判断中日韩文的正则表达式

PHP中GBK和UTF8编码处理

一、编码范围

1. GBK (GB2312/GB18030)
\x00-\xff  GBK双字节编码范围
\x20-\x7f  ASCII
\xa1-\xff  中文
\x80-\xff  中文

2. UTF-8 (Unicode)
\u4e00-\u9fa5 (中文)
\x3130-\x318F (韩文
\xAC00-\xD7A3 (韩文)
\u0800-\u4e00 (日文)
ps: 韩文是大于[\u9fa5]的字符

正则例子:
preg_replace("/([\x80-\xff])/","",$str);
preg_replace("/([u4e00-u9fa5])/","",$str);

二、代码例子

//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; $i<strlen($str); $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; $i<strlen($str); $i++){
        if($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; $i < strlen($str); $i++){
        $value = ord($str[$i]);
        if($value > 127) {
            $count++;
            if($value >= 192 && $value <= 223) $i++;
            elseif($value >= 224 && $value <= 239) $i = $i + 2;
            elseif($value >= 240 && $value <= 247) $i = $i + 3;
            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; $i < strlen($str); $i++){
        if($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 <= 223) $i++;
            elseif($value >= 224 && $value <= 239) $i = $i + 2;
            elseif($value >= 240 && $value <= 247) $i = $i + 3;
            else die('Not a UTF-8 compatible string');
        }
        $count++;

    }
    return(substr($str,$start_position,$end_position-$start_position));
}

//字符串长度统计-UTF8 [中文3个字节，俄文、韩文占2个字节，字母占1个字节] (Ruby)
def utf8_string_length(str)
    temp = CGI::unescape(str)
    i = 0;
    j = 0;
    temp.length.times{|t|
        if temp[t] < 127
            i += 1
        elseif temp[t] >= 127 and temp[t] < 224
            j += 1
            if 0 == (j % 2)
                i += 2
                j = 0
            end
        else
            j += 1
            if 0 == (j % 3)
                i +=2
                j = 0
            end
        end
    }
    return i
}

//判断是否是有韩文-UTF-8 (JavaScript)
function checkKoreaChar(str) {
    for(i=0; i<str.length; i++) {
        if(((str.charCodeAt(i) > 0x3130 && str.charCodeAt(i) < 0x318F) || (str.charCodeAt(i) >= 0xAC00 && str.charCodeAt(i) <= 0xD7A3))) {
            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);

三、参考文档

另：

public function csubstr($str, $start=0, $length, $charset="utf-8", $suffix=true)
{
if(function_exists("mb_substr"))
return mb_substr($str, $start, $length, $charset);
$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]/";
$re['big5'] = "/[\x01-\x7f]|[\x81-\xfe]([\x40-\x7e]|\xa1-\xfe])/";
preg_match_all($re[$charset], $str, $match);
$slice = join("",array_slice($match[0], $start, $length));
if($suffix) return $slice."…";
return $slice;
}