X-Git-Url: https://scripts.mit.edu/gitweb/autoinstalls/wordpress.git/blobdiff_plain/256a3b381f63716209b3527d0a14442ae570c283..48ab98cb1779cf2088c1351ac3dd3d0da6fb31d3:/wp-includes/formatting.php

diff --git a/wp-includes/formatting.php b/wp-includes/formatting.php
index c56d8201..1f18ab9d 100644
--- a/wp-includes/formatting.php
+++ b/wp-includes/formatting.php
@@ -24,15 +24,40 @@
  * @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) {
+function wptexturize($text, $reset = false) {
 	global $wp_cockneyreplace;
 	static $static_characters, $static_replacements, $dynamic_characters, $dynamic_replacements,
-		$default_no_texturize_tags, $default_no_texturize_shortcodes;
+		$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;
+		}
 
-	// No need to set up these static variables more than once
-	if ( ! isset( $static_characters ) ) {
 		/* translators: opening curly double quote */
 		$opening_quote = _x( '“', 'opening curly double quote' );
 		/* translators: closing curly double quote */
@@ -70,36 +95,93 @@ function wptexturize($text) {
 			$cockney = $cockneyreplace = array();
 		}
 
-		$static_characters = array_merge( array( '---', ' -- ', '--', ' - ', 'xn–', '...', '``', '\'\'', ' (tm)' ), $cockney );
-		$static_replacements = array_merge( array( $em_dash, ' ' . $em_dash . ' ', $en_dash, ' ' . $en_dash . ' ', 'xn--', '…', $opening_quote, $closing_quote, ' ™' ), $cockneyreplace );
+		$static_characters = array_merge( array( '...', '``', '\'\'', ' (tm)' ), $cockney );
+		$static_replacements = array_merge( array( '…', $opening_quote, $closing_quote, ' ™' ), $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();
-		if ( "'" != $apos ) {
-			$dynamic[ '/\'(\d\d(?:’|\')?s)/' ] = $apos . '$1'; // '99's
-			$dynamic[ '/\'(\d)/'                   ] = $apos . '$1'; // '99
+		$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|[.,)}\-\]]|>|' . $spaces . ')/' ] = $apos . '$1' . $closing_single_quote;
+		}
+		if ( "'" !== $apos || '"' !== $closing_quote ) {
+			$dynamic[ '/\'(\d\d)"(?=\Z|[.,)}\-\]]|>|' . $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;
 		}
-		if ( "'" != $opening_single_quote )
-			$dynamic[ '/(\s|\A|[([{<]|")\'/'       ] = '$1' . $opening_single_quote; // opening single quote, even after (, {, <, [
-		if ( '"' != $double_prime )
-			$dynamic[ '/(\d)"/'                    ] = '$1' . $double_prime; // 9" (double prime)
-		if ( "'" != $prime )
-			$dynamic[ '/(\d)\'/'                   ] = '$1' . $prime; // 9' (prime)
-		if ( "'" != $apos )
-			$dynamic[ '/(\S)\'([^\'\s])/'          ] = '$1' . $apos . '$2'; // apostrophe in a word
-		if ( '"' != $opening_quote )
-			$dynamic[ '/(\s|\A|[([{<])"(?!\s)/'    ] = '$1' . $opening_quote . '$2'; // opening double quote, even after (, {, <, [
-		if ( '"' != $closing_quote )
-			$dynamic[ '/"(\s|\S|\Z)/'              ] = $closing_quote . '$1'; // closing double quote
-		if ( "'" != $closing_single_quote )
-			$dynamic[ '/\'([\s.]|\Z)/'             ] = $closing_single_quote . '$1'; // closing single quote
-
-		$dynamic[ '/\b(\d+)x(\d+)\b/'              ] = '$1&#215;$2'; // 9x9 (times)
-
-		$dynamic_characters = array_keys( $dynamic );
-		$dynamic_replacements = array_values( $dynamic );
-	}
-
-	// Transform into regexp sub-expression used in _wptexturize_pushpop_element
+
+		// 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( $dynamic );
+	}
+
 	// Must do this every time in case plugins use these filters in a context sensitive manner
 	/**
 	 * Filter the list of HTML elements not to texturize.
@@ -108,7 +190,7 @@ function wptexturize($text) {
 	 *
 	 * @param array $default_no_texturize_tags An array of HTML element names.
 	 */
-	$no_texturize_tags = '(' . implode( '|', apply_filters( 'no_texturize_tags', $default_no_texturize_tags ) ) . ')';
+	$no_texturize_tags = apply_filters( 'no_texturize_tags', $default_no_texturize_tags );
 	/**
 	 * Filter the list of shortcodes not to texturize.
 	 *
@@ -116,52 +198,131 @@ function wptexturize($text) {
 	 *
 	 * @param array $default_no_texturize_shortcodes An array of shortcode names.
 	 */
-	$no_texturize_shortcodes = '(' . implode( '|', apply_filters( 'no_texturize_shortcodes', $default_no_texturize_shortcodes ) ) . ')';
+	$no_texturize_shortcodes = apply_filters( 'no_texturize_shortcodes', $default_no_texturize_shortcodes );
 
 	$no_texturize_tags_stack = array();
 	$no_texturize_shortcodes_stack = array();
 
-	$textarr = preg_split('/(<.*>|\[.*\])/Us', $text, -1, PREG_SPLIT_DELIM_CAPTURE);
+	// Look for shortcodes and HTML elements.
+
+	$regex =  '/('			// Capture the entire match.
+		.	'<'		// Find start of element.
+		.	'(?(?=!--)'	// Is this a comment?
+		.		'.+?--\s*>'	// Find end of comment
+		.	'|'
+		.		'[^>]+>'	// Find end of element
+		.	')'
+		. '|'
+		.	'\['		// Find start of shortcode.
+		.	'\[?'		// Shortcodes may begin with [[
+		.	'(?:'
+		.		'[^\[\]<>]'	// Shortcodes do not contain other shortcodes.
+		.	'|'
+		.		'<[^>]+>' 	// HTML elements permitted. Prevents matching ] before >.
+		.	')++'
+		.	'\]'		// Find end of shortcode.
+		.	'\]?'		// Shortcodes may end with ]]
+		. ')/s';
+
+	$textarr = preg_split( $regex, $text, -1, PREG_SPLIT_DELIM_CAPTURE | PREG_SPLIT_NO_EMPTY );
 
 	foreach ( $textarr as &$curl ) {
-		if ( empty( $curl ) )
+		// Only call _wptexturize_pushpop_element if $curl is a delimiter.
+		$first = $curl[0];
+		if ( '<' === $first && '>' === substr( $curl, -1 ) ) {
+			// This is an HTML delimiter.
+
+			if ( '<!--' !== substr( $curl, 0, 4 ) ) {
+				_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;
 
-		// Only call _wptexturize_pushpop_element if first char is correct tag opening
-		$first = $curl[0];
-		if ( '<' === $first ) {
-			_wptexturize_pushpop_element($curl, $no_texturize_tags_stack, $no_texturize_tags, '<', '>');
-		} elseif ( '[' === $first ) {
-			_wptexturize_pushpop_element($curl, $no_texturize_shortcodes_stack, $no_texturize_shortcodes, '[', ']');
-		} elseif ( empty($no_texturize_shortcodes_stack) && empty($no_texturize_tags_stack) ) {
-			// This is not a tag, nor is the texturization disabled static strings
-			$curl = str_replace($static_characters, $static_replacements, $curl);
-			// regular expressions
-			$curl = preg_replace($dynamic_characters, $dynamic_replacements, $curl);
+		} elseif ( '[' === $first && 1 === preg_match( '/^\[(?:[^\[\]<>]|<[^>]+>)++\]$/', $curl ) ) {
+			// This is a shortcode delimiter.
+
+			_wptexturize_pushpop_element( $curl, $no_texturize_shortcodes_stack, $no_texturize_shortcodes );
+
+		} elseif ( '[' === $first && 1 === preg_match( '/^\[\[?(?:[^\[\]<>]|<[^>]+>)++\]\]?$/', $curl ) ) {
+			// This is an escaped shortcode delimiter.
+
+			// Do not texturize.
+			// Do not push to the shortcodes stack.
+
+			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 );
+			}
 		}
-		$curl = preg_replace('/&([^#])(?![a-zA-Z1-4]{1,8};)/', '&#038;$1', $curl);
 	}
-	return implode( '', $textarr );
+	$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 character of $text is tag opening.
+ * 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. First character is assumed to be $opening
- * @param array $stack Array used as stack of opened tag elements
- * @param string $disabled_elements Tags to match against formatted as regexp sub-expression
- * @param string $opening Tag opening character, assumed to be 1 character long
- * @param string $closing Tag closing character
- */
-function _wptexturize_pushpop_element($text, &$stack, $disabled_elements, $opening = '<', $closing = '>') {
-	// Check if it is a closing tag -- otherwise assume opening tag
-	if (strncmp($opening . '/', $text, 2)) {
-		// Opening? Check $text+1 against disabled elements
-		if (preg_match('/^' . $disabled_elements . '\b/', substr($text, 1), $matches)) {
+ * @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 ( $opening_tag ) {
 			/*
 			 * This disables texturize until we find a closing tag of our type
 			 * (e.g. <pre>) even if there was invalid nesting before that
@@ -170,17 +331,9 @@ function _wptexturize_pushpop_element($text, &$stack, $disabled_elements, $openi
 			 *          "baba" won't be texturize
 			 */
 
-			array_push($stack, $matches[1]);
-		}
-	} else {
-		// Closing? Check $text+2 against disabled elements
-		$c = preg_quote($closing, '/');
-		if (preg_match('/^' . $disabled_elements . $c . '/', substr($text, 2), $matches)) {
-			$last = array_pop($stack);
-
-			// Make sure it matches the opening tag
-			if ($last != $matches[1])
-				array_push($stack, $last);
+			array_push( $stack, $tag );
+		} elseif ( end( $stack ) == $tag ) {
+			array_pop( $stack );
 		}
 	}
 }
@@ -234,20 +387,40 @@ function wpautop($pee, $br = true) {
 
 	$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|select|option|form|map|area|blockquote|address|math|style|p|h[1-6]|hr|fieldset|noscript|legend|section|article|aside|hgroup|header|footer|nav|figure|figcaption|details|menu|summary)';
+	$allblocks = '(?:table|thead|tfoot|caption|col|colgroup|tbody|tr|td|th|div|dl|dd|dt|ul|ol|li|pre|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, '<object') !== false ) {
-		$pee = preg_replace('|\s*<param([^>]*)>\s*|', "<param$1>", $pee); // no pee inside object/embed
-		$pee = preg_replace('|\s*</embed>\s*|', '</embed>', $pee);
+
+	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 )
+
+	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", $pee); // don't pee all over a tag
@@ -256,11 +429,13 @@ function wpautop($pee, $br = true) {
 	$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 );
@@ -302,11 +477,12 @@ function shortcode_unautop( $pee ) {
 	}
 
 	$tagregexp = join( '|', array_map( 'preg_quote', array_keys( $shortcode_tags ) ) );
+	$spaces = wp_spaces_regexp();
 
 	$pattern =
 		  '/'
 		. '<p>'                              // Opening paragraph
-		. '\\s*+'                            // Optional leading whitespace
+		. '(?:' . $spaces . ')*+'            // Optional leading whitespace
 		. '('                                // 1: The shortcode
 		.     '\\['                          // Opening bracket
 		.     "($tagregexp)"                 // 2: Shortcode name
@@ -331,7 +507,7 @@ function shortcode_unautop( $pee ) {
 		.         ')?'
 		.     ')'
 		. ')'
-		. '\\s*+'                            // optional trailing whitespace
+		. '(?:' . $spaces . ')*+'            // optional trailing whitespace
 		. '<\\/p>'                           // closing paragraph
 		. '/s';
 
@@ -351,7 +527,9 @@ function shortcode_unautop( $pee ) {
  * @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
@@ -575,7 +753,10 @@ function utf8_uri_encode( $utf8_string, $length = 0 ) {
 	$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 ] );
@@ -872,7 +1053,9 @@ function sanitize_file_name( $filename ) {
 	 * @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('/[\s-]+/', '-', $filename);
 	$filename = trim($filename, '.-_');
 
@@ -1137,7 +1320,7 @@ function sanitize_sql_orderby( $orderby ){
  * @since 2.8.0
  *
  * @param string $class The classname to be sanitized
- * @param string $fallback Optional. The value to return if the sanitization end's up as an empty string.
+ * @param string $fallback Optional. The value to return if the sanitization ends up as an empty string.
  * 	Defaults to an empty string.
  * @return string The sanitized value
  */
@@ -1408,26 +1591,6 @@ function format_to_edit( $content, $richedit = false ) {
 	return $content;
 }
 
-/**
- * Holder for the 'format_to_post' filter.
- *
- * @since 0.71
- *
- * @param string $content The text to pass through the filter.
- * @return string Text returned from the 'format_to_post' filter.
- */
-function format_to_post($content) {
-	/**
-	 * Filter the string returned by format_to_post().
-	 *
-	 * @since 1.2.0
-	 *
-	 * @param string $content The string to format.
-	 */
-	$content = apply_filters( 'format_to_post', $content );
-	return $content;
-}
-
 /**
  * Add leading zeros when necessary.
  *
@@ -1466,35 +1629,34 @@ function backslashit($string) {
 /**
  * Appends a trailing slash.
  *
- * Will remove trailing slash if it exists already before adding a trailing
- * slash. This prevents double slashing a string or path.
+ * Will remove trailing forward and backslashes if it exists already before adding
+ * a trailing forward slash. This prevents double slashing a string or path.
  *
  * The primary use of this is for paths and thus should be used for paths. It is
  * not restricted to paths and offers no specific path support.
  *
  * @since 1.2.0
- * @uses untrailingslashit() Unslashes string if it was slashed already.
  *
  * @param string $string What to add the trailing slash to.
  * @return string String with trailing slash added.
  */
-function trailingslashit($string) {
-	return untrailingslashit($string) . '/';
+function trailingslashit( $string ) {
+	return untrailingslashit( $string ) . '/';
 }
 
 /**
- * Removes trailing slash if it exists.
+ * Removes trailing forward slashes and backslashes if they exist.
  *
  * The primary use of this is for paths and thus should be used for paths. It is
  * not restricted to paths and offers no specific path support.
  *
  * @since 2.2.0
  *
- * @param string $string What to remove the trailing slash from.
- * @return string String without the trailing slash.
+ * @param string $string What to remove the trailing slashes from.
+ * @return string String without the trailing slashes.
  */
-function untrailingslashit($string) {
-	return rtrim($string, '/');
+function untrailingslashit( $string ) {
+	return rtrim( $string, '/\\' );
 }
 
 /**
@@ -1742,7 +1904,7 @@ function make_clickable( $text ) {
 	}
 
 	// Cleanup of accidental links within links
-	$r = preg_replace( '#(<a( [^>]+?>|>))<a [^>]+?>([^>]+?)</a></a>#i', "$1$3</a>", $r );
+	$r = preg_replace( '#(<a([ \r\n\t]+[^>]+?>|>))<a [^>]+?>([^>]+?)</a></a>#i', "$1$3</a>", $r );
 	return $r;
 }
 
@@ -1870,7 +2032,7 @@ function translate_smiley( $matches ) {
 	 */
 	$src_url = apply_filters( 'smilies_src', includes_url( "images/smilies/$img" ), $img, site_url() );
 
-	return sprintf( ' <img src="%s" alt="%s" class="wp-smiley" /> ', esc_url( $src_url ), esc_attr( $smiley ) );
+	return sprintf( '<img src="%s" alt="%s" class="wp-smiley" />', esc_url( $src_url ), esc_attr( $smiley ) );
 }
 
 /**
@@ -2296,8 +2458,9 @@ function sanitize_email( $email ) {
  * @return string Human readable time difference.
  */
 function human_time_diff( $from, $to = '' ) {
-	if ( empty( $to ) )
+	if ( empty( $to ) ) {
 		$to = time();
+	}
 
 	$diff = (int) abs( $to - $from );
 
@@ -2334,7 +2497,17 @@ function human_time_diff( $from, $to = '' ) {
 		$since = sprintf( _n( '%s year', '%s years', $years ), $years );
 	}
 
-	return $since;
+	/**
+	 * Filter the human readable difference between two timestamps.
+	 *
+	 * @since 4.0.0
+	 *
+	 * @param string $since The difference in human readable text.
+	 * @param int    $diff  The difference in seconds.
+	 * @param int    $from  Unix timestamp from which the difference begins.
+	 * @param int    $to    Unix timestamp to end the time difference.
+	 */
+	return apply_filters( 'human_time_diff', $since, $diff, $from, $to );
 }
 
 /**
@@ -3049,18 +3222,6 @@ function tag_escape($tag_name) {
 	return apply_filters( 'tag_escape', $safe_tag, $tag_name );
 }
 
-/**
- * Escapes text for SQL LIKE special characters % and _.
- *
- * @since 2.5.0
- *
- * @param string $text The text to be escaped.
- * @return string text, safe for inclusion in LIKE query.
- */
-function like_escape($text) {
-	return str_replace(array("%", "_"), array("\\%", "\\_"), $text);
-}
-
 /**
  * Convert full URL paths to absolute paths.
  *
@@ -3200,8 +3361,12 @@ function sanitize_option($option, $value) {
 
 		case 'WPLANG':
 			$allowed = get_available_languages();
-			if ( ! in_array( $value, $allowed ) && ! empty( $value ) )
+			if ( ! is_multisite() && defined( 'WPLANG' ) && '' !== WPLANG && 'en_US' !== WPLANG ) {
+				$allowed[] = WPLANG;
+			}
+			if ( ! in_array( $value, $allowed ) && ! empty( $value ) ) {
 				$value = get_option( $option );
+			}
 			break;
 
 		case 'illegal_names':
@@ -3250,6 +3415,14 @@ function sanitize_option($option, $value) {
 			if ( ! get_role( $value ) && get_role( 'subscriber' ) )
 				$value = 'subscriber';
 			break;
+
+		case 'moderation_keys':
+		case 'blacklist_keys':
+			$value = explode( "\n", $value );
+			$value = array_filter( array_map( 'trim', $value ) );
+			$value = array_unique( $value );
+			$value = implode( "\n", $value );
+			break;
 	}
 
 	/**
@@ -3415,6 +3588,8 @@ function wp_sprintf_l($pattern, $args) {
 
 	/**
 	 * Filter the translated delimiters used by wp_sprintf_l().
+	 * Placeholders (%s) are included to assist translators and then
+	 * removed before the array of strings reaches the filter.
 	 *
 	 * Please note: Ampersands and entities should be avoided here.
 	 *
@@ -3423,12 +3598,12 @@ function wp_sprintf_l($pattern, $args) {
 	 * @param array $delimiters An array of translated delimiters.
 	 */
 	$l = apply_filters( 'wp_sprintf_l', array(
-		/* translators: used between list items, there is a space after the comma */
-		'between'          => __(', '),
-		/* translators: used between list items, there is a space after the and */
-		'between_last_two' => __(', and '),
-		/* translators: used between only two list items, there is a space after the and */
-		'between_only_two' => __(' and '),
+		/* translators: used to join items in a list with more than 2 items */
+		'between'          => sprintf( __('%s, %s'), '', '' ),
+		/* translators: used to join last two items in a list with more than 2 times */
+		'between_last_two' => sprintf( __('%s, and %s'), '', '' ),
+		/* translators: used to join items in a list with only 2 items */
+		'between_only_two' => sprintf( __('%s and %s'), '', '' ),
 	) );
 
 	$args = (array) $args;
@@ -3569,6 +3744,10 @@ function normalize_whitespace( $str ) {
 /**
  * Properly strip all HTML tags including script and style
  *
+ * This differs from strip_tags() because it removes the contents of
+ * the <script> and <style> tags. E.g. strip_tags( '<script>something</script>' )
+ * will return 'something'. wp_strip_all_tags will return ''
+ *
  * @since 2.9.0
  *
  * @param string $string String containing HTML tags
@@ -3770,11 +3949,46 @@ function wp_unslash( $value ) {
  * @return string The found URL.
  */
 function get_url_in_content( $content ) {
-	if ( empty( $content ) )
-		return '';
+	if ( empty( $content ) ) {
+		return false;
+	}
 
-	if ( preg_match( '/<a\s[^>]*?href=([\'"])(.+?)\1/is', $content, $matches ) )
+	if ( preg_match( '/<a\s[^>]*?href=([\'"])(.+?)\1/is', $content, $matches ) ) {
 		return esc_url_raw( $matches[2] );
+	}
 
 	return false;
 }
+
+/**
+ * Returns the regexp for common whitespace characters.
+ *
+ * By default, spaces include new lines, tabs, nbsp entities, and the UTF-8 nbsp.
+ * This is designed to replace the PCRE \s sequence.  In ticket #22692, that
+ * sequence was found to be unreliable due to random inclusion of the A0 byte.
+ *
+ * @since 4.0.0
+ *
+ * @return string The spaces regexp.
+ */
+function wp_spaces_regexp() {
+	static $spaces;
+
+	if ( empty( $spaces ) ) {
+		/**
+		 * Filter the regexp for common whitespace characters.
+		 *
+		 * This string is substituted for the \s sequence as needed in regular
+		 * expressions. For websites not written in English, different characters
+		 * may represent whitespace. For websites not encoded in UTF-8, the 0xC2 0xA0
+		 * sequence may not be in use.
+		 *
+		 * @since 4.0.0
+		 *
+		 * @param string $spaces Regexp pattern for matching common whitespace characters.
+		 */
+		$spaces = apply_filters( 'wp_spaces_regexp', '[\r\n\t ]|\xC2\xA0|&nbsp;' );
+	}
+
+	return $spaces;
+}