Beanz/flatpress
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Bugfix: sanitize_title_with_dashes() handles characters > chr(128) correctly

Browse Source 
-> fixes https://github.com/flatpressblog/flatpress/pull/11 by @moortaube in a general way
This commit is contained in:
azett 2018-12-31 12:04:25 +01:00
parent 37674c542a
commit 9f610ddac3
1 changed files with 1072 additions and 937 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

537
fp-includes/core/core.wp-formatting.php
View File

@ -1,15 +1,11 @@
<?php <?php
function wptexturize($text) { function wptexturize($text) {
$output = ''; $output = '';
// Capture tags and everything inside them // Capture tags and everything inside them
$textarr = preg_split("/(<.*>)/Us", $text, -1, PREG_SPLIT_DELIM_CAPTURE); $textarr = preg_split("/(<.*>)/Us", $text, -1, PREG_SPLIT_DELIM_CAPTURE);
$stop = count($textarr); $skip = 0; // loop stuff $stop = count($textarr);
$skip = 0; // loop stuff
for($i = 0; $i < $stop; $i++) { for($i = 0; $i < $stop; $i++) {
$curl = $textarr [$i]; $curl = $textarr [$i];
@ -21,10 +17,31 @@
$curl = str_replace('...', '&#8230;', $curl); $curl = str_replace('...', '&#8230;', $curl);
$curl = str_replace('``', '&#8220;', $curl); $curl = str_replace('``', '&#8220;', $curl);
// This is a hack, look at this more later. It works pretty well though. // This is a hack, look at this more later. It works pretty well though.
$cockney = array("'tain't","'twere","'twas","'tis","'twill","'til","'bout","'nuff","'round","'cause"); $cockney = array(
$cockneyreplace = array("&#8217;tain&#8217;t","&#8217;twere","&#8217;twas","&#8217;tis","&#8217;twill","&#8217;til","&#8217;bout","&#8217;nuff","&#8217;round","&#8217;cause"); "'tain't",
"'twere",
"'twas",
"'tis",
"'twill",
"'til",
"'bout",
"'nuff",
"'round",
"'cause"
);
$cockneyreplace = array(
"&#8217;tain&#8217;t",
"&#8217;twere",
"&#8217;twas",
"&#8217;tis",
"&#8217;twill",
"&#8217;til",
"&#8217;bout",
"&#8217;nuff",
"&#8217;round",
"&#8217;cause"
);
$curl = str_replace($cockney, $cockneyreplace, $curl); $curl = str_replace($cockney, $cockneyreplace, $curl);
$curl = preg_replace("/'s/", '&#8217;s', $curl); $curl = preg_replace("/'s/", '&#8217;s', $curl);
@ -47,12 +64,14 @@
$curl = preg_replace('/(\d+)x(\d+)/', "$1&#215;$2", $curl); $curl = preg_replace('/(\d+)x(\d+)/', "$1&#215;$2", $curl);
} elseif (strstr($curl, '</') || strstr($curl, '/>')) { } elseif (strstr($curl, '</') || strstr($curl, '/>')) {
if ($skip > 0) $skip--; if ($skip > 0)
$skip--;
} elseif (strstr($curl, '<code') || strstr($curl, '<pre') || strstr($curl, '<kbd' || strstr($curl, '<style') || strstr($curl, '<script'))) { } elseif (strstr($curl, '<code') || strstr($curl, '<pre') || strstr($curl, '<kbd' || strstr($curl, '<style') || strstr($curl, '<script'))) {
// strstr is fast // strstr is fast
$skip++; $skip++;
} else { } else {
if (isset($curl{0}) && $curl{0} == "<" && $skip > 0) $skip++; if (isset($curl {0}) && $curl {0} == "<" && $skip > 0)
$skip++;
} }
$curl = preg_replace('/&([^#])(?![a-z12]{1,8};)/', '&#038;$1', $curl); $curl = preg_replace('/&([^#])(?![a-z12]{1,8};)/', '&#038;$1', $curl);
$output .= $curl; $output .= $curl;
@ -60,8 +79,6 @@
return $output; return $output;
} }
function clean_pre($matches) { function clean_pre($matches) {
if (is_array($matches)) if (is_array($matches))
$text = $matches [1] . $matches [2] . "</pre>"; $text = $matches [1] . $matches [2] . "</pre>";
@ -86,12 +103,13 @@
* *
* @since 0.71 * @since 0.71
* *
* @param string $pee The text which has to be formatted. * @param string $pee
* @param int|bool $br Optional. If set, this will convert all remaining line-breaks after paragraphing. Default true. * The text which has to be formatted.
* @param int|bool $br
* Optional. If set, this will convert all remaining line-breaks after paragraphing. Default true.
* @return string Text which has been converted into correct paragraph tags. * @return string Text which has been converted into correct paragraph tags.
*/ */
function wpautop($pee, $br = 1) { function wpautop($pee, $br = 1) {
if (trim($pee) === '') if (trim($pee) === '')
return ''; return '';
$pee = $pee . "\n"; // just to make things a little easier, pad the end $pee = $pee . "\n"; // just to make things a little easier, pad the end
@ -100,7 +118,10 @@ function wpautop($pee, $br = 1) {
$allblocks = '(?:table|thead|tfoot|caption|col|colgroup|tbody|tr|td|th|div|dl|dd|dt|ul|ol|li|pre|select|option|form|map|area|blockquote|address|math|style|input|p|h[1-6]|hr|fieldset|legend|section|article|aside|hgroup|header|footer|nav|figure|figcaption|details|menu|summary)'; $allblocks = '(?:table|thead|tfoot|caption|col|colgroup|tbody|tr|td|th|div|dl|dd|dt|ul|ol|li|pre|select|option|form|map|area|blockquote|address|math|style|input|p|h[1-6]|hr|fieldset|legend|section|article|aside|hgroup|header|footer|nav|figure|figcaption|details|menu|summary)';
$pee = preg_replace('!(<' . $allblocks . '[^>]*>)!', "\n$1", $pee); $pee = preg_replace('!(<' . $allblocks . '[^>]*>)!', "\n$1", $pee);
$pee = preg_replace('!(</' . $allblocks . '>)!', "$1\n\n", $pee); $pee = preg_replace('!(</' . $allblocks . '>)!', "$1\n\n", $pee);
$pee = str_replace(array("\r\n", "\r"), "\n", $pee); // cross-platform newlines $pee = str_replace(array(
"\r\n",
"\r"
), "\n", $pee); // cross-platform newlines
if (strpos($pee, '<object') !== false) { if (strpos($pee, '<object') !== false) {
$pee = preg_replace('|\s*<param([^>]*)>\s*|', "<param$1>", $pee); // no pee inside object/embed $pee = preg_replace('|\s*<param([^>]*)>\s*|', "<param$1>", $pee); // no pee inside object/embed
$pee = preg_replace('|\s*</embed>\s*|', '</embed>', $pee); $pee = preg_replace('|\s*</embed>\s*|', '</embed>', $pee);
@ -138,23 +159,31 @@ function wpautop($pee, $br = 1) {
* *
* @since 3.1.0 * @since 3.1.0
* @access private * @access private
* @param array $matches preg_replace_callback matches array * @param array $matches
* preg_replace_callback matches array
* @returns string * @returns string
*/ */
function _autop_newline_preservation_helper($matches) { function _autop_newline_preservation_helper($matches) {
return str_replace("\n", "<WPPreserveNewline />", $matches [0]); return str_replace("\n", "<WPPreserveNewline />", $matches [0]);
} }
function seems_utf8($Str) { # by bmorel at ssi dot fr function seems_utf8($Str) { // by bmorel at ssi dot fr
for($i = 0; $i < strlen($Str); $i++) { for($i = 0; $i < strlen($Str); $i++) {
if (ord($Str[$i]) < 0x80) continue; # 0bbbbbbb if (ord($Str [$i]) < 0x80)
elseif ((ord($Str[$i]) & 0xE0) == 0xC0) $n=1; # 110bbbbb continue; // 0bbbbbbb
elseif ((ord($Str[$i]) & 0xF0) == 0xE0) $n=2; # 1110bbbb elseif ((ord($Str [$i]) & 0xE0) == 0xC0)
elseif ((ord($Str[$i]) & 0xF8) == 0xF0) $n=3; # 11110bbb $n = 1; // 110bbbbb
elseif ((ord($Str[$i]) & 0xFC) == 0xF8) $n=4; # 111110bb elseif ((ord($Str [$i]) & 0xF0) == 0xE0)
elseif ((ord($Str[$i]) & 0xFE) == 0xFC) $n=5; # 1111110b $n = 2; // 1110bbbb
else return false; # Does not match any model elseif ((ord($Str [$i]) & 0xF8) == 0xF0)
for ($j=0; $j<$n; $j++) { # n bytes matching 10bbbbbb follow ? $n = 3; // 11110bbb
elseif ((ord($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 [$i]) & 0xC0) != 0x80)) if ((++$i == strlen($Str)) || ((ord($Str [$i]) & 0xC0) != 0x80))
return false; return false;
} }
@ -163,21 +192,15 @@ function _autop_newline_preservation_helper( $matches ) {
} }
function fmt_escape_separator($text, $sep = '|') { function fmt_escape_separator($text, $sep = '|') {
return str_replace('|', '&#124;', $text); return str_replace('|', '&#124;', $text);
} }
function fmt_unescape_separator($text, $sep = '|') { function fmt_unescape_separator($text, $sep = '|') {
return str_replace('&#124;', '|', $text); return str_replace('&#124;', '|', $text);
} }
function wp_specialchars($text, $quotes = 0) { function wp_specialchars($text, $quotes = 0) {
// Like htmlspecialchars except don't double-encode HTML entities // Like htmlspecialchars except don't double-encode HTML entities
$text = preg_replace('/&([^#])(?![a-z12]{1,8};)/', '&#038;$1', $text); $text = preg_replace('/&([^#])(?![a-z12]{1,8};)/', '&#038;$1', $text);
$text = str_replace('<', '&lt;', $text); $text = str_replace('<', '&lt;', $text);
$text = str_replace('>', '&gt;', $text); $text = str_replace('>', '&gt;', $text);
@ -201,7 +224,8 @@ function _autop_newline_preservation_helper( $matches ) {
if ($value < 128) { if ($value < 128) {
$unicode .= chr($value); $unicode .= chr($value);
} else { } else {
if ( count( $values ) == 0 ) $num_octets = ( $value < 224 ) ? 2 : 3; if (count($values) == 0)
$num_octets = ($value < 224) ? 2 : 3;
$values [] = $value; $values [] = $value;
@ -225,121 +249,224 @@ function _autop_newline_preservation_helper( $matches ) {
if (seems_utf8($string)) { if (seems_utf8($string)) {
$chars = array( $chars = array(
// Decompositions for Latin-1 Supplement // Decompositions for Latin-1 Supplement
chr(195).chr(128) => 'A', chr(195).chr(129) => 'A', chr(195) . chr(128) => 'A',
chr(195).chr(130) => 'A', chr(195).chr(131) => 'A', chr(195) . chr(129) => 'A',
chr(195).chr(132) => 'A', chr(195).chr(133) => 'A', chr(195) . chr(130) => 'A',
chr(195).chr(135) => 'C', chr(195).chr(136) => 'E', chr(195) . chr(131) => 'A',
chr(195).chr(137) => 'E', chr(195).chr(138) => 'E', chr(195) . chr(132) => 'A',
chr(195).chr(139) => 'E', chr(195).chr(140) => 'I', chr(195) . chr(133) => 'A',
chr(195).chr(141) => 'I', chr(195).chr(142) => 'I', chr(195) . chr(135) => 'C',
chr(195).chr(143) => 'I', chr(195).chr(145) => 'N', chr(195) . chr(136) => 'E',
chr(195).chr(146) => 'O', chr(195).chr(147) => 'O', chr(195) . chr(137) => 'E',
chr(195).chr(148) => 'O', chr(195).chr(149) => 'O', chr(195) . chr(138) => 'E',
chr(195).chr(150) => 'O', chr(195).chr(153) => 'U', chr(195) . chr(139) => 'E',
chr(195).chr(154) => 'U', chr(195).chr(155) => 'U', chr(195) . chr(140) => 'I',
chr(195).chr(156) => 'U', chr(195).chr(157) => 'Y', chr(195) . chr(141) => 'I',
chr(195).chr(159) => 's', chr(195).chr(160) => 'a', chr(195) . chr(142) => 'I',
chr(195).chr(161) => 'a', chr(195).chr(162) => 'a', chr(195) . chr(143) => 'I',
chr(195).chr(163) => 'a', chr(195).chr(164) => 'a', chr(195) . chr(145) => 'N',
chr(195).chr(165) => 'a', chr(195).chr(167) => 'c', chr(195) . chr(146) => 'O',
chr(195).chr(168) => 'e', chr(195).chr(169) => 'e', chr(195) . chr(147) => 'O',
chr(195).chr(170) => 'e', chr(195).chr(171) => 'e', chr(195) . chr(148) => 'O',
chr(195).chr(172) => 'i', chr(195).chr(173) => 'i', chr(195) . chr(149) => 'O',
chr(195).chr(174) => 'i', chr(195).chr(175) => 'i', chr(195) . chr(150) => 'O',
chr(195).chr(177) => 'n', chr(195).chr(178) => 'o', chr(195) . chr(153) => 'U',
chr(195).chr(179) => 'o', chr(195).chr(180) => 'o', chr(195) . chr(154) => 'U',
chr(195).chr(181) => 'o', chr(195).chr(182) => 'o', chr(195) . chr(155) => 'U',
chr(195).chr(182) => 'o', chr(195).chr(185) => 'u', chr(195) . chr(156) => 'U',
chr(195).chr(186) => 'u', chr(195).chr(187) => 'u', chr(195) . chr(157) => 'Y',
chr(195).chr(188) => 'u', chr(195).chr(189) => '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', chr(195) . chr(191) => 'y',
// Decompositions for Latin Extended-A // Decompositions for Latin Extended-A
chr(196).chr(128) => 'A', chr(196).chr(129) => 'a', chr(196) . chr(128) => 'A',
chr(196).chr(130) => 'A', chr(196).chr(131) => 'a', chr(196) . chr(129) => 'a',
chr(196).chr(132) => 'A', chr(196).chr(133) => 'a', chr(196) . chr(130) => 'A',
chr(196).chr(134) => 'C', chr(196).chr(134) => 'c', chr(196) . chr(131) => 'a',
chr(196).chr(136) => 'C', chr(196).chr(137) => 'c', chr(196) . chr(132) => 'A',
chr(196).chr(138) => 'C', chr(196).chr(139) => 'c', chr(196) . chr(133) => 'a',
chr(196).chr(140) => 'C', chr(196).chr(141) => 'c', chr(196) . chr(134) => 'C',
chr(196).chr(142) => 'D', chr(196).chr(143) => 'd', chr(196) . chr(134) => 'c',
chr(196).chr(144) => 'D', chr(196).chr(145) => 'd', chr(196) . chr(136) => 'C',
chr(196).chr(146) => 'E', chr(196).chr(147) => 'e', chr(196) . chr(137) => 'c',
chr(196).chr(148) => 'E', chr(196).chr(149) => 'e', chr(196) . chr(138) => 'C',
chr(196).chr(150) => 'E', chr(196).chr(151) => 'e', chr(196) . chr(139) => 'c',
chr(196).chr(152) => 'E', chr(196).chr(153) => 'e', chr(196) . chr(140) => 'C',
chr(196).chr(154) => 'E', chr(196).chr(155) => 'e', chr(196) . chr(141) => 'c',
chr(196).chr(156) => 'G', chr(196).chr(157) => 'g', chr(196) . chr(142) => 'D',
chr(196).chr(158) => 'G', chr(196).chr(159) => 'g', chr(196) . chr(143) => 'd',
chr(196).chr(160) => 'G', chr(196).chr(161) => 'g', chr(196) . chr(144) => 'D',
chr(196).chr(162) => 'G', chr(196).chr(163) => 'g', chr(196) . chr(145) => 'd',
chr(196).chr(164) => 'H', chr(196).chr(165) => 'h', chr(196) . chr(146) => 'E',
chr(196).chr(166) => 'H', chr(196).chr(167) => 'h', chr(196) . chr(147) => 'e',
chr(196).chr(168) => 'I', chr(196).chr(169) => 'i', chr(196) . chr(148) => 'E',
chr(196).chr(170) => 'I', chr(196).chr(171) => 'i', chr(196) . chr(149) => 'e',
chr(196).chr(172) => 'I', chr(196).chr(173) => 'i', chr(196) . chr(150) => 'E',
chr(196).chr(174) => 'I', chr(196).chr(175) => 'i', chr(196) . chr(151) => 'e',
chr(196).chr(176) => 'I', chr(196).chr(177) => 'i', chr(196) . chr(152) => 'E',
chr(196).chr(178) => 'IJ',chr(196).chr(179) => 'ij', chr(196) . chr(153) => 'e',
chr(196).chr(180) => 'J', chr(196).chr(181) => 'j', chr(196) . chr(154) => 'E',
chr(196).chr(182) => 'K', chr(196).chr(183) => 'k', chr(196) . chr(155) => 'e',
chr(196).chr(184) => 'k', chr(196).chr(185) => 'L', chr(196) . chr(156) => 'G',
chr(196).chr(186) => 'l', chr(196).chr(187) => 'L', chr(196) . chr(157) => 'g',
chr(196).chr(188) => 'l', chr(196).chr(189) => 'L', chr(196) . chr(158) => 'G',
chr(196).chr(190) => 'l', chr(196).chr(191) => 'L', chr(196) . chr(159) => 'g',
chr(197).chr(128) => 'l', chr(196).chr(129) => 'L', chr(196) . chr(160) => 'G',
chr(197).chr(130) => 'l', chr(196).chr(131) => 'N', chr(196) . chr(161) => 'g',
chr(197).chr(132) => 'n', chr(196).chr(133) => 'N', chr(196) . chr(162) => 'G',
chr(197).chr(134) => 'n', chr(196).chr(135) => 'N', chr(196) . chr(163) => 'g',
chr(197).chr(136) => 'n', chr(196).chr(137) => 'N', chr(196) . chr(164) => 'H',
chr(197).chr(138) => 'n', chr(196).chr(139) => 'N', chr(196) . chr(165) => 'h',
chr(197).chr(140) => 'O', chr(196).chr(141) => 'o', chr(196) . chr(166) => 'H',
chr(197).chr(142) => 'O', chr(196).chr(143) => 'o', chr(196) . chr(167) => 'h',
chr(197).chr(144) => 'O', chr(196).chr(145) => 'o', chr(196) . chr(168) => 'I',
chr(197).chr(146) => 'OE',chr(197).chr(147) => 'oe', chr(196) . chr(169) => 'i',
chr(197).chr(148) => 'R',chr(197).chr(149) => 'r', chr(196) . chr(170) => 'I',
chr(197).chr(150) => 'R',chr(197).chr(151) => 'r', chr(196) . chr(171) => 'i',
chr(197).chr(152) => 'R',chr(197).chr(153) => 'r', chr(196) . chr(172) => 'I',
chr(197).chr(154) => 'S',chr(197).chr(155) => 's', chr(196) . chr(173) => 'i',
chr(197).chr(156) => 'S',chr(197).chr(157) => 's', chr(196) . chr(174) => 'I',
chr(197).chr(158) => 'S',chr(197).chr(159) => 's', chr(196) . chr(175) => 'i',
chr(197).chr(160) => 'S', chr(197).chr(161) => 's', chr(196) . chr(176) => 'I',
chr(197).chr(162) => 'T', chr(197).chr(163) => 't', chr(196) . chr(177) => 'i',
chr(197).chr(164) => 'T', chr(197).chr(165) => 't', chr(196) . chr(178) => 'IJ',
chr(197).chr(166) => 'T', chr(197).chr(167) => 't', chr(196) . chr(179) => 'ij',
chr(197).chr(168) => 'U', chr(197).chr(169) => 'u', chr(196) . chr(180) => 'J',
chr(197).chr(170) => 'U', chr(197).chr(171) => 'u', chr(196) . chr(181) => 'j',
chr(197).chr(172) => 'U', chr(197).chr(173) => 'u', chr(196) . chr(182) => 'K',
chr(197).chr(174) => 'U', chr(197).chr(175) => 'u', chr(196) . chr(183) => 'k',
chr(197).chr(176) => 'U', chr(197).chr(177) => 'u', chr(196) . chr(184) => 'k',
chr(197).chr(178) => 'U', chr(197).chr(179) => 'u', chr(196) . chr(185) => 'L',
chr(197).chr(180) => 'W', chr(197).chr(181) => 'w', chr(196) . chr(186) => 'l',
chr(197).chr(182) => 'Y', chr(197).chr(183) => 'y', chr(196) . chr(187) => 'L',
chr(197).chr(184) => 'Y', chr(197).chr(185) => 'Z', chr(196) . chr(188) => 'l',
chr(197).chr(186) => 'z', chr(197).chr(187) => 'Z', chr(196) . chr(189) => 'L',
chr(197).chr(188) => 'z', chr(197).chr(189) => 'Z', chr(196) . chr(190) => 'l',
chr(197).chr(190) => 'z', chr(197).chr(191) => 's', chr(196) . chr(191) => 'L',
chr(197) . chr(128) => 'l',
chr(196) . chr(129) => 'L',
chr(197) . chr(130) => 'l',
chr(196) . chr(131) => 'N',
chr(197) . chr(132) => 'n',
chr(196) . chr(133) => 'N',
chr(197) . chr(134) => 'n',
chr(196) . chr(135) => 'N',
chr(197) . chr(136) => 'n',
chr(196) . chr(137) => 'N',
chr(197) . chr(138) => 'n',
chr(196) . chr(139) => 'N',
chr(197) . chr(140) => 'O',
chr(196) . chr(141) => 'o',
chr(197) . chr(142) => 'O',
chr(196) . chr(143) => 'o',
chr(197) . chr(144) => 'O',
chr(196) . 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 // Euro Sign
chr(226).chr(130).chr(172) => 'E'); chr(226) . chr(130) . chr(172) => 'E'
);
$string = strtr($string, $chars); $string = strtr($string, $chars);
} else { } else {
// Assume ISO-8859-1 if not UTF-8 // Assume ISO-8859-1 if not UTF-8
$chars['in'] = chr(128).chr(131).chr(138).chr(142).chr(154).chr(158) $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);
.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"; $chars ['out'] = "EfSZszYcYuAAAAAACEEEEIIIINOOOOOOUUUUYaaaaaaceeeeiiiinoooooouuuuyy";
$string = strtr($string, $chars ['in'], $chars ['out']); $string = strtr($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 ['in'] = array(
$double_chars['out'] = array('OE', 'oe', 'AE', 'DH', 'TH', 'ss', 'ae', 'dh', 'th'); 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); $string = str_replace($double_chars ['in'], $double_chars ['out'], $string);
} }
@ -348,6 +475,7 @@ function _autop_newline_preservation_helper( $matches ) {
function sanitize_title($title, $fallback_title = '') { function sanitize_title($title, $fallback_title = '') {
$title = strip_tags($title); $title = strip_tags($title);
$title = apply_filters('sanitize_title', $title); $title = apply_filters('sanitize_title', $title);
if (empty($title)) { if (empty($title)) {
@ -359,14 +487,7 @@ function _autop_newline_preservation_helper( $matches ) {
function sanitize_title_with_dashes($title) { function sanitize_title_with_dashes($title) {
$title = strip_tags($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($title)) { if (seems_utf8($title)) {
if (function_exists('mb_strtolower')) { if (function_exists('mb_strtolower')) {
$title = mb_strtolower($title, 'UTF-8'); $title = mb_strtolower($title, 'UTF-8');
@ -374,11 +495,32 @@ function _autop_newline_preservation_helper( $matches ) {
$title = utf8_uri_encode($title); $title = utf8_uri_encode($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);
// and finally: Kill octets
$title = preg_replace('|%([a-fA-F0-9][a-fA-F0-9])|', '', $title);
// remove accents
$title = remove_accents($title);
// title is in lower case always
$title = strtolower($title); $title = strtolower($title);
$title = preg_replace('/&.+?;/', '', $title); // kill entities
// kill entities
$title = preg_replace('/&.+?;/', '', $title);
// kill special chars
$title = preg_replace('/[^%a-z0-9 _-]/', '', $title); $title = preg_replace('/[^%a-z0-9 _-]/', '', $title);
// replace spaces by dash
$title = preg_replace('/\s+/', '-', $title); $title = preg_replace('/\s+/', '-', $title);
// Kill multiple dashes
$title = preg_replace('|-+|', '-', $title); $title = preg_replace('|-+|', '-', $title);
// kill dashes at beginning and end of string
$title = trim($title, '-'); $title = trim($title, '-');
return $title; return $title;
@ -449,37 +591,39 @@ function _autop_newline_preservation_helper( $matches ) {
} }
/* /*
balanceTags * balanceTags
*
Balances Tags of string using a modified stack. * Balances Tags of string using a modified stack.
*
@param text Text to be balanced * @param text Text to be balanced
@return Returns balanced text * @return Returns balanced text
@author Leonard Lin (leonard@acm.org) * @author Leonard Lin (leonard@acm.org)
@version v1.1 * @version v1.1
@date November 4, 2001 * @date November 4, 2001
@license GPL v2.0 * @license GPL v2.0
@notes * @notes
@changelog * @changelog
--- Modified by Scott Reilly (coffee2code) 02 Aug 2004 * --- Modified by Scott Reilly (coffee2code) 02 Aug 2004
1.2 ***TODO*** Make better - change loop condition to $text * 1.2 ***TODO*** Make better - change loop condition to $text
1.1 Fixed handling of append/stack pop order of end text * 1.1 Fixed handling of append/stack pop order of end text
Added Cleaning Hooks * Added Cleaning Hooks
1.0 First Version * 1.0 First Version
*/ */
function balanceTags($text, $is_comment = 0) { function balanceTags($text, $is_comment = 0) {
/* /*
if (get_settings('use_balanceTags') == 0) { * if (get_settings('use_balanceTags') == 0) {
return $text; * return $text;
} * }
*/ */
$tagstack = array();
$stacksize = 0;
$tagqueue = '';
$newtext = '';
$tagstack = array(); $stacksize = 0; $tagqueue = ''; $newtext = ''; // WP bug fix for comments - in case you REALLY meant to type '< !--'
# WP bug fix for comments - in case you REALLY meant to type '< !--'
$text = str_replace('< !--', '< !--', $text); $text = str_replace('< !--', '< !--', $text);
# WP bug fix for LOVE <3 (and other situations with '<' before a number) // WP bug fix for LOVE <3 (and other situations with '<' before a number)
$text = preg_replace('#<([0-9]{1})#', '&lt;$1', $text); $text = preg_replace('#<([0-9]{1})#', '&lt;$1', $text);
while (preg_match("/<(\/?\w*)\s*([^>]*)>/", $text, $regex)) { while (preg_match("/<(\/?\w*)\s*([^>]*)>/", $text, $regex)) {
@ -497,8 +641,7 @@ function _autop_newline_preservation_helper( $matches ) {
if ($stacksize <= 0) { if ($stacksize <= 0) {
$tag = ''; $tag = '';
// or close to be safe $tag = '/' . $tag; // or close to be safe $tag = '/' . $tag;
} } // if stacktop value = tag close value then pop
// if stacktop value = tag close value then pop
else if ($tagstack [$stacksize - 1] == $tag) { // found closing tag else if ($tagstack [$stacksize - 1] == $tag) { // found closing tag
$tag = '</' . $tag . '>'; // Close Tag $tag = '</' . $tag . '>'; // Close Tag
// Pop // Pop
@ -524,8 +667,7 @@ function _autop_newline_preservation_helper( $matches ) {
// If self-closing or '', don't do anything. // If self-closing or '', don't do anything.
if ((substr($regex [2], -1) == '/') || ($tag == '')) { if ((substr($regex [2], -1) == '/') || ($tag == '')) {
} } // ElseIf it's a known single-entity tag but it doesn't close itself, do so
// ElseIf it's a known single-entity tag but it doesn't close itself, do so
elseif ($tag == 'br' || $tag == 'img' || $tag == 'hr' || $tag == 'input') { elseif ($tag == 'br' || $tag == 'img' || $tag == 'hr' || $tag == 'input') {
$regex [2] .= '/'; $regex [2] .= '/';
} else { // Push the tag onto the stack } else { // Push the tag onto the stack
@ -571,7 +713,6 @@ function _autop_newline_preservation_helper( $matches ) {
return $newtext; return $newtext;
} }
function format_to_edit($content) { function format_to_edit($content) {
$content = apply_filters('format_to_edit', $content); $content = apply_filters('format_to_edit', $content);
$content = htmlspecialchars($content); $content = htmlspecialchars($content);
@ -588,7 +729,6 @@ function _autop_newline_preservation_helper( $matches ) {
return sprintf('%0' . $threshold . 's', $number); return sprintf('%0' . $threshold . 's', $number);
} }
function backslashit($string) { function backslashit($string) {
$string = preg_replace('/([a-z])/i', '\\\\\1', $string); $string = preg_replace('/([a-z])/i', '\\\\\1', $string);
return $string; return $string;
@ -639,30 +779,28 @@ function _autop_newline_preservation_helper( $matches ) {
return $text; return $text;
} }
/* /*
function convert_smilies($text) { * function convert_smilies($text) {
global $wp_smiliessearch, $wp_smiliesreplace; * global $wp_smiliessearch, $wp_smiliesreplace;
$output = ''; * $output = '';
if (get_settings('use_smilies')) { * if (get_settings('use_smilies')) {
// HTML loop taken from texturize function, could possible be consolidated * // 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 * $textarr = preg_split("/(<.*>)/U", $text, -1, PREG_SPLIT_DELIM_CAPTURE); // capture the tags as well as in between
$stop = count($textarr);// loop stuff * $stop = count($textarr);// loop stuff
for ($i = 0; $i < $stop; $i++) { * for ($i = 0; $i < $stop; $i++) {
$content = $textarr[$i]; * $content = $textarr[$i];
if ((strlen($content) > 0) && ('<' != $content{0})) { // If it's not a tag * if ((strlen($content) > 0) && ('<' != $content{0})) { // If it's not a tag
$content = str_replace($wp_smiliessearch, $wp_smiliesreplace, $content); * $content = str_replace($wp_smiliessearch, $wp_smiliesreplace, $content);
} * }
$output .= $content; * $output .= $content;
} * }
} else { * } else {
// return default text. * // return default text.
$output = $text; * $output = $text;
} * }
return $output; * return $output;
} * }
*/ */
function is_email($user_email) { function is_email($user_email) {
$chars = "/^([a-z0-9+_]|\\-|\\.)+@(([a-z0-9_]|\\-)+\\.)+[a-z]{2,6}\$/i"; $chars = "/^([a-z0-9+_]|\\-|\\.)+@(([a-z0-9_]|\\-)+\\.)+[a-z]{2,6}\$/i";
if (strstr($user_email, '@') && strstr($user_email, '.')) { if (strstr($user_email, '@') && strstr($user_email, '.')) {
@ -676,7 +814,6 @@ function _autop_newline_preservation_helper( $matches ) {
} }
} }
function strip_all_but_one_link($text, $mylink) { function strip_all_but_one_link($text, $mylink) {
$match_link = '#(<a.+?href.+?' . '>)(.+?)(</a>)#'; $match_link = '#(<a.+?href.+?' . '>)(.+?)(</a>)#';
preg_match_all($match_link, $text, $matches); preg_match_all($match_link, $text, $matches);
@ -689,7 +826,6 @@ function _autop_newline_preservation_helper( $matches ) {
return $text; return $text;
} }
// used by wp-mail to handle charsets in email subjects // used by wp-mail to handle charsets in email subjects
function wp_iso_descrambler($string) { function wp_iso_descrambler($string) {
/* this may only work with iso-8859-1, I'm afraid */ /* this may only work with iso-8859-1, I'm afraid */
@ -702,7 +838,6 @@ function _autop_newline_preservation_helper( $matches ) {
} }
} }
// give it a date, it will give you the same date as GMT // give it a date, it will give you the same date as GMT
function get_gmt_from_date($string) { function get_gmt_from_date($string) {
// note: this only substracts $time_difference from the given date // note: this only substracts $time_difference from the given date