判断字符串是utf-8 还是gb2312函数
/*** 判断字符串是utf-8 还是gb2312* @param unknown $str* @param string $default* @return string*/function utf<div>本文#来源gaodai.ma#com搞##代!^码7网</div><pre>搞代gaodaima码
8_gb2312($str, $default = ‘gb2312’){ $str = preg_replace(“/[\x01-\x7F]+/”, “”, $str); if (empty($str)) return $default; $preg = array( “gb2312” => “/^([\xA1-\xF7][\xA0-\xFE])+$/”, //正则判断是否是gb2312 “utf-8” => “/^[\x{4E00}-\x{9FA5}]+$/u”, //正则判断是否是汉字(utf8编码的条件了),这个范围实际上已经包含了繁体中文字了 ); if ($default == ‘gb2312’) { $option = ‘utf-8’; } else { $option = ‘gb2312’; } if (!preg_match($preg[$default], $str)) { return $option; } $str = @iconv($default, $option, $str); //不能转成 $option, 说明原来的不是 $default if (empty($str)) { return $option; } return $default;}
utf-8和gb2312自动转化
/*** utf-8和gb2312自动转化* @param unknown $string* @param string $outEncoding* @return unknown|string*/function safeEncoding($string,$outEncoding = 'UTF-8'){$encoding = "UTF-8";for($i = 0; $i < strlen ( $string ); $i ++) {if (ord ( $string {$i} ) < 128)continue; if ((ord ( $string {$i} ) & 224) == 224) {// 第一个字节判断通过$char = $string {++ $i};if ((ord ( $char ) & 128) == 128) {// 第二个字节判断通过$char = $string {++ $i};if ((ord ( $char ) & 128) == 128) {$encoding = "UTF-8";break;}}}if ((ord ( $string {$i} ) & 192) == 192) {// 第一个字节判断通过$char = $string {++ $i};if ((ord ( $char ) & 128) == 128) {// 第二个字节判断通过$encoding = "GB2312";break;}}} if (strtoupper ( $encoding ) == strtoupper ( $outEncoding ))return $string;elsereturn @iconv ( $encoding, $outEncoding, $string );}