php

中文字符串和Unicode互转

将GBK，UTF8字符串转化为Unicode编码的类

unicode.class.php

1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
<?php
/**
 * 提供GBK,UTF8转化为Unicode编码,
 * Unicode转化为GBK,UTF8编码字符串类库
 * 
 * @author wang chong(wangchong1985@gmail.com)
 * @link http://www.wangchong.org
 * @version 1.0.0 (2011-04-15)
 * @package php-Unicode
 */
class Unicode
{
    /**
     * 自定义str_to_unicode后的连接符
     * @var string
     */
    public $glue = "";
    /**
     * 将字符串转换成unicode编码
     *
     * @param string $input
     * @param string $input_charset
     * @return string
     */
    public function str_to_unicode($input, $input_charset = 'gbk')
    {
        $input = iconv($input_charset, "gbk", $input);
        preg_match_all("/[\x80-\xff]?./", $input, $ar);
        $b = array_map(array($this, 'utf8_unicode_'), $ar[0]);
        $outstr = join($this->glue, $b);
        return $outstr;
    }
    private function utf8_unicode_($c, $input_charset = 'gbk')
    {
        $c = iconv($input_charset, 'utf-8', $c);
        return $this->utf8_unicode($c);
    }
    // utf8 -> unicode
    private function utf8_unicode($c)
    {
        switch(strlen($c)) {
            case 1:
                //return $c;
                $n = ord($c[0]);
                break;
            case 2:
                $n = (ord($c[0]) & 0x3f) << 6;
                $n += ord($c[1]) & 0x3f;
                break;
            case 3:
                $n = (ord($c[0]) & 0x1f) << 12;
                $n += (ord($c[1]) & 0x3f) << 6;
                $n += ord($c[2]) & 0x3f;
                break;
            case 4:
                $n = (ord($c[0]) & 0x0f) << 18;
                $n += (ord($c[1]) & 0x3f) << 12;
                $n += (ord($c[2]) & 0x3f) << 6;
                $n += ord($c[3]) & 0x3f;
                break;
        }
        return "\u".base_convert($n, 10, 16);
    }
    /**
     * 将unicode字符转换成普通编码字符
     *
     * @param string $str
     * @param string $out_charset
     * @return string
     */
    public function str_from_unicode($str, $out_charset = 'gbk')
    {
        $str = preg_replace_callback("|\\\u([0-9a-f]{1,4})|", array($this, 'unicode2utf8_'), $str);
        $str = iconv("UTF-8", $out_charset, $str);
        return $str;
    }
    private function unicode2utf8_($c)
    {
        return $this->unicode2utf8($c[1]);
    }
    private function unicode2utf8($c)
    {
        $c = base_convert($c, 16, 10);
        $str="";
        if ($c < 0x80) {
            $str.=chr($c);
        } else if ($c < 0x800) {
            $str.=chr(0xC0 | $c>>6);
            $str.=chr(0x80 | $c & 0x3F);
        } else if ($c < 0x10000) {
            $str.=chr(0xE0 | $c>>12);
            $str.=chr(0x80 | $c>>6 & 0x3F);
            $str.=chr(0x80 | $c & 0x3F);
        } else if ($c < 0x200000) {
            $str.=chr(0xF0 | $c>>18);
            $str.=chr(0x80 | $c>>12 & 0x3F);
            $str.=chr(0x80 | $c>>6 & 0x3F);
            $str.=chr(0x80 | $c & 0x3F);
        }
        return $str;
    }
}

unicode.example.php

1
2
3
4
5
6
7
8
9
10
11
12
13
<?php

include 'unicode.class.php';

$str = '这是一个测试Demo!~！wangchong1985@gmail.com';

$convert = new Unicode();

//convert to Unicode
var_dump($str = $convert->str_to_unicode($str, 'UTF-8'));

//convert to UTF-8
var_dump($str = $convert->str_from_unicode($str, 'UTF-8'))

转自：https://github.com/wangchll/PHP-Unicode-Convert