判断某字符串是否是UTF-8编码

 1 //参考 http://w3.org/International/questions/qa-forms-utf-8.html
 2 function is_utf8($string) {
 3     return preg_match('%^(?:
 4     [\x09\x0A\x0D\x20-\x7E] // ASCII
 5     | [\xC2-\xDF][\x80-\xBF] // non-overlong 2-byte
 6     |  \xE0[\xA0-\xBF][\x80-\xBF] // excluding overlongs
 7     | [\xE1-\xEC\xEE\xEF][\x80-\xBF]{2} // straight 3-byte
 8     |  \xED[\x80-\x9F][\x80-\xBF] // excluding surrogates
 9     |  \xF0[\x90-\xBF][\x80-\xBF]{2} // planes 1-3
10     | [\xF1-\xF3][\x80-\xBF]{3} // planes 4-15
11     |  \xF4[\x80-\x8F][\x80-\xBF]{2} // plane 16
12     )*$%xs', $string);
13 }