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
Code
1
//判断内容里有没有中文-GBK (PHP)
2function check_is_chinese($s){
3 return preg_match('/[\x80-\xff]./', $s);
4}
5
6//获取字符串长度-GBK (PHP)
7function gb_strlen($str){
8 $count = 0;
9 for($i=0; $i<strlen($str); $i++){
10 $s = substr($str, $i, 1);
11 if (preg_match("/[\x80-\xff]/", $s)) ++$i;
12 ++$count;
13 }
14 return $count;
15}
16
17//截取字符串字串-GBK (PHP)
18function gb_substr($str, $len){
19 $count = 0;
20 for($i=0; $i<strlen($str); $i++){
21 if($count == $len) break;
22 if(preg_match("/[\x80-\xff]/", substr($str, $i, 1))) ++$i;
23 ++$count;
24 }
25 return substr($str, 0, $i);
26}
27
28//统计字符串长度-UTF8 (PHP)
29function utf8_strlen($str) {
30 $count = 0;
31 for($i = 0; $i < strlen($str); $i++){
32 $value = ord($str[$i]);
33 if($value > 127) {
34 $count++;
35 if($value >= 192 && $value <= 223) $i++;
36 elseif($value >= 224 && $value <= 239) $i = $i + 2;
37 elseif($value >= 240 && $value <= 247) $i = $i + 3;
38 else die('Not a UTF-8 compatible string');
39 }
40 $count++;
41 }
42 return $count;
43}
44
45
46//截取字符串-UTF8(PHP)
47function utf8_substr($str,$position,$length){
48 $start_position = strlen($str);
49 $start_byte = 0;
50 $end_position = strlen($str);
51 $count = 0;
52 for($i = 0; $i < strlen($str); $i++){
53 if($count >= $position && $start_position > $i){
54 $start_position = $i;
55 $start_byte = $count;
56 }
57 if(($count-$start_byte)>=$length) {
58 $end_position = $i;
59 break;
60 }
61 $value = ord($str[$i]);
62 if($value > 127){
63 $count++;
64 if($value >= 192 && $value <= 223) $i++;
65 elseif($value >= 224 && $value <= 239) $i = $i + 2;
66 elseif($value >= 240 && $value <= 247) $i = $i + 3;
67 else die('Not a UTF-8 compatible string');
68 }
69 $count++;
70
71 }
72 return(substr($str,$start_position,$end_position-$start_position));
73}
74
75
76//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)
77def utf8_string_length(str)
78 temp = CGI::unescape(str)
79 i = 0;
80 j = 0;
81 temp.length.times{|t|
82 if temp[t] < 127
83 i += 1
84 elseif temp[t] >= 127 and temp[t] < 224
85 j += 1
86 if 0 == (j % 2)
87 i += 2
88 j = 0
89 end
90 else
91 j += 1
92 if 0 == (j % 3)
93 i +=2
94 j = 0
95 end
96 end
97 }
98 return i
99}
100
101//判断是否是有韩文-UTF-8 (JavaScript)
102function checkKoreaChar(str) {
103 for(i=0; i<str.length; i++) {
104 if(((str.charCodeAt(i) > 0x3130 && str.charCodeAt(i) < 0x318F) || (str.charCodeAt(i) >= 0xAC00 && str.charCodeAt(i) <= 0xD7A3))) {
105 return true;
106 }
107 }
108 return false;
109}
110//判断是否有中文字符-GBK (JavaScript)
111function check_chinese_char(s){
112 return (s.length != s.replace(/[^\x00-\xff]/g,"**").length);
http://www.unicode.org/
http://examples.oreilly.com/cjkvinfo/doc/cjk.inf
http://www.ansell-uebersetzungen.com/gbuni.html
http://www.haiyan.com/steelk/navigator/ref/gbk/gbindex.htm
http://baike.baidu.com/view/40801.htm
http://www.chedong.com/tech/hello_unicode.html
另：
Code
1/*
2* 中文截取，支持gb2312,gbk,utf-8,big5
3*
4* @param string $str 要截取的字串
5* @param int $start 截取起始位置
6* @param int $length 截取长度
7* @param string $charset utf-8|gb2312|gbk|big5 编码
8* @param $suffix 是否加尾缀
9*/
10public function csubstr($str, $start=0, $length, $charset="utf-8", $suffix=true)
11{
12if(function_exists("mb_substr"))
13return mb_substr($str, $start, $length, $charset);
14$re['utf-8'] = "/[\x01-\x7f]|[\xc2-\xdf][\x80-\xbf]|[\xe0-\xef][\x80-\xbf]{2}|[\xf0-\xff][\x80-\xbf]{3}/";
15$re['gb2312'] = "/[\x01-\x7f]|[\xb0-\xf7][\xa0-\xfe]/";
16$re['gbk'] = "/[\x01-\x7f]|[\x81-\xfe][\x40-\xfe]/";
17$re['big5'] = "/[\x01-\x7f]|[\x81-\xfe]([\x40-\x7e]|\xa1-\xfe])/";
18preg_match_all($re[$charset], $str, $match);
19$slice = join("",array_slice($match[0], $start, $length));
20if($suffix) return $slice."…";
21return $slice;
22}
23
24
posted on 2008-04-10 11:12
冷风旋 阅读(31)
评论(0) 编辑 收藏 网摘 所属分类:
PHP