function valid_1byte($char) {
if(!is_int($char)) return false;
return ($char & 0x80) == 0x00;
}
function valid_2byte($char) {
if(!is_int($char)) return false;
return ($char & 0xE0) == 0xC0;
}
function valid_3byte($char) {
if(!is_int($char)) return false;
return ($char & 0xF0) == 0xE0;
}
function valid_4byte($char) {
if(!is_int($char)) return false;
return ($char & 0xF8) == 0xF0;
}
function valid_nextbyte($char) {
if(!is_int($char)) return false;
return ($char & 0xC0) == 0x80;
}
function valid_utf8($string) {
$len = strlen($string);
$i = 0;
while( $i < $len ) {
$char = ord(substr($string, $i++, 1));
if(valid_1byte($char)) { // continue
continue;
} else if(valid_2byte($char)) { // check 1 byte
if(!valid_nextbyte(ord(substr($string, $i++, 1))))
return false;
} else if(valid_3byte($char)) { // check 2 bytes
if(!valid_nextbyte(ord(substr($string, $i++, 1))))
return false;
if(!valid_nextbyte(ord(substr($string, $i++, 1))))
return false;
} else if(valid_4byte($char)) { // check 3 bytes
if(!valid_nextbyte(ord(substr($string, $i++, 1))))
return false;
if(!valid_nextbyte(ord(substr($string, $i++, 1))))
return false;
if(!valid_nextbyte(ord(substr($string, $i++, 1))))
return false;
} // goto next char
}
return true; // done
}
比较准确地检测字符的编码是否是UTF8
最新推荐文章于 2024-06-09 18:30:55 发布