-
- preg_replace(”/([\x80-\xff])/”,”",$str);
- preg_replace(”/([u4e00-u9fa5])/”,”",$str);
例子，php中文编码判断。
-
-
//判断内容里有没有中文-gbk (php)
- function check_is_chinese($s){
- return preg_match('/[\x80-\xff]./', $s);
- }
- //获取字符串长度-gbk (php)
- function gb_strlen($str){
- $count = 0;
- for($i=0; $i$s = substr($str, $i, 1);
- if (preg_match("/[\x80-\xff]/", $s)) ++$i;
- ++$count;
- }
- return $count;
- }
- //截取字符串字串-gbk (php)
- function gb_substr($str, $len){
- $count = 0;
- for($i=0; $iif($count == $len) break;
- if(preg_match("/[\x80-\xff]/", substr($str, $i, 1))) ++$i;
- ++$count;
- }
- return substr($str, 0, $i);
- }
- //统计字符串长度-utf8 (php)
- function utf8_strlen($str) {
- $count = 0;
- for($i = 0; $i $value = ord($str[$i]);
- if($value > 127) {
- $count++;
- if($value >= 192 && $value elseif($value >= 224 && $value elseif($value >= 240 && $value else die('not a utf-8 compatible string');
- }
- $count++;
- }
- return $count;
- }
- //截取字符串-utf8(php)
- function utf8_substr($str,$position,$length){
- $start_position = strlen($str);
- $start_byte = 0;
- $end_position = strlen($str);
- $count = 0;
- for($i = 0; $i if($count >= $position && $start_position > $i){
- $start_position = $i;
- $start_byte = $count;
- }
- if(($count-$start_byte)>=$length) {
- $end_position = $i;
- break;
- }
- $value = ord($str[$i]);
- if($value > 127){
- $count++;
- if($value >= 192 && $value elseif($value >= 224 && $value elseif($value >= 240 && $value else die('not a utf-8 compatible string');
- }
- $count++;
- }
- return(substr($str,$start_position,$end_position-$start_position));
- }
- //判断是否是有韩文-utf-8 (javascript)
- function checkkoreachar(str) {
- for(i=0; iif(((str.charcodeat(i) > 0x3130 && str.charcodeat(i) = 0xac00 && str.charcodeat(i) return true;
- }
- }
- return false;
- }
- //判断是否有中文字符-gbk (javascript)
- function check_chinese_char(s){
- return (s.length != s.replace(/[^\x00-\xff]/g,"**").length);
- }
|
