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.
236 _wptexturize_pushpop_element( $curl, $no_texturize_tags_stack, $no_texturize_tags );
239 } elseif ( '' === trim( $curl ) ) {
240 // This is a newline between delimiters. Performance improves when we check this.
243 } elseif ( '[' === $first && $found_shortcodes && 1 === preg_match( '/^' . $shortcode_regex . '$/', $curl ) ) {
244 // This is a shortcode delimiter.
246 if ( '[[' !== substr( $curl, 0, 2 ) && ']]' !== substr( $curl, -2 ) ) {
247 // Looks like a normal shortcode.
248 _wptexturize_pushpop_element( $curl, $no_texturize_shortcodes_stack, $no_texturize_shortcodes );
250 // Looks like an escaped shortcode.
254 } elseif ( empty( $no_texturize_shortcodes_stack ) && empty( $no_texturize_tags_stack ) ) {
255 // This is neither a delimiter, nor is this content inside of no_texturize pairs. Do texturize.
257 $curl = str_replace( $static_characters, $static_replacements, $curl );
259 if ( false !== strpos( $curl, "'" ) ) {
260 $curl = preg_replace( $dynamic_characters['apos'], $dynamic_replacements['apos'], $curl );
261 $curl = wptexturize_primes( $curl, "'", $prime, $open_sq_flag, $closing_single_quote );
262 $curl = str_replace( $apos_flag, $apos, $curl );
263 $curl = str_replace( $open_sq_flag, $opening_single_quote, $curl );
265 if ( false !== strpos( $curl, '"' ) ) {
266 $curl = preg_replace( $dynamic_characters['quote'], $dynamic_replacements['quote'], $curl );
267 $curl = wptexturize_primes( $curl, '"', $double_prime, $open_q_flag, $closing_quote );
268 $curl = str_replace( $open_q_flag, $opening_quote, $curl );
270 if ( false !== strpos( $curl, '-' ) ) {
271 $curl = preg_replace( $dynamic_characters['dash'], $dynamic_replacements['dash'], $curl );
274 // 9x9 (times), but never 0x9999
275 if ( 1 === preg_match( '/(?<=\d)x\d/', $curl ) ) {
276 // Searching for a digit is 10 times more expensive than for the x, so we avoid doing this one!
277 $curl = preg_replace( '/\b(\d(?(?<=0)[\d\.,]+|[\d\.,]*))x(\d[\d\.,]*)\b/', '$1×$2', $curl );
280 // Replace each & with & unless it already looks like an entity.
281 $curl = preg_replace( '/&(?!#(?:\d+|x[a-f0-9]+);|[a-z1-4]{1,8};)/i', '&', $curl );
285 return implode( '', $textarr );
289 * Implements a logic tree to determine whether or not "7'." represents seven feet,
290 * then converts the special char into either a prime char or a closing quote char.
294 * @param string $haystack The plain text to be searched.
295 * @param string $needle The character to search for such as ' or ".
296 * @param string $prime The prime char to use for replacement.
297 * @param string $open_quote The opening quote char. Opening quote replacement must be
298 * accomplished already.
299 * @param string $close_quote The closing quote char to use for replacement.
300 * @return string The $haystack value after primes and quotes replacements.
302 function wptexturize_primes( $haystack, $needle, $prime, $open_quote, $close_quote ) {
303 $spaces = wp_spaces_regexp();
304 $flag = '<!--wp-prime-or-quote-->';
305 $quote_pattern = "/$needle(?=\\Z|[.,:;!?)}\\-\\]]|>|" . $spaces . ")/";
306 $prime_pattern = "/(?<=\\d)$needle/";
307 $flag_after_digit = "/(?<=\\d)$flag/";
308 $flag_no_digit = "/(?<!\\d)$flag/";
310 $sentences = explode( $open_quote, $haystack );
312 foreach ( $sentences as $key => &$sentence ) {
313 if ( false === strpos( $sentence, $needle ) ) {
315 } elseif ( 0 !== $key && 0 === substr_count( $sentence, $close_quote ) ) {
316 $sentence = preg_replace( $quote_pattern, $flag, $sentence, -1, $count );
318 // This sentence appears to have multiple closing quotes. Attempt Vulcan logic.
319 $sentence = preg_replace( $flag_no_digit, $close_quote, $sentence, -1, $count2 );
320 if ( 0 === $count2 ) {
321 // Try looking for a quote followed by a period.
322 $count2 = substr_count( $sentence, "$flag." );
324 // Assume the rightmost quote-period match is the end of quotation.
325 $pos = strrpos( $sentence, "$flag." );
327 // When all else fails, make the rightmost candidate a closing quote.
328 // This is most likely to be problematic in the context of bug #18549.
329 $pos = strrpos( $sentence, $flag );
331 $sentence = substr_replace( $sentence, $close_quote, $pos, strlen( $flag ) );
333 // Use conventional replacement on any remaining primes and quotes.
334 $sentence = preg_replace( $prime_pattern, $prime, $sentence );
335 $sentence = preg_replace( $flag_after_digit, $prime, $sentence );
336 $sentence = str_replace( $flag, $close_quote, $sentence );
337 } elseif ( 1 == $count ) {
338 // Found only one closing quote candidate, so give it priority over primes.
339 $sentence = str_replace( $flag, $close_quote, $sentence );
340 $sentence = preg_replace( $prime_pattern, $prime, $sentence );
342 // No closing quotes found. Just run primes pattern.
343 $sentence = preg_replace( $prime_pattern, $prime, $sentence );
346 $sentence = preg_replace( $prime_pattern, $prime, $sentence );
347 $sentence = preg_replace( $quote_pattern, $close_quote, $sentence );
349 if ( '"' == $needle && false !== strpos( $sentence, '"' ) ) {
350 $sentence = str_replace( '"', $close_quote, $sentence );
354 return implode( $open_quote, $sentences );
358 * Search for disabled element tags. Push element to stack on tag open and pop
361 * Assumes first char of $text is tag opening and last char is tag closing.
362 * Assumes second char of $text is optionally '/' to indicate closing as in </html>.
367 * @param string $text Text to check. Must be a tag like `<html>` or `[shortcode]`.
368 * @param array $stack List of open tag elements.
369 * @param array $disabled_elements The tag names to match against. Spaces are not allowed in tag names.
371 function _wptexturize_pushpop_element( $text, &$stack, $disabled_elements ) {
372 // Is it an opening tag or closing tag?
373 if ( '/' !== $text[1] ) {
376 } elseif ( 0 == count( $stack ) ) {
377 // Stack is empty. Just stop.
380 $opening_tag = false;
384 // Parse out the tag name.
385 $space = strpos( $text, ' ' );
386 if ( false === $space ) {
389 $space -= $name_offset;
391 $tag = substr( $text, $name_offset, $space );
393 // Handle disabled tags.
394 if ( in_array( $tag, $disabled_elements ) ) {
395 if ( $opening_tag ) {
397 * This disables texturize until we find a closing tag of our type
398 * (e.g. <pre>) even if there was invalid nesting before that
400 * Example: in the case <pre>sadsadasd</code>"baba"</pre>
401 * "baba" won't be texturize
404 array_push( $stack, $tag );
405 } elseif ( end( $stack ) == $tag ) {
412 * Replaces double line-breaks with paragraph elements.
414 * A group of regex replaces used to identify text formatted with newlines and
415 * replace double line-breaks with HTML paragraph tags. The remaining line-breaks
416 * after conversion become <<br />> tags, unless $br is set to '0' or 'false'.
420 * @param string $pee The text which has to be formatted.
421 * @param bool $br Optional. If set, this will convert all remaining line-breaks
422 * after paragraphing. Default true.
423 * @return string Text which has been converted into correct paragraph tags.
425 function wpautop( $pee, $br = true ) {
428 if ( trim($pee) === '' )
431 // Just to make things a little easier, pad the end.
435 * Pre tags shouldn't be touched by autop.
436 * Replace pre tags with placeholders and bring them back after autop.
438 if ( strpos($pee, '<pre') !== false ) {
439 $pee_parts = explode( '</pre>', $pee );
440 $last_pee = array_pop($pee_parts);
444 foreach ( $pee_parts as $pee_part ) {
445 $start = strpos($pee_part, '<pre');
448 if ( $start === false ) {
453 $name = "<pre wp-pre-tag-$i></pre>";
454 $pre_tags[$name] = substr( $pee_part, $start ) . '</pre>';
456 $pee .= substr( $pee_part, 0, $start ) . $name;
462 // Change multiple <br>s into two line breaks, which will turn into paragraphs.
463 $pee = preg_replace('|<br\s*/?>\s*<br\s*/?>|', "\n\n", $pee);
465 $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)';
467 // Add a single line break above block-level opening tags.
468 $pee = preg_replace('!(<' . $allblocks . '[\s/>])!', "\n$1", $pee);
470 // Add a double line break below block-level closing tags.
471 $pee = preg_replace('!(</' . $allblocks . '>)!', "$1\n\n", $pee);
473 // Standardize newline characters to "\n".
474 $pee = str_replace(array("\r\n", "\r"), "\n", $pee);
476 // Find newlines in all elements and add placeholders.
477 $pee = wp_replace_in_html_tags( $pee, array( "\n" => " <!-- wpnl --> " ) );
479 // Collapse line breaks before and after <option> elements so they don't get autop'd.
480 if ( strpos( $pee, '<option' ) !== false ) {
481 $pee = preg_replace( '|\s*<option|', '<option', $pee );
482 $pee = preg_replace( '|</option>\s*|', '</option>', $pee );
486 * Collapse line breaks inside <object> elements, before <param> and <embed> elements
487 * so they don't get autop'd.
489 if ( strpos( $pee, '</object>' ) !== false ) {
490 $pee = preg_replace( '|(<object[^>]*>)\s*|', '$1', $pee );
491 $pee = preg_replace( '|\s*</object>|', '</object>', $pee );
492 $pee = preg_replace( '%\s*(</?(?:param|embed)[^>]*>)\s*%', '$1', $pee );
496 * Collapse line breaks inside <audio> and <video> elements,
497 * before and after <source> and <track> elements.
499 if ( strpos( $pee, '<source' ) !== false || strpos( $pee, '<track' ) !== false ) {
500 $pee = preg_replace( '%([<\[](?:audio|video)[^>\]]*[>\]])\s*%', '$1', $pee );
501 $pee = preg_replace( '%\s*([<\[]/(?:audio|video)[>\]])%', '$1', $pee );
502 $pee = preg_replace( '%\s*(<(?:source|track)[^>]*>)\s*%', '$1', $pee );
505 // Remove more than two contiguous line breaks.
506 $pee = preg_replace("/\n\n+/", "\n\n", $pee);
508 // Split up the contents into an array of strings, separated by double line breaks.
509 $pees = preg_split('/\n\s*\n/', $pee, -1, PREG_SPLIT_NO_EMPTY);
511 // Reset $pee prior to rebuilding.
514 // Rebuild the content as a string, wrapping every bit with a <p>.
515 foreach ( $pees as $tinkle ) {
516 $pee .= '<p>' . trim($tinkle, "\n") . "</p>\n";
519 // Under certain strange conditions it could create a P of entirely whitespace.
520 $pee = preg_replace('|<p>\s*</p>|', '', $pee);
522 // Add a closing <p> inside <div>, <address>, or <form> tag if missing.
523 $pee = preg_replace('!<p>([^<]+)</(div|address|form)>!', "<p>$1</p></$2>", $pee);
525 // If an opening or closing block element tag is wrapped in a <p>, unwrap it.
526 $pee = preg_replace('!<p>\s*(</?' . $allblocks . '[^>]*>)\s*</p>!', "$1", $pee);
528 // In some cases <li> may get wrapped in <p>, fix them.
529 $pee = preg_replace("|<p>(<li.+?)</p>|", "$1", $pee);
531 // If a <blockquote> is wrapped with a <p>, move it inside the <blockquote>.
532 $pee = preg_replace('|<p><blockquote([^>]*)>|i', "<blockquote$1><p>", $pee);
533 $pee = str_replace('</blockquote></p>', '</p></blockquote>', $pee);
535 // If an opening or closing block element tag is preceded by an opening <p> tag, remove it.
536 $pee = preg_replace('!<p>\s*(</?' . $allblocks . '[^>]*>)!', "$1", $pee);
538 // If an opening or closing block element tag is followed by a closing <p> tag, remove it.
539 $pee = preg_replace('!(</?' . $allblocks . '[^>]*>)\s*</p>!', "$1", $pee);
541 // Optionally insert line breaks.
543 // Replace newlines that shouldn't be touched with a placeholder.
544 $pee = preg_replace_callback('/<(script|style).*?<\/\\1>/s', '_autop_newline_preservation_helper', $pee);
547 $pee = str_replace( array( '<br>', '<br/>' ), '<br />', $pee );
549 // Replace any new line characters that aren't preceded by a <br /> with a <br />.
550 $pee = preg_replace('|(?<!<br />)\s*\n|', "<br />\n", $pee);
552 // Replace newline placeholders with newlines.
553 $pee = str_replace('<WPPreserveNewline />', "\n", $pee);
556 // If a <br /> tag is after an opening or closing block tag, remove it.
557 $pee = preg_replace('!(</?' . $allblocks . '[^>]*>)\s*<br />!', "$1", $pee);
559 // If a <br /> tag is before a subset of opening or closing block tags, remove it.
560 $pee = preg_replace('!<br />(\s*</?(?:p|li|div|dl|dd|dt|th|pre|td|ul|ol)[^>]*>)!', '$1', $pee);
561 $pee = preg_replace( "|\n</p>$|", '</p>', $pee );
563 // Replace placeholder <pre> tags with their original content.
564 if ( !empty($pre_tags) )
565 $pee = str_replace(array_keys($pre_tags), array_values($pre_tags), $pee);
567 // Restore newlines in all elements.
568 if ( false !== strpos( $pee, '<!-- wpnl -->' ) ) {
569 $pee = str_replace( array( ' <!-- wpnl --> ', '<!-- wpnl -->' ), "\n", $pee );
576 * Separate HTML elements and comments from the text.
580 * @param string $input The text which has to be formatted.
581 * @return array The formatted text.
583 function wp_html_split( $input ) {
584 return preg_split( get_html_split_regex(), $input, -1, PREG_SPLIT_DELIM_CAPTURE );
588 * Retrieve the regular expression for an HTML element.
592 * @return string The regular expression
594 function get_html_split_regex() {
597 if ( ! isset( $regex ) ) {
599 '!' // Start of comment, after the <.
600 . '(?:' // Unroll the loop: Consume everything until --> is found.
601 . '-(?!->)' // Dash not followed by end of comment.
602 . '[^\-]*+' // Consume non-dashes.
603 . ')*+' // Loop possessively.
604 . '(?:-->)?'; // End of comment. If not found, match all input.
607 '!\[CDATA\[' // Start of comment, after the <.
608 . '[^\]]*+' // Consume non-].
609 . '(?:' // Unroll the loop: Consume everything until ]]> is found.
610 . '](?!]>)' // One ] not followed by end of comment.
611 . '[^\]]*+' // Consume non-].
612 . ')*+' // Loop possessively.
613 . '(?:]]>)?'; // End of comment. If not found, match all input.
616 '(?=' // Is the element escaped?
621 . '(?(?=!-)' // If yes, which type?
628 '/(' // Capture the entire match.
629 . '<' // Find start of element.
630 . '(?' // Conditional expression follows.
631 . $escaped // Find end of escaped element.
632 . '|' // ... else ...
633 . '[^>]*>?' // Find end of normal element.
642 * Retrieve the combined regular expression for HTML and shortcodes.
646 * @internal This function will be removed in 4.5.0 per Shortcode API Roadmap.
649 * @param string $shortcode_regex The result from _get_wptexturize_shortcode_regex(). Optional.
650 * @return string The regular expression
652 function _get_wptexturize_split_regex( $shortcode_regex = '' ) {
655 if ( ! isset( $html_regex ) ) {
657 '!' // Start of comment, after the <.
658 . '(?:' // Unroll the loop: Consume everything until --> is found.
659 . '-(?!->)' // Dash not followed by end of comment.
660 . '[^\-]*+' // Consume non-dashes.
661 . ')*+' // Loop possessively.
662 . '(?:-->)?'; // End of comment. If not found, match all input.
664 $html_regex = // Needs replaced with wp_html_split() per Shortcode API Roadmap.
665 '<' // Find start of element.
666 . '(?(?=!--)' // Is this a comment?
667 . $comment_regex // Find end of comment.
669 . '[^>]*>?' // Find end of element. If not found, match all input.
673 if ( empty( $shortcode_regex ) ) {
674 $regex = '/(' . $html_regex . ')/';
676 $regex = '/(' . $html_regex . '|' . $shortcode_regex . ')/';
683 * Retrieve the regular expression for shortcodes.
687 * @internal This function will be removed in 4.5.0 per Shortcode API Roadmap.
690 * @param array $tagnames List of shortcodes to find.
691 * @return string The regular expression
693 function _get_wptexturize_shortcode_regex( $tagnames ) {
694 $tagregexp = join( '|', array_map( 'preg_quote', $tagnames ) );
695 $tagregexp = "(?:$tagregexp)(?=[\\s\\]\\/])"; // Excerpt of get_shortcode_regex().
697 '\[' // Find start of shortcode.
698 . '[\/\[]?' // Shortcodes may begin with [/ or [[
699 . $tagregexp // Only match registered shortcodes, because performance.
701 . '[^\[\]<>]+' // Shortcodes do not contain other shortcodes. Quantifier critical.
703 . '<[^\[\]>]*>' // HTML elements permitted. Prevents matching ] before >.
704 . ')*+' // Possessive critical.
705 . '\]' // Find end of shortcode.
706 . '\]?'; // Shortcodes may end with ]]
712 * Replace characters or phrases within HTML elements only.
716 * @param string $haystack The text which has to be formatted.
717 * @param array $replace_pairs In the form array('from' => 'to', ...).
718 * @return string The formatted text.
720 function wp_replace_in_html_tags( $haystack, $replace_pairs ) {
721 // Find all elements.
722 $textarr = wp_html_split( $haystack );
725 // Optimize when searching for one item.
726 if ( 1 === count( $replace_pairs ) ) {
727 // Extract $needle and $replace.
728 foreach ( $replace_pairs as $needle => $replace );
730 // Loop through delimiters (elements) only.
731 for ( $i = 1, $c = count( $textarr ); $i < $c; $i += 2 ) {
732 if ( false !== strpos( $textarr[$i], $needle ) ) {
733 $textarr[$i] = str_replace( $needle, $replace, $textarr[$i] );
738 // Extract all $needles.
739 $needles = array_keys( $replace_pairs );
741 // Loop through delimiters (elements) only.
742 for ( $i = 1, $c = count( $textarr ); $i < $c; $i += 2 ) {
743 foreach ( $needles as $needle ) {
744 if ( false !== strpos( $textarr[$i], $needle ) ) {
745 $textarr[$i] = strtr( $textarr[$i], $replace_pairs );
747 // After one strtr() break out of the foreach loop and look at next element.
755 $haystack = implode( $textarr );
762 * Newline preservation help function for wpautop
767 * @param array $matches preg_replace_callback matches array
770 function _autop_newline_preservation_helper( $matches ) {
771 return str_replace( "\n", "<WPPreserveNewline />", $matches[0] );
775 * Don't auto-p wrap shortcodes that stand alone
777 * Ensures that shortcodes are not wrapped in `<p>...</p>`.
781 * @global array $shortcode_tags
783 * @param string $pee The content.
784 * @return string The filtered content.
786 function shortcode_unautop( $pee ) {
787 global $shortcode_tags;
789 if ( empty( $shortcode_tags ) || !is_array( $shortcode_tags ) ) {
793 $tagregexp = join( '|', array_map( 'preg_quote', array_keys( $shortcode_tags ) ) );
794 $spaces = wp_spaces_regexp();
798 . '<p>' // Opening paragraph
799 . '(?:' . $spaces . ')*+' // Optional leading whitespace
800 . '(' // 1: The shortcode
801 . '\\[' // Opening bracket
802 . "($tagregexp)" // 2: Shortcode name
803 . '(?![\\w-])' // Not followed by word character or hyphen
804 // Unroll the loop: Inside the opening shortcode tag
805 . '[^\\]\\/]*' // Not a closing bracket or forward slash
807 . '\\/(?!\\])' // A forward slash not followed by a closing bracket
808 . '[^\\]\\/]*' // Not a closing bracket or forward slash
811 . '\\/\\]' // Self closing tag and closing bracket
813 . '\\]' // Closing bracket
814 . '(?:' // Unroll the loop: Optionally, anything between the opening and closing shortcode tags
815 . '[^\\[]*+' // Not an opening bracket
817 . '\\[(?!\\/\\2\\])' // An opening bracket not followed by the closing shortcode tag
818 . '[^\\[]*+' // Not an opening bracket
820 . '\\[\\/\\2\\]' // Closing shortcode tag
824 . '(?:' . $spaces . ')*+' // optional trailing whitespace
825 . '<\\/p>' // closing paragraph
828 return preg_replace( $pattern, '$1', $pee );
832 * Checks to see if a string is utf8 encoded.
834 * NOTE: This function checks for 5-Byte sequences, UTF8
835 * has Bytes Sequences with a maximum length of 4.
837 * @author bmorel at ssi dot fr (modified)
840 * @param string $str The string to be checked
841 * @return bool True if $str fits a UTF-8 model, false otherwise.
843 function seems_utf8( $str ) {
844 mbstring_binary_safe_encoding();
845 $length = strlen($str);
846 reset_mbstring_encoding();
847 for ($i=0; $i < $length; $i++) {
849 if ($c < 0x80) $n = 0; // 0bbbbbbb
850 elseif (($c & 0xE0) == 0xC0) $n=1; // 110bbbbb
851 elseif (($c & 0xF0) == 0xE0) $n=2; // 1110bbbb
852 elseif (($c & 0xF8) == 0xF0) $n=3; // 11110bbb
853 elseif (($c & 0xFC) == 0xF8) $n=4; // 111110bb
854 elseif (($c & 0xFE) == 0xFC) $n=5; // 1111110b
855 else return false; // Does not match any model
856 for ($j=0; $j<$n; $j++) { // n bytes matching 10bbbbbb follow ?
857 if ((++$i == $length) || ((ord($str[$i]) & 0xC0) != 0x80))
865 * Converts a number of special characters into their HTML entities.
867 * Specifically deals with: &, <, >, ", and '.
869 * $quote_style can be set to ENT_COMPAT to encode " to
870 * ", or ENT_QUOTES to do both. Default is ENT_NOQUOTES where no quotes are encoded.
875 * @staticvar string $_charset
877 * @param string $string The text which is to be encoded.
878 * @param int|string $quote_style Optional. Converts double quotes if set to ENT_COMPAT,
879 * both single and double if set to ENT_QUOTES or none if set to ENT_NOQUOTES.
880 * Also compatible with old values; converting single quotes if set to 'single',
881 * double if set to 'double' or both if otherwise set.
882 * Default is ENT_NOQUOTES.
883 * @param string $charset Optional. The character encoding of the string. Default is false.
884 * @param bool $double_encode Optional. Whether to encode existing html entities. Default is false.
885 * @return string The encoded text with HTML entities.
887 function _wp_specialchars( $string, $quote_style = ENT_NOQUOTES, $charset = false, $double_encode = false ) {
888 $string = (string) $string;
890 if ( 0 === strlen( $string ) )
893 // Don't bother if there are no specialchars - saves some processing
894 if ( ! preg_match( '/[&<>"\']/', $string ) )
897 // Account for the previous behaviour of the function when the $quote_style is not an accepted value
898 if ( empty( $quote_style ) )
899 $quote_style = ENT_NOQUOTES;
900 elseif ( ! in_array( $quote_style, array( 0, 2, 3, 'single', 'double' ), true ) )
901 $quote_style = ENT_QUOTES;
903 // Store the site charset as a static to avoid multiple calls to wp_load_alloptions()
905 static $_charset = null;
906 if ( ! isset( $_charset ) ) {
907 $alloptions = wp_load_alloptions();
908 $_charset = isset( $alloptions['blog_charset'] ) ? $alloptions['blog_charset'] : '';
910 $charset = $_charset;
913 if ( in_array( $charset, array( 'utf8', 'utf-8', 'UTF8' ) ) )
916 $_quote_style = $quote_style;
918 if ( $quote_style === 'double' ) {
919 $quote_style = ENT_COMPAT;
920 $_quote_style = ENT_COMPAT;
921 } elseif ( $quote_style === 'single' ) {
922 $quote_style = ENT_NOQUOTES;
925 if ( ! $double_encode ) {
926 // Guarantee every &entity; is valid, convert &garbage; into &garbage;
927 // This is required for PHP < 5.4.0 because ENT_HTML401 flag is unavailable.
928 $string = wp_kses_normalize_entities( $string );
931 $string = @htmlspecialchars( $string, $quote_style, $charset, $double_encode );
933 // Backwards compatibility
934 if ( 'single' === $_quote_style )
935 $string = str_replace( "'", ''', $string );
941 * Converts a number of HTML entities into their special characters.
943 * Specifically deals with: &, <, >, ", and '.
945 * $quote_style can be set to ENT_COMPAT to decode " entities,
946 * or ENT_QUOTES to do both " and '. Default is ENT_NOQUOTES where no quotes are decoded.
950 * @param string $string The text which is to be decoded.
951 * @param string|int $quote_style Optional. Converts double quotes if set to ENT_COMPAT,
952 * both single and double if set to ENT_QUOTES or
953 * none if set to ENT_NOQUOTES.
954 * Also compatible with old _wp_specialchars() values;
955 * converting single quotes if set to 'single',
956 * double if set to 'double' or both if otherwise set.
957 * Default is ENT_NOQUOTES.
958 * @return string The decoded text without HTML entities.
960 function wp_specialchars_decode( $string, $quote_style = ENT_NOQUOTES ) {
961 $string = (string) $string;
963 if ( 0 === strlen( $string ) ) {
967 // Don't bother if there are no entities - saves a lot of processing
968 if ( strpos( $string, '&' ) === false ) {
972 // Match the previous behaviour of _wp_specialchars() when the $quote_style is not an accepted value
973 if ( empty( $quote_style ) ) {
974 $quote_style = ENT_NOQUOTES;
975 } elseif ( !in_array( $quote_style, array( 0, 2, 3, 'single', 'double' ), true ) ) {
976 $quote_style = ENT_QUOTES;
979 // More complete than get_html_translation_table( HTML_SPECIALCHARS )
980 $single = array( ''' => '\'', ''' => '\'' );
981 $single_preg = array( '/�*39;/' => ''', '/�*27;/i' => ''' );
982 $double = array( '"' => '"', '"' => '"', '"' => '"' );
983 $double_preg = array( '/�*34;/' => '"', '/�*22;/i' => '"' );
984 $others = array( '<' => '<', '<' => '<', '>' => '>', '>' => '>', '&' => '&', '&' => '&', '&' => '&' );
985 $others_preg = array( '/�*60;/' => '<', '/�*62;/' => '>', '/�*38;/' => '&', '/�*26;/i' => '&' );
987 if ( $quote_style === ENT_QUOTES ) {
988 $translation = array_merge( $single, $double, $others );
989 $translation_preg = array_merge( $single_preg, $double_preg, $others_preg );
990 } elseif ( $quote_style === ENT_COMPAT || $quote_style === 'double' ) {
991 $translation = array_merge( $double, $others );
992 $translation_preg = array_merge( $double_preg, $others_preg );
993 } elseif ( $quote_style === 'single' ) {
994 $translation = array_merge( $single, $others );
995 $translation_preg = array_merge( $single_preg, $others_preg );
996 } elseif ( $quote_style === ENT_NOQUOTES ) {
997 $translation = $others;
998 $translation_preg = $others_preg;
1001 // Remove zero padding on numeric entities
1002 $string = preg_replace( array_keys( $translation_preg ), array_values( $translation_preg ), $string );
1004 // Replace characters according to translation table
1005 return strtr( $string, $translation );
1009 * Checks for invalid UTF8 in a string.
1013 * @staticvar bool $is_utf8
1014 * @staticvar bool $utf8_pcre
1016 * @param string $string The text which is to be checked.
1017 * @param bool $strip Optional. Whether to attempt to strip out invalid UTF8. Default is false.
1018 * @return string The checked text.
1020 function wp_check_invalid_utf8( $string, $strip = false ) {
1021 $string = (string) $string;
1023 if ( 0 === strlen( $string ) ) {
1027 // Store the site charset as a static to avoid multiple calls to get_option()
1028 static $is_utf8 = null;
1029 if ( ! isset( $is_utf8 ) ) {
1030 $is_utf8 = in_array( get_option( 'blog_charset' ), array( 'utf8', 'utf-8', 'UTF8', 'UTF-8' ) );
1036 // Check for support for utf8 in the installed PCRE library once and store the result in a static
1037 static $utf8_pcre = null;
1038 if ( ! isset( $utf8_pcre ) ) {
1039 $utf8_pcre = @preg_match( '/^./u', 'a' );
1041 // We can't demand utf8 in the PCRE installation, so just return the string in those cases
1042 if ( !$utf8_pcre ) {
1046 // preg_match fails when it encounters invalid UTF8 in $string
1047 if ( 1 === @preg_match( '/^./us', $string ) ) {
1051 // Attempt to strip the bad chars if requested (not recommended)
1052 if ( $strip && function_exists( 'iconv' ) ) {
1053 return iconv( 'utf-8', 'utf-8', $string );
1060 * Encode the Unicode values to be used in the URI.
1064 * @param string $utf8_string
1065 * @param int $length Max length of the string
1066 * @return string String with Unicode encoded for URI.
1068 function utf8_uri_encode( $utf8_string, $length = 0 ) {
1072 $unicode_length = 0;
1074 mbstring_binary_safe_encoding();
1075 $string_length = strlen( $utf8_string );
1076 reset_mbstring_encoding();
1078 for ($i = 0; $i < $string_length; $i++ ) {
1080 $value = ord( $utf8_string[ $i ] );
1082 if ( $value < 128 ) {
1083 if ( $length && ( $unicode_length >= $length ) )
1085 $unicode .= chr($value);
1088 if ( count( $values ) == 0 ) {
1089 if ( $value < 224 ) {
1091 } elseif ( $value < 240 ) {
1100 if ( $length && ( $unicode_length + ($num_octets * 3) ) > $length )
1102 if ( count( $values ) == $num_octets ) {
1103 for ( $j = 0; $j < $num_octets; $j++ ) {
1104 $unicode .= '%' . dechex( $values[ $j ] );
1107 $unicode_length += $num_octets * 3;
1119 * Converts all accent characters to ASCII characters.
1121 * If there are no accent characters, then the string given is just returned.
1125 * @param string $string Text that might have accent characters
1126 * @return string Filtered string with replaced "nice" characters.
1128 function remove_accents( $string ) {
1129 if ( !preg_match('/[\x80-\xff]/', $string) )
1132 if (seems_utf8($string)) {
1134 // Decompositions for Latin-1 Supplement
1135 chr(194).chr(170) => 'a', chr(194).chr(186) => 'o',
1136 chr(195).chr(128) => 'A', chr(195).chr(129) => 'A',
1137 chr(195).chr(130) => 'A', chr(195).chr(131) => 'A',
1138 chr(195).chr(132) => 'A', chr(195).chr(133) => 'A',
1139 chr(195).chr(134) => 'AE',chr(195).chr(135) => 'C',
1140 chr(195).chr(136) => 'E', chr(195).chr(137) => 'E',
1141 chr(195).chr(138) => 'E', chr(195).chr(139) => 'E',
1142 chr(195).chr(140) => 'I', chr(195).chr(141) => 'I',
1143 chr(195).chr(142) => 'I', chr(195).chr(143) => 'I',
1144 chr(195).chr(144) => 'D', chr(195).chr(145) => 'N',
1145 chr(195).chr(146) => 'O', chr(195).chr(147) => 'O',
1146 chr(195).chr(148) => 'O', chr(195).chr(149) => 'O',
1147 chr(195).chr(150) => 'O', chr(195).chr(153) => 'U',
1148 chr(195).chr(154) => 'U', chr(195).chr(155) => 'U',
1149 chr(195).chr(156) => 'U', chr(195).chr(157) => 'Y',
1150 chr(195).chr(158) => 'TH',chr(195).chr(159) => 's',
1151 chr(195).chr(160) => 'a', chr(195).chr(161) => 'a',
1152 chr(195).chr(162) => 'a', chr(195).chr(163) => 'a',
1153 chr(195).chr(164) => 'a', chr(195).chr(165) => 'a',
1154 chr(195).chr(166) => 'ae',chr(195).chr(167) => 'c',
1155 chr(195).chr(168) => 'e', chr(195).chr(169) => 'e',
1156 chr(195).chr(170) => 'e', chr(195).chr(171) => 'e',
1157 chr(195).chr(172) => 'i', chr(195).chr(173) => 'i',
1158 chr(195).chr(174) => 'i', chr(195).chr(175) => 'i',
1159 chr(195).chr(176) => 'd', chr(195).chr(177) => 'n',
1160 chr(195).chr(178) => 'o', chr(195).chr(179) => 'o',
1161 chr(195).chr(180) => 'o', chr(195).chr(181) => 'o',
1162 chr(195).chr(182) => 'o', chr(195).chr(184) => 'o',
1163 chr(195).chr(185) => 'u', chr(195).chr(186) => 'u',
1164 chr(195).chr(187) => 'u', chr(195).chr(188) => 'u',
1165 chr(195).chr(189) => 'y', chr(195).chr(190) => 'th',
1166 chr(195).chr(191) => 'y', chr(195).chr(152) => 'O',
1167 // Decompositions for Latin Extended-A
1168 chr(196).chr(128) => 'A', chr(196).chr(129) => 'a',
1169 chr(196).chr(130) => 'A', chr(196).chr(131) => 'a',
1170 chr(196).chr(132) => 'A', chr(196).chr(133) => 'a',
1171 chr(196).chr(134) => 'C', chr(196).chr(135) => 'c',
1172 chr(196).chr(136) => 'C', chr(196).chr(137) => 'c',
1173 chr(196).chr(138) => 'C', chr(196).chr(139) => 'c',
1174 chr(196).chr(140) => 'C', chr(196).chr(141) => 'c',
1175 chr(196).chr(142) => 'D', chr(196).chr(143) => 'd',
1176 chr(196).chr(144) => 'D', chr(196).chr(145) => 'd',
1177 chr(196).chr(146) => 'E', chr(196).chr(147) => 'e',
1178 chr(196).chr(148) => 'E', chr(196).chr(149) => 'e',
1179 chr(196).chr(150) => 'E', chr(196).chr(151) => 'e',
1180 chr(196).chr(152) => 'E', chr(196).chr(153) => 'e',
1181 chr(196).chr(154) => 'E', chr(196).chr(155) => 'e',
1182 chr(196).chr(156) => 'G', chr(196).chr(157) => 'g',
1183 chr(196).chr(158) => 'G', chr(196).chr(159) => 'g',
1184 chr(196).chr(160) => 'G', chr(196).chr(161) => 'g',
1185 chr(196).chr(162) => 'G', chr(196).chr(163) => 'g',
1186 chr(196).chr(164) => 'H', chr(196).chr(165) => 'h',
1187 chr(196).chr(166) => 'H', chr(196).chr(167) => 'h',
1188 chr(196).chr(168) => 'I', chr(196).chr(169) => 'i',
1189 chr(196).chr(170) => 'I', chr(196).chr(171) => 'i',
1190 chr(196).chr(172) => 'I', chr(196).chr(173) => 'i',
1191 chr(196).chr(174) => 'I', chr(196).chr(175) => 'i',
1192 chr(196).chr(176) => 'I', chr(196).chr(177) => 'i',
1193 chr(196).chr(178) => 'IJ',chr(196).chr(179) => 'ij',
1194 chr(196).chr(180) => 'J', chr(196).chr(181) => 'j',
1195 chr(196).chr(182) => 'K', chr(196).chr(183) => 'k',
1196 chr(196).chr(184) => 'k', chr(196).chr(185) => 'L',
1197 chr(196).chr(186) => 'l', chr(196).chr(187) => 'L',
1198 chr(196).chr(188) => 'l', chr(196).chr(189) => 'L',
1199 chr(196).chr(190) => 'l', chr(196).chr(191) => 'L',
1200 chr(197).chr(128) => 'l', chr(197).chr(129) => 'L',
1201 chr(197).chr(130) => 'l', chr(197).chr(131) => 'N',
1202 chr(197).chr(132) => 'n', chr(197).chr(133) => 'N',
1203 chr(197).chr(134) => 'n', chr(197).chr(135) => 'N',
1204 chr(197).chr(136) => 'n', chr(197).chr(137) => 'N',
1205 chr(197).chr(138) => 'n', chr(197).chr(139) => 'N',
1206 chr(197).chr(140) => 'O', chr(197).chr(141) => 'o',
1207 chr(197).chr(142) => 'O', chr(197).chr(143) => 'o',
1208 chr(197).chr(144) => 'O', chr(197).chr(145) => 'o',
1209 chr(197).chr(146) => 'OE',chr(197).chr(147) => 'oe',
1210 chr(197).chr(148) => 'R',chr(197).chr(149) => 'r',
1211 chr(197).chr(150) => 'R',chr(197).chr(151) => 'r',
1212 chr(197).chr(152) => 'R',chr(197).chr(153) => 'r',
1213 chr(197).chr(154) => 'S',chr(197).chr(155) => 's',
1214 chr(197).chr(156) => 'S',chr(197).chr(157) => 's',
1215 chr(197).chr(158) => 'S',chr(197).chr(159) => 's',
1216 chr(197).chr(160) => 'S', chr(197).chr(161) => 's',
1217 chr(197).chr(162) => 'T', chr(197).chr(163) => 't',
1218 chr(197).chr(164) => 'T', chr(197).chr(165) => 't',
1219 chr(197).chr(166) => 'T', chr(197).chr(167) => 't',
1220 chr(197).chr(168) => 'U', chr(197).chr(169) => 'u',
1221 chr(197).chr(170) => 'U', chr(197).chr(171) => 'u',
1222 chr(197).chr(172) => 'U', chr(197).chr(173) => 'u',
1223 chr(197).chr(174) => 'U', chr(197).chr(175) => 'u',
1224 chr(197).chr(176) => 'U', chr(197).chr(177) => 'u',
1225 chr(197).chr(178) => 'U', chr(197).chr(179) => 'u',
1226 chr(197).chr(180) => 'W', chr(197).chr(181) => 'w',
1227 chr(197).chr(182) => 'Y', chr(197).chr(183) => 'y',
1228 chr(197).chr(184) => 'Y', chr(197).chr(185) => 'Z',
1229 chr(197).chr(186) => 'z', chr(197).chr(187) => 'Z',
1230 chr(197).chr(188) => 'z', chr(197).chr(189) => 'Z',
1231 chr(197).chr(190) => 'z', chr(197).chr(191) => 's',
1232 // Decompositions for Latin Extended-B
1233 chr(200).chr(152) => 'S', chr(200).chr(153) => 's',
1234 chr(200).chr(154) => 'T', chr(200).chr(155) => 't',
1236 chr(226).chr(130).chr(172) => 'E',
1238 chr(194).chr(163) => '',
1239 // Vowels with diacritic (Vietnamese)
1241 chr(198).chr(160) => 'O', chr(198).chr(161) => 'o',
1242 chr(198).chr(175) => 'U', chr(198).chr(176) => 'u',
1244 chr(225).chr(186).chr(166) => 'A', chr(225).chr(186).chr(167) => 'a',
1245 chr(225).chr(186).chr(176) => 'A', chr(225).chr(186).chr(177) => 'a',
1246 chr(225).chr(187).chr(128) => 'E', chr(225).chr(187).chr(129) => 'e',
1247 chr(225).chr(187).chr(146) => 'O', chr(225).chr(187).chr(147) => 'o',
1248 chr(225).chr(187).chr(156) => 'O', chr(225).chr(187).chr(157) => 'o',
1249 chr(225).chr(187).chr(170) => 'U', chr(225).chr(187).chr(171) => 'u',
1250 chr(225).chr(187).chr(178) => 'Y', chr(225).chr(187).chr(179) => 'y',
1252 chr(225).chr(186).chr(162) => 'A', chr(225).chr(186).chr(163) => 'a',
1253 chr(225).chr(186).chr(168) => 'A', chr(225).chr(186).chr(169) => 'a',
1254 chr(225).chr(186).chr(178) => 'A', chr(225).chr(186).chr(179) => 'a',
1255 chr(225).chr(186).chr(186) => 'E', chr(225).chr(186).chr(187) => 'e',
1256 chr(225).chr(187).chr(130) => 'E', chr(225).chr(187).chr(131) => 'e',
1257 chr(225).chr(187).chr(136) => 'I', chr(225).chr(187).chr(137) => 'i',
1258 chr(225).chr(187).chr(142) => 'O', chr(225).chr(187).chr(143) => 'o',
1259 chr(225).chr(187).chr(148) => 'O', chr(225).chr(187).chr(149) => 'o',
1260 chr(225).chr(187).chr(158) => 'O', chr(225).chr(187).chr(159) => 'o',
1261 chr(225).chr(187).chr(166) => 'U', chr(225).chr(187).chr(167) => 'u',
1262 chr(225).chr(187).chr(172) => 'U', chr(225).chr(187).chr(173) => 'u',
1263 chr(225).chr(187).chr(182) => 'Y', chr(225).chr(187).chr(183) => 'y',
1265 chr(225).chr(186).chr(170) => 'A', chr(225).chr(186).chr(171) => 'a',
1266 chr(225).chr(186).chr(180) => 'A', chr(225).chr(186).chr(181) => 'a',
1267 chr(225).chr(186).chr(188) => 'E', chr(225).chr(186).chr(189) => 'e',
1268 chr(225).chr(187).chr(132) => 'E', chr(225).chr(187).chr(133) => 'e',
1269 chr(225).chr(187).chr(150) => 'O', chr(225).chr(187).chr(151) => 'o',
1270 chr(225).chr(187).chr(160) => 'O', chr(225).chr(187).chr(161) => 'o',
1271 chr(225).chr(187).chr(174) => 'U', chr(225).chr(187).chr(175) => 'u',
1272 chr(225).chr(187).chr(184) => 'Y', chr(225).chr(187).chr(185) => 'y',
1274 chr(225).chr(186).chr(164) => 'A', chr(225).chr(186).chr(165) => 'a',
1275 chr(225).chr(186).chr(174) => 'A', chr(225).chr(186).chr(175) => 'a',
1276 chr(225).chr(186).chr(190) => 'E', chr(225).chr(186).chr(191) => 'e',
1277 chr(225).chr(187).chr(144) => 'O', chr(225).chr(187).chr(145) => 'o',
1278 chr(225).chr(187).chr(154) => 'O', chr(225).chr(187).chr(155) => 'o',
1279 chr(225).chr(187).chr(168) => 'U', chr(225).chr(187).chr(169) => 'u',
1281 chr(225).chr(186).chr(160) => 'A', chr(225).chr(186).chr(161) => 'a',
1282 chr(225).chr(186).chr(172) => 'A', chr(225).chr(186).chr(173) => 'a',
1283 chr(225).chr(186).chr(182) => 'A', chr(225).chr(186).chr(183) => 'a',
1284 chr(225).chr(186).chr(184) => 'E', chr(225).chr(186).chr(185) => 'e',
1285 chr(225).chr(187).chr(134) => 'E', chr(225).chr(187).chr(135) => 'e',
1286 chr(225).chr(187).chr(138) => 'I', chr(225).chr(187).chr(139) => 'i',
1287 chr(225).chr(187).chr(140) => 'O', chr(225).chr(187).chr(141) => 'o',
1288 chr(225).chr(187).chr(152) => 'O', chr(225).chr(187).chr(153) => 'o',
1289 chr(225).chr(187).chr(162) => 'O', chr(225).chr(187).chr(163) => 'o',
1290 chr(225).chr(187).chr(164) => 'U', chr(225).chr(187).chr(165) => 'u',
1291 chr(225).chr(187).chr(176) => 'U', chr(225).chr(187).chr(177) => 'u',
1292 chr(225).chr(187).chr(180) => 'Y', chr(225).chr(187).chr(181) => 'y',
1293 // Vowels with diacritic (Chinese, Hanyu Pinyin)
1294 chr(201).chr(145) => 'a',
1296 chr(199).chr(149) => 'U', chr(199).chr(150) => 'u',
1298 chr(199).chr(151) => 'U', chr(199).chr(152) => 'u',
1300 chr(199).chr(141) => 'A', chr(199).chr(142) => 'a',
1301 chr(199).chr(143) => 'I', chr(199).chr(144) => 'i',
1302 chr(199).chr(145) => 'O', chr(199).chr(146) => 'o',
1303 chr(199).chr(147) => 'U', chr(199).chr(148) => 'u',
1304 chr(199).chr(153) => 'U', chr(199).chr(154) => 'u',
1306 chr(199).chr(155) => 'U', chr(199).chr(156) => 'u',
1309 // Used for locale-specific rules
1310 $locale = get_locale();
1312 if ( 'de_DE' == $locale || 'de_DE_formal' == $locale ) {
1313 $chars[ chr(195).chr(132) ] = 'Ae';
1314 $chars[ chr(195).chr(164) ] = 'ae';
1315 $chars[ chr(195).chr(150) ] = 'Oe';
1316 $chars[ chr(195).chr(182) ] = 'oe';
1317 $chars[ chr(195).chr(156) ] = 'Ue';
1318 $chars[ chr(195).chr(188) ] = 'ue';
1319 $chars[ chr(195).chr(159) ] = 'ss';
1320 } elseif ( 'da_DK' === $locale ) {
1321 $chars[ chr(195).chr(134) ] = 'Ae';
1322 $chars[ chr(195).chr(166) ] = 'ae';
1323 $chars[ chr(195).chr(152) ] = 'Oe';
1324 $chars[ chr(195).chr(184) ] = 'oe';
1325 $chars[ chr(195).chr(133) ] = 'Aa';
1326 $chars[ chr(195).chr(165) ] = 'aa';
1329 $string = strtr($string, $chars);
1332 // Assume ISO-8859-1 if not UTF-8
1333 $chars['in'] = chr(128).chr(131).chr(138).chr(142).chr(154).chr(158)
1334 .chr(159).chr(162).chr(165).chr(181).chr(192).chr(193).chr(194)
1335 .chr(195).chr(196).chr(197).chr(199).chr(200).chr(201).chr(202)
1336 .chr(203).chr(204).chr(205).chr(206).chr(207).chr(209).chr(210)
1337 .chr(211).chr(212).chr(213).chr(214).chr(216).chr(217).chr(218)
1338 .chr(219).chr(220).chr(221).chr(224).chr(225).chr(226).chr(227)
1339 .chr(228).chr(229).chr(231).chr(232).chr(233).chr(234).chr(235)
1340 .chr(236).chr(237).chr(238).chr(239).chr(241).chr(242).chr(243)
1341 .chr(244).chr(245).chr(246).chr(248).chr(249).chr(250).chr(251)
1342 .chr(252).chr(253).chr(255);
1344 $chars['out'] = "EfSZszYcYuAAAAAACEEEEIIIINOOOOOOUUUUYaaaaaaceeeeiiiinoooooouuuuyy";
1346 $string = strtr($string, $chars['in'], $chars['out']);
1347 $double_chars = array();
1348 $double_chars['in'] = array(chr(140), chr(156), chr(198), chr(208), chr(222), chr(223), chr(230), chr(240), chr(254));
1349 $double_chars['out'] = array('OE', 'oe', 'AE', 'DH', 'TH', 'ss', 'ae', 'dh', 'th');
1350 $string = str_replace($double_chars['in'], $double_chars['out'], $string);
1357 * Sanitizes a filename, replacing whitespace with dashes.
1359 * Removes special characters that are illegal in filenames on certain
1360 * operating systems and special characters requiring special escaping
1361 * to manipulate at the command line. Replaces spaces and consecutive
1362 * dashes with a single dash. Trims period, dash and underscore from beginning
1363 * and end of filename.
1367 * @param string $filename The filename to be sanitized
1368 * @return string The sanitized filename
1370 function sanitize_file_name( $filename ) {
1371 $filename_raw = $filename;
1372 $special_chars = array("?", "[", "]", "/", "\\", "=", "<", ">", ":", ";", ",", "'", "\"", "&", "$", "#", "*", "(", ")", "|", "~", "`", "!", "{", "}", "%", "+", chr(0));
1374 * Filter the list of characters to remove from a filename.
1378 * @param array $special_chars Characters to remove.
1379 * @param string $filename_raw Filename as it was passed into sanitize_file_name().
1381 $special_chars = apply_filters( 'sanitize_file_name_chars', $special_chars, $filename_raw );
1382 $filename = preg_replace( "#\x{00a0}#siu", ' ', $filename );
1383 $filename = str_replace( $special_chars, '', $filename );
1384 $filename = str_replace( array( '%20', '+' ), '-', $filename );
1385 $filename = preg_replace( '/[\r\n\t -]+/', '-', $filename );
1386 $filename = trim( $filename, '.-_' );
1388 // Split the filename into a base and extension[s]
1389 $parts = explode('.', $filename);
1391 // Return if only one extension
1392 if ( count( $parts ) <= 2 ) {
1394 * Filter a sanitized filename string.
1398 * @param string $filename Sanitized filename.
1399 * @param string $filename_raw The filename prior to sanitization.
1401 return apply_filters( 'sanitize_file_name', $filename, $filename_raw );
1404 // Process multiple extensions
1405 $filename = array_shift($parts);
1406 $extension = array_pop($parts);
1407 $mimes = get_allowed_mime_types();
1410 * Loop over any intermediate extensions. Postfix them with a trailing underscore
1411 * if they are a 2 - 5 character long alpha string not in the extension whitelist.
1413 foreach ( (array) $parts as $part) {
1414 $filename .= '.' . $part;
1416 if ( preg_match("/^[a-zA-Z]{2,5}\d?$/", $part) ) {
1418 foreach ( $mimes as $ext_preg => $mime_match ) {
1419 $ext_preg = '!^(' . $ext_preg . ')$!i';
1420 if ( preg_match( $ext_preg, $part ) ) {
1429 $filename .= '.' . $extension;
1430 /** This filter is documented in wp-includes/formatting.php */
1431 return apply_filters('sanitize_file_name', $filename, $filename_raw);
1435 * Sanitizes a username, stripping out unsafe characters.
1437 * Removes tags, octets, entities, and if strict is enabled, will only keep
1438 * alphanumeric, _, space, ., -, @. After sanitizing, it passes the username,
1439 * raw username (the username in the parameter), and the value of $strict as
1440 * parameters for the 'sanitize_user' filter.
1444 * @param string $username The username to be sanitized.
1445 * @param bool $strict If set limits $username to specific characters. Default false.
1446 * @return string The sanitized username, after passing through filters.
1448 function sanitize_user( $username, $strict = false ) {
1449 $raw_username = $username;
1450 $username = wp_strip_all_tags( $username );
1451 $username = remove_accents( $username );
1453 $username = preg_replace( '|%([a-fA-F0-9][a-fA-F0-9])|', '', $username );
1454 $username = preg_replace( '/&.+?;/', '', $username ); // Kill entities
1456 // If strict, reduce to ASCII for max portability.
1458 $username = preg_replace( '|[^a-z0-9 _.\-@]|i', '', $username );
1460 $username = trim( $username );
1461 // Consolidate contiguous whitespace
1462 $username = preg_replace( '|\s+|', ' ', $username );
1465 * Filter a sanitized username string.
1469 * @param string $username Sanitized username.
1470 * @param string $raw_username The username prior to sanitization.
1471 * @param bool $strict Whether to limit the sanitization to specific characters. Default false.
1473 return apply_filters( 'sanitize_user', $username, $raw_username, $strict );
1477 * Sanitizes a string key.
1479 * Keys are used as internal identifiers. Lowercase alphanumeric characters, dashes and underscores are allowed.
1483 * @param string $key String key
1484 * @return string Sanitized key
1486 function sanitize_key( $key ) {
1488 $key = strtolower( $key );
1489 $key = preg_replace( '/[^a-z0-9_\-]/', '', $key );
1492 * Filter a sanitized key string.
1496 * @param string $key Sanitized key.
1497 * @param string $raw_key The key prior to sanitization.
1499 return apply_filters( 'sanitize_key', $key, $raw_key );
1503 * Sanitizes a title, or returns a fallback title.
1505 * Specifically, HTML and PHP tags are stripped. Further actions can be added
1506 * via the plugin API. If $title is empty and $fallback_title is set, the latter
1511 * @param string $title The string to be sanitized.
1512 * @param string $fallback_title Optional. A title to use if $title is empty.
1513 * @param string $context Optional. The operation for which the string is sanitized
1514 * @return string The sanitized string.
1516 function sanitize_title( $title, $fallback_title = '', $context = 'save' ) {
1517 $raw_title = $title;
1519 if ( 'save' == $context )
1520 $title = remove_accents($title);
1523 * Filter a sanitized title string.
1527 * @param string $title Sanitized title.
1528 * @param string $raw_title The title prior to sanitization.
1529 * @param string $context The context for which the title is being sanitized.
1531 $title = apply_filters( 'sanitize_title', $title, $raw_title, $context );
1533 if ( '' === $title || false === $title )
1534 $title = $fallback_title;
1540 * Sanitizes a title with the 'query' context.
1542 * Used for querying the database for a value from URL.
1546 * @param string $title The string to be sanitized.
1547 * @return string The sanitized string.
1549 function sanitize_title_for_query( $title ) {
1550 return sanitize_title( $title, '', 'query' );
1554 * Sanitizes a title, replacing whitespace and a few other characters with dashes.
1556 * Limits the output to alphanumeric characters, underscore (_) and dash (-).
1557 * Whitespace becomes a dash.
1561 * @param string $title The title to be sanitized.
1562 * @param string $raw_title Optional. Not used.
1563 * @param string $context Optional. The operation for which the string is sanitized.
1564 * @return string The sanitized title.
1566 function sanitize_title_with_dashes( $title, $raw_title = '', $context = 'display' ) {
1567 $title = strip_tags($title);
1568 // Preserve escaped octets.
1569 $title = preg_replace('|%([a-fA-F0-9][a-fA-F0-9])|', '---$1---', $title);
1570 // Remove percent signs that are not part of an octet.
1571 $title = str_replace('%', '', $title);
1573 $title = preg_replace('|---([a-fA-F0-9][a-fA-F0-9])---|', '%$1', $title);
1575 if (seems_utf8($title)) {
1576 if (function_exists('mb_strtolower')) {
1577 $title = mb_strtolower($title, 'UTF-8');
1579 $title = utf8_uri_encode($title, 200);
1582 $title = strtolower($title);
1583 $title = preg_replace('/&.+?;/', '', $title); // kill entities
1584 $title = str_replace('.', '-', $title);
1586 if ( 'save' == $context ) {
1587 // Convert nbsp, ndash and mdash to hyphens
1588 $title = str_replace( array( '%c2%a0', '%e2%80%93', '%e2%80%94' ), '-', $title );
1590 // Strip these characters entirely
1591 $title = str_replace( array(
1595 '%c2%ab', '%c2%bb', '%e2%80%b9', '%e2%80%ba',
1597 '%e2%80%98', '%e2%80%99', '%e2%80%9c', '%e2%80%9d',
1598 '%e2%80%9a', '%e2%80%9b', '%e2%80%9e', '%e2%80%9f',
1599 // copy, reg, deg, hellip and trade
1600 '%c2%a9', '%c2%ae', '%c2%b0', '%e2%80%a6', '%e2%84%a2',
1602 '%c2%b4', '%cb%8a', '%cc%81', '%cd%81',
1603 // grave accent, macron, caron
1604 '%cc%80', '%cc%84', '%cc%8c',
1607 // Convert times to x
1608 $title = str_replace( '%c3%97', 'x', $title );
1611 $title = preg_replace('/[^%a-z0-9 _-]/', '', $title);
1612 $title = preg_replace('/\s+/', '-', $title);
1613 $title = preg_replace('|-+|', '-', $title);
1614 $title = trim($title, '-');
1620 * Ensures a string is a valid SQL 'order by' clause.
1622 * Accepts one or more columns, with or without a sort order (ASC / DESC).
1623 * e.g. 'column_1', 'column_1, column_2', 'column_1 ASC, column_2 DESC' etc.
1625 * Also accepts 'RAND()'.
1629 * @param string $orderby Order by clause to be validated.
1630 * @return string|false Returns $orderby if valid, false otherwise.
1632 function sanitize_sql_orderby( $orderby ) {
1633 if ( preg_match( '/^\s*(([a-z0-9_]+|`[a-z0-9_]+`)(\s+(ASC|DESC))?\s*(,\s*(?=[a-z0-9_`])|$))+$/i', $orderby ) || preg_match( '/^\s*RAND\(\s*\)\s*$/i', $orderby ) ) {
1640 * Sanitizes an HTML classname to ensure it only contains valid characters.
1642 * Strips the string down to A-Z,a-z,0-9,_,-. If this results in an empty
1643 * string then it will return the alternative value supplied.
1645 * @todo Expand to support the full range of CDATA that a class attribute can contain.
1649 * @param string $class The classname to be sanitized
1650 * @param string $fallback Optional. The value to return if the sanitization ends up as an empty string.
1651 * Defaults to an empty string.
1652 * @return string The sanitized value
1654 function sanitize_html_class( $class, $fallback = '' ) {
1655 //Strip out any % encoded octets
1656 $sanitized = preg_replace( '|%[a-fA-F0-9][a-fA-F0-9]|', '', $class );
1658 //Limit to A-Z,a-z,0-9,_,-
1659 $sanitized = preg_replace( '/[^A-Za-z0-9_-]/', '', $sanitized );
1661 if ( '' == $sanitized && $fallback ) {
1662 return sanitize_html_class( $fallback );
1665 * Filter a sanitized HTML class string.
1669 * @param string $sanitized The sanitized HTML class.
1670 * @param string $class HTML class before sanitization.
1671 * @param string $fallback The fallback string.
1673 return apply_filters( 'sanitize_html_class', $sanitized, $class, $fallback );
1677 * Converts lone & characters into `&` (a.k.a. `&`)
1681 * @param string $content String of characters to be converted.
1682 * @param string $deprecated Not used.
1683 * @return string Converted string.
1685 function convert_chars( $content, $deprecated = '' ) {
1686 if ( ! empty( $deprecated ) ) {
1687 _deprecated_argument( __FUNCTION__, '0.71' );
1690 if ( strpos( $content, '&' ) !== false ) {
1691 $content = preg_replace( '/&([^#])(?![a-z1-4]{1,8};)/i', '&$1', $content );
1698 * Converts invalid Unicode references range to valid range.
1702 * @param string $content String with entities that need converting.
1703 * @return string Converted string.
1705 function convert_invalid_entities( $content ) {
1706 $wp_htmltranswinuni = array(
1707 '€' => '€', // the Euro sign
1709 '‚' => '‚', // these are Windows CP1252 specific characters
1710 'ƒ' => 'ƒ', // they would look weird on non-Windows browsers
1711 '„' => '„',
1712 '…' => '…',
1713 '†' => '†',
1714 '‡' => '‡',
1715 'ˆ' => 'ˆ',
1716 '‰' => '‰',
1717 'Š' => 'Š',
1718 '‹' => '‹',
1719 'Œ' => 'Œ',
1721 'Ž' => 'Ž',
1724 '‘' => '‘',
1725 '’' => '’',
1726 '“' => '“',
1727 '”' => '”',
1728 '•' => '•',
1729 '–' => '–',
1730 '—' => '—',
1731 '˜' => '˜',
1732 '™' => '™',
1733 'š' => 'š',
1734 '›' => '›',
1735 'œ' => 'œ',
1737 'ž' => 'ž',
1738 'Ÿ' => 'Ÿ'
1741 if ( strpos( $content, '' ) !== false ) {
1742 $content = strtr( $content, $wp_htmltranswinuni );
1749 * Balances tags if forced to, or if the 'use_balanceTags' option is set to true.
1753 * @param string $text Text to be balanced
1754 * @param bool $force If true, forces balancing, ignoring the value of the option. Default false.
1755 * @return string Balanced text
1757 function balanceTags( $text, $force = false ) {
1758 if ( $force || get_option('use_balanceTags') == 1 ) {
1759 return force_balance_tags( $text );
1766 * Balances tags of string using a modified stack.
1770 * @author Leonard Lin <leonard@acm.org>
1772 * @copyright November 4, 2001
1774 * @todo Make better - change loop condition to $text in 1.2
1775 * @internal Modified by Scott Reilly (coffee2code) 02 Aug 2004
1776 * 1.1 Fixed handling of append/stack pop order of end text
1777 * Added Cleaning Hooks
1780 * @param string $text Text to be balanced.
1781 * @return string Balanced text.
1783 function force_balance_tags( $text ) {
1784 $tagstack = array();
1788 // Known single-entity/self-closing tags
1789 $single_tags = array( 'area', 'base', 'basefont', 'br', 'col', 'command', 'embed', 'frame', 'hr', 'img', 'input', 'isindex', 'link', 'meta', 'param', 'source' );
1790 // Tags that can be immediately nested within themselves
1791 $nestable_tags = array( 'blockquote', 'div', 'object', 'q', 'span' );
1793 // WP bug fix for comments - in case you REALLY meant to type '< !--'
1794 $text = str_replace('< !--', '< !--', $text);
1795 // WP bug fix for LOVE <3 (and other situations with '<' before a number)
1796 $text = preg_replace('#<([0-9]{1})#', '<$1', $text);
1798 while ( preg_match("/<(\/?[\w:]*)\s*([^>]*)>/", $text, $regex) ) {
1799 $newtext .= $tagqueue;
1801 $i = strpos($text, $regex[0]);
1802 $l = strlen($regex[0]);
1804 // clear the shifter
1807 if ( isset($regex[1][0]) && '/' == $regex[1][0] ) { // End Tag
1808 $tag = strtolower(substr($regex[1],1));
1809 // if too many closing tags
1810 if ( $stacksize <= 0 ) {
1812 // or close to be safe $tag = '/' . $tag;
1814 // if stacktop value = tag close value then pop
1815 elseif ( $tagstack[$stacksize - 1] == $tag ) { // found closing tag
1816 $tag = '</' . $tag . '>'; // Close Tag
1818 array_pop( $tagstack );
1820 } else { // closing tag not at top, search for it
1821 for ( $j = $stacksize-1; $j >= 0; $j-- ) {
1822 if ( $tagstack[$j] == $tag ) {
1823 // add tag to tagqueue
1824 for ( $k = $stacksize-1; $k >= $j; $k--) {
1825 $tagqueue .= '</' . array_pop( $tagstack ) . '>';
1833 } else { // Begin Tag
1834 $tag = strtolower($regex[1]);
1838 // If it's an empty tag "< >", do nothing
1842 // ElseIf it presents itself as a self-closing tag...
1843 elseif ( substr( $regex[2], -1 ) == '/' ) {
1844 // ...but it isn't a known single-entity self-closing tag, then don't let it be treated as such and
1845 // immediately close it with a closing tag (the tag will encapsulate no text as a result)
1846 if ( ! in_array( $tag, $single_tags ) )
1847 $regex[2] = trim( substr( $regex[2], 0, -1 ) ) . "></$tag";
1849 // ElseIf it's a known single-entity tag but it doesn't close itself, do so
1850 elseif ( in_array($tag, $single_tags) ) {
1853 // Else it's not a single-entity tag
1855 // If the top of the stack is the same as the tag we want to push, close previous tag
1856 if ( $stacksize > 0 && !in_array($tag, $nestable_tags) && $tagstack[$stacksize - 1] == $tag ) {
1857 $tagqueue = '</' . array_pop( $tagstack ) . '>';
1860 $stacksize = array_push( $tagstack, $tag );
1864 $attributes = $regex[2];
1865 if ( ! empty( $attributes ) && $attributes[0] != '>' )
1866 $attributes = ' ' . $attributes;
1868 $tag = '<' . $tag . $attributes . '>';
1869 //If already queuing a close tag, then put this tag on, too
1870 if ( !empty($tagqueue) ) {
1875 $newtext .= substr($text, 0, $i) . $tag;
1876 $text = substr($text, $i + $l);
1880 $newtext .= $tagqueue;
1882 // Add Remaining text
1886 while( $x = array_pop($tagstack) )
1887 $newtext .= '</' . $x . '>'; // Add remaining tags to close
1889 // WP fix for the bug with HTML comments
1890 $newtext = str_replace("< !--","<!--",$newtext);
1891 $newtext = str_replace("< !--","< !--",$newtext);
1897 * Acts on text which is about to be edited.
1899 * The $content is run through esc_textarea(), which uses htmlspecialchars()
1900 * to convert special characters to HTML entities. If $richedit is set to true,
1901 * it is simply a holder for the 'format_to_edit' filter.
1904 * @since 4.4.0 The `$richedit` parameter was renamed to `$rich_text` for clarity.
1906 * @param string $content The text about to be edited.
1907 * @param bool $rich_text Optional. Whether `$content` should be considered rich text,
1908 * in which case it would not be passed through esc_textarea().
1910 * @return string The text after the filter (and possibly htmlspecialchars()) has been run.
1912 function format_to_edit( $content, $rich_text = false ) {
1914 * Filter the text to be formatted for editing.
1918 * @param string $content The text, prior to formatting for editing.
1920 $content = apply_filters( 'format_to_edit', $content );
1922 $content = esc_textarea( $content );
1927 * Add leading zeros when necessary.
1929 * If you set the threshold to '4' and the number is '10', then you will get
1930 * back '0010'. If you set the threshold to '4' and the number is '5000', then you
1931 * will get back '5000'.
1933 * Uses sprintf to append the amount of zeros based on the $threshold parameter
1934 * and the size of the number. If the number is large enough, then no zeros will
1939 * @param int $number Number to append zeros to if not greater than threshold.
1940 * @param int $threshold Digit places number needs to be to not have zeros added.
1941 * @return string Adds leading zeros to number if needed.
1943 function zeroise( $number, $threshold ) {
1944 return sprintf( '%0' . $threshold . 's', $number );
1948 * Adds backslashes before letters and before a number at the start of a string.
1952 * @param string $string Value to which backslashes will be added.
1953 * @return string String with backslashes inserted.
1955 function backslashit( $string ) {
1956 if ( isset( $string[0] ) && $string[0] >= '0' && $string[0] <= '9' )
1957 $string = '\\\\' . $string;
1958 return addcslashes( $string, 'A..Za..z' );
1962 * Appends a trailing slash.
1964 * Will remove trailing forward and backslashes if it exists already before adding
1965 * a trailing forward slash. This prevents double slashing a string or path.
1967 * The primary use of this is for paths and thus should be used for paths. It is
1968 * not restricted to paths and offers no specific path support.
1972 * @param string $string What to add the trailing slash to.
1973 * @return string String with trailing slash added.
1975 function trailingslashit( $string ) {
1976 return untrailingslashit( $string ) . '/';
1980 * Removes trailing forward slashes and backslashes if they exist.
1982 * The primary use of this is for paths and thus should be used for paths. It is
1983 * not restricted to paths and offers no specific path support.
1987 * @param string $string What to remove the trailing slashes from.
1988 * @return string String without the trailing slashes.
1990 function untrailingslashit( $string ) {
1991 return rtrim( $string, '/\\' );
1995 * Adds slashes to escape strings.
1997 * Slashes will first be removed if magic_quotes_gpc is set, see {@link
1998 * http://www.php.net/magic_quotes} for more details.
2002 * @param string $gpc The string returned from HTTP request data.
2003 * @return string Returns a string escaped with slashes.
2005 function addslashes_gpc($gpc) {
2006 if ( get_magic_quotes_gpc() )
2007 $gpc = stripslashes($gpc);
2009 return wp_slash($gpc);
2013 * Navigates through an array, object, or scalar, and removes slashes from the values.
2017 * @param mixed $value The value to be stripped.
2018 * @return mixed Stripped value.
2020 function stripslashes_deep( $value ) {
2021 return map_deep( $value, 'stripslashes_from_strings_only' );
2025 * Callback function for `stripslashes_deep()` which strips slashes from strings.
2029 * @param mixed $value The array or string to be stripped.
2030 * @return mixed $value The stripped value.
2032 function stripslashes_from_strings_only( $value ) {
2033 return is_string( $value ) ? stripslashes( $value ) : $value;
2037 * Navigates through an array, object, or scalar, and encodes the values to be used in a URL.
2041 * @param mixed $value The array or string to be encoded.
2042 * @return mixed $value The encoded value.
2044 function urlencode_deep( $value ) {
2045 return map_deep( $value, 'urlencode' );
2049 * Navigates through an array, object, or scalar, and raw-encodes the values to be used in a URL.
2053 * @param mixed $value The array or string to be encoded.
2054 * @return mixed $value The encoded value.
2056 function rawurlencode_deep( $value ) {
2057 return map_deep( $value, 'rawurlencode' );
2061 * Navigates through an array, object, or scalar, and decodes URL-encoded values
2065 * @param mixed $value The array or string to be decoded.
2066 * @return mixed $value The decoded value.
2068 function urldecode_deep( $value ) {
2069 return map_deep( $value, 'urldecode' );
2073 * Converts email addresses characters to HTML entities to block spam bots.
2077 * @param string $email_address Email address.
2078 * @param int $hex_encoding Optional. Set to 1 to enable hex encoding.
2079 * @return string Converted email address.
2081 function antispambot( $email_address, $hex_encoding = 0 ) {
2082 $email_no_spam_address = '';
2083 for ( $i = 0, $len = strlen( $email_address ); $i < $len; $i++ ) {
2084 $j = rand( 0, 1 + $hex_encoding );
2086 $email_no_spam_address .= '&#' . ord( $email_address[$i] ) . ';';
2087 } elseif ( $j == 1 ) {
2088 $email_no_spam_address .= $email_address[$i];
2089 } elseif ( $j == 2 ) {
2090 $email_no_spam_address .= '%' . zeroise( dechex( ord( $email_address[$i] ) ), 2 );
2094 return str_replace( '@', '@', $email_no_spam_address );
2098 * Callback to convert URI match to HTML A element.
2100 * This function was backported from 2.5.0 to 2.3.2. Regex callback for {@link
2101 * make_clickable()}.
2106 * @param array $matches Single Regex Match.
2107 * @return string HTML A element with URI address.
2109 function _make_url_clickable_cb( $matches ) {
2112 if ( ')' == $matches[3] && strpos( $url, '(' ) ) {
2113 // If the trailing character is a closing parethesis, and the URL has an opening parenthesis in it, add the closing parenthesis to the URL.
2114 // Then we can let the parenthesis balancer do its thing below.
2115 $url .= $matches[3];
2118 $suffix = $matches[3];
2121 // Include parentheses in the URL only if paired
2122 while ( substr_count( $url, '(' ) < substr_count( $url, ')' ) ) {
2123 $suffix = strrchr( $url, ')' ) . $suffix;
2124 $url = substr( $url, 0, strrpos( $url, ')' ) );
2127 $url = esc_url($url);
2131 return $matches[1] . "<a href=\"$url\" rel=\"nofollow\">$url</a>" . $suffix;
2135 * Callback to convert URL match to HTML A element.
2137 * This function was backported from 2.5.0 to 2.3.2. Regex callback for {@link
2138 * make_clickable()}.
2143 * @param array $matches Single Regex Match.
2144 * @return string HTML A element with URL address.
2146 function _make_web_ftp_clickable_cb( $matches ) {
2148 $dest = $matches[2];
2149 $dest = 'http://' . $dest;
2151 // removed trailing [.,;:)] from URL
2152 if ( in_array( substr($dest, -1), array('.', ',', ';', ':', ')') ) === true ) {
2153 $ret = substr($dest, -1);
2154 $dest = substr($dest, 0, strlen($dest)-1);
2157 $dest = esc_url($dest);
2161 return $matches[1] . "<a href=\"$dest\" rel=\"nofollow\">$dest</a>$ret";
2165 * Callback to convert email address match to HTML A element.
2167 * This function was backported from 2.5.0 to 2.3.2. Regex callback for {@link
2168 * make_clickable()}.
2173 * @param array $matches Single Regex Match.
2174 * @return string HTML A element with email address.
2176 function _make_email_clickable_cb( $matches ) {
2177 $email = $matches[2] . '@' . $matches[3];
2178 return $matches[1] . "<a href=\"mailto:$email\">$email</a>";
2182 * Convert plaintext URI to HTML links.
2184 * Converts URI, www and ftp, and email addresses. Finishes by fixing links
2189 * @param string $text Content to convert URIs.
2190 * @return string Content with converted URIs.
2192 function make_clickable( $text ) {
2194 $textarr = preg_split( '/(<[^<>]+>)/', $text, -1, PREG_SPLIT_DELIM_CAPTURE ); // split out HTML tags
2195 $nested_code_pre = 0; // Keep track of how many levels link is nested inside <pre> or <code>
2196 foreach ( $textarr as $piece ) {
2198 if ( preg_match( '|^<code[\s>]|i', $piece ) || preg_match( '|^<pre[\s>]|i', $piece ) )
2200 elseif ( ( '</code>' === strtolower( $piece ) || '</pre>' === strtolower( $piece ) ) && $nested_code_pre )
2203 if ( $nested_code_pre || empty( $piece ) || ( $piece[0] === '<' && ! preg_match( '|^<\s*[\w]{1,20}+://|', $piece ) ) ) {
2208 // Long strings might contain expensive edge cases ...
2209 if ( 10000 < strlen( $piece ) ) {
2211 foreach ( _split_str_by_whitespace( $piece, 2100 ) as $chunk ) { // 2100: Extra room for scheme and leading and trailing paretheses
2212 if ( 2101 < strlen( $chunk ) ) {
2213 $r .= $chunk; // Too big, no whitespace: bail.
2215 $r .= make_clickable( $chunk );
2219 $ret = " $piece "; // Pad with whitespace to simplify the regexes
2222 ([\\s(<.,;:!?]) # 1: Leading whitespace, or punctuation
2224 [\\w]{1,20}+:// # Scheme and hier-part prefix
2225 (?=\S{1,2000}\s) # Limit to URLs less than about 2000 characters long
2226 [\\w\\x80-\\xff#%\\~/@\\[\\]*(+=&$-]*+ # Non-punctuation URL character
2227 (?: # Unroll the Loop: Only allow puctuation URL character if followed by a non-punctuation URL character
2228 [\'.,;:!?)] # Punctuation URL character
2229 [\\w\\x80-\\xff#%\\~/@\\[\\]*(+=&$-]++ # Non-punctuation URL character
2232 (\)?) # 3: Trailing closing parenthesis (for parethesis balancing post processing)
2233 ~xS'; // The regex is a non-anchored pattern and does not have a single fixed starting character.
2234 // Tell PCRE to spend more time optimizing since, when used on a page load, it will probably be used several times.
2236 $ret = preg_replace_callback( $url_clickable, '_make_url_clickable_cb', $ret );
2238 $ret = preg_replace_callback( '#([\s>])((www|ftp)\.[\w\\x80-\\xff\#$%&~/.\-;:=,?@\[\]+]+)#is', '_make_web_ftp_clickable_cb', $ret );
2239 $ret = preg_replace_callback( '#([\s>])([.0-9a-z_+-]+)@(([0-9a-z-]+\.)+[0-9a-z]{2,})#i', '_make_email_clickable_cb', $ret );
2241 $ret = substr( $ret, 1, -1 ); // Remove our whitespace padding.
2246 // Cleanup of accidental links within links
2247 return preg_replace( '#(<a([ \r\n\t]+[^>]+?>|>))<a [^>]+?>([^>]+?)</a></a>#i', "$1$3</a>", $r );
2251 * Breaks a string into chunks by splitting at whitespace characters.
2252 * The length of each returned chunk is as close to the specified length goal as possible,
2253 * with the caveat that each chunk includes its trailing delimiter.
2254 * Chunks longer than the goal are guaranteed to not have any inner whitespace.
2256 * Joining the returned chunks with empty delimiters reconstructs the input string losslessly.
2258 * Input string must have no null characters (or eventual transformations on output chunks must not care about null characters)
2260 * _split_str_by_whitespace( "1234 67890 1234 67890a cd 1234 890 123456789 1234567890a 45678 1 3 5 7 90 ", 10 ) ==
2262 * 0 => '1234 67890 ', // 11 characters: Perfect split
2263 * 1 => '1234 ', // 5 characters: '1234 67890a' was too long
2264 * 2 => '67890a cd ', // 10 characters: '67890a cd 1234' was too long
2265 * 3 => '1234 890 ', // 11 characters: Perfect split
2266 * 4 => '123456789 ', // 10 characters: '123456789 1234567890a' was too long
2267 * 5 => '1234567890a ', // 12 characters: Too long, but no inner whitespace on which to split
2268 * 6 => ' 45678 ', // 11 characters: Perfect split
2269 * 7 => '1 3 5 7 90 ', // 11 characters: End of $string
2275 * @param string $string The string to split.
2276 * @param int $goal The desired chunk length.
2277 * @return array Numeric array of chunks.
2279 function _split_str_by_whitespace( $string, $goal ) {
2282 $string_nullspace = strtr( $string, "\r\n\t\v\f ", "\000\000\000\000\000\000" );
2284 while ( $goal < strlen( $string_nullspace ) ) {
2285 $pos = strrpos( substr( $string_nullspace, 0, $goal + 1 ), "\000" );
2287 if ( false === $pos ) {
2288 $pos = strpos( $string_nullspace, "\000", $goal + 1 );
2289 if ( false === $pos ) {
2294 $chunks[] = substr( $string, 0, $pos + 1 );
2295 $string = substr( $string, $pos + 1 );
2296 $string_nullspace = substr( $string_nullspace, $pos + 1 );
2300 $chunks[] = $string;
2307 * Adds rel nofollow string to all HTML A elements in content.
2311 * @param string $text Content that may contain HTML A elements.
2312 * @return string Converted content.
2314 function wp_rel_nofollow( $text ) {
2315 // This is a pre save filter, so text is already escaped.
2316 $text = stripslashes($text);
2317 $text = preg_replace_callback('|<a (.+?)>|i', 'wp_rel_nofollow_callback', $text);
2318 return wp_slash( $text );
2322 * Callback to add rel=nofollow string to HTML A element.
2324 * Will remove already existing rel="nofollow" and rel='nofollow' from the
2325 * string to prevent from invalidating (X)HTML.
2329 * @param array $matches Single Match
2330 * @return string HTML A Element with rel nofollow.
2332 function wp_rel_nofollow_callback( $matches ) {
2333 $text = $matches[1];
2334 $atts = shortcode_parse_atts( $matches[1] );
2336 if ( ! empty( $atts['rel'] ) ) {
2337 $parts = array_map( 'trim', explode( ' ', $atts['rel'] ) );
2338 if ( false === array_search( 'nofollow', $parts ) ) {
2339 $parts[] = 'nofollow';
2341 $rel = implode( ' ', $parts );
2342 unset( $atts['rel'] );
2345 foreach ( $atts as $name => $value ) {
2346 $html .= "{$name}=\"$value\" ";
2348 $text = trim( $html );
2350 return "<a $text rel=\"$rel\">";
2354 * Convert one smiley code to the icon graphic file equivalent.
2356 * Callback handler for {@link convert_smilies()}.
2357 * Looks up one smiley code in the $wpsmiliestrans global array and returns an
2358 * `<img>` string for that smiley.
2362 * @global array $wpsmiliestrans
2364 * @param array $matches Single match. Smiley code to convert to image.
2365 * @return string Image string for smiley.
2367 function translate_smiley( $matches ) {
2368 global $wpsmiliestrans;
2370 if ( count( $matches ) == 0 )
2373 $smiley = trim( reset( $matches ) );
2374 $img = $wpsmiliestrans[ $smiley ];
2377 $ext = preg_match( '/\.([^.]+)$/', $img, $matches ) ? strtolower( $matches[1] ) : false;
2378 $image_exts = array( 'jpg', 'jpeg', 'jpe', 'gif', 'png' );
2380 // Don't convert smilies that aren't images - they're probably emoji.
2381 if ( ! in_array( $ext, $image_exts ) ) {
2386 * Filter the Smiley image URL before it's used in the image element.
2390 * @param string $smiley_url URL for the smiley image.
2391 * @param string $img Filename for the smiley image.
2392 * @param string $site_url Site URL, as returned by site_url().
2394 $src_url = apply_filters( 'smilies_src', includes_url( "images/smilies/$img" ), $img, site_url() );
2396 return sprintf( '<img src="%s" alt="%s" class="wp-smiley" style="height: 1em; max-height: 1em;" />', esc_url( $src_url ), esc_attr( $smiley ) );
2400 * Convert text equivalent of smilies to images.
2402 * Will only convert smilies if the option 'use_smilies' is true and the global
2403 * used in the function isn't empty.
2407 * @global string|array $wp_smiliessearch
2409 * @param string $text Content to convert smilies from text.
2410 * @return string Converted content with text smilies replaced with images.
2412 function convert_smilies( $text ) {
2413 global $wp_smiliessearch;
2415 if ( get_option( 'use_smilies' ) && ! empty( $wp_smiliessearch ) ) {
2416 // HTML loop taken from texturize function, could possible be consolidated
2417 $textarr = preg_split( '/(<.*>)/U', $text, -1, PREG_SPLIT_DELIM_CAPTURE ); // capture the tags as well as in between
2418 $stop = count( $textarr );// loop stuff
2420 // Ignore proessing of specific tags
2421 $tags_to_ignore = 'code|pre|style|script|textarea';
2422 $ignore_block_element = '';
2424 for ( $i = 0; $i < $stop; $i++ ) {
2425 $content = $textarr[$i];
2427 // If we're in an ignore block, wait until we find its closing tag
2428 if ( '' == $ignore_block_element && preg_match( '/^<(' . $tags_to_ignore . ')>/', $content, $matches ) ) {
2429 $ignore_block_element = $matches[1];
2432 // If it's not a tag and not in ignore block
2433 if ( '' == $ignore_block_element && strlen( $content ) > 0 && '<' != $content[0] ) {
2434 $content = preg_replace_callback( $wp_smiliessearch, 'translate_smiley', $content );
2437 // did we exit ignore block
2438 if ( '' != $ignore_block_element && '</' . $ignore_block_element . '>' == $content ) {
2439 $ignore_block_element = '';
2442 $output .= $content;
2445 // return default text.
2452 * Verifies that an email is valid.
2454 * Does not grok i18n domains. Not RFC compliant.
2458 * @param string $email Email address to verify.
2459 * @param bool $deprecated Deprecated.
2460 * @return string|bool Either false or the valid email address.
2462 function is_email( $email, $deprecated = false ) {
2463 if ( ! empty( $deprecated ) )
2464 _deprecated_argument( __FUNCTION__, '3.0' );
2466 // Test for the minimum length the email can be
2467 if ( strlen( $email ) < 3 ) {
2469 * Filter whether an email address is valid.
2471 * This filter is evaluated under several different contexts, such as 'email_too_short',
2472 * 'email_no_at', 'local_invalid_chars', 'domain_period_sequence', 'domain_period_limits',
2473 * 'domain_no_periods', 'sub_hyphen_limits', 'sub_invalid_chars', or no specific context.
2477 * @param bool $is_email Whether the email address has passed the is_email() checks. Default false.
2478 * @param string $email The email address being checked.
2479 * @param string $context Context under which the email was tested.
2481 return apply_filters( 'is_email', false, $email, 'email_too_short' );
2484 // Test for an @ character after the first position
2485 if ( strpos( $email, '@', 1 ) === false ) {
2486 /** This filter is documented in wp-includes/formatting.php */
2487 return apply_filters( 'is_email', false, $email, 'email_no_at' );
2490 // Split out the local and domain parts
2491 list( $local, $domain ) = explode( '@', $email, 2 );
2494 // Test for invalid characters
2495 if ( !preg_match( '/^[a-zA-Z0-9!#$%&\'*+\/=?^_`{|}~\.-]+$/', $local ) ) {
2496 /** This filter is documented in wp-includes/formatting.php */
2497 return apply_filters( 'is_email', false, $email, 'local_invalid_chars' );
2501 // Test for sequences of periods
2502 if ( preg_match( '/\.{2,}/', $domain ) ) {
2503 /** This filter is documented in wp-includes/formatting.php */
2504 return apply_filters( 'is_email', false, $email, 'domain_period_sequence' );
2507 // Test for leading and trailing periods and whitespace
2508 if ( trim( $domain, " \t\n\r\0\x0B." ) !== $domain ) {
2509 /** This filter is documented in wp-includes/formatting.php */
2510 return apply_filters( 'is_email', false, $email, 'domain_period_limits' );
2513 // Split the domain into subs
2514 $subs = explode( '.', $domain );
2516 // Assume the domain will have at least two subs
2517 if ( 2 > count( $subs ) ) {
2518 /** This filter is documented in wp-includes/formatting.php */
2519 return apply_filters( 'is_email', false, $email, 'domain_no_periods' );
2522 // Loop through each sub
2523 foreach ( $subs as $sub ) {
2524 // Test for leading and trailing hyphens and whitespace
2525 if ( trim( $sub, " \t\n\r\0\x0B-" ) !== $sub ) {
2526 /** This filter is documented in wp-includes/formatting.php */
2527 return apply_filters( 'is_email', false, $email, 'sub_hyphen_limits' );
2530 // Test for invalid characters
2531 if ( !preg_match('/^[a-z0-9-]+$/i', $sub ) ) {
2532 /** This filter is documented in wp-includes/formatting.php */
2533 return apply_filters( 'is_email', false, $email, 'sub_invalid_chars' );
2537 // Congratulations your email made it!
2538 /** This filter is documented in wp-includes/formatting.php */
2539 return apply_filters( 'is_email', $email, $email, null );
2543 * Convert to ASCII from email subjects.
2547 * @param string $string Subject line
2548 * @return string Converted string to ASCII
2550 function wp_iso_descrambler( $string ) {
2551 /* this may only work with iso-8859-1, I'm afraid */
2552 if (!preg_match('#\=\?(.+)\?Q\?(.+)\?\=#i', $string, $matches)) {
2555 $subject = str_replace('_', ' ', $matches[2]);
2556 return preg_replace_callback( '#\=([0-9a-f]{2})#i', '_wp_iso_convert', $subject );
2561 * Helper function to convert hex encoded chars to ASCII
2566 * @param array $match The preg_replace_callback matches array
2567 * @return string Converted chars
2569 function _wp_iso_convert( $match ) {
2570 return chr( hexdec( strtolower( $match[1] ) ) );
2574 * Returns a date in the GMT equivalent.
2576 * Requires and returns a date in the Y-m-d H:i:s format. If there is a
2577 * timezone_string available, the date is assumed to be in that timezone,
2578 * otherwise it simply subtracts the value of the 'gmt_offset' option. Return
2579 * format can be overridden using the $format parameter.
2583 * @param string $string The date to be converted.
2584 * @param string $format The format string for the returned date (default is Y-m-d H:i:s)
2585 * @return string GMT version of the date provided.
2587 function get_gmt_from_date( $string, $format = 'Y-m-d H:i:s' ) {
2588 $tz = get_option( 'timezone_string' );
2590 $datetime = date_create( $string, new DateTimeZone( $tz ) );
2591 if ( ! $datetime ) {
2592 return gmdate( $format, 0 );
2594 $datetime->setTimezone( new DateTimeZone( 'UTC' ) );
2595 $string_gmt = $datetime->format( $format );
2597 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 ) ) {
2598 $datetime = strtotime( $string );
2599 if ( false === $datetime ) {
2600 return gmdate( $format, 0 );
2602 return gmdate( $format, $datetime );
2604 $string_time = gmmktime( $matches[4], $matches[5], $matches[6], $matches[2], $matches[3], $matches[1] );
2605 $string_gmt = gmdate( $format, $string_time - get_option( 'gmt_offset' ) * HOUR_IN_SECONDS );
2611 * Converts a GMT date into the correct format for the blog.
2613 * Requires and returns a date in the Y-m-d H:i:s format. If there is a
2614 * timezone_string available, the returned date is in that timezone, otherwise
2615 * it simply adds the value of gmt_offset. Return format can be overridden
2616 * using the $format parameter
2620 * @param string $string The date to be converted.
2621 * @param string $format The format string for the returned date (default is Y-m-d H:i:s)
2622 * @return string Formatted date relative to the timezone / GMT offset.
2624 function get_date_from_gmt( $string, $format = 'Y-m-d H:i:s' ) {
2625 $tz = get_option( 'timezone_string' );
2627 $datetime = date_create( $string, new DateTimeZone( 'UTC' ) );
2629 return date( $format, 0 );
2630 $datetime->setTimezone( new DateTimeZone( $tz ) );
2631 $string_localtime = $datetime->format( $format );
2633 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) )
2634 return date( $format, 0 );
2635 $string_time = gmmktime( $matches[4], $matches[5], $matches[6], $matches[2], $matches[3], $matches[1] );
2636 $string_localtime = gmdate( $format, $string_time + get_option( 'gmt_offset' ) * HOUR_IN_SECONDS );
2638 return $string_localtime;
2642 * Computes an offset in seconds from an iso8601 timezone.
2646 * @param string $timezone Either 'Z' for 0 offset or '±hhmm'.
2647 * @return int|float The offset in seconds.
2649 function iso8601_timezone_to_offset( $timezone ) {
2650 // $timezone is either 'Z' or '[+|-]hhmm'
2651 if ($timezone == 'Z') {
2654 $sign = (substr($timezone, 0, 1) == '+') ? 1 : -1;
2655 $hours = intval(substr($timezone, 1, 2));
2656 $minutes = intval(substr($timezone, 3, 4)) / 60;
2657 $offset = $sign * HOUR_IN_SECONDS * ($hours + $minutes);
2663 * Converts an iso8601 date to MySQL DateTime format used by post_date[_gmt].
2667 * @param string $date_string Date and time in ISO 8601 format {@link http://en.wikipedia.org/wiki/ISO_8601}.
2668 * @param string $timezone Optional. If set to GMT returns the time minus gmt_offset. Default is 'user'.
2669 * @return string The date and time in MySQL DateTime format - Y-m-d H:i:s.
2671 function iso8601_to_datetime( $date_string, $timezone = 'user' ) {
2672 $timezone = strtolower($timezone);
2674 if ($timezone == 'gmt') {
2676 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, $date_bits);
2678 if (!empty($date_bits[7])) { // we have a timezone, so let's compute an offset
2679 $offset = iso8601_timezone_to_offset($date_bits[7]);
2680 } else { // we don't have a timezone, so we assume user local timezone (not server's!)
2681 $offset = HOUR_IN_SECONDS * get_option('gmt_offset');
2684 $timestamp = gmmktime($date_bits[4], $date_bits[5], $date_bits[6], $date_bits[2], $date_bits[3], $date_bits[1]);
2685 $timestamp -= $offset;
2687 return gmdate('Y-m-d H:i:s', $timestamp);
2689 } elseif ($timezone == 'user') {
2690 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);
2695 * Adds a element attributes to open links in new windows.
2697 * Comment text in popup windows should be filtered through this. Right now it's
2698 * a moderately dumb function, ideally it would detect whether a target or rel
2699 * attribute was already there and adjust its actions accordingly.
2703 * @param string $text Content to replace links to open in a new window.
2704 * @return string Content that has filtered links.
2706 function popuplinks( $text ) {
2707 $text = preg_replace('/<a (.+?)>/i', "<a $1 target='_blank' rel='external'>", $text);
2712 * Strips out all characters that are not allowable in an email.
2716 * @param string $email Email address to filter.
2717 * @return string Filtered email address.
2719 function sanitize_email( $email ) {
2720 // Test for the minimum length the email can be
2721 if ( strlen( $email ) < 3 ) {
2723 * Filter a sanitized email address.
2725 * This filter is evaluated under several contexts, including 'email_too_short',
2726 * 'email_no_at', 'local_invalid_chars', 'domain_period_sequence', 'domain_period_limits',
2727 * 'domain_no_periods', 'domain_no_valid_subs', or no context.
2731 * @param string $email The sanitized email address.
2732 * @param string $email The email address, as provided to sanitize_email().
2733 * @param string $message A message to pass to the user.
2735 return apply_filters( 'sanitize_email', '', $email, 'email_too_short' );
2738 // Test for an @ character after the first position
2739 if ( strpos( $email, '@', 1 ) === false ) {
2740 /** This filter is documented in wp-includes/formatting.php */
2741 return apply_filters( 'sanitize_email', '', $email, 'email_no_at' );
2744 // Split out the local and domain parts
2745 list( $local, $domain ) = explode( '@', $email, 2 );
2748 // Test for invalid characters
2749 $local = preg_replace( '/[^a-zA-Z0-9!#$%&\'*+\/=?^_`{|}~\.-]/', '', $local );
2750 if ( '' === $local ) {
2751 /** This filter is documented in wp-includes/formatting.php */
2752 return apply_filters( 'sanitize_email', '', $email, 'local_invalid_chars' );
2756 // Test for sequences of periods
2757 $domain = preg_replace( '/\.{2,}/', '', $domain );
2758 if ( '' === $domain ) {
2759 /** This filter is documented in wp-includes/formatting.php */
2760 return apply_filters( 'sanitize_email', '', $email, 'domain_period_sequence' );
2763 // Test for leading and trailing periods and whitespace
2764 $domain = trim( $domain, " \t\n\r\0\x0B." );
2765 if ( '' === $domain ) {
2766 /** This filter is documented in wp-includes/formatting.php */
2767 return apply_filters( 'sanitize_email', '', $email, 'domain_period_limits' );
2770 // Split the domain into subs
2771 $subs = explode( '.', $domain );
2773 // Assume the domain will have at least two subs
2774 if ( 2 > count( $subs ) ) {
2775 /** This filter is documented in wp-includes/formatting.php */
2776 return apply_filters( 'sanitize_email', '', $email, 'domain_no_periods' );
2779 // Create an array that will contain valid subs
2780 $new_subs = array();
2782 // Loop through each sub
2783 foreach ( $subs as $sub ) {
2784 // Test for leading and trailing hyphens
2785 $sub = trim( $sub, " \t\n\r\0\x0B-" );
2787 // Test for invalid characters
2788 $sub = preg_replace( '/[^a-z0-9-]+/i', '', $sub );
2790 // If there's anything left, add it to the valid subs
2791 if ( '' !== $sub ) {
2796 // If there aren't 2 or more valid subs
2797 if ( 2 > count( $new_subs ) ) {
2798 /** This filter is documented in wp-includes/formatting.php */
2799 return apply_filters( 'sanitize_email', '', $email, 'domain_no_valid_subs' );
2802 // Join valid subs into the new domain
2803 $domain = join( '.', $new_subs );
2805 // Put the email back together
2806 $email = $local . '@' . $domain;
2808 // Congratulations your email made it!
2809 /** This filter is documented in wp-includes/formatting.php */
2810 return apply_filters( 'sanitize_email', $email, $email, null );
2814 * Determines the difference between two timestamps.
2816 * The difference is returned in a human readable format such as "1 hour",
2817 * "5 mins", "2 days".
2821 * @param int $from Unix timestamp from which the difference begins.
2822 * @param int $to Optional. Unix timestamp to end the time difference. Default becomes time() if not set.
2823 * @return string Human readable time difference.
2825 function human_time_diff( $from, $to = '' ) {
2826 if ( empty( $to ) ) {
2830 $diff = (int) abs( $to - $from );
2832 if ( $diff < HOUR_IN_SECONDS ) {
2833 $mins = round( $diff / MINUTE_IN_SECONDS );
2836 /* translators: min=minute */
2837 $since = sprintf( _n( '%s min', '%s mins', $mins ), $mins );
2838 } elseif ( $diff < DAY_IN_SECONDS && $diff >= HOUR_IN_SECONDS ) {
2839 $hours = round( $diff / HOUR_IN_SECONDS );
2842 $since = sprintf( _n( '%s hour', '%s hours', $hours ), $hours );
2843 } elseif ( $diff < WEEK_IN_SECONDS && $diff >= DAY_IN_SECONDS ) {
2844 $days = round( $diff / DAY_IN_SECONDS );
2847 $since = sprintf( _n( '%s day', '%s days', $days ), $days );
2848 } elseif ( $diff < MONTH_IN_SECONDS && $diff >= WEEK_IN_SECONDS ) {
2849 $weeks = round( $diff / WEEK_IN_SECONDS );
2852 $since = sprintf( _n( '%s week', '%s weeks', $weeks ), $weeks );
2853 } elseif ( $diff < YEAR_IN_SECONDS && $diff >= MONTH_IN_SECONDS ) {
2854 $months = round( $diff / MONTH_IN_SECONDS );
2857 $since = sprintf( _n( '%s month', '%s months', $months ), $months );
2858 } elseif ( $diff >= YEAR_IN_SECONDS ) {
2859 $years = round( $diff / YEAR_IN_SECONDS );
2862 $since = sprintf( _n( '%s year', '%s years', $years ), $years );
2866 * Filter the human readable difference between two timestamps.
2870 * @param string $since The difference in human readable text.
2871 * @param int $diff The difference in seconds.
2872 * @param int $from Unix timestamp from which the difference begins.
2873 * @param int $to Unix timestamp to end the time difference.
2875 return apply_filters( 'human_time_diff', $since, $diff, $from, $to );
2879 * Generates an excerpt from the content, if needed.
2881 * The excerpt word amount will be 55 words and if the amount is greater than
2882 * that, then the string ' […]' will be appended to the excerpt. If the string
2883 * is less than 55 words, then the content will be returned as is.
2885 * The 55 word limit can be modified by plugins/themes using the excerpt_length filter
2886 * The ' […]' string can be modified by plugins/themes using the excerpt_more filter
2890 * @param string $text Optional. The excerpt. If set to empty, an excerpt is generated.
2891 * @return string The excerpt.
2893 function wp_trim_excerpt( $text = '' ) {
2894 $raw_excerpt = $text;
2895 if ( '' == $text ) {
2896 $text = get_the_content('');
2898 $text = strip_shortcodes( $text );
2900 /** This filter is documented in wp-includes/post-template.php */
2901 $text = apply_filters( 'the_content', $text );
2902 $text = str_replace(']]>', ']]>', $text);
2905 * Filter the number of words in an excerpt.
2909 * @param int $number The number of words. Default 55.
2911 $excerpt_length = apply_filters( 'excerpt_length', 55 );
2913 * Filter the string in the "more" link displayed after a trimmed excerpt.
2917 * @param string $more_string The string shown within the more link.
2919 $excerpt_more = apply_filters( 'excerpt_more', ' ' . '[…]' );
2920 $text = wp_trim_words( $text, $excerpt_length, $excerpt_more );
2923 * Filter the trimmed excerpt string.
2927 * @param string $text The trimmed text.
2928 * @param string $raw_excerpt The text prior to trimming.
2930 return apply_filters( 'wp_trim_excerpt', $text, $raw_excerpt );
2934 * Trims text to a certain number of words.
2936 * This function is localized. For languages that count 'words' by the individual
2937 * character (such as East Asian languages), the $num_words argument will apply
2938 * to the number of individual characters.
2942 * @param string $text Text to trim.
2943 * @param int $num_words Number of words. Default 55.
2944 * @param string $more Optional. What to append if $text needs to be trimmed. Default '…'.
2945 * @return string Trimmed text.
2947 function wp_trim_words( $text, $num_words = 55, $more = null ) {
2948 if ( null === $more ) {
2949 $more = __( '…' );
2952 $original_text = $text;
2953 $text = wp_strip_all_tags( $text );
2956 * translators: If your word count is based on single characters (e.g. East Asian characters),
2957 * enter 'characters_excluding_spaces' or 'characters_including_spaces'. Otherwise, enter 'words'.
2958 * Do not translate into your own language.
2960 if ( strpos( _x( 'words', 'Word count type. Do not translate!' ), 'characters' ) === 0 && preg_match( '/^utf\-?8$/i', get_option( 'blog_charset' ) ) ) {
2961 $text = trim( preg_replace( "/[\n\r\t ]+/", ' ', $text ), ' ' );
2962 preg_match_all( '/./u', $text, $words_array );
2963 $words_array = array_slice( $words_array[0], 0, $num_words + 1 );
2966 $words_array = preg_split( "/[\n\r\t ]+/", $text, $num_words + 1, PREG_SPLIT_NO_EMPTY );
2970 if ( count( $words_array ) > $num_words ) {
2971 array_pop( $words_array );
2972 $text = implode( $sep, $words_array );
2973 $text = $text . $more;
2975 $text = implode( $sep, $words_array );
2979 * Filter the text content after words have been trimmed.
2983 * @param string $text The trimmed text.
2984 * @param int $num_words The number of words to trim the text to. Default 5.
2985 * @param string $more An optional string to append to the end of the trimmed text, e.g. ….
2986 * @param string $original_text The text before it was trimmed.
2988 return apply_filters( 'wp_trim_words', $text, $num_words, $more, $original_text );
2992 * Converts named entities into numbered entities.
2996 * @param string $text The text within which entities will be converted.
2997 * @return string Text with converted entities.
2999 function ent2ncr( $text ) {
3002 * Filter text before named entities are converted into numbered entities.
3004 * A non-null string must be returned for the filter to be evaluated.
3008 * @param null $converted_text The text to be converted. Default null.
3009 * @param string $text The text prior to entity conversion.
3011 $filtered = apply_filters( 'pre_ent2ncr', null, $text );
3012 if ( null !== $filtered )
3016 '"' => '"',
3021 ' ' => ' ',
3022 '¡' => '¡',
3023 '¢' => '¢',
3024 '£' => '£',
3025 '¤' => '¤',
3026 '¥' => '¥',
3027 '¦' => '¦',
3028 '&brkbar;' => '¦',
3029 '§' => '§',
3030 '¨' => '¨',
3031 '¨' => '¨',
3032 '©' => '©',
3033 'ª' => 'ª',
3034 '«' => '«',
3035 '¬' => '¬',
3036 '­' => '­',
3037 '®' => '®',
3038 '¯' => '¯',
3039 '&hibar;' => '¯',
3040 '°' => '°',
3041 '±' => '±',
3042 '²' => '²',
3043 '³' => '³',
3044 '´' => '´',
3045 'µ' => 'µ',
3046 '¶' => '¶',
3047 '·' => '·',
3048 '¸' => '¸',
3049 '¹' => '¹',
3050 'º' => 'º',
3051 '»' => '»',
3052 '¼' => '¼',
3053 '½' => '½',
3054 '¾' => '¾',
3055 '¿' => '¿',
3056 'À' => 'À',
3057 'Á' => 'Á',
3058 'Â' => 'Â',
3059 'Ã' => 'Ã',
3060 'Ä' => 'Ä',
3061 'Å' => 'Å',
3062 'Æ' => 'Æ',
3063 'Ç' => 'Ç',
3064 'È' => 'È',
3065 'É' => 'É',
3066 'Ê' => 'Ê',
3067 'Ë' => 'Ë',
3068 'Ì' => 'Ì',
3069 'Í' => 'Í',
3070 'Î' => 'Î',
3071 'Ï' => 'Ï',
3072 'Ð' => 'Ð',
3073 'Ñ' => 'Ñ',
3074 'Ò' => 'Ò',
3075 'Ó' => 'Ó',
3076 'Ô' => 'Ô',
3077 'Õ' => 'Õ',
3078 'Ö' => 'Ö',
3079 '×' => '×',
3080 'Ø' => 'Ø',
3081 'Ù' => 'Ù',
3082 'Ú' => 'Ú',
3083 'Û' => 'Û',
3084 'Ü' => 'Ü',
3085 'Ý' => 'Ý',
3086 'Þ' => 'Þ',
3087 'ß' => 'ß',
3088 'à' => 'à',
3089 'á' => 'á',
3090 'â' => 'â',
3091 'ã' => 'ã',
3092 'ä' => 'ä',
3093 'å' => 'å',
3094 'æ' => 'æ',
3095 'ç' => 'ç',
3096 'è' => 'è',
3097 'é' => 'é',
3098 'ê' => 'ê',
3099 'ë' => 'ë',
3100 'ì' => 'ì',
3101 'í' => 'í',
3102 'î' => 'î',
3103 'ï' => 'ï',
3104 'ð' => 'ð',
3105 'ñ' => 'ñ',
3106 'ò' => 'ò',
3107 'ó' => 'ó',
3108 'ô' => 'ô',
3109 'õ' => 'õ',
3110 'ö' => 'ö',
3111 '÷' => '÷',
3112 'ø' => 'ø',
3113 'ù' => 'ù',
3114 'ú' => 'ú',
3115 'û' => 'û',
3116 'ü' => 'ü',
3117 'ý' => 'ý',
3118 'þ' => 'þ',
3119 'ÿ' => 'ÿ',
3120 'Œ' => 'Œ',
3121 'œ' => 'œ',
3122 'Š' => 'Š',
3123 'š' => 'š',
3124 'Ÿ' => 'Ÿ',
3125 'ƒ' => 'ƒ',
3126 'ˆ' => 'ˆ',
3127 '˜' => '˜',
3128 'Α' => 'Α',
3129 'Β' => 'Β',
3130 'Γ' => 'Γ',
3131 'Δ' => 'Δ',
3132 'Ε' => 'Ε',
3133 'Ζ' => 'Ζ',
3134 'Η' => 'Η',
3135 'Θ' => 'Θ',
3136 'Ι' => 'Ι',
3137 'Κ' => 'Κ',
3138 'Λ' => 'Λ',
3142 'Ο' => 'Ο',
3144 'Ρ' => 'Ρ',
3145 'Σ' => 'Σ',
3146 'Τ' => 'Τ',
3147 'Υ' => 'Υ',
3148 'Φ' => 'Φ',
3149 'Χ' => 'Χ',
3150 'Ψ' => 'Ψ',
3151 'Ω' => 'Ω',
3152 'α' => 'α',
3153 'β' => 'β',
3154 'γ' => 'γ',
3155 'δ' => 'δ',
3156 'ε' => 'ε',
3157 'ζ' => 'ζ',
3158 'η' => 'η',
3159 'θ' => 'θ',
3160 'ι' => 'ι',
3161 'κ' => 'κ',
3162 'λ' => 'λ',
3166 'ο' => 'ο',
3168 'ρ' => 'ρ',
3169 'ς' => 'ς',
3170 'σ' => 'σ',
3171 'τ' => 'τ',
3172 'υ' => 'υ',
3173 'φ' => 'φ',
3174 'χ' => 'χ',
3175 'ψ' => 'ψ',
3176 'ω' => 'ω',
3177 'ϑ' => 'ϑ',
3178 'ϒ' => 'ϒ',
3179 'ϖ' => 'ϖ',
3180 ' ' => ' ',
3181 ' ' => ' ',
3182 ' ' => ' ',
3183 '‌' => '‌',
3184 '‍' => '‍',
3185 '‎' => '‎',
3186 '‏' => '‏',
3187 '–' => '–',
3188 '—' => '—',
3189 '‘' => '‘',
3190 '’' => '’',
3191 '‚' => '‚',
3192 '“' => '“',
3193 '”' => '”',
3194 '„' => '„',
3195 '†' => '†',
3196 '‡' => '‡',
3197 '•' => '•',
3198 '…' => '…',
3199 '‰' => '‰',
3200 '′' => '′',
3201 '″' => '″',
3202 '‹' => '‹',
3203 '›' => '›',
3204 '‾' => '‾',
3205 '⁄' => '⁄',
3206 '€' => '€',
3207 'ℑ' => 'ℑ',
3208 '℘' => '℘',
3209 'ℜ' => 'ℜ',
3210 '™' => '™',
3211 'ℵ' => 'ℵ',
3212 '↵' => '↵',
3213 '⇐' => '⇐',
3214 '⇑' => '⇑',
3215 '⇒' => '⇒',
3216 '⇓' => '⇓',
3217 '⇔' => '⇔',
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 '♦' => '♦'
3274 return str_replace( array_keys($to_ncr), array_values($to_ncr), $text );
3278 * Formats text for the editor.
3280 * Generally the browsers treat everything inside a textarea as text, but
3281 * it is still a good idea to HTML entity encode `<`, `>` and `&` in the content.
3283 * The filter {@see 'format_for_editor'} is applied here. If `$text` is empty the
3284 * filter will be applied to an empty string.
3288 * @param string $text The text to be formatted.
3289 * @return string The formatted text after filter is applied.
3291 function format_for_editor( $text, $default_editor = null ) {
3293 $text = htmlspecialchars( $text, ENT_NOQUOTES, get_option( 'blog_charset' ) );
3297 * Filter the text after it is formatted for the editor.
3301 * @param string $text The formatted text.
3303 return apply_filters( 'format_for_editor', $text, $default_editor );
3307 * Perform a deep string replace operation to ensure the values in $search are no longer present
3309 * Repeats the replacement operation until it no longer replaces anything so as to remove "nested" values
3310 * e.g. $subject = '%0%0%0DDD', $search ='%0D', $result ='' rather than the '%0%0DD' that
3311 * str_replace would return
3316 * @param string|array $search The value being searched for, otherwise known as the needle.
3317 * An array may be used to designate multiple needles.
3318 * @param string $subject The string being searched and replaced on, otherwise known as the haystack.
3319 * @return string The string with the replaced svalues.
3321 function _deep_replace( $search, $subject ) {
3322 $subject = (string) $subject;
3326 $subject = str_replace( $search, '', $subject, $count );
3333 * Escapes data for use in a MySQL query.
3335 * Usually you should prepare queries using wpdb::prepare().
3336 * Sometimes, spot-escaping is required or useful. One example
3337 * is preparing an array for use in an IN clause.
3341 * @global wpdb $wpdb WordPress database abstraction object.
3343 * @param string|array $data Unescaped data
3344 * @return string|array Escaped data
3346 function esc_sql( $data ) {
3348 return $wpdb->_escape( $data );
3352 * Checks and cleans a URL.
3354 * A number of characters are removed from the URL. If the URL is for displaying
3355 * (the default behaviour) ampersands are also replaced. The 'clean_url' filter
3356 * is applied to the returned cleaned URL.
3360 * @param string $url The URL to be cleaned.
3361 * @param array $protocols Optional. An array of acceptable protocols.
3362 * Defaults to return value of wp_allowed_protocols()
3363 * @param string $_context Private. Use esc_url_raw() for database usage.
3364 * @return string The cleaned $url after the 'clean_url' filter is applied.
3366 function esc_url( $url, $protocols = null, $_context = 'display' ) {
3367 $original_url = $url;
3372 $url = str_replace( ' ', '%20', $url );
3373 $url = preg_replace('|[^a-z0-9-~+_.?#=!&;,/:%@$\|*\'()\[\]\\x80-\\xff]|i', '', $url);
3375 if ( '' === $url ) {
3379 if ( 0 !== stripos( $url, 'mailto:' ) ) {
3380 $strip = array('%0d', '%0a', '%0D', '%0A');
3381 $url = _deep_replace($strip, $url);
3384 $url = str_replace(';//', '://', $url);
3385 /* If the URL doesn't appear to contain a scheme, we
3386 * presume it needs http:// prepended (unless a relative
3387 * link starting with /, # or ? or a php file).
3389 if ( strpos($url, ':') === false && ! in_array( $url[0], array( '/', '#', '?' ) ) &&
3390 ! preg_match('/^[a-z0-9-]+?\.php/i', $url) )
3391 $url = 'http://' . $url;
3393 // Replace ampersands and single quotes only when displaying.
3394 if ( 'display' == $_context ) {
3395 $url = wp_kses_normalize_entities( $url );
3396 $url = str_replace( '&', '&', $url );
3397 $url = str_replace( "'", ''', $url );
3400 if ( ( false !== strpos( $url, '[' ) ) || ( false !== strpos( $url, ']' ) ) ) {
3402 $parsed = wp_parse_url( $url );
3405 if ( isset( $parsed['scheme'] ) ) {
3406 $front .= $parsed['scheme'] . '://';
3407 } elseif ( '/' === $url[0] ) {
3411 if ( isset( $parsed['user'] ) ) {
3412 $front .= $parsed['user'];
3415 if ( isset( $parsed['pass'] ) ) {
3416 $front .= ':' . $parsed['pass'];
3419 if ( isset( $parsed['user'] ) || isset( $parsed['pass'] ) ) {
3423 if ( isset( $parsed['host'] ) ) {
3424 $front .= $parsed['host'];
3427 if ( isset( $parsed['port'] ) ) {
3428 $front .= ':' . $parsed['port'];
3431 $end_dirty = str_replace( $front, '', $url );
3432 $end_clean = str_replace( array( '[', ']' ), array( '%5B', '%5D' ), $end_dirty );
3433 $url = str_replace( $end_dirty, $end_clean, $url );
3437 if ( '/' === $url[0] ) {
3438 $good_protocol_url = $url;
3440 if ( ! is_array( $protocols ) )
3441 $protocols = wp_allowed_protocols();
3442 $good_protocol_url = wp_kses_bad_protocol( $url, $protocols );
3443 if ( strtolower( $good_protocol_url ) != strtolower( $url ) )
3448 * Filter a string cleaned and escaped for output as a URL.
3452 * @param string $good_protocol_url The cleaned URL to be returned.
3453 * @param string $original_url The URL prior to cleaning.
3454 * @param string $_context If 'display', replace ampersands and single quotes only.
3456 return apply_filters( 'clean_url', $good_protocol_url, $original_url, $_context );
3460 * Performs esc_url() for database usage.
3464 * @param string $url The URL to be cleaned.
3465 * @param array $protocols An array of acceptable protocols.
3466 * @return string The cleaned URL.
3468 function esc_url_raw( $url, $protocols = null ) {
3469 return esc_url( $url, $protocols, 'db' );
3473 * Convert entities, while preserving already-encoded entities.
3475 * @link http://www.php.net/htmlentities Borrowed from the PHP Manual user notes.
3479 * @param string $myHTML The text to be converted.
3480 * @return string Converted text.
3482 function htmlentities2( $myHTML ) {
3483 $translation_table = get_html_translation_table( HTML_ENTITIES, ENT_QUOTES );
3484 $translation_table[chr(38)] = '&';
3485 return preg_replace( "/&(?![A-Za-z]{0,4}\w{2,3};|#[0-9]{2,3};)/", "&", strtr($myHTML, $translation_table) );
3489 * Escape single quotes, htmlspecialchar " < > &, and fix line endings.
3491 * Escapes text strings for echoing in JS. It is intended to be used for inline JS
3492 * (in a tag attribute, for example onclick="..."). Note that the strings have to
3493 * be in single quotes. The filter 'js_escape' is also applied here.
3497 * @param string $text The text to be escaped.
3498 * @return string Escaped text.
3500 function esc_js( $text ) {
3501 $safe_text = wp_check_invalid_utf8( $text );
3502 $safe_text = _wp_specialchars( $safe_text, ENT_COMPAT );
3503 $safe_text = preg_replace( '/&#(x)?0*(?(1)27|39);?/i', "'", stripslashes( $safe_text ) );
3504 $safe_text = str_replace( "\r", '', $safe_text );
3505 $safe_text = str_replace( "\n", '\\n', addslashes( $safe_text ) );
3507 * Filter a string cleaned and escaped for output in JavaScript.
3509 * Text passed to esc_js() is stripped of invalid or special characters,
3510 * and properly slashed for output.
3514 * @param string $safe_text The text after it has been escaped.
3515 * @param string $text The text prior to being escaped.
3517 return apply_filters( 'js_escape', $safe_text, $text );
3521 * Escaping for HTML blocks.
3525 * @param string $text
3528 function esc_html( $text ) {
3529 $safe_text = wp_check_invalid_utf8( $text );
3530 $safe_text = _wp_specialchars( $safe_text, ENT_QUOTES );
3532 * Filter a string cleaned and escaped for output in HTML.
3534 * Text passed to esc_html() is stripped of invalid or special characters
3539 * @param string $safe_text The text after it has been escaped.
3540 * @param string $text The text prior to being escaped.
3542 return apply_filters( 'esc_html', $safe_text, $text );
3546 * Escaping for HTML attributes.
3550 * @param string $text
3553 function esc_attr( $text ) {
3554 $safe_text = wp_check_invalid_utf8( $text );
3555 $safe_text = _wp_specialchars( $safe_text, ENT_QUOTES );
3557 * Filter a string cleaned and escaped for output in an HTML attribute.
3559 * Text passed to esc_attr() is stripped of invalid or special characters
3564 * @param string $safe_text The text after it has been escaped.
3565 * @param string $text The text prior to being escaped.
3567 return apply_filters( 'attribute_escape', $safe_text, $text );
3571 * Escaping for textarea values.
3575 * @param string $text
3578 function esc_textarea( $text ) {
3579 $safe_text = htmlspecialchars( $text, ENT_QUOTES, get_option( 'blog_charset' ) );
3581 * Filter a string cleaned and escaped for output in a textarea element.
3585 * @param string $safe_text The text after it has been escaped.
3586 * @param string $text The text prior to being escaped.
3588 return apply_filters( 'esc_textarea', $safe_text, $text );
3592 * Escape an HTML tag name.
3596 * @param string $tag_name
3599 function tag_escape( $tag_name ) {
3600 $safe_tag = strtolower( preg_replace('/[^a-zA-Z0-9_:]/', '', $tag_name) );
3602 * Filter a string cleaned and escaped for output as an HTML tag.
3606 * @param string $safe_tag The tag name after it has been escaped.
3607 * @param string $tag_name The text before it was escaped.
3609 return apply_filters( 'tag_escape', $safe_tag, $tag_name );
3613 * Convert full URL paths to absolute paths.
3615 * Removes the http or https protocols and the domain. Keeps the path '/' at the
3616 * beginning, so it isn't a true relative link, but from the web root base.
3619 * @since 4.1.0 Support was added for relative URLs.
3621 * @param string $link Full URL path.
3622 * @return string Absolute path.
3624 function wp_make_link_relative( $link ) {
3625 return preg_replace( '|^(https?:)?//[^/]+(/?.*)|i', '$2', $link );
3629 * Sanitises various option values based on the nature of the option.
3631 * This is basically a switch statement which will pass $value through a number
3632 * of functions depending on the $option.
3636 * @global wpdb $wpdb WordPress database abstraction object.
3638 * @param string $option The name of the option.
3639 * @param string $value The unsanitised value.
3640 * @return string Sanitized value.
3642 function sanitize_option( $option, $value ) {
3645 $original_value = $value;
3648 switch ( $option ) {
3649 case 'admin_email' :
3650 case 'new_admin_email' :
3651 $value = $wpdb->strip_invalid_text_for_column( $wpdb->options, 'option_value', $value );
3652 if ( is_wp_error( $value ) ) {
3653 $error = $value->get_error_message();
3655 $value = sanitize_email( $value );
3656 if ( ! is_email( $value ) ) {
3657 $error = __( 'The email address entered did not appear to be a valid email address. Please enter a valid email address.' );
3662 case 'thumbnail_size_w':
3663 case 'thumbnail_size_h':
3664 case 'medium_size_w':
3665 case 'medium_size_h':
3666 case 'medium_large_size_w':
3667 case 'medium_large_size_h':
3668 case 'large_size_w':
3669 case 'large_size_h':
3670 case 'mailserver_port':
3671 case 'comment_max_links':
3672 case 'page_on_front':
3673 case 'page_for_posts':
3674 case 'rss_excerpt_length':
3675 case 'default_category':
3676 case 'default_email_category':
3677 case 'default_link_category':
3678 case 'close_comments_days_old':
3679 case 'comments_per_page':
3680 case 'thread_comments_depth':
3681 case 'users_can_register':
3682 case 'start_of_week':
3684 $value = absint( $value );
3687 case 'posts_per_page':
3688 case 'posts_per_rss':
3689 $value = (int) $value;
3690 if ( empty($value) )
3693 $value = abs($value);
3696 case 'default_ping_status':
3697 case 'default_comment_status':
3698 // Options that if not there have 0 value but need to be something like "closed"
3699 if ( $value == '0' || $value == '')
3703 case 'blogdescription':
3705 $value = $wpdb->strip_invalid_text_for_column( $wpdb->options, 'option_value', $value );
3706 if ( is_wp_error( $value ) ) {
3707 $error = $value->get_error_message();
3709 $value = wp_kses_post( $value );
3710 $value = esc_html( $value );
3714 case 'blog_charset':
3715 $value = preg_replace('/[^a-zA-Z0-9_-]/', '', $value); // strips slashes
3719 // This is the value if the settings checkbox is not checked on POST. Don't rely on this.
3720 if ( null === $value )
3723 $value = intval( $value );
3728 case 'mailserver_url':
3729 case 'mailserver_login':
3730 case 'mailserver_pass':
3732 $value = $wpdb->strip_invalid_text_for_column( $wpdb->options, 'option_value', $value );
3733 if ( is_wp_error( $value ) ) {
3734 $error = $value->get_error_message();
3736 $value = strip_tags( $value );
3737 $value = wp_kses_data( $value );
3742 $value = explode( "\n", $value );
3743 $value = array_filter( array_map( 'trim', $value ) );
3744 $value = array_filter( array_map( 'esc_url_raw', $value ) );
3745 $value = implode( "\n", $value );
3749 $value = preg_replace('/[^0-9:.-]/', '', $value); // strips slashes
3753 $value = $wpdb->strip_invalid_text_for_column( $wpdb->options, 'option_value', $value );
3754 if ( is_wp_error( $value ) ) {
3755 $error = $value->get_error_message();
3757 if ( preg_match( '#http(s?)://(.+)#i', $value ) ) {
3758 $value = esc_url_raw( $value );
3760 $error = __( 'The WordPress address you entered did not appear to be a valid URL. Please enter a valid URL.' );
3766 $value = $wpdb->strip_invalid_text_for_column( $wpdb->options, 'option_value', $value );
3767 if ( is_wp_error( $value ) ) {
3768 $error = $value->get_error_message();
3770 if ( preg_match( '#http(s?)://(.+)#i', $value ) ) {
3771 $value = esc_url_raw( $value );
3773 $error = __( 'The Site address you entered did not appear to be a valid URL. Please enter a valid URL.' );
3779 $allowed = get_available_languages();
3780 if ( ! is_multisite() && defined( 'WPLANG' ) && '' !== WPLANG && 'en_US' !== WPLANG ) {
3781 $allowed[] = WPLANG;
3783 if ( ! in_array( $value, $allowed ) && ! empty( $value ) ) {
3784 $value = get_option( $option );
3788 case 'illegal_names':
3789 $value = $wpdb->strip_invalid_text_for_column( $wpdb->options, 'option_value', $value );
3790 if ( is_wp_error( $value ) ) {
3791 $error = $value->get_error_message();
3793 if ( ! is_array( $value ) )
3794 $value = explode( ' ', $value );
3796 $value = array_values( array_filter( array_map( 'trim', $value ) ) );
3803 case 'limited_email_domains':
3804 case 'banned_email_domains':
3805 $value = $wpdb->strip_invalid_text_for_column( $wpdb->options, 'option_value', $value );
3806 if ( is_wp_error( $value ) ) {
3807 $error = $value->get_error_message();
3809 if ( ! is_array( $value ) )
3810 $value = explode( "\n", $value );
3812 $domains = array_values( array_filter( array_map( 'trim', $value ) ) );
3815 foreach ( $domains as $domain ) {
3816 if ( ! preg_match( '/(--|\.\.)/', $domain ) && preg_match( '|^([a-zA-Z0-9-\.])+$|', $domain ) ) {
3825 case 'timezone_string':
3826 $allowed_zones = timezone_identifiers_list();
3827 if ( ! in_array( $value, $allowed_zones ) && ! empty( $value ) ) {
3828 $error = __( 'The timezone you have entered is not valid. Please select a valid timezone.' );
3832 case 'permalink_structure':
3833 case 'category_base':
3835 $value = $wpdb->strip_invalid_text_for_column( $wpdb->options, 'option_value', $value );
3836 if ( is_wp_error( $value ) ) {
3837 $error = $value->get_error_message();
3839 $value = esc_url_raw( $value );
3840 $value = str_replace( 'http://', '', $value );
3844 case 'default_role' :
3845 if ( ! get_role( $value ) && get_role( 'subscriber' ) )
3846 $value = 'subscriber';
3849 case 'moderation_keys':
3850 case 'blacklist_keys':
3851 $value = $wpdb->strip_invalid_text_for_column( $wpdb->options, 'option_value', $value );
3852 if ( is_wp_error( $value ) ) {
3853 $error = $value->get_error_message();
3855 $value = explode( "\n", $value );
3856 $value = array_filter( array_map( 'trim', $value ) );
3857 $value = array_unique( $value );
3858 $value = implode( "\n", $value );
3863 if ( ! empty( $error ) ) {
3864 $value = get_option( $option );
3865 if ( function_exists( 'add_settings_error' ) ) {
3866 add_settings_error( $option, "invalid_{$option}", $error );
3871 * Filter an option value following sanitization.
3874 * @since 4.3.0 Added the `$original_value` parameter.
3876 * @param string $value The sanitized option value.
3877 * @param string $option The option name.
3878 * @param string $original_value The original value passed to the function.
3880 return apply_filters( "sanitize_option_{$option}", $value, $option, $original_value );
3884 * Maps a function to all non-iterable elements of an array or an object.
3886 * This is similar to `array_walk_recursive()` but acts upon objects too.
3890 * @param mixed $value The array, object, or scalar.
3891 * @param callable $callback The function to map onto $value.
3892 * @return The value with the callback applied to all non-arrays and non-objects inside it.
3894 function map_deep( $value, $callback ) {
3895 if ( is_array( $value ) || is_object( $value ) ) {
3896 foreach ( $value as &$item ) {
3897 $item = map_deep( $item, $callback );
3901 return call_user_func( $callback, $value );
3906 * Parses a string into variables to be stored in an array.
3908 * Uses {@link http://www.php.net/parse_str parse_str()} and stripslashes if
3909 * {@link http://www.php.net/magic_quotes magic_quotes_gpc} is on.
3913 * @param string $string The string to be parsed.
3914 * @param array $array Variables will be stored in this array.
3916 function wp_parse_str( $string, &$array ) {
3917 parse_str( $string, $array );
3918 if ( get_magic_quotes_gpc() )
3919 $array = stripslashes_deep( $array );
3921 * Filter the array of variables derived from a parsed string.
3925 * @param array $array The array populated with variables.
3927 $array = apply_filters( 'wp_parse_str', $array );
3931 * Convert lone less than signs.
3933 * KSES already converts lone greater than signs.
3937 * @param string $text Text to be converted.
3938 * @return string Converted text.
3940 function wp_pre_kses_less_than( $text ) {
3941 return preg_replace_callback('%<[^>]*?((?=<)|>|$)%', 'wp_pre_kses_less_than_callback', $text);
3945 * Callback function used by preg_replace.
3949 * @param array $matches Populated by matches to preg_replace.
3950 * @return string The text returned after esc_html if needed.
3952 function wp_pre_kses_less_than_callback( $matches ) {
3953 if ( false === strpos($matches[0], '>') )
3954 return esc_html($matches[0]);
3959 * WordPress implementation of PHP sprintf() with filters.
3962 * @link http://www.php.net/sprintf
3964 * @param string $pattern The string which formatted args are inserted.
3965 * @param mixed $args ,... Arguments to be formatted into the $pattern string.
3966 * @return string The formatted string.
3968 function wp_sprintf( $pattern ) {
3969 $args = func_get_args();
3970 $len = strlen($pattern);
3974 while ( $len > $start ) {
3975 // Last character: append and break
3976 if ( strlen($pattern) - 1 == $start ) {
3977 $result .= substr($pattern, -1);
3981 // Literal %: append and continue
3982 if ( substr($pattern, $start, 2) == '%%' ) {
3988 // Get fragment before next %
3989 $end = strpos($pattern, '%', $start + 1);
3990 if ( false === $end )
3992 $fragment = substr($pattern, $start, $end - $start);
3994 // Fragment has a specifier
3995 if ( $pattern[$start] == '%' ) {
3996 // Find numbered arguments or take the next one in order
3997 if ( preg_match('/^%(\d+)\$/', $fragment, $matches) ) {
3998 $arg = isset($args[$matches[1]]) ? $args[$matches[1]] : '';
3999 $fragment = str_replace("%{$matches[1]}$", '%', $fragment);
4002 $arg = isset($args[$arg_index]) ? $args[$arg_index] : '';
4006 * Filter a fragment from the pattern passed to wp_sprintf().
4008 * If the fragment is unchanged, then sprintf() will be run on the fragment.
4012 * @param string $fragment A fragment from the pattern.
4013 * @param string $arg The argument.
4015 $_fragment = apply_filters( 'wp_sprintf', $fragment, $arg );
4016 if ( $_fragment != $fragment )
4017 $fragment = $_fragment;
4019 $fragment = sprintf($fragment, strval($arg) );
4022 // Append to result and move to next fragment
4023 $result .= $fragment;
4030 * Localize list items before the rest of the content.
4032 * The '%l' must be at the first characters can then contain the rest of the
4033 * content. The list items will have ', ', ', and', and ' and ' added depending
4034 * on the amount of list items in the $args parameter.
4038 * @param string $pattern Content containing '%l' at the beginning.
4039 * @param array $args List items to prepend to the content and replace '%l'.
4040 * @return string Localized list items and rest of the content.
4042 function wp_sprintf_l( $pattern, $args ) {
4044 if ( substr($pattern, 0, 2) != '%l' )
4047 // Nothing to work with
4052 * Filter the translated delimiters used by wp_sprintf_l().
4053 * Placeholders (%s) are included to assist translators and then
4054 * removed before the array of strings reaches the filter.
4056 * Please note: Ampersands and entities should be avoided here.
4060 * @param array $delimiters An array of translated delimiters.
4062 $l = apply_filters( 'wp_sprintf_l', array(
4063 /* translators: used to join items in a list with more than 2 items */
4064 'between' => sprintf( __('%s, %s'), '', '' ),
4065 /* translators: used to join last two items in a list with more than 2 times */
4066 'between_last_two' => sprintf( __('%s, and %s'), '', '' ),
4067 /* translators: used to join items in a list with only 2 items */
4068 'between_only_two' => sprintf( __('%s and %s'), '', '' ),
4071 $args = (array) $args;
4072 $result = array_shift($args);
4073 if ( count($args) == 1 )
4074 $result .= $l['between_only_two'] . array_shift($args);
4075 // Loop when more than two args
4078 $arg = array_shift($args);
4081 $result .= $l['between_last_two'] . $arg;
4083 $result .= $l['between'] . $arg;
4085 return $result . substr($pattern, 2);
4089 * Safely extracts not more than the first $count characters from html string.
4091 * UTF-8, tags and entities safe prefix extraction. Entities inside will *NOT*
4092 * be counted as one character. For example & will be counted as 4, < as
4097 * @param string $str String to get the excerpt from.
4098 * @param int $count Maximum number of characters to take.
4099 * @param string $more Optional. What to append if $str needs to be trimmed. Defaults to empty string.
4100 * @return string The excerpt.
4102 function wp_html_excerpt( $str, $count, $more = null ) {
4103 if ( null === $more )
4105 $str = wp_strip_all_tags( $str, true );
4106 $excerpt = mb_substr( $str, 0, $count );
4107 // remove part of an entity at the end
4108 $excerpt = preg_replace( '/&[^;\s]{0,6}$/', '', $excerpt );
4109 if ( $str != $excerpt )
4110 $excerpt = trim( $excerpt ) . $more;
4115 * Add a Base url to relative links in passed content.
4117 * By default it supports the 'src' and 'href' attributes. However this can be
4118 * changed via the 3rd param.
4122 * @global string $_links_add_base
4124 * @param string $content String to search for links in.
4125 * @param string $base The base URL to prefix to links.
4126 * @param array $attrs The attributes which should be processed.
4127 * @return string The processed content.
4129 function links_add_base_url( $content, $base, $attrs = array('src', 'href') ) {
4130 global $_links_add_base;
4131 $_links_add_base = $base;
4132 $attrs = implode('|', (array)$attrs);
4133 return preg_replace_callback( "!($attrs)=(['\"])(.+?)\\2!i", '_links_add_base', $content );
4137 * Callback to add a base url to relative links in passed content.
4142 * @global string $_links_add_base
4144 * @param string $m The matched link.
4145 * @return string The processed link.
4147 function _links_add_base( $m ) {
4148 global $_links_add_base;
4149 //1 = attribute name 2 = quotation mark 3 = URL
4150 return $m[1] . '=' . $m[2] .
4151 ( preg_match( '#^(\w{1,20}):#', $m[3], $protocol ) && in_array( $protocol[1], wp_allowed_protocols() ) ?
4153 WP_Http::make_absolute_url( $m[3], $_links_add_base )
4159 * Adds a Target attribute to all links in passed content.
4161 * This function by default only applies to `<a>` tags, however this can be
4162 * modified by the 3rd param.
4164 * *NOTE:* Any current target attributed will be stripped and replaced.
4168 * @global string $_links_add_target
4170 * @param string $content String to search for links in.
4171 * @param string $target The Target to add to the links.
4172 * @param array $tags An array of tags to apply to.
4173 * @return string The processed content.
4175 function links_add_target( $content, $target = '_blank', $tags = array('a') ) {
4176 global $_links_add_target;
4177 $_links_add_target = $target;
4178 $tags = implode('|', (array)$tags);
4179 return preg_replace_callback( "!<($tags)([^>]*)>!i", '_links_add_target', $content );
4183 * Callback to add a target attribute to all links in passed content.
4188 * @global string $_links_add_target
4190 * @param string $m The matched link.
4191 * @return string The processed link.
4193 function _links_add_target( $m ) {
4194 global $_links_add_target;
4196 $link = preg_replace('|( target=([\'"])(.*?)\2)|i', '', $m[2]);
4197 return '<' . $tag . $link . ' target="' . esc_attr( $_links_add_target ) . '">';
4201 * Normalize EOL characters and strip duplicate whitespace.
4205 * @param string $str The string to normalize.
4206 * @return string The normalized string.
4208 function normalize_whitespace( $str ) {
4209 $str = trim( $str );
4210 $str = str_replace( "\r", "\n", $str );
4211 $str = preg_replace( array( '/\n+/', '/[ \t]+/' ), array( "\n", ' ' ), $str );
4216 * Properly strip all HTML tags including script and style
4218 * This differs from strip_tags() because it removes the contents of
4219 * the `<script>` and `<style>` tags. E.g. `strip_tags( '<script>something</script>' )`
4220 * will return 'something'. wp_strip_all_tags will return ''
4224 * @param string $string String containing HTML tags
4225 * @param bool $remove_breaks Optional. Whether to remove left over line breaks and white space chars
4226 * @return string The processed string.
4228 function wp_strip_all_tags($string, $remove_breaks = false) {
4229 $string = preg_replace( '@<(script|style)[^>]*?>.*?</\\1>@si', '', $string );
4230 $string = strip_tags($string);
4232 if ( $remove_breaks )
4233 $string = preg_replace('/[\r\n\t ]+/', ' ', $string);
4235 return trim( $string );
4239 * Sanitize a string from user input or from the db
4241 * check for invalid UTF-8,
4242 * Convert single < characters to entity,
4244 * remove line breaks, tabs and extra white space,
4249 * @param string $str
4252 function sanitize_text_field( $str ) {
4253 $filtered = wp_check_invalid_utf8( $str );
4255 if ( strpos($filtered, '<') !== false ) {
4256 $filtered = wp_pre_kses_less_than( $filtered );
4257 // This will strip extra whitespace for us.
4258 $filtered = wp_strip_all_tags( $filtered, true );
4260 $filtered = trim( preg_replace('/[\r\n\t ]+/', ' ', $filtered) );
4264 while ( preg_match('/%[a-f0-9]{2}/i', $filtered, $match) ) {
4265 $filtered = str_replace($match[0], '', $filtered);
4270 // Strip out the whitespace that may now exist after removing the octets.
4271 $filtered = trim( preg_replace('/ +/', ' ', $filtered) );
4275 * Filter a sanitized text field string.
4279 * @param string $filtered The sanitized string.
4280 * @param string $str The string prior to being sanitized.
4282 return apply_filters( 'sanitize_text_field', $filtered, $str );
4286 * i18n friendly version of basename()
4290 * @param string $path A path.
4291 * @param string $suffix If the filename ends in suffix this will also be cut off.
4294 function wp_basename( $path, $suffix = '' ) {
4295 return urldecode( basename( str_replace( array( '%2F', '%5C' ), '/', urlencode( $path ) ), $suffix ) );
4299 * Forever eliminate "Wordpress" from the planet (or at least the little bit we can influence).
4301 * Violating our coding standards for a good function name.
4305 * @staticvar string|false $dblq
4307 function capital_P_dangit( $text ) {
4308 // Simple replacement for titles
4309 $current_filter = current_filter();
4310 if ( 'the_title' === $current_filter || 'wp_title' === $current_filter )
4311 return str_replace( 'Wordpress', 'WordPress', $text );
4312 // Still here? Use the more judicious replacement
4313 static $dblq = false;
4314 if ( false === $dblq ) {
4315 $dblq = _x( '“', 'opening curly double quote' );
4318 array( ' Wordpress', '‘Wordpress', $dblq . 'Wordpress', '>Wordpress', '(Wordpress' ),
4319 array( ' WordPress', '‘WordPress', $dblq . 'WordPress', '>WordPress', '(WordPress' ),
4324 * Sanitize a mime type
4328 * @param string $mime_type Mime type
4329 * @return string Sanitized mime type
4331 function sanitize_mime_type( $mime_type ) {
4332 $sani_mime_type = preg_replace( '/[^-+*.a-zA-Z0-9\/]/', '', $mime_type );
4334 * Filter a mime type following sanitization.
4338 * @param string $sani_mime_type The sanitized mime type.
4339 * @param string $mime_type The mime type prior to sanitization.
4341 return apply_filters( 'sanitize_mime_type', $sani_mime_type, $mime_type );
4345 * Sanitize space or carriage return separated URLs that are used to send trackbacks.
4349 * @param string $to_ping Space or carriage return separated URLs
4350 * @return string URLs starting with the http or https protocol, separated by a carriage return.
4352 function sanitize_trackback_urls( $to_ping ) {
4353 $urls_to_ping = preg_split( '/[\r\n\t ]/', trim( $to_ping ), -1, PREG_SPLIT_NO_EMPTY );
4354 foreach ( $urls_to_ping as $k => $url ) {
4355 if ( !preg_match( '#^https?://.#i', $url ) )
4356 unset( $urls_to_ping[$k] );
4358 $urls_to_ping = array_map( 'esc_url_raw', $urls_to_ping );
4359 $urls_to_ping = implode( "\n", $urls_to_ping );
4361 * Filter a list of trackback URLs following sanitization.
4363 * The string returned here consists of a space or carriage return-delimited list
4364 * of trackback URLs.
4368 * @param string $urls_to_ping Sanitized space or carriage return separated URLs.
4369 * @param string $to_ping Space or carriage return separated URLs before sanitization.
4371 return apply_filters( 'sanitize_trackback_urls', $urls_to_ping, $to_ping );
4375 * Add slashes to a string or array of strings.
4377 * This should be used when preparing data for core API that expects slashed data.
4378 * This should not be used to escape data going directly into an SQL query.
4382 * @param string|array $value String or array of strings to slash.
4383 * @return string|array Slashed $value
4385 function wp_slash( $value ) {
4386 if ( is_array( $value ) ) {
4387 foreach ( $value as $k => $v ) {
4388 if ( is_array( $v ) ) {
4389 $value[$k] = wp_slash( $v );
4391 $value[$k] = addslashes( $v );
4395 $value = addslashes( $value );
4402 * Remove slashes from a string or array of strings.
4404 * This should be used to remove slashes from data passed to core API that
4405 * expects data to be unslashed.
4409 * @param string|array $value String or array of strings to unslash.
4410 * @return string|array Unslashed $value
4412 function wp_unslash( $value ) {
4413 return stripslashes_deep( $value );
4417 * Extract and return the first URL from passed content.
4421 * @param string $content A string which might contain a URL.
4422 * @return string|false The found URL.
4424 function get_url_in_content( $content ) {
4425 if ( empty( $content ) ) {
4429 if ( preg_match( '/<a\s[^>]*?href=([\'"])(.+?)\1/is', $content, $matches ) ) {
4430 return esc_url_raw( $matches[2] );
4437 * Returns the regexp for common whitespace characters.
4439 * By default, spaces include new lines, tabs, nbsp entities, and the UTF-8 nbsp.
4440 * This is designed to replace the PCRE \s sequence. In ticket #22692, that
4441 * sequence was found to be unreliable due to random inclusion of the A0 byte.
4445 * @staticvar string $spaces
4447 * @return string The spaces regexp.
4449 function wp_spaces_regexp() {
4450 static $spaces = '';
4452 if ( empty( $spaces ) ) {
4454 * Filter the regexp for common whitespace characters.
4456 * This string is substituted for the \s sequence as needed in regular
4457 * expressions. For websites not written in English, different characters
4458 * may represent whitespace. For websites not encoded in UTF-8, the 0xC2 0xA0
4459 * sequence may not be in use.
4463 * @param string $spaces Regexp pattern for matching common whitespace characters.
4465 $spaces = apply_filters( 'wp_spaces_regexp', '[\r\n\t ]|\xC2\xA0| ' );
4472 * Print the important emoji-related styles.
4476 * @staticvar bool $printed
4478 function print_emoji_styles() {
4479 static $printed = false;
4487 <style type="text/css">
4490 display: inline !important;
4491 border: none !important;
4492 box-shadow: none !important;
4493 height: 1em !important;
4494 width: 1em !important;
4495 margin: 0 .07em !important;
4496 vertical-align: -0.1em !important;
4497 background: none !important;
4498 padding: 0 !important;
4506 * @global string $wp_version
4507 * @staticvar bool $printed
4509 function print_emoji_detection_script() {
4511 static $printed = false;
4521 * Filter the URL where emoji images are hosted.
4525 * @param string The emoji base URL.
4527 'baseUrl' => apply_filters( 'emoji_url', set_url_scheme( '//s.w.org/images/core/emoji/72x72/' ) ),
4530 * Filter the extension of the emoji files.
4534 * @param string The emoji extension. Default .png.
4536 'ext' => apply_filters( 'emoji_ext', '.png' ),
4539 $version = 'ver=' . $wp_version;
4541 if ( SCRIPT_DEBUG ) {
4542 $settings['source'] = array(
4543 /** This filter is documented in wp-includes/class.wp-scripts.php */
4544 'wpemoji' => apply_filters( 'script_loader_src', includes_url( "js/wp-emoji.js?$version" ), 'wpemoji' ),
4545 /** This filter is documented in wp-includes/class.wp-scripts.php */
4546 'twemoji' => apply_filters( 'script_loader_src', includes_url( "js/twemoji.js?$version" ), 'twemoji' ),
4550 <script type="text/javascript">
4551 window._wpemojiSettings = <?php echo wp_json_encode( $settings ); ?>;
4552 <?php readfile( ABSPATH . WPINC . "/js/wp-emoji-loader.js" ); ?>
4556 $settings['source'] = array(
4557 /** This filter is documented in wp-includes/class.wp-scripts.php */
4558 'concatemoji' => apply_filters( 'script_loader_src', includes_url( "js/wp-emoji-release.min.js?$version" ), 'concatemoji' ),
4562 * If you're looking at a src version of this file, you'll see an "include"
4563 * statement below. This is used by the `grunt build` process to directly
4564 * include a minified version of wp-emoji-loader.js, instead of using the
4565 * readfile() method from above.
4567 * If you're looking at a build version of this file, you'll see a string of
4568 * minified JavaScript. If you need to debug it, please turn on SCRIPT_DEBUG
4569 * and edit wp-emoji-loader.js directly.
4572 <script type="text/javascript">
4573 window._wpemojiSettings = <?php echo wp_json_encode( $settings ); ?>;
4574 !function(a,b,c){function d(a){var c=b.createElement("canvas"),d=c.getContext&&c.getContext("2d");return d&&d.fillText?(d.textBaseline="top",d.font="600 32px Arial","flag"===a?(d.fillText(String.fromCharCode(55356,56806,55356,56826),0,0),c.toDataURL().length>3e3):("simple"===a?d.fillText(String.fromCharCode(55357,56835),0,0):d.fillText(String.fromCharCode(55356,57135),0,0),0!==d.getImageData(16,16,1,1).data[0])):!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;c.supports={simple:d("simple"),flag:d("flag"),unicode8:d("unicode8")},c.DOMReady=!1,c.readyCallback=function(){c.DOMReady=!0},c.supports.simple&&c.supports.flag&&c.supports.unicode8||(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);
4581 * Convert any 4 byte emoji in a string to their equivalent HTML entity.
4583 * Currently, only Unicode 7 emoji are supported. Skin tone modifiers are allowed,
4584 * all other Unicode 8 emoji will be added when the spec is finalised.
4586 * This allows us to store emoji in a DB using the utf8 character set.
4590 * @param string $content The content to encode.
4591 * @return string The encoded content.
4593 function wp_encode_emoji( $content ) {
4594 if ( function_exists( 'mb_convert_encoding' ) ) {
4596 \x23\xE2\x83\xA3 # Digits
4597 [\x30-\x39]\xE2\x83\xA3
4598 | \xF0\x9F[\x85-\x88][\xA6-\xBF] # Enclosed characters
4599 | \xF0\x9F[\x8C-\x97][\x80-\xBF] # Misc
4600 | \xF0\x9F\x98[\x80-\xBF] # Smilies
4601 | \xF0\x9F\x99[\x80-\x8F]
4602 | \xF0\x9F\x9A[\x80-\xBF] # Transport and map symbols
4606 if ( preg_match_all( $regex, $content, $matches ) ) {
4607 if ( ! empty( $matches[1] ) ) {
4608 foreach ( $matches[1] as $emoji ) {
4610 * UTF-32's hex encoding is the same as HTML's hex encoding.
4611 * So, by converting the emoji from UTF-8 to UTF-32, we magically
4612 * get the correct hex encoding.
4614 $unpacked = unpack( 'H*', mb_convert_encoding( $emoji, 'UTF-32', 'UTF-8' ) );
4615 if ( isset( $unpacked[1] ) ) {
4616 $entity = '&#x' . ltrim( $unpacked[1], '0' ) . ';';
4617 $content = str_replace( $emoji, $entity, $content );
4628 * Convert emoji to a static img element.
4632 * @param string $text The content to encode.
4633 * @return string The encoded content.
4635 function wp_staticize_emoji( $text ) {
4636 $text = wp_encode_emoji( $text );
4638 /** This filter is documented in wp-includes/formatting.php */
4639 $cdn_url = apply_filters( 'emoji_url', set_url_scheme( '//s.w.org/images/core/emoji/72x72/' ) );
4641 /** This filter is documented in wp-includes/formatting.php */
4642 $ext = apply_filters( 'emoji_ext', '.png' );
4646 * HTML loop taken from smiley function, which was taken from texturize function.
4647 * It'll never be consolidated.
4649 * First, capture the tags as well as in between.
4651 $textarr = preg_split( '/(<.*>)/U', $text, -1, PREG_SPLIT_DELIM_CAPTURE );
4652 $stop = count( $textarr );
4654 // Ignore processing of specific tags.
4655 $tags_to_ignore = 'code|pre|style|script|textarea';
4656 $ignore_block_element = '';
4658 for ( $i = 0; $i < $stop; $i++ ) {
4659 $content = $textarr[$i];
4661 // If we're in an ignore block, wait until we find its closing tag.
4662 if ( '' == $ignore_block_element && preg_match( '/^<(' . $tags_to_ignore . ')>/', $content, $matches ) ) {
4663 $ignore_block_element = $matches[1];
4666 // If it's not a tag and not in ignore block.
4667 if ( '' == $ignore_block_element && strlen( $content ) > 0 && '<' != $content[0] ) {
4669 if ( preg_match_all( '/(DZ(e[6-9a-f]|f[0-9a-f]);){2}/', $content, $matches ) ) {
4670 if ( ! empty( $matches[0] ) ) {
4671 foreach ( $matches[0] as $flag ) {
4672 $chars = str_replace( array( '&#x', ';'), '', $flag );
4674 list( $char1, $char2 ) = str_split( $chars, 5 );
4675 $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 ) );
4677 $content = str_replace( $flag, $entity, $content );
4682 // Loosely match the Emoji Unicode range.
4683 $regex = '/(&#x[2-3][0-9a-f]{3};|[1-6][0-9a-f]{2};)/';
4686 if ( preg_match_all( $regex, $content, $matches ) ) {
4687 if ( ! empty( $matches[1] ) ) {
4688 foreach ( $matches[1] as $emoji ) {
4689 $char = str_replace( array( '&#x', ';'), '', $emoji );
4690 $entity = sprintf( '<img src="%s" alt="%s" class="wp-smiley" style="height: 1em; max-height: 1em;" />', $cdn_url . $char . $ext, html_entity_decode( $emoji ) );
4692 $content = str_replace( $emoji, $entity, $content );
4698 // Did we exit ignore block.
4699 if ( '' != $ignore_block_element && '</' . $ignore_block_element . '>' == $content ) {
4700 $ignore_block_element = '';
4703 $output .= $content;
4710 * Convert emoji in emails into static images.
4714 * @param array $mail The email data array.
4715 * @return array The email data array, with emoji in the message staticized.
4717 function wp_staticize_emoji_for_email( $mail ) {
4718 if ( ! isset( $mail['message'] ) ) {
4723 * We can only transform the emoji into images if it's a text/html email.
4724 * To do that, here's a cut down version of the same process that happens
4725 * in wp_mail() - get the Content-Type from the headers, if there is one,
4726 * then pass it through the wp_mail_content_type filter, in case a plugin
4727 * is handling changing the Content-Type.
4730 if ( isset( $mail['headers'] ) ) {
4731 if ( is_array( $mail['headers'] ) ) {
4732 $headers = $mail['headers'];
4734 $headers = explode( "\n", str_replace( "\r\n", "\n", $mail['headers'] ) );
4738 foreach ( $headers as $header ) {
4739 if ( strpos($header, ':') === false ) {
4743 // Explode them out.
4744 list( $name, $content ) = explode( ':', trim( $header ), 2 );
4747 $name = trim( $name );
4748 $content = trim( $content );
4750 if ( 'content-type' === strtolower( $name ) ) {
4751 if ( strpos( $content, ';' ) !== false ) {
4752 list( $type, $charset ) = explode( ';', $content );
4753 $content_type = trim( $type );
4755 $content_type = trim( $content );
4761 // Set Content-Type if we don't have a content-type from the input headers.
4762 if ( ! isset( $content_type ) ) {
4763 $content_type = 'text/plain';
4766 /** This filter is documented in wp-includes/pluggable.php */
4767 $content_type = apply_filters( 'wp_mail_content_type', $content_type );
4769 if ( 'text/html' === $content_type ) {
4770 $mail['message'] = wp_staticize_emoji( $mail['message'] );
4777 * Shorten an URL, to be used as link text.
4780 * @since 4.4.0 Moved to wp-includes/formatting.php from wp-admin/includes/misc.php and added $length param.
4782 * @param string $url URL to shorten.
4783 * @param int $length Optional. Maximum length of the shortened URL. Default 35 characters.
4784 * @return string Shortened URL.
4786 function url_shorten( $url, $length = 35 ) {
4787 $stripped = str_replace( array( 'https://', 'http://', 'www.' ), '', $url );
4788 $short_url = untrailingslashit( $stripped );
4790 if ( strlen( $short_url ) > $length ) {
4791 $short_url = substr( $short_url, 0, $length - 3 ) . '…';