<?php
function utf8_scrub($str, $substitute = "\xE3\x80\x93")
{
$regex = '/
([\x00-\x7F] # U+0000 - U+007F
|[\xC2-\xDF][\x80-\xBF] # U+0080 - U+07FF
| \xE0[\xA0-\xBF][\x80-\xBF] # U+0800 - U+0FFF
|[\xE1-\xEC\xEE\xEF][\x80-\xBF]{2} # U+1000 - U+CFFF
| \xED[\x80-\x9F][\x80-\xBF] # U+D000 - U+D7FF
| \xF0[\x90-\xBF][\x80-\xBF]{2} # U+10000 - U+3FFFF
|[\xF1-\xF3][\x80-\xBF]{3} # U+40000 - U+FFFFF
| \xF4[\x80-\x8F][\x80-\xBF]{2}) # U+100000 - U+10FFFF
|(\xE0[\xA0-\xBF] # U+0800 - U+0FFF (invalid)
|[\xE1-\xEC\xEE\xEF][\x80-\xBF] # U+1000 - U+CFFF (invalid)
| \xED[\x80-\x9F] # U+D000 - U+D7FF (invalid)
| \xF0[\x90-\xBF][\x80-\xBF]? # U+10000 - U+3FFFF (invalid)
|[\xF1-\xF3][\x80-\xBF]{1,2} # U+40000 - U+FFFFF (invalid)
| \xF4[\x80-\x8F][\x80-\xBF]?) # U+100000 - U+10FFFF (invalid)
|(.) # invalid 1-byte
/xs';
// $matches[1]: valid character
// $matches[2]: invalid 3-byte or 4-byte character
// $matches[3]: invalid 1-byte
$ret = preg_replace_callback(
$regex,
function ($matches) use ($substitute) {
if (isset($matches[2]) || isset($matches[3])) {
return $substitute;
}
return $matches[1];
},
$str
);
return $ret;
}
$examples = array(
'Valid ASCII' => "a",
'Valid 2 Octet Sequence' => "\xc3\xb1",
'Invalid 2 Octet Sequence' => "\xc3\x28",
'Invalid Sequence Identifier' => "\xa0\xa1",
'Valid 3 Octet Sequence' => "\xe2\x82\xa1",
'Invalid 3 Octet Sequence (in 2nd Octet)' => "\xe2\x28\xa1",
'Invalid 3 Octet Sequence (in 3rd Octet)' => "\xe2\x82\x28",
'Valid 4 Octet Sequence' => "\xf0\x90\x8c\xbc",
'Invalid 4 Octet Sequence (in 2nd Octet)' => "\xf0\x28\x8c\xbc",
'Invalid 4 Octet Sequence (in 3rd Octet)' => "\xf0\x90\x28\xbc",
'Invalid 4 Octet Sequence (in 4th Octet)' => "\xf0\x28\x8c\x28",
'Valid 5 Octet Sequence (but not Unicode!)' => "\xf8\xa1\xa1\xa1\xa1",
'Valid 6 Octet Sequence (but not Unicode!)' => "\xfc\xa1\xa1\xa1\xa1\xa1",
);
foreach ($examples as $k => $v) {
echo "{$k}\n";
echo utf8_scrub($v);
echo "\n";
}
preferences:
30.85 ms | 402 KiB | 5 Q