wp-includes/compat.php:212Internal compat function to mimic mb_strlen().
$strstring$encodingstring|nulloptionalnullintfunction _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(). */ if ( ! _is_utf8_charset( $encoding ) ) { return strlen( $str ); } 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'; // Start at 1 instead of 0 since the first thing we do is decrement. $count = 1; do { // We had some string left over from the last round, but we counted it in that last round. --$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 ); // If there's anything left over, repeat the loop. } while ( $str = array_pop( $pieces ) ); // Fencepost: preg_split() always returns one extra item in the array. return --$count;}Introduced in 4.2.0. Unchanged from 6.7.7 through 7.1.0.
Signature, return type and hooks compared across 5 parsed releases.
src/wp-includes/compat.php, and regenerated for each WordPress release so it tracks the code rather than a snapshot of it.