3 * Main WordPress Formatting API.
5 * Handles many functions for formatting output.
11 * Replaces common plain text characters into formatted entities
15 * 'cause today's effort makes it worth tomorrow's "holiday" ...
19 * ’cause today’s effort makes it worth tomorrow’s “holiday” …
21 * Code within certain html blocks are skipped.
23 * Do not use this function before the 'init' action hook; everything will break.
27 * @global array $wp_cockneyreplace Array of formatted entities for certain common phrases
28 * @global array $shortcode_tags
29 * @staticvar array $static_characters
30 * @staticvar array $static_replacements
31 * @staticvar array $dynamic_characters
32 * @staticvar array $dynamic_replacements
33 * @staticvar array $default_no_texturize_tags
34 * @staticvar array $default_no_texturize_shortcodes
35 * @staticvar bool $run_texturize
37 * @param string $text The text to be formatted
38 * @param bool $reset Set to true for unit testing. Translated patterns will reset.
39 * @return string The string replaced with html entities
41 function wptexturize( $text, $reset = false ) {
42 global $wp_cockneyreplace, $shortcode_tags;
43 static $static_characters = null,
44 $static_replacements = null,
45 $dynamic_characters = null,
46 $dynamic_replacements = null,
47 $default_no_texturize_tags = null,
48 $default_no_texturize_shortcodes = null,
49 $run_texturize = true,
53 $opening_quote = null,
54 $closing_quote = null,
55 $opening_single_quote = null,
56 $closing_single_quote = null,
57 $open_q_flag = '<!--oq-->',
58 $open_sq_flag = '<!--osq-->',
59 $apos_flag = '<!--apos-->';
61 // If there's nothing to do, just stop.
62 if ( empty( $text ) || false === $run_texturize ) {
66 // Set up static variables. Run once only.
67 if ( $reset || ! isset( $static_characters ) ) {
69 * Filter whether to skip running wptexturize().
71 * Passing false to the filter will effectively short-circuit wptexturize().
72 * returning the original text passed to the function instead.
74 * The filter runs only once, the first time wptexturize() is called.
80 * @param bool $run_texturize Whether to short-circuit wptexturize().
82 $run_texturize = apply_filters( 'run_wptexturize', $run_texturize );
83 if ( false === $run_texturize ) {
87 /* translators: opening curly double quote */
88 $opening_quote = _x( '“', 'opening curly double quote' );
89 /* translators: closing curly double quote */
90 $closing_quote = _x( '”', 'closing curly double quote' );
92 /* translators: apostrophe, for example in 'cause or can't */
93 $apos = _x( '’', 'apostrophe' );
95 /* translators: prime, for example in 9' (nine feet) */
96 $prime = _x( '′', 'prime' );
97 /* translators: double prime, for example in 9" (nine inches) */
98 $double_prime = _x( '″', 'double prime' );
100 /* translators: opening curly single quote */
101 $opening_single_quote = _x( '‘', 'opening curly single quote' );
102 /* translators: closing curly single quote */
103 $closing_single_quote = _x( '’', 'closing curly single quote' );
105 /* translators: en dash */
106 $en_dash = _x( '–', 'en dash' );
107 /* translators: em dash */
108 $em_dash = _x( '—', 'em dash' );
110 $default_no_texturize_tags = array('pre', 'code', 'kbd', 'style', 'script', 'tt');
111 $default_no_texturize_shortcodes = array('code');
113 // if a plugin has provided an autocorrect array, use it
114 if ( isset($wp_cockneyreplace) ) {
115 $cockney = array_keys( $wp_cockneyreplace );
116 $cockneyreplace = array_values( $wp_cockneyreplace );
118 /* translators: This is a comma-separated list of words that defy the syntax of quotations in normal use,
119 * for example... 'We do not have enough words yet' ... is a typical quoted phrase. But when we write
120 * lines of code 'til we have enough of 'em, then we need to insert apostrophes instead of quotes.
122 $cockney = explode( ',', _x( "'tain't,'twere,'twas,'tis,'twill,'til,'bout,'nuff,'round,'cause,'em",
123 'Comma-separated list of words to texturize in your language' ) );
125 $cockneyreplace = explode( ',', _x( '’tain’t,’twere,’twas,’tis,’twill,’til,’bout,’nuff,’round,’cause,’em',
126 'Comma-separated list of replacement words in your language' ) );
129 $static_characters = array_merge( array( '...', '``', '\'\'', ' (tm)' ), $cockney );
130 $static_replacements = array_merge( array( '…', $opening_quote, $closing_quote, ' ™' ), $cockneyreplace );
133 // Pattern-based replacements of characters.
134 // Sort the remaining patterns into several arrays for performance tuning.
135 $dynamic_characters = array( 'apos' => array(), 'quote' => array(), 'dash' => array() );
136 $dynamic_replacements = array( 'apos' => array(), 'quote' => array(), 'dash' => array() );
138 $spaces = wp_spaces_regexp();
140 // '99' and '99" are ambiguous among other patterns; assume it's an abbreviated year at the end of a quotation.
141 if ( "'" !== $apos || "'" !== $closing_single_quote ) {
142 $dynamic[ '/\'(\d\d)\'(?=\Z|[.,:;!?)}\-\]]|>|' . $spaces . ')/' ] = $apos_flag . '$1' . $closing_single_quote;
144 if ( "'" !== $apos || '"' !== $closing_quote ) {
145 $dynamic[ '/\'(\d\d)"(?=\Z|[.,:;!?)}\-\]]|>|' . $spaces . ')/' ] = $apos_flag . '$1' . $closing_quote;
148 // '99 '99s '99's (apostrophe) But never '9 or '99% or '999 or '99.0.
149 if ( "'" !== $apos ) {
150 $dynamic[ '/\'(?=\d\d(?:\Z|(?![%\d]|[.,]\d)))/' ] = $apos_flag;
153 // Quoted Numbers like '0.42'
154 if ( "'" !== $opening_single_quote && "'" !== $closing_single_quote ) {
155 $dynamic[ '/(?<=\A|' . $spaces . ')\'(\d[.,\d]*)\'/' ] = $open_sq_flag . '$1' . $closing_single_quote;
158 // Single quote at start, or preceded by (, {, <, [, ", -, or spaces.
159 if ( "'" !== $opening_single_quote ) {
160 $dynamic[ '/(?<=\A|[([{"\-]|<|' . $spaces . ')\'/' ] = $open_sq_flag;
163 // Apostrophe in a word. No spaces, double apostrophes, or other punctuation.
164 if ( "'" !== $apos ) {
165 $dynamic[ '/(?<!' . $spaces . ')\'(?!\Z|[.,:;!?"\'(){}[\]\-]|&[lg]t;|' . $spaces . ')/' ] = $apos_flag;
168 $dynamic_characters['apos'] = array_keys( $dynamic );
169 $dynamic_replacements['apos'] = array_values( $dynamic );
172 // Quoted Numbers like "42"
173 if ( '"' !== $opening_quote && '"' !== $closing_quote ) {
174 $dynamic[ '/(?<=\A|' . $spaces . ')"(\d[.,\d]*)"/' ] = $open_q_flag . '$1' . $closing_quote;
177 // Double quote at start, or preceded by (, {, <, [, -, or spaces, and not followed by spaces.
178 if ( '"' !== $opening_quote ) {
179 $dynamic[ '/(?<=\A|[([{\-]|<|' . $spaces . ')"(?!' . $spaces . ')/' ] = $open_q_flag;
182 $dynamic_characters['quote'] = array_keys( $dynamic );
183 $dynamic_replacements['quote'] = array_values( $dynamic );
187 $dynamic[ '/---/' ] = $em_dash;
188 $dynamic[ '/(?<=^|' . $spaces . ')--(?=$|' . $spaces . ')/' ] = $em_dash;
189 $dynamic[ '/(?<!xn)--/' ] = $en_dash;
190 $dynamic[ '/(?<=^|' . $spaces . ')-(?=$|' . $spaces . ')/' ] = $en_dash;
192 $dynamic_characters['dash'] = array_keys( $dynamic );
193 $dynamic_replacements['dash'] = array_values( $dynamic );
196 // Must do this every time in case plugins use these filters in a context sensitive manner
198 * Filter the list of HTML elements not to texturize.
202 * @param array $default_no_texturize_tags An array of HTML element names.
204 $no_texturize_tags = apply_filters( 'no_texturize_tags', $default_no_texturize_tags );
206 * Filter the list of shortcodes not to texturize.
210 * @param array $default_no_texturize_shortcodes An array of shortcode names.
212 $no_texturize_shortcodes = apply_filters( 'no_texturize_shortcodes', $default_no_texturize_shortcodes );
214 $no_texturize_tags_stack = array();
215 $no_texturize_shortcodes_stack = array();
217 // Look for shortcodes and HTML elements.
219 preg_match_all( '@\[/?([^<>&/\[\]\x00-\x20=]++)@', $text, $matches );
220 $tagnames = array_intersect( array_keys( $shortcode_tags ), $matches[1] );
221 $found_shortcodes = ! empty( $tagnames );
222 $shortcode_regex = $found_shortcodes ? _get_wptexturize_shortcode_regex( $tagnames ) : '';
223 $regex = _get_wptexturize_split_regex( $shortcode_regex );
225 $textarr = preg_split( $regex, $text, -1, PREG_SPLIT_DELIM_CAPTURE | PREG_SPLIT_NO_EMPTY );
227 foreach ( $textarr as &$curl ) {
228 // Only call _wptexturize_pushpop_element if $curl is a delimiter.
230 if ( '<' === $first ) {
231 if ( '<!--' === substr( $curl, 0, 4 ) ) {
232 // This is an HTML comment delimiter.
235 // This is an HTML element delimiter.
237 // Replace each & with & unless it already looks like an entity.
238 $curl = preg_replace( '/&(?!#(?:\d+|x[a-f0-9]+);|[a-z1-4]{1,8};)/i', '&', $curl );
240 _wptexturize_pushpop_element( $curl, $no_texturize_tags_stack, $no_texturize_tags );
243 } elseif ( '' === trim( $curl ) ) {
244 // This is a newline between delimiters. Performance improves when we check this.
247 } elseif ( '[' === $first && $found_shortcodes && 1 === preg_match( '/^' . $shortcode_regex . '$/', $curl ) ) {
248 // This is a shortcode delimiter.
250 if ( '[[' !== substr( $curl, 0, 2 ) && ']]' !== substr( $curl, -2 ) ) {
251 // Looks like a normal shortcode.
252 _wptexturize_pushpop_element( $curl, $no_texturize_shortcodes_stack, $no_texturize_shortcodes );
254 // Looks like an escaped shortcode.
258 } elseif ( empty( $no_texturize_shortcodes_stack ) && empty( $no_texturize_tags_stack ) ) {
259 // This is neither a delimiter, nor is this content inside of no_texturize pairs. Do texturize.
261 $curl = str_replace( $static_characters, $static_replacements, $curl );
263 if ( false !== strpos( $curl, "'" ) ) {
264 $curl = preg_replace( $dynamic_characters['apos'], $dynamic_replacements['apos'], $curl );
265 $curl = wptexturize_primes( $curl, "'", $prime, $open_sq_flag, $closing_single_quote );
266 $curl = str_replace( $apos_flag, $apos, $curl );
267 $curl = str_replace( $open_sq_flag, $opening_single_quote, $curl );
269 if ( false !== strpos( $curl, '"' ) ) {
270 $curl = preg_replace( $dynamic_characters['quote'], $dynamic_replacements['quote'], $curl );
271 $curl = wptexturize_primes( $curl, '"', $double_prime, $open_q_flag, $closing_quote );
272 $curl = str_replace( $open_q_flag, $opening_quote, $curl );
274 if ( false !== strpos( $curl, '-' ) ) {
275 $curl = preg_replace( $dynamic_characters['dash'], $dynamic_replacements['dash'], $curl );
278 // 9x9 (times), but never 0x9999
279 if ( 1 === preg_match( '/(?<=\d)x\d/', $curl ) ) {
280 // Searching for a digit is 10 times more expensive than for the x, so we avoid doing this one!
281 $curl = preg_replace( '/\b(\d(?(?<=0)[\d\.,]+|[\d\.,]*))x(\d[\d\.,]*)\b/', '$1×$2', $curl );
284 // Replace each & with & unless it already looks like an entity.
285 $curl = preg_replace( '/&(?!#(?:\d+|x[a-f0-9]+);|[a-z1-4]{1,8};)/i', '&', $curl );
289 return implode( '', $textarr );
293 * Implements a logic tree to determine whether or not "7'." represents seven feet,
294 * then converts the special char into either a prime char or a closing quote char.
298 * @param string $haystack The plain text to be searched.
299 * @param string $needle The character to search for such as ' or ".
300 * @param string $prime The prime char to use for replacement.
301 * @param string $open_quote The opening quote char. Opening quote replacement must be
302 * accomplished already.
303 * @param string $close_quote The closing quote char to use for replacement.
304 * @return string The $haystack value after primes and quotes replacements.
306 function wptexturize_primes( $haystack, $needle, $prime, $open_quote, $close_quote ) {
307 $spaces = wp_spaces_regexp();
308 $flag = '<!--wp-prime-or-quote-->';
309 $quote_pattern = "/$needle(?=\\Z|[.,:;!?)}\\-\\]]|>|" . $spaces . ")/";
310 $prime_pattern = "/(?<=\\d)$needle/";
311 $flag_after_digit = "/(?<=\\d)$flag/";
312 $flag_no_digit = "/(?<!\\d)$flag/";
314 $sentences = explode( $open_quote, $haystack );
316 foreach ( $sentences as $key => &$sentence ) {
317 if ( false === strpos( $sentence, $needle ) ) {
319 } elseif ( 0 !== $key && 0 === substr_count( $sentence, $close_quote ) ) {
320 $sentence = preg_replace( $quote_pattern, $flag, $sentence, -1, $count );
322 // This sentence appears to have multiple closing quotes. Attempt Vulcan logic.
323 $sentence = preg_replace( $flag_no_digit, $close_quote, $sentence, -1, $count2 );
324 if ( 0 === $count2 ) {
325 // Try looking for a quote followed by a period.
326 $count2 = substr_count( $sentence, "$flag." );
328 // Assume the rightmost quote-period match is the end of quotation.
329 $pos = strrpos( $sentence, "$flag." );
331 // When all else fails, make the rightmost candidate a closing quote.
332 // This is most likely to be problematic in the context of bug #18549.
333 $pos = strrpos( $sentence, $flag );
335 $sentence = substr_replace( $sentence, $close_quote, $pos, strlen( $flag ) );
337 // Use conventional replacement on any remaining primes and quotes.
338 $sentence = preg_replace( $prime_pattern, $prime, $sentence );
339 $sentence = preg_replace( $flag_after_digit, $prime, $sentence );
340 $sentence = str_replace( $flag, $close_quote, $sentence );
341 } elseif ( 1 == $count ) {
342 // Found only one closing quote candidate, so give it priority over primes.
343 $sentence = str_replace( $flag, $close_quote, $sentence );
344 $sentence = preg_replace( $prime_pattern, $prime, $sentence );
346 // No closing quotes found. Just run primes pattern.
347 $sentence = preg_replace( $prime_pattern, $prime, $sentence );
350 $sentence = preg_replace( $prime_pattern, $prime, $sentence );
351 $sentence = preg_replace( $quote_pattern, $close_quote, $sentence );
353 if ( '"' == $needle && false !== strpos( $sentence, '"' ) ) {
354 $sentence = str_replace( '"', $close_quote, $sentence );
358 return implode( $open_quote, $sentences );
362 * Search for disabled element tags. Push element to stack on tag open and pop
365 * Assumes first char of $text is tag opening and last char is tag closing.
366 * Assumes second char of $text is optionally '/' to indicate closing as in </html>.
371 * @param string $text Text to check. Must be a tag like `<html>` or `[shortcode]`.
372 * @param array $stack List of open tag elements.
373 * @param array $disabled_elements The tag names to match against. Spaces are not allowed in tag names.
375 function _wptexturize_pushpop_element( $text, &$stack, $disabled_elements ) {
376 // Is it an opening tag or closing tag?
377 if ( isset( $text[1] ) && '/' !== $text[1] ) {
380 } elseif ( 0 == count( $stack ) ) {
381 // Stack is empty. Just stop.
384 $opening_tag = false;
388 // Parse out the tag name.
389 $space = strpos( $text, ' ' );
390 if ( false === $space ) {
393 $space -= $name_offset;
395 $tag = substr( $text, $name_offset, $space );
397 // Handle disabled tags.
398 if ( in_array( $tag, $disabled_elements ) ) {
399 if ( $opening_tag ) {
401 * This disables texturize until we find a closing tag of our type
402 * (e.g. <pre>) even if there was invalid nesting before that
404 * Example: in the case <pre>sadsadasd</code>"baba"</pre>
405 * "baba" won't be texturize
408 array_push( $stack, $tag );
409 } elseif ( end( $stack ) == $tag ) {
416 * Replaces double line-breaks with paragraph elements.
418 * A group of regex replaces used to identify text formatted with newlines and
419 * replace double line-breaks with HTML paragraph tags. The remaining line-breaks
420 * after conversion become <<br />> tags, unless $br is set to '0' or 'false'.
424 * @param string $pee The text which has to be formatted.
425 * @param bool $br Optional. If set, this will convert all remaining line-breaks
426 * after paragraphing. Default true.
427 * @return string Text which has been converted into correct paragraph tags.
429 function wpautop( $pee, $br = true ) {
432 if ( trim($pee) === '' )
435 // Just to make things a little easier, pad the end.
439 * Pre tags shouldn't be touched by autop.
440 * Replace pre tags with placeholders and bring them back after autop.
442 if ( strpos($pee, '<pre') !== false ) {
443 $pee_parts = explode( '</pre>', $pee );
444 $last_pee = array_pop($pee_parts);
448 foreach ( $pee_parts as $pee_part ) {
449 $start = strpos($pee_part, '<pre');
452 if ( $start === false ) {
457 $name = "<pre wp-pre-tag-$i></pre>";
458 $pre_tags[$name] = substr( $pee_part, $start ) . '</pre>';
460 $pee .= substr( $pee_part, 0, $start ) . $name;
466 // Change multiple <br>s into two line breaks, which will turn into paragraphs.
467 $pee = preg_replace('|<br\s*/?>\s*<br\s*/?>|', "\n\n", $pee);
469 $allblocks = '(?:table|thead|tfoot|caption|col|colgroup|tbody|tr|td|th|div|dl|dd|dt|ul|ol|li|pre|form|map|area|blockquote|address|math|style|p|h[1-6]|hr|fieldset|legend|section|article|aside|hgroup|header|footer|nav|figure|figcaption|details|menu|summary)';
471 // Add a single line break above block-level opening tags.
472 $pee = preg_replace('!(<' . $allblocks . '[\s/>])!', "\n$1", $pee);
474 // Add a double line break below block-level closing tags.
475 $pee = preg_replace('!(</' . $allblocks . '>)!', "$1\n\n", $pee);
477 // Standardize newline characters to "\n".
478 $pee = str_replace(array("\r\n", "\r"), "\n", $pee);
480 // Find newlines in all elements and add placeholders.
481 $pee = wp_replace_in_html_tags( $pee, array( "\n" => " <!-- wpnl --> " ) );
483 // Collapse line breaks before and after <option> elements so they don't get autop'd.
484 if ( strpos( $pee, '<option' ) !== false ) {
485 $pee = preg_replace( '|\s*<option|', '<option', $pee );
486 $pee = preg_replace( '|</option>\s*|', '</option>', $pee );
490 * Collapse line breaks inside <object> elements, before <param> and <embed> elements
491 * so they don't get autop'd.
493 if ( strpos( $pee, '</object>' ) !== false ) {
494 $pee = preg_replace( '|(<object[^>]*>)\s*|', '$1', $pee );
495 $pee = preg_replace( '|\s*</object>|', '</object>', $pee );
496 $pee = preg_replace( '%\s*(</?(?:param|embed)[^>]*>)\s*%', '$1', $pee );
500 * Collapse line breaks inside <audio> and <video> elements,
501 * before and after <source> and <track> elements.
503 if ( strpos( $pee, '<source' ) !== false || strpos( $pee, '<track' ) !== false ) {
504 $pee = preg_replace( '%([<\[](?:audio|video)[^>\]]*[>\]])\s*%', '$1', $pee );
505 $pee = preg_replace( '%\s*([<\[]/(?:audio|video)[>\]])%', '$1', $pee );
506 $pee = preg_replace( '%\s*(<(?:source|track)[^>]*>)\s*%', '$1', $pee );
509 // Remove more than two contiguous line breaks.
510 $pee = preg_replace("/\n\n+/", "\n\n", $pee);
512 // Split up the contents into an array of strings, separated by double line breaks.
513 $pees = preg_split('/\n\s*\n/', $pee, -1, PREG_SPLIT_NO_EMPTY);
515 // Reset $pee prior to rebuilding.
518 // Rebuild the content as a string, wrapping every bit with a <p>.
519 foreach ( $pees as $tinkle ) {
520 $pee .= '<p>' . trim($tinkle, "\n") . "</p>\n";
523 // Under certain strange conditions it could create a P of entirely whitespace.
524 $pee = preg_replace('|<p>\s*</p>|', '', $pee);
526 // Add a closing <p> inside <div>, <address>, or <form> tag if missing.
527 $pee = preg_replace('!<p>([^<]+)</(div|address|form)>!', "<p>$1</p></$2>", $pee);
529 // If an opening or closing block element tag is wrapped in a <p>, unwrap it.
530 $pee = preg_replace('!<p>\s*(</?' . $allblocks . '[^>]*>)\s*</p>!', "$1", $pee);
532 // In some cases <li> may get wrapped in <p>, fix them.
533 $pee = preg_replace("|<p>(<li.+?)</p>|", "$1", $pee);
535 // If a <blockquote> is wrapped with a <p>, move it inside the <blockquote>.
536 $pee = preg_replace('|<p><blockquote([^>]*)>|i', "<blockquote$1><p>", $pee);
537 $pee = str_replace('</blockquote></p>', '</p></blockquote>', $pee);
539 // If an opening or closing block element tag is preceded by an opening <p> tag, remove it.
540 $pee = preg_replace('!<p>\s*(</?' . $allblocks . '[^>]*>)!', "$1", $pee);
542 // If an opening or closing block element tag is followed by a closing <p> tag, remove it.
543 $pee = preg_replace('!(</?' . $allblocks . '[^>]*>)\s*</p>!', "$1", $pee);
545 // Optionally insert line breaks.
547 // Replace newlines that shouldn't be touched with a placeholder.
548 $pee = preg_replace_callback('/<(script|style).*?<\/\\1>/s', '_autop_newline_preservation_helper', $pee);
551 $pee = str_replace( array( '<br>', '<br/>' ), '<br />', $pee );
553 // Replace any new line characters that aren't preceded by a <br /> with a <br />.
554 $pee = preg_replace('|(?<!<br />)\s*\n|', "<br />\n", $pee);
556 // Replace newline placeholders with newlines.
557 $pee = str_replace('<WPPreserveNewline />', "\n", $pee);
560 // If a <br /> tag is after an opening or closing block tag, remove it.
561 $pee = preg_replace('!(</?' . $allblocks . '[^>]*>)\s*<br />!', "$1", $pee);
563 // If a <br /> tag is before a subset of opening or closing block tags, remove it.
564 $pee = preg_replace('!<br />(\s*</?(?:p|li|div|dl|dd|dt|th|pre|td|ul|ol)[^>]*>)!', '$1', $pee);
565 $pee = preg_replace( "|\n</p>$|", '</p>', $pee );
567 // Replace placeholder <pre> tags with their original content.
568 if ( !empty($pre_tags) )
569 $pee = str_replace(array_keys($pre_tags), array_values($pre_tags), $pee);
571 // Restore newlines in all elements.
572 if ( false !== strpos( $pee, '<!-- wpnl -->' ) ) {
573 $pee = str_replace( array( ' <!-- wpnl --> ', '<!-- wpnl -->' ), "\n", $pee );
580 * Separate HTML elements and comments from the text.
584 * @param string $input The text which has to be formatted.
585 * @return array The formatted text.
587 function wp_html_split( $input ) {
588 return preg_split( get_html_split_regex(), $input, -1, PREG_SPLIT_DELIM_CAPTURE );
592 * Retrieve the regular expression for an HTML element.
596 * @return string The regular expression
598 function get_html_split_regex() {
601 if ( ! isset( $regex ) ) {
603 '!' // Start of comment, after the <.
604 . '(?:' // Unroll the loop: Consume everything until --> is found.
605 . '-(?!->)' // Dash not followed by end of comment.
606 . '[^\-]*+' // Consume non-dashes.
607 . ')*+' // Loop possessively.
608 . '(?:-->)?'; // End of comment. If not found, match all input.
611 '!\[CDATA\[' // Start of comment, after the <.
612 . '[^\]]*+' // Consume non-].
613 . '(?:' // Unroll the loop: Consume everything until ]]> is found.
614 . '](?!]>)' // One ] not followed by end of comment.
615 . '[^\]]*+' // Consume non-].
616 . ')*+' // Loop possessively.
617 . '(?:]]>)?'; // End of comment. If not found, match all input.
620 '(?=' // Is the element escaped?
625 . '(?(?=!-)' // If yes, which type?
632 '/(' // Capture the entire match.
633 . '<' // Find start of element.
634 . '(?' // Conditional expression follows.
635 . $escaped // Find end of escaped element.
636 . '|' // ... else ...
637 . '[^>]*>?' // Find end of normal element.
646 * Retrieve the combined regular expression for HTML and shortcodes.
650 * @internal This function will be removed in 4.5.0 per Shortcode API Roadmap.
653 * @param string $shortcode_regex The result from _get_wptexturize_shortcode_regex(). Optional.
654 * @return string The regular expression
656 function _get_wptexturize_split_regex( $shortcode_regex = '' ) {
659 if ( ! isset( $html_regex ) ) {
661 '!' // Start of comment, after the <.
662 . '(?:' // Unroll the loop: Consume everything until --> is found.
663 . '-(?!->)' // Dash not followed by end of comment.
664 . '[^\-]*+' // Consume non-dashes.
665 . ')*+' // Loop possessively.
666 . '(?:-->)?'; // End of comment. If not found, match all input.
668 $html_regex = // Needs replaced with wp_html_split() per Shortcode API Roadmap.
669 '<' // Find start of element.
670 . '(?(?=!--)' // Is this a comment?
671 . $comment_regex // Find end of comment.
673 . '[^>]*>?' // Find end of element. If not found, match all input.
677 if ( empty( $shortcode_regex ) ) {
678 $regex = '/(' . $html_regex . ')/';
680 $regex = '/(' . $html_regex . '|' . $shortcode_regex . ')/';
687 * Retrieve the regular expression for shortcodes.
691 * @internal This function will be removed in 4.5.0 per Shortcode API Roadmap.
694 * @param array $tagnames List of shortcodes to find.
695 * @return string The regular expression
697 function _get_wptexturize_shortcode_regex( $tagnames ) {
698 $tagregexp = join( '|', array_map( 'preg_quote', $tagnames ) );
699 $tagregexp = "(?:$tagregexp)(?=[\\s\\]\\/])"; // Excerpt of get_shortcode_regex().
701 '\[' // Find start of shortcode.
702 . '[\/\[]?' // Shortcodes may begin with [/ or [[
703 . $tagregexp // Only match registered shortcodes, because performance.
705 . '[^\[\]<>]+' // Shortcodes do not contain other shortcodes. Quantifier critical.
707 . '<[^\[\]>]*>' // HTML elements permitted. Prevents matching ] before >.
708 . ')*+' // Possessive critical.
709 . '\]' // Find end of shortcode.
710 . '\]?'; // Shortcodes may end with ]]
716 * Replace characters or phrases within HTML elements only.
720 * @param string $haystack The text which has to be formatted.
721 * @param array $replace_pairs In the form array('from' => 'to', ...).
722 * @return string The formatted text.
724 function wp_replace_in_html_tags( $haystack, $replace_pairs ) {
725 // Find all elements.
726 $textarr = wp_html_split( $haystack );
729 // Optimize when searching for one item.
730 if ( 1 === count( $replace_pairs ) ) {
731 // Extract $needle and $replace.
732 foreach ( $replace_pairs as $needle => $replace );
734 // Loop through delimiters (elements) only.
735 for ( $i = 1, $c = count( $textarr ); $i < $c; $i += 2 ) {
736 if ( false !== strpos( $textarr[$i], $needle ) ) {
737 $textarr[$i] = str_replace( $needle, $replace, $textarr[$i] );
742 // Extract all $needles.
743 $needles = array_keys( $replace_pairs );
745 // Loop through delimiters (elements) only.
746 for ( $i = 1, $c = count( $textarr ); $i < $c; $i += 2 ) {
747 foreach ( $needles as $needle ) {
748 if ( false !== strpos( $textarr[$i], $needle ) ) {
749 $textarr[$i] = strtr( $textarr[$i], $replace_pairs );
751 // After one strtr() break out of the foreach loop and look at next element.
759 $haystack = implode( $textarr );
766 * Newline preservation help function for wpautop
771 * @param array $matches preg_replace_callback matches array
774 function _autop_newline_preservation_helper( $matches ) {
775 return str_replace( "\n", "<WPPreserveNewline />", $matches[0] );
779 * Don't auto-p wrap shortcodes that stand alone
781 * Ensures that shortcodes are not wrapped in `<p>...</p>`.
785 * @global array $shortcode_tags
787 * @param string $pee The content.
788 * @return string The filtered content.
790 function shortcode_unautop( $pee ) {
791 global $shortcode_tags;
793 if ( empty( $shortcode_tags ) || !is_array( $shortcode_tags ) ) {
797 $tagregexp = join( '|', array_map( 'preg_quote', array_keys( $shortcode_tags ) ) );
798 $spaces = wp_spaces_regexp();
802 . '<p>' // Opening paragraph
803 . '(?:' . $spaces . ')*+' // Optional leading whitespace
804 . '(' // 1: The shortcode
805 . '\\[' // Opening bracket
806 . "($tagregexp)" // 2: Shortcode name
807 . '(?![\\w-])' // Not followed by word character or hyphen
808 // Unroll the loop: Inside the opening shortcode tag
809 . '[^\\]\\/]*' // Not a closing bracket or forward slash
811 . '\\/(?!\\])' // A forward slash not followed by a closing bracket
812 . '[^\\]\\/]*' // Not a closing bracket or forward slash
815 . '\\/\\]' // Self closing tag and closing bracket
817 . '\\]' // Closing bracket
818 . '(?:' // Unroll the loop: Optionally, anything between the opening and closing shortcode tags
819 . '[^\\[]*+' // Not an opening bracket
821 . '\\[(?!\\/\\2\\])' // An opening bracket not followed by the closing shortcode tag
822 . '[^\\[]*+' // Not an opening bracket
824 . '\\[\\/\\2\\]' // Closing shortcode tag
828 . '(?:' . $spaces . ')*+' // optional trailing whitespace
829 . '<\\/p>' // closing paragraph
832 return preg_replace( $pattern, '$1', $pee );
836 * Checks to see if a string is utf8 encoded.
838 * NOTE: This function checks for 5-Byte sequences, UTF8
839 * has Bytes Sequences with a maximum length of 4.
841 * @author bmorel at ssi dot fr (modified)
844 * @param string $str The string to be checked
845 * @return bool True if $str fits a UTF-8 model, false otherwise.
847 function seems_utf8( $str ) {
848 mbstring_binary_safe_encoding();
849 $length = strlen($str);
850 reset_mbstring_encoding();
851 for ($i=0; $i < $length; $i++) {
853 if ($c < 0x80) $n = 0; // 0bbbbbbb
854 elseif (($c & 0xE0) == 0xC0) $n=1; // 110bbbbb
855 elseif (($c & 0xF0) == 0xE0) $n=2; // 1110bbbb
856 elseif (($c & 0xF8) == 0xF0) $n=3; // 11110bbb
857 elseif (($c & 0xFC) == 0xF8) $n=4; // 111110bb
858 elseif (($c & 0xFE) == 0xFC) $n=5; // 1111110b
859 else return false; // Does not match any model
860 for ($j=0; $j<$n; $j++) { // n bytes matching 10bbbbbb follow ?
861 if ((++$i == $length) || ((ord($str[$i]) & 0xC0) != 0x80))
869 * Converts a number of special characters into their HTML entities.
871 * Specifically deals with: &, <, >, ", and '.
873 * $quote_style can be set to ENT_COMPAT to encode " to
874 * ", or ENT_QUOTES to do both. Default is ENT_NOQUOTES where no quotes are encoded.
879 * @staticvar string $_charset
881 * @param string $string The text which is to be encoded.
882 * @param int|string $quote_style Optional. Converts double quotes if set to ENT_COMPAT,
883 * both single and double if set to ENT_QUOTES or none if set to ENT_NOQUOTES.
884 * Also compatible with old values; converting single quotes if set to 'single',
885 * double if set to 'double' or both if otherwise set.
886 * Default is ENT_NOQUOTES.
887 * @param string $charset Optional. The character encoding of the string. Default is false.
888 * @param bool $double_encode Optional. Whether to encode existing html entities. Default is false.
889 * @return string The encoded text with HTML entities.
891 function _wp_specialchars( $string, $quote_style = ENT_NOQUOTES, $charset = false, $double_encode = false ) {
892 $string = (string) $string;
894 if ( 0 === strlen( $string ) )
897 // Don't bother if there are no specialchars - saves some processing
898 if ( ! preg_match( '/[&<>"\']/', $string ) )
901 // Account for the previous behaviour of the function when the $quote_style is not an accepted value
902 if ( empty( $quote_style ) )
903 $quote_style = ENT_NOQUOTES;
904 elseif ( ! in_array( $quote_style, array( 0, 2, 3, 'single', 'double' ), true ) )
905 $quote_style = ENT_QUOTES;
907 // Store the site charset as a static to avoid multiple calls to wp_load_alloptions()
909 static $_charset = null;
910 if ( ! isset( $_charset ) ) {
911 $alloptions = wp_load_alloptions();
912 $_charset = isset( $alloptions['blog_charset'] ) ? $alloptions['blog_charset'] : '';
914 $charset = $_charset;
917 if ( in_array( $charset, array( 'utf8', 'utf-8', 'UTF8' ) ) )
920 $_quote_style = $quote_style;
922 if ( $quote_style === 'double' ) {
923 $quote_style = ENT_COMPAT;
924 $_quote_style = ENT_COMPAT;
925 } elseif ( $quote_style === 'single' ) {
926 $quote_style = ENT_NOQUOTES;
929 if ( ! $double_encode ) {
930 // Guarantee every &entity; is valid, convert &garbage; into &garbage;
931 // This is required for PHP < 5.4.0 because ENT_HTML401 flag is unavailable.
932 $string = wp_kses_normalize_entities( $string );
935 $string = @htmlspecialchars( $string, $quote_style, $charset, $double_encode );
937 // Backwards compatibility
938 if ( 'single' === $_quote_style )
939 $string = str_replace( "'", ''', $string );
945 * Converts a number of HTML entities into their special characters.
947 * Specifically deals with: &, <, >, ", and '.
949 * $quote_style can be set to ENT_COMPAT to decode " entities,
950 * or ENT_QUOTES to do both " and '. Default is ENT_NOQUOTES where no quotes are decoded.
954 * @param string $string The text which is to be decoded.
955 * @param string|int $quote_style Optional. Converts double quotes if set to ENT_COMPAT,
956 * both single and double if set to ENT_QUOTES or
957 * none if set to ENT_NOQUOTES.
958 * Also compatible with old _wp_specialchars() values;
959 * converting single quotes if set to 'single',
960 * double if set to 'double' or both if otherwise set.
961 * Default is ENT_NOQUOTES.
962 * @return string The decoded text without HTML entities.
964 function wp_specialchars_decode( $string, $quote_style = ENT_NOQUOTES ) {
965 $string = (string) $string;
967 if ( 0 === strlen( $string ) ) {
971 // Don't bother if there are no entities - saves a lot of processing
972 if ( strpos( $string, '&' ) === false ) {
976 // Match the previous behaviour of _wp_specialchars() when the $quote_style is not an accepted value
977 if ( empty( $quote_style ) ) {
978 $quote_style = ENT_NOQUOTES;
979 } elseif ( !in_array( $quote_style, array( 0, 2, 3, 'single', 'double' ), true ) ) {
980 $quote_style = ENT_QUOTES;
983 // More complete than get_html_translation_table( HTML_SPECIALCHARS )
984 $single = array( ''' => '\'', ''' => '\'' );
985 $single_preg = array( '/�*39;/' => ''', '/�*27;/i' => ''' );
986 $double = array( '"' => '"', '"' => '"', '"' => '"' );
987 $double_preg = array( '/�*34;/' => '"', '/�*22;/i' => '"' );
988 $others = array( '<' => '<', '<' => '<', '>' => '>', '>' => '>', '&' => '&', '&' => '&', '&' => '&' );
989 $others_preg = array( '/�*60;/' => '<', '/�*62;/' => '>', '/�*38;/' => '&', '/�*26;/i' => '&' );
991 if ( $quote_style === ENT_QUOTES ) {
992 $translation = array_merge( $single, $double, $others );
993 $translation_preg = array_merge( $single_preg, $double_preg, $others_preg );
994 } elseif ( $quote_style === ENT_COMPAT || $quote_style === 'double' ) {
995 $translation = array_merge( $double, $others );
996 $translation_preg = array_merge( $double_preg, $others_preg );
997 } elseif ( $quote_style === 'single' ) {
998 $translation = array_merge( $single, $others );
999 $translation_preg = array_merge( $single_preg, $others_preg );
1000 } elseif ( $quote_style === ENT_NOQUOTES ) {
1001 $translation = $others;
1002 $translation_preg = $others_preg;
1005 // Remove zero padding on numeric entities
1006 $string = preg_replace( array_keys( $translation_preg ), array_values( $translation_preg ), $string );
1008 // Replace characters according to translation table
1009 return strtr( $string, $translation );
1013 * Checks for invalid UTF8 in a string.
1017 * @staticvar bool $is_utf8
1018 * @staticvar bool $utf8_pcre
1020 * @param string $string The text which is to be checked.
1021 * @param bool $strip Optional. Whether to attempt to strip out invalid UTF8. Default is false.
1022 * @return string The checked text.
1024 function wp_check_invalid_utf8( $string, $strip = false ) {
1025 $string = (string) $string;
1027 if ( 0 === strlen( $string ) ) {
1031 // Store the site charset as a static to avoid multiple calls to get_option()
1032 static $is_utf8 = null;
1033 if ( ! isset( $is_utf8 ) ) {
1034 $is_utf8 = in_array( get_option( 'blog_charset' ), array( 'utf8', 'utf-8', 'UTF8', 'UTF-8' ) );
1040 // Check for support for utf8 in the installed PCRE library once and store the result in a static
1041 static $utf8_pcre = null;
1042 if ( ! isset( $utf8_pcre ) ) {
1043 $utf8_pcre = @preg_match( '/^./u', 'a' );
1045 // We can't demand utf8 in the PCRE installation, so just return the string in those cases
1046 if ( !$utf8_pcre ) {
1050 // preg_match fails when it encounters invalid UTF8 in $string
1051 if ( 1 === @preg_match( '/^./us', $string ) ) {
1055 // Attempt to strip the bad chars if requested (not recommended)
1056 if ( $strip && function_exists( 'iconv' ) ) {
1057 return iconv( 'utf-8', 'utf-8', $string );
1064 * Encode the Unicode values to be used in the URI.
1068 * @param string $utf8_string
1069 * @param int $length Max length of the string
1070 * @return string String with Unicode encoded for URI.
1072 function utf8_uri_encode( $utf8_string, $length = 0 ) {
1076 $unicode_length = 0;
1078 mbstring_binary_safe_encoding();
1079 $string_length = strlen( $utf8_string );
1080 reset_mbstring_encoding();
1082 for ($i = 0; $i < $string_length; $i++ ) {
1084 $value = ord( $utf8_string[ $i ] );
1086 if ( $value < 128 ) {
1087 if ( $length && ( $unicode_length >= $length ) )
1089 $unicode .= chr($value);
1092 if ( count( $values ) == 0 ) {
1093 if ( $value < 224 ) {
1095 } elseif ( $value < 240 ) {
1104 if ( $length && ( $unicode_length + ($num_octets * 3) ) > $length )
1106 if ( count( $values ) == $num_octets ) {
1107 for ( $j = 0; $j < $num_octets; $j++ ) {
1108 $unicode .= '%' . dechex( $values[ $j ] );
1111 $unicode_length += $num_octets * 3;
1123 * Converts all accent characters to ASCII characters.
1125 * If there are no accent characters, then the string given is just returned.
1129 * @param string $string Text that might have accent characters
1130 * @return string Filtered string with replaced "nice" characters.
1132 function remove_accents( $string ) {
1133 if ( !preg_match('/[\x80-\xff]/', $string) )
1136 if (seems_utf8($string)) {
1138 // Decompositions for Latin-1 Supplement
1139 chr(194).chr(170) => 'a', chr(194).chr(186) => 'o',
1140 chr(195).chr(128) => 'A', chr(195).chr(129) => 'A',
1141 chr(195).chr(130) => 'A', chr(195).chr(131) => 'A',
1142 chr(195).chr(132) => 'A', chr(195).chr(133) => 'A',
1143 chr(195).chr(134) => 'AE',chr(195).chr(135) => 'C',
1144 chr(195).chr(136) => 'E', chr(195).chr(137) => 'E',
1145 chr(195).chr(138) => 'E', chr(195).chr(139) => 'E',
1146 chr(195).chr(140) => 'I', chr(195).chr(141) => 'I',
1147 chr(195).chr(142) => 'I', chr(195).chr(143) => 'I',
1148 chr(195).chr(144) => 'D', chr(195).chr(145) => 'N',
1149 chr(195).chr(146) => 'O', chr(195).chr(147) => 'O',
1150 chr(195).chr(148) => 'O', chr(195).chr(149) => 'O',
1151 chr(195).chr(150) => 'O', chr(195).chr(153) => 'U',
1152 chr(195).chr(154) => 'U', chr(195).chr(155) => 'U',
1153 chr(195).chr(156) => 'U', chr(195).chr(157) => 'Y',
1154 chr(195).chr(158) => 'TH',chr(195).chr(159) => 's',
1155 chr(195).chr(160) => 'a', chr(195).chr(161) => 'a',
1156 chr(195).chr(162) => 'a', chr(195).chr(163) => 'a',
1157 chr(195).chr(164) => 'a', chr(195).chr(165) => 'a',
1158 chr(195).chr(166) => 'ae',chr(195).chr(167) => 'c',
1159 chr(195).chr(168) => 'e', chr(195).chr(169) => 'e',
1160 chr(195).chr(170) => 'e', chr(195).chr(171) => 'e',
1161 chr(195).chr(172) => 'i', chr(195).chr(173) => 'i',
1162 chr(195).chr(174) => 'i', chr(195).chr(175) => 'i',
1163 chr(195).chr(176) => 'd', chr(195).chr(177) => 'n',
1164 chr(195).chr(178) => 'o', chr(195).chr(179) => 'o',
1165 chr(195).chr(180) => 'o', chr(195).chr(181) => 'o',
1166 chr(195).chr(182) => 'o', chr(195).chr(184) => 'o',
1167 chr(195).chr(185) => 'u', chr(195).chr(186) => 'u',
1168 chr(195).chr(187) => 'u', chr(195).chr(188) => 'u',
1169 chr(195).chr(189) => 'y', chr(195).chr(190) => 'th',
1170 chr(195).chr(191) => 'y', chr(195).chr(152) => 'O',
1171 // Decompositions for Latin Extended-A
1172 chr(196).chr(128) => 'A', chr(196).chr(129) => 'a',
1173 chr(196).chr(130) => 'A', chr(196).chr(131) => 'a',
1174 chr(196).chr(132) => 'A', chr(196).chr(133) => 'a',
1175 chr(196).chr(134) => 'C', chr(196).chr(135) => 'c',
1176 chr(196).chr(136) => 'C', chr(196).chr(137) => 'c',
1177 chr(196).chr(138) => 'C', chr(196).chr(139) => 'c',
1178 chr(196).chr(140) => 'C', chr(196).chr(141) => 'c',
1179 chr(196).chr(142) => 'D', chr(196).chr(143) => 'd',
1180 chr(196).chr(144) => 'D', chr(196).chr(145) => 'd',
1181 chr(196).chr(146) => 'E', chr(196).chr(147) => 'e',
1182 chr(196).chr(148) => 'E', chr(196).chr(149) => 'e',
1183 chr(196).chr(150) => 'E', chr(196).chr(151) => 'e',
1184 chr(196).chr(152) => 'E', chr(196).chr(153) => 'e',
1185 chr(196).chr(154) => 'E', chr(196).chr(155) => 'e',
1186 chr(196).chr(156) => 'G', chr(196).chr(157) => 'g',
1187 chr(196).chr(158) => 'G', chr(196).chr(159) => 'g',
1188 chr(196).chr(160) => 'G', chr(196).chr(161) => 'g',
1189 chr(196).chr(162) => 'G', chr(196).chr(163) => 'g',
1190 chr(196).chr(164) => 'H', chr(196).chr(165) => 'h',
1191 chr(196).chr(166) => 'H', chr(196).chr(167) => 'h',
1192 chr(196).chr(168) => 'I', chr(196).chr(169) => 'i',
1193 chr(196).chr(170) => 'I', chr(196).chr(171) => 'i',
1194 chr(196).chr(172) => 'I', chr(196).chr(173) => 'i',
1195 chr(196).chr(174) => 'I', chr(196).chr(175) => 'i',
1196 chr(196).chr(176) => 'I', chr(196).chr(177) => 'i',
1197 chr(196).chr(178) => 'IJ',chr(196).chr(179) => 'ij',
1198 chr(196).chr(180) => 'J', chr(196).chr(181) => 'j',
1199 chr(196).chr(182) => 'K', chr(196).chr(183) => 'k',
1200 chr(196).chr(184) => 'k', chr(196).chr(185) => 'L',
1201 chr(196).chr(186) => 'l', chr(196).chr(187) => 'L',
1202 chr(196).chr(188) => 'l', chr(196).chr(189) => 'L',
1203 chr(196).chr(190) => 'l', chr(196).chr(191) => 'L',
1204 chr(197).chr(128) => 'l', chr(197).chr(129) => 'L',
1205 chr(197).chr(130) => 'l', chr(197).chr(131) => 'N',
1206 chr(197).chr(132) => 'n', chr(197).chr(133) => 'N',
1207 chr(197).chr(134) => 'n', chr(197).chr(135) => 'N',
1208 chr(197).chr(136) => 'n', chr(197).chr(137) => 'N',
1209 chr(197).chr(138) => 'n', chr(197).chr(139) => 'N',
1210 chr(197).chr(140) => 'O', chr(197).chr(141) => 'o',
1211 chr(197).chr(142) => 'O', chr(197).chr(143) => 'o',
1212 chr(197).chr(144) => 'O', chr(197).chr(145) => 'o',
1213 chr(197).chr(146) => 'OE',chr(197).chr(147) => 'oe',
1214 chr(197).chr(148) => 'R',chr(197).chr(149) => 'r',
1215 chr(197).chr(150) => 'R',chr(197).chr(151) => 'r',
1216 chr(197).chr(152) => 'R',chr(197).chr(153) => 'r',
1217 chr(197).chr(154) => 'S',chr(197).chr(155) => 's',
1218 chr(197).chr(156) => 'S',chr(197).chr(157) => 's',
1219 chr(197).chr(158) => 'S',chr(197).chr(159) => 's',
1220 chr(197).chr(160) => 'S', chr(197).chr(161) => 's',
1221 chr(197).chr(162) => 'T', chr(197).chr(163) => 't',
1222 chr(197).chr(164) => 'T', chr(197).chr(165) => 't',
1223 chr(197).chr(166) => 'T', chr(197).chr(167) => 't',
1224 chr(197).chr(168) => 'U', chr(197).chr(169) => 'u',
1225 chr(197).chr(170) => 'U', chr(197).chr(171) => 'u',
1226 chr(197).chr(172) => 'U', chr(197).chr(173) => 'u',
1227 chr(197).chr(174) => 'U', chr(197).chr(175) => 'u',
1228 chr(197).chr(176) => 'U', chr(197).chr(177) => 'u',
1229 chr(197).chr(178) => 'U', chr(197).chr(179) => 'u',
1230 chr(197).chr(180) => 'W', chr(197).chr(181) => 'w',
1231 chr(197).chr(182) => 'Y', chr(197).chr(183) => 'y',
1232 chr(197).chr(184) => 'Y', chr(197).chr(185) => 'Z',
1233 chr(197).chr(186) => 'z', chr(197).chr(187) => 'Z',
1234 chr(197).chr(188) => 'z', chr(197).chr(189) => 'Z',
1235 chr(197).chr(190) => 'z', chr(197).chr(191) => 's',
1236 // Decompositions for Latin Extended-B
1237 chr(200).chr(152) => 'S', chr(200).chr(153) => 's',
1238 chr(200).chr(154) => 'T', chr(200).chr(155) => 't',
1240 chr(226).chr(130).chr(172) => 'E',
1242 chr(194).chr(163) => '',
1243 // Vowels with diacritic (Vietnamese)
1245 chr(198).chr(160) => 'O', chr(198).chr(161) => 'o',
1246 chr(198).chr(175) => 'U', chr(198).chr(176) => 'u',
1248 chr(225).chr(186).chr(166) => 'A', chr(225).chr(186).chr(167) => 'a',
1249 chr(225).chr(186).chr(176) => 'A', chr(225).chr(186).chr(177) => 'a',
1250 chr(225).chr(187).chr(128) => 'E', chr(225).chr(187).chr(129) => 'e',
1251 chr(225).chr(187).chr(146) => 'O', chr(225).chr(187).chr(147) => 'o',
1252 chr(225).chr(187).chr(156) => 'O', chr(225).chr(187).chr(157) => 'o',
1253 chr(225).chr(187).chr(170) => 'U', chr(225).chr(187).chr(171) => 'u',
1254 chr(225).chr(187).chr(178) => 'Y', chr(225).chr(187).chr(179) => 'y',
1256 chr(225).chr(186).chr(162) => 'A', chr(225).chr(186).chr(163) => 'a',
1257 chr(225).chr(186).chr(168) => 'A', chr(225).chr(186).chr(169) => 'a',
1258 chr(225).chr(186).chr(178) => 'A', chr(225).chr(186).chr(179) => 'a',
1259 chr(225).chr(186).chr(186) => 'E', chr(225).chr(186).chr(187) => 'e',
1260 chr(225).chr(187).chr(130) => 'E', chr(225).chr(187).chr(131) => 'e',
1261 chr(225).chr(187).chr(136) => 'I', chr(225).chr(187).chr(137) => 'i',
1262 chr(225).chr(187).chr(142) => 'O', chr(225).chr(187).chr(143) => 'o',
1263 chr(225).chr(187).chr(148) => 'O', chr(225).chr(187).chr(149) => 'o',
1264 chr(225).chr(187).chr(158) => 'O', chr(225).chr(187).chr(159) => 'o',
1265 chr(225).chr(187).chr(166) => 'U', chr(225).chr(187).chr(167) => 'u',
1266 chr(225).chr(187).chr(172) => 'U', chr(225).chr(187).chr(173) => 'u',
1267 chr(225).chr(187).chr(182) => 'Y', chr(225).chr(187).chr(183) => 'y',
1269 chr(225).chr(186).chr(170) => 'A', chr(225).chr(186).chr(171) => 'a',
1270 chr(225).chr(186).chr(180) => 'A', chr(225).chr(186).chr(181) => 'a',
1271 chr(225).chr(186).chr(188) => 'E', chr(225).chr(186).chr(189) => 'e',
1272 chr(225).chr(187).chr(132) => 'E', chr(225).chr(187).chr(133) => 'e',
1273 chr(225).chr(187).chr(150) => 'O', chr(225).chr(187).chr(151) => 'o',
1274 chr(225).chr(187).chr(160) => 'O', chr(225).chr(187).chr(161) => 'o',
1275 chr(225).chr(187).chr(174) => 'U', chr(225).chr(187).chr(175) => 'u',
1276 chr(225).chr(187).chr(184) => 'Y', chr(225).chr(187).chr(185) => 'y',
1278 chr(225).chr(186).chr(164) => 'A', chr(225).chr(186).chr(165) => 'a',
1279 chr(225).chr(186).chr(174) => 'A', chr(225).chr(186).chr(175) => 'a',
1280 chr(225).chr(186).chr(190) => 'E', chr(225).chr(186).chr(191) => 'e',
1281 chr(225).chr(187).chr(144) => 'O', chr(225).chr(187).chr(145) => 'o',
1282 chr(225).chr(187).chr(154) => 'O', chr(225).chr(187).chr(155) => 'o',
1283 chr(225).chr(187).chr(168) => 'U', chr(225).chr(187).chr(169) => 'u',
1285 chr(225).chr(186).chr(160) => 'A', chr(225).chr(186).chr(161) => 'a',
1286 chr(225).chr(186).chr(172) => 'A', chr(225).chr(186).chr(173) => 'a',
1287 chr(225).chr(186).chr(182) => 'A', chr(225).chr(186).chr(183) => 'a',
1288 chr(225).chr(186).chr(184) => 'E', chr(225).chr(186).chr(185) => 'e',
1289 chr(225).chr(187).chr(134) => 'E', chr(225).chr(187).chr(135) => 'e',
1290 chr(225).chr(187).chr(138) => 'I', chr(225).chr(187).chr(139) => 'i',
1291 chr(225).chr(187).chr(140) => 'O', chr(225).chr(187).chr(141) => 'o',
1292 chr(225).chr(187).chr(152) => 'O', chr(225).chr(187).chr(153) => 'o',
1293 chr(225).chr(187).chr(162) => 'O', chr(225).chr(187).chr(163) => 'o',
1294 chr(225).chr(187).chr(164) => 'U', chr(225).chr(187).chr(165) => 'u',
1295 chr(225).chr(187).chr(176) => 'U', chr(225).chr(187).chr(177) => 'u',
1296 chr(225).chr(187).chr(180) => 'Y', chr(225).chr(187).chr(181) => 'y',
1297 // Vowels with diacritic (Chinese, Hanyu Pinyin)
1298 chr(201).chr(145) => 'a',
1300 chr(199).chr(149) => 'U', chr(199).chr(150) => 'u',
1302 chr(199).chr(151) => 'U', chr(199).chr(152) => 'u',
1304 chr(199).chr(141) => 'A', chr(199).chr(142) => 'a',
1305 chr(199).chr(143) => 'I', chr(199).chr(144) => 'i',
1306 chr(199).chr(145) => 'O', chr(199).chr(146) => 'o',
1307 chr(199).chr(147) => 'U', chr(199).chr(148) => 'u',
1308 chr(199).chr(153) => 'U', chr(199).chr(154) => 'u',
1310 chr(199).chr(155) => 'U', chr(199).chr(156) => 'u',
1313 // Used for locale-specific rules
1314 $locale = get_locale();
1316 if ( 'de_DE' == $locale || 'de_DE_formal' == $locale ) {
1317 $chars[ chr(195).chr(132) ] = 'Ae';
1318 $chars[ chr(195).chr(164) ] = 'ae';
1319 $chars[ chr(195).chr(150) ] = 'Oe';
1320 $chars[ chr(195).chr(182) ] = 'oe';
1321 $chars[ chr(195).chr(156) ] = 'Ue';
1322 $chars[ chr(195).chr(188) ] = 'ue';
1323 $chars[ chr(195).chr(159) ] = 'ss';
1324 } elseif ( 'da_DK' === $locale ) {
1325 $chars[ chr(195).chr(134) ] = 'Ae';
1326 $chars[ chr(195).chr(166) ] = 'ae';
1327 $chars[ chr(195).chr(152) ] = 'Oe';
1328 $chars[ chr(195).chr(184) ] = 'oe';
1329 $chars[ chr(195).chr(133) ] = 'Aa';
1330 $chars[ chr(195).chr(165) ] = 'aa';
1333 $string = strtr($string, $chars);
1336 // Assume ISO-8859-1 if not UTF-8
1337 $chars['in'] = chr(128).chr(131).chr(138).chr(142).chr(154).chr(158)
1338 .chr(159).chr(162).chr(165).chr(181).chr(192).chr(193).chr(194)
1339 .chr(195).chr(196).chr(197).chr(199).chr(200).chr(201).chr(202)
1340 .chr(203).chr(204).chr(205).chr(206).chr(207).chr(209).chr(210)
1341 .chr(211).chr(212).chr(213).chr(214).chr(216).chr(217).chr(218)
1342 .chr(219).chr(220).chr(221).chr(224).chr(225).chr(226).chr(227)
1343 .chr(228).chr(229).chr(231).chr(232).chr(233).chr(234).chr(235)
1344 .chr(236).chr(237).chr(238).chr(239).chr(241).chr(242).chr(243)
1345 .chr(244).chr(245).chr(246).chr(248).chr(249).chr(250).chr(251)
1346 .chr(252).chr(253).chr(255);
1348 $chars['out'] = "EfSZszYcYuAAAAAACEEEEIIIINOOOOOOUUUUYaaaaaaceeeeiiiinoooooouuuuyy";
1350 $string = strtr($string, $chars['in'], $chars['out']);
1351 $double_chars = array();
1352 $double_chars['in'] = array(chr(140), chr(156), chr(198), chr(208), chr(222), chr(223), chr(230), chr(240), chr(254));
1353 $double_chars['out'] = array('OE', 'oe', 'AE', 'DH', 'TH', 'ss', 'ae', 'dh', 'th');
1354 $string = str_replace($double_chars['in'], $double_chars['out'], $string);
1361 * Sanitizes a filename, replacing whitespace with dashes.
1363 * Removes special characters that are illegal in filenames on certain
1364 * operating systems and special characters requiring special escaping
1365 * to manipulate at the command line. Replaces spaces and consecutive
1366 * dashes with a single dash. Trims period, dash and underscore from beginning
1367 * and end of filename. It is not guaranteed that this function will return a
1368 * filename that is allowed to be uploaded.
1372 * @param string $filename The filename to be sanitized
1373 * @return string The sanitized filename
1375 function sanitize_file_name( $filename ) {
1376 $filename_raw = $filename;
1377 $special_chars = array("?", "[", "]", "/", "\\", "=", "<", ">", ":", ";", ",", "'", "\"", "&", "$", "#", "*", "(", ")", "|", "~", "`", "!", "{", "}", "%", "+", chr(0));
1379 * Filter the list of characters to remove from a filename.
1383 * @param array $special_chars Characters to remove.
1384 * @param string $filename_raw Filename as it was passed into sanitize_file_name().
1386 $special_chars = apply_filters( 'sanitize_file_name_chars', $special_chars, $filename_raw );
1387 $filename = preg_replace( "#\x{00a0}#siu", ' ', $filename );
1388 $filename = str_replace( $special_chars, '', $filename );
1389 $filename = str_replace( array( '%20', '+' ), '-', $filename );
1390 $filename = preg_replace( '/[\r\n\t -]+/', '-', $filename );
1391 $filename = trim( $filename, '.-_' );
1393 if ( false === strpos( $filename, '.' ) ) {
1394 $mime_types = wp_get_mime_types();
1395 $filetype = wp_check_filetype( 'test.' . $filename, $mime_types );
1396 if ( $filetype['ext'] === $filename ) {
1397 $filename = 'unnamed-file.' . $filetype['ext'];
1401 // Split the filename into a base and extension[s]
1402 $parts = explode('.', $filename);
1404 // Return if only one extension
1405 if ( count( $parts ) <= 2 ) {
1407 * Filter a sanitized filename string.
1411 * @param string $filename Sanitized filename.
1412 * @param string $filename_raw The filename prior to sanitization.
1414 return apply_filters( 'sanitize_file_name', $filename, $filename_raw );
1417 // Process multiple extensions
1418 $filename = array_shift($parts);
1419 $extension = array_pop($parts);
1420 $mimes = get_allowed_mime_types();
1423 * Loop over any intermediate extensions. Postfix them with a trailing underscore
1424 * if they are a 2 - 5 character long alpha string not in the extension whitelist.
1426 foreach ( (array) $parts as $part) {
1427 $filename .= '.' . $part;
1429 if ( preg_match("/^[a-zA-Z]{2,5}\d?$/", $part) ) {
1431 foreach ( $mimes as $ext_preg => $mime_match ) {
1432 $ext_preg = '!^(' . $ext_preg . ')$!i';
1433 if ( preg_match( $ext_preg, $part ) ) {
1442 $filename .= '.' . $extension;
1443 /** This filter is documented in wp-includes/formatting.php */
1444 return apply_filters('sanitize_file_name', $filename, $filename_raw);
1448 * Sanitizes a username, stripping out unsafe characters.
1450 * Removes tags, octets, entities, and if strict is enabled, will only keep
1451 * alphanumeric, _, space, ., -, @. After sanitizing, it passes the username,
1452 * raw username (the username in the parameter), and the value of $strict as
1453 * parameters for the 'sanitize_user' filter.
1457 * @param string $username The username to be sanitized.
1458 * @param bool $strict If set limits $username to specific characters. Default false.
1459 * @return string The sanitized username, after passing through filters.
1461 function sanitize_user( $username, $strict = false ) {
1462 $raw_username = $username;
1463 $username = wp_strip_all_tags( $username );
1464 $username = remove_accents( $username );
1466 $username = preg_replace( '|%([a-fA-F0-9][a-fA-F0-9])|', '', $username );
1467 $username = preg_replace( '/&.+?;/', '', $username ); // Kill entities
1469 // If strict, reduce to ASCII for max portability.
1471 $username = preg_replace( '|[^a-z0-9 _.\-@]|i', '', $username );
1473 $username = trim( $username );
1474 // Consolidate contiguous whitespace
1475 $username = preg_replace( '|\s+|', ' ', $username );
1478 * Filter a sanitized username string.
1482 * @param string $username Sanitized username.
1483 * @param string $raw_username The username prior to sanitization.
1484 * @param bool $strict Whether to limit the sanitization to specific characters. Default false.
1486 return apply_filters( 'sanitize_user', $username, $raw_username, $strict );
1490 * Sanitizes a string key.
1492 * Keys are used as internal identifiers. Lowercase alphanumeric characters, dashes and underscores are allowed.
1496 * @param string $key String key
1497 * @return string Sanitized key
1499 function sanitize_key( $key ) {
1501 $key = strtolower( $key );
1502 $key = preg_replace( '/[^a-z0-9_\-]/', '', $key );
1505 * Filter a sanitized key string.
1509 * @param string $key Sanitized key.
1510 * @param string $raw_key The key prior to sanitization.
1512 return apply_filters( 'sanitize_key', $key, $raw_key );
1516 * Sanitizes a title, or returns a fallback title.
1518 * Specifically, HTML and PHP tags are stripped. Further actions can be added
1519 * via the plugin API. If $title is empty and $fallback_title is set, the latter
1524 * @param string $title The string to be sanitized.
1525 * @param string $fallback_title Optional. A title to use if $title is empty.
1526 * @param string $context Optional. The operation for which the string is sanitized
1527 * @return string The sanitized string.
1529 function sanitize_title( $title, $fallback_title = '', $context = 'save' ) {
1530 $raw_title = $title;
1532 if ( 'save' == $context )
1533 $title = remove_accents($title);
1536 * Filter a sanitized title string.
1540 * @param string $title Sanitized title.
1541 * @param string $raw_title The title prior to sanitization.
1542 * @param string $context The context for which the title is being sanitized.
1544 $title = apply_filters( 'sanitize_title', $title, $raw_title, $context );
1546 if ( '' === $title || false === $title )
1547 $title = $fallback_title;
1553 * Sanitizes a title with the 'query' context.
1555 * Used for querying the database for a value from URL.
1559 * @param string $title The string to be sanitized.
1560 * @return string The sanitized string.
1562 function sanitize_title_for_query( $title ) {
1563 return sanitize_title( $title, '', 'query' );
1567 * Sanitizes a title, replacing whitespace and a few other characters with dashes.
1569 * Limits the output to alphanumeric characters, underscore (_) and dash (-).
1570 * Whitespace becomes a dash.
1574 * @param string $title The title to be sanitized.
1575 * @param string $raw_title Optional. Not used.
1576 * @param string $context Optional. The operation for which the string is sanitized.
1577 * @return string The sanitized title.
1579 function sanitize_title_with_dashes( $title, $raw_title = '', $context = 'display' ) {
1580 $title = strip_tags($title);
1581 // Preserve escaped octets.
1582 $title = preg_replace('|%([a-fA-F0-9][a-fA-F0-9])|', '---$1---', $title);
1583 // Remove percent signs that are not part of an octet.
1584 $title = str_replace('%', '', $title);
1586 $title = preg_replace('|---([a-fA-F0-9][a-fA-F0-9])---|', '%$1', $title);
1588 if (seems_utf8($title)) {
1589 if (function_exists('mb_strtolower')) {
1590 $title = mb_strtolower($title, 'UTF-8');
1592 $title = utf8_uri_encode($title, 200);
1595 $title = strtolower($title);
1597 if ( 'save' == $context ) {
1598 // Convert nbsp, ndash and mdash to hyphens
1599 $title = str_replace( array( '%c2%a0', '%e2%80%93', '%e2%80%94' ), '-', $title );
1600 // Convert nbsp, ndash and mdash HTML entities to hyphens
1601 $title = str_replace( array( ' ', ' ', '–', '–', '—', '—' ), '-', $title );
1603 // Strip these characters entirely
1604 $title = str_replace( array(
1608 '%c2%ab', '%c2%bb', '%e2%80%b9', '%e2%80%ba',
1610 '%e2%80%98', '%e2%80%99', '%e2%80%9c', '%e2%80%9d',
1611 '%e2%80%9a', '%e2%80%9b', '%e2%80%9e', '%e2%80%9f',
1612 // copy, reg, deg, hellip and trade
1613 '%c2%a9', '%c2%ae', '%c2%b0', '%e2%80%a6', '%e2%84%a2',
1615 '%c2%b4', '%cb%8a', '%cc%81', '%cd%81',
1616 // grave accent, macron, caron
1617 '%cc%80', '%cc%84', '%cc%8c',
1620 // Convert times to x
1621 $title = str_replace( '%c3%97', 'x', $title );
1624 $title = preg_replace('/&.+?;/', '', $title); // kill entities
1625 $title = str_replace('.', '-', $title);
1627 $title = preg_replace('/[^%a-z0-9 _-]/', '', $title);
1628 $title = preg_replace('/\s+/', '-', $title);
1629 $title = preg_replace('|-+|', '-', $title);
1630 $title = trim($title, '-');
1636 * Ensures a string is a valid SQL 'order by' clause.
1638 * Accepts one or more columns, with or without a sort order (ASC / DESC).
1639 * e.g. 'column_1', 'column_1, column_2', 'column_1 ASC, column_2 DESC' etc.
1641 * Also accepts 'RAND()'.
1645 * @param string $orderby Order by clause to be validated.
1646 * @return string|false Returns $orderby if valid, false otherwise.
1648 function sanitize_sql_orderby( $orderby ) {
1649 if ( preg_match( '/^\s*(([a-z0-9_]+|`[a-z0-9_]+`)(\s+(ASC|DESC))?\s*(,\s*(?=[a-z0-9_`])|$))+$/i', $orderby ) || preg_match( '/^\s*RAND\(\s*\)\s*$/i', $orderby ) ) {
1656 * Sanitizes an HTML classname to ensure it only contains valid characters.
1658 * Strips the string down to A-Z,a-z,0-9,_,-. If this results in an empty
1659 * string then it will return the alternative value supplied.
1661 * @todo Expand to support the full range of CDATA that a class attribute can contain.
1665 * @param string $class The classname to be sanitized
1666 * @param string $fallback Optional. The value to return if the sanitization ends up as an empty string.
1667 * Defaults to an empty string.
1668 * @return string The sanitized value
1670 function sanitize_html_class( $class, $fallback = '' ) {
1671 //Strip out any % encoded octets
1672 $sanitized = preg_replace( '|%[a-fA-F0-9][a-fA-F0-9]|', '', $class );
1674 //Limit to A-Z,a-z,0-9,_,-
1675 $sanitized = preg_replace( '/[^A-Za-z0-9_-]/', '', $sanitized );
1677 if ( '' == $sanitized && $fallback ) {
1678 return sanitize_html_class( $fallback );
1681 * Filter a sanitized HTML class string.
1685 * @param string $sanitized The sanitized HTML class.
1686 * @param string $class HTML class before sanitization.
1687 * @param string $fallback The fallback string.
1689 return apply_filters( 'sanitize_html_class', $sanitized, $class, $fallback );
1693 * Converts lone & characters into `&` (a.k.a. `&`)
1697 * @param string $content String of characters to be converted.
1698 * @param string $deprecated Not used.
1699 * @return string Converted string.
1701 function convert_chars( $content, $deprecated = '' ) {
1702 if ( ! empty( $deprecated ) ) {
1703 _deprecated_argument( __FUNCTION__, '0.71' );
1706 if ( strpos( $content, '&' ) !== false ) {
1707 $content = preg_replace( '/&([^#])(?![a-z1-4]{1,8};)/i', '&$1', $content );
1714 * Converts invalid Unicode references range to valid range.
1718 * @param string $content String with entities that need converting.
1719 * @return string Converted string.
1721 function convert_invalid_entities( $content ) {
1722 $wp_htmltranswinuni = array(
1723 '€' => '€', // the Euro sign
1725 '‚' => '‚', // these are Windows CP1252 specific characters
1726 'ƒ' => 'ƒ', // they would look weird on non-Windows browsers
1727 '„' => '„',
1728 '…' => '…',
1729 '†' => '†',
1730 '‡' => '‡',
1731 'ˆ' => 'ˆ',
1732 '‰' => '‰',
1733 'Š' => 'Š',
1734 '‹' => '‹',
1735 'Œ' => 'Œ',
1737 'Ž' => 'Ž',
1740 '‘' => '‘',
1741 '’' => '’',
1742 '“' => '“',
1743 '”' => '”',
1744 '•' => '•',
1745 '–' => '–',
1746 '—' => '—',
1747 '˜' => '˜',
1748 '™' => '™',
1749 'š' => 'š',
1750 '›' => '›',
1751 'œ' => 'œ',
1753 'ž' => 'ž',
1754 'Ÿ' => 'Ÿ'
1757 if ( strpos( $content, '' ) !== false ) {
1758 $content = strtr( $content, $wp_htmltranswinuni );
1765 * Balances tags if forced to, or if the 'use_balanceTags' option is set to true.
1769 * @param string $text Text to be balanced
1770 * @param bool $force If true, forces balancing, ignoring the value of the option. Default false.
1771 * @return string Balanced text
1773 function balanceTags( $text, $force = false ) {
1774 if ( $force || get_option('use_balanceTags') == 1 ) {
1775 return force_balance_tags( $text );
1782 * Balances tags of string using a modified stack.
1786 * @author Leonard Lin <leonard@acm.org>
1788 * @copyright November 4, 2001
1790 * @todo Make better - change loop condition to $text in 1.2
1791 * @internal Modified by Scott Reilly (coffee2code) 02 Aug 2004
1792 * 1.1 Fixed handling of append/stack pop order of end text
1793 * Added Cleaning Hooks
1796 * @param string $text Text to be balanced.
1797 * @return string Balanced text.
1799 function force_balance_tags( $text ) {
1800 $tagstack = array();
1804 // Known single-entity/self-closing tags
1805 $single_tags = array( 'area', 'base', 'basefont', 'br', 'col', 'command', 'embed', 'frame', 'hr', 'img', 'input', 'isindex', 'link', 'meta', 'param', 'source' );
1806 // Tags that can be immediately nested within themselves
1807 $nestable_tags = array( 'blockquote', 'div', 'object', 'q', 'span' );
1809 // WP bug fix for comments - in case you REALLY meant to type '< !--'
1810 $text = str_replace('< !--', '< !--', $text);
1811 // WP bug fix for LOVE <3 (and other situations with '<' before a number)
1812 $text = preg_replace('#<([0-9]{1})#', '<$1', $text);
1814 while ( preg_match("/<(\/?[\w:]*)\s*([^>]*)>/", $text, $regex) ) {
1815 $newtext .= $tagqueue;
1817 $i = strpos($text, $regex[0]);
1818 $l = strlen($regex[0]);
1820 // clear the shifter
1823 if ( isset($regex[1][0]) && '/' == $regex[1][0] ) { // End Tag
1824 $tag = strtolower(substr($regex[1],1));
1825 // if too many closing tags
1826 if ( $stacksize <= 0 ) {
1828 // or close to be safe $tag = '/' . $tag;
1830 // if stacktop value = tag close value then pop
1831 elseif ( $tagstack[$stacksize - 1] == $tag ) { // found closing tag
1832 $tag = '</' . $tag . '>'; // Close Tag
1834 array_pop( $tagstack );
1836 } else { // closing tag not at top, search for it
1837 for ( $j = $stacksize-1; $j >= 0; $j-- ) {
1838 if ( $tagstack[$j] == $tag ) {
1839 // add tag to tagqueue
1840 for ( $k = $stacksize-1; $k >= $j; $k--) {
1841 $tagqueue .= '</' . array_pop( $tagstack ) . '>';
1849 } else { // Begin Tag
1850 $tag = strtolower($regex[1]);
1854 // If it's an empty tag "< >", do nothing
1858 // ElseIf it presents itself as a self-closing tag...
1859 elseif ( substr( $regex[2], -1 ) == '/' ) {
1860 // ...but it isn't a known single-entity self-closing tag, then don't let it be treated as such and
1861 // immediately close it with a closing tag (the tag will encapsulate no text as a result)
1862 if ( ! in_array( $tag, $single_tags ) )
1863 $regex[2] = trim( substr( $regex[2], 0, -1 ) ) . "></$tag";
1865 // ElseIf it's a known single-entity tag but it doesn't close itself, do so
1866 elseif ( in_array($tag, $single_tags) ) {
1869 // Else it's not a single-entity tag
1871 // If the top of the stack is the same as the tag we want to push, close previous tag
1872 if ( $stacksize > 0 && !in_array($tag, $nestable_tags) && $tagstack[$stacksize - 1] == $tag ) {
1873 $tagqueue = '</' . array_pop( $tagstack ) . '>';
1876 $stacksize = array_push( $tagstack, $tag );
1880 $attributes = $regex[2];
1881 if ( ! empty( $attributes ) && $attributes[0] != '>' )
1882 $attributes = ' ' . $attributes;
1884 $tag = '<' . $tag . $attributes . '>';
1885 //If already queuing a close tag, then put this tag on, too
1886 if ( !empty($tagqueue) ) {
1891 $newtext .= substr($text, 0, $i) . $tag;
1892 $text = substr($text, $i + $l);
1896 $newtext .= $tagqueue;
1898 // Add Remaining text
1902 while( $x = array_pop($tagstack) )
1903 $newtext .= '</' . $x . '>'; // Add remaining tags to close
1905 // WP fix for the bug with HTML comments
1906 $newtext = str_replace("< !--","<!--",$newtext);
1907 $newtext = str_replace("< !--","< !--",$newtext);
1913 * Acts on text which is about to be edited.
1915 * The $content is run through esc_textarea(), which uses htmlspecialchars()
1916 * to convert special characters to HTML entities. If $richedit is set to true,
1917 * it is simply a holder for the 'format_to_edit' filter.
1920 * @since 4.4.0 The `$richedit` parameter was renamed to `$rich_text` for clarity.
1922 * @param string $content The text about to be edited.
1923 * @param bool $rich_text Optional. Whether `$content` should be considered rich text,
1924 * in which case it would not be passed through esc_textarea().
1926 * @return string The text after the filter (and possibly htmlspecialchars()) has been run.
1928 function format_to_edit( $content, $rich_text = false ) {
1930 * Filter the text to be formatted for editing.
1934 * @param string $content The text, prior to formatting for editing.
1936 $content = apply_filters( 'format_to_edit', $content );
1938 $content = esc_textarea( $content );
1943 * Add leading zeros when necessary.
1945 * If you set the threshold to '4' and the number is '10', then you will get
1946 * back '0010'. If you set the threshold to '4' and the number is '5000', then you
1947 * will get back '5000'.
1949 * Uses sprintf to append the amount of zeros based on the $threshold parameter
1950 * and the size of the number. If the number is large enough, then no zeros will
1955 * @param int $number Number to append zeros to if not greater than threshold.
1956 * @param int $threshold Digit places number needs to be to not have zeros added.
1957 * @return string Adds leading zeros to number if needed.
1959 function zeroise( $number, $threshold ) {
1960 return sprintf( '%0' . $threshold . 's', $number );
1964 * Adds backslashes before letters and before a number at the start of a string.
1968 * @param string $string Value to which backslashes will be added.
1969 * @return string String with backslashes inserted.
1971 function backslashit( $string ) {
1972 if ( isset( $string[0] ) && $string[0] >= '0' && $string[0] <= '9' )
1973 $string = '\\\\' . $string;
1974 return addcslashes( $string, 'A..Za..z' );
1978 * Appends a trailing slash.
1980 * Will remove trailing forward and backslashes if it exists already before adding
1981 * a trailing forward slash. This prevents double slashing a string or path.
1983 * The primary use of this is for paths and thus should be used for paths. It is
1984 * not restricted to paths and offers no specific path support.
1988 * @param string $string What to add the trailing slash to.
1989 * @return string String with trailing slash added.
1991 function trailingslashit( $string ) {
1992 return untrailingslashit( $string ) . '/';
1996 * Removes trailing forward slashes and backslashes if they exist.
1998 * The primary use of this is for paths and thus should be used for paths. It is
1999 * not restricted to paths and offers no specific path support.
2003 * @param string $string What to remove the trailing slashes from.
2004 * @return string String without the trailing slashes.
2006 function untrailingslashit( $string ) {
2007 return rtrim( $string, '/\\' );
2011 * Adds slashes to escape strings.
2013 * Slashes will first be removed if magic_quotes_gpc is set, see {@link
2014 * http://www.php.net/magic_quotes} for more details.
2018 * @param string $gpc The string returned from HTTP request data.
2019 * @return string Returns a string escaped with slashes.
2021 function addslashes_gpc($gpc) {
2022 if ( get_magic_quotes_gpc() )
2023 $gpc = stripslashes($gpc);
2025 return wp_slash($gpc);
2029 * Navigates through an array, object, or scalar, and removes slashes from the values.
2033 * @param mixed $value The value to be stripped.
2034 * @return mixed Stripped value.
2036 function stripslashes_deep( $value ) {
2037 return map_deep( $value, 'stripslashes_from_strings_only' );
2041 * Callback function for `stripslashes_deep()` which strips slashes from strings.
2045 * @param mixed $value The array or string to be stripped.
2046 * @return mixed $value The stripped value.
2048 function stripslashes_from_strings_only( $value ) {
2049 return is_string( $value ) ? stripslashes( $value ) : $value;
2053 * Navigates through an array, object, or scalar, and encodes the values to be used in a URL.
2057 * @param mixed $value The array or string to be encoded.
2058 * @return mixed $value The encoded value.
2060 function urlencode_deep( $value ) {
2061 return map_deep( $value, 'urlencode' );
2065 * Navigates through an array, object, or scalar, and raw-encodes the values to be used in a URL.
2069 * @param mixed $value The array or string to be encoded.
2070 * @return mixed $value The encoded value.
2072 function rawurlencode_deep( $value ) {
2073 return map_deep( $value, 'rawurlencode' );
2077 * Navigates through an array, object, or scalar, and decodes URL-encoded values
2081 * @param mixed $value The array or string to be decoded.
2082 * @return mixed $value The decoded value.
2084 function urldecode_deep( $value ) {
2085 return map_deep( $value, 'urldecode' );
2089 * Converts email addresses characters to HTML entities to block spam bots.
2093 * @param string $email_address Email address.
2094 * @param int $hex_encoding Optional. Set to 1 to enable hex encoding.
2095 * @return string Converted email address.
2097 function antispambot( $email_address, $hex_encoding = 0 ) {
2098 $email_no_spam_address = '';
2099 for ( $i = 0, $len = strlen( $email_address ); $i < $len; $i++ ) {
2100 $j = rand( 0, 1 + $hex_encoding );
2102 $email_no_spam_address .= '&#' . ord( $email_address[$i] ) . ';';
2103 } elseif ( $j == 1 ) {
2104 $email_no_spam_address .= $email_address[$i];
2105 } elseif ( $j == 2 ) {
2106 $email_no_spam_address .= '%' . zeroise( dechex( ord( $email_address[$i] ) ), 2 );
2110 return str_replace( '@', '@', $email_no_spam_address );
2114 * Callback to convert URI match to HTML A element.
2116 * This function was backported from 2.5.0 to 2.3.2. Regex callback for {@link
2117 * make_clickable()}.
2122 * @param array $matches Single Regex Match.
2123 * @return string HTML A element with URI address.
2125 function _make_url_clickable_cb( $matches ) {
2128 if ( ')' == $matches[3] && strpos( $url, '(' ) ) {
2129 // If the trailing character is a closing parethesis, and the URL has an opening parenthesis in it, add the closing parenthesis to the URL.
2130 // Then we can let the parenthesis balancer do its thing below.
2131 $url .= $matches[3];
2134 $suffix = $matches[3];
2137 // Include parentheses in the URL only if paired
2138 while ( substr_count( $url, '(' ) < substr_count( $url, ')' ) ) {
2139 $suffix = strrchr( $url, ')' ) . $suffix;
2140 $url = substr( $url, 0, strrpos( $url, ')' ) );
2143 $url = esc_url($url);
2147 return $matches[1] . "<a href=\"$url\" rel=\"nofollow\">$url</a>" . $suffix;
2151 * Callback to convert URL match to HTML A element.
2153 * This function was backported from 2.5.0 to 2.3.2. Regex callback for {@link
2154 * make_clickable()}.
2159 * @param array $matches Single Regex Match.
2160 * @return string HTML A element with URL address.
2162 function _make_web_ftp_clickable_cb( $matches ) {
2164 $dest = $matches[2];
2165 $dest = 'http://' . $dest;
2167 // removed trailing [.,;:)] from URL
2168 if ( in_array( substr($dest, -1), array('.', ',', ';', ':', ')') ) === true ) {
2169 $ret = substr($dest, -1);
2170 $dest = substr($dest, 0, strlen($dest)-1);
2173 $dest = esc_url($dest);
2177 return $matches[1] . "<a href=\"$dest\" rel=\"nofollow\">$dest</a>$ret";
2181 * Callback to convert email address match to HTML A element.
2183 * This function was backported from 2.5.0 to 2.3.2. Regex callback for {@link
2184 * make_clickable()}.
2189 * @param array $matches Single Regex Match.
2190 * @return string HTML A element with email address.
2192 function _make_email_clickable_cb( $matches ) {
2193 $email = $matches[2] . '@' . $matches[3];
2194 return $matches[1] . "<a href=\"mailto:$email\">$email</a>";
2198 * Convert plaintext URI to HTML links.
2200 * Converts URI, www and ftp, and email addresses. Finishes by fixing links
2205 * @param string $text Content to convert URIs.
2206 * @return string Content with converted URIs.
2208 function make_clickable( $text ) {
2210 $textarr = preg_split( '/(<[^<>]+>)/', $text, -1, PREG_SPLIT_DELIM_CAPTURE ); // split out HTML tags
2211 $nested_code_pre = 0; // Keep track of how many levels link is nested inside <pre> or <code>
2212 foreach ( $textarr as $piece ) {
2214 if ( preg_match( '|^<code[\s>]|i', $piece ) || preg_match( '|^<pre[\s>]|i', $piece ) || preg_match( '|^<script[\s>]|i', $piece ) || preg_match( '|^<style[\s>]|i', $piece ) )
2216 elseif ( $nested_code_pre && ( '</code>' === strtolower( $piece ) || '</pre>' === strtolower( $piece ) || '</script>' === strtolower( $piece ) || '</style>' === strtolower( $piece ) ) )
2219 if ( $nested_code_pre || empty( $piece ) || ( $piece[0] === '<' && ! preg_match( '|^<\s*[\w]{1,20}+://|', $piece ) ) ) {
2224 // Long strings might contain expensive edge cases ...
2225 if ( 10000 < strlen( $piece ) ) {
2227 foreach ( _split_str_by_whitespace( $piece, 2100 ) as $chunk ) { // 2100: Extra room for scheme and leading and trailing paretheses
2228 if ( 2101 < strlen( $chunk ) ) {
2229 $r .= $chunk; // Too big, no whitespace: bail.
2231 $r .= make_clickable( $chunk );
2235 $ret = " $piece "; // Pad with whitespace to simplify the regexes
2238 ([\\s(<.,;:!?]) # 1: Leading whitespace, or punctuation
2240 [\\w]{1,20}+:// # Scheme and hier-part prefix
2241 (?=\S{1,2000}\s) # Limit to URLs less than about 2000 characters long
2242 [\\w\\x80-\\xff#%\\~/@\\[\\]*(+=&$-]*+ # Non-punctuation URL character
2243 (?: # Unroll the Loop: Only allow puctuation URL character if followed by a non-punctuation URL character
2244 [\'.,;:!?)] # Punctuation URL character
2245 [\\w\\x80-\\xff#%\\~/@\\[\\]*(+=&$-]++ # Non-punctuation URL character
2248 (\)?) # 3: Trailing closing parenthesis (for parethesis balancing post processing)
2249 ~xS'; // The regex is a non-anchored pattern and does not have a single fixed starting character.
2250 // Tell PCRE to spend more time optimizing since, when used on a page load, it will probably be used several times.
2252 $ret = preg_replace_callback( $url_clickable, '_make_url_clickable_cb', $ret );
2254 $ret = preg_replace_callback( '#([\s>])((www|ftp)\.[\w\\x80-\\xff\#$%&~/.\-;:=,?@\[\]+]+)#is', '_make_web_ftp_clickable_cb', $ret );
2255 $ret = preg_replace_callback( '#([\s>])([.0-9a-z_+-]+)@(([0-9a-z-]+\.)+[0-9a-z]{2,})#i', '_make_email_clickable_cb', $ret );
2257 $ret = substr( $ret, 1, -1 ); // Remove our whitespace padding.
2262 // Cleanup of accidental links within links
2263 return preg_replace( '#(<a([ \r\n\t]+[^>]+?>|>))<a [^>]+?>([^>]+?)</a></a>#i', "$1$3</a>", $r );
2267 * Breaks a string into chunks by splitting at whitespace characters.
2268 * The length of each returned chunk is as close to the specified length goal as possible,
2269 * with the caveat that each chunk includes its trailing delimiter.
2270 * Chunks longer than the goal are guaranteed to not have any inner whitespace.
2272 * Joining the returned chunks with empty delimiters reconstructs the input string losslessly.
2274 * Input string must have no null characters (or eventual transformations on output chunks must not care about null characters)
2276 * _split_str_by_whitespace( "1234 67890 1234 67890a cd 1234 890 123456789 1234567890a 45678 1 3 5 7 90 ", 10 ) ==
2278 * 0 => '1234 67890 ', // 11 characters: Perfect split
2279 * 1 => '1234 ', // 5 characters: '1234 67890a' was too long
2280 * 2 => '67890a cd ', // 10 characters: '67890a cd 1234' was too long
2281 * 3 => '1234 890 ', // 11 characters: Perfect split
2282 * 4 => '123456789 ', // 10 characters: '123456789 1234567890a' was too long
2283 * 5 => '1234567890a ', // 12 characters: Too long, but no inner whitespace on which to split
2284 * 6 => ' 45678 ', // 11 characters: Perfect split
2285 * 7 => '1 3 5 7 90 ', // 11 characters: End of $string
2291 * @param string $string The string to split.
2292 * @param int $goal The desired chunk length.
2293 * @return array Numeric array of chunks.
2295 function _split_str_by_whitespace( $string, $goal ) {
2298 $string_nullspace = strtr( $string, "\r\n\t\v\f ", "\000\000\000\000\000\000" );
2300 while ( $goal < strlen( $string_nullspace ) ) {
2301 $pos = strrpos( substr( $string_nullspace, 0, $goal + 1 ), "\000" );
2303 if ( false === $pos ) {
2304 $pos = strpos( $string_nullspace, "\000", $goal + 1 );
2305 if ( false === $pos ) {
2310 $chunks[] = substr( $string, 0, $pos + 1 );
2311 $string = substr( $string, $pos + 1 );
2312 $string_nullspace = substr( $string_nullspace, $pos + 1 );
2316 $chunks[] = $string;
2323 * Adds rel nofollow string to all HTML A elements in content.
2327 * @param string $text Content that may contain HTML A elements.
2328 * @return string Converted content.
2330 function wp_rel_nofollow( $text ) {
2331 // This is a pre save filter, so text is already escaped.
2332 $text = stripslashes($text);
2333 $text = preg_replace_callback('|<a (.+?)>|i', 'wp_rel_nofollow_callback', $text);
2334 return wp_slash( $text );
2338 * Callback to add rel=nofollow string to HTML A element.
2340 * Will remove already existing rel="nofollow" and rel='nofollow' from the
2341 * string to prevent from invalidating (X)HTML.
2345 * @param array $matches Single Match
2346 * @return string HTML A Element with rel nofollow.
2348 function wp_rel_nofollow_callback( $matches ) {
2349 $text = $matches[1];
2350 $atts = shortcode_parse_atts( $matches[1] );
2353 if ( preg_match( '%href=["\'](' . preg_quote( set_url_scheme( home_url(), 'http' ) ) . ')%i', $text ) ||
2354 preg_match( '%href=["\'](' . preg_quote( set_url_scheme( home_url(), 'https' ) ) . ')%i', $text )
2359 if ( ! empty( $atts['rel'] ) ) {
2360 $parts = array_map( 'trim', explode( ' ', $atts['rel'] ) );
2361 if ( false === array_search( 'nofollow', $parts ) ) {
2362 $parts[] = 'nofollow';
2364 $rel = implode( ' ', $parts );
2365 unset( $atts['rel'] );
2368 foreach ( $atts as $name => $value ) {
2369 $html .= "{$name}=\"$value\" ";
2371 $text = trim( $html );
2373 return "<a $text rel=\"$rel\">";
2377 * Convert one smiley code to the icon graphic file equivalent.
2379 * Callback handler for {@link convert_smilies()}.
2380 * Looks up one smiley code in the $wpsmiliestrans global array and returns an
2381 * `<img>` string for that smiley.
2385 * @global array $wpsmiliestrans
2387 * @param array $matches Single match. Smiley code to convert to image.
2388 * @return string Image string for smiley.
2390 function translate_smiley( $matches ) {
2391 global $wpsmiliestrans;
2393 if ( count( $matches ) == 0 )
2396 $smiley = trim( reset( $matches ) );
2397 $img = $wpsmiliestrans[ $smiley ];
2400 $ext = preg_match( '/\.([^.]+)$/', $img, $matches ) ? strtolower( $matches[1] ) : false;
2401 $image_exts = array( 'jpg', 'jpeg', 'jpe', 'gif', 'png' );
2403 // Don't convert smilies that aren't images - they're probably emoji.
2404 if ( ! in_array( $ext, $image_exts ) ) {
2409 * Filter the Smiley image URL before it's used in the image element.
2413 * @param string $smiley_url URL for the smiley image.
2414 * @param string $img Filename for the smiley image.
2415 * @param string $site_url Site URL, as returned by site_url().
2417 $src_url = apply_filters( 'smilies_src', includes_url( "images/smilies/$img" ), $img, site_url() );
2419 return sprintf( '<img src="%s" alt="%s" class="wp-smiley" style="height: 1em; max-height: 1em;" />', esc_url( $src_url ), esc_attr( $smiley ) );
2423 * Convert text equivalent of smilies to images.
2425 * Will only convert smilies if the option 'use_smilies' is true and the global
2426 * used in the function isn't empty.
2430 * @global string|array $wp_smiliessearch
2432 * @param string $text Content to convert smilies from text.
2433 * @return string Converted content with text smilies replaced with images.
2435 function convert_smilies( $text ) {
2436 global $wp_smiliessearch;
2438 if ( get_option( 'use_smilies' ) && ! empty( $wp_smiliessearch ) ) {
2439 // HTML loop taken from texturize function, could possible be consolidated
2440 $textarr = preg_split( '/(<.*>)/U', $text, -1, PREG_SPLIT_DELIM_CAPTURE ); // capture the tags as well as in between
2441 $stop = count( $textarr );// loop stuff
2443 // Ignore proessing of specific tags
2444 $tags_to_ignore = 'code|pre|style|script|textarea';
2445 $ignore_block_element = '';
2447 for ( $i = 0; $i < $stop; $i++ ) {
2448 $content = $textarr[$i];
2450 // If we're in an ignore block, wait until we find its closing tag
2451 if ( '' == $ignore_block_element && preg_match( '/^<(' . $tags_to_ignore . ')>/', $content, $matches ) ) {
2452 $ignore_block_element = $matches[1];
2455 // If it's not a tag and not in ignore block
2456 if ( '' == $ignore_block_element && strlen( $content ) > 0 && '<' != $content[0] ) {
2457 $content = preg_replace_callback( $wp_smiliessearch, 'translate_smiley', $content );
2460 // did we exit ignore block
2461 if ( '' != $ignore_block_element && '</' . $ignore_block_element . '>' == $content ) {
2462 $ignore_block_element = '';
2465 $output .= $content;
2468 // return default text.
2475 * Verifies that an email is valid.
2477 * Does not grok i18n domains. Not RFC compliant.
2481 * @param string $email Email address to verify.
2482 * @param bool $deprecated Deprecated.
2483 * @return string|bool Either false or the valid email address.
2485 function is_email( $email, $deprecated = false ) {
2486 if ( ! empty( $deprecated ) )
2487 _deprecated_argument( __FUNCTION__, '3.0' );
2489 // Test for the minimum length the email can be
2490 if ( strlen( $email ) < 3 ) {
2492 * Filter whether an email address is valid.
2494 * This filter is evaluated under several different contexts, such as 'email_too_short',
2495 * 'email_no_at', 'local_invalid_chars', 'domain_period_sequence', 'domain_period_limits',
2496 * 'domain_no_periods', 'sub_hyphen_limits', 'sub_invalid_chars', or no specific context.
2500 * @param bool $is_email Whether the email address has passed the is_email() checks. Default false.
2501 * @param string $email The email address being checked.
2502 * @param string $context Context under which the email was tested.
2504 return apply_filters( 'is_email', false, $email, 'email_too_short' );
2507 // Test for an @ character after the first position
2508 if ( strpos( $email, '@', 1 ) === false ) {
2509 /** This filter is documented in wp-includes/formatting.php */
2510 return apply_filters( 'is_email', false, $email, 'email_no_at' );
2513 // Split out the local and domain parts
2514 list( $local, $domain ) = explode( '@', $email, 2 );
2517 // Test for invalid characters
2518 if ( !preg_match( '/^[a-zA-Z0-9!#$%&\'*+\/=?^_`{|}~\.-]+$/', $local ) ) {
2519 /** This filter is documented in wp-includes/formatting.php */
2520 return apply_filters( 'is_email', false, $email, 'local_invalid_chars' );
2524 // Test for sequences of periods
2525 if ( preg_match( '/\.{2,}/', $domain ) ) {
2526 /** This filter is documented in wp-includes/formatting.php */
2527 return apply_filters( 'is_email', false, $email, 'domain_period_sequence' );
2530 // Test for leading and trailing periods and whitespace
2531 if ( trim( $domain, " \t\n\r\0\x0B." ) !== $domain ) {
2532 /** This filter is documented in wp-includes/formatting.php */
2533 return apply_filters( 'is_email', false, $email, 'domain_period_limits' );
2536 // Split the domain into subs
2537 $subs = explode( '.', $domain );
2539 // Assume the domain will have at least two subs
2540 if ( 2 > count( $subs ) ) {
2541 /** This filter is documented in wp-includes/formatting.php */
2542 return apply_filters( 'is_email', false, $email, 'domain_no_periods' );
2545 // Loop through each sub
2546 foreach ( $subs as $sub ) {
2547 // Test for leading and trailing hyphens and whitespace
2548 if ( trim( $sub, " \t\n\r\0\x0B-" ) !== $sub ) {
2549 /** This filter is documented in wp-includes/formatting.php */
2550 return apply_filters( 'is_email', false, $email, 'sub_hyphen_limits' );
2553 // Test for invalid characters
2554 if ( !preg_match('/^[a-z0-9-]+$/i', $sub ) ) {
2555 /** This filter is documented in wp-includes/formatting.php */
2556 return apply_filters( 'is_email', false, $email, 'sub_invalid_chars' );
2560 // Congratulations your email made it!
2561 /** This filter is documented in wp-includes/formatting.php */
2562 return apply_filters( 'is_email', $email, $email, null );
2566 * Convert to ASCII from email subjects.
2570 * @param string $string Subject line
2571 * @return string Converted string to ASCII
2573 function wp_iso_descrambler( $string ) {
2574 /* this may only work with iso-8859-1, I'm afraid */
2575 if (!preg_match('#\=\?(.+)\?Q\?(.+)\?\=#i', $string, $matches)) {
2578 $subject = str_replace('_', ' ', $matches[2]);
2579 return preg_replace_callback( '#\=([0-9a-f]{2})#i', '_wp_iso_convert', $subject );
2584 * Helper function to convert hex encoded chars to ASCII
2589 * @param array $match The preg_replace_callback matches array
2590 * @return string Converted chars
2592 function _wp_iso_convert( $match ) {
2593 return chr( hexdec( strtolower( $match[1] ) ) );
2597 * Returns a date in the GMT equivalent.
2599 * Requires and returns a date in the Y-m-d H:i:s format. If there is a
2600 * timezone_string available, the date is assumed to be in that timezone,
2601 * otherwise it simply subtracts the value of the 'gmt_offset' option. Return
2602 * format can be overridden using the $format parameter.
2606 * @param string $string The date to be converted.
2607 * @param string $format The format string for the returned date (default is Y-m-d H:i:s)
2608 * @return string GMT version of the date provided.
2610 function get_gmt_from_date( $string, $format = 'Y-m-d H:i:s' ) {
2611 $tz = get_option( 'timezone_string' );
2613 $datetime = date_create( $string, new DateTimeZone( $tz ) );
2614 if ( ! $datetime ) {
2615 return gmdate( $format, 0 );
2617 $datetime->setTimezone( new DateTimeZone( 'UTC' ) );
2618 $string_gmt = $datetime->format( $format );
2620 if ( ! preg_match( '#([0-9]{1,4})-([0-9]{1,2})-([0-9]{1,2}) ([0-9]{1,2}):([0-9]{1,2}):([0-9]{1,2})#', $string, $matches ) ) {
2621 $datetime = strtotime( $string );
2622 if ( false === $datetime ) {
2623 return gmdate( $format, 0 );
2625 return gmdate( $format, $datetime );
2627 $string_time = gmmktime( $matches[4], $matches[5], $matches[6], $matches[2], $matches[3], $matches[1] );
2628 $string_gmt = gmdate( $format, $string_time - get_option( 'gmt_offset' ) * HOUR_IN_SECONDS );
2634 * Converts a GMT date into the correct format for the blog.
2636 * Requires and returns a date in the Y-m-d H:i:s format. If there is a
2637 * timezone_string available, the returned date is in that timezone, otherwise
2638 * it simply adds the value of gmt_offset. Return format can be overridden
2639 * using the $format parameter
2643 * @param string $string The date to be converted.
2644 * @param string $format The format string for the returned date (default is Y-m-d H:i:s)
2645 * @return string Formatted date relative to the timezone / GMT offset.
2647 function get_date_from_gmt( $string, $format = 'Y-m-d H:i:s' ) {
2648 $tz = get_option( 'timezone_string' );
2650 $datetime = date_create( $string, new DateTimeZone( 'UTC' ) );
2652 return date( $format, 0 );
2653 $datetime->setTimezone( new DateTimeZone( $tz ) );
2654 $string_localtime = $datetime->format( $format );
2656 if ( ! preg_match('#([0-9]{1,4})-([0-9]{1,2})-([0-9]{1,2}) ([0-9]{1,2}):([0-9]{1,2}):([0-9]{1,2})#', $string, $matches) )
2657 return date( $format, 0 );
2658 $string_time = gmmktime( $matches[4], $matches[5], $matches[6], $matches[2], $matches[3], $matches[1] );
2659 $string_localtime = gmdate( $format, $string_time + get_option( 'gmt_offset' ) * HOUR_IN_SECONDS );
2661 return $string_localtime;
2665 * Computes an offset in seconds from an iso8601 timezone.
2669 * @param string $timezone Either 'Z' for 0 offset or '±hhmm'.
2670 * @return int|float The offset in seconds.
2672 function iso8601_timezone_to_offset( $timezone ) {
2673 // $timezone is either 'Z' or '[+|-]hhmm'
2674 if ($timezone == 'Z') {
2677 $sign = (substr($timezone, 0, 1) == '+') ? 1 : -1;
2678 $hours = intval(substr($timezone, 1, 2));
2679 $minutes = intval(substr($timezone, 3, 4)) / 60;
2680 $offset = $sign * HOUR_IN_SECONDS * ($hours + $minutes);
2686 * Converts an iso8601 date to MySQL DateTime format used by post_date[_gmt].
2690 * @param string $date_string Date and time in ISO 8601 format {@link http://en.wikipedia.org/wiki/ISO_8601}.
2691 * @param string $timezone Optional. If set to GMT returns the time minus gmt_offset. Default is 'user'.
2692 * @return string The date and time in MySQL DateTime format - Y-m-d H:i:s.
2694 function iso8601_to_datetime( $date_string, $timezone = 'user' ) {
2695 $timezone = strtolower($timezone);
2697 if ($timezone == 'gmt') {
2699 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, $date_bits);
2701 if (!empty($date_bits[7])) { // we have a timezone, so let's compute an offset
2702 $offset = iso8601_timezone_to_offset($date_bits[7]);
2703 } else { // we don't have a timezone, so we assume user local timezone (not server's!)
2704 $offset = HOUR_IN_SECONDS * get_option('gmt_offset');
2707 $timestamp = gmmktime($date_bits[4], $date_bits[5], $date_bits[6], $date_bits[2], $date_bits[3], $date_bits[1]);
2708 $timestamp -= $offset;
2710 return gmdate('Y-m-d H:i:s', $timestamp);
2712 } elseif ($timezone == 'user') {
2713 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);
2718 * Strips out all characters that are not allowable in an email.
2722 * @param string $email Email address to filter.
2723 * @return string Filtered email address.
2725 function sanitize_email( $email ) {
2726 // Test for the minimum length the email can be
2727 if ( strlen( $email ) < 3 ) {
2729 * Filter a sanitized email address.
2731 * This filter is evaluated under several contexts, including 'email_too_short',
2732 * 'email_no_at', 'local_invalid_chars', 'domain_period_sequence', 'domain_period_limits',
2733 * 'domain_no_periods', 'domain_no_valid_subs', or no context.
2737 * @param string $email The sanitized email address.
2738 * @param string $email The email address, as provided to sanitize_email().
2739 * @param string $message A message to pass to the user.
2741 return apply_filters( 'sanitize_email', '', $email, 'email_too_short' );
2744 // Test for an @ character after the first position
2745 if ( strpos( $email, '@', 1 ) === false ) {
2746 /** This filter is documented in wp-includes/formatting.php */
2747 return apply_filters( 'sanitize_email', '', $email, 'email_no_at' );
2750 // Split out the local and domain parts
2751 list( $local, $domain ) = explode( '@', $email, 2 );
2754 // Test for invalid characters
2755 $local = preg_replace( '/[^a-zA-Z0-9!#$%&\'*+\/=?^_`{|}~\.-]/', '', $local );
2756 if ( '' === $local ) {
2757 /** This filter is documented in wp-includes/formatting.php */
2758 return apply_filters( 'sanitize_email', '', $email, 'local_invalid_chars' );
2762 // Test for sequences of periods
2763 $domain = preg_replace( '/\.{2,}/', '', $domain );
2764 if ( '' === $domain ) {
2765 /** This filter is documented in wp-includes/formatting.php */
2766 return apply_filters( 'sanitize_email', '', $email, 'domain_period_sequence' );
2769 // Test for leading and trailing periods and whitespace
2770 $domain = trim( $domain, " \t\n\r\0\x0B." );
2771 if ( '' === $domain ) {
2772 /** This filter is documented in wp-includes/formatting.php */
2773 return apply_filters( 'sanitize_email', '', $email, 'domain_period_limits' );
2776 // Split the domain into subs
2777 $subs = explode( '.', $domain );
2779 // Assume the domain will have at least two subs
2780 if ( 2 > count( $subs ) ) {
2781 /** This filter is documented in wp-includes/formatting.php */
2782 return apply_filters( 'sanitize_email', '', $email, 'domain_no_periods' );
2785 // Create an array that will contain valid subs
2786 $new_subs = array();
2788 // Loop through each sub
2789 foreach ( $subs as $sub ) {
2790 // Test for leading and trailing hyphens
2791 $sub = trim( $sub, " \t\n\r\0\x0B-" );
2793 // Test for invalid characters
2794 $sub = preg_replace( '/[^a-z0-9-]+/i', '', $sub );
2796 // If there's anything left, add it to the valid subs
2797 if ( '' !== $sub ) {
2802 // If there aren't 2 or more valid subs
2803 if ( 2 > count( $new_subs ) ) {
2804 /** This filter is documented in wp-includes/formatting.php */
2805 return apply_filters( 'sanitize_email', '', $email, 'domain_no_valid_subs' );
2808 // Join valid subs into the new domain
2809 $domain = join( '.', $new_subs );
2811 // Put the email back together
2812 $email = $local . '@' . $domain;
2814 // Congratulations your email made it!
2815 /** This filter is documented in wp-includes/formatting.php */
2816 return apply_filters( 'sanitize_email', $email, $email, null );
2820 * Determines the difference between two timestamps.
2822 * The difference is returned in a human readable format such as "1 hour",
2823 * "5 mins", "2 days".
2827 * @param int $from Unix timestamp from which the difference begins.
2828 * @param int $to Optional. Unix timestamp to end the time difference. Default becomes time() if not set.
2829 * @return string Human readable time difference.
2831 function human_time_diff( $from, $to = '' ) {
2832 if ( empty( $to ) ) {
2836 $diff = (int) abs( $to - $from );
2838 if ( $diff < HOUR_IN_SECONDS ) {
2839 $mins = round( $diff / MINUTE_IN_SECONDS );
2842 /* translators: min=minute */
2843 $since = sprintf( _n( '%s min', '%s mins', $mins ), $mins );
2844 } elseif ( $diff < DAY_IN_SECONDS && $diff >= HOUR_IN_SECONDS ) {
2845 $hours = round( $diff / HOUR_IN_SECONDS );
2848 $since = sprintf( _n( '%s hour', '%s hours', $hours ), $hours );
2849 } elseif ( $diff < WEEK_IN_SECONDS && $diff >= DAY_IN_SECONDS ) {
2850 $days = round( $diff / DAY_IN_SECONDS );
2853 $since = sprintf( _n( '%s day', '%s days', $days ), $days );
2854 } elseif ( $diff < MONTH_IN_SECONDS && $diff >= WEEK_IN_SECONDS ) {
2855 $weeks = round( $diff / WEEK_IN_SECONDS );
2858 $since = sprintf( _n( '%s week', '%s weeks', $weeks ), $weeks );
2859 } elseif ( $diff < YEAR_IN_SECONDS && $diff >= MONTH_IN_SECONDS ) {
2860 $months = round( $diff / MONTH_IN_SECONDS );
2863 $since = sprintf( _n( '%s month', '%s months', $months ), $months );
2864 } elseif ( $diff >= YEAR_IN_SECONDS ) {
2865 $years = round( $diff / YEAR_IN_SECONDS );
2868 $since = sprintf( _n( '%s year', '%s years', $years ), $years );
2872 * Filter the human readable difference between two timestamps.
2876 * @param string $since The difference in human readable text.
2877 * @param int $diff The difference in seconds.
2878 * @param int $from Unix timestamp from which the difference begins.
2879 * @param int $to Unix timestamp to end the time difference.
2881 return apply_filters( 'human_time_diff', $since, $diff, $from, $to );
2885 * Generates an excerpt from the content, if needed.
2887 * The excerpt word amount will be 55 words and if the amount is greater than
2888 * that, then the string ' […]' will be appended to the excerpt. If the string
2889 * is less than 55 words, then the content will be returned as is.
2891 * The 55 word limit can be modified by plugins/themes using the excerpt_length filter
2892 * The ' […]' string can be modified by plugins/themes using the excerpt_more filter
2896 * @param string $text Optional. The excerpt. If set to empty, an excerpt is generated.
2897 * @return string The excerpt.
2899 function wp_trim_excerpt( $text = '' ) {
2900 $raw_excerpt = $text;
2901 if ( '' == $text ) {
2902 $text = get_the_content('');
2904 $text = strip_shortcodes( $text );
2906 /** This filter is documented in wp-includes/post-template.php */
2907 $text = apply_filters( 'the_content', $text );
2908 $text = str_replace(']]>', ']]>', $text);
2911 * Filter the number of words in an excerpt.
2915 * @param int $number The number of words. Default 55.
2917 $excerpt_length = apply_filters( 'excerpt_length', 55 );
2919 * Filter the string in the "more" link displayed after a trimmed excerpt.
2923 * @param string $more_string The string shown within the more link.
2925 $excerpt_more = apply_filters( 'excerpt_more', ' ' . '[…]' );
2926 $text = wp_trim_words( $text, $excerpt_length, $excerpt_more );
2929 * Filter the trimmed excerpt string.
2933 * @param string $text The trimmed text.
2934 * @param string $raw_excerpt The text prior to trimming.
2936 return apply_filters( 'wp_trim_excerpt', $text, $raw_excerpt );
2940 * Trims text to a certain number of words.
2942 * This function is localized. For languages that count 'words' by the individual
2943 * character (such as East Asian languages), the $num_words argument will apply
2944 * to the number of individual characters.
2948 * @param string $text Text to trim.
2949 * @param int $num_words Number of words. Default 55.
2950 * @param string $more Optional. What to append if $text needs to be trimmed. Default '…'.
2951 * @return string Trimmed text.
2953 function wp_trim_words( $text, $num_words = 55, $more = null ) {
2954 if ( null === $more ) {
2955 $more = __( '…' );
2958 $original_text = $text;
2959 $text = wp_strip_all_tags( $text );
2962 * translators: If your word count is based on single characters (e.g. East Asian characters),
2963 * enter 'characters_excluding_spaces' or 'characters_including_spaces'. Otherwise, enter 'words'.
2964 * Do not translate into your own language.
2966 if ( strpos( _x( 'words', 'Word count type. Do not translate!' ), 'characters' ) === 0 && preg_match( '/^utf\-?8$/i', get_option( 'blog_charset' ) ) ) {
2967 $text = trim( preg_replace( "/[\n\r\t ]+/", ' ', $text ), ' ' );
2968 preg_match_all( '/./u', $text, $words_array );
2969 $words_array = array_slice( $words_array[0], 0, $num_words + 1 );
2972 $words_array = preg_split( "/[\n\r\t ]+/", $text, $num_words + 1, PREG_SPLIT_NO_EMPTY );
2976 if ( count( $words_array ) > $num_words ) {
2977 array_pop( $words_array );
2978 $text = implode( $sep, $words_array );
2979 $text = $text . $more;
2981 $text = implode( $sep, $words_array );
2985 * Filter the text content after words have been trimmed.
2989 * @param string $text The trimmed text.
2990 * @param int $num_words The number of words to trim the text to. Default 5.
2991 * @param string $more An optional string to append to the end of the trimmed text, e.g. ….
2992 * @param string $original_text The text before it was trimmed.
2994 return apply_filters( 'wp_trim_words', $text, $num_words, $more, $original_text );
2998 * Converts named entities into numbered entities.
3002 * @param string $text The text within which entities will be converted.
3003 * @return string Text with converted entities.
3005 function ent2ncr( $text ) {
3008 * Filter text before named entities are converted into numbered entities.
3010 * A non-null string must be returned for the filter to be evaluated.
3014 * @param null $converted_text The text to be converted. Default null.
3015 * @param string $text The text prior to entity conversion.
3017 $filtered = apply_filters( 'pre_ent2ncr', null, $text );
3018 if ( null !== $filtered )
3022 '"' => '"',
3027 ' ' => ' ',
3028 '¡' => '¡',
3029 '¢' => '¢',
3030 '£' => '£',
3031 '¤' => '¤',
3032 '¥' => '¥',
3033 '¦' => '¦',
3034 '&brkbar;' => '¦',
3035 '§' => '§',
3036 '¨' => '¨',
3037 '¨' => '¨',
3038 '©' => '©',
3039 'ª' => 'ª',
3040 '«' => '«',
3041 '¬' => '¬',
3042 '­' => '­',
3043 '®' => '®',
3044 '¯' => '¯',
3045 '&hibar;' => '¯',
3046 '°' => '°',
3047 '±' => '±',
3048 '²' => '²',
3049 '³' => '³',
3050 '´' => '´',
3051 'µ' => 'µ',
3052 '¶' => '¶',
3053 '·' => '·',
3054 '¸' => '¸',
3055 '¹' => '¹',
3056 'º' => 'º',
3057 '»' => '»',
3058 '¼' => '¼',
3059 '½' => '½',
3060 '¾' => '¾',
3061 '¿' => '¿',
3062 'À' => 'À',
3063 'Á' => 'Á',
3064 'Â' => 'Â',
3065 'Ã' => 'Ã',
3066 'Ä' => 'Ä',
3067 'Å' => 'Å',
3068 'Æ' => 'Æ',
3069 'Ç' => 'Ç',
3070 'È' => 'È',
3071 'É' => 'É',
3072 'Ê' => 'Ê',
3073 'Ë' => 'Ë',
3074 'Ì' => 'Ì',
3075 'Í' => 'Í',
3076 'Î' => 'Î',
3077 'Ï' => 'Ï',
3078 'Ð' => 'Ð',
3079 'Ñ' => 'Ñ',
3080 'Ò' => 'Ò',
3081 'Ó' => 'Ó',
3082 'Ô' => 'Ô',
3083 'Õ' => 'Õ',
3084 'Ö' => 'Ö',
3085 '×' => '×',
3086 'Ø' => 'Ø',
3087 'Ù' => 'Ù',
3088 'Ú' => 'Ú',
3089 'Û' => 'Û',
3090 'Ü' => 'Ü',
3091 'Ý' => 'Ý',
3092 'Þ' => 'Þ',
3093 'ß' => 'ß',
3094 'à' => 'à',
3095 'á' => 'á',
3096 'â' => 'â',
3097 'ã' => 'ã',
3098 'ä' => 'ä',
3099 'å' => 'å',
3100 'æ' => 'æ',
3101 'ç' => 'ç',
3102 'è' => 'è',
3103 'é' => 'é',
3104 'ê' => 'ê',
3105 'ë' => 'ë',
3106 'ì' => 'ì',
3107 'í' => 'í',
3108 'î' => 'î',
3109 'ï' => 'ï',
3110 'ð' => 'ð',
3111 'ñ' => 'ñ',
3112 'ò' => 'ò',
3113 'ó' => 'ó',
3114 'ô' => 'ô',
3115 'õ' => 'õ',
3116 'ö' => 'ö',
3117 '÷' => '÷',
3118 'ø' => 'ø',
3119 'ù' => 'ù',
3120 'ú' => 'ú',
3121 'û' => 'û',
3122 'ü' => 'ü',
3123 'ý' => 'ý',
3124 'þ' => 'þ',
3125 'ÿ' => 'ÿ',
3126 'Œ' => 'Œ',
3127 'œ' => 'œ',
3128 'Š' => 'Š',
3129 'š' => 'š',
3130 'Ÿ' => 'Ÿ',
3131 'ƒ' => 'ƒ',
3132 'ˆ' => 'ˆ',
3133 '˜' => '˜',
3134 'Α' => 'Α',
3135 'Β' => 'Β',
3136 'Γ' => 'Γ',
3137 'Δ' => 'Δ',
3138 'Ε' => 'Ε',
3139 'Ζ' => 'Ζ',
3140 'Η' => 'Η',
3141 'Θ' => 'Θ',
3142 'Ι' => 'Ι',
3143 'Κ' => 'Κ',
3144 'Λ' => 'Λ',
3148 'Ο' => 'Ο',
3150 'Ρ' => 'Ρ',
3151 'Σ' => 'Σ',
3152 'Τ' => 'Τ',
3153 'Υ' => 'Υ',
3154 'Φ' => 'Φ',
3155 'Χ' => 'Χ',
3156 'Ψ' => 'Ψ',
3157 'Ω' => 'Ω',
3158 'α' => 'α',
3159 'β' => 'β',
3160 'γ' => 'γ',
3161 'δ' => 'δ',
3162 'ε' => 'ε',
3163 'ζ' => 'ζ',
3164 'η' => 'η',
3165 'θ' => 'θ',
3166 'ι' => 'ι',
3167 'κ' => 'κ',
3168 'λ' => 'λ',
3172 'ο' => 'ο',
3174 'ρ' => 'ρ',
3175 'ς' => 'ς',
3176 'σ' => 'σ',
3177 'τ' => 'τ',
3178 'υ' => 'υ',
3179 'φ' => 'φ',
3180 'χ' => 'χ',
3181 'ψ' => 'ψ',
3182 'ω' => 'ω',
3183 'ϑ' => 'ϑ',
3184 'ϒ' => 'ϒ',
3185 'ϖ' => 'ϖ',
3186 ' ' => ' ',
3187 ' ' => ' ',
3188 ' ' => ' ',
3189 '‌' => '‌',
3190 '‍' => '‍',
3191 '‎' => '‎',
3192 '‏' => '‏',
3193 '–' => '–',
3194 '—' => '—',
3195 '‘' => '‘',
3196 '’' => '’',
3197 '‚' => '‚',
3198 '“' => '“',
3199 '”' => '”',
3200 '„' => '„',
3201 '†' => '†',
3202 '‡' => '‡',
3203 '•' => '•',
3204 '…' => '…',
3205 '‰' => '‰',
3206 '′' => '′',
3207 '″' => '″',
3208 '‹' => '‹',
3209 '›' => '›',
3210 '‾' => '‾',
3211 '⁄' => '⁄',
3212 '€' => '€',
3213 'ℑ' => 'ℑ',
3214 '℘' => '℘',
3215 'ℜ' => 'ℜ',
3216 '™' => '™',
3217 'ℵ' => 'ℵ',
3218 '↵' => '↵',
3219 '⇐' => '⇐',
3220 '⇑' => '⇑',
3221 '⇒' => '⇒',
3222 '⇓' => '⇓',
3223 '⇔' => '⇔',
3224 '∀' => '∀',
3225 '∂' => '∂',
3226 '∃' => '∃',
3227 '∅' => '∅',
3228 '∇' => '∇',
3229 '∈' => '∈',
3230 '∉' => '∉',
3231 '∋' => '∋',
3232 '∏' => '∏',
3233 '∑' => '∑',
3234 '−' => '−',
3235 '∗' => '∗',
3236 '√' => '√',
3237 '∝' => '∝',
3238 '∞' => '∞',
3239 '∠' => '∠',
3240 '∧' => '∧',
3241 '∨' => '∨',
3242 '∩' => '∩',
3243 '∪' => '∪',
3244 '∫' => '∫',
3245 '∴' => '∴',
3246 '∼' => '∼',
3247 '≅' => '≅',
3248 '≈' => '≈',
3249 '≠' => '≠',
3250 '≡' => '≡',
3251 '≤' => '≤',
3252 '≥' => '≥',
3253 '⊂' => '⊂',
3254 '⊃' => '⊃',
3255 '⊄' => '⊄',
3256 '⊆' => '⊆',
3257 '⊇' => '⊇',
3258 '⊕' => '⊕',
3259 '⊗' => '⊗',
3260 '⊥' => '⊥',
3261 '⋅' => '⋅',
3262 '⌈' => '⌈',
3263 '⌉' => '⌉',
3264 '⌊' => '⌊',
3265 '⌋' => '⌋',
3266 '⟨' => '〈',
3267 '⟩' => '〉',
3268 '←' => '←',
3269 '↑' => '↑',
3270 '→' => '→',
3271 '↓' => '↓',
3272 '↔' => '↔',
3273 '◊' => '◊',
3274 '♠' => '♠',
3275 '♣' => '♣',
3276 '♥' => '♥',
3277 '♦' => '♦'
3280 return str_replace( array_keys($to_ncr), array_values($to_ncr), $text );
3284 * Formats text for the editor.
3286 * Generally the browsers treat everything inside a textarea as text, but
3287 * it is still a good idea to HTML entity encode `<`, `>` and `&` in the content.
3289 * The filter {@see 'format_for_editor'} is applied here. If `$text` is empty the
3290 * filter will be applied to an empty string.
3294 * @see _WP_Editors::editor()
3296 * @param string $text The text to be formatted.
3297 * @param string $default_editor The default editor for the current user.
3298 * It is usually either 'html' or 'tinymce'.
3299 * @return string The formatted text after filter is applied.
3301 function format_for_editor( $text, $default_editor = null ) {
3303 $text = htmlspecialchars( $text, ENT_NOQUOTES, get_option( 'blog_charset' ) );
3307 * Filter the text after it is formatted for the editor.
3311 * @param string $text The formatted text.
3312 * @param string $default_editor The default editor for the current user.
3313 * It is usually either 'html' or 'tinymce'.
3315 return apply_filters( 'format_for_editor', $text, $default_editor );
3319 * Perform a deep string replace operation to ensure the values in $search are no longer present
3321 * Repeats the replacement operation until it no longer replaces anything so as to remove "nested" values
3322 * e.g. $subject = '%0%0%0DDD', $search ='%0D', $result ='' rather than the '%0%0DD' that
3323 * str_replace would return
3328 * @param string|array $search The value being searched for, otherwise known as the needle.
3329 * An array may be used to designate multiple needles.
3330 * @param string $subject The string being searched and replaced on, otherwise known as the haystack.
3331 * @return string The string with the replaced svalues.
3333 function _deep_replace( $search, $subject ) {
3334 $subject = (string) $subject;
3338 $subject = str_replace( $search, '', $subject, $count );
3345 * Escapes data for use in a MySQL query.
3347 * Usually you should prepare queries using wpdb::prepare().
3348 * Sometimes, spot-escaping is required or useful. One example
3349 * is preparing an array for use in an IN clause.
3353 * @global wpdb $wpdb WordPress database abstraction object.
3355 * @param string|array $data Unescaped data
3356 * @return string|array Escaped data
3358 function esc_sql( $data ) {
3360 return $wpdb->_escape( $data );
3364 * Checks and cleans a URL.
3366 * A number of characters are removed from the URL. If the URL is for displaying
3367 * (the default behaviour) ampersands are also replaced. The 'clean_url' filter
3368 * is applied to the returned cleaned URL.
3372 * @param string $url The URL to be cleaned.
3373 * @param array $protocols Optional. An array of acceptable protocols.
3374 * Defaults to return value of wp_allowed_protocols()
3375 * @param string $_context Private. Use esc_url_raw() for database usage.
3376 * @return string The cleaned $url after the 'clean_url' filter is applied.
3378 function esc_url( $url, $protocols = null, $_context = 'display' ) {
3379 $original_url = $url;
3384 $url = str_replace( ' ', '%20', $url );
3385 $url = preg_replace('|[^a-z0-9-~+_.?#=!&;,/:%@$\|*\'()\[\]\\x80-\\xff]|i', '', $url);
3387 if ( '' === $url ) {
3391 if ( 0 !== stripos( $url, 'mailto:' ) ) {
3392 $strip = array('%0d', '%0a', '%0D', '%0A');
3393 $url = _deep_replace($strip, $url);
3396 $url = str_replace(';//', '://', $url);
3397 /* If the URL doesn't appear to contain a scheme, we
3398 * presume it needs http:// prepended (unless a relative
3399 * link starting with /, # or ? or a php file).
3401 if ( strpos($url, ':') === false && ! in_array( $url[0], array( '/', '#', '?' ) ) &&
3402 ! preg_match('/^[a-z0-9-]+?\.php/i', $url) )
3403 $url = 'http://' . $url;
3405 // Replace ampersands and single quotes only when displaying.
3406 if ( 'display' == $_context ) {
3407 $url = wp_kses_normalize_entities( $url );
3408 $url = str_replace( '&', '&', $url );
3409 $url = str_replace( "'", ''', $url );
3412 if ( ( false !== strpos( $url, '[' ) ) || ( false !== strpos( $url, ']' ) ) ) {
3414 $parsed = wp_parse_url( $url );
3417 if ( isset( $parsed['scheme'] ) ) {
3418 $front .= $parsed['scheme'] . '://';
3419 } elseif ( '/' === $url[0] ) {
3423 if ( isset( $parsed['user'] ) ) {
3424 $front .= $parsed['user'];
3427 if ( isset( $parsed['pass'] ) ) {
3428 $front .= ':' . $parsed['pass'];
3431 if ( isset( $parsed['user'] ) || isset( $parsed['pass'] ) ) {
3435 if ( isset( $parsed['host'] ) ) {
3436 $front .= $parsed['host'];
3439 if ( isset( $parsed['port'] ) ) {
3440 $front .= ':' . $parsed['port'];
3443 $end_dirty = str_replace( $front, '', $url );
3444 $end_clean = str_replace( array( '[', ']' ), array( '%5B', '%5D' ), $end_dirty );
3445 $url = str_replace( $end_dirty, $end_clean, $url );
3449 if ( '/' === $url[0] ) {
3450 $good_protocol_url = $url;
3452 if ( ! is_array( $protocols ) )
3453 $protocols = wp_allowed_protocols();
3454 $good_protocol_url = wp_kses_bad_protocol( $url, $protocols );
3455 if ( strtolower( $good_protocol_url ) != strtolower( $url ) )
3460 * Filter a string cleaned and escaped for output as a URL.
3464 * @param string $good_protocol_url The cleaned URL to be returned.
3465 * @param string $original_url The URL prior to cleaning.
3466 * @param string $_context If 'display', replace ampersands and single quotes only.
3468 return apply_filters( 'clean_url', $good_protocol_url, $original_url, $_context );
3472 * Performs esc_url() for database usage.
3476 * @param string $url The URL to be cleaned.
3477 * @param array $protocols An array of acceptable protocols.
3478 * @return string The cleaned URL.
3480 function esc_url_raw( $url, $protocols = null ) {
3481 return esc_url( $url, $protocols, 'db' );
3485 * Convert entities, while preserving already-encoded entities.
3487 * @link http://www.php.net/htmlentities Borrowed from the PHP Manual user notes.
3491 * @param string $myHTML The text to be converted.
3492 * @return string Converted text.
3494 function htmlentities2( $myHTML ) {
3495 $translation_table = get_html_translation_table( HTML_ENTITIES, ENT_QUOTES );
3496 $translation_table[chr(38)] = '&';
3497 return preg_replace( "/&(?![A-Za-z]{0,4}\w{2,3};|#[0-9]{2,3};)/", "&", strtr($myHTML, $translation_table) );
3501 * Escape single quotes, htmlspecialchar " < > &, and fix line endings.
3503 * Escapes text strings for echoing in JS. It is intended to be used for inline JS
3504 * (in a tag attribute, for example onclick="..."). Note that the strings have to
3505 * be in single quotes. The filter 'js_escape' is also applied here.
3509 * @param string $text The text to be escaped.
3510 * @return string Escaped text.
3512 function esc_js( $text ) {
3513 $safe_text = wp_check_invalid_utf8( $text );
3514 $safe_text = _wp_specialchars( $safe_text, ENT_COMPAT );
3515 $safe_text = preg_replace( '/&#(x)?0*(?(1)27|39);?/i', "'", stripslashes( $safe_text ) );
3516 $safe_text = str_replace( "\r", '', $safe_text );
3517 $safe_text = str_replace( "\n", '\\n', addslashes( $safe_text ) );
3519 * Filter a string cleaned and escaped for output in JavaScript.
3521 * Text passed to esc_js() is stripped of invalid or special characters,
3522 * and properly slashed for output.
3526 * @param string $safe_text The text after it has been escaped.
3527 * @param string $text The text prior to being escaped.
3529 return apply_filters( 'js_escape', $safe_text, $text );
3533 * Escaping for HTML blocks.
3537 * @param string $text
3540 function esc_html( $text ) {
3541 $safe_text = wp_check_invalid_utf8( $text );
3542 $safe_text = _wp_specialchars( $safe_text, ENT_QUOTES );
3544 * Filter a string cleaned and escaped for output in HTML.
3546 * Text passed to esc_html() is stripped of invalid or special characters
3551 * @param string $safe_text The text after it has been escaped.
3552 * @param string $text The text prior to being escaped.
3554 return apply_filters( 'esc_html', $safe_text, $text );
3558 * Escaping for HTML attributes.
3562 * @param string $text
3565 function esc_attr( $text ) {
3566 $safe_text = wp_check_invalid_utf8( $text );
3567 $safe_text = _wp_specialchars( $safe_text, ENT_QUOTES );
3569 * Filter a string cleaned and escaped for output in an HTML attribute.
3571 * Text passed to esc_attr() is stripped of invalid or special characters
3576 * @param string $safe_text The text after it has been escaped.
3577 * @param string $text The text prior to being escaped.
3579 return apply_filters( 'attribute_escape', $safe_text, $text );
3583 * Escaping for textarea values.
3587 * @param string $text
3590 function esc_textarea( $text ) {
3591 $safe_text = htmlspecialchars( $text, ENT_QUOTES, get_option( 'blog_charset' ) );
3593 * Filter a string cleaned and escaped for output in a textarea element.
3597 * @param string $safe_text The text after it has been escaped.
3598 * @param string $text The text prior to being escaped.
3600 return apply_filters( 'esc_textarea', $safe_text, $text );
3604 * Escape an HTML tag name.
3608 * @param string $tag_name
3611 function tag_escape( $tag_name ) {
3612 $safe_tag = strtolower( preg_replace('/[^a-zA-Z0-9_:]/', '', $tag_name) );
3614 * Filter a string cleaned and escaped for output as an HTML tag.
3618 * @param string $safe_tag The tag name after it has been escaped.
3619 * @param string $tag_name The text before it was escaped.
3621 return apply_filters( 'tag_escape', $safe_tag, $tag_name );
3625 * Convert full URL paths to absolute paths.
3627 * Removes the http or https protocols and the domain. Keeps the path '/' at the
3628 * beginning, so it isn't a true relative link, but from the web root base.
3631 * @since 4.1.0 Support was added for relative URLs.
3633 * @param string $link Full URL path.
3634 * @return string Absolute path.
3636 function wp_make_link_relative( $link ) {
3637 return preg_replace( '|^(https?:)?//[^/]+(/?.*)|i', '$2', $link );
3641 * Sanitises various option values based on the nature of the option.
3643 * This is basically a switch statement which will pass $value through a number
3644 * of functions depending on the $option.
3648 * @global wpdb $wpdb WordPress database abstraction object.
3650 * @param string $option The name of the option.
3651 * @param string $value The unsanitised value.
3652 * @return string Sanitized value.
3654 function sanitize_option( $option, $value ) {
3657 $original_value = $value;
3660 switch ( $option ) {
3661 case 'admin_email' :
3662 case 'new_admin_email' :
3663 $value = $wpdb->strip_invalid_text_for_column( $wpdb->options, 'option_value', $value );
3664 if ( is_wp_error( $value ) ) {
3665 $error = $value->get_error_message();
3667 $value = sanitize_email( $value );
3668 if ( ! is_email( $value ) ) {
3669 $error = __( 'The email address entered did not appear to be a valid email address. Please enter a valid email address.' );
3674 case 'thumbnail_size_w':
3675 case 'thumbnail_size_h':
3676 case 'medium_size_w':
3677 case 'medium_size_h':
3678 case 'medium_large_size_w':
3679 case 'medium_large_size_h':
3680 case 'large_size_w':
3681 case 'large_size_h':
3682 case 'mailserver_port':
3683 case 'comment_max_links':
3684 case 'page_on_front':
3685 case 'page_for_posts':
3686 case 'rss_excerpt_length':
3687 case 'default_category':
3688 case 'default_email_category':
3689 case 'default_link_category':
3690 case 'close_comments_days_old':
3691 case 'comments_per_page':
3692 case 'thread_comments_depth':
3693 case 'users_can_register':
3694 case 'start_of_week':
3696 $value = absint( $value );
3699 case 'posts_per_page':
3700 case 'posts_per_rss':
3701 $value = (int) $value;
3702 if ( empty($value) )
3705 $value = abs($value);
3708 case 'default_ping_status':
3709 case 'default_comment_status':
3710 // Options that if not there have 0 value but need to be something like "closed"
3711 if ( $value == '0' || $value == '')
3715 case 'blogdescription':
3717 $value = $wpdb->strip_invalid_text_for_column( $wpdb->options, 'option_value', $value );
3718 if ( is_wp_error( $value ) ) {
3719 $error = $value->get_error_message();
3721 $value = esc_html( $value );
3725 case 'blog_charset':
3726 $value = preg_replace('/[^a-zA-Z0-9_-]/', '', $value); // strips slashes
3730 // This is the value if the settings checkbox is not checked on POST. Don't rely on this.
3731 if ( null === $value )
3734 $value = intval( $value );
3739 case 'mailserver_url':
3740 case 'mailserver_login':
3741 case 'mailserver_pass':
3743 $value = $wpdb->strip_invalid_text_for_column( $wpdb->options, 'option_value', $value );
3744 if ( is_wp_error( $value ) ) {
3745 $error = $value->get_error_message();
3747 $value = strip_tags( $value );
3748 $value = wp_kses_data( $value );
3753 $value = explode( "\n", $value );
3754 $value = array_filter( array_map( 'trim', $value ) );
3755 $value = array_filter( array_map( 'esc_url_raw', $value ) );
3756 $value = implode( "\n", $value );
3760 $value = preg_replace('/[^0-9:.-]/', '', $value); // strips slashes
3764 $value = $wpdb->strip_invalid_text_for_column( $wpdb->options, 'option_value', $value );
3765 if ( is_wp_error( $value ) ) {
3766 $error = $value->get_error_message();
3768 if ( preg_match( '#http(s?)://(.+)#i', $value ) ) {
3769 $value = esc_url_raw( $value );
3771 $error = __( 'The WordPress address you entered did not appear to be a valid URL. Please enter a valid URL.' );
3777 $value = $wpdb->strip_invalid_text_for_column( $wpdb->options, 'option_value', $value );
3778 if ( is_wp_error( $value ) ) {
3779 $error = $value->get_error_message();
3781 if ( preg_match( '#http(s?)://(.+)#i', $value ) ) {
3782 $value = esc_url_raw( $value );
3784 $error = __( 'The Site address you entered did not appear to be a valid URL. Please enter a valid URL.' );
3790 $allowed = get_available_languages();
3791 if ( ! is_multisite() && defined( 'WPLANG' ) && '' !== WPLANG && 'en_US' !== WPLANG ) {
3792 $allowed[] = WPLANG;
3794 if ( ! in_array( $value, $allowed ) && ! empty( $value ) ) {
3795 $value = get_option( $option );
3799 case 'illegal_names':
3800 $value = $wpdb->strip_invalid_text_for_column( $wpdb->options, 'option_value', $value );
3801 if ( is_wp_error( $value ) ) {
3802 $error = $value->get_error_message();
3804 if ( ! is_array( $value ) )
3805 $value = explode( ' ', $value );
3807 $value = array_values( array_filter( array_map( 'trim', $value ) ) );
3814 case 'limited_email_domains':
3815 case 'banned_email_domains':
3816 $value = $wpdb->strip_invalid_text_for_column( $wpdb->options, 'option_value', $value );
3817 if ( is_wp_error( $value ) ) {
3818 $error = $value->get_error_message();
3820 if ( ! is_array( $value ) )
3821 $value = explode( "\n", $value );
3823 $domains = array_values( array_filter( array_map( 'trim', $value ) ) );
3826 foreach ( $domains as $domain ) {
3827 if ( ! preg_match( '/(--|\.\.)/', $domain ) && preg_match( '|^([a-zA-Z0-9-\.])+$|', $domain ) ) {
3836 case 'timezone_string':
3837 $allowed_zones = timezone_identifiers_list();
3838 if ( ! in_array( $value, $allowed_zones ) && ! empty( $value ) ) {
3839 $error = __( 'The timezone you have entered is not valid. Please select a valid timezone.' );
3843 case 'permalink_structure':
3844 case 'category_base':
3846 $value = $wpdb->strip_invalid_text_for_column( $wpdb->options, 'option_value', $value );
3847 if ( is_wp_error( $value ) ) {
3848 $error = $value->get_error_message();
3850 $value = esc_url_raw( $value );
3851 $value = str_replace( 'http://', '', $value );
3855 case 'default_role' :
3856 if ( ! get_role( $value ) && get_role( 'subscriber' ) )
3857 $value = 'subscriber';
3860 case 'moderation_keys':
3861 case 'blacklist_keys':
3862 $value = $wpdb->strip_invalid_text_for_column( $wpdb->options, 'option_value', $value );
3863 if ( is_wp_error( $value ) ) {
3864 $error = $value->get_error_message();
3866 $value = explode( "\n", $value );
3867 $value = array_filter( array_map( 'trim', $value ) );
3868 $value = array_unique( $value );
3869 $value = implode( "\n", $value );
3874 if ( ! empty( $error ) ) {
3875 $value = get_option( $option );
3876 if ( function_exists( 'add_settings_error' ) ) {
3877 add_settings_error( $option, "invalid_{$option}", $error );
3882 * Filter an option value following sanitization.
3885 * @since 4.3.0 Added the `$original_value` parameter.
3887 * @param string $value The sanitized option value.
3888 * @param string $option The option name.
3889 * @param string $original_value The original value passed to the function.
3891 return apply_filters( "sanitize_option_{$option}", $value, $option, $original_value );
3895 * Maps a function to all non-iterable elements of an array or an object.
3897 * This is similar to `array_walk_recursive()` but acts upon objects too.
3901 * @param mixed $value The array, object, or scalar.
3902 * @param callable $callback The function to map onto $value.
3903 * @return mixed The value with the callback applied to all non-arrays and non-objects inside it.
3905 function map_deep( $value, $callback ) {
3906 if ( is_array( $value ) ) {
3907 foreach ( $value as $index => $item ) {
3908 $value[ $index ] = map_deep( $item, $callback );
3910 } elseif ( is_object( $value ) ) {
3911 $object_vars = get_object_vars( $value );
3912 foreach ( $object_vars as $property_name => $property_value ) {
3913 $value->$property_name = map_deep( $property_value, $callback );
3916 $value = call_user_func( $callback, $value );
3923 * Parses a string into variables to be stored in an array.
3925 * Uses {@link http://www.php.net/parse_str parse_str()} and stripslashes if
3926 * {@link http://www.php.net/magic_quotes magic_quotes_gpc} is on.
3930 * @param string $string The string to be parsed.
3931 * @param array $array Variables will be stored in this array.
3933 function wp_parse_str( $string, &$array ) {
3934 parse_str( $string, $array );
3935 if ( get_magic_quotes_gpc() )
3936 $array = stripslashes_deep( $array );
3938 * Filter the array of variables derived from a parsed string.
3942 * @param array $array The array populated with variables.
3944 $array = apply_filters( 'wp_parse_str', $array );
3948 * Convert lone less than signs.
3950 * KSES already converts lone greater than signs.
3954 * @param string $text Text to be converted.
3955 * @return string Converted text.
3957 function wp_pre_kses_less_than( $text ) {
3958 return preg_replace_callback('%<[^>]*?((?=<)|>|$)%', 'wp_pre_kses_less_than_callback', $text);
3962 * Callback function used by preg_replace.
3966 * @param array $matches Populated by matches to preg_replace.
3967 * @return string The text returned after esc_html if needed.
3969 function wp_pre_kses_less_than_callback( $matches ) {
3970 if ( false === strpos($matches[0], '>') )
3971 return esc_html($matches[0]);
3976 * WordPress implementation of PHP sprintf() with filters.
3979 * @link http://www.php.net/sprintf
3981 * @param string $pattern The string which formatted args are inserted.
3982 * @param mixed $args ,... Arguments to be formatted into the $pattern string.
3983 * @return string The formatted string.
3985 function wp_sprintf( $pattern ) {
3986 $args = func_get_args();
3987 $len = strlen($pattern);
3991 while ( $len > $start ) {
3992 // Last character: append and break
3993 if ( strlen($pattern) - 1 == $start ) {
3994 $result .= substr($pattern, -1);
3998 // Literal %: append and continue
3999 if ( substr($pattern, $start, 2) == '%%' ) {
4005 // Get fragment before next %
4006 $end = strpos($pattern, '%', $start + 1);
4007 if ( false === $end )
4009 $fragment = substr($pattern, $start, $end - $start);
4011 // Fragment has a specifier
4012 if ( $pattern[$start] == '%' ) {
4013 // Find numbered arguments or take the next one in order
4014 if ( preg_match('/^%(\d+)\$/', $fragment, $matches) ) {
4015 $arg = isset($args[$matches[1]]) ? $args[$matches[1]] : '';
4016 $fragment = str_replace("%{$matches[1]}$", '%', $fragment);
4019 $arg = isset($args[$arg_index]) ? $args[$arg_index] : '';
4023 * Filter a fragment from the pattern passed to wp_sprintf().
4025 * If the fragment is unchanged, then sprintf() will be run on the fragment.
4029 * @param string $fragment A fragment from the pattern.
4030 * @param string $arg The argument.
4032 $_fragment = apply_filters( 'wp_sprintf', $fragment, $arg );
4033 if ( $_fragment != $fragment )
4034 $fragment = $_fragment;
4036 $fragment = sprintf($fragment, strval($arg) );
4039 // Append to result and move to next fragment
4040 $result .= $fragment;
4047 * Localize list items before the rest of the content.
4049 * The '%l' must be at the first characters can then contain the rest of the
4050 * content. The list items will have ', ', ', and', and ' and ' added depending
4051 * on the amount of list items in the $args parameter.
4055 * @param string $pattern Content containing '%l' at the beginning.
4056 * @param array $args List items to prepend to the content and replace '%l'.
4057 * @return string Localized list items and rest of the content.
4059 function wp_sprintf_l( $pattern, $args ) {
4061 if ( substr($pattern, 0, 2) != '%l' )
4064 // Nothing to work with
4069 * Filter the translated delimiters used by wp_sprintf_l().
4070 * Placeholders (%s) are included to assist translators and then
4071 * removed before the array of strings reaches the filter.
4073 * Please note: Ampersands and entities should be avoided here.
4077 * @param array $delimiters An array of translated delimiters.
4079 $l = apply_filters( 'wp_sprintf_l', array(
4080 /* translators: used to join items in a list with more than 2 items */
4081 'between' => sprintf( __('%s, %s'), '', '' ),
4082 /* translators: used to join last two items in a list with more than 2 times */
4083 'between_last_two' => sprintf( __('%s, and %s'), '', '' ),
4084 /* translators: used to join items in a list with only 2 items */
4085 'between_only_two' => sprintf( __('%s and %s'), '', '' ),
4088 $args = (array) $args;
4089 $result = array_shift($args);
4090 if ( count($args) == 1 )
4091 $result .= $l['between_only_two'] . array_shift($args);
4092 // Loop when more than two args
4095 $arg = array_shift($args);
4098 $result .= $l['between_last_two'] . $arg;
4100 $result .= $l['between'] . $arg;
4102 return $result . substr($pattern, 2);
4106 * Safely extracts not more than the first $count characters from html string.
4108 * UTF-8, tags and entities safe prefix extraction. Entities inside will *NOT*
4109 * be counted as one character. For example & will be counted as 4, < as
4114 * @param string $str String to get the excerpt from.
4115 * @param int $count Maximum number of characters to take.
4116 * @param string $more Optional. What to append if $str needs to be trimmed. Defaults to empty string.
4117 * @return string The excerpt.
4119 function wp_html_excerpt( $str, $count, $more = null ) {
4120 if ( null === $more )
4122 $str = wp_strip_all_tags( $str, true );
4123 $excerpt = mb_substr( $str, 0, $count );
4124 // remove part of an entity at the end
4125 $excerpt = preg_replace( '/&[^;\s]{0,6}$/', '', $excerpt );
4126 if ( $str != $excerpt )
4127 $excerpt = trim( $excerpt ) . $more;
4132 * Add a Base url to relative links in passed content.
4134 * By default it supports the 'src' and 'href' attributes. However this can be
4135 * changed via the 3rd param.
4139 * @global string $_links_add_base
4141 * @param string $content String to search for links in.
4142 * @param string $base The base URL to prefix to links.
4143 * @param array $attrs The attributes which should be processed.
4144 * @return string The processed content.
4146 function links_add_base_url( $content, $base, $attrs = array('src', 'href') ) {
4147 global $_links_add_base;
4148 $_links_add_base = $base;
4149 $attrs = implode('|', (array)$attrs);
4150 return preg_replace_callback( "!($attrs)=(['\"])(.+?)\\2!i", '_links_add_base', $content );
4154 * Callback to add a base url to relative links in passed content.
4159 * @global string $_links_add_base
4161 * @param string $m The matched link.
4162 * @return string The processed link.
4164 function _links_add_base( $m ) {
4165 global $_links_add_base;
4166 //1 = attribute name 2 = quotation mark 3 = URL
4167 return $m[1] . '=' . $m[2] .
4168 ( preg_match( '#^(\w{1,20}):#', $m[3], $protocol ) && in_array( $protocol[1], wp_allowed_protocols() ) ?
4170 WP_Http::make_absolute_url( $m[3], $_links_add_base )
4176 * Adds a Target attribute to all links in passed content.
4178 * This function by default only applies to `<a>` tags, however this can be
4179 * modified by the 3rd param.
4181 * *NOTE:* Any current target attributed will be stripped and replaced.
4185 * @global string $_links_add_target
4187 * @param string $content String to search for links in.
4188 * @param string $target The Target to add to the links.
4189 * @param array $tags An array of tags to apply to.
4190 * @return string The processed content.
4192 function links_add_target( $content, $target = '_blank', $tags = array('a') ) {
4193 global $_links_add_target;
4194 $_links_add_target = $target;
4195 $tags = implode('|', (array)$tags);
4196 return preg_replace_callback( "!<($tags)([^>]*)>!i", '_links_add_target', $content );
4200 * Callback to add a target attribute to all links in passed content.
4205 * @global string $_links_add_target
4207 * @param string $m The matched link.
4208 * @return string The processed link.
4210 function _links_add_target( $m ) {
4211 global $_links_add_target;
4213 $link = preg_replace('|( target=([\'"])(.*?)\2)|i', '', $m[2]);
4214 return '<' . $tag . $link . ' target="' . esc_attr( $_links_add_target ) . '">';
4218 * Normalize EOL characters and strip duplicate whitespace.
4222 * @param string $str The string to normalize.
4223 * @return string The normalized string.
4225 function normalize_whitespace( $str ) {
4226 $str = trim( $str );
4227 $str = str_replace( "\r", "\n", $str );
4228 $str = preg_replace( array( '/\n+/', '/[ \t]+/' ), array( "\n", ' ' ), $str );
4233 * Properly strip all HTML tags including script and style
4235 * This differs from strip_tags() because it removes the contents of
4236 * the `<script>` and `<style>` tags. E.g. `strip_tags( '<script>something</script>' )`
4237 * will return 'something'. wp_strip_all_tags will return ''
4241 * @param string $string String containing HTML tags
4242 * @param bool $remove_breaks Optional. Whether to remove left over line breaks and white space chars
4243 * @return string The processed string.
4245 function wp_strip_all_tags($string, $remove_breaks = false) {
4246 $string = preg_replace( '@<(script|style)[^>]*?>.*?</\\1>@si', '', $string );
4247 $string = strip_tags($string);
4249 if ( $remove_breaks )
4250 $string = preg_replace('/[\r\n\t ]+/', ' ', $string);
4252 return trim( $string );
4256 * Sanitize a string from user input or from the db
4258 * check for invalid UTF-8,
4259 * Convert single < characters to entity,
4261 * remove line breaks, tabs and extra white space,
4266 * @param string $str
4269 function sanitize_text_field( $str ) {
4270 $filtered = wp_check_invalid_utf8( $str );
4272 if ( strpos($filtered, '<') !== false ) {
4273 $filtered = wp_pre_kses_less_than( $filtered );
4274 // This will strip extra whitespace for us.
4275 $filtered = wp_strip_all_tags( $filtered, true );
4277 $filtered = trim( preg_replace('/[\r\n\t ]+/', ' ', $filtered) );
4281 while ( preg_match('/%[a-f0-9]{2}/i', $filtered, $match) ) {
4282 $filtered = str_replace($match[0], '', $filtered);
4287 // Strip out the whitespace that may now exist after removing the octets.
4288 $filtered = trim( preg_replace('/ +/', ' ', $filtered) );
4292 * Filter a sanitized text field string.
4296 * @param string $filtered The sanitized string.
4297 * @param string $str The string prior to being sanitized.
4299 return apply_filters( 'sanitize_text_field', $filtered, $str );
4303 * i18n friendly version of basename()
4307 * @param string $path A path.
4308 * @param string $suffix If the filename ends in suffix this will also be cut off.
4311 function wp_basename( $path, $suffix = '' ) {
4312 return urldecode( basename( str_replace( array( '%2F', '%5C' ), '/', urlencode( $path ) ), $suffix ) );
4316 * Forever eliminate "Wordpress" from the planet (or at least the little bit we can influence).
4318 * Violating our coding standards for a good function name.
4322 * @staticvar string|false $dblq
4324 * @param string $text The text to be modified.
4325 * @return string The modified text.
4327 function capital_P_dangit( $text ) {
4328 // Simple replacement for titles
4329 $current_filter = current_filter();
4330 if ( 'the_title' === $current_filter || 'wp_title' === $current_filter )
4331 return str_replace( 'Wordpress', 'WordPress', $text );
4332 // Still here? Use the more judicious replacement
4333 static $dblq = false;
4334 if ( false === $dblq ) {
4335 $dblq = _x( '“', 'opening curly double quote' );
4338 array( ' Wordpress', '‘Wordpress', $dblq . 'Wordpress', '>Wordpress', '(Wordpress' ),
4339 array( ' WordPress', '‘WordPress', $dblq . 'WordPress', '>WordPress', '(WordPress' ),
4344 * Sanitize a mime type
4348 * @param string $mime_type Mime type
4349 * @return string Sanitized mime type
4351 function sanitize_mime_type( $mime_type ) {
4352 $sani_mime_type = preg_replace( '/[^-+*.a-zA-Z0-9\/]/', '', $mime_type );
4354 * Filter a mime type following sanitization.
4358 * @param string $sani_mime_type The sanitized mime type.
4359 * @param string $mime_type The mime type prior to sanitization.
4361 return apply_filters( 'sanitize_mime_type', $sani_mime_type, $mime_type );
4365 * Sanitize space or carriage return separated URLs that are used to send trackbacks.
4369 * @param string $to_ping Space or carriage return separated URLs
4370 * @return string URLs starting with the http or https protocol, separated by a carriage return.
4372 function sanitize_trackback_urls( $to_ping ) {
4373 $urls_to_ping = preg_split( '/[\r\n\t ]/', trim( $to_ping ), -1, PREG_SPLIT_NO_EMPTY );
4374 foreach ( $urls_to_ping as $k => $url ) {
4375 if ( !preg_match( '#^https?://.#i', $url ) )
4376 unset( $urls_to_ping[$k] );
4378 $urls_to_ping = array_map( 'esc_url_raw', $urls_to_ping );
4379 $urls_to_ping = implode( "\n", $urls_to_ping );
4381 * Filter a list of trackback URLs following sanitization.
4383 * The string returned here consists of a space or carriage return-delimited list
4384 * of trackback URLs.
4388 * @param string $urls_to_ping Sanitized space or carriage return separated URLs.
4389 * @param string $to_ping Space or carriage return separated URLs before sanitization.
4391 return apply_filters( 'sanitize_trackback_urls', $urls_to_ping, $to_ping );
4395 * Add slashes to a string or array of strings.
4397 * This should be used when preparing data for core API that expects slashed data.
4398 * This should not be used to escape data going directly into an SQL query.
4402 * @param string|array $value String or array of strings to slash.
4403 * @return string|array Slashed $value
4405 function wp_slash( $value ) {
4406 if ( is_array( $value ) ) {
4407 foreach ( $value as $k => $v ) {
4408 if ( is_array( $v ) ) {
4409 $value[$k] = wp_slash( $v );
4411 $value[$k] = addslashes( $v );
4415 $value = addslashes( $value );
4422 * Remove slashes from a string or array of strings.
4424 * This should be used to remove slashes from data passed to core API that
4425 * expects data to be unslashed.
4429 * @param string|array $value String or array of strings to unslash.
4430 * @return string|array Unslashed $value
4432 function wp_unslash( $value ) {
4433 return stripslashes_deep( $value );
4437 * Extract and return the first URL from passed content.
4441 * @param string $content A string which might contain a URL.
4442 * @return string|false The found URL.
4444 function get_url_in_content( $content ) {
4445 if ( empty( $content ) ) {
4449 if ( preg_match( '/<a\s[^>]*?href=([\'"])(.+?)\1/is', $content, $matches ) ) {
4450 return esc_url_raw( $matches[2] );
4457 * Returns the regexp for common whitespace characters.
4459 * By default, spaces include new lines, tabs, nbsp entities, and the UTF-8 nbsp.
4460 * This is designed to replace the PCRE \s sequence. In ticket #22692, that
4461 * sequence was found to be unreliable due to random inclusion of the A0 byte.
4465 * @staticvar string $spaces
4467 * @return string The spaces regexp.
4469 function wp_spaces_regexp() {
4470 static $spaces = '';
4472 if ( empty( $spaces ) ) {
4474 * Filter the regexp for common whitespace characters.
4476 * This string is substituted for the \s sequence as needed in regular
4477 * expressions. For websites not written in English, different characters
4478 * may represent whitespace. For websites not encoded in UTF-8, the 0xC2 0xA0
4479 * sequence may not be in use.
4483 * @param string $spaces Regexp pattern for matching common whitespace characters.
4485 $spaces = apply_filters( 'wp_spaces_regexp', '[\r\n\t ]|\xC2\xA0| ' );
4492 * Print the important emoji-related styles.
4496 * @staticvar bool $printed
4498 function print_emoji_styles() {
4499 static $printed = false;
4507 <style type="text/css">
4510 display: inline !important;
4511 border: none !important;
4512 box-shadow: none !important;
4513 height: 1em !important;
4514 width: 1em !important;
4515 margin: 0 .07em !important;
4516 vertical-align: -0.1em !important;
4517 background: none !important;
4518 padding: 0 !important;
4526 * @global string $wp_version
4527 * @staticvar bool $printed
4529 function print_emoji_detection_script() {
4531 static $printed = false;
4541 * Filter the URL where emoji images are hosted.
4545 * @param string The emoji base URL.
4547 'baseUrl' => apply_filters( 'emoji_url', 'https://s.w.org/images/core/emoji/72x72/' ),
4550 * Filter the extension of the emoji files.
4554 * @param string The emoji extension. Default .png.
4556 'ext' => apply_filters( 'emoji_ext', '.png' ),
4559 $version = 'ver=' . $wp_version;
4561 if ( SCRIPT_DEBUG ) {
4562 $settings['source'] = array(
4563 /** This filter is documented in wp-includes/class.wp-scripts.php */
4564 'wpemoji' => apply_filters( 'script_loader_src', includes_url( "js/wp-emoji.js?$version" ), 'wpemoji' ),
4565 /** This filter is documented in wp-includes/class.wp-scripts.php */
4566 'twemoji' => apply_filters( 'script_loader_src', includes_url( "js/twemoji.js?$version" ), 'twemoji' ),
4570 <script type="text/javascript">
4571 window._wpemojiSettings = <?php echo wp_json_encode( $settings ); ?>;
4572 <?php readfile( ABSPATH . WPINC . "/js/wp-emoji-loader.js" ); ?>
4576 $settings['source'] = array(
4577 /** This filter is documented in wp-includes/class.wp-scripts.php */
4578 'concatemoji' => apply_filters( 'script_loader_src', includes_url( "js/wp-emoji-release.min.js?$version" ), 'concatemoji' ),
4582 * If you're looking at a src version of this file, you'll see an "include"
4583 * statement below. This is used by the `grunt build` process to directly
4584 * include a minified version of wp-emoji-loader.js, instead of using the
4585 * readfile() method from above.
4587 * If you're looking at a build version of this file, you'll see a string of
4588 * minified JavaScript. If you need to debug it, please turn on SCRIPT_DEBUG
4589 * and edit wp-emoji-loader.js directly.
4592 <script type="text/javascript">
4593 window._wpemojiSettings = <?php echo wp_json_encode( $settings ); ?>;
4594 !function(a,b,c){function d(a){var c,d,e,f=b.createElement("canvas"),g=f.getContext&&f.getContext("2d"),h=String.fromCharCode;if(!g||!g.fillText)return!1;switch(g.textBaseline="top",g.font="600 32px Arial",a){case"flag":return g.fillText(h(55356,56806,55356,56826),0,0),f.toDataURL().length>3e3;case"diversity":return g.fillText(h(55356,57221),0,0),c=g.getImageData(16,16,1,1).data,d=c[0]+","+c[1]+","+c[2]+","+c[3],g.fillText(h(55356,57221,55356,57343),0,0),c=g.getImageData(16,16,1,1).data,e=c[0]+","+c[1]+","+c[2]+","+c[3],d!==e;case"simple":return g.fillText(h(55357,56835),0,0),0!==g.getImageData(16,16,1,1).data[0];case"unicode8":return g.fillText(h(55356,57135),0,0),0!==g.getImageData(16,16,1,1).data[0]}return!1}function e(a){var c=b.createElement("script");c.src=a,c.type="text/javascript",b.getElementsByTagName("head")[0].appendChild(c)}var f,g,h,i;for(i=Array("simple","flag","unicode8","diversity"),c.supports={everything:!0,everythingExceptFlag:!0},h=0;h<i.length;h++)c.supports[i[h]]=d(i[h]),c.supports.everything=c.supports.everything&&c.supports[i[h]],"flag"!==i[h]&&(c.supports.everythingExceptFlag=c.supports.everythingExceptFlag&&c.supports[i[h]]);c.supports.everythingExceptFlag=c.supports.everythingExceptFlag&&!c.supports.flag,c.DOMReady=!1,c.readyCallback=function(){c.DOMReady=!0},c.supports.everything||(g=function(){c.readyCallback()},b.addEventListener?(b.addEventListener("DOMContentLoaded",g,!1),a.addEventListener("load",g,!1)):(a.attachEvent("onload",g),b.attachEvent("onreadystatechange",function(){"complete"===b.readyState&&c.readyCallback()})),f=c.source||{},f.concatemoji?e(f.concatemoji):f.wpemoji&&f.twemoji&&(e(f.twemoji),e(f.wpemoji)))}(window,document,window._wpemojiSettings);
4601 * Convert any 4 byte emoji in a string to their equivalent HTML entity.
4603 * Currently, only Unicode 7 emoji are supported. Skin tone modifiers are allowed,
4604 * all other Unicode 8 emoji will be added when the spec is finalised.
4606 * This allows us to store emoji in a DB using the utf8 character set.
4610 * @param string $content The content to encode.
4611 * @return string The encoded content.
4613 function wp_encode_emoji( $content ) {
4614 if ( function_exists( 'mb_convert_encoding' ) ) {
4616 \x23\xE2\x83\xA3 # Digits
4617 [\x30-\x39]\xE2\x83\xA3
4618 | \xF0\x9F[\x85-\x88][\xA6-\xBF] # Enclosed characters
4619 | \xF0\x9F[\x8C-\x97][\x80-\xBF] # Misc
4620 | \xF0\x9F\x98[\x80-\xBF] # Smilies
4621 | \xF0\x9F\x99[\x80-\x8F]
4622 | \xF0\x9F\x9A[\x80-\xBF] # Transport and map symbols
4626 if ( preg_match_all( $regex, $content, $matches ) ) {
4627 if ( ! empty( $matches[1] ) ) {
4628 foreach ( $matches[1] as $emoji ) {
4630 * UTF-32's hex encoding is the same as HTML's hex encoding.
4631 * So, by converting the emoji from UTF-8 to UTF-32, we magically
4632 * get the correct hex encoding.
4634 $unpacked = unpack( 'H*', mb_convert_encoding( $emoji, 'UTF-32', 'UTF-8' ) );
4635 if ( isset( $unpacked[1] ) ) {
4636 $entity = '&#x' . ltrim( $unpacked[1], '0' ) . ';';
4637 $content = str_replace( $emoji, $entity, $content );
4648 * Convert emoji to a static img element.
4652 * @param string $text The content to encode.
4653 * @return string The encoded content.
4655 function wp_staticize_emoji( $text ) {
4656 $text = wp_encode_emoji( $text );
4658 /** This filter is documented in wp-includes/formatting.php */
4659 $cdn_url = apply_filters( 'emoji_url', 'https://s.w.org/images/core/emoji/72x72/' );
4661 /** This filter is documented in wp-includes/formatting.php */
4662 $ext = apply_filters( 'emoji_ext', '.png' );
4666 * HTML loop taken from smiley function, which was taken from texturize function.
4667 * It'll never be consolidated.
4669 * First, capture the tags as well as in between.
4671 $textarr = preg_split( '/(<.*>)/U', $text, -1, PREG_SPLIT_DELIM_CAPTURE );
4672 $stop = count( $textarr );
4674 // Ignore processing of specific tags.
4675 $tags_to_ignore = 'code|pre|style|script|textarea';
4676 $ignore_block_element = '';
4678 for ( $i = 0; $i < $stop; $i++ ) {
4679 $content = $textarr[$i];
4681 // If we're in an ignore block, wait until we find its closing tag.
4682 if ( '' == $ignore_block_element && preg_match( '/^<(' . $tags_to_ignore . ')>/', $content, $matches ) ) {
4683 $ignore_block_element = $matches[1];
4686 // If it's not a tag and not in ignore block.
4687 if ( '' == $ignore_block_element && strlen( $content ) > 0 && '<' != $content[0] ) {
4689 if ( preg_match_all( '/(DZ(e[6-9a-f]|f[0-9a-f]);){2}/', $content, $matches ) ) {
4690 if ( ! empty( $matches[0] ) ) {
4691 foreach ( $matches[0] as $flag ) {
4692 $chars = str_replace( array( '&#x', ';'), '', $flag );
4694 list( $char1, $char2 ) = str_split( $chars, 5 );
4695 $entity = sprintf( '<img src="%s" alt="%s" class="wp-smiley" style="height: 1em; max-height: 1em;" />', $cdn_url . $char1 . '-' . $char2 . $ext, html_entity_decode( $flag ) );
4697 $content = str_replace( $flag, $entity, $content );
4702 // Loosely match the Emoji Unicode range.
4703 $regex = '/(&#x[2-3][0-9a-f]{3};|[1-6][0-9a-f]{2};)/';
4706 if ( preg_match_all( $regex, $content, $matches ) ) {
4707 if ( ! empty( $matches[1] ) ) {
4708 foreach ( $matches[1] as $emoji ) {
4709 $char = str_replace( array( '&#x', ';'), '', $emoji );
4710 $entity = sprintf( '<img src="%s" alt="%s" class="wp-smiley" style="height: 1em; max-height: 1em;" />', $cdn_url . $char . $ext, html_entity_decode( $emoji ) );
4712 $content = str_replace( $emoji, $entity, $content );
4718 // Did we exit ignore block.
4719 if ( '' != $ignore_block_element && '</' . $ignore_block_element . '>' == $content ) {
4720 $ignore_block_element = '';
4723 $output .= $content;
4730 * Convert emoji in emails into static images.
4734 * @param array $mail The email data array.
4735 * @return array The email data array, with emoji in the message staticized.
4737 function wp_staticize_emoji_for_email( $mail ) {
4738 if ( ! isset( $mail['message'] ) ) {
4743 * We can only transform the emoji into images if it's a text/html email.
4744 * To do that, here's a cut down version of the same process that happens
4745 * in wp_mail() - get the Content-Type from the headers, if there is one,
4746 * then pass it through the wp_mail_content_type filter, in case a plugin
4747 * is handling changing the Content-Type.
4750 if ( isset( $mail['headers'] ) ) {
4751 if ( is_array( $mail['headers'] ) ) {
4752 $headers = $mail['headers'];
4754 $headers = explode( "\n", str_replace( "\r\n", "\n", $mail['headers'] ) );
4758 foreach ( $headers as $header ) {
4759 if ( strpos($header, ':') === false ) {
4763 // Explode them out.
4764 list( $name, $content ) = explode( ':', trim( $header ), 2 );
4767 $name = trim( $name );
4768 $content = trim( $content );
4770 if ( 'content-type' === strtolower( $name ) ) {
4771 if ( strpos( $content, ';' ) !== false ) {
4772 list( $type, $charset ) = explode( ';', $content );
4773 $content_type = trim( $type );
4775 $content_type = trim( $content );
4781 // Set Content-Type if we don't have a content-type from the input headers.
4782 if ( ! isset( $content_type ) ) {
4783 $content_type = 'text/plain';
4786 /** This filter is documented in wp-includes/pluggable.php */
4787 $content_type = apply_filters( 'wp_mail_content_type', $content_type );
4789 if ( 'text/html' === $content_type ) {
4790 $mail['message'] = wp_staticize_emoji( $mail['message'] );
4797 * Shorten a URL, to be used as link text.
4800 * @since 4.4.0 Moved to wp-includes/formatting.php from wp-admin/includes/misc.php and added $length param.
4802 * @param string $url URL to shorten.
4803 * @param int $length Optional. Maximum length of the shortened URL. Default 35 characters.
4804 * @return string Shortened URL.
4806 function url_shorten( $url, $length = 35 ) {
4807 $stripped = str_replace( array( 'https://', 'http://', 'www.' ), '', $url );
4808 $short_url = untrailingslashit( $stripped );
4810 if ( strlen( $short_url ) > $length ) {
4811 $short_url = substr( $short_url, 0, $length - 3 ) . '…';