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
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
|
/*-------
* Module: win_unicode.c
*
* Description: This module contains utf8 <-> ucs2 conversion routines
* under WIndows
*
*-------
*/
#include "psqlodbc.h"
#include <stdio.h>
#include <string.h>
#define byte3check 0xf800
#define byte2_base 0x80c0
#define byte2_mask1 0x07c0
#define byte2_mask2 0x003f
#define byte3_base 0x8080e0
#define byte3_mask1 0xf000
#define byte3_mask2 0x0fc0
#define byte3_mask3 0x003f
UInt4 ucs2strlen(const SQLWCHAR *ucs2str)
{
UInt4 len;
for (len = 0; ucs2str[len]; len++)
;
return len;
}
char *ucs2_to_utf8(const SQLWCHAR *ucs2str, Int4 ilen, UInt4 *olen)
{
char * utf8str;
/*mylog("ucs2_to_utf8 %x ilen=%d ", ucs2str, ilen);*/
if (!ucs2str)
return NULL;
if (ilen < 0)
ilen = ucs2strlen(ucs2str);
/*mylog(" newlen=%d", ilen);*/
utf8str = (char *) malloc(ilen * 3 + 1);
if (utf8str)
{
int i, len = 0;
UInt2 byte2code;
Int4 byte4code;
const SQLWCHAR *wstr;
for (i = 0, wstr = ucs2str; i < ilen; i++, wstr++)
{
if (!*wstr)
break;
else if (0 == (*wstr & 0xff80))
utf8str[len++] = (char) *wstr;
else if ((*wstr & byte3check) == 0)
{
byte2code = byte2_base |
((byte2_mask1 & *wstr) >> 6) |
((byte2_mask2 & *wstr) << 8);
memcpy(utf8str + len, (char *) &byte2code, sizeof(byte2code));
len += 2;
}
else
{
byte4code = byte3_base |
((byte3_mask1 & *wstr) >> 12) |
((byte3_mask2 & *wstr) << 2) |
((byte3_mask3 & *wstr) << 16);
memcpy(utf8str + len, (char *) &byte4code, 3);
len += 3;
}
}
utf8str[len] = '\0';
if (olen)
*olen = len;
}
/*mylog(" olen=%d %s\n", *olen, utf8str ? utf8str : "");*/
return utf8str;
}
#define byte3_m1 0x0f
#define byte3_m2 0x3f
#define byte3_m3 0x3f
#define byte2_m1 0x1f
#define byte2_m2 0x3f
UInt4 utf8_to_ucs2(const char *utf8str, Int4 ilen, SQLWCHAR *ucs2str, UInt4 bufcount)
{
int i;
UInt4 ocount, wcode;
const unsigned char *str;
/*mylog("utf8_to_ucs2 ilen=%d bufcount=%d", ilen, bufcount);*/
if (!utf8str || !ilen)
return 0;
/*mylog(" string=%s\n", utf8str);*/
if (!bufcount)
ucs2str = NULL;
else if (!ucs2str)
bufcount = 0;
if (ilen < 0)
ilen = strlen(utf8str);
for (i = 0, ocount = 0, str = utf8str; i < ilen;)
{
if (iswascii(*str))
{
if (ocount < bufcount)
ucs2str[ocount] = *str;
ocount++;
i++;
str++;
}
else if (0xe0 == (*str & 0xe0)) /* 3 byte code */
{
if (ocount < bufcount)
{
wcode = ((((UInt4) *str) & byte3_m1) << 12) |
((((UInt4) str[1]) & byte3_m2) << 6) |
(((UInt4) str[2]) & byte3_m3);
ucs2str[ocount] = (SQLWCHAR) wcode;
}
ocount++;
i += 3;
str += 3;
}
else
{
if (ocount < bufcount)
{
wcode = ((((UInt4) *str) & byte2_m1) << 6) |
(((UInt4) str[1]) & byte2_m2);
ucs2str[ocount] = (SQLWCHAR) wcode;
}
ocount++;
i += 2;
str += 2;
}
}
if (ocount && ocount < bufcount && ucs2str)
ucs2str[ocount] = 0;
/*mylog(" ocount=%d\n", ocount);*/
return ocount;
}
|
