' . trim($tinkle, "\n") . "
\n";
$pee = preg_replace('|\s*(?' . $allblocks . '[^>]*>)\s*
!', "$1", $pee); // don't pee all over a tag
$pee = preg_replace("||", "$1", $pee); // problem with nested lists
$pee = preg_replace('|]*)>|i', "", $pee);
$pee = str_replace('
', '
', $pee);
$pee = preg_replace('!\s*(?' . $allblocks . '[^>]*>)!', "$1", $pee);
$pee = preg_replace('!(?' . $allblocks . '[^>]*>)\s*
!', "$1", $pee);
if ($br) {
$pee = preg_replace_callback('/<(script|style).*?<\/\\1>/s', create_function('$matches', 'return str_replace("\n", "", $matches[0]);'), $pee);
$pee = preg_replace('|(?)\s*\n|', "
\n", $pee); // optionally make line breaks
$pee = str_replace('', "\n", $pee);
}
$pee = preg_replace('!(?' . $allblocks . '[^>]*>)\s*
!', "$1", $pee);
$pee = preg_replace('!
(\s*?(?:p|li|div|dl|dd|dt|th|pre|td|ul|ol)[^>]*>)!', '$1', $pee);
if (strpos($pee, ']*>)(.*?)
!is', 'clean_pre', $pee );
$pee = preg_replace( "|\n$|", '', $pee );
$pee = preg_replace('/\s*?(' . get_shortcode_regex() . ')\s*<\/p>/s', '$1', $pee); // don't auto-p wrap shortcodes that stand alone
return $pee;
}
/**
* Checks to see if a string is utf8 encoded.
*
* NOTE: This function checks for 5-Byte sequences, UTF8
* has Bytes Sequences with a maximum length of 4.
*
* @author bmorel at ssi dot fr (modified)
* @since 1.2.1
*
* @param string $str The string to be checked
* @return bool True if $str fits a UTF-8 model, false otherwise.
*/
function seems_utf8(&$str) {
$length = strlen($str);
for ($i=0; $i < $length; $i++) {
$c = ord($str[$i]);
if ($c < 0x80) $n = 0; # 0bbbbbbb
elseif (($c & 0xE0) == 0xC0) $n=1; # 110bbbbb
elseif (($c & 0xF0) == 0xE0) $n=2; # 1110bbbb
elseif (($c & 0xF8) == 0xF0) $n=3; # 11110bbb
elseif (($c & 0xFC) == 0xF8) $n=4; # 111110bb
elseif (($c & 0xFE) == 0xFC) $n=5; # 1111110b
else return false; # Does not match any model
for ($j=0; $j<$n; $j++) { # n bytes matching 10bbbbbb follow ?
if ((++$i == $length) || ((ord($str[$i]) & 0xC0) != 0x80))
return false;
}
}
return true;
}
/**
* Converts a number of special characters into their HTML entities.
*
* Specifically deals with: &, <, >, ", and '.
*
* $quote_style can be set to ENT_COMPAT to encode " to
* ", or ENT_QUOTES to do both. Default is ENT_NOQUOTES where no quotes are encoded.
*
* @since 1.2.2
*
* @param string $string The text which is to be encoded.
* @param mixed $quote_style Optional. Converts double quotes if set to ENT_COMPAT, both single and double if set to ENT_QUOTES or none if set to ENT_NOQUOTES. Also compatible with old values; converting single quotes if set to 'single', double if set to 'double' or both if otherwise set. Default is ENT_NOQUOTES.
* @param string $charset Optional. The character encoding of the string. Default is false.
* @param boolean $double_encode Optional. Whether or not to encode existing html entities. Default is false.
* @return string The encoded text with HTML entities.
*/
function _wp_specialchars( $string, $quote_style = ENT_NOQUOTES, $charset = false, $double_encode = false ) {
$string = (string) $string;
if ( 0 === strlen( $string ) ) {
return '';
}
// Don't bother if there are no specialchars - saves some processing
if ( !preg_match( '/[&<>"\']/', $string ) ) {
return $string;
}
// Account for the previous behaviour of the function when the $quote_style is not an accepted value
if ( empty( $quote_style ) ) {
$quote_style = ENT_NOQUOTES;
} elseif ( !in_array( $quote_style, array( 0, 2, 3, 'single', 'double' ), true ) ) {
$quote_style = ENT_QUOTES;
}
// Store the site charset as a static to avoid multiple calls to wp_load_alloptions()
if ( !$charset ) {
static $_charset;
if ( !isset( $_charset ) ) {
$alloptions = wp_load_alloptions();
$_charset = isset( $alloptions['blog_charset'] ) ? $alloptions['blog_charset'] : '';
}
$charset = $_charset;
}
if ( in_array( $charset, array( 'utf8', 'utf-8', 'UTF8' ) ) ) {
$charset = 'UTF-8';
}
$_quote_style = $quote_style;
if ( $quote_style === 'double' ) {
$quote_style = ENT_COMPAT;
$_quote_style = ENT_COMPAT;
} elseif ( $quote_style === 'single' ) {
$quote_style = ENT_NOQUOTES;
}
// Handle double encoding ourselves
if ( !$double_encode ) {
$string = wp_specialchars_decode( $string, $_quote_style );
$string = preg_replace( '/&(#?x?[0-9a-z]+);/i', '|wp_entity|$1|/wp_entity|', $string );
}
$string = @htmlspecialchars( $string, $quote_style, $charset );
// Handle double encoding ourselves
if ( !$double_encode ) {
$string = str_replace( array( '|wp_entity|', '|/wp_entity|' ), array( '&', ';' ), $string );
}
// Backwards compatibility
if ( 'single' === $_quote_style ) {
$string = str_replace( "'", ''', $string );
}
return $string;
}
/**
* Converts a number of HTML entities into their special characters.
*
* Specifically deals with: &, <, >, ", and '.
*
* $quote_style can be set to ENT_COMPAT to decode " entities,
* or ENT_QUOTES to do both " and '. Default is ENT_NOQUOTES where no quotes are decoded.
*
* @since 2.8
*
* @param string $string The text which is to be decoded.
* @param mixed $quote_style Optional. Converts double quotes if set to ENT_COMPAT, both single and double if set to ENT_QUOTES or none if set to ENT_NOQUOTES. Also compatible with old _wp_specialchars() values; converting single quotes if set to 'single', double if set to 'double' or both if otherwise set. Default is ENT_NOQUOTES.
* @return string The decoded text without HTML entities.
*/
function wp_specialchars_decode( $string, $quote_style = ENT_NOQUOTES ) {
$string = (string) $string;
if ( 0 === strlen( $string ) ) {
return '';
}
// Don't bother if there are no entities - saves a lot of processing
if ( strpos( $string, '&' ) === false ) {
return $string;
}
// Match the previous behaviour of _wp_specialchars() when the $quote_style is not an accepted value
if ( empty( $quote_style ) ) {
$quote_style = ENT_NOQUOTES;
} elseif ( !in_array( $quote_style, array( 0, 2, 3, 'single', 'double' ), true ) ) {
$quote_style = ENT_QUOTES;
}
// More complete than get_html_translation_table( HTML_SPECIALCHARS )
$single = array( ''' => '\'', ''' => '\'' );
$single_preg = array( '/*39;/' => ''', '/*27;/i' => ''' );
$double = array( '"' => '"', '"' => '"', '"' => '"' );
$double_preg = array( '/*34;/' => '"', '/*22;/i' => '"' );
$others = array( '<' => '<', '<' => '<', '>' => '>', '>' => '>', '&' => '&', '&' => '&', '&' => '&' );
$others_preg = array( '/*60;/' => '<', '/*62;/' => '>', '/*38;/' => '&', '/*26;/i' => '&' );
if ( $quote_style === ENT_QUOTES ) {
$translation = array_merge( $single, $double, $others );
$translation_preg = array_merge( $single_preg, $double_preg, $others_preg );
} elseif ( $quote_style === ENT_COMPAT || $quote_style === 'double' ) {
$translation = array_merge( $double, $others );
$translation_preg = array_merge( $double_preg, $others_preg );
} elseif ( $quote_style === 'single' ) {
$translation = array_merge( $single, $others );
$translation_preg = array_merge( $single_preg, $others_preg );
} elseif ( $quote_style === ENT_NOQUOTES ) {
$translation = $others;
$translation_preg = $others_preg;
}
// Remove zero padding on numeric entities
$string = preg_replace( array_keys( $translation_preg ), array_values( $translation_preg ), $string );
// Replace characters according to translation table
return strtr( $string, $translation );
}
/**
* Checks for invalid UTF8 in a string.
*
* @since 2.8
*
* @param string $string The text which is to be checked.
* @param boolean $strip Optional. Whether to attempt to strip out invalid UTF8. Default is false.
* @return string The checked text.
*/
function wp_check_invalid_utf8( $string, $strip = false ) {
$string = (string) $string;
if ( 0 === strlen( $string ) ) {
return '';
}
// Store the site charset as a static to avoid multiple calls to get_option()
static $is_utf8;
if ( !isset( $is_utf8 ) ) {
$is_utf8 = in_array( get_option( 'blog_charset' ), array( 'utf8', 'utf-8', 'UTF8', 'UTF-8' ) );
}
if ( !$is_utf8 ) {
return $string;
}
// Check for support for utf8 in the installed PCRE library once and store the result in a static
static $utf8_pcre;
if ( !isset( $utf8_pcre ) ) {
$utf8_pcre = @preg_match( '/^./u', 'a' );
}
// We can't demand utf8 in the PCRE installation, so just return the string in those cases
if ( !$utf8_pcre ) {
return $string;
}
// preg_match fails when it encounters invalid UTF8 in $string
if ( 1 === @preg_match( '/^./us', $string ) ) {
return $string;
}
// Attempt to strip the bad chars if requested (not recommended)
if ( $strip && function_exists( 'iconv' ) ) {
return iconv( 'utf-8', 'utf-8', $string );
}
return '';
}
/**
* Encode the Unicode values to be used in the URI.
*
* @since 1.5.0
*
* @param string $utf8_string
* @param int $length Max length of the string
* @return string String with Unicode encoded for URI.
*/
function utf8_uri_encode( $utf8_string, $length = 0 ) {
$unicode = '';
$values = array();
$num_octets = 1;
$unicode_length = 0;
$string_length = strlen( $utf8_string );
for ($i = 0; $i < $string_length; $i++ ) {
$value = ord( $utf8_string[ $i ] );
if ( $value < 128 ) {
if ( $length && ( $unicode_length >= $length ) )
break;
$unicode .= chr($value);
$unicode_length++;
} else {
if ( count( $values ) == 0 ) $num_octets = ( $value < 224 ) ? 2 : 3;
$values[] = $value;
if ( $length && ( $unicode_length + ($num_octets * 3) ) > $length )
break;
if ( count( $values ) == $num_octets ) {
if ($num_octets == 3) {
$unicode .= '%' . dechex($values[0]) . '%' . dechex($values[1]) . '%' . dechex($values[2]);
$unicode_length += 9;
} else {
$unicode .= '%' . dechex($values[0]) . '%' . dechex($values[1]);
$unicode_length += 6;
}
$values = array();
$num_octets = 1;
}
}
}
return $unicode;
}
/**
* Converts all accent characters to ASCII characters.
*
* If there are no accent characters, then the string given is just returned.
*
* @since 1.2.1
*
* @param string $string Text that might have accent characters
* @return string Filtered string with replaced "nice" characters.
*/
function remove_accents($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;
}
/**
* Sanitizes a filename replacing whitespace with dashes
*
* Removes special characters that are illegal in filenames on certain
* operating systems and special characters requiring special escaping
* to manipulate at the command line. Replaces spaces and consecutive
* dashes with a single dash. Trim period, dash and underscore from beginning
* and end of filename.
*
* @since 2.1.0
*
* @param string $filename The filename to be sanitized
* @return string The sanitized filename
*/
function sanitize_file_name( $filename ) {
$filename_raw = $filename;
$special_chars = array("?", "[", "]", "/", "\\", "=", "<", ">", ":", ";", ",", "'", "\"", "&", "$", "#", "*", "(", ")", "|", "~", "`", "!", "{", "}");
$special_chars = apply_filters('sanitize_file_name_chars', $special_chars, $filename_raw);
$filename = str_replace($special_chars, '', $filename);
$filename = preg_replace('/[\s-]+/', '-', $filename);
$filename = trim($filename, '.-_');
return apply_filters('sanitize_file_name', $filename, $filename_raw);
}
/**
* Sanitize username stripping out unsafe characters.
*
* If $strict is true, only alphanumeric characters (as well as _, space, ., -,
* @) are returned.
* Removes tags, octets, entities, and if strict is enabled, will remove all
* non-ASCII characters. After sanitizing, it passes the username, raw username
* (the username in the parameter), and the strict parameter as parameters for
* the filter.
*
* @since 2.0.0
* @uses apply_filters() Calls 'sanitize_user' hook on username, raw username,
* and $strict parameter.
*
* @param string $username The username to be sanitized.
* @param bool $strict If set limits $username to specific characters. Default false.
* @return string The sanitized username, after passing through filters.
*/
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);
// Consolidate contiguous whitespace
$username = preg_replace('|\s+|', ' ', $username);
return apply_filters('sanitize_user', $username, $raw_username, $strict);
}
/**
* Sanitizes title or use fallback title.
*
* Specifically, HTML and PHP tags are stripped. Further actions can be added
* via the plugin API. If $title is empty and $fallback_title is set, the latter
* will be used.
*
* @since 1.0.0
*
* @param string $title The string to be sanitized.
* @param string $fallback_title Optional. A title to use if $title is empty.
* @return string The sanitized string.
*/
function sanitize_title($title, $fallback_title = '') {
$raw_title = $title;
$title = strip_tags($title);
$title = apply_filters('sanitize_title', $title, $raw_title);
if ( '' === $title || false === $title )
$title = $fallback_title;
return $title;
}
/**
* Sanitizes title, replacing whitespace with dashes.
*
* Limits the output to alphanumeric characters, underscore (_) and dash (-).
* Whitespace becomes a dash.
*
* @since 1.2.0
*
* @param string $title The title to be sanitized.
* @return string The sanitized title.
*/
function sanitize_title_with_dashes($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 = str_replace('.', '-', $title);
$title = preg_replace('/[^%a-z0-9 _-]/', '', $title);
$title = preg_replace('/\s+/', '-', $title);
$title = preg_replace('|-+|', '-', $title);
$title = trim($title, '-');
return $title;
}
/**
* Ensures a string is a valid SQL order by clause.
*
* Accepts one or more columns, with or without ASC/DESC, and also accepts
* RAND().
*
* @since 2.5.1
*
* @param string $orderby Order by string to be checked.
* @return string|false Returns the order by clause if it is a match, false otherwise.
*/
function sanitize_sql_orderby( $orderby ){
preg_match('/^\s*([a-z0-9_]+(\s+(ASC|DESC))?(\s*,\s*|\s*$))+|^\s*RAND\(\s*\)\s*$/i', $orderby, $obmatches);
if ( !$obmatches )
return false;
return $orderby;
}
/**
* Converts a number of characters from a string.
*
* Metadata tags <
> and <> are removed, <
> and <
> are
* converted into correct XHTML and Unicode characters are converted to the
* valid range.
*
* @since 0.71
*
* @param string $content String of characters to be converted.
* @param string $deprecated Not used.
* @return string Converted string.
*/
function convert_chars($content, $deprecated = '') {
// Translation of invalid Unicode references range to valid range
$wp_htmltranswinuni = array(
'' => '€', // the Euro sign
'' => '',
'' => '‚', // these are Windows CP1252 specific characters
'' => 'ƒ', // they would look weird on non-Windows browsers
'' => '„',
'
' => '…',
'' => '†',
'' => '‡',
'' => 'ˆ',
'' => '‰',
'' => 'Š',
'' => '‹',
'' => 'Œ',
'' => '',
'' => 'ž',
'' => '',
'' => '',
'' => '‘',
'' => '’',
'' => '“',
'' => '”',
'' => '•',
'' => '–',
'' => '—',
'' => '˜',
'' => '™',
'' => 'š',
'' => '›',
'' => 'œ',
'' => '',
'' => '',
'' => 'Ÿ'
);
// Remove metadata tags
$content = preg_replace('/(.+?)<\/title>/','',$content);
$content = preg_replace('/(.+?)<\/category>/','',$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('
', '
', $content);
$content = str_replace('
', '
', $content);
return $content;
}
/**
* Callback used to change %uXXXX to YYY; syntax
*
* @since 2.8?
*
* @param array $matches Single Match
* @return string An HTML entity
*/
function funky_javascript_callback($matches) {
return "".base_convert($matches[1],16,10).";";
}
/**
* Fixes javascript bugs in browsers.
*
* Converts unicode characters to HTML numbered entities.
*
* @since 1.5.0
* @uses $is_macIE
* @uses $is_winIE
*
* @param string $text Text to be made safe.
* @return string Fixed text.
*/
function funky_javascript_fix($text) {
// Fixes for browsers' javascript bugs
global $is_macIE, $is_winIE;
if ( $is_winIE || $is_macIE )
$text = preg_replace_callback("/\%u([0-9A-F]{4,4})/",
"funky_javascript_callback",
$text);
return $text;
}
/**
* 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.
*
* @since 0.71
*
* @param string $text Text to be balanced
* @param bool $force Forces balancing, ignoring the value of the option. Default false.
* @return string Balanced text
*/
function balanceTags( $text, $force = false ) {
if ( !$force && get_option('use_balanceTags') == 0 )
return $text;
return force_balance_tags( $text );
}
/**
* Balances tags of string using a modified stack.
*
* @since 2.0.4
*
* @author Leonard Lin
* @license GPL v2.0
* @copyright November 4, 2001
* @version 1.1
* @todo Make better - change loop condition to $text in 1.2
* @internal Modified by Scott Reilly (coffee2code) 02 Aug 2004
* 1.1 Fixed handling of append/stack pop order of end text
* Added Cleaning Hooks
* 1.0 First Version
*
* @param string $text Text to be balanced.
* @return string Balanced text.
*/
function force_balance_tags( $text ) {
$tagstack = array(); $stacksize = 0; $tagqueue = ''; $newtext = '';
$single_tags = array('br', 'hr', 'img', 'input'); //Known single-entity/self-closing tags
$nestable_tags = array('blockquote', 'div', 'span'); //Tags that can be immediately nested within themselves
# 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
$tagqueue = '';
// Pop or Push
if ( isset($regex[1][0]) && '/' == $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 ( in_array($tag, $single_tags) ) {
$regex[2] .= '/';
} else { // Push the tag onto the stack
// If the top of the stack is the same as the tag we want to push, close previous tag
if (($stacksize > 0) && !in_array($tag, $nestable_tags) && ($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("< !--","