Windows WCHAR 到 Linux wchar_t 字符类型的转换
标签: windowslinux字符乱码转换
2015-05-14 12:05 679人阅读 评论(0) 收藏 举报
分类: Linux 编程(14)
版权声明:本文为博主原创文章,未经博主允许不得转载。
1、简介
这几天涉及到一个小项目,Windows 和Linux通过TCP进行通信,但是他们之间的字符类型上是有区别的,所有Windows上的数据发送到Linux上后,如果不经过转换,会出现乱码的情况,Windows 的WCHAR类型实际上是wchar_t,但是它只占用2个字节(既UTF-16),而Linux上wchar_t则使用的是多字节(UTF-8),下面的函数提供了他们之间的相互转换!
2、程序代码
#ifdef WINDOWS
#include <windows.h>
#include <stdio.h>
#include <ctype.h>
#else
#include <wchar.h>
#include <string.h>
#endif
#ifdef WIN32
#define USES_WCSUTF16_CONV
#define WCS2UTF16(wcs) (wcs)
#define UTF162WCS(utf16) (utf16)
#else //WIN32
//wchar_t to char16_t
unsigned short * _wcsu16_wcs2utf16(wchar_t *wcs, unsigned short * utf16, int len)
{
int wc;
wchar_t *end = wcs + len;
unsigned short * ret = utf16;
while(wcs < end)
{
wc = *(wcs++);
if (wc > 0xFFFF)
{
wc -= 0x00010000L;
*utf16++ = 0xD800 | (wc >> 10);
*utf16++ = 0xDC00 | (wc & 0x03FF);
}
else
{
*utf16++ = wc;
}
}
return ret;
}
//wchar_t length
int _wcsu16_utf16len(wchar_t *wcs)
{
int wc;
int ret = 0;
while(wc = *wcs++)
ret += wc > 0xFFFF ? 2 : 1;
return ret;
}
//char16_t length
int _wcsu16_wcslen(unsigned short * utf16)
{
unsigned short * start = utf16;
while(*utf16++) ;
return (int)(utf16 - start - 1);
}
//char16_t to wchar_t
wchar_t * _wcsu16_utf162wcs(unsigned short * utf16, wchar_t *wcs, int len)
{
if (sizeof(unsigned short) == sizeof(wchar_t))
{
memcpy(wcs, utf16, (len + 1) * sizeof(wchar_t));
return wcs;
}
else
{
int u32;
unsigned short *end = utf16 + len;
wchar_t * ret = wcs;
int u32low = 0;
while (utf16 < end)
{
u32 = *utf16++;
if (u32>=0xD800 && u32<0xDC00)
{
u32low = *utf16++;
u32 &= 0x3FF;
u32low &= 0x3FF;
u32 <<= 10;
u32 += u32low;
u32 += 0x10000;
}
*wcs++ = u32;
}
*(wcs-1) = 0;
return ret;
}
}
#define USES_WCSUTF16_CONV int _len; (_len); wchar_t * _wcs; (_wcs); unsigned short * _utf16; (_utf16)
#define WCS2UTF16(wcs) \
(((_wcs = wcs) == NULL) ? NULL : (\
_len = (_wcsu16_utf16len(_wcs)+1),\
_wcsu16_wcs2utf16(_wcs, (unsigned short *) alloca(_len*2), _len)))
#define UTF162WCS(utf16) \
(((_utf16 = utf16) == NULL) ? NULL : (\
_len = (_wcsu16_wcslen(_utf16)+1),\
_wcsu16_utf162wcs(_utf16, (wchar_t *) alloca(_len*sizeof(wchar_t)), _len)))
#endif //WIN32
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
103
104
105
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
103
104
105
3、附加说明
标签: windowslinux字符乱码转换
2015-05-14 12:05 679人阅读 评论(0) 收藏 举报
分类: Linux 编程(14)
版权声明:本文为博主原创文章,未经博主允许不得转载。
1、简介
这几天涉及到一个小项目,Windows 和Linux通过TCP进行通信,但是他们之间的字符类型上是有区别的,所有Windows上的数据发送到Linux上后,如果不经过转换,会出现乱码的情况,Windows 的WCHAR类型实际上是wchar_t,但是它只占用2个字节(既UTF-16),而Linux上wchar_t则使用的是多字节(UTF-8),下面的函数提供了他们之间的相互转换!
2、程序代码
#ifdef WINDOWS
#include <windows.h>
#include <stdio.h>
#include <ctype.h>
#else
#include <wchar.h>
#include <string.h>
#endif
#ifdef WIN32
#define USES_WCSUTF16_CONV
#define WCS2UTF16(wcs) (wcs)
#define UTF162WCS(utf16) (utf16)
#else //WIN32
//wchar_t to char16_t
unsigned short * _wcsu16_wcs2utf16(wchar_t *wcs, unsigned short * utf16, int len)
{
int wc;
wchar_t *end = wcs + len;
unsigned short * ret = utf16;
while(wcs < end)
{
wc = *(wcs++);
if (wc > 0xFFFF)
{
wc -= 0x00010000L;
*utf16++ = 0xD800 | (wc >> 10);
*utf16++ = 0xDC00 | (wc & 0x03FF);
}
else
{
*utf16++ = wc;
}
}
return ret;
}
//wchar_t length
int _wcsu16_utf16len(wchar_t *wcs)
{
int wc;
int ret = 0;
while(wc = *wcs++)
ret += wc > 0xFFFF ? 2 : 1;
return ret;
}
//char16_t length
int _wcsu16_wcslen(unsigned short * utf16)
{
unsigned short * start = utf16;
while(*utf16++) ;
return (int)(utf16 - start - 1);
}
//char16_t to wchar_t
wchar_t * _wcsu16_utf162wcs(unsigned short * utf16, wchar_t *wcs, int len)
{
if (sizeof(unsigned short) == sizeof(wchar_t))
{
memcpy(wcs, utf16, (len + 1) * sizeof(wchar_t));
return wcs;
}
else
{
int u32;
unsigned short *end = utf16 + len;
wchar_t * ret = wcs;
int u32low = 0;
while (utf16 < end)
{
u32 = *utf16++;
if (u32>=0xD800 && u32<0xDC00)
{
u32low = *utf16++;
u32 &= 0x3FF;
u32low &= 0x3FF;
u32 <<= 10;
u32 += u32low;
u32 += 0x10000;
}
*wcs++ = u32;
}
*(wcs-1) = 0;
return ret;
}
}
#define USES_WCSUTF16_CONV int _len; (_len); wchar_t * _wcs; (_wcs); unsigned short * _utf16; (_utf16)
#define WCS2UTF16(wcs) \
(((_wcs = wcs) == NULL) ? NULL : (\
_len = (_wcsu16_utf16len(_wcs)+1),\
_wcsu16_wcs2utf16(_wcs, (unsigned short *) alloca(_len*2), _len)))
#define UTF162WCS(utf16) \
(((_utf16 = utf16) == NULL) ? NULL : (\
_len = (_wcsu16_wcslen(_utf16)+1),\
_wcsu16_utf162wcs(_utf16, (wchar_t *) alloca(_len*sizeof(wchar_t)), _len)))
#endif //WIN32
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
103
104
105
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
103
104
105
3、附加说明
Linux下表示Windows下的16位的wchar_t类型可使用unsigned short来表示,也可直接使用C++中的char16_t类型
http://blog.csdn.net/cmbug/article/details/45719209