/wp-includes/formatting.php

Large files files are truncated, but you can click here to view the full file

<?php
/**
 * Main WordPress Formatting API.
 *
 * Handles many functions for formatting output.
 *
 * @package WordPress
 */

/**
 * Replaces common plain text characters into formatted entities
 *
 * As an example,
 *
 *     'cause today's effort makes it worth tomorrow's "holiday" ...
 *
 * Becomes:
 *
 *     &#8217;cause today&#8217;s effort makes it worth tomorrow&#8217;s &#8220;holiday&#8221; &#8230;
 *
 * Code within certain html blocks are skipped.
 *
 * @since 0.71
 * @uses $wp_cockneyreplace Array of formatted entities for certain common phrases
 *
 * @param string $text The text to be formatted
 * @param bool $reset Set to true for unit testing. Translated patterns will reset.
 * @return string The string replaced with html entities
 */
function wptexturize($text, $reset = false) {
	global $wp_cockneyreplace, $shortcode_tags;
	static $static_characters, $static_replacements, $dynamic_characters, $dynamic_replacements,
		$default_no_texturize_tags, $default_no_texturize_shortcodes, $run_texturize = true;

	// If there's nothing to do, just stop.
	if ( empty( $text ) || false === $run_texturize ) {
		return $text;
	}

	// Set up static variables. Run once only.
	if ( $reset || ! isset( $static_characters ) ) {
		/**
		 * Filter whether to skip running wptexturize().
		 *
		 * Passing false to the filter will effectively short-circuit wptexturize().
		 * returning the original text passed to the function instead.
		 *
		 * The filter runs only once, the first time wptexturize() is called.
		 *
		 * @since 4.0.0
		 *
		 * @see wptexturize()
		 *
		 * @param bool $run_texturize Whether to short-circuit wptexturize().
		 */
		$run_texturize = apply_filters( 'run_wptexturize', $run_texturize );
		if ( false === $run_texturize ) {
			return $text;
		}

		/* translators: opening curly double quote */
		$opening_quote = _x( '&#8220;', 'opening curly double quote' );
		/* translators: closing curly double quote */
		$closing_quote = _x( '&#8221;', 'closing curly double quote' );

		/* translators: apostrophe, for example in 'cause or can't */
		$apos = _x( '&#8217;', 'apostrophe' );

		/* translators: prime, for example in 9' (nine feet) */
		$prime = _x( '&#8242;', 'prime' );
		/* translators: double prime, for example in 9" (nine inches) */
		$double_prime = _x( '&#8243;', 'double prime' );

		/* translators: opening curly single quote */
		$opening_single_quote = _x( '&#8216;', 'opening curly single quote' );
		/* translators: closing curly single quote */
		$closing_single_quote = _x( '&#8217;', 'closing curly single quote' );

		/* translators: en dash */
		$en_dash = _x( '&#8211;', 'en dash' );
		/* translators: em dash */
		$em_dash = _x( '&#8212;', 'em dash' );

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

		// if a plugin has provided an autocorrect array, use it
		if ( isset($wp_cockneyreplace) ) {
			$cockney = array_keys($wp_cockneyreplace);
			$cockneyreplace = array_values($wp_cockneyreplace);
		} elseif ( "'" != $apos ) { // Only bother if we're doing a replacement.
			$cockney = array( "'tain't", "'twere", "'twas", "'tis", "'twill", "'til", "'bout", "'nuff", "'round", "'cause" );
			$cockneyreplace = array( $apos . "tain" . $apos . "t", $apos . "twere", $apos . "twas", $apos . "tis", $apos . "twill", $apos . "til", $apos . "bout", $apos . "nuff", $apos . "round", $apos . "cause" );
		} else {
			$cockney = $cockneyreplace = array();
		}

		$static_characters = array_merge( array( '...', '``', '\'\'', ' (tm)' ), $cockney );
		$static_replacements = array_merge( array( '&#8230;', $opening_quote, $closing_quote, ' &#8482;' ), $cockneyreplace );


		// Pattern-based replacements of characters.
		// Sort the remaining patterns into several arrays for performance tuning.
		$dynamic_characters = array( 'apos' => array(), 'quote' => array(), 'dash' => array() );
		$dynamic_replacements = array( 'apos' => array(), 'quote' => array(), 'dash' => array() );
		$dynamic = array();
		$spaces = wp_spaces_regexp();

		// '99' and '99" are ambiguous among other patterns; assume it's an abbreviated year at the end of a quotation.
		if ( "'" !== $apos || "'" !== $closing_single_quote ) {
			$dynamic[ '/\'(\d\d)\'(?=\Z|[.,)}\-\]]|&gt;|' . $spaces . ')/' ] = $apos . '$1' . $closing_single_quote;
		}
		if ( "'" !== $apos || '"' !== $closing_quote ) {
			$dynamic[ '/\'(\d\d)"(?=\Z|[.,)}\-\]]|&gt;|' . $spaces . ')/' ] = $apos . '$1' . $closing_quote;
		}

		// '99 '99s '99's (apostrophe)  But never '9 or '99% or '999 or '99.0.
		if ( "'" !== $apos ) {
			$dynamic[ '/\'(?=\d\d(?:\Z|(?![%\d]|[.,]\d)))/' ] = $apos;
		}

		// Quoted Numbers like '0.42'
		if ( "'" !== $opening_single_quote && "'" !== $closing_single_quote ) {
			$dynamic[ '/(?<=\A|' . $spaces . ')\'(\d[.,\d]*)\'/' ] = $opening_single_quote . '$1' . $closing_single_quote;
		}

		// Single quote at start, or preceded by (, {, <, [, ", -, or spaces.
		if ( "'" !== $opening_single_quote ) {
			$dynamic[ '/(?<=\A|[([{"\-]|&lt;|' . $spaces . ')\'/' ] = $opening_single_quote;
		}

		// Apostrophe in a word.  No spaces, double apostrophes, or other punctuation.
		if ( "'" !== $apos ) {
			$dynamic[ '/(?<!' . $spaces . ')\'(?!\Z|[.,:;"\'(){}[\]\-]|&[lg]t;|' . $spaces . ')/' ] = $apos;
		}

		// 9' (prime)
		if ( "'" !== $prime ) {
			$dynamic[ '/(?<=\d)\'/' ] = $prime;
		}

		// Single quotes followed by spaces or ending punctuation.
		if ( "'" !== $closing_single_quote ) {
			$dynamic[ '/\'(?=\Z|[.,)}\-\]]|&gt;|' . $spaces . ')/' ] = $closing_single_quote;
		}

		$dynamic_characters['apos'] = array_keys( $dynamic );
		$dynamic_replacements['apos'] = array_values( $dynamic );
		$dynamic = array();

		// Quoted Numbers like "42"
		if ( '"' !== $opening_quote && '"' !== $closing_quote ) {
			$dynamic[ '/(?<=\A|' . $spaces . ')"(\d[.,\d]*)"/' ] = $opening_quote . '$1' . $closing_quote;
		}

		// 9" (double prime)
		if ( '"' !== $double_prime ) {
			$dynamic[ '/(?<=\d)"/' ] = $double_prime;
		}

		// Double quote at start, or preceded by (, {, <, [, -, or spaces, and not followed by spaces.
		if ( '"' !== $opening_quote ) {
			$dynamic[ '/(?<=\A|[([{\-]|&lt;|' . $spaces . ')"(?!' . $spaces . ')/' ] = $opening_quote;
		}

		// Any remaining double quotes.
		if ( '"' !== $closing_quote ) {
			$dynamic[ '/"/' ] = $closing_quote;
		}

		$dynamic_characters['quote'] = array_keys( $dynamic );
		$dynamic_replacements['quote'] = array_values( $dynamic );
		$dynamic = array();

		// Dashes and spaces
		$dynamic[ '/---/' ] = $em_dash;
		$dynamic[ '/(?<=' . $spaces . ')--(?=' . $spaces . ')/' ] = $em_dash;
		$dynamic[ '/(?<!xn)--/' ] = $en_dash;
		$dynamic[ '/(?<=' . $spaces . ')-(?=' . $spaces . ')/' ] = $en_dash;

		$dynamic_characters['dash'] = array_keys( $dynamic );
		$dynamic_replacements['dash'] = array_values( $dynamic );
	}

	// Must do this every time in case plugins use these filters in a context sensitive manner
	/**
	 * Filter the list of HTML elements not to texturize.
	 *
	 * @since 2.8.0
	 *
	 * @param array $default_no_texturize_tags An array of HTML element names.
	 */
	$no_texturize_tags = apply_filters( 'no_texturize_tags', $default_no_texturize_tags );
	/**
	 * Filter the list of shortcodes not to texturize.
	 *
	 * @since 2.8.0
	 *
	 * @param array $default_no_texturize_shortcodes An array of shortcode names.
	 */
	$no_texturize_shortcodes = apply_filters( 'no_texturize_shortcodes', $default_no_texturize_shortcodes );

	$no_texturize_tags_stack = array();
	$no_texturize_shortcodes_stack = array();

	// Look for shortcodes and HTML elements.

	$tagnames = array_keys( $shortcode_tags );
	$tagregexp = join( '|', array_map( 'preg_quote', $tagnames ) );
	$tagregexp = "(?:$tagregexp)(?![\\w-])"; // Excerpt of get_shortcode_regex().

	$comment_regex =
		  '!'           // Start of comment, after the <.
		. '(?:'         // Unroll the loop: Consume everything until --> is found.
		.     '-(?!->)' // Dash not followed by end of comment.
		.     '[^\-]*+' // Consume non-dashes.
		. ')*+'         // Loop possessively.
		. '(?:-->)?';   // End of comment. If not found, match all input.

	$shortcode_regex =
		  '\['              // Find start of shortcode.
		. '[\/\[]?'         // Shortcodes may begin with [/ or [[
		. $tagregexp        // Only match registered shortcodes, because performance.
		. '(?:'
		.     '[^\[\]<>]+'  // Shortcodes do not contain other shortcodes. Quantifier critical.
		. '|'
		.     '<[^\[\]>]*>' // HTML elements permitted. Prevents matching ] before >.
		. ')*+'             // Possessive critical.
		. '\]'              // Find end of shortcode.
		. '\]?';            // Shortcodes may end with ]]

	$regex =
		  '/('                   // Capture the entire match.
		.     '<'                // Find start of element.
		.     '(?(?=!--)'        // Is this a comment?
		.         $comment_regex // Find end of comment.
		.     '|'
		.         '[^>]+>'       // Find end of element.
		.     ')'
		. '|'
		.     $shortcode_regex   // Find shortcodes.
		. ')/s';

	$textarr = preg_split( $regex, $text, -1, PREG_SPLIT_DELIM_CAPTURE | PREG_SPLIT_NO_EMPTY );

	foreach ( $textarr as &$curl ) {
		// Only call _wptexturize_pushpop_element if $curl is a delimiter.
		$first = $curl[0];
		if ( '<' === $first && '<!--' === substr( $curl, 0, 4 ) ) {
			// This is an HTML comment delimeter.

			continue;

		} elseif ( '<' === $first && '>' === substr( $curl, -1 ) ) {
			// This is an HTML element delimiter.

			_wptexturize_pushpop_element( $curl, $no_texturize_tags_stack, $no_texturize_tags );

		} elseif ( '' === trim( $curl ) ) {
			// This is a newline between delimiters.  Performance improves when we check this.

			continue;

		} elseif ( '[' === $first && 1 === preg_match( '/^' . $shortcode_regex . '$/', $curl ) ) {
			// This is a shortcode delimiter.

			if ( '[[' !== substr( $curl, 0, 2 ) && ']]' !== substr( $curl, -2 ) ) {
				// Looks like a normal shortcode.
				_wptexturize_pushpop_element( $curl, $no_texturize_shortcodes_stack, $no_texturize_shortcodes );
			} else {
				// Looks like an escaped shortcode.
				continue;
			}

		} elseif ( empty( $no_texturize_shortcodes_stack ) && empty( $no_texturize_tags_stack ) ) {
			// This is neither a delimiter, nor is this content inside of no_texturize pairs.  Do texturize.

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

			if ( false !== strpos( $curl, "'" ) ) {
				$curl = preg_replace( $dynamic_characters['apos'], $dynamic_replacements['apos'], $curl );
			}
			if ( false !== strpos( $curl, '"' ) ) {
				$curl = preg_replace( $dynamic_characters['quote'], $dynamic_replacements['quote'], $curl );
			}
			if ( false !== strpos( $curl, '-' ) ) {
				$curl = preg_replace( $dynamic_characters['dash'], $dynamic_replacements['dash'], $curl );
			}

			// 9x9 (times), but never 0x9999
			if ( 1 === preg_match( '/(?<=\d)x\d/', $curl ) ) {
				// Searching for a digit is 10 times more expensive than for the x, so we avoid doing this one!
				$curl = preg_replace( '/\b(\d(?(?<=0)[\d\.,]+|[\d\.,]*))x(\d[\d\.,]*)\b/', '$1&#215;$2', $curl );
			}
		}
	}
	$text = implode( '', $textarr );

	// Replace each & with &#038; unless it already looks like an entity.
	$text = preg_replace('/&(?!#(?:\d+|x[a-f0-9]+);|[a-z1-4]{1,8};)/i', '&#038;', $text);

	return $text;
}

/**
 * Search for disabled element tags. Push element to stack on tag open and pop
 * on tag close.
 *
 * Assumes first char of $text is tag opening and last char is tag closing.
 * Assumes second char of $text is optionally '/' to indicate closing as in </html>.
 *
 * @since 2.9.0
 * @access private
 *
 * @param string $text Text to check. Must be a tag like `<html>` or `[shortcode]`.
 * @param array $stack List of open tag elements.
 * @param array $disabled_elements The tag names to match against. Spaces are not allowed in tag names.
 */
function _wptexturize_pushpop_element($text, &$stack, $disabled_elements) {
	// Is it an opening tag or closing tag?
	if ( '/' !== $text[1] ) {
		$opening_tag = true;
		$name_offset = 1;
	} elseif ( 0 == count( $stack ) ) {
		// Stack is empty. Just stop.
		return;
	} else {
		$opening_tag = false;
		$name_offset = 2;
	}

	// Parse out the tag name.
	$space = strpos( $text, ' ' );
	if ( false === $space ) {
		$space = -1;
	} else {
		$space -= $name_offset;
	}
	$tag = substr( $text, $name_offset, $space );

	// Handle disabled tags.
	if ( in_array( $tag, $disabled_elements ) ) {
		if ( $opening_tag ) {
			/*
			 * This disables texturize until we find a closing tag of our type
			 * (e.g. <pre>) even if there was invalid nesting before that
			 *
			 * Example: in the case <pre>sadsadasd</code>"baba"</pre>
			 *          "baba" won't be texturize
			 */

			array_push( $stack, $tag );
		} elseif ( end( $stack ) == $tag ) {
			array_pop( $stack );
		}
	}
}

/**
 * Replaces double line-breaks with paragraph elements.
 *
 * A group of regex replaces used to identify text formatted with newlines and
 * replace double line-breaks with HTML paragraph tags. The remaining
 * line-breaks after conversion become <<br />> tags, unless $br is set to '0'
 * or 'false'.
 *
 * @since 0.71
 *
 * @param string $pee The text which has to be formatted.
 * @param bool $br Optional. If set, this will convert all remaining line-breaks after paragraphing. Default true.
 * @return string Text which has been converted into correct paragraph tags.
 */
function wpautop($pee, $br = true) {
	$pre_tags = array();

	if ( trim($pee) === '' )
		return '';

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

	if ( strpos($pee, '<pre') !== false ) {
		$pee_parts = explode( '</pre>', $pee );
		$last_pee = array_pop($pee_parts);
		$pee = '';
		$i = 0;

		foreach ( $pee_parts as $pee_part ) {
			$start = strpos($pee_part, '<pre');

			// Malformed html?
			if ( $start === false ) {
				$pee .= $pee_part;
				continue;
			}

			$name = "<pre wp-pre-tag-$i></pre>";
			$pre_tags[$name] = substr( $pee_part, $start ) . '</pre>';

			$pee .= substr( $pee_part, 0, $start ) . $name;
			$i++;
		}

		$pee .= $last_pee;
	}

	$pee = preg_replace('|<br />\s*<br />|', "\n\n", $pee);
	// Space things out a little
	$allblocks = '(?:table|thead|tfoot|caption|col|colgroup|tbody|tr|td|th|div|dl|dd|dt|ul|ol|li|pre|form|map|area|blockquote|address|math|style|p|h[1-6]|hr|fieldset|legend|section|article|aside|hgroup|header|footer|nav|figure|details|menu|summary)';
	$pee = preg_replace('!(<' . $allblocks . '[^>]*>)!', "\n$1", $pee);
	$pee = preg_replace('!(</' . $allblocks . '>)!', "$1\n\n", $pee);
	$pee = str_replace(array("\r\n", "\r"), "\n", $pee); // cross-platform newlines

	if ( strpos( $pee, '<option' ) !== false ) {
		// no P/BR around option
		$pee = preg_replace( '|\s*<option|', '<option', $pee );
		$pee = preg_replace( '|</option>\s*|', '</option>', $pee );
	}

	if ( strpos( $pee, '</object>' ) !== false ) {
		// no P/BR around param and embed
		$pee = preg_replace( '|(<object[^>]*>)\s*|', '$1', $pee );
		$pee = preg_replace( '|\s*</object>|', '</object>', $pee );
		$pee = preg_replace( '%\s*(</?(?:param|embed)[^>]*>)\s*%', '$1', $pee );
	}

	if ( strpos( $pee, '<source' ) !== false || strpos( $pee, '<track' ) !== false ) {
		// no P/BR around source and track
		$pee = preg_replace( '%([<\[](?:audio|video)[^>\]]*[>\]])\s*%', '$1', $pee );
		$pee = preg_replace( '%\s*([<\[]/(?:audio|video)[>\]])%', '$1', $pee );
		$pee = preg_replace( '%\s*(<(?:source|track)[^>]*>)\s*%', '$1', $pee );
	}

	$pee = preg_replace("/\n\n+/", "\n\n", $pee); // take care of duplicates
	// make paragraphs, including one at the end
	$pees = preg_split('/\n\s*\n/', $pee, -1, PREG_SPLIT_NO_EMPTY);
	$pee = '';

	foreach ( $pees as $tinkle ) {
		$pee .= '<p>' . trim($tinkle, "\n") . "</p>\n";
	}

	$pee = preg_replace('|<p>\s*</p>|', '', $pee); // under certain strange conditions it could create a P of entirely whitespace
	$pee = preg_replace('!<p>([^<]+)</(div|address|form)>!', "<p>$1</p></$2>", $pee);
	$pee = preg_replace('!<p>\s*(</?' . $allblocks . '[^>]*>)\s*</p>!', "$1", $pee); // don't pee all over a tag
	$pee = preg_replace("|<p>(<li.+?)</p>|", "$1", $pee); // problem with nested lists
	$pee = preg_replace('|<p><blockquote([^>]*)>|i', "<blockquote$1><p>", $pee);
	$pee = str_replace('</blockquote></p>', '</p></blockquote>', $pee);
	$pee = preg_replace('!<p>\s*(</?' . $allblocks . '[^>]*>)!', "$1", $pee);
	$pee = preg_replace('!(</?' . $allblocks . '[^>]*>)\s*</p>!', "$1", $pee);

	if ( $br ) {
		$pee = preg_replace_callback('/<(script|style).*?<\/\\1>/s', '_autop_newline_preservation_helper', $pee);
		$pee = preg_replace('|(?<!<br />)\s*\n|', "<br />\n", $pee); // optionally make line breaks
		$pee = str_replace('<WPPreserveNewline />', "\n", $pee);
	}

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

	if ( !empty($pre_tags) )
		$pee = str_replace(array_keys($pre_tags), array_values($pre_tags), $pee);

	return $pee;
}

/**
 * Newline preservation help function for wpautop
 *
 * @since 3.1.0
 * @access private
 *
 * @param array $matches preg_replace_callback matches array
 * @return string
 */
function _autop_newline_preservation_helper( $matches ) {
	return str_replace("\n", "<WPPreserveNewline />", $matches[0]);
}

/**
 * Don't auto-p wrap shortcodes that stand alone
 *
 * Ensures that shortcodes are not wrapped in `<p>...</p>`.
 *
 * @since 2.9.0
 *
 * @param string $pee The content.
 * @return string The filtered content.
 */
function shortcode_unautop( $pee ) {
	global $shortcode_tags;

	if ( empty( $shortcode_tags ) || !is_array( $shortcode_tags ) ) {
		return $pee;
	}

	$tagregexp = join( '|', array_map( 'preg_quote', array_keys( $shortcode_tags ) ) );
	$spaces = wp_spaces_regexp();

	$pattern =
		  '/'
		. '<p>'                              // Opening paragraph
		. '(?:' . $spaces . ')*+'            // Optional leading whitespace
		. '('                                // 1: The shortcode
		.     '\\['                          // Opening bracket
		.     "($tagregexp)"                 // 2: Shortcode name
		.     '(?![\\w-])'                   // Not followed by word character or hyphen
		                                     // Unroll the loop: Inside the opening shortcode tag
		.     '[^\\]\\/]*'                   // Not a closing bracket or forward slash
		.     '(?:'
		.         '\\/(?!\\])'               // A forward slash not followed by a closing bracket
		.         '[^\\]\\/]*'               // Not a closing bracket or forward slash
		.     ')*?'
		.     '(?:'
		.         '\\/\\]'                   // Self closing tag and closing bracket
		.     '|'
		.         '\\]'                      // Closing bracket
		.         '(?:'                      // Unroll the loop: Optionally, anything between the opening and closing shortcode tags
		.             '[^\\[]*+'             // Not an opening bracket
		.             '(?:'
		.                 '\\[(?!\\/\\2\\])' // An opening bracket not followed by the closing shortcode tag
		.                 '[^\\[]*+'         // Not an opening bracket
		.             ')*+'
		.             '\\[\\/\\2\\]'         // Closing shortcode tag
		.         ')?'
		.     ')'
		. ')'
		. '(?:' . $spaces . ')*+'            // optional trailing whitespace
		. '<\\/p>'                           // closing paragraph
		. '/s';

	return preg_replace( $pattern, '$1', $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) {
	mbstring_binary_safe_encoding();
	$length = strlen($str);
	reset_mbstring_encoding();
	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
 * &quot;, or ENT_QUOTES to do both. Default is ENT_NOQUOTES where no quotes are encoded.
 *
 * @since 1.2.2
 * @access private
 *
 * @param string $string The text which is to be encoded.
 * @param int $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 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 = @htmlspecialchars( $string, $quote_style, $charset );
	} else {
		// Decode &amp; into &
		$string = wp_specialchars_decode( $string, $_quote_style );

		// Guarantee every &entity; is valid or re-encode the &
		$string = wp_kses_normalize_entities( $string );

		// Now re-encode everything except &entity;
		$string = preg_split( '/(&#?x?[0-9a-z]+;)/i', $string, -1, PREG_SPLIT_DELIM_CAPTURE );

		for ( $i = 0; $i < count( $string ); $i += 2 )
			$string[$i] = @htmlspecialchars( $string[$i], $quote_style, $charset );

		$string = implode( '', $string );
	}

	// Backwards compatibility
	if ( 'single' === $_quote_style )
		$string = str_replace( "'", '&#039;', $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 2.8.0
 *
 * @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( '&#039;'  => '\'', '&#x27;' => '\'' );
	$single_preg = array( '/&#0*39;/'  => '&#039;', '/&#x0*27;/i' => '&#x27;' );
	$double = array( '&quot;' => '"', '&#034;'  => '"', '&#x22;' => '"' );
	$double_preg = array( '/&#0*34;/'  => '&#034;', '/&#x0*22;/i' => '&#x22;' );
	$others = array( '&lt;'   => '<', '&#060;'  => '<', '&gt;'   => '>', '&#062;'  => '>', '&amp;'  => '&', '&#038;'  => '&', '&#x26;' => '&' );
	$others_preg = array( '/&#0*60;/'  => '&#060;', '/&#0*62;/'  => '&#062;', '/&#0*38;/'  => '&#038;', '/&#x0*26;/i' => '&#x26;' );

	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 2.8.0
 *
 * @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;

	mbstring_binary_safe_encoding();
	$string_length = strlen( $utf8_string );
	reset_mbstring_encoding();

	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(194).chr(170) => 'a', chr(194).chr(186) => 'o',
		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(134) => 'AE',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(144) => 'D', 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(158) => 'TH',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(166) => 'ae',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(176) => 'd', 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(184) => '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(190) => 'th',
		chr(195).chr(191) => 'y', chr(195).chr(152) => 'O',
		// 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',
		// Decompositions for Latin Extended-B
		chr(200).chr(152) => 'S', chr(200).chr(153) => 's',
		chr(200).chr(154) => 'T', chr(200).chr(155) => 't',
		// Euro Sign
		chr(226).chr(130).chr(172) => 'E',
		// GBP (Pound) Sign
		chr(194).chr(163) => '',
		// Vowels with diacritic (Vietnamese)
		// unmarked
		chr(198).chr(160) => 'O', chr(198).chr(161) => 'o',
		chr(198).chr(175) => 'U', chr(198).chr(176) => 'u',
		// grave accent
		chr(225).chr(186).chr(166) => 'A', chr(225).chr(186).chr(167) => 'a',
		chr(225).chr(186).chr(176) => 'A', chr(225).chr(186).chr(177) => 'a',
		chr(225).chr(187).chr(128) => 'E', chr(225).chr(187).chr(129) => 'e',
		chr(225).chr(187).chr(146) => 'O', chr(225).chr(187).chr(147) => 'o',
		chr(225).chr(187).chr(156) => 'O', chr(225).chr(187).chr(157) => 'o',
		chr(225).chr(187).chr(170) => 'U', chr(225).chr(187).chr(171) => 'u',
		chr(225).chr(187).chr(178) => 'Y', chr(225).chr(187).chr(179) => 'y',
		// hook
		chr(225).chr(186).chr(162) => 'A', chr(225).chr(186).chr(163) => 'a',
		chr(225).chr(186).chr(168) => 'A', chr(225).chr(186).chr(169) => 'a',
		chr(225).chr(186).chr(178) => 'A', chr(225).chr(186).chr(179) => 'a',
		chr(225).chr(186).chr(186) => 'E', chr(225).chr(186).chr(187) => 'e',
		chr(225).chr(187).chr(130) => 'E', chr(225).chr(187).chr(131) => 'e',
		chr(225).chr(187).chr(136) => 'I', chr(225).chr(187).chr(137) => 'i',
		chr(225).chr(187).chr(142) => 'O', chr(225).chr(187).chr(143) => 'o',
		chr(225).chr(187).chr(148) => 'O', chr(225).chr(187).chr(149) => 'o',
		chr(225).chr(187).chr(158) => 'O', chr(225).chr(187).chr(159) => 'o',
		chr(225).chr(187).chr(166) => 'U', chr(225).chr(187).chr(167) => 'u',
		chr(225).chr(187).chr(172) => 'U', chr(225).chr(187).chr(173) => 'u',
		chr(225).chr(187).chr(182) => 'Y', chr(225).chr(187).chr(183) => 'y',
		// tilde
		chr(225).chr(186).chr(170) => 'A', chr(225).chr(186).chr(171) => 'a',
		chr(225).chr(186).chr(180) => 'A', chr(225).chr(186).chr(181) => 'a',
		chr(225).chr(186).chr(188) => 'E', chr(225).chr(186).chr(189) => 'e',
		chr(225).chr(187).chr(132) => 'E', chr(225).chr(187).chr(133) => 'e',
		chr(225).chr(187).chr(150) => 'O', chr(225).chr(187).chr(151) => 'o',
		chr(225).chr(187).chr(160) => 'O', chr(225).chr(187).chr(161) => 'o',
		chr(225).chr(187).chr(174) => 'U', chr(225).chr(187).chr(175) => 'u',
		chr(225).chr(187).chr(184) => 'Y', chr(225).chr(187).chr(185) => 'y',
		// acute accent
		chr(225).chr(186).chr(164) => 'A', chr(225).chr(186).chr(165) => 'a',
		chr(225).chr(186).chr(174) => 'A', chr(225).chr(186).chr(175) => 'a',
		chr(225).chr(186).chr(190) => 'E', chr(225).chr(186).chr(191) => 'e',
		chr(225).chr(187).chr(144) => 'O', chr(225).chr(187).chr(145) => 'o',
		chr(225).chr(187).chr(154) => 'O', chr(225).chr(187).chr(155) => 'o',
		chr(225).chr(187).chr(168) => 'U', chr(225).chr(187).chr(169) => 'u',
		// dot below
		chr(225).chr(186).chr(160) => 'A', chr(225).chr(186).chr(161) => 'a',
		chr(225).chr(186).chr(172) => 'A', chr(225).chr(186).chr(173) => 'a',
		chr(225).chr(186).chr(182) => 'A', chr(225).chr(186).chr(183) => 'a',
		chr(225).chr(186).chr(184) => 'E', chr(225).chr(186).chr(185) => 'e',
		chr(225).chr(187).chr(134) => 'E', chr(225).chr(187).chr(135) => 'e',
		chr(225).chr(187).chr(138) => 'I', chr(225).chr(187).chr(139) => 'i',
		chr(225).chr(187).chr(140) => 'O', chr(225).chr(187).chr(141) => 'o',
		chr(225).chr(187).chr(152) => 'O', chr(225).chr(187).chr(153) => 'o',
		chr(225).chr(187).chr(162) => 'O', chr(225).chr(187).chr(163) => 'o',
		chr(225).chr(187).chr(164) => 'U', chr(225).chr(187).chr(165) => 'u',
		chr(225).chr(187).chr(176) => 'U', chr(225).chr(187).chr(177) => 'u',
		chr(225).chr(187).chr(180) => 'Y', chr(225).chr(187).chr(181) => 'y',
		// Vowels with diacritic (Chinese, Hanyu Pinyin)
		chr(201).chr(145) => 'a',
		// macron
		chr(199).chr(149) => 'U', chr(199).chr(150) => 'u',
		// acute accent
		chr(199).chr(151) => 'U', chr(199).chr(152) => 'u',
		// caron
		chr(199).chr(141) => 'A', chr(199).chr(142) => 'a',
		chr(199).chr(143) => 'I', chr(199).chr(144) => 'i',
		chr(199).chr(145) => 'O', chr(199).chr(146) => 'o',
		chr(199).chr(147) => 'U', chr(199).chr(148) => 'u',
		chr(199).chr(153) => 'U', chr(199).chr(154) => 'u',
		// grave accent
		chr(199).chr(155) => 'U', chr(199).chr(156) => 'u',
		);

		// Used for locale-specific rules
		$locale = get_locale();

		if ( 'de_DE' == $locale ) {
			$chars[ chr(195).chr(132) ] = 'Ae';
			$chars[ chr(195).chr(164) ] = 'ae';
			$chars[ chr(195).chr(150) ] = 'Oe';
			$chars[ chr(195).chr(182) ] = 'oe';
			$chars[ chr(195).chr(156) ] = 'Ue';
			$chars[ chr(195).chr(188) ] = 'ue';
			$chars[ chr(195).chr(159) ] = 'ss';
		} elseif ( 'da_DK' === $locale ) {
			$chars[ chr(195).chr(134) ] = 'Ae';
 			$chars[ chr(195).chr(166) ] = 'ae';
			$chars[ chr(195).chr(152) ] = 'Oe';
			$chars[ chr(195).chr(184) ] = 'oe';
			$chars[ chr(195).chr(133) ] = 'Aa';
			$chars[ chr(195).chr(165) ] = 'aa';
		}

		$string = strtr($string, $chars);
	} else {
		$chars = array();
		// 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 = array();
		$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. Trims 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;
	$special_chars = array("?", "[", "]", "/", "\\", "=", "<", ">", ":", ";", ",", "'", "\"", "&", "$", "#", "*", "(", ")", "|", "~", "`", "!", "{", "}", chr(0));
	/**
	 * Filter the list of characters to remove from a filename.
	 *
	 * @since 2.8.0
	 *
	 * @param array  $special_chars Characters to remove.
	 * @param string $filename_raw  Filename as it was passed into sanitize_file_name().
	 */
	$special_chars = apply_filters( 'sanitize_file_name_chars', $special_chars, $filename_raw );
	$filename = preg_replace( "#\x{00a0}#siu", ' ', $filename );
	$filename = str_replace( $special_chars, '', $filename );
	$filename = str_replace( array( '%20', '+' ), '-', $filename );
	$filename = preg_replace( '/[\r\n\t -]+/', '-', $filename );
	$filename = trim( $filename, '.-_' );

	// Split the filename into a base and extension[s]
	$parts = explode('.', $filename);

	// Return if only one extension
	if ( count( $parts ) <= 2 ) {
		/**
		 * Filter a sanitized filename string.
		 *
		 * @since 2.8.0
		 *
		 * @param string $filename     Sanitized filename.
		 * @param string $filename_raw The filename prior to sanitization.
		 */
		return apply_filters( 'sanitize_file_name', $filename, $filename_raw );
	}

	// Process multiple extensions
	$filename = array_shift($parts);
	$extension = array_pop($parts);
	$mimes = get_allowed_mime_types();

	/*
	 * Loop over any intermediate extensions. Postfix them with a trailing underscore
	 * if they are a 2 - 5 character long alpha string not in the extension whitelist.
	 */
	foreach ( (array) $parts as $part) {
		$filename .= '.' . $part;

		if ( preg_match("/^[a-zA-Z]{2,5}\d?$/", $part) ) {
			$allowed = false;
			foreach ( $mimes as $ext_preg => $mime_match ) {
				$ext_preg = '!^(' . $ext_preg . ')$!i';
				if ( preg_match( $ext_preg, $part ) ) {
					$allowed = true;
					break;
				}
			}
			if ( !$allowed )
				$filename .= '_';
		}
	}
	$filename .= '.' . $extension;
	/** This filter is documented in wp-includes/formatting.php */
	return apply_filters('sanitize_file_name', $filename, $filename_raw);
}

/**
 * Sanitizes a username, stripping out unsafe characters.
 *
 * Removes tags, octets, entities, and if strict is enabled, will only keep
 * alphanumeric, _, space, ., -, @. After sanitizing, it passes the username,
 * raw username (the username in the parameter), and the value of $strict as
 * parameters for the 'sanitize_user' filter.
 *
 * @since 2.0.0
 *
 * @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 = wp_strip_all_tags( $username );
	$username = remove_accents( $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 );

	$username = trim( $username );
	// Consolidate contiguous whitespace
	$username = preg_replace( '|\s+|', ' ', $username );

	/**
	 * Filter a sanitized username string.
	 *
	 * @since 2.0.1
	 *
	 * @param string $username     Sanitized username.
	 * @param string $raw_username The username prior to sanitization.
	 * @param bool   $strict       Whether to limit the sanitization to specific characters. Default false.
	 */
	return apply_filters( 'sanitize_user', $username, $raw_username, $strict );
}

/**
 * Sanitizes a string key.
 *
 * Keys are used as internal identifiers. Lowercase alphanumeric characters, dashes and underscores are allowed.
 *
 * @since 3.0.0
 *
 * @param string $key String key
 * @return string Sanitized key
 */
function sanitize_key( $key ) {
	$raw_key = $key;
	$key = strtolower( $key );
	$key = preg_replace( '/[^a-z0-9_\-]/', '', $key );

	/**
	 * Filter a sanitized key string.
	 *
	 * @since 3.0.0
	 *
	 * @param string $key     Sanitized key.
	 * @param string $raw_key The key prior to sanitization.
	 */
	return apply_filters( 'sanitize_key', $key, $raw_key );
}

/**
 * Sanitizes a title, or returns a 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.
 * @param string $context Optional. The operation for which the string is sanitized
 * @return string The sanitized string.
 */
function sanitize_title( $title, $fallback_title = '', $context = 'save' ) {
	$raw_title = $title;

	if ( 'save' == $context )
		$title = remove_accents($title);

	/**
	 * Filter a sanitized title string.
	 *
	 * @since 1.2.0
	 *
	 * @param string $title     Sanitized title.
	 * @param string $raw_title The title prior to sanitization.
	 * @param string $context   The context for which the title is being sanitized.
	 */
	$title = apply_filters( 'sanitize_title', $title, $raw_title, $context );

	if ( '' === $title || false === $title )
		$title = $fallback_title;

	return $title;
}

/**
 * Sanitizes a title with the 'query' context.
 *
 * Used for querying the database for a value from URL.
 *
 * @since 3.1.0
 *
 * @param string $title The string to be sanitized.
 * @return string The sanitized string.
 */
function sanitize_title_for_query( $title ) {
	return sanitize_title( $title, '', 'query' );
}

/**
 * Sanitizes a title, replacing whitespace and a few other characters 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.
 * @param string $raw_title Optional. Not used.
 * @param string $context Optional. The operation for which the string is sanitized.
 * @return string The sanitized title.
 */
function sanitize_title_with_dashes( $title, $raw_title = '', $context = 'display' ) {
	$title = strip_tags($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);

	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);

	if ( 'save' == $context ) {
		// Convert nbsp, ndash and mdash to hyphens
		$title = str_replace( array( '%c2%a0', '%e2%80%93', '%e2%80%94' ), '-', $title );

		// Strip these characters entirely
		$title = str_replace( array(
			// iexcl and iquest
			'%c2%a1', '%c2%bf',
			// angle quotes
			'%c2%ab', '%c2%bb', '%e2%80%b9', '%e2%80%ba',
			// curly quotes
			'%e2%80%98', '%e2%80%99', '%e2%80%9c', '%e2%80%9d',
			'%e2%80%9a', '%e2%80%9b', '%e2%80%9e', '%e2%80%9f',
			// copy, reg, deg, hellip and trade
			'%c2%a9', '%c2%ae', '%c2%b0', '%e2%80%a6', '%e2%84%a2',
			// acute accents
			'%c2%b4', '%cb%8a', '%cc%81', '%cd%81',
			// grave accent, macron, caron
			'%cc%80', '%cc%84', '%cc%8c',
		), '', $title );

		// Convert times to x
		$title = str_replace( '%c3%97', 'x', $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 false|string 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;
}

/**
 * Sanitizes an HTML classname to ensure it only contains valid characters.
 *
 * Strips the string down to A-Z,a-z,0-9,_,-. If this results in an empty
 * string then it will return the alternative value supplied.
 *
 * @todo Expand to support the full range of CDATA that a…