153154155156157158159160161162163164165166167168169170171 // decided to directly append valid UTF-8 characters onto a string
// $out once they're done. $char accumulates raw bytes, while $mUcs4
// turns into the Unicode code point, so there's some redundancy.
$out = '';
$char = '';
$len = strlen($str);
for ($i = 0; $i < $len; $i++) {
$in = ord($str{$i});
$char .= $str[$i]; // append byte to char
if (0 == $mState) {
// When mState is zero we expect either a US-ASCII character
// or a multi-octet sequence.
if (0 == (0x80 & ($in))) {
// US-ASCII, pass straight through.
if (($in <= 31 || $in == 127) &&
!($in == 9 || $in == 13 || $in == 10) // save \r\t\n
) {