Revision: 13117
Initial Code
Initial URL
Initial Description
Initial Title
Initial Tags
Initial Language
at April 9, 2009 10:35 by michaelfox
Initial Code
function charset_decode_utf_8($string) {
/* Only do the slow convert if there are 8-bit characters */
/* avoid using 0xA0 (240) in ereg ranges. RH73 does not like that */
if (! ereg("[200-237]", $string) and ! ereg("[241-377]", $string))
return $string;
// decode three byte unicode characters
$string = preg_replace("/([340-357])([200-277])([200-277])/e",
"'&#'.((ord('\1')-224)*4096 + (ord('\2')-128)*64 + (ord('\3')-128)).';'",
$string);
// decode two byte unicode characters
$string = preg_replace("/([300-337])([200-277])/e",
"'&#'.((ord('\1')-192)*64+(ord('\2')-128)).';'",
$string);
return $string;
}
Initial URL
Initial Description
Initial Title
decode utf8 charset
Initial Tags
textmate
Initial Language
PHP