X-Git-Url: https://scripts.mit.edu/gitweb/autoinstalls/wordpress.git/blobdiff_plain/fcaa67f093b5c83deea7a361a8cf8c6ac4e832d3..899389d1e4043331309c0433543419258b230b60:/wp-includes/compat.php?ds=sidebyside

diff --git a/wp-includes/compat.php b/wp-includes/compat.php
index 43667053..4317eb68 100644
--- a/wp-includes/compat.php
+++ b/wp-includes/compat.php
@@ -13,23 +13,85 @@ if ( !function_exists('_') ) {
 	}
 }
 
+/**
+ * Returns whether PCRE/u (PCRE_UTF8 modifier) is available for use.
+ *
+ * @ignore
+ * @since 4.2.2
+ * @access private
+ *
+ * @param bool $set - Used for testing only
+ *             null   : default - get PCRE/u capability
+ *             false  : Used for testing - return false for future calls to this function
+ *             'reset': Used for testing - restore default behavior of this function
+ */
+function _wp_can_use_pcre_u( $set = null ) {
+	static $utf8_pcre = 'reset';
+
+	if ( null !== $set ) {
+		$utf8_pcre = $set;
+	}
+
+	if ( 'reset' === $utf8_pcre ) {
+		$utf8_pcre = @preg_match( '/^./u', 'a' );
+	}
+
+	return $utf8_pcre;
+}
+
 if ( ! function_exists( 'mb_substr' ) ) :
 	function mb_substr( $str, $start, $length = null, $encoding = null ) {
 		return _mb_substr( $str, $start, $length, $encoding );
 	}
 endif;
 
+/*
+ * Only understands UTF-8 and 8bit.  All other character sets will be treated as 8bit.
+ * For $encoding === UTF-8, the $str input is expected to be a valid UTF-8 byte sequence.
+ * The behavior of this function for invalid inputs is undefined.
+ */
 function _mb_substr( $str, $start, $length = null, $encoding = null ) {
+	if ( null === $encoding ) {
+		$encoding = get_option( 'blog_charset' );
+	}
+
 	// The solution below works only for UTF-8,
 	// so in case of a different charset just use built-in substr()
-	$charset = get_option( 'blog_charset' );
-	if ( ! in_array( $charset, array( 'utf8', 'utf-8', 'UTF8', 'UTF-8' ) ) ) {
+	if ( ! in_array( $encoding, array( 'utf8', 'utf-8', 'UTF8', 'UTF-8' ) ) ) {
 		return is_null( $length ) ? substr( $str, $start ) : substr( $str, $start, $length );
 	}
-	// Use the regex unicode support to separate the UTF-8 characters into an array
-	preg_match_all( '/./us', $str, $match );
-	$chars = is_null( $length ) ? array_slice( $match[0], $start ) : array_slice( $match[0], $start, $length );
-	return implode( '', $chars );
+
+	if ( _wp_can_use_pcre_u() ) {
+		// Use the regex unicode support to separate the UTF-8 characters into an array
+		preg_match_all( '/./us', $str, $match );
+		$chars = is_null( $length ) ? array_slice( $match[0], $start ) : array_slice( $match[0], $start, $length );
+		return implode( '', $chars );
+	}
+
+	$regex = '/(
+		  [\x00-\x7F]                  # single-byte sequences   0xxxxxxx
+		| [\xC2-\xDF][\x80-\xBF]       # double-byte sequences   110xxxxx 10xxxxxx
+		| \xE0[\xA0-\xBF][\x80-\xBF]   # triple-byte sequences   1110xxxx 10xxxxxx * 2
+		| [\xE1-\xEC][\x80-\xBF]{2}
+		| \xED[\x80-\x9F][\x80-\xBF]
+		| [\xEE-\xEF][\x80-\xBF]{2}
+		| \xF0[\x90-\xBF][\x80-\xBF]{2} # four-byte sequences   11110xxx 10xxxxxx * 3
+		| [\xF1-\xF3][\x80-\xBF]{3}
+		| \xF4[\x80-\x8F][\x80-\xBF]{2}
+	)/x';
+
+	$chars = array( '' ); // Start with 1 element instead of 0 since the first thing we do is pop
+	do {
+		// We had some string left over from the last round, but we counted it in that last round.
+		array_pop( $chars );
+
+		// Split by UTF-8 character, limit to 1000 characters (last array element will contain the rest of the string)
+		$pieces = preg_split( $regex, $str, 1000, PREG_SPLIT_DELIM_CAPTURE | PREG_SPLIT_NO_EMPTY );
+
+		$chars = array_merge( $chars, $pieces );
+	} while ( count( $pieces ) > 1 && $str = array_pop( $pieces ) ); // If there's anything left over, repeat the loop.
+
+	return join( '', array_slice( $chars, $start, $length ) );
 }
 
 if ( ! function_exists( 'mb_strlen' ) ) :
@@ -38,16 +100,54 @@ if ( ! function_exists( 'mb_strlen' ) ) :
 	}
 endif;
 
+/*
+ * Only understands UTF-8 and 8bit.  All other character sets will be treated as 8bit.
+ * For $encoding === UTF-8, the $str input is expected to be a valid UTF-8 byte sequence.
+ * The behavior of this function for invalid inputs is undefined.
+ */
 function _mb_strlen( $str, $encoding = null ) {
+	if ( null === $encoding ) {
+		$encoding = get_option( 'blog_charset' );
+	}
+
 	// The solution below works only for UTF-8,
 	// so in case of a different charset just use built-in strlen()
-	$charset = get_option( 'blog_charset' );
-	if ( ! in_array( $charset, array( 'utf8', 'utf-8', 'UTF8', 'UTF-8' ) ) ) {
+	if ( ! in_array( $encoding, array( 'utf8', 'utf-8', 'UTF8', 'UTF-8' ) ) ) {
 		return strlen( $str );
 	}
-	// Use the regex unicode support to separate the UTF-8 characters into an array
-	preg_match_all( '/./us', $str, $match );
-	return count( $match[0] );
+
+	if ( _wp_can_use_pcre_u() ) {
+		// Use the regex unicode support to separate the UTF-8 characters into an array
+		preg_match_all( '/./us', $str, $match );
+		return count( $match[0] );
+	}
+
+	$regex = '/(?:
+		  [\x00-\x7F]                  # single-byte sequences   0xxxxxxx
+		| [\xC2-\xDF][\x80-\xBF]       # double-byte sequences   110xxxxx 10xxxxxx
+		| \xE0[\xA0-\xBF][\x80-\xBF]   # triple-byte sequences   1110xxxx 10xxxxxx * 2
+		| [\xE1-\xEC][\x80-\xBF]{2}
+		| \xED[\x80-\x9F][\x80-\xBF]
+		| [\xEE-\xEF][\x80-\xBF]{2}
+		| \xF0[\x90-\xBF][\x80-\xBF]{2} # four-byte sequences   11110xxx 10xxxxxx * 3
+		| [\xF1-\xF3][\x80-\xBF]{3}
+		| \xF4[\x80-\x8F][\x80-\xBF]{2}
+	)/x';
+
+	$count = 1; // Start at 1 instead of 0 since the first thing we do is decrement
+	do {
+		// We had some string left over from the last round, but we counted it in that last round.
+		$count--;
+
+		// Split by UTF-8 character, limit to 1000 characters (last array element will contain the rest of the string)
+		$pieces = preg_split( $regex, $str, 1000 );
+
+		// Increment
+		$count += count( $pieces );
+	} while ( $str = array_pop( $pieces ) ); // If there's anything left over, repeat the loop.
+
+	// Fencepost: preg_split() always returns one extra item in the array
+	return --$count;
 }
 
 if ( !function_exists('hash_hmac') ):