X-Git-Url: https://scripts.mit.edu/gitweb/autoinstalls/wordpress.git/blobdiff_plain/5aa86a9053fb0fa15846bb60aac2fb8fdfff524a..refs/tags/wordpress-3.4.2:/wp-includes/formatting.php?ds=sidebyside diff --git a/wp-includes/formatting.php b/wp-includes/formatting.php index 3452ed2a..fcf519c3 100644 --- a/wp-includes/formatting.php +++ b/wp-includes/formatting.php @@ -28,18 +28,33 @@ */ function wptexturize($text) { global $wp_cockneyreplace; - static $opening_quote, $closing_quote, $en_dash, $em_dash, $default_no_texturize_tags, $default_no_texturize_shortcodes, $static_characters, $static_replacements, $dynamic_characters, $dynamic_replacements; + static $static_characters, $static_replacements, $dynamic_characters, $dynamic_replacements, + $default_no_texturize_tags, $default_no_texturize_shortcodes; // No need to set up these static variables more than once - if ( empty( $opening_quote ) ) { - /* translators: opening curly quote */ - $opening_quote = _x('“', 'opening curly quote'); - /* translators: closing curly quote */ - $closing_quote = _x('”', 'closing curly quote'); + if ( ! isset( $static_characters ) ) { + /* translators: opening curly double quote */ + $opening_quote = _x( '“', 'opening curly double quote' ); + /* translators: closing curly double quote */ + $closing_quote = _x( '”', 'closing curly double 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'); + $en_dash = _x( '–', 'en dash' ); /* translators: em dash */ - $em_dash = _x('—', 'em dash'); + $em_dash = _x( '—', 'em dash' ); $default_no_texturize_tags = array('pre', 'code', 'kbd', 'style', 'script', 'tt'); $default_no_texturize_shortcodes = array('code'); @@ -48,16 +63,40 @@ function wptexturize($text) { if ( isset($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" ); + $cockneyreplace = array( $apos . "tain" . $apos . "t", $apos . "twere", $apos . "twas", $apos . "tis", $apos . "twill", $apos . "til", $apos . "bout", $apos . "nuff", $apos . "round", $apos . "cause" ); } 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('---', ' -- ', '--', ' - ', 'xn–', '...', '``', '\'\'', ' (tm)'), $cockney ); - $static_replacements = array_merge( array($em_dash, ' ' . $em_dash . ' ', $en_dash, ' ' . $en_dash . ' ', 'xn--', '…', $opening_quote, $closing_quote, ' ™'), $cockneyreplace ); + $static_characters = array_merge( array( '---', ' -- ', '--', ' - ', 'xn–', '...', '``', '\'\'', ' (tm)' ), $cockney ); + $static_replacements = array_merge( array( $em_dash, ' ' . $em_dash . ' ', $en_dash, ' ' . $en_dash . ' ', 'xn--', '…', $opening_quote, $closing_quote, ' ™' ), $cockneyreplace ); - $dynamic_characters = array('/\'(\d\d(?:’|\')?s)/', '/\'(\d)/', '/(\s|\A|[([{<]|")\'/', '/(\d)"/', '/(\d)\'/', '/(\S)\'([^\'\s])/', '/(\s|\A|[([{<])"(?!\s)/', '/"(\s|\S|\Z)/', '/\'([\s.]|\Z)/', '/\b(\d+)x(\d+)\b/'); - $dynamic_replacements = array('’$1','’$1', '$1‘', '$1″', '$1′', '$1’$2', '$1' . $opening_quote . '$2', $closing_quote . '$1', '’$1', '$1×$2'); + $dynamic = array(); + if ( "'" != $apos ) { + $dynamic[ '/\'(\d\d(?:’|\')?s)/' ] = $apos . '$1'; // '99's + $dynamic[ '/\'(\d)/' ] = $apos . '$1'; // '99 + } + if ( "'" != $opening_single_quote ) + $dynamic[ '/(\s|\A|[([{<]|")\'/' ] = '$1' . $opening_single_quote; // opening single quote, even after (, {, <, [ + if ( '"' != $double_prime ) + $dynamic[ '/(\d)"/' ] = '$1' . $double_prime; // 9" (double prime) + if ( "'" != $prime ) + $dynamic[ '/(\d)\'/' ] = '$1' . $prime; // 9' (prime) + if ( "'" != $apos ) + $dynamic[ '/(\S)\'([^\'\s])/' ] = '$1' . $apos . '$2'; // apostrophe in a word + if ( '"' != $opening_quote ) + $dynamic[ '/(\s|\A|[([{<])"(?!\s)/' ] = '$1' . $opening_quote . '$2'; // opening double quote, even after (, {, <, [ + if ( '"' != $closing_quote ) + $dynamic[ '/"(\s|\S|\Z)/' ] = $closing_quote . '$1'; // closing double quote + if ( "'" != $closing_single_quote ) + $dynamic[ '/\'([\s.]|\Z)/' ] = $closing_single_quote . '$1'; // closing single quote + + $dynamic[ '/\b(\d+)x(\d+)\b/' ] = '$1×$2'; // 9x9 (times) + + $dynamic_characters = array_keys( $dynamic ); + $dynamic_replacements = array_values( $dynamic ); } // Transform into regexp sub-expression used in _wptexturize_pushpop_element @@ -133,30 +172,6 @@ function _wptexturize_pushpop_element($text, &$stack, $disabled_elements, $openi } } -/** - * Accepts matches array from preg_replace_callback in wpautop() or a string. - * - * Ensures that the contents of a <
>...<> HTML block are not - * converted into paragraphs or line-breaks. - * - * @since 1.2.0 - * - * @param array|string $matches The array or string - * @return string The pre block without paragraph/line-break conversion. - */ -function clean_pre($matches) { - if ( is_array($matches) ) - $text = $matches[1] . $matches[2] . ""; - else - $text = $matches; - - $text = str_replace('
', "\n", $text); - $text = str_replace('
', '', $text); - - return $text; -} - /** * Replaces double line-breaks with paragraph elements. * @@ -168,17 +183,45 @@ function clean_pre($matches) { * @since 0.71 * * @param string $pee The text which has to be formatted. - * @param int|bool $br Optional. If set, this will convert all remaining line-breaks after paragraphing. Default true. + * @param bool $br Optional. If set, this will convert all remaining line-breaks after paragraphing. Default true. * @return string Text which has been converted into correct paragraph tags. */ -function wpautop($pee, $br = 1) { +function wpautop($pee, $br = true) { + $pre_tags = array(); if ( trim($pee) === '' ) return ''; + $pee = $pee . "\n"; // just to make things a little easier, pad the end + + if ( strpos($pee, '', $pee ); + $last_pee = array_pop($pee_parts); + $pee = ''; + $i = 0; + + foreach ( $pee_parts as $pee_part ) { + $start = strpos($pee_part, '"; + $pre_tags[$name] = substr( $pee_part, $start ) . ''; + + $pee .= substr( $pee_part, 0, $start ) . $name; + $i++; + } + + $pee .= $last_pee; + } + $pee = preg_replace('|
\s*(?' . $allblocks . '[^>]*>)!', "$1", $pee); $pee = preg_replace('!(?' . $allblocks . '[^>]*>)\s*
!', "$1", $pee); - if ($br) { + if ( $br ) { $pee = preg_replace_callback('/<(script|style).*?<\/\\1>/s', '_autop_newline_preservation_helper', $pee); $pee = preg_replace('|(?)\s*\n|', "]*>)(.*?)!is', 'clean_pre', $pee ); $pee = preg_replace( "|\n$|", '', $pee ); + if ( !empty($pre_tags) ) + $pee = str_replace(array_keys($pre_tags), array_values($pre_tags), $pee); + return $pee; } @@ -671,7 +715,62 @@ function remove_accents($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', + ); $string = strtr($string, $chars); } else { @@ -732,7 +831,7 @@ function sanitize_file_name( $filename ) { $extension = array_pop($parts); $mimes = get_allowed_mime_types(); - // Loop over any intermediate extensions. Munge them with a trailing underscore if they are a 2 - 5 character + // 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. foreach ( (array) $parts as $part) { $filename .= '.' . $part; @@ -873,16 +972,24 @@ function sanitize_title_with_dashes($title, $raw_title = '', $context = 'display $title = str_replace('.', '-', $title); if ( 'save' == $context ) { - // nbsp, ndash and mdash + // Convert nbsp, ndash and mdash to hyphens $title = str_replace( array( '%c2%a0', '%e2%80%93', '%e2%80%94' ), '-', $title ); - // iexcl and iquest - $title = str_replace( array( '%c2%a1', '%c2%bf' ), '', $title ); - // angle quotes - $title = str_replace( array( '%c2%ab', '%c2%bb', '%e2%80%b9', '%e2%80%ba' ), '', $title ); - // curly quotes - $title = str_replace( array( '%e2%80%98', '%e2%80%99', '%e2%80%9c', '%e2%80%9d' ), '', $title ); - // copy, reg, deg, hellip and trade - $title = str_replace( array( '%c2%a9', '%c2%ae', '%c2%b0', '%e2%80%a6', '%e2%84%a2' ), '', $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', + ), '', $title ); + + // Convert times to x + $title = str_replace( '%c3%97', 'x', $title ); } $title = preg_replace('/[^%a-z0-9 _-]/', '', $title); @@ -972,7 +1079,7 @@ function convert_chars($content, $deprecated = '') { '' => '‹', '' => 'Œ', '' => '', - '' => 'ž', + '' => 'Ž', '' => '', '' => '', '' => '‘', @@ -988,7 +1095,7 @@ function convert_chars($content, $deprecated = '') { '' => '›', '' => 'œ', '' => '', - '' => '', + '' => 'ž', '' => 'Ÿ' ); @@ -1012,14 +1119,12 @@ function convert_chars($content, $deprecated = '') { /** * Will only balance the tags if forced to and the option is set to balance tags. * - * The option 'use_balanceTags' is used for whether the tags will be balanced. - * Both the $force parameter and 'use_balanceTags' option will have to be true - * before the tags will be balanced. + * The option 'use_balanceTags' is used to determine whether the tags will be balanced. * * @since 0.71 * * @param string $text Text to be balanced - * @param bool $force Forces balancing, ignoring the value of the option. Default false. + * @param bool $force If true, forces balancing, ignoring the value of the option. Default false. * @return string Balanced text */ function balanceTags( $text, $force = false ) { @@ -1151,14 +1256,14 @@ function force_balance_tags( $text ) { /** * Acts on text which is about to be edited. * - * Unless $richedit is set, it is simply a holder for the 'format_to_edit' - * filter. If $richedit is set true htmlspecialchars(), through esc_textarea(), - * will be run on the content, converting special characters to HTML entities. + * The $content is run through esc_textarea(), which uses htmlspecialchars() + * to convert special characters to HTML entities. If $richedit is set to true, + * it is simply a holder for the 'format_to_edit' filter. * * @since 0.71 * * @param string $content The text about to be edited. - * @param bool $richedit Whether the $content should pass through htmlspecialchars(). Default false. + * @param bool $richedit Whether the $content should not pass through htmlspecialchars(). Default false (meaning it will be passed). * @return string The text after the filter (and possibly htmlspecialchars()) has been run. */ function format_to_edit( $content, $richedit = false ) { @@ -1297,8 +1402,6 @@ function stripslashes_deep($value) { /** * Navigates through an array and encodes the values to be used in a URL. * - * Uses a callback to pass the value of the array back to the function as a - * string. * * @since 2.2.0 * @@ -1310,6 +1413,18 @@ function urlencode_deep($value) { return $value; } +/** + * Navigates through an array and raw encodes the values to be used in a URL. + * + * @since 3.4.0 + * + * @param array|string $value The array or string to be encoded. + * @return array|string $value The encoded array (or string from the callback). + */ +function rawurlencode_deep( $value ) { + return is_array( $value ) ? array_map( 'rawurlencode_deep', $value ) : rawurlencode( $value ); +} + /** * Converts email addresses characters to HTML entities to block spam bots. * @@ -1350,9 +1465,17 @@ function antispambot($emailaddy, $mailto=0) { */ function _make_url_clickable_cb($matches) { $url = $matches[2]; - $suffix = ''; - /** Include parentheses in the URL only if paired **/ + if ( ')' == $matches[3] && strpos( $url, '(' ) ) { + // If the trailing character is a closing parethesis, and the URL has an opening parenthesis in it, add the closing parenthesis to the URL. + // Then we can let the parenthesis balancer do its thing below. + $url .= $matches[3]; + $suffix = ''; + } else { + $suffix = $matches[3]; + } + + // Include parentheses in the URL only if paired while ( substr_count( $url, '(' ) < substr_count( $url, ')' ) ) { $suffix = strrchr( $url, ')' ) . $suffix; $url = substr( $url, 0, strrpos( $url, ')' ) ); @@ -1418,23 +1541,117 @@ function _make_email_clickable_cb($matches) { * * @since 0.71 * - * @param string $ret Content to convert URIs. + * @param string $text Content to convert URIs. * @return string Content with converted URIs. */ -function make_clickable($ret) { - $ret = ' ' . $ret; - // in testing, using arrays here was found to be faster - $save = @ini_set('pcre.recursion_limit', 10000); - $retval = preg_replace_callback('#(?])(\()?([\w]+?://(?:[\w\\x80-\\xff\#%~/?@\[\]-]{1,2000}|[\'*(+.,;:!=&$](?![\b\)]|(\))?([\s]|$))|(?(1)\)(?![\s<.,;:]|$)|\)))+)#is', '_make_url_clickable_cb', $ret); - if (null !== $retval ) - $ret = $retval; - @ini_set('pcre.recursion_limit', $save); - $ret = preg_replace_callback('#([\s>])((www|ftp)\.[\w\\x80-\\xff\#$%&~/.\-;:=,?@\[\]+]+)#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); - // this one is not in an array because we need it to run last, for cleanup of accidental links within links - $ret = preg_replace("#(]+?>|>))]+?>([^>]+?)#i", "$1$3", $ret); - $ret = trim($ret); - return $ret; +function make_clickable( $text ) { + $r = ''; + $textarr = preg_split( '/(<[^<>]+>)/', $text, -1, PREG_SPLIT_DELIM_CAPTURE ); // split out HTML tags + foreach ( $textarr as $piece ) { + if ( 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 9', // 9 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 $chunks;
}
/**
@@ -1910,6 +2127,10 @@ function wp_trim_excerpt($text = '') {
/**
* 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.
@@ -1922,13 +2143,23 @@ function wp_trim_words( $text, $num_words = 55, $more = null ) {
$more = __( '…' );
$original_text = $text;
$text = wp_strip_all_tags( $text );
- $words_array = preg_split( "/[\n\r\t ]+/", $text, $num_words + 1, PREG_SPLIT_NO_EMPTY );
+ /* translators: If your word count is based on single characters (East Asian characters),
+ enter 'characters'. Otherwise, enter 'words'. Do not translate into your own language. */
+ if ( 'characters' == _x( 'words', 'word count: words or characters?' ) && preg_match( '/^utf\-?8$/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 = ' ';
+ }
if ( count( $words_array ) > $num_words ) {
array_pop( $words_array );
- $text = implode( ' ', $words_array );
+ $text = implode( $sep, $words_array );
$text = $text . $more;
} else {
- $text = implode( ' ', $words_array );
+ $text = implode( $sep, $words_array );
}
return apply_filters( 'wp_trim_words', $text, $num_words, $more, $original_text );
}
@@ -2491,21 +2722,13 @@ function wp_make_link_relative( $link ) {
function sanitize_option($option, $value) {
switch ( $option ) {
- case 'admin_email':
- $value = sanitize_email($value);
- if ( !is_email($value) ) {
- $value = get_option( $option ); // Resets option to stored value in the case of failed sanitization
- if ( function_exists('add_settings_error') )
- add_settings_error('admin_email', 'invalid_admin_email', __('The email address entered did not appear to be a valid email address. Please enter a valid email address.'));
- }
- break;
-
- case 'new_admin_email':
- $value = sanitize_email($value);
- if ( !is_email($value) ) {
+ case 'admin_email' :
+ case 'new_admin_email' :
+ $value = sanitize_email( $value );
+ if ( ! is_email( $value ) ) {
$value = get_option( $option ); // Resets option to stored value in the case of failed sanitization
- if ( function_exists('add_settings_error') )
- add_settings_error('new_admin_email', 'invalid_admin_email', __('The email address entered did not appear to be a valid email address. Please enter a valid email address.'));
+ if ( function_exists( 'add_settings_error' ) )
+ add_settings_error( $option, 'invalid_admin_email', __( 'The email address entered did not appear to be a valid email address. Please enter a valid email address.' ) );
}
break;
@@ -2845,9 +3068,9 @@ function _links_add_base($m) {
global $_links_add_base;
//1 = attribute name 2 = quotation mark 3 = URL
return $m[1] . '=' . $m[2] .
- (strpos($m[3], 'http://') === false ?
- path_join($_links_add_base, $m[3]) :
- $m[3])
+ ( preg_match( '#^(\w{1,20}):#', $m[3], $protocol ) && in_array( $protocol[1], wp_allowed_protocols() ) ?
+ $m[3] :
+ path_join( $_links_add_base, $m[3] ) )
. $m[2];
}
@@ -2913,7 +3136,7 @@ function wp_strip_all_tags($string, $remove_breaks = false) {
if ( $remove_breaks )
$string = preg_replace('/[\r\n\t ]+/', ' ', $string);
- return trim($string);
+ return trim( $string );
}
/**
@@ -3004,4 +3227,21 @@ function sanitize_mime_type( $mime_type ) {
return apply_filters( 'sanitize_mime_type', $sani_mime_type, $mime_type );
}
-?>
+/**
+ * Sanitize space or carriage return separated URLs that are used to send trackbacks.
+ *
+ * @since 3.4.0
+ *
+ * @param string $to_ping Space or carriage return separated URLs
+ * @return string URLs starting with the http or https protocol, separated by a carriage return.
+ */
+function sanitize_trackback_urls( $to_ping ) {
+ $urls_to_ping = preg_split( '/[\r\n\t ]/', trim( $to_ping ), -1, PREG_SPLIT_NO_EMPTY );
+ foreach ( $urls_to_ping as $k => $url ) {
+ if ( !preg_match( '#^https?://.#i', $url ) )
+ unset( $urls_to_ping[$k] );
+ }
+ $urls_to_ping = array_map( 'esc_url_raw', $urls_to_ping );
+ $urls_to_ping = implode( "\n", $urls_to_ping );
+ return apply_filters( 'sanitize_trackback_urls', $urls_to_ping, $to_ping );
+}