/tags/2.2.3/wp-includes/formatting.php
PHP | 1201 lines | 1000 code | 117 blank | 84 comment | 140 complexity | f02d84ec8ff9ce0b1603ce2122dc6546 MD5 | raw file
Possible License(s): AGPL-1.0, LGPL-2.0, LGPL-2.1, GPL-2.0
- <?php
- function wptexturize($text) {
- global $wp_cockneyreplace;
- $next = true;
- $output = '';
- $curl = '';
- $textarr = preg_split('/(<.*>)/Us', $text, -1, PREG_SPLIT_DELIM_CAPTURE);
- $stop = count($textarr);
- // if a plugin has provided an autocorrect array, use it
- if ( isset($wp_cockneyreplace) ) {
- $cockney = array_keys($wp_cockneyreplace);
- $cockneyreplace = array_values($wp_cockneyreplace);
- } 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");
- }
- $static_characters = array_merge(array('---', ' -- ', '--', 'xn–', '...', '``', '\'s', '\'\'', ' (tm)'), $cockney);
- $static_replacements = array_merge(array('—', ' — ', '–', 'xn--', '…', '“', '’s', '”', ' ™'), $cockneyreplace);
- $dynamic_characters = array('/\'(\d\d(?:’|\')?s)/', '/(\s|\A|")\'/', '/(\d+)"/', '/(\d+)\'/', '/(\S)\'([^\'\s])/', '/(\s|\A)"(?!\s)/', '/"(\s|\S|\Z)/', '/\'([\s.]|\Z)/', '/(\d+)x(\d+)/');
- $dynamic_replacements = array('’$1','$1‘', '$1″', '$1′', '$1’$2', '$1“$2', '”$1', '’$1', '$1×$2');
- for ( $i = 0; $i < $stop; $i++ ) {
- $curl = $textarr[$i];
- if (isset($curl{0}) && '<' != $curl{0} && $next) { // If it's not a tag
- // static strings
- $curl = str_replace($static_characters, $static_replacements, $curl);
- // regular expressions
- $curl = preg_replace($dynamic_characters, $dynamic_replacements, $curl);
- } elseif (strpos($curl, '<code') !== false || strpos($curl, '<pre') !== false || strpos($curl, '<kbd') !== false || strpos($curl, '<style') !== false || strpos($curl, '<script') !== false) {
- $next = false;
- } else {
- $next = true;
- }
- $curl = preg_replace('/&([^#])(?![a-zA-Z1-4]{1,8};)/', '&$1', $curl);
- $output .= $curl;
- }
- return $output;
- }
- function clean_pre($text) {
- $text = str_replace('<br />', '', $text);
- $text = str_replace('<p>', "\n", $text);
- $text = str_replace('</p>', '', $text);
- return $text;
- }
- function wpautop($pee, $br = 1) {
- $pee = $pee . "\n"; // just to make things a little easier, pad the end
- $pee = preg_replace('|<br />\s*<br />|', "\n\n", $pee);
- // Space things out a little
- $allblocks = '(?:table|thead|tfoot|caption|colgroup|tbody|tr|td|th|div|dl|dd|dt|ul|ol|li|pre|select|form|map|area|blockquote|address|math|style|input|p|h[1-6]|hr)';
- $pee = preg_replace('!(<' . $allblocks . '[^>]*>)!', "\n$1", $pee);
- $pee = preg_replace('!(</' . $allblocks . '>)!', "$1\n\n", $pee);
- $pee = str_replace(array("\r\n", "\r"), "\n", $pee); // cross-platform newlines
- $pee = preg_replace("/\n\n+/", "\n\n", $pee); // take care of duplicates
- $pee = preg_replace('/\n?(.+?)(?:\n\s*\n|\z)/s', "<p>$1</p>\n", $pee); // make paragraphs, including one at the end
- $pee = preg_replace('|<p>\s*?</p>|', '', $pee); // under certain strange conditions it could create a P of entirely whitespace
- $pee = preg_replace('!<p>([^<]+)\s*?(</(?:div|address|form)[^>]*>)!', "<p>$1</p>$2", $pee);
- $pee = preg_replace( '|<p>|', "$1<p>", $pee );
- $pee = preg_replace('!<p>\s*(</?' . $allblocks . '[^>]*>)\s*</p>!', "$1", $pee); // don't pee all over a tag
- $pee = preg_replace("|<p>(<li.+?)</p>|", "$1", $pee); // problem with nested lists
- $pee = preg_replace('|<p><blockquote([^>]*)>|i', "<blockquote$1><p>", $pee);
- $pee = str_replace('</blockquote></p>', '</p></blockquote>', $pee);
- $pee = preg_replace('!<p>\s*(</?' . $allblocks . '[^>]*>)!', "$1", $pee);
- $pee = preg_replace('!(</?' . $allblocks . '[^>]*>)\s*</p>!', "$1", $pee);
- if ($br) {
- $pee = preg_replace('/<(script|style).*?<\/\\1>/se', 'str_replace("\n", "<WPPreserveNewline />", "\\0")', $pee);
- $pee = preg_replace('|(?<!<br />)\s*\n|', "<br />\n", $pee); // optionally make line breaks
- $pee = str_replace('<WPPreserveNewline />', "\n", $pee);
- }
- $pee = preg_replace('!(</?' . $allblocks . '[^>]*>)\s*<br />!', "$1", $pee);
- $pee = preg_replace('!<br />(\s*</?(?:p|li|div|dl|dd|dt|th|pre|td|ul|ol)[^>]*>)!', '$1', $pee);
- if (strpos($pee, '<pre') !== false)
- $pee = preg_replace('!(<pre.*?>)(.*?)</pre>!ise', " stripslashes('$1') . stripslashes(clean_pre('$2')) . '</pre>' ", $pee);
- $pee = preg_replace( "|\n</p>$|", '</p>', $pee );
- return $pee;
- }
- function seems_utf8($Str) { # by bmorel at ssi dot fr
- for ($i=0; $i<strlen($Str); $i++) {
- if (ord($Str[$i]) < 0x80) continue; # 0bbbbbbb
- elseif ((ord($Str[$i]) & 0xE0) == 0xC0) $n=1; # 110bbbbb
- elseif ((ord($Str[$i]) & 0xF0) == 0xE0) $n=2; # 1110bbbb
- elseif ((ord($Str[$i]) & 0xF8) == 0xF0) $n=3; # 11110bbb
- elseif ((ord($Str[$i]) & 0xFC) == 0xF8) $n=4; # 111110bb
- elseif ((ord($Str[$i]) & 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 == strlen($Str)) || ((ord($Str[$i]) & 0xC0) != 0x80))
- return false;
- }
- }
- return true;
- }
- function wp_specialchars( $text, $quotes = 0 ) {
- // Like htmlspecialchars except don't double-encode HTML entities
- $text = str_replace('&&', '&&', $text);
- $text = str_replace('&&', '&&', $text);
- $text = preg_replace('/&(?:$|([^#])(?![a-z1-4]{1,8};))/', '&$1', $text);
- $text = str_replace('<', '<', $text);
- $text = str_replace('>', '>', $text);
- if ( 'double' === $quotes ) {
- $text = str_replace('"', '"', $text);
- } elseif ( 'single' === $quotes ) {
- $text = str_replace("'", ''', $text);
- } elseif ( $quotes ) {
- $text = str_replace('"', '"', $text);
- $text = str_replace("'", ''', $text);
- }
- return $text;
- }
- function utf8_uri_encode( $utf8_string, $length = 0 ) {
- $unicode = '';
- $values = array();
- $num_octets = 1;
- for ($i = 0; $i < strlen( $utf8_string ); $i++ ) {
- $value = ord( $utf8_string[ $i ] );
- if ( $value < 128 ) {
- if ( $length && ( strlen($unicode) + 1 > $length ) )
- break;
- $unicode .= chr($value);
- } else {
- if ( count( $values ) == 0 ) $num_octets = ( $value < 224 ) ? 2 : 3;
- $values[] = $value;
- if ( $length && ( (strlen($unicode) + ($num_octets * 3)) > $length ) )
- break;
- if ( count( $values ) == $num_octets ) {
- if ($num_octets == 3) {
- $unicode .= '%' . dechex($values[0]) . '%' . dechex($values[1]) . '%' . dechex($values[2]);
- } else {
- $unicode .= '%' . dechex($values[0]) . '%' . dechex($values[1]);
- }
- $values = array();
- $num_octets = 1;
- }
- }
- }
- return $unicode;
- }
- function remove_accents($string) {
- if ( !preg_match('/[\x80-\xff]/', $string) )
- return $string;
- if (seems_utf8($string)) {
- $chars = array(
- // Decompositions for Latin-1 Supplement
- 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',
- chr(195).chr(135) => 'C', chr(195).chr(136) => 'E',
- chr(195).chr(137) => 'E', chr(195).chr(138) => 'E',
- chr(195).chr(139) => 'E', chr(195).chr(140) => 'I',
- chr(195).chr(141) => 'I', chr(195).chr(142) => 'I',
- chr(195).chr(143) => 'I', chr(195).chr(145) => 'N',
- chr(195).chr(146) => 'O', chr(195).chr(147) => 'O',
- chr(195).chr(148) => 'O', chr(195).chr(149) => 'O',
- chr(195).chr(150) => 'O', chr(195).chr(153) => 'U',
- chr(195).chr(154) => 'U', chr(195).chr(155) => 'U',
- chr(195).chr(156) => 'U', chr(195).chr(157) => 'Y',
- chr(195).chr(159) => 's', chr(195).chr(160) => 'a',
- chr(195).chr(161) => 'a', chr(195).chr(162) => 'a',
- chr(195).chr(163) => 'a', chr(195).chr(164) => 'a',
- chr(195).chr(165) => 'a', chr(195).chr(167) => 'c',
- chr(195).chr(168) => 'e', chr(195).chr(169) => 'e',
- chr(195).chr(170) => 'e', chr(195).chr(171) => 'e',
- chr(195).chr(172) => 'i', chr(195).chr(173) => 'i',
- chr(195).chr(174) => 'i', chr(195).chr(175) => 'i',
- 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(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(191) => 'y',
- // 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',
- chr(196).chr(132) => 'A', chr(196).chr(133) => 'a',
- chr(196).chr(134) => 'C', chr(196).chr(135) => 'c',
- chr(196).chr(136) => 'C', chr(196).chr(137) => 'c',
- chr(196).chr(138) => 'C', chr(196).chr(139) => 'c',
- chr(196).chr(140) => 'C', chr(196).chr(141) => 'c',
- chr(196).chr(142) => 'D', chr(196).chr(143) => 'd',
- chr(196).chr(144) => 'D', chr(196).chr(145) => 'd',
- chr(196).chr(146) => 'E', chr(196).chr(147) => 'e',
- chr(196).chr(148) => 'E', chr(196).chr(149) => 'e',
- chr(196).chr(150) => 'E', chr(196).chr(151) => 'e',
- chr(196).chr(152) => 'E', chr(196).chr(153) => 'e',
- chr(196).chr(154) => 'E', chr(196).chr(155) => 'e',
- chr(196).chr(156) => 'G', chr(196).chr(157) => 'g',
- chr(196).chr(158) => 'G', chr(196).chr(159) => 'g',
- chr(196).chr(160) => 'G', chr(196).chr(161) => 'g',
- chr(196).chr(162) => 'G', chr(196).chr(163) => 'g',
- chr(196).chr(164) => 'H', chr(196).chr(165) => 'h',
- chr(196).chr(166) => 'H', chr(196).chr(167) => 'h',
- chr(196).chr(168) => 'I', chr(196).chr(169) => 'i',
- chr(196).chr(170) => 'I', chr(196).chr(171) => 'i',
- chr(196).chr(172) => 'I', chr(196).chr(173) => 'i',
- chr(196).chr(174) => 'I', chr(196).chr(175) => 'i',
- chr(196).chr(176) => 'I', chr(196).chr(177) => 'i',
- chr(196).chr(178) => 'IJ',chr(196).chr(179) => 'ij',
- chr(196).chr(180) => 'J', chr(196).chr(181) => 'j',
- chr(196).chr(182) => 'K', chr(196).chr(183) => 'k',
- chr(196).chr(184) => 'k', chr(196).chr(185) => 'L',
- chr(196).chr(186) => 'l', chr(196).chr(187) => 'L',
- chr(196).chr(188) => 'l', chr(196).chr(189) => 'L',
- chr(196).chr(190) => 'l', chr(196).chr(191) => 'L',
- chr(197).chr(128) => 'l', chr(197).chr(129) => 'L',
- chr(197).chr(130) => 'l', chr(197).chr(131) => 'N',
- chr(197).chr(132) => 'n', chr(197).chr(133) => 'N',
- chr(197).chr(134) => 'n', chr(197).chr(135) => 'N',
- chr(197).chr(136) => 'n', chr(197).chr(137) => 'N',
- chr(197).chr(138) => 'n', chr(197).chr(139) => 'N',
- chr(197).chr(140) => 'O', chr(197).chr(141) => 'o',
- chr(197).chr(142) => 'O', chr(197).chr(143) => 'o',
- chr(197).chr(144) => 'O', chr(197).chr(145) => 'o',
- chr(197).chr(146) => 'OE',chr(197).chr(147) => 'oe',
- chr(197).chr(148) => 'R',chr(197).chr(149) => 'r',
- chr(197).chr(150) => 'R',chr(197).chr(151) => 'r',
- chr(197).chr(152) => 'R',chr(197).chr(153) => 'r',
- chr(197).chr(154) => 'S',chr(197).chr(155) => 's',
- chr(197).chr(156) => 'S',chr(197).chr(157) => 's',
- chr(197).chr(158) => 'S',chr(197).chr(159) => 's',
- chr(197).chr(160) => 'S', chr(197).chr(161) => 's',
- chr(197).chr(162) => 'T', chr(197).chr(163) => 't',
- chr(197).chr(164) => 'T', chr(197).chr(165) => 't',
- chr(197).chr(166) => 'T', chr(197).chr(167) => 't',
- chr(197).chr(168) => 'U', chr(197).chr(169) => 'u',
- chr(197).chr(170) => 'U', chr(197).chr(171) => 'u',
- chr(197).chr(172) => 'U', chr(197).chr(173) => 'u',
- chr(197).chr(174) => 'U', chr(197).chr(175) => 'u',
- chr(197).chr(176) => 'U', chr(197).chr(177) => 'u',
- chr(197).chr(178) => 'U', chr(197).chr(179) => 'u',
- chr(197).chr(180) => 'W', chr(197).chr(181) => 'w',
- chr(197).chr(182) => 'Y', chr(197).chr(183) => 'y',
- chr(197).chr(184) => 'Y', chr(197).chr(185) => 'Z',
- chr(197).chr(186) => 'z', chr(197).chr(187) => 'Z',
- chr(197).chr(188) => 'z', chr(197).chr(189) => 'Z',
- chr(197).chr(190) => 'z', chr(197).chr(191) => 's',
- // Euro Sign
- chr(226).chr(130).chr(172) => 'E',
- // GBP (Pound) Sign
- chr(194).chr(163) => '');
- $string = strtr($string, $chars);
- } else {
- // 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)
- .chr(195).chr(196).chr(197).chr(199).chr(200).chr(201).chr(202)
- .chr(203).chr(204).chr(205).chr(206).chr(207).chr(209).chr(210)
- .chr(211).chr(212).chr(213).chr(214).chr(216).chr(217).chr(218)
- .chr(219).chr(220).chr(221).chr(224).chr(225).chr(226).chr(227)
- .chr(228).chr(229).chr(231).chr(232).chr(233).chr(234).chr(235)
- .chr(236).chr(237).chr(238).chr(239).chr(241).chr(242).chr(243)
- .chr(244).chr(245).chr(246).chr(248).chr(249).chr(250).chr(251)
- .chr(252).chr(253).chr(255);
- $chars['out'] = "EfSZszYcYuAAAAAACEEEEIIIINOOOOOOUUUUYaaaaaaceeeeiiiinoooooouuuuyy";
- $string = strtr($string, $chars['in'], $chars['out']);
- $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);
- }
- return $string;
- }
- function sanitize_file_name( $name ) { // Like sanitize_title, but with periods
- $name = strtolower( $name );
- $name = preg_replace('/&.+?;/', '', $name); // kill entities
- $name = str_replace( '_', '-', $name );
- $name = preg_replace('/[^a-z0-9\s-.]/', '', $name);
- $name = preg_replace('/\s+/', '-', $name);
- $name = preg_replace('|-+|', '-', $name);
- $name = trim($name, '-');
- return $name;
- }
- function sanitize_user( $username, $strict = false ) {
- $raw_username = $username;
- $username = strip_tags($username);
- // Kill octets
- $username = preg_replace('|%([a-fA-F0-9][a-fA-F0-9])|', '', $username);
- $username = preg_replace('/&.+?;/', '', $username); // Kill entities
- // If strict, reduce to ASCII for max portability.
- if ( $strict )
- $username = preg_replace('|[^a-z0-9 _.\-@]|i', '', $username);
- return apply_filters('sanitize_user', $username, $raw_username, $strict);
- }
- function sanitize_title($title, $fallback_title = '') {
- $title = strip_tags($title);
- $title = apply_filters('sanitize_title', $title);
- if (empty($title)) {
- $title = $fallback_title;
- }
- return $title;
- }
- function sanitize_title_with_dashes($title) {
- $title = strip_tags($title);
- // Preserve escaped octets.
- $title = preg_replace('|%([a-fA-F0-9][a-fA-F0-9])|', '---$1---', $title);
- // Remove percent signs that are not part of an octet.
- $title = str_replace('%', '', $title);
- // Restore octets.
- $title = preg_replace('|---([a-fA-F0-9][a-fA-F0-9])---|', '%$1', $title);
- $title = remove_accents($title);
- if (seems_utf8($title)) {
- if (function_exists('mb_strtolower')) {
- $title = mb_strtolower($title, 'UTF-8');
- }
- $title = utf8_uri_encode($title, 200);
- }
- $title = strtolower($title);
- $title = preg_replace('/&.+?;/', '', $title); // kill entities
- $title = preg_replace('/[^%a-z0-9 _-]/', '', $title);
- $title = preg_replace('/\s+/', '-', $title);
- $title = preg_replace('|-+|', '-', $title);
- $title = trim($title, '-');
- return $title;
- }
- function convert_chars($content, $flag = 'obsolete') {
- // Translation of invalid Unicode references range to valid range
- $wp_htmltranswinuni = array(
- '€' => '€', // the Euro sign
- '' => '',
- '‚' => '‚', // these are Windows CP1252 specific characters
- 'ƒ' => 'ƒ', // they would look weird on non-Windows browsers
- '„' => '„',
- '…' => '…',
- '†' => '†',
- '‡' => '‡',
- 'ˆ' => 'ˆ',
- '‰' => '‰',
- 'Š' => 'Š',
- '‹' => '‹',
- 'Œ' => 'Œ',
- '' => '',
- 'Ž' => 'ž',
- '' => '',
- '' => '',
- '‘' => '‘',
- '’' => '’',
- '“' => '“',
- '”' => '”',
- '•' => '•',
- '–' => '–',
- '—' => '—',
- '˜' => '˜',
- '™' => '™',
- 'š' => 'š',
- '›' => '›',
- 'œ' => 'œ',
- '' => '',
- 'ž' => '',
- 'Ÿ' => 'Ÿ'
- );
- // Remove metadata tags
- $content = preg_replace('/<title>(.+?)<\/title>/','',$content);
- $content = preg_replace('/<category>(.+?)<\/category>/','',$content);
- // Converts lone & characters into & (a.k.a. &)
- $content = preg_replace('/&([^#])(?![a-z1-4]{1,8};)/i', '&$1', $content);
- // Fix Word pasting
- $content = strtr($content, $wp_htmltranswinuni);
- // Just a little XHTML help
- $content = str_replace('<br>', '<br />', $content);
- $content = str_replace('<hr>', '<hr />', $content);
- return $content;
- }
- function funky_javascript_fix($text) {
- // Fixes for browsers' javascript bugs
- global $is_macIE, $is_winIE;
- if ( $is_winIE || $is_macIE )
- $text = preg_replace("/\%u([0-9A-F]{4,4})/e", "'&#'.base_convert('\\1',16,10).';'", $text);
- return $text;
- }
- /*
- balanceTags
- Balances Tags of string using a modified stack.
- @param text Text to be balanced
- @param force Forces balancing, ignoring the value of the option
- @return Returns balanced text
- @author Leonard Lin (leonard@acm.org)
- @version v1.1
- @date November 4, 2001
- @license GPL v2.0
- @notes
- @changelog
- --- Modified by Scott Reilly (coffee2code) 02 Aug 2004
- 1.2 ***TODO*** Make better - change loop condition to $text
- 1.1 Fixed handling of append/stack pop order of end text
- Added Cleaning Hooks
- 1.0 First Version
- */
- function balanceTags($text, $force = false) {
- if ( !$force && get_option('use_balanceTags') == 0 )
- return $text;
- $tagstack = array(); $stacksize = 0; $tagqueue = ''; $newtext = '';
- # WP bug fix for comments - in case you REALLY meant to type '< !--'
- $text = str_replace('< !--', '< !--', $text);
- # WP bug fix for LOVE <3 (and other situations with '<' before a number)
- $text = preg_replace('#<([0-9]{1})#', '<$1', $text);
- while (preg_match("/<(\/?\w*)\s*([^>]*)>/",$text,$regex)) {
- $newtext .= $tagqueue;
- $i = strpos($text,$regex[0]);
- $l = strlen($regex[0]);
- // clear the shifter
- $tagqueue = '';
- // Pop or Push
- if ($regex[1][0] == "/") { // End Tag
- $tag = strtolower(substr($regex[1],1));
- // if too many closing tags
- if($stacksize <= 0) {
- $tag = '';
- //or close to be safe $tag = '/' . $tag;
- }
- // if stacktop value = tag close value then pop
- else if ($tagstack[$stacksize - 1] == $tag) { // found closing tag
- $tag = '</' . $tag . '>'; // Close Tag
- // Pop
- array_pop ($tagstack);
- $stacksize--;
- } else { // closing tag not at top, search for it
- for ($j=$stacksize-1;$j>=0;$j--) {
- if ($tagstack[$j] == $tag) {
- // add tag to tagqueue
- for ($k=$stacksize-1;$k>=$j;$k--){
- $tagqueue .= '</' . array_pop ($tagstack) . '>';
- $stacksize--;
- }
- break;
- }
- }
- $tag = '';
- }
- } else { // Begin Tag
- $tag = strtolower($regex[1]);
- // Tag Cleaning
- // If self-closing or '', don't do anything.
- if((substr($regex[2],-1) == '/') || ($tag == '')) {
- }
- // ElseIf it's a known single-entity tag but it doesn't close itself, do so
- elseif ($tag == 'br' || $tag == 'img' || $tag == 'hr' || $tag == 'input') {
- $regex[2] .= '/';
- } else { // Push the tag onto the stack
- // If the top of the stack is the same as the tag we want to push, close previous tag
- if (($stacksize > 0) && ($tag != 'div') && ($tagstack[$stacksize - 1] == $tag)) {
- $tagqueue = '</' . array_pop ($tagstack) . '>';
- $stacksize--;
- }
- $stacksize = array_push ($tagstack, $tag);
- }
- // Attributes
- $attributes = $regex[2];
- if($attributes) {
- $attributes = ' '.$attributes;
- }
- $tag = '<'.$tag.$attributes.'>';
- //If already queuing a close tag, then put this tag on, too
- if ($tagqueue) {
- $tagqueue .= $tag;
- $tag = '';
- }
- }
- $newtext .= substr($text,0,$i) . $tag;
- $text = substr($text,$i+$l);
- }
- // Clear Tag Queue
- $newtext .= $tagqueue;
- // Add Remaining text
- $newtext .= $text;
- // Empty Stack
- while($x = array_pop($tagstack)) {
- $newtext .= '</' . $x . '>'; // Add remaining tags to close
- }
- // WP fix for the bug with HTML comments
- $newtext = str_replace("< !--","<!--",$newtext);
- $newtext = str_replace("< !--","< !--",$newtext);
- return $newtext;
- }
- function force_balance_tags($text) {
- return balanceTags($text, true);
- }
- function format_to_edit($content, $richedit = false) {
- $content = apply_filters('format_to_edit', $content);
- if (! $richedit )
- $content = htmlspecialchars($content);
- return $content;
- }
- function format_to_post($content) {
- global $wpdb;
- $content = apply_filters('format_to_post', $content);
- return $content;
- }
- function zeroise($number,$threshold) { // function to add leading zeros when necessary
- return sprintf('%0'.$threshold.'s', $number);
- }
- function backslashit($string) {
- $string = preg_replace('/^([0-9])/', '\\\\\\\\\1', $string);
- $string = preg_replace('/([a-z])/i', '\\\\\1', $string);
- return $string;
- }
- function trailingslashit($string) {
- return untrailingslashit($string) . '/';
- }
- function untrailingslashit($string) {
- return rtrim($string, '/');
- }
- function addslashes_gpc($gpc) {
- global $wpdb;
- if (get_magic_quotes_gpc()) {
- $gpc = stripslashes($gpc);
- }
- return $wpdb->escape($gpc);
- }
- function stripslashes_deep($value) {
- $value = is_array($value) ?
- array_map('stripslashes_deep', $value) :
- stripslashes($value);
- return $value;
- }
- function urlencode_deep($value) {
- $value = is_array($value) ?
- array_map('urlencode_deep', $value) :
- urlencode($value);
- return $value;
- }
- function antispambot($emailaddy, $mailto=0) {
- $emailNOSPAMaddy = '';
- srand ((float) microtime() * 1000000);
- for ($i = 0; $i < strlen($emailaddy); $i = $i + 1) {
- $j = floor(rand(0, 1+$mailto));
- if ($j==0) {
- $emailNOSPAMaddy .= '&#'.ord(substr($emailaddy,$i,1)).';';
- } elseif ($j==1) {
- $emailNOSPAMaddy .= substr($emailaddy,$i,1);
- } elseif ($j==2) {
- $emailNOSPAMaddy .= '%'.zeroise(dechex(ord(substr($emailaddy, $i, 1))), 2);
- }
- }
- $emailNOSPAMaddy = str_replace('@','@',$emailNOSPAMaddy);
- return $emailNOSPAMaddy;
- }
- function make_clickable($ret) {
- $ret = ' ' . $ret;
- // in testing, using arrays here was found to be faster
- $ret = preg_replace(
- array(
- '#([\s>])([\w]+?://[\w\#$%&~/.\-;:=,?@\[\]+]*)#is',
- '#([\s>])((www|ftp)\.[\w\#$%&~/.\-;:=,?@\[\]+]*)#is',
- '#([\s>])([a-z0-9\-_.]+)@([^,< \n\r]+)#i'),
- array(
- '$1<a href="$2" rel="nofollow">$2</a>',
- '$1<a href="http://$2" rel="nofollow">$2</a>',
- '$1<a href="mailto:$2@$3">$2@$3</a>'),$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("#(<a( [^>]+?>|>))<a [^>]+?>([^>]+?)</a></a>#i", "$1$3</a>", $ret);
- $ret = trim($ret);
- return $ret;
- }
- function wp_rel_nofollow( $text ) {
- global $wpdb;
- // This is a pre save filter, so text is already escaped.
- $text = stripslashes($text);
- $text = preg_replace('|<a (.+?)>|ie', "'<a ' . str_replace(' rel=\"nofollow\"','',stripslashes('$1')) . ' rel=\"nofollow\">'", $text);
- $text = $wpdb->escape($text);
- return $text;
- }
- function convert_smilies($text) {
- global $wp_smiliessearch, $wp_smiliesreplace;
- $output = '';
- if (get_option('use_smilies')) {
- // 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++) {
- $content = $textarr[$i];
- if ((strlen($content) > 0) && ('<' != $content{0})) { // If it's not a tag
- $content = preg_replace($wp_smiliessearch, $wp_smiliesreplace, $content);
- }
- $output .= $content;
- }
- } else {
- // return default text.
- $output = $text;
- }
- return $output;
- }
- function is_email($user_email) {
- $chars = "/^([a-z0-9+_]|\\-|\\.)+@(([a-z0-9_]|\\-)+\\.)+[a-z]{2,6}\$/i";
- if (strpos($user_email, '@') !== false && strpos($user_email, '.') !== false) {
- if (preg_match($chars, $user_email)) {
- return true;
- } else {
- return false;
- }
- } else {
- return false;
- }
- }
- // used by wp-mail to handle charsets in email subjects
- function wp_iso_descrambler($string) {
- /* this may only work with iso-8859-1, I'm afraid */
- if (!preg_match('#\=\?(.+)\?Q\?(.+)\?\=#i', $string, $matches)) {
- return $string;
- } else {
- $subject = str_replace('_', ' ', $matches[2]);
- $subject = preg_replace('#\=([0-9a-f]{2})#ei', "chr(hexdec(strtolower('$1')))", $subject);
- return $subject;
- }
- }
- // give it a date, it will give you the same date as GMT
- function get_gmt_from_date($string) {
- // note: this only substracts $time_difference from the given date
- 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_gmt = gmdate('Y-m-d H:i:s', $string_time - get_option('gmt_offset') * 3600);
- return $string_gmt;
- }
- // give it a GMT date, it will give you the same date with $time_difference added
- function get_date_from_gmt($string) {
- // note: this only adds $time_difference to the given date
- 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('Y-m-d H:i:s', $string_time + get_option('gmt_offset')*3600);
- return $string_localtime;
- }
- // computes an offset in seconds from an iso8601 timezone
- function iso8601_timezone_to_offset($timezone) {
- // $timezone is either 'Z' or '[+|-]hhmm'
- if ($timezone == 'Z') {
- $offset = 0;
- } else {
- $sign = (substr($timezone, 0, 1) == '+') ? 1 : -1;
- $hours = intval(substr($timezone, 1, 2));
- $minutes = intval(substr($timezone, 3, 4)) / 60;
- $offset = $sign * 3600 * ($hours + $minutes);
- }
- return $offset;
- }
- // converts an iso8601 date to MySQL DateTime format used by post_date[_gmt]
- function iso8601_to_datetime($date_string, $timezone = USER) {
- if ($timezone == GMT) {
- preg_match('#([0-9]{4})([0-9]{2})([0-9]{2})T([0-9]{2}):([0-9]{2}):([0-9]{2})(Z|[\+|\-][0-9]{2,4}){0,1}#', $date_string, $date_bits);
- if (!empty($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');
- }
- $timestamp = gmmktime($date_bits[4], $date_bits[5], $date_bits[6], $date_bits[2], $date_bits[3], $date_bits[1]);
- $timestamp -= $offset;
- return gmdate('Y-m-d H:i:s', $timestamp);
- } elseif ($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', $date_string);
- }
- }
- function popuplinks($text) {
- // Comment text in popup windows should be filtered through this.
- // Right now it's a moderately dumb function, ideally it would detect whether
- // a target or rel attribute was already there and adjust its actions accordingly.
- $text = preg_replace('/<a (.+?)>/i', "<a $1 target='_blank' rel='external'>", $text);
- return $text;
- }
- function sanitize_email($email) {
- return preg_replace('/[^a-z0-9+_.@-]/i', '', $email);
- }
- function human_time_diff( $from, $to = '' ) {
- if ( empty($to) )
- $to = time();
- $diff = (int) abs($to - $from);
- if ($diff <= 3600) {
- $mins = round($diff / 60);
- if ($mins <= 1) {
- $mins = 1;
- }
- $since = sprintf(__ngettext('%s min', '%s mins', $mins), $mins);
- } else if (($diff <= 86400) && ($diff > 3600)) {
- $hours = round($diff / 3600);
- if ($hours <= 1) {
- $hour = 1;
- }
- $since = sprintf(__ngettext('%s hour', '%s hours', $hours), $hours);
- } elseif ($diff >= 86400) {
- $days = round($diff / 86400);
- if ($days <= 1) {
- $days = 1;
- }
- $since = sprintf(__ngettext('%s day', '%s days', $days), $days);
- }
- return $since;
- }
- function wp_trim_excerpt($text) { // Fakes an excerpt if needed
- global $post;
- if ( '' == $text ) {
- $text = get_the_content('');
- $text = apply_filters('the_content', $text);
- $text = str_replace(']]>', ']]>', $text);
- $text = strip_tags($text);
- $excerpt_length = 55;
- $words = explode(' ', $text, $excerpt_length + 1);
- if (count($words) > $excerpt_length) {
- array_pop($words);
- array_push($words, '[...]');
- $text = implode(' ', $words);
- }
- }
- return $text;
- }
- function ent2ncr($text) {
- $to_ncr = array(
- '"' => '"',
- '&' => '&',
- '⁄' => '/',
- '<' => '<',
- '>' => '>',
- '|' => '|',
- ' ' => ' ',
- '¡' => '¡',
- '¢' => '¢',
- '£' => '£',
- '¤' => '¤',
- '¥' => '¥',
- '¦' => '¦',
- '&brkbar;' => '¦',
- '§' => '§',
- '¨' => '¨',
- '¨' => '¨',
- '©' => '©',
- 'ª' => 'ª',
- '«' => '«',
- '¬' => '¬',
- '­' => '­',
- '®' => '®',
- '¯' => '¯',
- '&hibar;' => '¯',
- '°' => '°',
- '±' => '±',
- '²' => '²',
- '³' => '³',
- '´' => '´',
- 'µ' => 'µ',
- '¶' => '¶',
- '·' => '·',
- '¸' => '¸',
- '¹' => '¹',
- 'º' => 'º',
- '»' => '»',
- '¼' => '¼',
- '½' => '½',
- '¾' => '¾',
- '¿' => '¿',
- 'À' => 'À',
- 'Á' => 'Á',
- 'Â' => 'Â',
- 'Ã' => 'Ã',
- 'Ä' => 'Ä',
- 'Å' => 'Å',
- 'Æ' => 'Æ',
- 'Ç' => 'Ç',
- 'È' => 'È',
- 'É' => 'É',
- 'Ê' => 'Ê',
- 'Ë' => 'Ë',
- 'Ì' => 'Ì',
- 'Í' => 'Í',
- 'Î' => 'Î',
- 'Ï' => 'Ï',
- 'Ð' => 'Ð',
- 'Ñ' => 'Ñ',
- 'Ò' => 'Ò',
- 'Ó' => 'Ó',
- 'Ô' => 'Ô',
- 'Õ' => 'Õ',
- 'Ö' => 'Ö',
- '×' => '×',
- 'Ø' => 'Ø',
- 'Ù' => 'Ù',
- 'Ú' => 'Ú',
- 'Û' => 'Û',
- 'Ü' => 'Ü',
- 'Ý' => 'Ý',
- 'Þ' => 'Þ',
- 'ß' => 'ß',
- 'à' => 'à',
- 'á' => 'á',
- 'â' => 'â',
- 'ã' => 'ã',
- 'ä' => 'ä',
- 'å' => 'å',
- 'æ' => 'æ',
- 'ç' => 'ç',
- 'è' => 'è',
- 'é' => 'é',
- 'ê' => 'ê',
- 'ë' => 'ë',
- 'ì' => 'ì',
- 'í' => 'í',
- 'î' => 'î',
- 'ï' => 'ï',
- 'ð' => 'ð',
- 'ñ' => 'ñ',
- 'ò' => 'ò',
- 'ó' => 'ó',
- 'ô' => 'ô',
- 'õ' => 'õ',
- 'ö' => 'ö',
- '÷' => '÷',
- 'ø' => 'ø',
- 'ù' => 'ù',
- 'ú' => 'ú',
- 'û' => 'û',
- 'ü' => 'ü',
- 'ý' => 'ý',
- 'þ' => 'þ',
- 'ÿ' => 'ÿ',
- 'Œ' => 'Œ',
- 'œ' => 'œ',
- 'Š' => 'Š',
- 'š' => 'š',
- 'Ÿ' => 'Ÿ',
- 'ƒ' => 'ƒ',
- 'ˆ' => 'ˆ',
- '˜' => '˜',
- 'Α' => 'Α',
- 'Β' => 'Β',
- 'Γ' => 'Γ',
- 'Δ' => 'Δ',
- 'Ε' => 'Ε',
- 'Ζ' => 'Ζ',
- 'Η' => 'Η',
- 'Θ' => 'Θ',
- 'Ι' => 'Ι',
- 'Κ' => 'Κ',
- 'Λ' => 'Λ',
- 'Μ' => 'Μ',
- 'Ν' => 'Ν',
- 'Ξ' => 'Ξ',
- 'Ο' => 'Ο',
- 'Π' => 'Π',
- 'Ρ' => 'Ρ',
- 'Σ' => 'Σ',
- 'Τ' => 'Τ',
- 'Υ' => 'Υ',
- 'Φ' => 'Φ',
- 'Χ' => 'Χ',
- 'Ψ' => 'Ψ',
- 'Ω' => 'Ω',
- 'α' => 'α',
- 'β' => 'β',
- 'γ' => 'γ',
- 'δ' => 'δ',
- 'ε' => 'ε',
- 'ζ' => 'ζ',
- 'η' => 'η',
- 'θ' => 'θ',
- 'ι' => 'ι',
- 'κ' => 'κ',
- 'λ' => 'λ',
- 'μ' => 'μ',
- 'ν' => 'ν',
- 'ξ' => 'ξ',
- 'ο' => 'ο',
- 'π' => 'π',
- 'ρ' => 'ρ',
- 'ς' => 'ς',
- 'σ' => 'σ',
- 'τ' => 'τ',
- 'υ' => 'υ',
- 'φ' => 'φ',
- 'χ' => 'χ',
- 'ψ' => 'ψ',
- 'ω' => 'ω',
- 'ϑ' => 'ϑ',
- 'ϒ' => 'ϒ',
- 'ϖ' => 'ϖ',
- ' ' => ' ',
- ' ' => ' ',
- ' ' => ' ',
- '‌' => '‌',
- '‍' => '‍',
- '‎' => '‎',
- '‏' => '‏',
- '–' => '–',
- '—' => '—',
- '‘' => '‘',
- '’' => '’',
- '‚' => '‚',
- '“' => '“',
- '”' => '”',
- '„' => '„',
- '†' => '†',
- '‡' => '‡',
- '•' => '•',
- '…' => '…',
- '‰' => '‰',
- '′' => '′',
- '″' => '″',
- '‹' => '‹',
- '›' => '›',
- '‾' => '‾',
- '⁄' => '⁄',
- '€' => '€',
- 'ℑ' => 'ℑ',
- '℘' => '℘',
- 'ℜ' => 'ℜ',
- '™' => '™',
- 'ℵ' => 'ℵ',
- '↵' => '↵',
- '⇐' => '⇐',
- '⇑' => '⇑',
- '⇒' => '⇒',
- '⇓' => '⇓',
- '⇔' => '⇔',
- '∀' => '∀',
- '∂' => '∂',
- '∃' => '∃',
- '∅' => '∅',
- '∇' => '∇',
- '∈' => '∈',
- '∉' => '∉',
- '∋' => '∋',
- '∏' => '∏',
- '∑' => '∑',
- '−' => '−',
- '∗' => '∗',
- '√' => '√',
- '∝' => '∝',
- '∞' => '∞',
- '∠' => '∠',
- '∧' => '∧',
- '∨' => '∨',
- '∩' => '∩',
- '∪' => '∪',
- '∫' => '∫',
- '∴' => '∴',
- '∼' => '∼',
- '≅' => '≅',
- '≈' => '≈',
- '≠' => '≠',
- '≡' => '≡',
- '≤' => '≤',
- '≥' => '≥',
- '⊂' => '⊂',
- '⊃' => '⊃',
- '⊄' => '⊄',
- '⊆' => '⊆',
- '⊇' => '⊇',
- '⊕' => '⊕',
- '⊗' => '⊗',
- '⊥' => '⊥',
- '⋅' => '⋅',
- '⌈' => '⌈',
- '⌉' => '⌉',
- '⌊' => '⌊',
- '⌋' => '⌋',
- '⟨' => '〈',
- '⟩' => '〉',
- '←' => '←',
- '↑' => '↑',
- '→' => '→',
- '↓' => '↓',
- '↔' => '↔',
- '◊' => '◊',
- '♠' => '♠',
- '♣' => '♣',
- '♥' => '♥',
- '♦' => '♦'
- );
- return str_replace( array_keys($to_ncr), array_values($to_ncr), $text );
- }
- function wp_richedit_pre($text) {
- // Filtering a blank results in an annoying <br />\n
- if ( empty($text) ) return apply_filters('richedit_pre', '');
- $output = $text;
- $output = convert_chars($output);
- $output = wpautop($output);
- // These must be double-escaped or planets will collide.
- $output = str_replace('<', '&lt;', $output);
- $output = str_replace('>', '&gt;', $output);
- return apply_filters('richedit_pre', $output);
- }
- function clean_url( $url, $protocols = null ) {
- if ('' == $url) return $url;
- $url = preg_replace('|[^a-z0-9-~+_.?#=!&;,/:%]|i', '', $url);
- $strip = array('%0d', '%0a');
- $url = str_replace($strip, '', $url);
- $url = str_replace(';//', '://', $url);
- // Append http unless a relative link starting with / or a php file.
- if ( strpos($url, '://') === false &&
- substr( $url, 0, 1 ) != '/' && !preg_match('/^[a-z0-9-]+?\.php/i', $url) )
- $url = 'http://' . $url;
-
- $url = preg_replace('/&([^#])(?![a-z]{2,8};)/', '&$1', $url);
- if ( !is_array($protocols) )
- $protocols = array('http', 'https', 'ftp', 'ftps', 'mailto', 'news', 'irc', 'gopher', 'nntp', 'feed', 'telnet');
- if ( wp_kses_bad_protocol( $url, $protocols ) != $url )
- return '';
- return $url;
- }
- // Borrowed from the PHP Manual user notes. Convert entities, while
- // preserving already-encoded entities:
- function htmlentities2($myHTML) {
- $translation_table=get_html_translation_table (HTML_ENTITIES,ENT_QUOTES);
- $translation_table[chr(38)] = '&';
- return preg_replace("/&(?![A-Za-z]{0,4}\w{2,3};|#[0-9]{2,3};)/","&" , strtr($myHTML, $translation_table));
- }
- // Escape single quotes, specialchar double quotes, and fix line endings.
- function js_escape($text) {
- $safe_text = wp_specialchars($text, 'double');
- $safe_text = preg_replace('/&#(x)?0*(?(1)27|39);?/i', "'", stripslashes($safe_text));
- $safe_text = preg_replace("/\r?\n/", "\\n", addslashes($safe_text));
- return apply_filters('js_escape', $safe_text, $text);
- }
- // Escaping for HTML attributes
- function attribute_escape($text) {
- $safe_text = wp_specialchars($text, true);
- return apply_filters('attribute_escape', $safe_text, $text);
- }
- function wp_make_link_relative( $link ) {
- return preg_replace('|https?://[^/]+(/.*)|i', '$1', $link );
- }
- function sanitize_option($option, $value) { // Remember to call stripslashes!
- switch ($option) {
- case 'admin_email':
- $value = sanitize_email($value);
- break;
- case 'default_post_edit_rows':
- case 'mailserver_port':
- case 'comment_max_links':
- case 'page_on_front':
- case 'rss_excerpt_length':
- case 'default_category':
- case 'default_email_category':
- case 'default_link_category':
- $value = abs((int) $value);
- break;
- case 'posts_per_page':
- case 'posts_per_rss':
- $value = (int) $value;
- if ( empty($value) ) $value = 1;
- if ( $value < -1 ) $value = abs($value);
- break;
- case 'default_ping_status':
- case 'default_comment_status':
- // Options that if not there have 0 value but need to be something like "closed"
- if ( $value == '0' || $value == '')
- $value = 'closed';
- break;
- case 'blogdescription':
- case 'blogname':
- $value = addslashes($value);
- $value = wp_filter_post_kses( $value ); // calls stripslashes then addslashes
- $value = stripslashes($value);
- $value = wp_specialchars( $value );
- break;
- case 'blog_charset':
- $value = preg_replace('/[^a-zA-Z0-9_-]/', '', $value); // strips slashes
- break;
- case 'date_format':
- case 'time_format':
- case 'mailserver_url':
- case 'mailserver_login':
- case 'mailserver_pass':
- case 'ping_sites':
- case 'upload_path':
- $value = strip_tags($value);
- $value = addslashes($value);
- $value = wp_filter_kses($value); // calls stripslashes then addslashes
- $value = stripslashes($value);
- break;
- case 'gmt_offset':
- $value = preg_replace('/[^0-9:.-]/', '', $value); // strips slashes
- break;
- case 'siteurl':
- case 'home':
- $value = stripslashes($value);
- $value = clean_url($value);
- break;
- default :
- break;
- }
- return $value;
- }
- function wp_parse_str( $string, &$array ) {
- parse_str( $string, $array );
- if ( get_magic_quotes_gpc() )
- $array = stripslashes_deep( $array ); // parse_str() adds slashes if magicquotes is on. See: http://php.net/parse_str
- $array = apply_filters( 'wp_parse_str', $array );
- }
- ?>