X-Git-Url: https://scripts.mit.edu/gitweb/autoinstalls/wordpress.git/blobdiff_plain/f9001779751f83dc8a10e478bfecb4d8dd5f964c..refs/tags/wordpress-4.2.3:/wp-includes/formatting.php
diff --git a/wp-includes/formatting.php b/wp-includes/formatting.php
index be2669c1..08c367c6 100644
--- a/wp-includes/formatting.php
+++ b/wp-includes/formatting.php
@@ -5,118 +5,342 @@
* Handles many functions for formatting output.
*
* @package WordPress
- **/
+ */
/**
* Replaces common plain text characters into formatted entities
*
* As an example,
- *
- * 'cause today's effort makes it worth tomorrow's "holiday"...
- *
+ *
+ * 'cause today's effort makes it worth tomorrow's "holiday" ...
+ *
* Becomes:
- *
- * ’cause today’s effort makes it worth tomorrow’s “holiday”…
- *
+ *
+ * ’cause today’s effort makes it worth tomorrow’s “holiday” …
+ *
* Code within certain html blocks are skipped.
*
* @since 0.71
* @uses $wp_cockneyreplace Array of formatted entities for certain common phrases
*
* @param string $text The text to be formatted
+ * @param bool $reset Set to true for unit testing. Translated patterns will reset.
* @return string The string replaced with html entities
*/
-function wptexturize($text) {
- global $wp_cockneyreplace;
- static $static_setup = false, $opening_quote, $closing_quote, $default_no_texturize_tags, $default_no_texturize_shortcodes, $static_characters, $static_replacements, $dynamic_characters, $dynamic_replacements;
- $output = '';
- $curl = '';
- $textarr = preg_split('/(<.*>|\[.*\])/Us', $text, -1, PREG_SPLIT_DELIM_CAPTURE);
- $stop = count($textarr);
+function wptexturize($text, $reset = false) {
+ global $wp_cockneyreplace, $shortcode_tags;
+ static $static_characters, $static_replacements, $dynamic_characters, $dynamic_replacements,
+ $default_no_texturize_tags, $default_no_texturize_shortcodes, $run_texturize = true;
+
+ // If there's nothing to do, just stop.
+ if ( empty( $text ) || false === $run_texturize ) {
+ return $text;
+ }
+
+ // Set up static variables. Run once only.
+ if ( $reset || ! isset( $static_characters ) ) {
+ /**
+ * Filter whether to skip running wptexturize().
+ *
+ * Passing false to the filter will effectively short-circuit wptexturize().
+ * returning the original text passed to the function instead.
+ *
+ * The filter runs only once, the first time wptexturize() is called.
+ *
+ * @since 4.0.0
+ *
+ * @see wptexturize()
+ *
+ * @param bool $run_texturize Whether to short-circuit wptexturize().
+ */
+ $run_texturize = apply_filters( 'run_wptexturize', $run_texturize );
+ if ( false === $run_texturize ) {
+ return $text;
+ }
+
+ /* translators: opening curly double quote */
+ $opening_quote = _x( '“', 'opening curly double quote' );
+ /* translators: closing curly double quote */
+ $closing_quote = _x( '”', 'closing curly double quote' );
- // No need to set up these variables more than once
- if (!$static_setup) {
- /* translators: opening curly quote */
- $opening_quote = _x('“', 'opening curly quote');
- /* translators: closing curly quote */
- $closing_quote = _x('”', 'closing curly quote');
+ /* translators: apostrophe, for example in 'cause or can't */
+ $apos = _x( '’', 'apostrophe' );
+
+ /* translators: prime, for example in 9' (nine feet) */
+ $prime = _x( '′', 'prime' );
+ /* translators: double prime, for example in 9" (nine inches) */
+ $double_prime = _x( '″', 'double prime' );
+
+ /* translators: opening curly single quote */
+ $opening_single_quote = _x( '‘', 'opening curly single quote' );
+ /* translators: closing curly single quote */
+ $closing_single_quote = _x( '’', 'closing curly single quote' );
+
+ /* translators: en dash */
+ $en_dash = _x( '–', 'en dash' );
+ /* translators: em dash */
+ $em_dash = _x( '—', 'em dash' );
$default_no_texturize_tags = array('pre', 'code', 'kbd', 'style', 'script', 'tt');
$default_no_texturize_shortcodes = array('code');
// if a plugin has provided an autocorrect array, use it
if ( isset($wp_cockneyreplace) ) {
- $cockney = array_keys($wp_cockneyreplace);
- $cockneyreplace = array_values($wp_cockneyreplace);
+ $cockney = array_keys( $wp_cockneyreplace );
+ $cockneyreplace = array_values( $wp_cockneyreplace );
+ } elseif ( "'" != $apos ) { // Only bother if we're doing a replacement.
+ $cockney = array( "'tain't", "'twere", "'twas", "'tis", "'twill", "'til", "'bout", "'nuff", "'round", "'cause", "'em" );
+ $cockneyreplace = array( $apos . "tain" . $apos . "t", $apos . "twere", $apos . "twas", $apos . "tis", $apos . "twill", $apos . "til", $apos . "bout", $apos . "nuff", $apos . "round", $apos . "cause", $apos . "em" );
} else {
- $cockney = array("'tain't","'twere","'twas","'tis","'twill","'til","'bout","'nuff","'round","'cause");
- $cockneyreplace = array("’tain’t","’twere","’twas","’tis","’twill","’til","’bout","’nuff","’round","’cause");
+ $cockney = $cockneyreplace = array();
+ }
+
+ $static_characters = array_merge( array( '...', '``', '\'\'', ' (tm)' ), $cockney );
+ $static_replacements = array_merge( array( '…', $opening_quote, $closing_quote, ' ™' ), $cockneyreplace );
+
+
+ // Pattern-based replacements of characters.
+ // Sort the remaining patterns into several arrays for performance tuning.
+ $dynamic_characters = array( 'apos' => array(), 'quote' => array(), 'dash' => array() );
+ $dynamic_replacements = array( 'apos' => array(), 'quote' => array(), 'dash' => array() );
+ $dynamic = array();
+ $spaces = wp_spaces_regexp();
+
+ // '99' and '99" are ambiguous among other patterns; assume it's an abbreviated year at the end of a quotation.
+ if ( "'" !== $apos || "'" !== $closing_single_quote ) {
+ $dynamic[ '/\'(\d\d)\'(?=\Z|[.,)}\-\]]|>|' . $spaces . ')/' ] = $apos . '$1' . $closing_single_quote;
+ }
+ if ( "'" !== $apos || '"' !== $closing_quote ) {
+ $dynamic[ '/\'(\d\d)"(?=\Z|[.,)}\-\]]|>|' . $spaces . ')/' ] = $apos . '$1' . $closing_quote;
+ }
+
+ // '99 '99s '99's (apostrophe) But never '9 or '99% or '999 or '99.0.
+ if ( "'" !== $apos ) {
+ $dynamic[ '/\'(?=\d\d(?:\Z|(?![%\d]|[.,]\d)))/' ] = $apos;
+ }
+
+ // Quoted Numbers like '0.42'
+ if ( "'" !== $opening_single_quote && "'" !== $closing_single_quote ) {
+ $dynamic[ '/(?<=\A|' . $spaces . ')\'(\d[.,\d]*)\'/' ] = $opening_single_quote . '$1' . $closing_single_quote;
+ }
+
+ // Single quote at start, or preceded by (, {, <, [, ", -, or spaces.
+ if ( "'" !== $opening_single_quote ) {
+ $dynamic[ '/(?<=\A|[([{"\-]|<|' . $spaces . ')\'/' ] = $opening_single_quote;
+ }
+
+ // Apostrophe in a word. No spaces, double apostrophes, or other punctuation.
+ if ( "'" !== $apos ) {
+ $dynamic[ '/(?');
- elseif ('[' == $curl[0])
- _wptexturize_pushpop_element($curl, $no_texturize_shortcodes_stack, $no_texturize_shortcodes, '[', ']');
- }
+ // Look for shortcodes and HTML elements.
+
+ $tagnames = array_keys( $shortcode_tags );
+ $tagregexp = join( '|', array_map( 'preg_quote', $tagnames ) );
+ $tagregexp = "(?:$tagregexp)(?![\\w-])"; // Excerpt of get_shortcode_regex().
+
+ $comment_regex =
+ '!' // Start of comment, after the <.
+ . '(?:' // Unroll the loop: Consume everything until --> is found.
+ . '-(?!->)' // Dash not followed by end of comment.
+ . '[^\-]*+' // Consume non-dashes.
+ . ')*+' // Loop possessively.
+ . '(?:-->)?'; // End of comment. If not found, match all input.
+
+ $shortcode_regex =
+ '\[' // Find start of shortcode.
+ . '[\/\[]?' // Shortcodes may begin with [/ or [[
+ . $tagregexp // Only match registered shortcodes, because performance.
+ . '(?:'
+ . '[^\[\]<>]+' // Shortcodes do not contain other shortcodes. Quantifier critical.
+ . '|'
+ . '<[^\[\]>]*>' // HTML elements permitted. Prevents matching ] before >.
+ . ')*+' // Possessive critical.
+ . '\]' // Find end of shortcode.
+ . '\]?'; // Shortcodes may end with ]]
+
+ $regex =
+ '/(' // Capture the entire match.
+ . '<' // Find start of element.
+ . '(?(?=!--)' // Is this a comment?
+ . $comment_regex // Find end of comment.
+ . '|'
+ . '[^>]*>' // Find end of element.
+ . ')'
+ . '|'
+ . $shortcode_regex // Find shortcodes.
+ . ')/s';
+
+ $textarr = preg_split( $regex, $text, -1, PREG_SPLIT_DELIM_CAPTURE | PREG_SPLIT_NO_EMPTY );
+
+ foreach ( $textarr as &$curl ) {
+ // Only call _wptexturize_pushpop_element if $curl is a delimiter.
+ $first = $curl[0];
+ if ( '<' === $first && ' is found.
+ . '-(?!->)' // Dash not followed by end of comment.
+ . '[^\-]*+' // Consume non-dashes.
+ . ')*+' // Loop possessively.
+ . '(?:-->)?'; // End of comment. If not found, match all input.
+
+ $regex =
+ '/(' // Capture the entire match.
+ . '<' // Find start of element.
+ . '(?(?=!--)' // Is this a comment?
+ . $comments // Find end of comment.
+ . '|'
+ . '[^>]*>?' // Find end of element. If not found, match all input.
+ . ')'
+ . ')/s';
+
+ $textarr = preg_split( $regex, $haystack, -1, PREG_SPLIT_DELIM_CAPTURE );
+ $changed = false;
+
+ // Optimize when searching for one item.
+ if ( 1 === count( $replace_pairs ) ) {
+ // Extract $needle and $replace.
+ foreach ( $replace_pairs as $needle => $replace );
+
+ // Loop through delimeters (elements) only.
+ for ( $i = 1, $c = count( $textarr ); $i < $c; $i += 2 ) {
+ if ( false !== strpos( $textarr[$i], $needle ) ) {
+ $textarr[$i] = str_replace( $needle, $replace, $textarr[$i] );
+ $changed = true;
+ }
+ }
+ } else {
+ // Extract all $needles.
+ $needles = array_keys( $replace_pairs );
+
+ // Loop through delimeters (elements) only.
+ for ( $i = 1, $c = count( $textarr ); $i < $c; $i += 2 ) {
+ foreach ( $needles as $needle ) {
+ if ( false !== strpos( $textarr[$i], $needle ) ) {
+ $textarr[$i] = strtr( $textarr[$i], $replace_pairs );
+ $changed = true;
+ // After one strtr() break out of the foreach loop and look at next element.
+ break;
+ }
+ }
+ }
+ }
+
+ if ( $changed ) {
+ $haystack = implode( $textarr );
+ }
+
+ return $haystack;
+}
+
/**
* Newline preservation help function for wpautop
*
* @since 3.1.0
* @access private
+ *
* @param array $matches preg_replace_callback matches array
- * @returns string
+ * @return string
*/
function _autop_newline_preservation_helper( $matches ) {
return str_replace("\n", "
>...<
>. + * Ensures that shortcodes are not wrapped in `...
`. * * @since 2.9.0 * * @param string $pee The content. * @return string The filtered content. */ -function shortcode_unautop($pee) { +function shortcode_unautop( $pee ) { global $shortcode_tags; - if ( !empty($shortcode_tags) && is_array($shortcode_tags) ) { - $tagnames = array_keys($shortcode_tags); - $tagregexp = join( '|', array_map('preg_quote', $tagnames) ); - $pee = preg_replace('/\\s*?(\\[(' . $tagregexp . ')\\b.*?\\/?\\](?:.+?\\[\\/\\2\\])?)\\s*<\\/p>/s', '$1', $pee); + if ( empty( $shortcode_tags ) || !is_array( $shortcode_tags ) ) { + return $pee; } - return $pee; + $tagregexp = join( '|', array_map( 'preg_quote', array_keys( $shortcode_tags ) ) ); + $spaces = wp_spaces_regexp(); + + $pattern = + '/' + . '
' // Opening paragraph + . '(?:' . $spaces . ')*+' // Optional leading whitespace + . '(' // 1: The shortcode + . '\\[' // Opening bracket + . "($tagregexp)" // 2: Shortcode name + . '(?![\\w-])' // Not followed by word character or hyphen + // Unroll the loop: Inside the opening shortcode tag + . '[^\\]\\/]*' // Not a closing bracket or forward slash + . '(?:' + . '\\/(?!\\])' // A forward slash not followed by a closing bracket + . '[^\\]\\/]*' // Not a closing bracket or forward slash + . ')*?' + . '(?:' + . '\\/\\]' // Self closing tag and closing bracket + . '|' + . '\\]' // Closing bracket + . '(?:' // Unroll the loop: Optionally, anything between the opening and closing shortcode tags + . '[^\\[]*+' // Not an opening bracket + . '(?:' + . '\\[(?!\\/\\2\\])' // An opening bracket not followed by the closing shortcode tag + . '[^\\[]*+' // Not an opening bracket + . ')*+' + . '\\[\\/\\2\\]' // Closing shortcode tag + . ')?' + . ')' + . ')' + . '(?:' . $spaces . ')*+' // optional trailing whitespace + . '<\\/p>' // closing paragraph + . '/s'; + + return preg_replace( $pattern, '$1', $pee ); } /** @@ -268,17 +661,19 @@ function shortcode_unautop($pee) { * @return bool True if $str fits a UTF-8 model, false otherwise. */ function seems_utf8($str) { + mbstring_binary_safe_encoding(); $length = strlen($str); + reset_mbstring_encoding(); for ($i=0; $i < $length; $i++) { $c = ord($str[$i]); - if ($c < 0x80) $n = 0; # 0bbbbbbb - elseif (($c & 0xE0) == 0xC0) $n=1; # 110bbbbb - elseif (($c & 0xF0) == 0xE0) $n=2; # 1110bbbb - elseif (($c & 0xF8) == 0xF0) $n=3; # 11110bbb - elseif (($c & 0xFC) == 0xF8) $n=4; # 111110bb - elseif (($c & 0xFE) == 0xFC) $n=5; # 1111110b - else return false; # Does not match any model - for ($j=0; $j<$n; $j++) { # n bytes matching 10bbbbbb follow ? + if ($c < 0x80) $n = 0; // 0bbbbbbb + elseif (($c & 0xE0) == 0xC0) $n=1; // 110bbbbb + elseif (($c & 0xF0) == 0xE0) $n=2; // 1110bbbb + elseif (($c & 0xF8) == 0xF0) $n=3; // 11110bbb + elseif (($c & 0xFC) == 0xF8) $n=4; // 111110bb + elseif (($c & 0xFE) == 0xFC) $n=5; // 1111110b + else return false; // Does not match any model + for ($j=0; $j<$n; $j++) { // n bytes matching 10bbbbbb follow ? if ((++$i == $length) || ((ord($str[$i]) & 0xC0) != 0x80)) return false; } @@ -295,9 +690,10 @@ function seems_utf8($str) { * ", or ENT_QUOTES to do both. Default is ENT_NOQUOTES where no quotes are encoded. * * @since 1.2.2 + * @access private * * @param string $string The text which is to be encoded. - * @param mixed $quote_style Optional. Converts double quotes if set to ENT_COMPAT, both single and double if set to ENT_QUOTES or none if set to ENT_NOQUOTES. Also compatible with old values; converting single quotes if set to 'single', double if set to 'double' or both if otherwise set. Default is ENT_NOQUOTES. + * @param int $quote_style Optional. Converts double quotes if set to ENT_COMPAT, both single and double if set to ENT_QUOTES or none if set to ENT_NOQUOTES. Also compatible with old values; converting single quotes if set to 'single', double if set to 'double' or both if otherwise set. Default is ENT_NOQUOTES. * @param string $charset Optional. The character encoding of the string. Default is false. * @param boolean $double_encode Optional. Whether to encode existing html entities. Default is false. * @return string The encoded text with HTML entities. @@ -305,34 +701,31 @@ function seems_utf8($str) { function _wp_specialchars( $string, $quote_style = ENT_NOQUOTES, $charset = false, $double_encode = false ) { $string = (string) $string; - if ( 0 === strlen( $string ) ) { + if ( 0 === strlen( $string ) ) return ''; - } // Don't bother if there are no specialchars - saves some processing - if ( !preg_match( '/[&<>"\']/', $string ) ) { + if ( ! preg_match( '/[&<>"\']/', $string ) ) return $string; - } // Account for the previous behaviour of the function when the $quote_style is not an accepted value - if ( empty( $quote_style ) ) { + if ( empty( $quote_style ) ) $quote_style = ENT_NOQUOTES; - } elseif ( !in_array( $quote_style, array( 0, 2, 3, 'single', 'double' ), true ) ) { + elseif ( ! in_array( $quote_style, array( 0, 2, 3, 'single', 'double' ), true ) ) $quote_style = ENT_QUOTES; - } // Store the site charset as a static to avoid multiple calls to wp_load_alloptions() - if ( !$charset ) { + if ( ! $charset ) { static $_charset; - if ( !isset( $_charset ) ) { + if ( ! isset( $_charset ) ) { $alloptions = wp_load_alloptions(); $_charset = isset( $alloptions['blog_charset'] ) ? $alloptions['blog_charset'] : ''; } $charset = $_charset; } - if ( in_array( $charset, array( 'utf8', 'utf-8', 'UTF8' ) ) ) { + + if ( in_array( $charset, array( 'utf8', 'utf-8', 'UTF8' ) ) ) $charset = 'UTF-8'; - } $_quote_style = $quote_style; @@ -344,28 +737,27 @@ function _wp_specialchars( $string, $quote_style = ENT_NOQUOTES, $charset = fals } // Handle double encoding ourselves - if ( !$double_encode ) { + if ( $double_encode ) { + $string = @htmlspecialchars( $string, $quote_style, $charset ); + } else { + // Decode & into & $string = wp_specialchars_decode( $string, $_quote_style ); - /* Critical */ - // The previous line decodes &phrase; into &phrase; We must guarantee that &phrase; is valid before proceeding. - $string = wp_kses_normalize_entities($string); + // Guarantee every &entity; is valid or re-encode the & + $string = wp_kses_normalize_entities( $string ); - // Now proceed with custom double-encoding silliness - $string = preg_replace( '/&(#?x?[0-9a-z]+);/i', '|wp_entity|$1|/wp_entity|', $string ); - } - - $string = @htmlspecialchars( $string, $quote_style, $charset ); + // Now re-encode everything except &entity; + $string = preg_split( '/(?x?[0-9a-z]+;)/i', $string, -1, PREG_SPLIT_DELIM_CAPTURE ); - // Handle double encoding ourselves - if ( !$double_encode ) { - $string = str_replace( array( '|wp_entity|', '|/wp_entity|' ), array( '&', ';' ), $string ); + for ( $i = 0, $c = count( $string ); $i < $c; $i += 2 ) { + $string[$i] = @htmlspecialchars( $string[$i], $quote_style, $charset ); + } + $string = implode( '', $string ); } // Backwards compatibility - if ( 'single' === $_quote_style ) { + if ( 'single' === $_quote_style ) $string = str_replace( "'", ''', $string ); - } return $string; } @@ -378,7 +770,7 @@ function _wp_specialchars( $string, $quote_style = ENT_NOQUOTES, $charset = fals * $quote_style can be set to ENT_COMPAT to decode " entities, * or ENT_QUOTES to do both " and '. Default is ENT_NOQUOTES where no quotes are decoded. * - * @since 2.8 + * @since 2.8.0 * * @param string $string The text which is to be decoded. * @param mixed $quote_style Optional. Converts double quotes if set to ENT_COMPAT, both single and double if set to ENT_QUOTES or none if set to ENT_NOQUOTES. Also compatible with old _wp_specialchars() values; converting single quotes if set to 'single', double if set to 'double' or both if otherwise set. Default is ENT_NOQUOTES. @@ -435,7 +827,7 @@ function wp_specialchars_decode( $string, $quote_style = ENT_NOQUOTES ) { /** * Checks for invalid UTF8 in a string. * - * @since 2.8 + * @since 2.8.0 * * @param string $string The text which is to be checked. * @param boolean $strip Optional. Whether to attempt to strip out invalid UTF8. Default is false. @@ -495,7 +887,10 @@ function utf8_uri_encode( $utf8_string, $length = 0 ) { $num_octets = 1; $unicode_length = 0; + mbstring_binary_safe_encoding(); $string_length = strlen( $utf8_string ); + reset_mbstring_encoding(); + for ($i = 0; $i < $string_length; $i++ ) { $value = ord( $utf8_string[ $i ] ); @@ -506,21 +901,27 @@ function utf8_uri_encode( $utf8_string, $length = 0 ) { $unicode .= chr($value); $unicode_length++; } else { - if ( count( $values ) == 0 ) $num_octets = ( $value < 224 ) ? 2 : 3; + if ( count( $values ) == 0 ) { + if ( $value < 224 ) { + $num_octets = 2; + } elseif ( $value < 240 ) { + $num_octets = 3; + } else { + $num_octets = 4; + } + } $values[] = $value; if ( $length && ( $unicode_length + ($num_octets * 3) ) > $length ) break; if ( count( $values ) == $num_octets ) { - if ($num_octets == 3) { - $unicode .= '%' . dechex($values[0]) . '%' . dechex($values[1]) . '%' . dechex($values[2]); - $unicode_length += 9; - } else { - $unicode .= '%' . dechex($values[0]) . '%' . dechex($values[1]); - $unicode_length += 6; + for ( $j = 0; $j < $num_octets; $j++ ) { + $unicode .= '%' . dechex( $values[ $j ] ); } + $unicode_length += $num_octets * 3; + $values = array(); $num_octets = 1; } @@ -547,6 +948,7 @@ function remove_accents($string) { if (seems_utf8($string)) { $chars = array( // Decompositions for Latin-1 Supplement + chr(194).chr(170) => 'a', chr(194).chr(186) => 'o', chr(195).chr(128) => 'A', chr(195).chr(129) => 'A', chr(195).chr(130) => 'A', chr(195).chr(131) => 'A', chr(195).chr(132) => 'A', chr(195).chr(133) => 'A', @@ -573,11 +975,11 @@ function remove_accents($string) { chr(195).chr(176) => 'd', chr(195).chr(177) => 'n', chr(195).chr(178) => 'o', chr(195).chr(179) => 'o', chr(195).chr(180) => 'o', chr(195).chr(181) => 'o', - chr(195).chr(182) => 'o', chr(195).chr(182) => 'o', + chr(195).chr(182) => 'o', chr(195).chr(184) => 'o', chr(195).chr(185) => 'u', chr(195).chr(186) => 'u', chr(195).chr(187) => 'u', chr(195).chr(188) => 'u', chr(195).chr(189) => 'y', chr(195).chr(190) => 'th', - chr(195).chr(191) => 'y', + chr(195).chr(191) => 'y', chr(195).chr(152) => 'O', // Decompositions for Latin Extended-A chr(196).chr(128) => 'A', chr(196).chr(129) => 'a', chr(196).chr(130) => 'A', chr(196).chr(131) => 'a', @@ -649,10 +1051,100 @@ function remove_accents($string) { // Euro Sign chr(226).chr(130).chr(172) => 'E', // GBP (Pound) Sign - chr(194).chr(163) => ''); + chr(194).chr(163) => '', + // Vowels with diacritic (Vietnamese) + // unmarked + chr(198).chr(160) => 'O', chr(198).chr(161) => 'o', + chr(198).chr(175) => 'U', chr(198).chr(176) => 'u', + // grave accent + chr(225).chr(186).chr(166) => 'A', chr(225).chr(186).chr(167) => 'a', + chr(225).chr(186).chr(176) => 'A', chr(225).chr(186).chr(177) => 'a', + chr(225).chr(187).chr(128) => 'E', chr(225).chr(187).chr(129) => 'e', + chr(225).chr(187).chr(146) => 'O', chr(225).chr(187).chr(147) => 'o', + chr(225).chr(187).chr(156) => 'O', chr(225).chr(187).chr(157) => 'o', + chr(225).chr(187).chr(170) => 'U', chr(225).chr(187).chr(171) => 'u', + chr(225).chr(187).chr(178) => 'Y', chr(225).chr(187).chr(179) => 'y', + // hook + chr(225).chr(186).chr(162) => 'A', chr(225).chr(186).chr(163) => 'a', + chr(225).chr(186).chr(168) => 'A', chr(225).chr(186).chr(169) => 'a', + chr(225).chr(186).chr(178) => 'A', chr(225).chr(186).chr(179) => 'a', + chr(225).chr(186).chr(186) => 'E', chr(225).chr(186).chr(187) => 'e', + chr(225).chr(187).chr(130) => 'E', chr(225).chr(187).chr(131) => 'e', + chr(225).chr(187).chr(136) => 'I', chr(225).chr(187).chr(137) => 'i', + chr(225).chr(187).chr(142) => 'O', chr(225).chr(187).chr(143) => 'o', + chr(225).chr(187).chr(148) => 'O', chr(225).chr(187).chr(149) => 'o', + chr(225).chr(187).chr(158) => 'O', chr(225).chr(187).chr(159) => 'o', + chr(225).chr(187).chr(166) => 'U', chr(225).chr(187).chr(167) => 'u', + chr(225).chr(187).chr(172) => 'U', chr(225).chr(187).chr(173) => 'u', + chr(225).chr(187).chr(182) => 'Y', chr(225).chr(187).chr(183) => 'y', + // tilde + chr(225).chr(186).chr(170) => 'A', chr(225).chr(186).chr(171) => 'a', + chr(225).chr(186).chr(180) => 'A', chr(225).chr(186).chr(181) => 'a', + chr(225).chr(186).chr(188) => 'E', chr(225).chr(186).chr(189) => 'e', + chr(225).chr(187).chr(132) => 'E', chr(225).chr(187).chr(133) => 'e', + chr(225).chr(187).chr(150) => 'O', chr(225).chr(187).chr(151) => 'o', + chr(225).chr(187).chr(160) => 'O', chr(225).chr(187).chr(161) => 'o', + chr(225).chr(187).chr(174) => 'U', chr(225).chr(187).chr(175) => 'u', + chr(225).chr(187).chr(184) => 'Y', chr(225).chr(187).chr(185) => 'y', + // acute accent + chr(225).chr(186).chr(164) => 'A', chr(225).chr(186).chr(165) => 'a', + chr(225).chr(186).chr(174) => 'A', chr(225).chr(186).chr(175) => 'a', + chr(225).chr(186).chr(190) => 'E', chr(225).chr(186).chr(191) => 'e', + chr(225).chr(187).chr(144) => 'O', chr(225).chr(187).chr(145) => 'o', + chr(225).chr(187).chr(154) => 'O', chr(225).chr(187).chr(155) => 'o', + chr(225).chr(187).chr(168) => 'U', chr(225).chr(187).chr(169) => 'u', + // dot below + chr(225).chr(186).chr(160) => 'A', chr(225).chr(186).chr(161) => 'a', + chr(225).chr(186).chr(172) => 'A', chr(225).chr(186).chr(173) => 'a', + chr(225).chr(186).chr(182) => 'A', chr(225).chr(186).chr(183) => 'a', + chr(225).chr(186).chr(184) => 'E', chr(225).chr(186).chr(185) => 'e', + chr(225).chr(187).chr(134) => 'E', chr(225).chr(187).chr(135) => 'e', + chr(225).chr(187).chr(138) => 'I', chr(225).chr(187).chr(139) => 'i', + chr(225).chr(187).chr(140) => 'O', chr(225).chr(187).chr(141) => 'o', + chr(225).chr(187).chr(152) => 'O', chr(225).chr(187).chr(153) => 'o', + chr(225).chr(187).chr(162) => 'O', chr(225).chr(187).chr(163) => 'o', + chr(225).chr(187).chr(164) => 'U', chr(225).chr(187).chr(165) => 'u', + chr(225).chr(187).chr(176) => 'U', chr(225).chr(187).chr(177) => 'u', + chr(225).chr(187).chr(180) => 'Y', chr(225).chr(187).chr(181) => 'y', + // Vowels with diacritic (Chinese, Hanyu Pinyin) + chr(201).chr(145) => 'a', + // macron + chr(199).chr(149) => 'U', chr(199).chr(150) => 'u', + // acute accent + chr(199).chr(151) => 'U', chr(199).chr(152) => 'u', + // caron + chr(199).chr(141) => 'A', chr(199).chr(142) => 'a', + chr(199).chr(143) => 'I', chr(199).chr(144) => 'i', + chr(199).chr(145) => 'O', chr(199).chr(146) => 'o', + chr(199).chr(147) => 'U', chr(199).chr(148) => 'u', + chr(199).chr(153) => 'U', chr(199).chr(154) => 'u', + // grave accent + chr(199).chr(155) => 'U', chr(199).chr(156) => 'u', + ); + + // Used for locale-specific rules + $locale = get_locale(); + + if ( 'de_DE' == $locale ) { + $chars[ chr(195).chr(132) ] = 'Ae'; + $chars[ chr(195).chr(164) ] = 'ae'; + $chars[ chr(195).chr(150) ] = 'Oe'; + $chars[ chr(195).chr(182) ] = 'oe'; + $chars[ chr(195).chr(156) ] = 'Ue'; + $chars[ chr(195).chr(188) ] = 'ue'; + $chars[ chr(195).chr(159) ] = 'ss'; + } elseif ( 'da_DK' === $locale ) { + $chars[ chr(195).chr(134) ] = 'Ae'; + $chars[ chr(195).chr(166) ] = 'ae'; + $chars[ chr(195).chr(152) ] = 'Oe'; + $chars[ chr(195).chr(184) ] = 'oe'; + $chars[ chr(195).chr(133) ] = 'Aa'; + $chars[ chr(195).chr(165) ] = 'aa'; + } $string = strtr($string, $chars); } else { + $chars = array(); // Assume ISO-8859-1 if not UTF-8 $chars['in'] = chr(128).chr(131).chr(138).chr(142).chr(154).chr(158) .chr(159).chr(162).chr(165).chr(181).chr(192).chr(193).chr(194) @@ -668,6 +1160,7 @@ function remove_accents($string) { $chars['out'] = "EfSZszYcYuAAAAAACEEEEIIIINOOOOOOUUUUYaaaaaaceeeeiiiinoooooouuuuyy"; $string = strtr($string, $chars['in'], $chars['out']); + $double_chars = array(); $double_chars['in'] = array(chr(140), chr(156), chr(198), chr(208), chr(222), chr(223), chr(230), chr(240), chr(254)); $double_chars['out'] = array('OE', 'oe', 'AE', 'DH', 'TH', 'ss', 'ae', 'dh', 'th'); $string = str_replace($double_chars['in'], $double_chars['out'], $string); @@ -677,12 +1170,12 @@ function remove_accents($string) { } /** - * Sanitizes a filename replacing whitespace with dashes + * Sanitizes a filename, replacing whitespace with dashes. * * Removes special characters that are illegal in filenames on certain * operating systems and special characters requiring special escaping * to manipulate at the command line. Replaces spaces and consecutive - * dashes with a single dash. Trim period, dash and underscore from beginning + * dashes with a single dash. Trims period, dash and underscore from beginning * and end of filename. * * @since 2.1.0 @@ -693,32 +1186,53 @@ function remove_accents($string) { function sanitize_file_name( $filename ) { $filename_raw = $filename; $special_chars = array("?", "[", "]", "/", "\\", "=", "<", ">", ":", ";", ",", "'", "\"", "&", "$", "#", "*", "(", ")", "|", "~", "`", "!", "{", "}", chr(0)); - $special_chars = apply_filters('sanitize_file_name_chars', $special_chars, $filename_raw); - $filename = str_replace($special_chars, '', $filename); - $filename = preg_replace('/[\s-]+/', '-', $filename); - $filename = trim($filename, '.-_'); + /** + * Filter the list of characters to remove from a filename. + * + * @since 2.8.0 + * + * @param array $special_chars Characters to remove. + * @param string $filename_raw Filename as it was passed into sanitize_file_name(). + */ + $special_chars = apply_filters( 'sanitize_file_name_chars', $special_chars, $filename_raw ); + $filename = preg_replace( "#\x{00a0}#siu", ' ', $filename ); + $filename = str_replace( $special_chars, '', $filename ); + $filename = str_replace( array( '%20', '+' ), '-', $filename ); + $filename = preg_replace( '/[\r\n\t -]+/', '-', $filename ); + $filename = trim( $filename, '.-_' ); // Split the filename into a base and extension[s] $parts = explode('.', $filename); // Return if only one extension - if ( count($parts) <= 2 ) - return apply_filters('sanitize_file_name', $filename, $filename_raw); + if ( count( $parts ) <= 2 ) { + /** + * Filter a sanitized filename string. + * + * @since 2.8.0 + * + * @param string $filename Sanitized filename. + * @param string $filename_raw The filename prior to sanitization. + */ + return apply_filters( 'sanitize_file_name', $filename, $filename_raw ); + } // Process multiple extensions $filename = array_shift($parts); $extension = array_pop($parts); $mimes = get_allowed_mime_types(); - // Loop over any intermediate extensions. Munge them with a trailing underscore if they are a 2 - 5 character - // long alpha string not in the extension whitelist. + /* + * Loop over any intermediate extensions. Postfix them with a trailing underscore + * if they are a 2 - 5 character long alpha string not in the extension whitelist. + */ foreach ( (array) $parts as $part) { $filename .= '.' . $part; if ( preg_match("/^[a-zA-Z]{2,5}\d?$/", $part) ) { $allowed = false; foreach ( $mimes as $ext_preg => $mime_match ) { - $ext_preg = '!(^' . $ext_preg . ')$!i'; + $ext_preg = '!^(' . $ext_preg . ')$!i'; if ( preg_match( $ext_preg, $part ) ) { $allowed = true; break; @@ -729,12 +1243,12 @@ function sanitize_file_name( $filename ) { } } $filename .= '.' . $extension; - + /** This filter is documented in wp-includes/formatting.php */ return apply_filters('sanitize_file_name', $filename, $filename_raw); } /** - * Sanitize username stripping out unsafe characters. + * Sanitizes a username, stripping out unsafe characters. * * Removes tags, octets, entities, and if strict is enabled, will only keep * alphanumeric, _, space, ., -, @. After sanitizing, it passes the username, @@ -742,8 +1256,6 @@ function sanitize_file_name( $filename ) { * parameters for the 'sanitize_user' filter. * * @since 2.0.0 - * @uses apply_filters() Calls 'sanitize_user' hook on username, raw username, - * and $strict parameter. * * @param string $username The username to be sanitized. * @param bool $strict If set limits $username to specific characters. Default false. @@ -765,11 +1277,20 @@ function sanitize_user( $username, $strict = false ) { // Consolidate contiguous whitespace $username = preg_replace( '|\s+|', ' ', $username ); + /** + * Filter a sanitized username string. + * + * @since 2.0.1 + * + * @param string $username Sanitized username. + * @param string $raw_username The username prior to sanitization. + * @param bool $strict Whether to limit the sanitization to specific characters. Default false. + */ return apply_filters( 'sanitize_user', $username, $raw_username, $strict ); } /** - * Sanitize a string key. + * Sanitizes a string key. * * Keys are used as internal identifiers. Lowercase alphanumeric characters, dashes and underscores are allowed. * @@ -782,11 +1303,20 @@ function sanitize_key( $key ) { $raw_key = $key; $key = strtolower( $key ); $key = preg_replace( '/[^a-z0-9_\-]/', '', $key ); + + /** + * Filter a sanitized key string. + * + * @since 3.0.0 + * + * @param string $key Sanitized key. + * @param string $raw_key The key prior to sanitization. + */ return apply_filters( 'sanitize_key', $key, $raw_key ); } /** - * Sanitizes title or use fallback title. + * Sanitizes a title, or returns a fallback title. * * Specifically, HTML and PHP tags are stripped. Further actions can be added * via the plugin API. If $title is empty and $fallback_title is set, the latter @@ -799,13 +1329,22 @@ function sanitize_key( $key ) { * @param string $context Optional. The operation for which the string is sanitized * @return string The sanitized string. */ -function sanitize_title($title, $fallback_title = '', $context = 'save') { +function sanitize_title( $title, $fallback_title = '', $context = 'save' ) { $raw_title = $title; if ( 'save' == $context ) $title = remove_accents($title); - $title = apply_filters('sanitize_title', $title, $raw_title, $context); + /** + * Filter a sanitized title string. + * + * @since 1.2.0 + * + * @param string $title Sanitized title. + * @param string $raw_title The title prior to sanitization. + * @param string $context The context for which the title is being sanitized. + */ + $title = apply_filters( 'sanitize_title', $title, $raw_title, $context ); if ( '' === $title || false === $title ) $title = $fallback_title; @@ -813,12 +1352,22 @@ function sanitize_title($title, $fallback_title = '', $context = 'save') { return $title; } -function sanitize_title_for_query($title) { - return sanitize_title($title, '', 'query'); +/** + * Sanitizes a title with the 'query' context. + * + * Used for querying the database for a value from URL. + * + * @since 3.1.0 + * + * @param string $title The string to be sanitized. + * @return string The sanitized string. + */ +function sanitize_title_for_query( $title ) { + return sanitize_title( $title, '', 'query' ); } /** - * Sanitizes title, replacing whitespace with dashes. + * Sanitizes a title, replacing whitespace and a few other characters with dashes. * * Limits the output to alphanumeric characters, underscore (_) and dash (-). * Whitespace becomes a dash. @@ -826,9 +1375,11 @@ function sanitize_title_for_query($title) { * @since 1.2.0 * * @param string $title The title to be sanitized. + * @param string $raw_title Optional. Not used. + * @param string $context Optional. The operation for which the string is sanitized. * @return string The sanitized title. */ -function sanitize_title_with_dashes($title) { +function sanitize_title_with_dashes( $title, $raw_title = '', $context = 'display' ) { $title = strip_tags($title); // Preserve escaped octets. $title = preg_replace('|%([a-fA-F0-9][a-fA-F0-9])|', '---$1---', $title); @@ -847,6 +1398,32 @@ function sanitize_title_with_dashes($title) { $title = strtolower($title); $title = preg_replace('/&.+?;/', '', $title); // kill entities $title = str_replace('.', '-', $title); + + if ( 'save' == $context ) { + // Convert nbsp, ndash and mdash to hyphens + $title = str_replace( array( '%c2%a0', '%e2%80%93', '%e2%80%94' ), '-', $title ); + + // Strip these characters entirely + $title = str_replace( array( + // iexcl and iquest + '%c2%a1', '%c2%bf', + // angle quotes + '%c2%ab', '%c2%bb', '%e2%80%b9', '%e2%80%ba', + // curly quotes + '%e2%80%98', '%e2%80%99', '%e2%80%9c', '%e2%80%9d', + '%e2%80%9a', '%e2%80%9b', '%e2%80%9e', '%e2%80%9f', + // copy, reg, deg, hellip and trade + '%c2%a9', '%c2%ae', '%c2%b0', '%e2%80%a6', '%e2%84%a2', + // acute accents + '%c2%b4', '%cb%8a', '%cc%81', '%cd%81', + // grave accent, macron, caron + '%cc%80', '%cc%84', '%cc%8c', + ), '', $title ); + + // Convert times to x + $title = str_replace( '%c3%97', 'x', $title ); + } + $title = preg_replace('/[^%a-z0-9 _-]/', '', $title); $title = preg_replace('/\s+/', '-', $title); $title = preg_replace('|-+|', '-', $title); @@ -856,27 +1433,29 @@ function sanitize_title_with_dashes($title) { } /** - * Ensures a string is a valid SQL order by clause. + * Ensures a string is a valid SQL 'order by' clause. + * + * Accepts one or more columns, with or without a sort order (ASC / DESC). + * e.g. 'column_1', 'column_1, column_2', 'column_1 ASC, column_2 DESC' etc. * - * Accepts one or more columns, with or without ASC/DESC, and also accepts - * RAND(). + * Also accepts 'RAND()'. * * @since 2.5.1 * - * @param string $orderby Order by string to be checked. - * @return string|false Returns the order by clause if it is a match, false otherwise. + * @param string $orderby Order by clause to be validated. + * @return string|bool Returns $orderby if valid, false otherwise. */ -function sanitize_sql_orderby( $orderby ){ - preg_match('/^\s*([a-z0-9_]+(\s+(ASC|DESC))?(\s*,\s*|\s*$))+|^\s*RAND\(\s*\)\s*$/i', $orderby, $obmatches); - if ( !$obmatches ) - return false; - return $orderby; +function sanitize_sql_orderby( $orderby ) { + if ( preg_match( '/^\s*(([a-z0-9_]+|`[a-z0-9_]+`)(\s+(ASC|DESC))?\s*(,\s*(?=[a-z0-9_`])|$))+$/i', $orderby ) || preg_match( '/^\s*RAND\(\s*\)\s*$/i', $orderby ) ) { + return $orderby; + } + return false; } /** - * Santizes a html classname to ensure it only contains valid characters + * Sanitizes an HTML classname to ensure it only contains valid characters. * - * Strips the string down to A-Z,a-z,0-9,'-' if this results in an empty + * Strips the string down to A-Z,a-z,0-9,_,-. If this results in an empty * string then it will return the alternative value supplied. * * @todo Expand to support the full range of CDATA that a class attribute can contain. @@ -884,27 +1463,36 @@ function sanitize_sql_orderby( $orderby ){ * @since 2.8.0 * * @param string $class The classname to be sanitized - * @param string $fallback Optional. The value to return if the sanitization end's up as an empty string. + * @param string $fallback Optional. The value to return if the sanitization ends up as an empty string. * Defaults to an empty string. * @return string The sanitized value */ function sanitize_html_class( $class, $fallback = '' ) { //Strip out any % encoded octets - $sanitized = preg_replace('|%[a-fA-F0-9][a-fA-F0-9]|', '', $class); + $sanitized = preg_replace( '|%[a-fA-F0-9][a-fA-F0-9]|', '', $class ); - //Limit to A-Z,a-z,0-9,'-' - $sanitized = preg_replace('/[^A-Za-z0-9-]/', '', $sanitized); + //Limit to A-Z,a-z,0-9,_,- + $sanitized = preg_replace( '/[^A-Za-z0-9_-]/', '', $sanitized ); if ( '' == $sanitized ) $sanitized = $fallback; + /** + * Filter a sanitized HTML class string. + * + * @since 2.8.0 + * + * @param string $sanitized The sanitized HTML class. + * @param string $class HTML class before sanitization. + * @param string $fallback The fallback string. + */ return apply_filters( 'sanitize_html_class', $sanitized, $class, $fallback ); } /** * Converts a number of characters from a string. * - * Metadata tags <
or
+ foreach ( $textarr as $piece ) {
+
+ if ( preg_match( '|^]|i', $piece ) || preg_match( '|^]|i', $piece ) )
+ $nested_code_pre++;
+ elseif ( ( '
' === strtolower( $piece ) || '
' === strtolower( $piece ) ) && $nested_code_pre )
+ $nested_code_pre--;
+
+ if ( $nested_code_pre || empty( $piece ) || ( $piece[0] === '<' && ! preg_match( '|^<\s*[\w]{1,20}+://|', $piece ) ) ) {
+ $r .= $piece;
+ continue;
+ }
+
+ // Long strings might contain expensive edge cases ...
+ if ( 10000 < strlen( $piece ) ) {
+ // ... break it up
+ foreach ( _split_str_by_whitespace( $piece, 2100 ) as $chunk ) { // 2100: Extra room for scheme and leading and trailing paretheses
+ if ( 2101 < strlen( $chunk ) ) {
+ $r .= $chunk; // Too big, no whitespace: bail.
+ } else {
+ $r .= make_clickable( $chunk );
+ }
+ }
+ } else {
+ $ret = " $piece "; // Pad with whitespace to simplify the regexes
+
+ $url_clickable = '~
+ ([\\s(<.,;:!?]) # 1: Leading whitespace, or punctuation
+ ( # 2: URL
+ [\\w]{1,20}+:// # Scheme and hier-part prefix
+ (?=\S{1,2000}\s) # Limit to URLs less than about 2000 characters long
+ [\\w\\x80-\\xff#%\\~/@\\[\\]*(+=&$-]*+ # Non-punctuation URL character
+ (?: # Unroll the Loop: Only allow puctuation URL character if followed by a non-punctuation URL character
+ [\'.,;:!?)] # Punctuation URL character
+ [\\w\\x80-\\xff#%\\~/@\\[\\]*(+=&$-]++ # Non-punctuation URL character
+ )*
+ )
+ (\)?) # 3: Trailing closing parenthesis (for parethesis balancing post processing)
+ ~xS'; // The regex is a non-anchored pattern and does not have a single fixed starting character.
+ // Tell PCRE to spend more time optimizing since, when used on a page load, it will probably be used several times.
+
+ $ret = preg_replace_callback( $url_clickable, '_make_url_clickable_cb', $ret );
+
+ $ret = preg_replace_callback( '#([\s>])((www|ftp)\.[\w\\x80-\\xff\#$%&~/.\-;:=,?@\[\]+]+)#is', '_make_web_ftp_clickable_cb', $ret );
+ $ret = preg_replace_callback( '#([\s>])([.0-9a-z_+-]+)@(([0-9a-z-]+\.)+[0-9a-z]{2,})#i', '_make_email_clickable_cb', $ret );
+
+ $ret = substr( $ret, 1, -1 ); // Remove our whitespace padding.
+ $r .= $ret;
+ }
+ }
+
+ // Cleanup of accidental links within links
+ $r = preg_replace( '#(]+?>|>))]+?>([^>]+?)#i', "$1$3", $r );
+ return $r;
+}
+
+/**
+ * Breaks a string into chunks by splitting at whitespace characters.
+ * The length of each returned chunk is as close to the specified length goal as possible,
+ * with the caveat that each chunk includes its trailing delimiter.
+ * Chunks longer than the goal are guaranteed to not have any inner whitespace.
+ *
+ * Joining the returned chunks with empty delimiters reconstructs the input string losslessly.
+ *
+ * Input string must have no null characters (or eventual transformations on output chunks must not care about null characters)
+ *
+ * _split_str_by_whitespace( "1234 67890 1234 67890a cd 1234 890 123456789 1234567890a 45678 1 3 5 7 90 ", 10 ) ==
+ * array (
+ * 0 => '1234 67890 ', // 11 characters: Perfect split
+ * 1 => '1234 ', // 5 characters: '1234 67890a' was too long
+ * 2 => '67890a cd ', // 10 characters: '67890a cd 1234' was too long
+ * 3 => '1234 890 ', // 11 characters: Perfect split
+ * 4 => '123456789 ', // 10 characters: '123456789 1234567890a' was too long
+ * 5 => '1234567890a ', // 12 characters: Too long, but no inner whitespace on which to split
+ * 6 => ' 45678 ', // 11 characters: Perfect split
+ * 7 => '1 3 5 7 90 ', // 11 characters: End of $string
+ * );
+ *
+ * @since 3.4.0
+ * @access private
+ *
+ * @param string $string The string to split.
+ * @param int $goal The desired chunk length.
+ * @return array Numeric array of chunks.
+ */
+function _split_str_by_whitespace( $string, $goal ) {
+ $chunks = array();
+
+ $string_nullspace = strtr( $string, "\r\n\t\v\f ", "\000\000\000\000\000\000" );
+
+ while ( $goal < strlen( $string_nullspace ) ) {
+ $pos = strrpos( substr( $string_nullspace, 0, $goal + 1 ), "\000" );
+
+ if ( false === $pos ) {
+ $pos = strpos( $string_nullspace, "\000", $goal + 1 );
+ if ( false === $pos ) {
+ break;
+ }
+ }
+
+ $chunks[] = substr( $string, 0, $pos + 1 );
+ $string = substr( $string, $pos + 1 );
+ $string_nullspace = substr( $string_nullspace, $pos + 1 );
+ }
+
+ if ( $string ) {
+ $chunks[] = $string;
+ }
+
+ return $chunks;
}
/**
@@ -1407,12 +2119,12 @@ function wp_rel_nofollow( $text ) {
// This is a pre save filter, so text is already escaped.
$text = stripslashes($text);
$text = preg_replace_callback('||i', 'wp_rel_nofollow_callback', $text);
- $text = esc_sql($text);
+ $text = wp_slash($text);
return $text;
}
/**
- * Callback to used to add rel=nofollow string to HTML A element.
+ * Callback to add rel=nofollow string to HTML A element.
*
* Will remove already existing rel="nofollow" and rel='nofollow' from the
* string to prevent from invalidating (X)HTML.
@@ -1431,29 +2143,46 @@ function wp_rel_nofollow_callback( $matches ) {
/**
* Convert one smiley code to the icon graphic file equivalent.
*
+ * Callback handler for {@link convert_smilies()}.
* Looks up one smiley code in the $wpsmiliestrans global array and returns an
- * string for that smiley.
+ * `` string for that smiley.
*
* @global array $wpsmiliestrans
* @since 2.8.0
*
- * @param string $smiley Smiley code to convert to image.
+ * @param array $matches Single match. Smiley code to convert to image.
* @return string Image string for smiley.
*/
-function translate_smiley($smiley) {
+function translate_smiley( $matches ) {
global $wpsmiliestrans;
- if (count($smiley) == 0) {
+ if ( count( $matches ) == 0 )
return '';
- }
- $smiley = trim(reset($smiley));
- $img = $wpsmiliestrans[$smiley];
- $smiley_masked = esc_attr($smiley);
+ $smiley = trim( reset( $matches ) );
+ $img = $wpsmiliestrans[ $smiley ];
+
+ $matches = array();
+ $ext = preg_match( '/\.([^.]+)$/', $img, $matches ) ? strtolower( $matches[1] ) : false;
+ $image_exts = array( 'jpg', 'jpeg', 'jpe', 'gif', 'png' );
+
+ // Don't convert smilies that aren't images - they're probably emoji.
+ if ( ! in_array( $ext, $image_exts ) ) {
+ return $img;
+ }
- $srcurl = apply_filters('smilies_src', includes_url("images/smilies/$img"), $img, site_url());
+ /**
+ * Filter the Smiley image URL before it's used in the image element.
+ *
+ * @since 2.9.0
+ *
+ * @param string $smiley_url URL for the smiley image.
+ * @param string $img Filename for the smiley image.
+ * @param string $site_url Site URL, as returned by site_url().
+ */
+ $src_url = apply_filters( 'smilies_src', includes_url( "images/smilies/$img" ), $img, site_url() );
- return " ";
+ return sprintf( '', esc_url( $src_url ), esc_attr( $smiley ) );
}
/**
@@ -1468,18 +2197,36 @@ function translate_smiley($smiley) {
* @param string $text Content to convert smilies from text.
* @return string Converted content with text smilies replaced with images.
*/
-function convert_smilies($text) {
+function convert_smilies( $text ) {
global $wp_smiliessearch;
$output = '';
- if ( get_option('use_smilies') && !empty($wp_smiliessearch) ) {
+ if ( get_option( 'use_smilies' ) && ! empty( $wp_smiliessearch ) ) {
// HTML loop taken from texturize function, could possible be consolidated
- $textarr = preg_split("/(<.*>)/U", $text, -1, PREG_SPLIT_DELIM_CAPTURE); // capture the tags as well as in between
- $stop = count($textarr);// loop stuff
- for ($i = 0; $i < $stop; $i++) {
+ $textarr = preg_split( '/(<.*>)/U', $text, -1, PREG_SPLIT_DELIM_CAPTURE ); // capture the tags as well as in between
+ $stop = count( $textarr );// loop stuff
+
+ // Ignore proessing of specific tags
+ $tags_to_ignore = 'code|pre|style|script|textarea';
+ $ignore_block_element = '';
+
+ for ( $i = 0; $i < $stop; $i++ ) {
$content = $textarr[$i];
- if ((strlen($content) > 0) && ('<' != $content[0])) { // If it's not a tag
- $content = preg_replace_callback($wp_smiliessearch, 'translate_smiley', $content);
+
+ // If we're in an ignore block, wait until we find its closing tag
+ if ( '' == $ignore_block_element && preg_match( '/^<(' . $tags_to_ignore . ')>/', $content, $matches ) ) {
+ $ignore_block_element = $matches[1];
+ }
+
+ // If it's not a tag and not in ignore block
+ if ( '' == $ignore_block_element && strlen( $content ) > 0 && '<' != $content[0] ) {
+ $content = preg_replace_callback( $wp_smiliessearch, 'translate_smiley', $content );
+ }
+
+ // did we exit ignore block
+ if ( '' != $ignore_block_element && '' . $ignore_block_element . '>' == $content ) {
+ $ignore_block_element = '';
}
+
$output .= $content;
}
} else {
@@ -1506,11 +2253,26 @@ function is_email( $email, $deprecated = false ) {
// Test for the minimum length the email can be
if ( strlen( $email ) < 3 ) {
+ /**
+ * Filter whether an email address is valid.
+ *
+ * This filter is evaluated under several different contexts, such as 'email_too_short',
+ * 'email_no_at', 'local_invalid_chars', 'domain_period_sequence', 'domain_period_limits',
+ * 'domain_no_periods', 'sub_hyphen_limits', 'sub_invalid_chars', or no specific context.
+ *
+ * @since 2.8.0
+ *
+ * @param bool $is_email Whether the email address has passed the is_email() checks. Default false.
+ * @param string $email The email address being checked.
+ * @param string $message An explanatory message to the user.
+ * @param string $context Context under which the email was tested.
+ */
return apply_filters( 'is_email', false, $email, 'email_too_short' );
}
// Test for an @ character after the first position
if ( strpos( $email, '@', 1 ) === false ) {
+ /** This filter is documented in wp-includes/formatting.php */
return apply_filters( 'is_email', false, $email, 'email_no_at' );
}
@@ -1520,17 +2282,20 @@ function is_email( $email, $deprecated = false ) {
// LOCAL PART
// Test for invalid characters
if ( !preg_match( '/^[a-zA-Z0-9!#$%&\'*+\/=?^_`{|}~\.-]+$/', $local ) ) {
+ /** This filter is documented in wp-includes/formatting.php */
return apply_filters( 'is_email', false, $email, 'local_invalid_chars' );
}
// DOMAIN PART
// Test for sequences of periods
if ( preg_match( '/\.{2,}/', $domain ) ) {
+ /** This filter is documented in wp-includes/formatting.php */
return apply_filters( 'is_email', false, $email, 'domain_period_sequence' );
}
// Test for leading and trailing periods and whitespace
if ( trim( $domain, " \t\n\r\0\x0B." ) !== $domain ) {
+ /** This filter is documented in wp-includes/formatting.php */
return apply_filters( 'is_email', false, $email, 'domain_period_limits' );
}
@@ -1539,6 +2304,7 @@ function is_email( $email, $deprecated = false ) {
// Assume the domain will have at least two subs
if ( 2 > count( $subs ) ) {
+ /** This filter is documented in wp-includes/formatting.php */
return apply_filters( 'is_email', false, $email, 'domain_no_periods' );
}
@@ -1546,16 +2312,19 @@ function is_email( $email, $deprecated = false ) {
foreach ( $subs as $sub ) {
// Test for leading and trailing hyphens and whitespace
if ( trim( $sub, " \t\n\r\0\x0B-" ) !== $sub ) {
+ /** This filter is documented in wp-includes/formatting.php */
return apply_filters( 'is_email', false, $email, 'sub_hyphen_limits' );
}
// Test for invalid characters
if ( !preg_match('/^[a-z0-9-]+$/i', $sub ) ) {
+ /** This filter is documented in wp-includes/formatting.php */
return apply_filters( 'is_email', false, $email, 'sub_invalid_chars' );
}
}
// Congratulations your email made it!
+ /** This filter is documented in wp-includes/formatting.php */
return apply_filters( 'is_email', $email, $email, null );
}
@@ -1563,7 +2332,6 @@ function is_email( $email, $deprecated = false ) {
* Convert to ASCII from email subjects.
*
* @since 1.2.0
- * @usedby wp_mail() handles charsets in email subjects
*
* @param string $string Subject line
* @return string Converted string to ASCII
@@ -1580,11 +2348,13 @@ function wp_iso_descrambler($string) {
}
/**
- * Helper function to convert hex encoded chars to ascii
+ * Helper function to convert hex encoded chars to ASCII
*
* @since 3.1.0
* @access private
- * @param array $match the preg_replace_callback matches array
+ *
+ * @param array $match The preg_replace_callback matches array
+ * @return string Converted chars
*/
function _wp_iso_convert( $match ) {
return chr( hexdec( strtolower( $match[1] ) ) );
@@ -1593,36 +2363,30 @@ function _wp_iso_convert( $match ) {
/**
* Returns a date in the GMT equivalent.
*
- * Requires and returns a date in the Y-m-d H:i:s format. Simply subtracts the
- * value of the 'gmt_offset' option. Return format can be overridden using the
- * $format parameter. If PHP5 is supported, the function uses the DateTime and
- * DateTimeZone objects to respect time zone differences in DST.
+ * Requires and returns a date in the Y-m-d H:i:s format. If there is a
+ * timezone_string available, the date is assumed to be in that timezone,
+ * otherwise it simply subtracts the value of the 'gmt_offset' option. Return
+ * format can be overridden using the $format parameter.
*
* @since 1.2.0
*
- * @uses get_option() to retrieve the the value of 'gmt_offset'.
* @param string $string The date to be converted.
* @param string $format The format string for the returned date (default is Y-m-d H:i:s)
* @return string GMT version of the date provided.
*/
-function get_gmt_from_date($string, $format = 'Y-m-d H:i:s') {
- 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);
- $tz = get_option('timezone_string');
- if( class_exists('DateTime') && $tz ) {
- //PHP5
- date_default_timezone_set( $tz );
- $datetime = new DateTime( $string );
- $datetime->setTimezone( new DateTimeZone('UTC') );
- $offset = $datetime->getOffset();
- $datetime->modify( '+' . $offset / 3600 . ' hours');
- $string_gmt = gmdate($format, $datetime->format('U'));
-
- date_default_timezone_set('UTC');
- }
- else {
- //PHP4
- $string_time = gmmktime($matches[4], $matches[5], $matches[6], $matches[2], $matches[3], $matches[1]);
- $string_gmt = gmdate($format, $string_time - get_option('gmt_offset') * 3600);
+function get_gmt_from_date( $string, $format = 'Y-m-d H:i:s' ) {
+ $tz = get_option( 'timezone_string' );
+ if ( $tz ) {
+ $datetime = date_create( $string, new DateTimeZone( $tz ) );
+ if ( ! $datetime )
+ return gmdate( $format, 0 );
+ $datetime->setTimezone( new DateTimeZone( 'UTC' ) );
+ $string_gmt = $datetime->format( $format );
+ } else {
+ 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 ) )
+ return gmdate( $format, 0 );
+ $string_time = gmmktime( $matches[4], $matches[5], $matches[6], $matches[2], $matches[3], $matches[1] );
+ $string_gmt = gmdate( $format, $string_time - get_option( 'gmt_offset' ) * HOUR_IN_SECONDS );
}
return $string_gmt;
}
@@ -1630,19 +2394,31 @@ function get_gmt_from_date($string, $format = 'Y-m-d H:i:s') {
/**
* Converts a GMT date into the correct format for the blog.
*
- * Requires and returns in the Y-m-d H:i:s format. Simply adds the value of
- * gmt_offset.Return format can be overridden using the $format parameter
+ * Requires and returns a date in the Y-m-d H:i:s format. If there is a
+ * timezone_string available, the returned date is in that timezone, otherwise
+ * it simply adds the value of gmt_offset. Return format can be overridden
+ * using the $format parameter
*
* @since 1.2.0
*
* @param string $string The date to be converted.
* @param string $format The format string for the returned date (default is Y-m-d H:i:s)
- * @return string Formatted date relative to the GMT offset.
+ * @return string Formatted date relative to the timezone / GMT offset.
*/
-function get_date_from_gmt($string, $format = 'Y-m-d H:i:s') {
- 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);
- $string_time = gmmktime($matches[4], $matches[5], $matches[6], $matches[2], $matches[3], $matches[1]);
- $string_localtime = gmdate($format, $string_time + get_option('gmt_offset')*3600);
+function get_date_from_gmt( $string, $format = 'Y-m-d H:i:s' ) {
+ $tz = get_option( 'timezone_string' );
+ if ( $tz ) {
+ $datetime = date_create( $string, new DateTimeZone( 'UTC' ) );
+ if ( ! $datetime )
+ return date( $format, 0 );
+ $datetime->setTimezone( new DateTimeZone( $tz ) );
+ $string_localtime = $datetime->format( $format );
+ } else {
+ 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) )
+ return date( $format, 0 );
+ $string_time = gmmktime( $matches[4], $matches[5], $matches[6], $matches[2], $matches[3], $matches[1] );
+ $string_localtime = gmdate( $format, $string_time + get_option( 'gmt_offset' ) * HOUR_IN_SECONDS );
+ }
return $string_localtime;
}
@@ -1662,7 +2438,7 @@ function iso8601_timezone_to_offset($timezone) {
$sign = (substr($timezone, 0, 1) == '+') ? 1 : -1;
$hours = intval(substr($timezone, 1, 2));
$minutes = intval(substr($timezone, 3, 4)) / 60;
- $offset = $sign * 3600 * ($hours + $minutes);
+ $offset = $sign * HOUR_IN_SECONDS * ($hours + $minutes);
}
return $offset;
}
@@ -1686,7 +2462,7 @@ function iso8601_to_datetime($date_string, $timezone = 'user') {
if (!empty($date_bits[7])) { // we have a timezone, so let's compute an offset
$offset = iso8601_timezone_to_offset($date_bits[7]);
} else { // we don't have a timezone, so we assume user local timezone (not server's!)
- $offset = 3600 * get_option('gmt_offset');
+ $offset = HOUR_IN_SECONDS * get_option('gmt_offset');
}
$timestamp = gmmktime($date_bits[4], $date_bits[5], $date_bits[6], $date_bits[2], $date_bits[3], $date_bits[1]);
@@ -1694,7 +2470,7 @@ function iso8601_to_datetime($date_string, $timezone = 'user') {
return gmdate('Y-m-d H:i:s', $timestamp);
- } else if ($timezone == 'user') {
+ } elseif ($timezone == 'user') {
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', $date_string);
}
}
@@ -1727,11 +2503,25 @@ function popuplinks($text) {
function sanitize_email( $email ) {
// Test for the minimum length the email can be
if ( strlen( $email ) < 3 ) {
+ /**
+ * Filter a sanitized email address.
+ *
+ * This filter is evaluated under several contexts, including 'email_too_short',
+ * 'email_no_at', 'local_invalid_chars', 'domain_period_sequence', 'domain_period_limits',
+ * 'domain_no_periods', 'domain_no_valid_subs', or no context.
+ *
+ * @since 2.8.0
+ *
+ * @param string $email The sanitized email address.
+ * @param string $email The email address, as provided to sanitize_email().
+ * @param string $message A message to pass to the user.
+ */
return apply_filters( 'sanitize_email', '', $email, 'email_too_short' );
}
// Test for an @ character after the first position
if ( strpos( $email, '@', 1 ) === false ) {
+ /** This filter is documented in wp-includes/formatting.php */
return apply_filters( 'sanitize_email', '', $email, 'email_no_at' );
}
@@ -1742,6 +2532,7 @@ function sanitize_email( $email ) {
// Test for invalid characters
$local = preg_replace( '/[^a-zA-Z0-9!#$%&\'*+\/=?^_`{|}~\.-]/', '', $local );
if ( '' === $local ) {
+ /** This filter is documented in wp-includes/formatting.php */
return apply_filters( 'sanitize_email', '', $email, 'local_invalid_chars' );
}
@@ -1749,12 +2540,14 @@ function sanitize_email( $email ) {
// Test for sequences of periods
$domain = preg_replace( '/\.{2,}/', '', $domain );
if ( '' === $domain ) {
+ /** This filter is documented in wp-includes/formatting.php */
return apply_filters( 'sanitize_email', '', $email, 'domain_period_sequence' );
}
// Test for leading and trailing periods and whitespace
$domain = trim( $domain, " \t\n\r\0\x0B." );
if ( '' === $domain ) {
+ /** This filter is documented in wp-includes/formatting.php */
return apply_filters( 'sanitize_email', '', $email, 'domain_period_limits' );
}
@@ -1763,6 +2556,7 @@ function sanitize_email( $email ) {
// Assume the domain will have at least two subs
if ( 2 > count( $subs ) ) {
+ /** This filter is documented in wp-includes/formatting.php */
return apply_filters( 'sanitize_email', '', $email, 'domain_no_periods' );
}
@@ -1785,6 +2579,7 @@ function sanitize_email( $email ) {
// If there aren't 2 or more valid subs
if ( 2 > count( $new_subs ) ) {
+ /** This filter is documented in wp-includes/formatting.php */
return apply_filters( 'sanitize_email', '', $email, 'domain_no_valid_subs' );
}
@@ -1795,6 +2590,7 @@ function sanitize_email( $email ) {
$email = $local . '@' . $domain;
// Congratulations your email made it!
+ /** This filter is documented in wp-includes/formatting.php */
return apply_filters( 'sanitize_email', $email, $email, null );
}
@@ -1811,69 +2607,161 @@ function sanitize_email( $email ) {
* @return string Human readable time difference.
*/
function human_time_diff( $from, $to = '' ) {
- if ( empty($to) )
+ if ( empty( $to ) ) {
$to = time();
- $diff = (int) abs($to - $from);
- if ($diff <= 3600) {
- $mins = round($diff / 60);
- if ($mins <= 1) {
+ }
+
+ $diff = (int) abs( $to - $from );
+
+ if ( $diff < HOUR_IN_SECONDS ) {
+ $mins = round( $diff / MINUTE_IN_SECONDS );
+ if ( $mins <= 1 )
$mins = 1;
- }
/* translators: min=minute */
- $since = sprintf(_n('%s min', '%s mins', $mins), $mins);
- } else if (($diff <= 86400) && ($diff > 3600)) {
- $hours = round($diff / 3600);
- if ($hours <= 1) {
+ $since = sprintf( _n( '%s min', '%s mins', $mins ), $mins );
+ } elseif ( $diff < DAY_IN_SECONDS && $diff >= HOUR_IN_SECONDS ) {
+ $hours = round( $diff / HOUR_IN_SECONDS );
+ if ( $hours <= 1 )
$hours = 1;
- }
- $since = sprintf(_n('%s hour', '%s hours', $hours), $hours);
- } elseif ($diff >= 86400) {
- $days = round($diff / 86400);
- if ($days <= 1) {
+ $since = sprintf( _n( '%s hour', '%s hours', $hours ), $hours );
+ } elseif ( $diff < WEEK_IN_SECONDS && $diff >= DAY_IN_SECONDS ) {
+ $days = round( $diff / DAY_IN_SECONDS );
+ if ( $days <= 1 )
$days = 1;
- }
- $since = sprintf(_n('%s day', '%s days', $days), $days);
+ $since = sprintf( _n( '%s day', '%s days', $days ), $days );
+ } elseif ( $diff < 30 * DAY_IN_SECONDS && $diff >= WEEK_IN_SECONDS ) {
+ $weeks = round( $diff / WEEK_IN_SECONDS );
+ if ( $weeks <= 1 )
+ $weeks = 1;
+ $since = sprintf( _n( '%s week', '%s weeks', $weeks ), $weeks );
+ } elseif ( $diff < YEAR_IN_SECONDS && $diff >= 30 * DAY_IN_SECONDS ) {
+ $months = round( $diff / ( 30 * DAY_IN_SECONDS ) );
+ if ( $months <= 1 )
+ $months = 1;
+ $since = sprintf( _n( '%s month', '%s months', $months ), $months );
+ } elseif ( $diff >= YEAR_IN_SECONDS ) {
+ $years = round( $diff / YEAR_IN_SECONDS );
+ if ( $years <= 1 )
+ $years = 1;
+ $since = sprintf( _n( '%s year', '%s years', $years ), $years );
}
- return $since;
+
+ /**
+ * Filter the human readable difference between two timestamps.
+ *
+ * @since 4.0.0
+ *
+ * @param string $since The difference in human readable text.
+ * @param int $diff The difference in seconds.
+ * @param int $from Unix timestamp from which the difference begins.
+ * @param int $to Unix timestamp to end the time difference.
+ */
+ return apply_filters( 'human_time_diff', $since, $diff, $from, $to );
}
/**
* Generates an excerpt from the content, if needed.
*
* The excerpt word amount will be 55 words and if the amount is greater than
- * that, then the string ' [...]' will be appended to the excerpt. If the string
+ * that, then the string ' […]' will be appended to the excerpt. If the string
* is less than 55 words, then the content will be returned as is.
*
* The 55 word limit can be modified by plugins/themes using the excerpt_length filter
- * The ' [...]' string can be modified by plugins/themes using the excerpt_more filter
+ * The ' […]' string can be modified by plugins/themes using the excerpt_more filter
*
* @since 1.5.0
*
- * @param string $text The excerpt. If set to empty an excerpt is generated.
+ * @param string $text Optional. The excerpt. If set to empty, an excerpt is generated.
* @return string The excerpt.
*/
-function wp_trim_excerpt($text) {
+function wp_trim_excerpt($text = '') {
$raw_excerpt = $text;
if ( '' == $text ) {
$text = get_the_content('');
$text = strip_shortcodes( $text );
- $text = apply_filters('the_content', $text);
+ /** This filter is documented in wp-includes/post-template.php */
+ $text = apply_filters( 'the_content', $text );
$text = str_replace(']]>', ']]>', $text);
- $text = strip_tags($text);
- $excerpt_length = apply_filters('excerpt_length', 55);
- $excerpt_more = apply_filters('excerpt_more', ' ' . '[...]');
- $words = preg_split("/[\n\r\t ]+/", $text, $excerpt_length + 1, PREG_SPLIT_NO_EMPTY);
- if ( count($words) > $excerpt_length ) {
- array_pop($words);
- $text = implode(' ', $words);
- $text = $text . $excerpt_more;
- } else {
- $text = implode(' ', $words);
- }
+
+ /**
+ * Filter the number of words in an excerpt.
+ *
+ * @since 2.7.0
+ *
+ * @param int $number The number of words. Default 55.
+ */
+ $excerpt_length = apply_filters( 'excerpt_length', 55 );
+ /**
+ * Filter the string in the "more" link displayed after a trimmed excerpt.
+ *
+ * @since 2.9.0
+ *
+ * @param string $more_string The string shown within the more link.
+ */
+ $excerpt_more = apply_filters( 'excerpt_more', ' ' . '[…]' );
+ $text = wp_trim_words( $text, $excerpt_length, $excerpt_more );
+ }
+ /**
+ * Filter the trimmed excerpt string.
+ *
+ * @since 2.8.0
+ *
+ * @param string $text The trimmed text.
+ * @param string $raw_excerpt The text prior to trimming.
+ */
+ return apply_filters( 'wp_trim_excerpt', $text, $raw_excerpt );
+}
+
+/**
+ * Trims text to a certain number of words.
+ *
+ * This function is localized. For languages that count 'words' by the individual
+ * character (such as East Asian languages), the $num_words argument will apply
+ * to the number of individual characters.
+ *
+ * @since 3.3.0
+ *
+ * @param string $text Text to trim.
+ * @param int $num_words Number of words. Default 55.
+ * @param string $more Optional. What to append if $text needs to be trimmed. Default '…'.
+ * @return string Trimmed text.
+ */
+function wp_trim_words( $text, $num_words = 55, $more = null ) {
+ if ( null === $more )
+ $more = __( '…' );
+ $original_text = $text;
+ $text = wp_strip_all_tags( $text );
+ /* translators: If your word count is based on single characters (East Asian characters),
+ enter 'characters'. Otherwise, enter 'words'. Do not translate into your own language. */
+ if ( 'characters' == _x( 'words', 'word count: words or characters?' ) && preg_match( '/^utf\-?8$/i', get_option( 'blog_charset' ) ) ) {
+ $text = trim( preg_replace( "/[\n\r\t ]+/", ' ', $text ), ' ' );
+ preg_match_all( '/./u', $text, $words_array );
+ $words_array = array_slice( $words_array[0], 0, $num_words + 1 );
+ $sep = '';
+ } else {
+ $words_array = preg_split( "/[\n\r\t ]+/", $text, $num_words + 1, PREG_SPLIT_NO_EMPTY );
+ $sep = ' ';
}
- return apply_filters('wp_trim_excerpt', $text, $raw_excerpt);
+ if ( count( $words_array ) > $num_words ) {
+ array_pop( $words_array );
+ $text = implode( $sep, $words_array );
+ $text = $text . $more;
+ } else {
+ $text = implode( $sep, $words_array );
+ }
+ /**
+ * Filter the text content after words have been trimmed.
+ *
+ * @since 3.3.0
+ *
+ * @param string $text The trimmed text.
+ * @param int $num_words The number of words to trim the text to. Default 5.
+ * @param string $more An optional string to append to the end of the trimmed text, e.g. ….
+ * @param string $original_text The text before it was trimmed.
+ */
+ return apply_filters( 'wp_trim_words', $text, $num_words, $more, $original_text );
}
/**
@@ -1885,10 +2773,24 @@ function wp_trim_excerpt($text) {
* @return string Text with converted entities.
*/
function ent2ncr($text) {
+
+ /**
+ * Filter text before named entities are converted into numbered entities.
+ *
+ * A non-null string must be returned for the filter to be evaluated.
+ *
+ * @since 3.3.0
+ *
+ * @param null $converted_text The text to be converted. Default null.
+ * @param string $text The text prior to entity conversion.
+ */
+ $filtered = apply_filters( 'pre_ent2ncr', null, $text );
+ if( null !== $filtered )
+ return $filtered;
+
$to_ncr = array(
'"' => '"',
'&' => '&',
- '⁄' => '/',
'<' => '<',
'>' => '>',
'|' => '|',
@@ -2160,14 +3062,30 @@ function ent2ncr($text) {
* @return string The formatted text after filter is applied.
*/
function wp_richedit_pre($text) {
- // Filtering a blank results in an annoying