[sourcecode lang=”php”]
//reject overly long 2 byte sequences,
//as well as characters above U+10000
//and replace with ?
$some_string = preg_replace(‘/’.
‘[x00-x08x10x0Bx0Cx0E-x19x7F]’.
‘|[x00-x7F][x80-xBF]+’.
‘|([xC0xC1]|[xF0-xFF])[x80-xBF]*’.
‘|[xC2-xDF]((?![x80-xBF])|[x80-xBF]{2,})’.
‘|[xE0-xEF](([x80-xBF](?![x80-xBF]))|’.
‘(?![x80-xBF]{2})|[x80-xBF]{3,})’.
‘/S’,
‘?’, $some_string );
//reject overly long 3 byte sequences
//and UTF-16 surrogates and replace with ?
$some_string = preg_replace(‘/’.
‘xE0[x80-x9F][x80-xBF]’.
‘|xED[xA0-xBF][x80-xBF]’.
‘/S’,
‘?’, $some_string );
[/sourcecode]
Via Remove non-UTF8 characters from string with PHP « Magp.ie.