_mb_substr( string $str, int $start, int|null $length = null, string|null $encoding = null ): string

123function _mb_substr( $str, $start, $length = null, $encoding = null ) {124	if ( null === $str ) {125		return '';126	}127 128	if ( null === $encoding ) {129		$encoding = get_option( 'blog_charset' );130	}131 132	/*133	 * The solution below works only for UTF-8, so in case of a different134	 * charset just use built-in substr().135	 */136	if ( ! _is_utf8_charset( $encoding ) ) {137		return is_null( $length ) ? substr( $str, $start ) : substr( $str, $start, $length );138	}139 140	if ( _wp_can_use_pcre_u() ) {141		// Use the regex unicode support to separate the UTF-8 characters into an array.142		preg_match_all( '/./us', $str, $match );143		$chars = is_null( $length ) ? array_slice( $match[0], $start ) : array_slice( $match[0], $start, $length );144		return implode( '', $chars );145	}146 147	$regex = '/(148		[\x00-\x7F]                  # single-byte sequences   0xxxxxxx149		| [\xC2-\xDF][\x80-\xBF]       # double-byte sequences   110xxxxx 10xxxxxx150		| \xE0[\xA0-\xBF][\x80-\xBF]   # triple-byte sequences   1110xxxx 10xxxxxx * 2151		| [\xE1-\xEC][\x80-\xBF]{2}152		| \xED[\x80-\x9F][\x80-\xBF]153		| [\xEE-\xEF][\x80-\xBF]{2}154		| \xF0[\x90-\xBF][\x80-\xBF]{2} # four-byte sequences   11110xxx 10xxxxxx * 3155		| [\xF1-\xF3][\x80-\xBF]{3}156		| \xF4[\x80-\x8F][\x80-\xBF]{2}157	)/x';158 159	// Start with 1 element instead of 0 since the first thing we do is pop.160	$chars = array( '' );161 162	do {163		// We had some string left over from the last round, but we counted it in that last round.164		array_pop( $chars );165 166		/*167		 * Split by UTF-8 character, limit to 1000 characters (last array element will contain168		 * the rest of the string).169		 */170		$pieces = preg_split( $regex, $str, 1000, PREG_SPLIT_DELIM_CAPTURE | PREG_SPLIT_NO_EMPTY );171 172		$chars = array_merge( $chars, $pieces );173 174		// If there's anything left over, repeat the loop.175	} while ( count( $pieces ) > 1 && $str = array_pop( $pieces ) );176 177	return implode( '', array_slice( $chars, $start, $length ) );178}