wpseek.com
A WordPress-centric search engine for devs and theme authors

function _wp_utf8_decode_fallback( $utf8_text ) {
	$utf8_text       = (string) $utf8_text;
	$at              = 0;
	$was_at          = 0;
	$end             = strlen( $utf8_text );
	$iso_8859_1_text = '';

	while ( $at < $end ) {
		// US-ASCII bytes are identical in ISO-8859-1 and UTF-8. These are 0x00–0x7F.
		$ascii_byte_count = strspn(
			$utf8_text,
			"\x00\x01\x02\x03\x04\x05\x06\x07\x08\x09\x0a\x0b\x0c\x0d\x0e\x0f" .
			"\x10\x11\x12\x13\x14\x15\x16\x17\x18\x19\x1a\x1b\x1c\x1d\x1e\x1f" .
			" !\"#$%&'()*+,-./0123456789:;<=>?@ABCDEFGHIJKLMNOPQRSTUVWXYZ[\\]^_`abcdefghijklmnopqrstuvwxyz{|}~\x7f",
			$at
		);

		if ( $ascii_byte_count > 0 ) {
			$at += $ascii_byte_count;
			continue;
		}

		$next_at        = $at;
		$invalid_length = 0;
		$found          = _wp_scan_utf8( $utf8_text, $next_at, $invalid_length, null, 1 );
		$span_length    = $next_at - $at;
		$next_byte      = '?';

		if ( 1 !== $found ) {
			if ( $invalid_length > 0 ) {
				$next_byte = '';
				goto flush_sub_part;
			}

			break;
		}

		// All convertible code points are two-bytes long.
		$byte1 = ord( $utf8_text[ $at ] );
		if ( 0xC0 !== ( $byte1 & 0xE0 ) ) {
			goto flush_sub_part;
		}

		// All convertible code points are not greater than U+FF.
		$byte2      = ord( $utf8_text[ $at + 1 ] );
		$code_point = ( ( $byte1 & 0x1F ) << 6 ) | ( ( $byte2 & 0x3F ) );
		if ( $code_point > 0xFF ) {
			goto flush_sub_part;
		}

		$next_byte = chr( $code_point );

		flush_sub_part:
		$iso_8859_1_text .= substr( $utf8_text, $was_at, $at - $was_at );
		$iso_8859_1_text .= $next_byte;
		$at              += $span_length;
		$was_at           = $at;

		if ( $invalid_length > 0 ) {
			$iso_8859_1_text .= '?';
			$at              += $invalid_length;
			$was_at           = $at;
		}
	}

	if ( 0 === $was_at ) {
		return $utf8_text;
	}

	$iso_8859_1_text .= substr( $utf8_text, $was_at );
	return $iso_8859_1_text;
}