php探测编码

<?php

//探测编码。注意：由于gb2312，gbk，big5范围有重合，按照最小范围判断
function get_encoding($string)
{
    $re['utf-8'] = "/[\x01-\x7f]|[\xc2-\xdf][\x80-\xbf]|[\xe0-\xef][\x80-\xbf]{2}|[\xf0-\xff][\x80-\xbf]{3}/";
    $re['gb2312'] = "/[\x01-\x7f]|[\xb0-\xf7][\xa0-\xfe]/";
    $re['gbk'] = "/[\x01-\x7f]|[\x81-\xfe][\x40-\xfe]/";
    $re['big5'] = "/[\x01-\x7f]|[\x81-\xfe]([\x40-\x7e]|\xa1-\xfe])/";
   
    foreach( $re as $encoding=>$pattern )
    {
        $rstring = preg_replace($pattern, "", $string);
        if( $rstring == "")
        {
            return $encoding;
        }
    }
    return null;
}

?>

注意：遇到内有乱码或者错误字符的情况未作测试，例如半个汉字的情形。