1 <?php

     2 /**

     3  * Main WordPress Formatting API.

     4  *

     5  * Handles many functions for formatting output.

     6  *

     7  * @package WordPress

     8  **/

     9 

    10 /**

    11  * Replaces common plain text characters into formatted entities

    12  *

    13  * As an example,

    14  * <code>

    15  * 'cause today's effort makes it worth tomorrow's "holiday"...

    16  * </code>

    17  * Becomes:

    18  * <code>

    19  * ’cause today’s effort makes it worth tomorrow’s “holiday”…

    20  * </code>

    21  * Code within certain html blocks are skipped.

    22  *

    23  * @since 0.71

    24  * @uses $wp_cockneyreplace Array of formatted entities for certain common phrases

    25  *

    26  * @param string $text The text to be formatted

    27  * @return string The string replaced with html entities

    28  */

    29 function wptexturize($text) {

    30 	global $wp_cockneyreplace;

    31 	static $static_setup = false, $opening_quote, $closing_quote, $default_no_texturize_tags, $default_no_texturize_shortcodes, $static_characters, $static_replacements, $dynamic_characters, $dynamic_replacements;

    32 	$output = '';

    33 	$curl = '';

    34 	$textarr = preg_split('/(<.*>|\[.*\])/Us', $text, -1, PREG_SPLIT_DELIM_CAPTURE);

    35 	$stop = count($textarr);

    36 	

    37 	// No need to setup these variables more than once

    38 	if (!$static_setup) {

    39 		/* translators: opening curly quote */

    40 		$opening_quote = _x('“', 'opening curly quote');

    41 		/* translators: closing curly quote */

    42 		$closing_quote = _x('”', 'closing curly quote');

    43 

    44 		$default_no_texturize_tags = array('pre', 'code', 'kbd', 'style', 'script', 'tt');

    45 		$default_no_texturize_shortcodes = array('code');

    46 

    47 		// if a plugin has provided an autocorrect array, use it

    48 		if ( isset($wp_cockneyreplace) ) {

    49 			$cockney = array_keys($wp_cockneyreplace);

    50 			$cockneyreplace = array_values($wp_cockneyreplace);

    51 		} else {

    52 			$cockney = array("'tain't","'twere","'twas","'tis","'twill","'til","'bout","'nuff","'round","'cause");

    53 			$cockneyreplace = array("’tain’t","’twere","’twas","’tis","’twill","’til","’bout","’nuff","’round","’cause");

    54 		}

    55 

    56 		$static_characters = array_merge(array('---', ' -- ', '--', ' - ', 'xn–', '...', '``', '\'s', '\'\'', ' (tm)'), $cockney);

    57 		$static_replacements = array_merge(array('—', ' — ', '–', ' – ', 'xn--', '…', $opening_quote, '’s', $closing_quote, ' ™'), $cockneyreplace);

    58 

    59 		$dynamic_characters = array('/\'(\d\d(?:&#8217;|\')?s)/', '/(\s|\A|[([{<]|")\'/', '/(\d+)"/', '/(\d+)\'/', '/(\S)\'([^\'\s])/', '/(\s|\A|[([{<])"(?!\s)/', '/"(\s|\S|\Z)/', '/\'([\s.]|\Z)/', '/(\d+)x(\d+)/');

    60 		$dynamic_replacements = array('’$1','$1‘', '$1″', '$1′', '$1’$2', '$1' . $opening_quote . '$2', $closing_quote . '$1', '’$1', '$1×$2');

    61 

    62 		$static_setup = true;

    63 	}

    64 

    65 	// Transform into regexp sub-expression used in _wptexturize_pushpop_element

    66 	// Must do this everytime in case plugins use these filters in a context sensitive manner

    67 	$no_texturize_tags = '(' . implode('|', apply_filters('no_texturize_tags', $default_no_texturize_tags) ) . ')';

    68 	$no_texturize_shortcodes = '(' . implode('|', apply_filters('no_texturize_shortcodes', $default_no_texturize_shortcodes) ) . ')';

    69 

    70 	$no_texturize_tags_stack = array();

    71 	$no_texturize_shortcodes_stack = array();

    72 

    73 	for ( $i = 0; $i < $stop; $i++ ) {

    74 		$curl = $textarr[$i];

    75 

    76 		if ( !empty($curl) && '<' != $curl{0} && '[' != $curl{0}

    77 				&& empty($no_texturize_shortcodes_stack) && empty($no_texturize_tags_stack)) { 

    78 			// This is not a tag, nor is the texturization disabled

    79 			// static strings

    80 			$curl = str_replace($static_characters, $static_replacements, $curl);

    81 			// regular expressions

    82 			$curl = preg_replace($dynamic_characters, $dynamic_replacements, $curl);

    83 		} elseif (!empty($curl)) {

    84 			/*

    85 			 * Only call _wptexturize_pushpop_element if first char is correct

    86 			 * tag opening

    87 			 */

    88 			if ('<' == $curl{0})

    89 				_wptexturize_pushpop_element($curl, $no_texturize_tags_stack, $no_texturize_tags, '<', '>');

    90 			elseif ('[' == $curl{0})

    91 				_wptexturize_pushpop_element($curl, $no_texturize_shortcodes_stack, $no_texturize_shortcodes, '[', ']');

    92 		}

    93 

    94 		$curl = preg_replace('/&([^#])(?![a-zA-Z1-4]{1,8};)/', '&$1', $curl);

    95 		$output .= $curl;

    96 	}

    97 

    98 	return $output;

    99 }

   100 

   101 /**

   102  * Search for disabled element tags. Push element to stack on tag open and pop

   103  * on tag close. Assumes first character of $text is tag opening.

   104  *

   105  * @access private

   106  * @since 2.9.0

   107  *

   108  * @param string $text Text to check. First character is assumed to be $opening

   109  * @param array $stack Array used as stack of opened tag elements

   110  * @param string $disabled_elements Tags to match against formatted as regexp sub-expression

   111  * @param string $opening Tag opening character, assumed to be 1 character long

   112  * @param string $opening Tag closing  character

   113  * @return object

   114  */

   115 function _wptexturize_pushpop_element($text, &$stack, $disabled_elements, $opening = '<', $closing = '>') {

   116 	// Check if it is a closing tag -- otherwise assume opening tag

   117 	if (strncmp($opening . '/', $text, 2)) {

   118 		// Opening? Check $text+1 against disabled elements

   119 		if (preg_match('/^' . $disabled_elements . '\b/', substr($text, 1), $matches)) {

   120 			/*

   121 			 * This disables texturize until we find a closing tag of our type

   122 			 * (e.g. <pre>) even if there was invalid nesting before that

   123 			 * 

   124 			 * Example: in the case <pre>sadsadasd</code>"baba"</pre>

   125 			 *          "baba" won't be texturize

   126 			 */

   127 

   128 			array_push($stack, $matches[1]);

   129 		}

   130 	} else {

   131 		// Closing? Check $text+2 against disabled elements

   132 		$c = preg_quote($closing, '/');

   133 		if (preg_match('/^' . $disabled_elements . $c . '/', substr($text, 2), $matches)) {

   134 			$last = array_pop($stack);

   135 

   136 			// Make sure it matches the opening tag

   137 			if ($last != $matches[1])

   138 				array_push($stack, $last);

   139 		}

   140 	}

   141 }

   142 

   143 /**

   144  * Accepts matches array from preg_replace_callback in wpautop() or a string.

   145  *

   146  * Ensures that the contents of a <<pre>>...<</pre>> HTML block are not

   147  * converted into paragraphs or line-breaks.

   148  *

   149  * @since 1.2.0

   150  *

   151  * @param array|string $matches The array or string

   152  * @return string The pre block without paragraph/line-break conversion.

   153  */

   154 function clean_pre($matches) {

   155 	if ( is_array($matches) )

   156 		$text = $matches[1] . $matches[2] . "</pre>";

   157 	else

   158 		$text = $matches;

   159 

   160 	$text = str_replace('<br />', '', $text);

   161 	$text = str_replace('<p>', "\n", $text);

   162 	$text = str_replace('</p>', '', $text);

   163 

   164 	return $text;

   165 }

   166 

   167 /**

   168  * Replaces double line-breaks with paragraph elements.

   169  *

   170  * A group of regex replaces used to identify text formatted with newlines and

   171  * replace double line-breaks with HTML paragraph tags. The remaining

   172  * line-breaks after conversion become <<br />> tags, unless $br is set to '0'

   173  * or 'false'.

   174  *

   175  * @since 0.71

   176  *

   177  * @param string $pee The text which has to be formatted.

   178  * @param int|bool $br Optional. If set, this will convert all remaining line-breaks after paragraphing. Default true.

   179  * @return string Text which has been converted into correct paragraph tags.

   180  */

   181 function wpautop($pee, $br = 1) {

   182 

   183 	if ( trim($pee) === '' )

   184 		return '';

   185 	$pee = $pee . "\n"; // just to make things a little easier, pad the end

   186 	$pee = preg_replace('|<br />\s*<br />|', "\n\n", $pee);

   187 	// Space things out a little

   188 	$allblocks = '(?:table|thead|tfoot|caption|col|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|fieldset|legend)';

   189 	$pee = preg_replace('!(<' . $allblocks . '[^>]*>)!', "\n$1", $pee);

   190 	$pee = preg_replace('!(</' . $allblocks . '>)!', "$1\n\n", $pee);

   191 	$pee = str_replace(array("\r\n", "\r"), "\n", $pee); // cross-platform newlines

   192 	if ( strpos($pee, '<object') !== false ) {

   193 		$pee = preg_replace('|\s*<param([^>]*)>\s*|', "<param$1>", $pee); // no pee inside object/embed

   194 		$pee = preg_replace('|\s*</embed>\s*|', '</embed>', $pee);

   195 	}

   196 	$pee = preg_replace("/\n\n+/", "\n\n", $pee); // take care of duplicates

   197 	// make paragraphs, including one at the end

   198 	$pees = preg_split('/\n\s*\n/', $pee, -1, PREG_SPLIT_NO_EMPTY);

   199 	$pee = '';

   200 	foreach ( $pees as $tinkle )

   201 		$pee .= '<p>' . trim($tinkle, "\n") . "</p>\n";

   202 	$pee = preg_replace('|<p>\s*</p>|', '', $pee); // under certain strange conditions it could create a P of entirely whitespace

   203 	$pee = preg_replace('!<p>([^<]+)</(div|address|form)>!', "<p>$1</p></$2>", $pee);

   204 	$pee = preg_replace('!<p>\s*(</?' . $allblocks . '[^>]*>)\s*</p>!', "$1", $pee); // don't pee all over a tag

   205 	$pee = preg_replace("|<p>(<li.+?)</p>|", "$1", $pee); // problem with nested lists

   206 	$pee = preg_replace('|<p><blockquote([^>]*)>|i', "<blockquote$1><p>", $pee);

   207 	$pee = str_replace('</blockquote></p>', '</p></blockquote>', $pee);

   208 	$pee = preg_replace('!<p>\s*(</?' . $allblocks . '[^>]*>)!', "$1", $pee);

   209 	$pee = preg_replace('!(</?' . $allblocks . '[^>]*>)\s*</p>!', "$1", $pee);

   210 	if ($br) {

   211 		$pee = preg_replace_callback('/<(script|style).*?<\/\\1>/s', create_function('$matches', 'return str_replace("\n", "<WPPreserveNewline />", $matches[0]);'), $pee);

   212 		$pee = preg_replace('|(?<!<br />)\s*\n|', "<br />\n", $pee); // optionally make line breaks

   213 		$pee = str_replace('<WPPreserveNewline />', "\n", $pee);

   214 	}

   215 	$pee = preg_replace('!(</?' . $allblocks . '[^>]*>)\s*<br />!', "$1", $pee);

   216 	$pee = preg_replace('!<br />(\s*</?(?:p|li|div|dl|dd|dt|th|pre|td|ul|ol)[^>]*>)!', '$1', $pee);

   217 	if (strpos($pee, '<pre') !== false)

   218 		$pee = preg_replace_callback('!(<pre[^>]*>)(.*?)</pre>!is', 'clean_pre', $pee );

   219 	$pee = preg_replace( "|\n</p>$|", '</p>', $pee );

   220 

   221 	return $pee;

   222 }

   223 

   224 /**

   225  * Don't auto-p wrap shortcodes that stand alone

   226  *

   227  * Ensures that shortcodes are not wrapped in <<p>>...<</p>>.

   228  *

   229  * @since 2.9.0

   230  *

   231  * @param string $pee The content.

   232  * @return string The filtered content.

   233  */

   234 function shortcode_unautop($pee) {

   235 	global $shortcode_tags;

   236 

   237 	if ( !empty($shortcode_tags) && is_array($shortcode_tags) ) {

   238 		$tagnames = array_keys($shortcode_tags);

   239 		$tagregexp = join( '|', array_map('preg_quote', $tagnames) );

   240 		$pee = preg_replace('/<p>\\s*?(\\[(' . $tagregexp . ')\\b.*?\\/?\\](?:.+?\\[\\/\\2\\])?)\\s*<\\/p>/s', '$1', $pee);

   241 	}

   242 

   243 	return $pee;

   244 }

   245 

   246 /**

   247  * Checks to see if a string is utf8 encoded.

   248  *

   249  * NOTE: This function checks for 5-Byte sequences, UTF8

   250  *       has Bytes Sequences with a maximum length of 4.

   251  *

   252  * @author bmorel at ssi dot fr (modified)

   253  * @since 1.2.1

   254  *

   255  * @param string $str The string to be checked

   256  * @return bool True if $str fits a UTF-8 model, false otherwise.

   257  */

   258 function seems_utf8($str) {

   259 	$length = strlen($str);

   260 	for ($i=0; $i < $length; $i++) {

   261 		$c = ord($str[$i]);

   262 		if ($c < 0x80) $n = 0; # 0bbbbbbb

   263 		elseif (($c & 0xE0) == 0xC0) $n=1; # 110bbbbb

   264 		elseif (($c & 0xF0) == 0xE0) $n=2; # 1110bbbb

   265 		elseif (($c & 0xF8) == 0xF0) $n=3; # 11110bbb

   266 		elseif (($c & 0xFC) == 0xF8) $n=4; # 111110bb

   267 		elseif (($c & 0xFE) == 0xFC) $n=5; # 1111110b

   268 		else return false; # Does not match any model

   269 		for ($j=0; $j<$n; $j++) { # n bytes matching 10bbbbbb follow ?

   270 			if ((++$i == $length) || ((ord($str[$i]) & 0xC0) != 0x80))

   271 				return false;

   272 		}

   273 	}

   274 	return true;

   275 }

   276 

   277 /**

   278  * Converts a number of special characters into their HTML entities.

   279  *

   280  * Specifically deals with: &, <, >, ", and '.

   281  *

   282  * $quote_style can be set to ENT_COMPAT to encode " to

   283  * ", or ENT_QUOTES to do both. Default is ENT_NOQUOTES where no quotes are encoded.

   284  *

   285  * @since 1.2.2

   286  *

   287  * @param string $string The text which is to be encoded.

   288  * @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.

   289  * @param string $charset Optional. The character encoding of the string. Default is false.

   290  * @param boolean $double_encode Optional. Whether or not to encode existing html entities. Default is false.

   291  * @return string The encoded text with HTML entities.

   292  */

   293 function _wp_specialchars( $string, $quote_style = ENT_NOQUOTES, $charset = false, $double_encode = false ) {

   294 	$string = (string) $string;

   295 

   296 	if ( 0 === strlen( $string ) ) {

   297 		return '';

   298 	}

   299 

   300 	// Don't bother if there are no specialchars - saves some processing

   301 	if ( !preg_match( '/[&<>"\']/', $string ) ) {

   302 		return $string;

   303 	}

   304 

   305 	// Account for the previous behaviour of the function when the $quote_style is not an accepted value

   306 	if ( empty( $quote_style ) ) {

   307 		$quote_style = ENT_NOQUOTES;

   308 	} elseif ( !in_array( $quote_style, array( 0, 2, 3, 'single', 'double' ), true ) ) {

   309 		$quote_style = ENT_QUOTES;

   310 	}

   311 

   312 	// Store the site charset as a static to avoid multiple calls to wp_load_alloptions()

   313 	if ( !$charset ) {

   314 		static $_charset;

   315 		if ( !isset( $_charset ) ) {

   316 			$alloptions = wp_load_alloptions();

   317 			$_charset = isset( $alloptions['blog_charset'] ) ? $alloptions['blog_charset'] : '';

   318 		}

   319 		$charset = $_charset;

   320 	}

   321 	if ( in_array( $charset, array( 'utf8', 'utf-8', 'UTF8' ) ) ) {

   322 		$charset = 'UTF-8';

   323 	}

   324 

   325 	$_quote_style = $quote_style;

   326 

   327 	if ( $quote_style === 'double' ) {

   328 		$quote_style = ENT_COMPAT;

   329 		$_quote_style = ENT_COMPAT;

   330 	} elseif ( $quote_style === 'single' ) {

   331 		$quote_style = ENT_NOQUOTES;

   332 	}

   333 

   334 	// Handle double encoding ourselves

   335 	if ( !$double_encode ) {

   336 		$string = wp_specialchars_decode( $string, $_quote_style );

   337 		$string = preg_replace( '/&(#?x?[0-9a-z]+);/i', '|wp_entity|$1|/wp_entity|', $string );

   338 	}

   339 

   340 	$string = @htmlspecialchars( $string, $quote_style, $charset );

   341 

   342 	// Handle double encoding ourselves

   343 	if ( !$double_encode ) {

   344 		$string = str_replace( array( '|wp_entity|', '|/wp_entity|' ), array( '&', ';' ), $string );

   345 	}

   346 

   347 	// Backwards compatibility

   348 	if ( 'single' === $_quote_style ) {

   349 		$string = str_replace( "'", ''', $string );

   350 	}

   351 

   352 	return $string;

   353 }

   354 

   355 /**

   356  * Converts a number of HTML entities into their special characters.

   357  *

   358  * Specifically deals with: &, <, >, ", and '.

   359  *

   360  * $quote_style can be set to ENT_COMPAT to decode " entities,

   361  * or ENT_QUOTES to do both " and '. Default is ENT_NOQUOTES where no quotes are decoded.

   362  *

   363  * @since 2.8

   364  *

   365  * @param string $string The text which is to be decoded.

   366  * @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.

   367  * @return string The decoded text without HTML entities.

   368  */

   369 function wp_specialchars_decode( $string, $quote_style = ENT_NOQUOTES ) {

   370 	$string = (string) $string;

   371 

   372 	if ( 0 === strlen( $string ) ) {

   373 		return '';

   374 	}

   375 

   376 	// Don't bother if there are no entities - saves a lot of processing

   377 	if ( strpos( $string, '&' ) === false ) {

   378 		return $string;

   379 	}

   380 

   381 	// Match the previous behaviour of _wp_specialchars() when the $quote_style is not an accepted value

   382 	if ( empty( $quote_style ) ) {

   383 		$quote_style = ENT_NOQUOTES;

   384 	} elseif ( !in_array( $quote_style, array( 0, 2, 3, 'single', 'double' ), true ) ) {

   385 		$quote_style = ENT_QUOTES;

   386 	}

   387 

   388 	// More complete than get_html_translation_table( HTML_SPECIALCHARS )

   389 	$single = array( '''  => '\'', ''' => '\'' );

   390 	$single_preg = array( '/&#0*39;/'  => ''', '/&#x0*27;/i' => ''' );

   391 	$double = array( '"' => '"', '"'  => '"', '"' => '"' );

   392 	$double_preg = array( '/&#0*34;/'  => '"', '/&#x0*22;/i' => '"' );

   393 	$others = array( '&lt;'   => '<', '&#060;'  => '<', '&gt;'   => '>', '&#062;'  => '>', '&amp;'  => '&', '&#038;'  => '&', '&#x26;' => '&' );

   394 	$others_preg = array( '/&#0*60;/'  => '<', '/&#0*62;/'  => '>', '/&#0*38;/'  => '&', '/&#x0*26;/i' => '&' );

   395 

   396 	if ( $quote_style === ENT_QUOTES ) {

   397 		$translation = array_merge( $single, $double, $others );

   398 		$translation_preg = array_merge( $single_preg, $double_preg, $others_preg );

   399 	} elseif ( $quote_style === ENT_COMPAT || $quote_style === 'double' ) {

   400 		$translation = array_merge( $double, $others );

   401 		$translation_preg = array_merge( $double_preg, $others_preg );

   402 	} elseif ( $quote_style === 'single' ) {

   403 		$translation = array_merge( $single, $others );

   404 		$translation_preg = array_merge( $single_preg, $others_preg );

   405 	} elseif ( $quote_style === ENT_NOQUOTES ) {

   406 		$translation = $others;

   407 		$translation_preg = $others_preg;

   408 	}

   409 

   410 	// Remove zero padding on numeric entities

   411 	$string = preg_replace( array_keys( $translation_preg ), array_values( $translation_preg ), $string );

   412 

   413 	// Replace characters according to translation table

   414 	return strtr( $string, $translation );

   415 }

   416 

   417 /**

   418  * Checks for invalid UTF8 in a string.

   419  *

   420  * @since 2.8

   421  *

   422  * @param string $string The text which is to be checked.

   423  * @param boolean $strip Optional. Whether to attempt to strip out invalid UTF8. Default is false.

   424  * @return string The checked text.

   425  */

   426 function wp_check_invalid_utf8( $string, $strip = false ) {

   427 	$string = (string) $string;

   428 

   429 	if ( 0 === strlen( $string ) ) {

   430 		return '';

   431 	}

   432 

   433 	// Store the site charset as a static to avoid multiple calls to get_option()

   434 	static $is_utf8;

   435 	if ( !isset( $is_utf8 ) ) {

   436 		$is_utf8 = in_array( get_option( 'blog_charset' ), array( 'utf8', 'utf-8', 'UTF8', 'UTF-8' ) );

   437 	}

   438 	if ( !$is_utf8 ) {

   439 		return $string;

   440 	}

   441 

   442 	// Check for support for utf8 in the installed PCRE library once and store the result in a static

   443 	static $utf8_pcre;

   444 	if ( !isset( $utf8_pcre ) ) {

   445 		$utf8_pcre = @preg_match( '/^./u', 'a' );

   446 	}

   447 	// We can't demand utf8 in the PCRE installation, so just return the string in those cases

   448 	if ( !$utf8_pcre ) {

   449 		return $string;

   450 	}

   451 

   452 	// preg_match fails when it encounters invalid UTF8 in $string

   453 	if ( 1 === @preg_match( '/^./us', $string ) ) {

   454 		return $string;

   455 	}

   456 

   457 	// Attempt to strip the bad chars if requested (not recommended)

   458 	if ( $strip && function_exists( 'iconv' ) ) {

   459 		return iconv( 'utf-8', 'utf-8', $string );

   460 	}

   461 

   462 	return '';

   463 }

   464 

   465 /**

   466  * Encode the Unicode values to be used in the URI.

   467  *

   468  * @since 1.5.0

   469  *

   470  * @param string $utf8_string

   471  * @param int $length Max length of the string

   472  * @return string String with Unicode encoded for URI.

   473  */

   474 function utf8_uri_encode( $utf8_string, $length = 0 ) {

   475 	$unicode = '';

   476 	$values = array();

   477 	$num_octets = 1;

   478 	$unicode_length = 0;

   479 

   480 	$string_length = strlen( $utf8_string );

   481 	for ($i = 0; $i < $string_length; $i++ ) {

   482 

   483 		$value = ord( $utf8_string[ $i ] );

   484 

   485 		if ( $value < 128 ) {

   486 			if ( $length && ( $unicode_length >= $length ) )

   487 				break;

   488 			$unicode .= chr($value);

   489 			$unicode_length++;

   490 		} else {

   491 			if ( count( $values ) == 0 ) $num_octets = ( $value < 224 ) ? 2 : 3;

   492 

   493 			$values[] = $value;

   494 

   495 			if ( $length && ( $unicode_length + ($num_octets * 3) ) > $length )

   496 				break;

   497 			if ( count( $values ) == $num_octets ) {

   498 				if ($num_octets == 3) {

   499 					$unicode .= '%' . dechex($values[0]) . '%' . dechex($values[1]) . '%' . dechex($values[2]);

   500 					$unicode_length += 9;

   501 				} else {

   502 					$unicode .= '%' . dechex($values[0]) . '%' . dechex($values[1]);

   503 					$unicode_length += 6;

   504 				}

   505 

   506 				$values = array();

   507 				$num_octets = 1;

   508 			}

   509 		}

   510 	}

   511 

   512 	return $unicode;

   513 }

   514 

   515 /**

   516  * Converts all accent characters to ASCII characters.

   517  *

   518  * If there are no accent characters, then the string given is just returned.

   519  *

   520  * @since 1.2.1

   521  *

   522  * @param string $string Text that might have accent characters

   523  * @return string Filtered string with replaced "nice" characters.

   524  */

   525 function remove_accents($string) {

   526 	if ( !preg_match('/[\x80-\xff]/', $string) )

   527 		return $string;

   528 

   529 	if (seems_utf8($string)) {

   530 		$chars = array(

   531 		// Decompositions for Latin-1 Supplement

   532 		chr(195).chr(128) => 'A', chr(195).chr(129) => 'A',

   533 		chr(195).chr(130) => 'A', chr(195).chr(131) => 'A',

   534 		chr(195).chr(132) => 'A', chr(195).chr(133) => 'A',

   535 		chr(195).chr(135) => 'C', chr(195).chr(136) => 'E',

   536 		chr(195).chr(137) => 'E', chr(195).chr(138) => 'E',

   537 		chr(195).chr(139) => 'E', chr(195).chr(140) => 'I',

   538 		chr(195).chr(141) => 'I', chr(195).chr(142) => 'I',

   539 		chr(195).chr(143) => 'I', chr(195).chr(145) => 'N',

   540 		chr(195).chr(146) => 'O', chr(195).chr(147) => 'O',

   541 		chr(195).chr(148) => 'O', chr(195).chr(149) => 'O',

   542 		chr(195).chr(150) => 'O', chr(195).chr(153) => 'U',

   543 		chr(195).chr(154) => 'U', chr(195).chr(155) => 'U',

   544 		chr(195).chr(156) => 'U', chr(195).chr(157) => 'Y',

   545 		chr(195).chr(159) => 's', chr(195).chr(160) => 'a',

   546 		chr(195).chr(161) => 'a', chr(195).chr(162) => 'a',

   547 		chr(195).chr(163) => 'a', chr(195).chr(164) => 'a',

   548 		chr(195).chr(165) => 'a', chr(195).chr(167) => 'c',

   549 		chr(195).chr(168) => 'e', chr(195).chr(169) => 'e',

   550 		chr(195).chr(170) => 'e', chr(195).chr(171) => 'e',

   551 		chr(195).chr(172) => 'i', chr(195).chr(173) => 'i',

   552 		chr(195).chr(174) => 'i', chr(195).chr(175) => 'i',

   553 		chr(195).chr(177) => 'n', chr(195).chr(178) => 'o',

   554 		chr(195).chr(179) => 'o', chr(195).chr(180) => 'o',

   555 		chr(195).chr(181) => 'o', chr(195).chr(182) => 'o',

   556 		chr(195).chr(182) => 'o', chr(195).chr(185) => 'u',

   557 		chr(195).chr(186) => 'u', chr(195).chr(187) => 'u',

   558 		chr(195).chr(188) => 'u', chr(195).chr(189) => 'y',

   559 		chr(195).chr(191) => 'y',

   560 		// Decompositions for Latin Extended-A

   561 		chr(196).chr(128) => 'A', chr(196).chr(129) => 'a',

   562 		chr(196).chr(130) => 'A', chr(196).chr(131) => 'a',

   563 		chr(196).chr(132) => 'A', chr(196).chr(133) => 'a',

   564 		chr(196).chr(134) => 'C', chr(196).chr(135) => 'c',

   565 		chr(196).chr(136) => 'C', chr(196).chr(137) => 'c',

   566 		chr(196).chr(138) => 'C', chr(196).chr(139) => 'c',

   567 		chr(196).chr(140) => 'C', chr(196).chr(141) => 'c',

   568 		chr(196).chr(142) => 'D', chr(196).chr(143) => 'd',

   569 		chr(196).chr(144) => 'D', chr(196).chr(145) => 'd',

   570 		chr(196).chr(146) => 'E', chr(196).chr(147) => 'e',

   571 		chr(196).chr(148) => 'E', chr(196).chr(149) => 'e',

   572 		chr(196).chr(150) => 'E', chr(196).chr(151) => 'e',

   573 		chr(196).chr(152) => 'E', chr(196).chr(153) => 'e',

   574 		chr(196).chr(154) => 'E', chr(196).chr(155) => 'e',

   575 		chr(196).chr(156) => 'G', chr(196).chr(157) => 'g',

   576 		chr(196).chr(158) => 'G', chr(196).chr(159) => 'g',

   577 		chr(196).chr(160) => 'G', chr(196).chr(161) => 'g',

   578 		chr(196).chr(162) => 'G', chr(196).chr(163) => 'g',

   579 		chr(196).chr(164) => 'H', chr(196).chr(165) => 'h',

   580 		chr(196).chr(166) => 'H', chr(196).chr(167) => 'h',

   581 		chr(196).chr(168) => 'I', chr(196).chr(169) => 'i',

   582 		chr(196).chr(170) => 'I', chr(196).chr(171) => 'i',

   583 		chr(196).chr(172) => 'I', chr(196).chr(173) => 'i',

   584 		chr(196).chr(174) => 'I', chr(196).chr(175) => 'i',

   585 		chr(196).chr(176) => 'I', chr(196).chr(177) => 'i',

   586 		chr(196).chr(178) => 'IJ',chr(196).chr(179) => 'ij',

   587 		chr(196).chr(180) => 'J', chr(196).chr(181) => 'j',

   588 		chr(196).chr(182) => 'K', chr(196).chr(183) => 'k',

   589 		chr(196).chr(184) => 'k', chr(196).chr(185) => 'L',

   590 		chr(196).chr(186) => 'l', chr(196).chr(187) => 'L',

   591 		chr(196).chr(188) => 'l', chr(196).chr(189) => 'L',

   592 		chr(196).chr(190) => 'l', chr(196).chr(191) => 'L',

   593 		chr(197).chr(128) => 'l', chr(197).chr(129) => 'L',

   594 		chr(197).chr(130) => 'l', chr(197).chr(131) => 'N',

   595 		chr(197).chr(132) => 'n', chr(197).chr(133) => 'N',

   596 		chr(197).chr(134) => 'n', chr(197).chr(135) => 'N',

   597 		chr(197).chr(136) => 'n', chr(197).chr(137) => 'N',

   598 		chr(197).chr(138) => 'n', chr(197).chr(139) => 'N',

   599 		chr(197).chr(140) => 'O', chr(197).chr(141) => 'o',

   600 		chr(197).chr(142) => 'O', chr(197).chr(143) => 'o',

   601 		chr(197).chr(144) => 'O', chr(197).chr(145) => 'o',

   602 		chr(197).chr(146) => 'OE',chr(197).chr(147) => 'oe',

   603 		chr(197).chr(148) => 'R',chr(197).chr(149) => 'r',

   604 		chr(197).chr(150) => 'R',chr(197).chr(151) => 'r',

   605 		chr(197).chr(152) => 'R',chr(197).chr(153) => 'r',

   606 		chr(197).chr(154) => 'S',chr(197).chr(155) => 's',

   607 		chr(197).chr(156) => 'S',chr(197).chr(157) => 's',

   608 		chr(197).chr(158) => 'S',chr(197).chr(159) => 's',

   609 		chr(197).chr(160) => 'S', chr(197).chr(161) => 's',

   610 		chr(197).chr(162) => 'T', chr(197).chr(163) => 't',

   611 		chr(197).chr(164) => 'T', chr(197).chr(165) => 't',

   612 		chr(197).chr(166) => 'T', chr(197).chr(167) => 't',

   613 		chr(197).chr(168) => 'U', chr(197).chr(169) => 'u',

   614 		chr(197).chr(170) => 'U', chr(197).chr(171) => 'u',

   615 		chr(197).chr(172) => 'U', chr(197).chr(173) => 'u',

   616 		chr(197).chr(174) => 'U', chr(197).chr(175) => 'u',

   617 		chr(197).chr(176) => 'U', chr(197).chr(177) => 'u',

   618 		chr(197).chr(178) => 'U', chr(197).chr(179) => 'u',

   619 		chr(197).chr(180) => 'W', chr(197).chr(181) => 'w',

   620 		chr(197).chr(182) => 'Y', chr(197).chr(183) => 'y',

   621 		chr(197).chr(184) => 'Y', chr(197).chr(185) => 'Z',

   622 		chr(197).chr(186) => 'z', chr(197).chr(187) => 'Z',

   623 		chr(197).chr(188) => 'z', chr(197).chr(189) => 'Z',

   624 		chr(197).chr(190) => 'z', chr(197).chr(191) => 's',

   625 		// Euro Sign

   626 		chr(226).chr(130).chr(172) => 'E',

   627 		// GBP (Pound) Sign

   628 		chr(194).chr(163) => '');

   629 

   630 		$string = strtr($string, $chars);

   631 	} else {

   632 		// Assume ISO-8859-1 if not UTF-8

   633 		$chars['in'] = chr(128).chr(131).chr(138).chr(142).chr(154).chr(158)

   634 			.chr(159).chr(162).chr(165).chr(181).chr(192).chr(193).chr(194)

   635 			.chr(195).chr(196).chr(197).chr(199).chr(200).chr(201).chr(202)

   636 			.chr(203).chr(204).chr(205).chr(206).chr(207).chr(209).chr(210)

   637 			.chr(211).chr(212).chr(213).chr(214).chr(216).chr(217).chr(218)

   638 			.chr(219).chr(220).chr(221).chr(224).chr(225).chr(226).chr(227)

   639 			.chr(228).chr(229).chr(231).chr(232).chr(233).chr(234).chr(235)

   640 			.chr(236).chr(237).chr(238).chr(239).chr(241).chr(242).chr(243)

   641 			.chr(244).chr(245).chr(246).chr(248).chr(249).chr(250).chr(251)

   642 			.chr(252).chr(253).chr(255);

   643 

   644 		$chars['out'] = "EfSZszYcYuAAAAAACEEEEIIIINOOOOOOUUUUYaaaaaaceeeeiiiinoooooouuuuyy";

   645 

   646 		$string = strtr($string, $chars['in'], $chars['out']);

   647 		$double_chars['in'] = array(chr(140), chr(156), chr(198), chr(208), chr(222), chr(223), chr(230), chr(240), chr(254));

   648 		$double_chars['out'] = array('OE', 'oe', 'AE', 'DH', 'TH', 'ss', 'ae', 'dh', 'th');

   649 		$string = str_replace($double_chars['in'], $double_chars['out'], $string);

   650 	}

   651 

   652 	return $string;

   653 }

   654 

   655 /**

   656  * Sanitizes a filename replacing whitespace with dashes

   657  *

   658  * Removes special characters that are illegal in filenames on certain

   659  * operating systems and special characters requiring special escaping

   660  * to manipulate at the command line. Replaces spaces and consecutive

   661  * dashes with a single dash. Trim period, dash and underscore from beginning

   662  * and end of filename.

   663  *

   664  * @since 2.1.0

   665  *

   666  * @param string $filename The filename to be sanitized

   667  * @return string The sanitized filename

   668  */

   669 function sanitize_file_name( $filename ) {

   670 	$filename_raw = $filename;

   671 	$special_chars = array("?", "[", "]", "/", "\\", "=", "<", ">", ":", ";", ",", "'", "\"", "&", "$", "#", "*", "(", ")", "|", "~", "`", "!", "{", "}", chr(0));

   672 	$special_chars = apply_filters('sanitize_file_name_chars', $special_chars, $filename_raw);

   673 	$filename = str_replace($special_chars, '', $filename);

   674 	$filename = preg_replace('/[\s-]+/', '-', $filename);

   675 	$filename = trim($filename, '.-_');

   676 

   677 	// Split the filename into a base and extension[s]

   678 	$parts = explode('.', $filename);

   679 

   680 	// Return if only one extension

   681 	if ( count($parts) <= 2 )

   682 		return apply_filters('sanitize_file_name', $filename, $filename_raw);

   683 

   684 	// Process multiple extensions

   685 	$filename = array_shift($parts);

   686 	$extension = array_pop($parts);

   687 	$mimes = get_allowed_mime_types();

   688 

   689 	// Loop over any intermediate extensions.  Munge them with a trailing underscore if they are a 2 - 5 character

   690 	// long alpha string not in the extension whitelist.

   691 	foreach ( (array) $parts as $part) {

   692 		$filename .= '.' . $part;

   693 		

   694 		if ( preg_match("/^[a-zA-Z]{2,5}\d?$/", $part) ) {

   695 			$allowed = false;

   696 			foreach ( $mimes as $ext_preg => $mime_match ) {

   697 				$ext_preg = '!(^' . $ext_preg . ')$!i';

   698 				if ( preg_match( $ext_preg, $part ) ) {

   699 					$allowed = true;

   700 					break;

   701 				}

   702 			}

   703 			if ( !$allowed )

   704 				$filename .= '_';

   705 		}

   706 	}

   707 	$filename .= '.' . $extension;

   708 

   709 	return apply_filters('sanitize_file_name', $filename, $filename_raw);

   710 }

   711 

   712 /**

   713  * Sanitize username stripping out unsafe characters.

   714  *

   715  * If $strict is true, only alphanumeric characters (as well as _, space, ., -,

   716  * @) are returned.

   717  * Removes tags, octets, entities, and if strict is enabled, will remove all

   718  * non-ASCII characters. After sanitizing, it passes the username, raw username

   719  * (the username in the parameter), and the strict parameter as parameters for

   720  * the filter.

   721  *

   722  * @since 2.0.0

   723  * @uses apply_filters() Calls 'sanitize_user' hook on username, raw username,

   724  *		and $strict parameter.

   725  *

   726  * @param string $username The username to be sanitized.

   727  * @param bool $strict If set limits $username to specific characters. Default false.

   728  * @return string The sanitized username, after passing through filters.

   729  */

   730 function sanitize_user( $username, $strict = false ) {

   731 	$raw_username = $username;

   732 	$username = wp_strip_all_tags($username);

   733 	// Kill octets

   734 	$username = preg_replace('|%([a-fA-F0-9][a-fA-F0-9])|', '', $username);

   735 	$username = preg_replace('/&.+?;/', '', $username); // Kill entities

   736 

   737 	// If strict, reduce to ASCII for max portability.

   738 	if ( $strict )

   739 		$username = preg_replace('|[^a-z0-9 _.\-@]|i', '', $username);

   740 

   741 	// Consolidate contiguous whitespace

   742 	$username = preg_replace('|\s+|', ' ', $username);

   743 

   744 	return apply_filters('sanitize_user', $username, $raw_username, $strict);

   745 }

   746 

   747 /**

   748  * Sanitizes title or use fallback title.

   749  *

   750  * Specifically, HTML and PHP tags are stripped. Further actions can be added

   751  * via the plugin API. If $title is empty and $fallback_title is set, the latter

   752  * will be used.

   753  *

   754  * @since 1.0.0

   755  *

   756  * @param string $title The string to be sanitized.

   757  * @param string $fallback_title Optional. A title to use if $title is empty.

   758  * @return string The sanitized string.

   759  */

   760 function sanitize_title($title, $fallback_title = '') {

   761 	$raw_title = $title;

   762 	$title = strip_tags($title);

   763 	$title = apply_filters('sanitize_title', $title, $raw_title);

   764 

   765 	if ( '' === $title || false === $title )

   766 		$title = $fallback_title;

   767 

   768 	return $title;

   769 }

   770 

   771 /**

   772  * Sanitizes title, replacing whitespace with dashes.

   773  *

   774  * Limits the output to alphanumeric characters, underscore (_) and dash (-).

   775  * Whitespace becomes a dash.

   776  *

   777  * @since 1.2.0

   778  *

   779  * @param string $title The title to be sanitized.

   780  * @return string The sanitized title.

   781  */

   782 function sanitize_title_with_dashes($title) {

   783 	$title = strip_tags($title);

   784 	// Preserve escaped octets.

   785 	$title = preg_replace('|%([a-fA-F0-9][a-fA-F0-9])|', '---$1---', $title);

   786 	// Remove percent signs that are not part of an octet.

   787 	$title = str_replace('%', '', $title);

   788 	// Restore octets.

   789 	$title = preg_replace('|---([a-fA-F0-9][a-fA-F0-9])---|', '%$1', $title);

   790 

   791 	$title = remove_accents($title);

   792 	if (seems_utf8($title)) {

   793 		if (function_exists('mb_strtolower')) {

   794 			$title = mb_strtolower($title, 'UTF-8');

   795 		}

   796 		$title = utf8_uri_encode($title, 200);

   797 	}

   798 

   799 	$title = strtolower($title);

   800 	$title = preg_replace('/&.+?;/', '', $title); // kill entities

   801 	$title = str_replace('.', '-', $title);

   802 	$title = preg_replace('/[^%a-z0-9 _-]/', '', $title);

   803 	$title = preg_replace('/\s+/', '-', $title);

   804 	$title = preg_replace('|-+|', '-', $title);

   805 	$title = trim($title, '-');

   806 

   807 	return $title;

   808 }

   809 

   810 /**

   811  * Ensures a string is a valid SQL order by clause.

   812  *

   813  * Accepts one or more columns, with or without ASC/DESC, and also accepts

   814  * RAND().

   815  *

   816  * @since 2.5.1

   817  *

   818  * @param string $orderby Order by string to be checked.

   819  * @return string|false Returns the order by clause if it is a match, false otherwise.

   820  */

   821 function sanitize_sql_orderby( $orderby ){

   822 	preg_match('/^\s*([a-z0-9_]+(\s+(ASC|DESC))?(\s*,\s*|\s*$))+|^\s*RAND\(\s*\)\s*$/i', $orderby, $obmatches);

   823 	if ( !$obmatches )

   824 		return false;

   825 	return $orderby;

   826 }

   827 

   828 /**

   829  * Santizes a html classname to ensure it only contains valid characters

   830  *

   831  * Strips the string down to A-Z,a-z,0-9,'-' if this results in an empty

   832  * string then it will return the alternative value supplied.

   833  *

   834  * @todo Expand to support the full range of CDATA that a class attribute can contain.

   835  *

   836  * @since 2.8.0

   837  *

   838  * @param string $class The classname to be sanitized

   839  * @param string $fallback The value to return if the sanitization end's up as an empty string.

   840  * @return string The sanitized value

   841  */

   842 function sanitize_html_class($class, $fallback){

   843 	//Strip out any % encoded octets

   844 	$sanitized = preg_replace('|%[a-fA-F0-9][a-fA-F0-9]|', '', $class);

   845 

   846 	//Limit to A-Z,a-z,0-9,'-'

   847 	$sanitized = preg_replace('/[^A-Za-z0-9-]/', '', $sanitized);

   848 

   849 	if ('' == $sanitized)

   850 		$sanitized = $fallback;

   851 

   852 	return apply_filters('sanitize_html_class',$sanitized, $class, $fallback);

   853 }

   854 

   855 /**

   856  * Converts a number of characters from a string.

   857  *

   858  * Metadata tags <<title>> and <<category>> are removed, <<br>> and <<hr>> are

   859  * converted into correct XHTML and Unicode characters are converted to the

   860  * valid range.

   861  *

   862  * @since 0.71

   863  *

   864  * @param string $content String of characters to be converted.

   865  * @param string $deprecated Not used.

   866  * @return string Converted string.

   867  */

   868 function convert_chars($content, $deprecated = '') {

   869 	// Translation of invalid Unicode references range to valid range

   870 	$wp_htmltranswinuni = array(

   871 	'€' => '€', // the Euro sign

   872 	'' => '',

   873 	'‚' => '‚', // these are Windows CP1252 specific characters

   874 	'ƒ' => 'ƒ',  // they would look weird on non-Windows browsers

   875 	'„' => '„',

   876 	'…' => '…',

   877 	'†' => '†',

   878 	'‡' => '‡',

   879 	'ˆ' => 'ˆ',

   880 	'‰' => '‰',

   881 	'Š' => 'Š',

   882 	'‹' => '‹',

   883 	'Œ' => 'Œ',

   884 	'' => '',

   885 	'Ž' => 'ž',

   886 	'' => '',

   887 	'' => '',

   888 	'‘' => '‘',

   889 	'’' => '’',

   890 	'“' => '“',

   891 	'”' => '”',

   892 	'•' => '•',

   893 	'–' => '–',

   894 	'—' => '—',

   895 	'˜' => '˜',

   896 	'™' => '™',

   897 	'š' => 'š',

   898 	'›' => '›',

   899 	'œ' => 'œ',

   900 	'' => '',

   901 	'ž' => '',

   902 	'Ÿ' => 'Ÿ'

   903 	);

   904 

   905 	// Remove metadata tags

   906 	$content = preg_replace('/<title>(.+?)<\/title>/','',$content);

   907 	$content = preg_replace('/<category>(.+?)<\/category>/','',$content);

   908 

   909 	// Converts lone & characters into & (a.k.a. &)

   910 	$content = preg_replace('/&([^#])(?![a-z1-4]{1,8};)/i', '&$1', $content);

   911 

   912 	// Fix Word pasting

   913 	$content = strtr($content, $wp_htmltranswinuni);

   914 

   915 	// Just a little XHTML help

   916 	$content = str_replace('<br>', '<br />', $content);

   917 	$content = str_replace('<hr>', '<hr />', $content);

   918 

   919 	return $content;

   920 }

   921 

   922 /**

   923  * Callback used to change %uXXXX to &#YYY; syntax

   924  *

   925  * @since 2.8?

   926  *

   927  * @param array $matches Single Match

   928  * @return string An HTML entity

   929  */

   930 function funky_javascript_callback($matches) {

   931 	return "&#".base_convert($matches[1],16,10).";";

   932 }

   933 

   934 /**

   935  * Fixes javascript bugs in browsers.

   936  *

   937  * Converts unicode characters to HTML numbered entities.

   938  *

   939  * @since 1.5.0

   940  * @uses $is_macIE

   941  * @uses $is_winIE

   942  *

   943  * @param string $text Text to be made safe.

   944  * @return string Fixed text.

   945  */

   946 function funky_javascript_fix($text) {

   947 	// Fixes for browsers' javascript bugs

   948 	global $is_macIE, $is_winIE;

   949 

   950 	if ( $is_winIE || $is_macIE )

   951 		$text =  preg_replace_callback("/\%u([0-9A-F]{4,4})/",

   952 					       "funky_javascript_callback",

   953 					       $text);

   954 

   955 	return $text;

   956 }

   957 

   958 /**

   959  * Will only balance the tags if forced to and the option is set to balance tags.

   960  *

   961  * The option 'use_balanceTags' is used for whether the tags will be balanced.

   962  * Both the $force parameter and 'use_balanceTags' option will have to be true

   963  * before the tags will be balanced.

   964  *

   965  * @since 0.71

   966  *

   967  * @param string $text Text to be balanced

   968  * @param bool $force Forces balancing, ignoring the value of the option. Default false.

   969  * @return string Balanced text

   970  */

   971 function balanceTags( $text, $force = false ) {

   972 	if ( !$force && get_option('use_balanceTags') == 0 )

   973 		return $text;

   974 	return force_balance_tags( $text );

   975 }

   976 

   977 /**

   978  * Balances tags of string using a modified stack.

   979  *

   980  * @since 2.0.4

   981  *

   982  * @author Leonard Lin <leonard@acm.org>

   983  * @license GPL v2.0

   984  * @copyright November 4, 2001

   985  * @version 1.1

   986  * @todo Make better - change loop condition to $text in 1.2

   987  * @internal Modified by Scott Reilly (coffee2code) 02 Aug 2004

   988  *		1.1  Fixed handling of append/stack pop order of end text

   989  *			 Added Cleaning Hooks

   990  *		1.0  First Version

   991  *

   992  * @param string $text Text to be balanced.

   993  * @return string Balanced text.

   994  */

   995 function force_balance_tags( $text ) {

   996 	$tagstack = array(); $stacksize = 0; $tagqueue = ''; $newtext = '';

   997 	$single_tags = array('br', 'hr', 'img', 'input'); //Known single-entity/self-closing tags

   998 	$nestable_tags = array('blockquote', 'div', 'span'); //Tags that can be immediately nested within themselves

   999 

  1000 	# WP bug fix for comments - in case you REALLY meant to type '< !--'

  1001 	$text = str_replace('< !--', '<    !--', $text);

  1002 	# WP bug fix for LOVE <3 (and other situations with '<' before a number)

  1003 	$text = preg_replace('#<([0-9]{1})#', '&lt;$1', $text);

  1004 

  1005 	while (preg_match("/<(\/?\w*)\s*([^>]*)>/",$text,$regex)) {

  1006 		$newtext .= $tagqueue;

  1007 

  1008 		$i = strpos($text,$regex[0]);

  1009 		$l = strlen($regex[0]);

  1010 

  1011 		// clear the shifter

  1012 		$tagqueue = '';

  1013 		// Pop or Push

  1014 		if ( isset($regex[1][0]) && '/' == $regex[1][0] ) { // End Tag

  1015 			$tag = strtolower(substr($regex[1],1));

  1016 			// if too many closing tags

  1017 			if($stacksize <= 0) {

  1018 				$tag = '';

  1019 				//or close to be safe $tag = '/' . $tag;

  1020 			}

  1021 			// if stacktop value = tag close value then pop

  1022 			else if ($tagstack[$stacksize - 1] == $tag) { // found closing tag

  1023 				$tag = '</' . $tag . '>'; // Close Tag

  1024 				// Pop

  1025 				array_pop ($tagstack);

  1026 				$stacksize--;

  1027 			} else { // closing tag not at top, search for it

  1028 				for ($j=$stacksize-1;$j>=0;$j--) {

  1029 					if ($tagstack[$j] == $tag) {

  1030 					// add tag to tagqueue

  1031 						for ($k=$stacksize-1;$k>=$j;$k--){

  1032 							$tagqueue .= '</' . array_pop ($tagstack) . '>';

  1033 							$stacksize--;

  1034 						}

  1035 						break;

  1036 					}

  1037 				}

  1038 				$tag = '';

  1039 			}

  1040 		} else { // Begin Tag

  1041 			$tag = strtolower($regex[1]);

  1042 

  1043 			// Tag Cleaning

  1044 

  1045 			// If self-closing or '', don't do anything.

  1046 			if((substr($regex[2],-1) == '/') || ($tag == '')) {

  1047 			}

  1048 			// ElseIf it's a known single-entity tag but it doesn't close itself, do so

  1049 			elseif ( in_array($tag, $single_tags) ) {

  1050 				$regex[2] .= '/';

  1051 			} else {	// Push the tag onto the stack

  1052 				// If the top of the stack is the same as the tag we want to push, close previous tag

  1053 				if (($stacksize > 0) && !in_array($tag, $nestable_tags) && ($tagstack[$stacksize - 1] == $tag)) {

  1054 					$tagqueue = '</' . array_pop ($tagstack) . '>';

  1055 					$stacksize--;

  1056 				}

  1057 				$stacksize = array_push ($tagstack, $tag);

  1058 			}

  1059 

  1060 			// Attributes

  1061 			$attributes = $regex[2];

  1062 			if($attributes) {

  1063 				$attributes = ' '.$attributes;

  1064 			}

  1065 			$tag = '<'.$tag.$attributes.'>';

  1066 			//If already queuing a close tag, then put this tag on, too

  1067 			if ($tagqueue) {

  1068 				$tagqueue .= $tag;

  1069 				$tag = '';

  1070 			}

  1071 		}

  1072 		$newtext .= substr($text,0,$i) . $tag;

  1073 		$text = substr($text,$i+$l);

  1074 	}

  1075 

  1076 	// Clear Tag Queue

  1077 	$newtext .= $tagqueue;

  1078 

  1079 	// Add Remaining text

  1080 	$newtext .= $text;

  1081 

  1082 	// Empty Stack

  1083 	while($x = array_pop($tagstack)) {

  1084 		$newtext .= '</' . $x . '>'; // Add remaining tags to close

  1085 	}

  1086 

  1087 	// WP fix for the bug with HTML comments

  1088 	$newtext = str_replace("< !--","<!--",$newtext);

  1089 	$newtext = str_replace("<    !--","< !--",$newtext);

  1090 

  1091 	return $newtext;

  1092 }

  1093 

  1094 /**

  1095  * Acts on text which is about to be edited.

  1096  *

  1097  * Unless $richedit is set, it is simply a holder for the 'format_to_edit'

  1098  * filter. If $richedit is set true htmlspecialchars() will be run on the

  1099  * content, converting special characters to HTMl entities.

  1100  *

  1101  * @since 0.71

  1102  *

  1103  * @param string $content The text about to be edited.

  1104  * @param bool $richedit Whether or not the $content should pass through htmlspecialchars(). Default false.

  1105  * @return string The text after the filter (and possibly htmlspecialchars()) has been run.

  1106  */

  1107 function format_to_edit($content, $richedit = false) {

  1108 	$content = apply_filters('format_to_edit', $content);

  1109 	if (! $richedit )

  1110 		$content = htmlspecialchars($content);

  1111 	return $content;

  1112 }

  1113 

  1114 /**

  1115  * Holder for the 'format_to_post' filter.

  1116  *

  1117  * @since 0.71

  1118  *

  1119  * @param string $content The text to pass through the filter.

  1120  * @return string Text returned from the 'format_to_post' filter.

  1121  */

  1122 function format_to_post($content) {

  1123 	$content = apply_filters('format_to_post', $content);

  1124 	return $content;

  1125 }

  1126 

  1127 /**

  1128  * Add leading zeros when necessary.

  1129  *

  1130  * If you set the threshold to '4' and the number is '10', then you will get

  1131  * back '0010'. If you set the number to '4' and the number is '5000', then you

  1132  * will get back '5000'.

  1133  *

  1134  * Uses sprintf to append the amount of zeros based on the $threshold parameter

  1135  * and the size of the number. If the number is large enough, then no zeros will