21,893
社区成员




$str="规:范化 不得不知,道代动不,动不得不风格感?表 ";
$result=getCN($str);//UTF-8编码调用
//$result=getCN($str,"GB2312",2);//GB2312编码调用
//$result=getCN($str,"?",单个字符字节数);//?编码调用
print_r($result);
function getCN($string,$charset="UTF-8",$charnum=3){
$tmpstr = $string;
$utf8 = $charset=="UTF-8"?true:false;
!$utf8 && $string = iconv($charset,"UTF-8",$string);
preg_match_all("/[\x80-\xff]{3}/",$string,$data);
$cnarr=array();
foreach($data[0] as $key=>$char){
if(!preg_match_all("/[\\pP]/u",$char,$math)){
$cnarr[$key]['char']=$utf8?$char:iconv("UTF-8",$charset,$char);
$cnarr[$key]['start']=strpos($tmpstr,$cnarr[$key]['char']);
$cnarr[$key]['end']=$cnarr[$key]['start']+$charnum;
}
}
return $cnarr;
}
$str = '一?二?';
$arr = preg_split('/\?|?| /', $str, -1, PREG_SPLIT_OFFSET_CAPTURE);
print_r($arr);
//得到二维数组,$arr[$i][0] 匹配满足的字符,$arr[$i][1]匹配位置
//这个位置是strlen,如果中文算一个字符,只需要截取前面那段字符,用mb_strlen即可
$k1 = mb_substr($this->Keywords, 0, 1, "UTF-8");