters to be converted.
1074 * @param string $deprecated Not used.
1075 * @return string Converted string.
1077 function convert_chars($content, $deprecated = '') {
1078 if ( !empty( $deprecated ) )
1079 _deprecated_argument( __FUNCTION__, '0.71' );
1081 // Translation of invalid Unicode references range to valid range
1082 $wp_htmltranswinuni = array(
1083 '€' => '€', // the Euro sign
1085 '‚' => '‚', // these are Windows CP1252 specific characters
1086 'ƒ' => 'ƒ', // they would look weird on non-Windows browsers
1087 '„' => '„',
1088 '…' => '…',
1089 '†' => '†',
1090 '‡' => '‡',
1091 'ˆ' => 'ˆ',
1092 '‰' => '‰',
1093 'Š' => 'Š',
1094 '‹' => '‹',
1095 'Œ' => 'Œ',
1097 'Ž' => 'Ž',
1100 '‘' => '‘',
1101 '’' => '’',
1102 '“' => '“',
1103 '”' => '”',
1104 '•' => '•',
1105 '–' => '–',
1106 '—' => '—',
1107 '˜' => '˜',
1108 '™' => '™',
1109 'š' => 'š',
1110 '›' => '›',
1111 'œ' => 'œ',
1113 'ž' => 'ž',
1114 'Ÿ' => 'Ÿ'
1117 // Remove metadata tags
1118 $content = preg_replace('/<title>(.+?)<\/title>/','',$content);
1119 $content = preg_replace('/<category>(.+?)<\/category>/','',$content);
1121 // Converts lone & characters into & (a.k.a. &)
1122 $content = preg_replace('/&([^#])(?![a-z1-4]{1,8};)/i', '&$1', $content);
1125 $content = strtr($content, $wp_htmltranswinuni);
1127 // Just a little XHTML help
1128 $content = str_replace('<br>', '<br />', $content);
1129 $content = str_replace('<hr>', '<hr />', $content);
1135 * Will only balance the tags if forced to and the option is set to balance tags.
1137 * The option 'use_balanceTags' is used to determine whether the tags will be balanced.
1141 * @param string $text Text to be balanced
1142 * @param bool $force If true, forces balancing, ignoring the value of the option. Default false.
1143 * @return string Balanced text
1145 function balanceTags( $text, $force = false ) {
1146 if ( !$force && get_option('use_balanceTags') == 0 )
1148 return force_balance_tags( $text );
1152 * Balances tags of string using a modified stack.
1156 * @author Leonard Lin <leonard@acm.org>
1158 * @copyright November 4, 2001
1160 * @todo Make better - change loop condition to $text in 1.2
1161 * @internal Modified by Scott Reilly (coffee2code) 02 Aug 2004
1162 * 1.1 Fixed handling of append/stack pop order of end text
1163 * Added Cleaning Hooks
1166 * @param string $text Text to be balanced.
1167 * @return string Balanced text.
1169 function force_balance_tags( $text ) {
1170 $tagstack = array();
1174 // Known single-entity/self-closing tags
1175 $single_tags = array( 'area', 'base', 'basefont', 'br', 'col', 'command', 'embed', 'frame', 'hr', 'img', 'input', 'isindex', 'link', 'meta', 'param', 'source' );
1176 // Tags that can be immediately nested within themselves
1177 $nestable_tags = array( 'blockquote', 'div', 'object', 'q', 'span' );
1179 // WP bug fix for comments - in case you REALLY meant to type '< !--'
1180 $text = str_replace('< !--', '< !--', $text);
1181 // WP bug fix for LOVE <3 (and other situations with '<' before a number)
1182 $text = preg_replace('#<([0-9]{1})#', '<$1', $text);
1184 while ( preg_match("/<(\/?[\w:]*)\s*([^>]*)>/", $text, $regex) ) {
1185 $newtext .= $tagqueue;
1187 $i = strpos($text, $regex[0]);
1188 $l = strlen($regex[0]);
1190 // clear the shifter
1193 if ( isset($regex[1][0]) && '/' == $regex[1][0] ) { // End Tag
1194 $tag = strtolower(substr($regex[1],1));
1195 // if too many closing tags
1196 if( $stacksize <= 0 ) {
1198 // or close to be safe $tag = '/' . $tag;
1200 // if stacktop value = tag close value then pop
1201 else if ( $tagstack[$stacksize - 1] == $tag ) { // found closing tag
1202 $tag = '</' . $tag . '>'; // Close Tag
1204 array_pop( $tagstack );
1206 } else { // closing tag not at top, search for it
1207 for ( $j = $stacksize-1; $j >= 0; $j-- ) {
1208 if ( $tagstack[$j] == $tag ) {
1209 // add tag to tagqueue
1210 for ( $k = $stacksize-1; $k >= $j; $k--) {
1211 $tagqueue .= '</' . array_pop( $tagstack ) . '>';
1219 } else { // Begin Tag
1220 $tag = strtolower($regex[1]);
1224 // If it's an empty tag "< >", do nothing
1228 // ElseIf it presents itself as a self-closing tag...
1229 elseif ( substr( $regex[2], -1 ) == '/' ) {
1230 // ...but it isn't a known single-entity self-closing tag, then don't let it be treated as such and
1231 // immediately close it with a closing tag (the tag will encapsulate no text as a result)
1232 if ( ! in_array( $tag, $single_tags ) )
1233 $regex[2] = trim( substr( $regex[2], 0, -1 ) ) . "></$tag";
1235 // ElseIf it's a known single-entity tag but it doesn't close itself, do so
1236 elseif ( in_array($tag, $single_tags) ) {
1239 // Else it's not a single-entity tag
1241 // If the top of the stack is the same as the tag we want to push, close previous tag
1242 if ( $stacksize > 0 && !in_array($tag, $nestable_tags) && $tagstack[$stacksize - 1] == $tag ) {
1243 $tagqueue = '</' . array_pop( $tagstack ) . '>';
1246 $stacksize = array_push( $tagstack, $tag );
1250 $attributes = $regex[2];
1251 if( ! empty( $attributes ) && $attributes[0] != '>' )
1252 $attributes = ' ' . $attributes;
1254 $tag = '<' . $tag . $attributes . '>';
1255 //If already queuing a close tag, then put this tag on, too
1256 if ( !empty($tagqueue) ) {
1261 $newtext .= substr($text, 0, $i) . $tag;
1262 $text = substr($text, $i + $l);
1266 $newtext .= $tagqueue;
1268 // Add Remaining text
1272 while( $x = array_pop($tagstack) )
1273 $newtext .= '</' . $x . '>'; // Add remaining tags to close
1275 // WP fix for the bug with HTML comments
1276 $newtext = str_replace("< !--","<!--",$newtext);
1277 $newtext = str_replace("< !--","< !--",$newtext);
1283 * Acts on text which is about to be edited.
1285 * The $content is run through esc_textarea(), which uses htmlspecialchars()
1286 * to convert special characters to HTML entities. If $richedit is set to true,
1287 * it is simply a holder for the 'format_to_edit' filter.
1291 * @param string $content The text about to be edited.
1292 * @param bool $richedit Whether the $content should not pass through htmlspecialchars(). Default false (meaning it will be passed).
1293 * @return string The text after the filter (and possibly htmlspecialchars()) has been run.
1295 function format_to_edit( $content, $richedit = false ) {
1296 $content = apply_filters( 'format_to_edit', $content );
1298 $content = esc_textarea( $content );
1303 * Holder for the 'format_to_post' filter.
1307 * @param string $content The text to pass through the filter.
1308 * @return string Text returned from the 'format_to_post' filter.
1310 function format_to_post($content) {
1311 $content = apply_filters('format_to_post', $content);
1316 * Add leading zeros when necessary.
1318 * If you set the threshold to '4' and the number is '10', then you will get
1319 * back '0010'. If you set the threshold to '4' and the number is '5000', then you
1320 * will get back '5000'.
1322 * Uses sprintf to append the amount of zeros based on the $threshold parameter
1323 * and the size of the number. If the number is large enough, then no zeros will
1328 * @param mixed $number Number to append zeros to if not greater than threshold.
1329 * @param int $threshold Digit places number needs to be to not have zeros added.
1330 * @return string Adds leading zeros to number if needed.
1332 function zeroise($number, $threshold) {
1333 return sprintf('%0'.$threshold.'s', $number);
1337 * Adds backslashes before letters and before a number at the start of a string.
1341 * @param string $string Value to which backslashes will be added.
1342 * @return string String with backslashes inserted.
1344 function backslashit($string) {
1345 $string = preg_replace('/^([0-9])/', '\\\\\\\\\1', $string);
1346 $string = preg_replace('/([a-z])/i', '\\\\\1', $string);
1351 * Appends a trailing slash.
1353 * Will remove trailing slash if it exists already before adding a trailing
1354 * slash. This prevents double slashing a string or path.
1356 * The primary use of this is for paths and thus should be used for paths. It is
1357 * not restricted to paths and offers no specific path support.
1360 * @uses untrailingslashit() Unslashes string if it was slashed already.
1362 * @param string $string What to add the trailing slash to.
1363 * @return string String with trailing slash added.
1365 function trailingslashit($string) {
1366 return untrailingslashit($string) . '/';
1370 * Removes trailing slash if it exists.
1372 * The primary use of this is for paths and thus should be used for paths. It is
1373 * not restricted to paths and offers no specific path support.
1377 * @param string $string What to remove the trailing slash from.
1378 * @return string String without the trailing slash.
1380 function untrailingslashit($string) {
1381 return rtrim($string, '/');
1385 * Adds slashes to escape strings.
1387 * Slashes will first be removed if magic_quotes_gpc is set, see {@link
1388 * http://www.php.net/magic_quotes} for more details.
1392 * @param string $gpc The string returned from HTTP request data.
1393 * @return string Returns a string escaped with slashes.
1395 function addslashes_gpc($gpc) {
1396 if ( get_magic_quotes_gpc() )
1397 $gpc = stripslashes($gpc);
1399 return esc_sql($gpc);
1403 * Navigates through an array and removes slashes from the values.
1405 * If an array is passed, the array_map() function causes a callback to pass the
1406 * value back to the function. The slashes from this value will removed.
1410 * @param mixed $value The value to be stripped.
1411 * @return mixed Stripped value.
1413 function stripslashes_deep($value) {
1414 if ( is_array($value) ) {
1415 $value = array_map('stripslashes_deep', $value);
1416 } elseif ( is_object($value) ) {
1417 $vars = get_object_vars( $value );
1418 foreach ($vars as $key=>$data) {
1419 $value->{$key} = stripslashes_deep( $data );
1421 } elseif ( is_string( $value ) ) {
1422 $value = stripslashes($value);
1429 * Navigates through an array and encodes the values to be used in a URL.
1434 * @param array|string $value The array or string to be encoded.
1435 * @return array|string $value The encoded array (or string from the callback).
1437 function urlencode_deep($value) {
1438 $value = is_array($value) ? array_map('urlencode_deep', $value) : urlencode($value);
1443 * Navigates through an array and raw encodes the values to be used in a URL.
1447 * @param array|string $value The array or string to be encoded.
1448 * @return array|string $value The encoded array (or string from the callback).
1450 function rawurlencode_deep( $value ) {
1451 return is_array( $value ) ? array_map( 'rawurlencode_deep', $value ) : rawurlencode( $value );
1455 * Converts email addresses characters to HTML entities to block spam bots.
1459 * @param string $emailaddy Email address.
1460 * @param int $mailto Optional. Range from 0 to 1. Used for encoding.
1461 * @return string Converted email address.
1463 function antispambot($emailaddy, $mailto=0) {
1464 $emailNOSPAMaddy = '';
1465 srand ((float) microtime() * 1000000);
1466 for ($i = 0; $i < strlen($emailaddy); $i = $i + 1) {
1467 $j = floor(rand(0, 1+$mailto));
1469 $emailNOSPAMaddy .= '&#'.ord(substr($emailaddy,$i,1)).';';
1471 $emailNOSPAMaddy .= substr($emailaddy,$i,1);
1473 $emailNOSPAMaddy .= '%'.zeroise(dechex(ord(substr($emailaddy, $i, 1))), 2);
1476 $emailNOSPAMaddy = str_replace('@','@',$emailNOSPAMaddy);
1477 return $emailNOSPAMaddy;
1481 * Callback to convert URI match to HTML A element.
1483 * This function was backported from 2.5.0 to 2.3.2. Regex callback for {@link
1484 * make_clickable()}.
1489 * @param array $matches Single Regex Match.
1490 * @return string HTML A element with URI address.
1492 function _make_url_clickable_cb($matches) {
1495 if ( ')' == $matches[3] && strpos( $url, '(' ) ) {
1496 // If the trailing character is a closing parethesis, and the URL has an opening parenthesis in it, add the closing parenthesis to the URL.
1497 // Then we can let the parenthesis balancer do its thing below.
1498 $url .= $matches[3];
1501 $suffix = $matches[3];
1504 // Include parentheses in the URL only if paired
1505 while ( substr_count( $url, '(' ) < substr_count( $url, ')' ) ) {
1506 $suffix = strrchr( $url, ')' ) . $suffix;
1507 $url = substr( $url, 0, strrpos( $url, ')' ) );
1510 $url = esc_url($url);
1514 return $matches[1] . "<a href=\"$url\" rel=\"nofollow\">$url</a>" . $suffix;
1518 * Callback to convert URL match to HTML A element.
1520 * This function was backported from 2.5.0 to 2.3.2. Regex callback for {@link
1521 * make_clickable()}.
1526 * @param array $matches Single Regex Match.
1527 * @return string HTML A element with URL address.
1529 function _make_web_ftp_clickable_cb($matches) {
1531 $dest = $matches[2];
1532 $dest = 'http://' . $dest;
1533 $dest = esc_url($dest);
1537 // removed trailing [.,;:)] from URL
1538 if ( in_array( substr($dest, -1), array('.', ',', ';', ':', ')') ) === true ) {
1539 $ret = substr($dest, -1);
1540 $dest = substr($dest, 0, strlen($dest)-1);
1542 return $matches[1] . "<a href=\"$dest\" rel=\"nofollow\">$dest</a>$ret";
1546 * Callback to convert email address match to HTML A element.
1548 * This function was backported from 2.5.0 to 2.3.2. Regex callback for {@link
1549 * make_clickable()}.
1554 * @param array $matches Single Regex Match.
1555 * @return string HTML A element with email address.
1557 function _make_email_clickable_cb($matches) {
1558 $email = $matches[2] . '@' . $matches[3];
1559 return $matches[1] . "<a href=\"mailto:$email\">$email</a>";
1563 * Convert plaintext URI to HTML links.
1565 * Converts URI, www and ftp, and email addresses. Finishes by fixing links
1570 * @param string $text Content to convert URIs.
1571 * @return string Content with converted URIs.
1573 function make_clickable( $text ) {
1575 $textarr = preg_split( '/(<[^<>]+>)/', $text, -1, PREG_SPLIT_DELIM_CAPTURE ); // split out HTML tags
1576 foreach ( $textarr as $piece ) {
1577 if ( empty( $piece ) || ( $piece[0] == '<' && ! preg_match('|^<\s*[\w]{1,20}+://|', $piece) ) ) {
1582 // Long strings might contain expensive edge cases ...
1583 if ( 10000 < strlen( $piece ) ) {
1585 foreach ( _split_str_by_whitespace( $piece, 2100 ) as $chunk ) { // 2100: Extra room for scheme and leading and trailing paretheses
1586 if ( 2101 < strlen( $chunk ) ) {
1587 $r .= $chunk; // Too big, no whitespace: bail.
1589 $r .= make_clickable( $chunk );
1593 $ret = " $piece "; // Pad with whitespace to simplify the regexes
1596 ([\\s(<.,;:!?]) # 1: Leading whitespace, or punctuation
1598 [\\w]{1,20}+:// # Scheme and hier-part prefix
1599 (?=\S{1,2000}\s) # Limit to URLs less than about 2000 characters long
1600 [\\w\\x80-\\xff#%\\~/@\\[\\]*(+=&$-]*+ # Non-punctuation URL character
1601 (?: # Unroll the Loop: Only allow puctuation URL character if followed by a non-punctuation URL character
1602 [\'.,;:!?)] # Punctuation URL character
1603 [\\w\\x80-\\xff#%\\~/@\\[\\]*(+=&$-]++ # Non-punctuation URL character
1606 (\)?) # 3: Trailing closing parenthesis (for parethesis balancing post processing)
1607 ~xS'; // The regex is a non-anchored pattern and does not have a single fixed starting character.
1608 // Tell PCRE to spend more time optimizing since, when used on a page load, it will probably be used several times.
1610 $ret = preg_replace_callback( $url_clickable, '_make_url_clickable_cb', $ret );
1612 $ret = preg_replace_callback( '#([\s>])((www|ftp)\.[\w\\x80-\\xff\#$%&~/.\-;:=,?@\[\]+]+)#is', '_make_web_ftp_clickable_cb', $ret );
1613 $ret = preg_replace_callback( '#([\s>])([.0-9a-z_+-]+)@(([0-9a-z-]+\.)+[0-9a-z]{2,})#i', '_make_email_clickable_cb', $ret );
1615 $ret = substr( $ret, 1, -1 ); // Remove our whitespace padding.
1620 // Cleanup of accidental links within links
1621 $r = preg_replace( '#(<a( [^>]+?>|>))<a [^>]+?>([^>]+?)</a></a>#i', "$1$3</a>", $r );
1626 * Breaks a string into chunks by splitting at whitespace characters.
1627 * The length of each returned chunk is as close to the specified length goal as possible,
1628 * with the caveat that each chunk includes its trailing delimiter.
1629 * Chunks longer than the goal are guaranteed to not have any inner whitespace.
1631 * Joining the returned chunks with empty delimiters reconstructs the input string losslessly.
1633 * Input string must have no null characters (or eventual transformations on output chunks must not care about null characters)
1636 * _split_str_by_whitespace( "1234 67890 1234 67890a cd 1234 890 123456789 1234567890a 45678 1 3 5 7 90 ", 10 ) ==
1638 * 0 => '1234 67890 ', // 11 characters: Perfect split
1639 * 1 => '1234 ', // 5 characters: '1234 67890a' was too long
1640 * 2 => '67890a cd ', // 10 characters: '67890a cd 1234' was too long
1641 * 3 => '1234 890 ', // 11 characters: Perfect split
1642 * 4 => '123456789 ', // 10 characters: '123456789 1234567890a' was too long
1643 * 5 => '1234567890a ', // 12 characters: Too long, but no inner whitespace on which to split
1644 * 6 => ' 45678 ', // 11 characters: Perfect split
1645 * 7 => '1 3 5 7 9', // 9 characters: End of $string
1652 * @param string $string The string to split.
1653 * @param int $goal The desired chunk length.
1654 * @return array Numeric array of chunks.
1656 function _split_str_by_whitespace( $string, $goal ) {
1659 $string_nullspace = strtr( $string, "\r\n\t\v\f ", "\000\000\000\000\000\000" );
1661 while ( $goal < strlen( $string_nullspace ) ) {
1662 $pos = strrpos( substr( $string_nullspace, 0, $goal + 1 ), "\000" );
1664 if ( false === $pos ) {
1665 $pos = strpos( $string_nullspace, "\000", $goal + 1 );
1666 if ( false === $pos ) {
1671 $chunks[] = substr( $string, 0, $pos + 1 );
1672 $string = substr( $string, $pos + 1 );
1673 $string_nullspace = substr( $string_nullspace, $pos + 1 );
1677 $chunks[] = $string;
1684 * Adds rel nofollow string to all HTML A elements in content.
1688 * @param string $text Content that may contain HTML A elements.
1689 * @return string Converted content.
1691 function wp_rel_nofollow( $text ) {
1692 // This is a pre save filter, so text is already escaped.
1693 $text = stripslashes($text);
1694 $text = preg_replace_callback('|<a (.+?)>|i', 'wp_rel_nofollow_callback', $text);
1695 $text = esc_sql($text);
1700 * Callback to used to add rel=nofollow string to HTML A element.
1702 * Will remove already existing rel="nofollow" and rel='nofollow' from the
1703 * string to prevent from invalidating (X)HTML.
1707 * @param array $matches Single Match
1708 * @return string HTML A Element with rel nofollow.
1710 function wp_rel_nofollow_callback( $matches ) {
1711 $text = $matches[1];
1712 $text = str_replace(array(' rel="nofollow"', " rel='nofollow'"), '', $text);
1713 return "<a $text rel=\"nofollow\">";
1717 * Convert one smiley code to the icon graphic file equivalent.
1719 * Looks up one smiley code in the $wpsmiliestrans global array and returns an
1720 * <img> string for that smiley.
1722 * @global array $wpsmiliestrans
1725 * @param string $smiley Smiley code to convert to image.
1726 * @return string Image string for smiley.
1728 function translate_smiley($smiley) {
1729 global $wpsmiliestrans;
1731 if (count($smiley) == 0) {
1735 $smiley = trim(reset($smiley));
1736 $img = $wpsmiliestrans[$smiley];
1737 $smiley_masked = esc_attr($smiley);
1739 $srcurl = apply_filters('smilies_src', includes_url("images/smilies/$img"), $img, site_url());
1741 return " <img src='$srcurl' alt='$smiley_masked' class='wp-smiley' /> ";
1745 * Convert text equivalent of smilies to images.
1747 * Will only convert smilies if the option 'use_smilies' is true and the global
1748 * used in the function isn't empty.
1751 * @uses $wp_smiliessearch
1753 * @param string $text Content to convert smilies from text.
1754 * @return string Converted content with text smilies replaced with images.
1756 function convert_smilies($text) {
1757 global $wp_smiliessearch;
1759 if ( get_option('use_smilies') && !empty($wp_smiliessearch) ) {
1760 // HTML loop taken from texturize function, could possible be consolidated
1761 $textarr = preg_split("/(<.*>)/U", $text, -1, PREG_SPLIT_DELIM_CAPTURE); // capture the tags as well as in between
1762 $stop = count($textarr);// loop stuff
1763 for ($i = 0; $i < $stop; $i++) {
1764 $content = $textarr[$i];
1765 if ((strlen($content) > 0) && ('<' != $content[0])) { // If it's not a tag
1766 $content = preg_replace_callback($wp_smiliessearch, 'translate_smiley', $content);
1768 $output .= $content;
1771 // return default text.
1778 * Verifies that an email is valid.
1780 * Does not grok i18n domains. Not RFC compliant.
1784 * @param string $email Email address to verify.
1785 * @param boolean $deprecated Deprecated.
1786 * @return string|bool Either false or the valid email address.
1788 function is_email( $email, $deprecated = false ) {
1789 if ( ! empty( $deprecated ) )
1790 _deprecated_argument( __FUNCTION__, '3.0' );
1792 // Test for the minimum length the email can be
1793 if ( strlen( $email ) < 3 ) {
1794 return apply_filters( 'is_email', false, $email, 'email_too_short' );
1797 // Test for an @ character after the first position
1798 if ( strpos( $email, '@', 1 ) === false ) {
1799 return apply_filters( 'is_email', false, $email, 'email_no_at' );
1802 // Split out the local and domain parts
1803 list( $local, $domain ) = explode( '@', $email, 2 );
1806 // Test for invalid characters
1807 if ( !preg_match( '/^[a-zA-Z0-9!#$%&\'*+\/=?^_`{|}~\.-]+$/', $local ) ) {
1808 return apply_filters( 'is_email', false, $email, 'local_invalid_chars' );
1812 // Test for sequences of periods
1813 if ( preg_match( '/\.{2,}/', $domain ) ) {
1814 return apply_filters( 'is_email', false, $email, 'domain_period_sequence' );
1817 // Test for leading and trailing periods and whitespace
1818 if ( trim( $domain, " \t\n\r\0\x0B." ) !== $domain ) {
1819 return apply_filters( 'is_email', false, $email, 'domain_period_limits' );
1822 // Split the domain into subs
1823 $subs = explode( '.', $domain );
1825 // Assume the domain will have at least two subs
1826 if ( 2 > count( $subs ) ) {
1827 return apply_filters( 'is_email', false, $email, 'domain_no_periods' );
1830 // Loop through each sub
1831 foreach ( $subs as $sub ) {
1832 // Test for leading and trailing hyphens and whitespace
1833 if ( trim( $sub, " \t\n\r\0\x0B-" ) !== $sub ) {
1834 return apply_filters( 'is_email', false, $email, 'sub_hyphen_limits' );
1837 // Test for invalid characters
1838 if ( !preg_match('/^[a-z0-9-]+$/i', $sub ) ) {
1839 return apply_filters( 'is_email', false, $email, 'sub_invalid_chars' );
1843 // Congratulations your email made it!
1844 return apply_filters( 'is_email', $email, $email, null );
1848 * Convert to ASCII from email subjects.
1852 * @param string $string Subject line
1853 * @return string Converted string to ASCII
1855 function wp_iso_descrambler($string) {
1856 /* this may only work with iso-8859-1, I'm afraid */
1857 if (!preg_match('#\=\?(.+)\?Q\?(.+)\?\=#i', $string, $matches)) {
1860 $subject = str_replace('_', ' ', $matches[2]);
1861 $subject = preg_replace_callback('#\=([0-9a-f]{2})#i', '_wp_iso_convert', $subject);
1867 * Helper function to convert hex encoded chars to ASCII
1871 * @param array $match The preg_replace_callback matches array
1872 * @return array Converted chars
1874 function _wp_iso_convert( $match ) {
1875 return chr( hexdec( strtolower( $match[1] ) ) );
1879 * Returns a date in the GMT equivalent.
1881 * Requires and returns a date in the Y-m-d H:i:s format. Simply subtracts the
1882 * value of the 'gmt_offset' option. Return format can be overridden using the
1883 * $format parameter. The DateTime and DateTimeZone classes are used to respect
1884 * time zone differences in DST.
1888 * @uses get_option() to retrieve the the value of 'gmt_offset'.
1889 * @param string $string The date to be converted.
1890 * @param string $format The format string for the returned date (default is Y-m-d H:i:s)
1891 * @return string GMT version of the date provided.
1893 function get_gmt_from_date($string, $format = 'Y-m-d H:i:s') {
1894 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);
1896 return date( $format, 0 );
1898 $tz = get_option('timezone_string');
1900 date_default_timezone_set( $tz );
1901 $datetime = date_create( $string );
1903 return date( $format, 0 );
1905 $datetime->setTimezone( new DateTimeZone('UTC') );
1906 $offset = $datetime->getOffset();
1907 $datetime->modify( '+' . $offset / HOUR_IN_SECONDS . ' hours');
1908 $string_gmt = gmdate($format, $datetime->format('U'));
1910 date_default_timezone_set('UTC');
1912 $string_time = gmmktime($matches[4], $matches[5], $matches[6], $matches[2], $matches[3], $matches[1]);
1913 $string_gmt = gmdate($format, $string_time - get_option('gmt_offset') * HOUR_IN_SECONDS);
1919 * Converts a GMT date into the correct format for the blog.
1921 * Requires and returns in the Y-m-d H:i:s format. Simply adds the value of
1922 * gmt_offset.Return format can be overridden using the $format parameter
1926 * @param string $string The date to be converted.
1927 * @param string $format The format string for the returned date (default is Y-m-d H:i:s)
1928 * @return string Formatted date relative to the GMT offset.
1930 function get_date_from_gmt($string, $format = 'Y-m-d H:i:s') {
1931 preg_match('#([0-9]{1,4})-([0-9]{1,2})-([0-9]{1,2}) ([0-9]{1,2}):([0-9]{1,2}):([0-9]{1,2})#', $string, $matches);
1932 $string_time = gmmktime($matches[4], $matches[5], $matches[6], $matches[2], $matches[3], $matches[1]);
1933 $string_localtime = gmdate($format, $string_time + get_option('gmt_offset') * HOUR_IN_SECONDS);
1934 return $string_localtime;
1938 * Computes an offset in seconds from an iso8601 timezone.
1942 * @param string $timezone Either 'Z' for 0 offset or '±hhmm'.
1943 * @return int|float The offset in seconds.
1945 function iso8601_timezone_to_offset($timezone) {
1946 // $timezone is either 'Z' or '[+|-]hhmm'
1947 if ($timezone == 'Z') {
1950 $sign = (substr($timezone, 0, 1) == '+') ? 1 : -1;
1951 $hours = intval(substr($timezone, 1, 2));
1952 $minutes = intval(substr($timezone, 3, 4)) / 60;
1953 $offset = $sign * HOUR_IN_SECONDS * ($hours + $minutes);
1959 * Converts an iso8601 date to MySQL DateTime format used by post_date[_gmt].
1963 * @param string $date_string Date and time in ISO 8601 format {@link http://en.wikipedia.org/wiki/ISO_8601}.
1964 * @param string $timezone Optional. If set to GMT returns the time minus gmt_offset. Default is 'user'.
1965 * @return string The date and time in MySQL DateTime format - Y-m-d H:i:s.
1967 function iso8601_to_datetime($date_string, $timezone = 'user') {
1968 $timezone = strtolower($timezone);
1970 if ($timezone == 'gmt') {
1972 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, $date_bits);
1974 if (!empty($date_bits[7])) { // we have a timezone, so let's compute an offset
1975 $offset = iso8601_timezone_to_offset($date_bits[7]);
1976 } else { // we don't have a timezone, so we assume user local timezone (not server's!)
1977 $offset = HOUR_IN_SECONDS * get_option('gmt_offset');
1980 $timestamp = gmmktime($date_bits[4], $date_bits[5], $date_bits[6], $date_bits[2], $date_bits[3], $date_bits[1]);
1981 $timestamp -= $offset;
1983 return gmdate('Y-m-d H:i:s', $timestamp);
1985 } else if ($timezone == 'user') {
1986 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);
1991 * Adds a element attributes to open links in new windows.
1993 * Comment text in popup windows should be filtered through this. Right now it's
1994 * a moderately dumb function, ideally it would detect whether a target or rel
1995 * attribute was already there and adjust its actions accordingly.
1999 * @param string $text Content to replace links to open in a new window.
2000 * @return string Content that has filtered links.
2002 function popuplinks($text) {
2003 $text = preg_replace('/<a (.+?)>/i', "<a $1 target='_blank' rel='external'>", $text);
2008 * Strips out all characters that are not allowable in an email.
2012 * @param string $email Email address to filter.
2013 * @return string Filtered email address.
2015 function sanitize_email( $email ) {
2016 // Test for the minimum length the email can be
2017 if ( strlen( $email ) < 3 ) {
2018 return apply_filters( 'sanitize_email', '', $email, 'email_too_short' );
2021 // Test for an @ character after the first position
2022 if ( strpos( $email, '@', 1 ) === false ) {
2023 return apply_filters( 'sanitize_email', '', $email, 'email_no_at' );
2026 // Split out the local and domain parts
2027 list( $local, $domain ) = explode( '@', $email, 2 );
2030 // Test for invalid characters
2031 $local = preg_replace( '/[^a-zA-Z0-9!#$%&\'*+\/=?^_`{|}~\.-]/', '', $local );
2032 if ( '' === $local ) {
2033 return apply_filters( 'sanitize_email', '', $email, 'local_invalid_chars' );
2037 // Test for sequences of periods
2038 $domain = preg_replace( '/\.{2,}/', '', $domain );
2039 if ( '' === $domain ) {
2040 return apply_filters( 'sanitize_email', '', $email, 'domain_period_sequence' );
2043 // Test for leading and trailing periods and whitespace
2044 $domain = trim( $domain, " \t\n\r\0\x0B." );
2045 if ( '' === $domain ) {
2046 return apply_filters( 'sanitize_email', '', $email, 'domain_period_limits' );
2049 // Split the domain into subs
2050 $subs = explode( '.', $domain );
2052 // Assume the domain will have at least two subs
2053 if ( 2 > count( $subs ) ) {
2054 return apply_filters( 'sanitize_email', '', $email, 'domain_no_periods' );
2057 // Create an array that will contain valid subs
2058 $new_subs = array();
2060 // Loop through each sub
2061 foreach ( $subs as $sub ) {
2062 // Test for leading and trailing hyphens
2063 $sub = trim( $sub, " \t\n\r\0\x0B-" );
2065 // Test for invalid characters
2066 $sub = preg_replace( '/[^a-z0-9-]+/i', '', $sub );
2068 // If there's anything left, add it to the valid subs
2069 if ( '' !== $sub ) {
2074 // If there aren't 2 or more valid subs
2075 if ( 2 > count( $new_subs ) ) {
2076 return apply_filters( 'sanitize_email', '', $email, 'domain_no_valid_subs' );
2079 // Join valid subs into the new domain
2080 $domain = join( '.', $new_subs );
2082 // Put the email back together
2083 $email = $local . '@' . $domain;
2085 // Congratulations your email made it!
2086 return apply_filters( 'sanitize_email', $email, $email, null );
2090 * Determines the difference between two timestamps.
2092 * The difference is returned in a human readable format such as "1 hour",
2093 * "5 mins", "2 days".
2097 * @param int $from Unix timestamp from which the difference begins.
2098 * @param int $to Optional. Unix timestamp to end the time difference. Default becomes time() if not set.
2099 * @return string Human readable time difference.
2101 function human_time_diff( $from, $to = '' ) {
2104 $diff = (int) abs( $to - $from );
2105 if ( $diff <= HOUR_IN_SECONDS ) {
2106 $mins = round( $diff / MINUTE_IN_SECONDS );
2110 /* translators: min=minute */
2111 $since = sprintf( _n( '%s min', '%s mins', $mins ), $mins );
2112 } elseif ( ( $diff <= DAY_IN_SECONDS ) && ( $diff > HOUR_IN_SECONDS ) ) {
2113 $hours = round( $diff / HOUR_IN_SECONDS );
2114 if ( $hours <= 1 ) {
2117 $since = sprintf( _n( '%s hour', '%s hours', $hours ), $hours );
2118 } elseif ( $diff >= DAY_IN_SECONDS ) {
2119 $days = round( $diff / DAY_IN_SECONDS );
2123 $since = sprintf( _n( '%s day', '%s days', $days ), $days );
2129 * Generates an excerpt from the content, if needed.
2131 * The excerpt word amount will be 55 words and if the amount is greater than
2132 * that, then the string ' [...]' will be appended to the excerpt. If the string
2133 * is less than 55 words, then the content will be returned as is.
2135 * The 55 word limit can be modified by plugins/themes using the excerpt_length filter
2136 * The ' [...]' string can be modified by plugins/themes using the excerpt_more filter
2140 * @param string $text Optional. The excerpt. If set to empty, an excerpt is generated.
2141 * @return string The excerpt.
2143 function wp_trim_excerpt($text = '') {
2144 $raw_excerpt = $text;
2145 if ( '' == $text ) {
2146 $text = get_the_content('');
2148 $text = strip_shortcodes( $text );
2150 $text = apply_filters('the_content', $text);
2151 $text = str_replace(']]>', ']]>', $text);
2152 $excerpt_length = apply_filters('excerpt_length', 55);
2153 $excerpt_more = apply_filters('excerpt_more', ' ' . '[...]');
2154 $text = wp_trim_words( $text, $excerpt_length, $excerpt_more );
2156 return apply_filters('wp_trim_excerpt', $text, $raw_excerpt);
2160 * Trims text to a certain number of words.
2162 * This function is localized. For languages that count 'words' by the individual
2163 * character (such as East Asian languages), the $num_words argument will apply
2164 * to the number of individual characters.
2168 * @param string $text Text to trim.
2169 * @param int $num_words Number of words. Default 55.
2170 * @param string $more What to append if $text needs to be trimmed. Default '…'.
2171 * @return string Trimmed text.
2173 function wp_trim_words( $text, $num_words = 55, $more = null ) {
2174 if ( null === $more )
2175 $more = __( '…' );
2176 $original_text = $text;
2177 $text = wp_strip_all_tags( $text );
2178 /* translators: If your word count is based on single characters (East Asian characters),
2179 enter 'characters'. Otherwise, enter 'words'. Do not translate into your own language. */
2180 if ( 'characters' == _x( 'words', 'word count: words or characters?' ) && preg_match( '/^utf\-?8$/i', get_option( 'blog_charset' ) ) ) {
2181 $text = trim( preg_replace( "/[\n\r\t ]+/", ' ', $text ), ' ' );
2182 preg_match_all( '/./u', $text, $words_array );
2183 $words_array = array_slice( $words_array[0], 0, $num_words + 1 );
2186 $words_array = preg_split( "/[\n\r\t ]+/", $text, $num_words + 1, PREG_SPLIT_NO_EMPTY );
2189 if ( count( $words_array ) > $num_words ) {
2190 array_pop( $words_array );
2191 $text = implode( $sep, $words_array );
2192 $text = $text . $more;
2194 $text = implode( $sep, $words_array );
2196 return apply_filters( 'wp_trim_words', $text, $num_words, $more, $original_text );
2200 * Converts named entities into numbered entities.
2204 * @param string $text The text within which entities will be converted.
2205 * @return string Text with converted entities.
2207 function ent2ncr($text) {
2209 // Allow a plugin to short-circuit and override the mappings.
2210 $filtered = apply_filters( 'pre_ent2ncr', null, $text );
2211 if( null !== $filtered )
2215 '"' => '"',
2217 '⁄' => '/',
2221 ' ' => ' ',
2222 '¡' => '¡',
2223 '¢' => '¢',
2224 '£' => '£',
2225 '¤' => '¤',
2226 '¥' => '¥',
2227 '¦' => '¦',
2228 '&brkbar;' => '¦',
2229 '§' => '§',
2230 '¨' => '¨',
2231 '¨' => '¨',
2232 '©' => '©',
2233 'ª' => 'ª',
2234 '«' => '«',
2235 '¬' => '¬',
2236 '­' => '­',
2237 '®' => '®',
2238 '¯' => '¯',
2239 '&hibar;' => '¯',
2240 '°' => '°',
2241 '±' => '±',
2242 '²' => '²',
2243 '³' => '³',
2244 '´' => '´',
2245 'µ' => 'µ',
2246 '¶' => '¶',
2247 '·' => '·',
2248 '¸' => '¸',
2249 '¹' => '¹',
2250 'º' => 'º',
2251 '»' => '»',
2252 '¼' => '¼',
2253 '½' => '½',
2254 '¾' => '¾',
2255 '¿' => '¿',
2256 'À' => 'À',
2257 'Á' => 'Á',
2258 'Â' => 'Â',
2259 'Ã' => 'Ã',
2260 'Ä' => 'Ä',
2261 'Å' => 'Å',
2262 'Æ' => 'Æ',
2263 'Ç' => 'Ç',
2264 'È' => 'È',
2265 'É' => 'É',
2266 'Ê' => 'Ê',
2267 'Ë' => 'Ë',
2268 'Ì' => 'Ì',
2269 'Í' => 'Í',
2270 'Î' => 'Î',
2271 'Ï' => 'Ï',
2272 'Ð' => 'Ð',
2273 'Ñ' => 'Ñ',
2274 'Ò' => 'Ò',
2275 'Ó' => 'Ó',
2276 'Ô' => 'Ô',
2277 'Õ' => 'Õ',
2278 'Ö' => 'Ö',
2279 '×' => '×',
2280 'Ø' => 'Ø',
2281 'Ù' => 'Ù',
2282 'Ú' => 'Ú',
2283 'Û' => 'Û',
2284 'Ü' => 'Ü',
2285 'Ý' => 'Ý',
2286 'Þ' => 'Þ',
2287 'ß' => 'ß',
2288 'à' => 'à',
2289 'á' => 'á',
2290 'â' => 'â',
2291 'ã' => 'ã',
2292 'ä' => 'ä',
2293 'å' => 'å',
2294 'æ' => 'æ',
2295 'ç' => 'ç',
2296 'è' => 'è',
2297 'é' => 'é',
2298 'ê' => 'ê',
2299 'ë' => 'ë',
2300 'ì' => 'ì',
2301 'í' => 'í',
2302 'î' => 'î',
2303 'ï' => 'ï',
2304 'ð' => 'ð',
2305 'ñ' => 'ñ',
2306 'ò' => 'ò',
2307 'ó' => 'ó',
2308 'ô' => 'ô',
2309 'õ' => 'õ',
2310 'ö' => 'ö',
2311 '÷' => '÷',
2312 'ø' => 'ø',
2313 'ù' => 'ù',
2314 'ú' => 'ú',
2315 'û' => 'û',
2316 'ü' => 'ü',
2317 'ý' => 'ý',
2318 'þ' => 'þ',
2319 'ÿ' => 'ÿ',
2320 'Œ' => 'Œ',
2321 'œ' => 'œ',
2322 'Š' => 'Š',
2323 'š' => 'š',
2324 'Ÿ' => 'Ÿ',
2325 'ƒ' => 'ƒ',
2326 'ˆ' => 'ˆ',
2327 '˜' => '˜',
2328 'Α' => 'Α',
2329 'Β' => 'Β',
2330 'Γ' => 'Γ',
2331 'Δ' => 'Δ',
2332 'Ε' => 'Ε',
2333 'Ζ' => 'Ζ',
2334 'Η' => 'Η',
2335 'Θ' => 'Θ',
2336 'Ι' => 'Ι',
2337 'Κ' => 'Κ',
2338 'Λ' => 'Λ',
2342 'Ο' => 'Ο',
2344 'Ρ' => 'Ρ',
2345 'Σ' => 'Σ',
2346 'Τ' => 'Τ',
2347 'Υ' => 'Υ',
2348 'Φ' => 'Φ',
2349 'Χ' => 'Χ',
2350 'Ψ' => 'Ψ',
2351 'Ω' => 'Ω',
2352 'α' => 'α',
2353 'β' => 'β',
2354 'γ' => 'γ',
2355 'δ' => 'δ',
2356 'ε' => 'ε',
2357 'ζ' => 'ζ',
2358 'η' => 'η',
2359 'θ' => 'θ',
2360 'ι' => 'ι',
2361 'κ' => 'κ',
2362 'λ' => 'λ',
2366 'ο' => 'ο',
2368 'ρ' => 'ρ',
2369 'ς' => 'ς',
2370 'σ' => 'σ',
2371 'τ' => 'τ',
2372 'υ' => 'υ',
2373 'φ' => 'φ',
2374 'χ' => 'χ',
2375 'ψ' => 'ψ',
2376 'ω' => 'ω',
2377 'ϑ' => 'ϑ',
2378 'ϒ' => 'ϒ',
2379 'ϖ' => 'ϖ',
2380 ' ' => ' ',
2381 ' ' => ' ',
2382 ' ' => ' ',
2383 '‌' => '‌',
2384 '‍' => '‍',
2385 '‎' => '‎',
2386 '‏' => '‏',
2387 '–' => '–',
2388 '—' => '—',
2389 '‘' => '‘',
2390 '’' => '’',
2391 '‚' => '‚',
2392 '“' => '“',
2393 '”' => '”',
2394 '„' => '„',
2395 '†' => '†',
2396 '‡' => '‡',
2397 '•' => '•',
2398 '…' => '…',
2399 '‰' => '‰',
2400 '′' => '′',
2401 '″' => '″',
2402 '‹' => '‹',
2403 '›' => '›',
2404 '‾' => '‾',
2405 '⁄' => '⁄',
2406 '€' => '€',
2407 'ℑ' => 'ℑ',
2408 '℘' => '℘',
2409 'ℜ' => 'ℜ',
2410 '™' => '™',
2411 'ℵ' => 'ℵ',
2412 '↵' => '↵',
2413 '⇐' => '⇐',
2414 '⇑' => '⇑',
2415 '⇒' => '⇒',
2416 '⇓' => '⇓',
2417 '⇔' => '⇔',
2418 '∀' => '∀',
2419 '∂' => '∂',
2420 '∃' => '∃',
2421 '∅' => '∅',
2422 '∇' => '∇',
2423 '∈' => '∈',
2424 '∉' => '∉',
2425 '∋' => '∋',
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 '⊗' => '⊗',
2454 '⊥' => '⊥',
2455 '⋅' => '⋅',
2456 '⌈' => '⌈',
2457 '⌉' => '⌉',
2458 '⌊' => '⌊',
2459 '⌋' => '⌋',
2460 '⟨' => '〈',
2461 '⟩' => '〉',
2462 '←' => '←',
2463 '↑' => '↑',
2464 '→' => '→',
2465 '↓' => '↓',
2466 '↔' => '↔',
2467 '◊' => '◊',
2468 '♠' => '♠',
2469 '♣' => '♣',
2470 '♥' => '♥',
2471 '♦' => '♦'
2474 return str_replace( array_keys($to_ncr), array_values($to_ncr), $text );
2478 * Formats text for the rich text editor.
2480 * The filter 'richedit_pre' is applied here. If $text is empty the filter will
2481 * be applied to an empty string.
2485 * @param string $text The text to be formatted.
2486 * @return string The formatted text after filter is applied.
2488 function wp_richedit_pre($text) {
2489 // Filtering a blank results in an annoying <br />\n
2490 if ( empty($text) ) return apply_filters('richedit_pre', '');
2492 $output = convert_chars($text);
2493 $output = wpautop($output);
2494 $output = htmlspecialchars($output, ENT_NOQUOTES);
2496 return apply_filters('richedit_pre', $output);
2500 * Formats text for the HTML editor.
2502 * Unless $output is empty it will pass through htmlspecialchars before the
2503 * 'htmledit_pre' filter is applied.
2507 * @param string $output The text to be formatted.
2508 * @return string Formatted text after filter applied.
2510 function wp_htmledit_pre($output) {
2511 if ( !empty($output) )
2512 $output = htmlspecialchars($output, ENT_NOQUOTES); // convert only < > &
2514 return apply_filters('htmledit_pre', $output);
2518 * Perform a deep string replace operation to ensure the values in $search are no longer present
2520 * Repeats the replacement operation until it no longer replaces anything so as to remove "nested" values
2521 * e.g. $subject = '%0%0%0DDD', $search ='%0D', $result ='' rather than the '%0%0DD' that
2522 * str_replace would return
2527 * @param string|array $search
2528 * @param string $subject
2529 * @return string The processed string
2531 function _deep_replace( $search, $subject ) {
2533 $subject = (string) $subject;
2536 foreach ( (array) $search as $val ) {
2537 while ( strpos( $subject, $val ) !== false ) {
2539 $subject = str_replace( $val, '', $subject );
2548 * Escapes data for use in a MySQL query
2550 * This is just a handy shortcut for $wpdb->escape(), for completeness' sake
2553 * @param string $sql Unescaped SQL data
2554 * @return string The cleaned $sql
2556 function esc_sql( $sql ) {
2558 return $wpdb->escape( $sql );
2562 * Checks and cleans a URL.
2564 * A number of characters are removed from the URL. If the URL is for displaying
2565 * (the default behaviour) ampersands are also replaced. The 'clean_url' filter
2566 * is applied to the returned cleaned URL.
2569 * @uses wp_kses_bad_protocol() To only permit protocols in the URL set
2570 * via $protocols or the common ones set in the function.
2572 * @param string $url The URL to be cleaned.
2573 * @param array $protocols Optional. An array of acceptable protocols.
2574 * Defaults to 'http', 'https', 'ftp', 'ftps', 'mailto', 'news', 'irc', 'gopher', 'nntp', 'feed', 'telnet', 'mms', 'rtsp', 'svn' if not set.
2575 * @param string $_context Private. Use esc_url_raw() for database usage.
2576 * @return string The cleaned $url after the 'clean_url' filter is applied.
2578 function esc_url( $url, $protocols = null, $_context = 'display' ) {
2579 $original_url = $url;
2583 $url = preg_replace('|[^a-z0-9-~+_.?#=!&;,/:%@$\|*\'()\\x80-\\xff]|i', '', $url);
2584 $strip = array('%0d', '%0a', '%0D', '%0A');
2585 $url = _deep_replace($strip, $url);
2586 $url = str_replace(';//', '://', $url);
2587 /* If the URL doesn't appear to contain a scheme, we
2588 * presume it needs http:// appended (unless a relative
2589 * link starting with /, # or ? or a php file).
2591 if ( strpos($url, ':') === false && ! in_array( $url[0], array( '/', '#', '?' ) ) &&
2592 ! preg_match('/^[a-z0-9-]+?\.php/i', $url) )
2593 $url = 'http://' . $url;
2595 // Replace ampersands and single quotes only when displaying.
2596 if ( 'display' == $_context ) {
2597 $url = wp_kses_normalize_entities( $url );
2598 $url = str_replace( '&', '&', $url );
2599 $url = str_replace( "'", ''', $url );
2602 if ( ! is_array( $protocols ) )
2603 $protocols = wp_allowed_protocols();
2604 if ( wp_kses_bad_protocol( $url, $protocols ) != $url )
2607 return apply_filters('clean_url', $url, $original_url, $_context);
2611 * Performs esc_url() for database usage.
2616 * @param string $url The URL to be cleaned.
2617 * @param array $protocols An array of acceptable protocols.
2618 * @return string The cleaned URL.
2620 function esc_url_raw( $url, $protocols = null ) {
2621 return esc_url( $url, $protocols, 'db' );
2625 * Convert entities, while preserving already-encoded entities.
2627 * @link http://www.php.net/htmlentities Borrowed from the PHP Manual user notes.
2631 * @param string $myHTML The text to be converted.
2632 * @return string Converted text.
2634 function htmlentities2($myHTML) {
2635 $translation_table = get_html_translation_table( HTML_ENTITIES, ENT_QUOTES );
2636 $translation_table[chr(38)] = '&';
2637 return preg_replace( "/&(?![A-Za-z]{0,4}\w{2,3};|#[0-9]{2,3};)/", "&", strtr($myHTML, $translation_table) );
2641 * Escape single quotes, htmlspecialchar " < > &, and fix line endings.
2643 * Escapes text strings for echoing in JS. It is intended to be used for inline JS
2644 * (in a tag attribute, for example onclick="..."). Note that the strings have to
2645 * be in single quotes. The filter 'js_escape' is also applied here.
2649 * @param string $text The text to be escaped.
2650 * @return string Escaped text.
2652 function esc_js( $text ) {
2653 $safe_text = wp_check_invalid_utf8( $text );
2654 $safe_text = _wp_specialchars( $safe_text, ENT_COMPAT );
2655 $safe_text = preg_replace( '/&#(x)?0*(?(1)27|39);?/i', "'", stripslashes( $safe_text ) );
2656 $safe_text = str_replace( "\r", '', $safe_text );
2657 $safe_text = str_replace( "\n", '\\n', addslashes( $safe_text ) );
2658 return apply_filters( 'js_escape', $safe_text, $text );
2662 * Escaping for HTML blocks.
2666 * @param string $text
2669 function esc_html( $text ) {
2670 $safe_text = wp_check_invalid_utf8( $text );
2671 $safe_text = _wp_specialchars( $safe_text, ENT_QUOTES );
2672 return apply_filters( 'esc_html', $safe_text, $text );
2676 * Escaping for HTML attributes.
2680 * @param string $text
2683 function esc_attr( $text ) {
2684 $safe_text = wp_check_invalid_utf8( $text );
2685 $safe_text = _wp_specialchars( $safe_text, ENT_QUOTES );
2686 return apply_filters( 'attribute_escape', $safe_text, $text );
2690 * Escaping for textarea values.
2694 * @param string $text
2697 function esc_textarea( $text ) {
2698 $safe_text = htmlspecialchars( $text, ENT_QUOTES );
2699 return apply_filters( 'esc_textarea', $safe_text, $text );
2703 * Escape a HTML tag name.
2707 * @param string $tag_name
2710 function tag_escape($tag_name) {
2711 $safe_tag = strtolower( preg_replace('/[^a-zA-Z0-9_:]/', '', $tag_name) );
2712 return apply_filters('tag_escape', $safe_tag, $tag_name);
2716 * Escapes text for SQL LIKE special characters % and _.
2720 * @param string $text The text to be escaped.
2721 * @return string text, safe for inclusion in LIKE query.
2723 function like_escape($text) {
2724 return str_replace(array("%", "_"), array("\\%", "\\_"), $text);
2728 * Convert full URL paths to absolute paths.
2730 * Removes the http or https protocols and the domain. Keeps the path '/' at the
2731 * beginning, so it isn't a true relative link, but from the web root base.
2735 * @param string $link Full URL path.
2736 * @return string Absolute path.
2738 function wp_make_link_relative( $link ) {
2739 return preg_replace( '|https?://[^/]+(/.*)|i', '$1', $link );
2743 * Sanitises various option values based on the nature of the option.
2745 * This is basically a switch statement which will pass $value through a number
2746 * of functions depending on the $option.
2750 * @param string $option The name of the option.
2751 * @param string $value The unsanitised value.
2752 * @return string Sanitized value.
2754 function sanitize_option($option, $value) {
2756 switch ( $option ) {
2757 case 'admin_email' :
2758 case 'new_admin_email' :
2759 $value = sanitize_email( $value );
2760 if ( ! is_email( $value ) ) {
2761 $value = get_option( $option ); // Resets option to stored value in the case of failed sanitization
2762 if ( function_exists( 'add_settings_error' ) )
2763 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.' ) );
2767 case 'thumbnail_size_w':
2768 case 'thumbnail_size_h':
2769 case 'medium_size_w':
2770 case 'medium_size_h':
2771 case 'large_size_w':
2772 case 'large_size_h':
2773 case 'mailserver_port':
2774 case 'comment_max_links':
2775 case 'page_on_front':
2776 case 'page_for_posts':
2777 case 'rss_excerpt_length':
2778 case 'default_category':
2779 case 'default_email_category':
2780 case 'default_link_category':
2781 case 'close_comments_days_old':
2782 case 'comments_per_page':
2783 case 'thread_comments_depth':
2784 case 'users_can_register':
2785 case 'start_of_week':
2786 $value = absint( $value );
2789 case 'posts_per_page':
2790 case 'posts_per_rss':
2791 $value = (int) $value;
2792 if ( empty($value) )
2795 $value = abs($value);
2798 case 'default_ping_status':
2799 case 'default_comment_status':
2800 // Options that if not there have 0 value but need to be something like "closed"
2801 if ( $value == '0' || $value == '')
2805 case 'blogdescription':
2807 $value = wp_kses_post( $value );
2808 $value = esc_html( $value );
2811 case 'blog_charset':
2812 $value = preg_replace('/[^a-zA-Z0-9_-]/', '', $value); // strips slashes
2816 // This is the value if the settings checkbox is not checked on POST. Don't rely on this.
2817 if ( null === $value )
2820 $value = intval( $value );
2825 case 'mailserver_url':
2826 case 'mailserver_login':
2827 case 'mailserver_pass':
2829 $value = strip_tags( $value );
2830 $value = wp_kses_data( $value );
2834 $value = explode( "\n", $value );
2835 $value = array_filter( array_map( 'trim', $value ) );
2836 $value = array_filter( array_map( 'esc_url_raw', $value ) );
2837 $value = implode( "\n", $value );
2841 $value = preg_replace('/[^0-9:.-]/', '', $value); // strips slashes
2845 if ( (bool)preg_match( '#http(s?)://(.+)#i', $value) ) {
2846 $value = esc_url_raw($value);
2848 $value = get_option( $option ); // Resets option to stored value in the case of failed sanitization
2849 if ( function_exists('add_settings_error') )
2850 add_settings_error('siteurl', 'invalid_siteurl', __('The WordPress address you entered did not appear to be a valid URL. Please enter a valid URL.'));
2855 if ( (bool)preg_match( '#http(s?)://(.+)#i', $value) ) {
2856 $value = esc_url_raw($value);
2858 $value = get_option( $option ); // Resets option to stored value in the case of failed sanitization
2859 if ( function_exists('add_settings_error') )
2860 add_settings_error('home', 'invalid_home', __('The Site address you entered did not appear to be a valid URL. Please enter a valid URL.'));
2865 $allowed = get_available_languages();
2866 if ( ! in_array( $value, $allowed ) && ! empty( $value ) )
2867 $value = get_option( $option );
2870 case 'illegal_names':
2871 if ( ! is_array( $value ) )
2872 $value = explode( "\n", $value );
2874 $value = array_values( array_filter( array_map( 'trim', $value ) ) );
2880 case 'limited_email_domains':
2881 case 'banned_email_domains':
2882 if ( ! is_array( $value ) )
2883 $value = explode( "\n", $value );
2885 $domains = array_values( array_filter( array_map( 'trim', $value ) ) );
2888 foreach ( $domains as $domain ) {
2889 if ( ! preg_match( '/(--|\.\.)/', $domain ) && preg_match( '|^([a-zA-Z0-9-\.])+$|', $domain ) )
2896 case 'timezone_string':
2897 $allowed_zones = timezone_identifiers_list();
2898 if ( ! in_array( $value, $allowed_zones ) && ! empty( $value ) ) {
2899 $value = get_option( $option ); // Resets option to stored value in the case of failed sanitization
2900 if ( function_exists('add_settings_error') )
2901 add_settings_error('timezone_string', 'invalid_timezone_string', __('The timezone you have entered is not valid. Please select a valid timezone.') );
2905 case 'permalink_structure':
2906 case 'category_base':
2908 $value = esc_url_raw( $value );
2909 $value = str_replace( 'http://', '', $value );
2913 $value = apply_filters("sanitize_option_{$option}", $value, $option);
2919 * Parses a string into variables to be stored in an array.
2921 * Uses {@link http://www.php.net/parse_str parse_str()} and stripslashes if
2922 * {@link http://www.php.net/magic_quotes magic_quotes_gpc} is on.
2925 * @uses apply_filters() for the 'wp_parse_str' filter.
2927 * @param string $string The string to be parsed.
2928 * @param array $array Variables will be stored in this array.
2930 function wp_parse_str( $string, &$array ) {
2931 parse_str( $string, $array );
2932 if ( get_magic_quotes_gpc() )
2933 $array = stripslashes_deep( $array );
2934 $array = apply_filters( 'wp_parse_str', $array );
2938 * Convert lone less than signs.
2940 * KSES already converts lone greater than signs.
2942 * @uses wp_pre_kses_less_than_callback in the callback function.
2945 * @param string $text Text to be converted.
2946 * @return string Converted text.
2948 function wp_pre_kses_less_than( $text ) {
2949 return preg_replace_callback('%<[^>]*?((?=<)|>|$)%', 'wp_pre_kses_less_than_callback', $text);
2953 * Callback function used by preg_replace.
2955 * @uses esc_html to format the $matches text.
2958 * @param array $matches Populated by matches to preg_replace.
2959 * @return string The text returned after esc_html if needed.
2961 function wp_pre_kses_less_than_callback( $matches ) {
2962 if ( false === strpos($matches[0], '>') )
2963 return esc_html($matches[0]);
2968 * WordPress implementation of PHP sprintf() with filters.
2971 * @link http://www.php.net/sprintf
2973 * @param string $pattern The string which formatted args are inserted.
2974 * @param mixed $args,... Arguments to be formatted into the $pattern string.
2975 * @return string The formatted string.
2977 function wp_sprintf( $pattern ) {
2978 $args = func_get_args( );
2979 $len = strlen($pattern);
2983 while ( $len > $start ) {
2984 // Last character: append and break
2985 if ( strlen($pattern) - 1 == $start ) {
2986 $result .= substr($pattern, -1);
2990 // Literal %: append and continue
2991 if ( substr($pattern, $start, 2) == '%%' ) {
2997 // Get fragment before next %
2998 $end = strpos($pattern, '%', $start + 1);
2999 if ( false === $end )
3001 $fragment = substr($pattern, $start, $end - $start);
3003 // Fragment has a specifier
3004 if ( $pattern[$start] == '%' ) {
3005 // Find numbered arguments or take the next one in order
3006 if ( preg_match('/^%(\d+)\$/', $fragment, $matches) ) {
3007 $arg = isset($args[$matches[1]]) ? $args[$matches[1]] : '';
3008 $fragment = str_replace("%{$matches[1]}$", '%', $fragment);
3011 $arg = isset($args[$arg_index]) ? $args[$arg_index] : '';
3014 // Apply filters OR sprintf
3015 $_fragment = apply_filters( 'wp_sprintf', $fragment, $arg );
3016 if ( $_fragment != $fragment )
3017 $fragment = $_fragment;
3019 $fragment = sprintf($fragment, strval($arg) );
3022 // Append to result and move to next fragment
3023 $result .= $fragment;
3030 * Localize list items before the rest of the content.
3032 * The '%l' must be at the first characters can then contain the rest of the
3033 * content. The list items will have ', ', ', and', and ' and ' added depending
3034 * on the amount of list items in the $args parameter.
3038 * @param string $pattern Content containing '%l' at the beginning.
3039 * @param array $args List items to prepend to the content and replace '%l'.
3040 * @return string Localized list items and rest of the content.
3042 function wp_sprintf_l($pattern, $args) {
3044 if ( substr($pattern, 0, 2) != '%l' )
3047 // Nothing to work with
3051 // Translate and filter the delimiter set (avoid ampersands and entities here)
3052 $l = apply_filters('wp_sprintf_l', array(
3053 /* translators: used between list items, there is a space after the comma */
3054 'between' => __(', '),
3055 /* translators: used between list items, there is a space after the and */
3056 'between_last_two' => __(', and '),
3057 /* translators: used between only two list items, there is a space after the and */
3058 'between_only_two' => __(' and '),
3061 $args = (array) $args;
3062 $result = array_shift($args);
3063 if ( count($args) == 1 )
3064 $result .= $l['between_only_two'] . array_shift($args);
3065 // Loop when more than two args
3068 $arg = array_shift($args);
3071 $result .= $l['between_last_two'] . $arg;
3073 $result .= $l['between'] . $arg;
3075 return $result . substr($pattern, 2);
3079 * Safely extracts not more than the first $count characters from html string.
3081 * UTF-8, tags and entities safe prefix extraction. Entities inside will *NOT*
3082 * be counted as one character. For example & will be counted as 4, < as
3087 * @param integer $str String to get the excerpt from.
3088 * @param integer $count Maximum number of characters to take.
3089 * @return string The excerpt.
3091 function wp_html_excerpt( $str, $count ) {
3092 $str = wp_strip_all_tags( $str, true );
3093 $str = mb_substr( $str, 0, $count );
3094 // remove part of an entity at the end
3095 $str = preg_replace( '/&[^;\s]{0,6}$/', '', $str );
3100 * Add a Base url to relative links in passed content.
3102 * By default it supports the 'src' and 'href' attributes. However this can be
3103 * changed via the 3rd param.
3107 * @param string $content String to search for links in.
3108 * @param string $base The base URL to prefix to links.
3109 * @param array $attrs The attributes which should be processed.
3110 * @return string The processed content.
3112 function links_add_base_url( $content, $base, $attrs = array('src', 'href') ) {
3113 global $_links_add_base;
3114 $_links_add_base = $base;
3115 $attrs = implode('|', (array)$attrs);
3116 return preg_replace_callback( "!($attrs)=(['\"])(.+?)\\2!i", '_links_add_base', $content );
3120 * Callback to add a base url to relative links in passed content.
3125 * @param string $m The matched link.
3126 * @return string The processed link.
3128 function _links_add_base($m) {
3129 global $_links_add_base;
3130 //1 = attribute name 2 = quotation mark 3 = URL
3131 return $m[1] . '=' . $m[2] .
3132 ( preg_match( '#^(\w{1,20}):#', $m[3], $protocol ) && in_array( $protocol[1], wp_allowed_protocols() ) ?
3134 path_join( $_links_add_base, $m[3] ) )
3139 * Adds a Target attribute to all links in passed content.
3141 * This function by default only applies to <a> tags, however this can be
3142 * modified by the 3rd param.
3144 * <b>NOTE:</b> Any current target attributed will be stripped and replaced.
3148 * @param string $content String to search for links in.
3149 * @param string $target The Target to add to the links.
3150 * @param array $tags An array of tags to apply to.
3151 * @return string The processed content.
3153 function links_add_target( $content, $target = '_blank', $tags = array('a') ) {
3154 global $_links_add_target;
3155 $_links_add_target = $target;
3156 $tags = implode('|', (array)$tags);
3157 return preg_replace_callback( "!<($tags)(.+?)>!i", '_links_add_target', $content );
3161 * Callback to add a target attribute to all links in passed content.
3166 * @param string $m The matched link.
3167 * @return string The processed link.
3169 function _links_add_target( $m ) {
3170 global $_links_add_target;
3172 $link = preg_replace('|(target=[\'"](.*?)[\'"])|i', '', $m[2]);
3173 return '<' . $tag . $link . ' target="' . esc_attr( $_links_add_target ) . '">';
3176 // normalize EOL characters and strip duplicate whitespace
3177 function normalize_whitespace( $str ) {
3179 $str = str_replace("\r", "\n", $str);
3180 $str = preg_replace( array( '/\n+/', '/[ \t]+/' ), array( "\n", ' ' ), $str );
3185 * Properly strip all HTML tags including script and style
3189 * @param string $string String containing HTML tags
3190 * @param bool $remove_breaks optional Whether to remove left over line breaks and white space chars
3191 * @return string The processed string.
3193 function wp_strip_all_tags($string, $remove_breaks = false) {
3194 $string = preg_replace( '@<(script|style)[^>]*?>.*?</\\1>@si', '', $string );
3195 $string = strip_tags($string);
3197 if ( $remove_breaks )
3198 $string = preg_replace('/[\r\n\t ]+/', ' ', $string);
3200 return trim( $string );
3204 * Sanitize a string from user input or from the db
3206 * check for invalid UTF-8,
3207 * Convert single < characters to entity,
3209 * remove line breaks, tabs and extra white space,
3214 * @param string $str
3217 function sanitize_text_field($str) {
3218 $filtered = wp_check_invalid_utf8( $str );
3220 if ( strpos($filtered, '<') !== false ) {
3221 $filtered = wp_pre_kses_less_than( $filtered );
3222 // This will strip extra whitespace for us.
3223 $filtered = wp_strip_all_tags( $filtered, true );
3225 $filtered = trim( preg_replace('/[\r\n\t ]+/', ' ', $filtered) );
3230 while ( preg_match('/%[a-f0-9]{2}/i', $filtered, $match) ) {
3231 $filtered = str_replace($match[0], '', $filtered);
3236 // Strip out the whitespace that may now exist after removing the octets.
3237 $filtered = trim( preg_replace('/ +/', ' ', $filtered) );
3240 return apply_filters('sanitize_text_field', $filtered, $str);
3244 * i18n friendly version of basename()
3248 * @param string $path A path.
3249 * @param string $suffix If the filename ends in suffix this will also be cut off.
3252 function wp_basename( $path, $suffix = '' ) {
3253 return urldecode( basename( str_replace( array( '%2F', '%5C' ), '/', urlencode( $path ) ), $suffix ) );
3257 * Forever eliminate "Wordpress" from the planet (or at least the little bit we can influence).
3259 * Violating our coding standards for a good function name.
3263 function capital_P_dangit( $text ) {
3264 // Simple replacement for titles
3265 if ( 'the_title' === current_filter() )
3266 return str_replace( 'Wordpress', 'WordPress', $text );
3267 // Still here? Use the more judicious replacement
3268 static $dblq = false;
3269 if ( false === $dblq )
3270 $dblq = _x( '“', 'opening curly double quote' );
3272 array( ' Wordpress', '‘Wordpress', $dblq . 'Wordpress', '>Wordpress', '(Wordpress' ),
3273 array( ' WordPress', '‘WordPress', $dblq . 'WordPress', '>WordPress', '(WordPress' ),
3279 * Sanitize a mime type
3283 * @param string $mime_type Mime type
3284 * @return string Sanitized mime type
3286 function sanitize_mime_type( $mime_type ) {
3287 $sani_mime_type = preg_replace( '/[^-+*.a-zA-Z0-9\/]/', '', $mime_type );
3288 return apply_filters( 'sanitize_mime_type', $sani_mime_type, $mime_type );
3292 * Sanitize space or carriage return separated URLs that are used to send trackbacks.
3296 * @param string $to_ping Space or carriage return separated URLs
3297 * @return string URLs starting with the http or https protocol, separated by a carriage return.
3299 function sanitize_trackback_urls( $to_ping ) {
3300 $urls_to_ping = preg_split( '/[\r\n\t ]/', trim( $to_ping ), -1, PREG_SPLIT_NO_EMPTY );
3301 foreach ( $urls_to_ping as $k => $url ) {
3302 if ( !preg_match( '#^https?://.#i', $url ) )
3303 unset( $urls_to_ping[$k] );
3305 $urls_to_ping = array_map( 'esc_url_raw', $urls_to_ping );
3306 $urls_to_ping = implode( "\n", $urls_to_ping );
3307 return apply_filters( 'sanitize_trackback_urls', $urls_to_ping, $to_ping );