+/**
+ * Returns whether PCRE/u (PCRE_UTF8 modifier) is available for use.
+ *
+ * @ignore
+ * @since 4.2.2
+ * @access private
+ *
+ * @staticvar string $utf8_pcre
+ *
+ * @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' ) ) :
+ /**
+ * Compat function to mimic mb_substr().
+ *
+ * @ignore
+ * @since 3.2.0
+ *
+ * @see _mb_substr()
+ *
+ * @param string $str The string to extract the substring from.
+ * @param int $start Position to being extraction from in `$str`.
+ * @param int|null $length Optional. Maximum number of characters to extract from `$str`.
+ * Default null.
+ * @param string|null $encoding Optional. Character encoding to use. Default null.
+ * @return string Extracted substring.
+ */
+ function mb_substr( $str, $start, $length = null, $encoding = null ) {
+ return _mb_substr( $str, $start, $length, $encoding );
+ }
+endif;
+
+/**
+ * Internal compat function to mimic mb_substr().
+ *
+ * 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.
+ *
+ * @ignore
+ * @since 3.2.0
+ *
+ * @param string $str The string to extract the substring from.
+ * @param int $start Position to being extraction from in `$str`.
+ * @param int|null $length Optional. Maximum number of characters to extract from `$str`.
+ * Default null.
+ * @param string|null $encoding Optional. Character encoding to use. Default null.
+ * @return string Extracted substring.
+ */
+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().
+ */
+ if ( ! in_array( $encoding, array( 'utf8', 'utf-8', 'UTF8', 'UTF-8' ) ) ) {
+ return is_null( $length ) ? substr( $str, $start ) : substr( $str, $start, $length );
+ }
+
+ 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';
+
+ // Start with 1 element instead of 0 since the first thing we do is pop.
+ $chars = array( '' );
+ 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 );
+
+ // If there's anything left over, repeat the loop.
+ } while ( count( $pieces ) > 1 && $str = array_pop( $pieces ) );
+
+ return join( '', array_slice( $chars, $start, $length ) );
+}
+
+if ( ! function_exists( 'mb_strlen' ) ) :
+ /**
+ * Compat function to mimic mb_strlen().
+ *
+ * @ignore
+ * @since 4.2.0
+ *
+ * @see _mb_strlen()
+ *
+ * @param string $str The string to retrieve the character length from.
+ * @param string|null $encoding Optional. Character encoding to use. Default null.
+ * @return int String length of `$str`.
+ */
+ function mb_strlen( $str, $encoding = null ) {
+ return _mb_strlen( $str, $encoding );