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
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
|
/*
* UTF-8 support routines
*
* Copyright 2000 Alexandre Julliard
*
* This library is free software; you can redistribute it and/or
* modify it under the terms of the GNU Lesser General Public
* License as published by the Free Software Foundation; either
* version 2.1 of the License, or (at your option) any later version.
*
* This library is distributed in the hope that it will be useful,
* but WITHOUT ANY WARRANTY; without even the implied warranty of
* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
* Lesser General Public License for more details.
*
* You should have received a copy of the GNU Lesser General Public
* License along with this library; if not, write to the Free Software
* Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA
*/
#include <string.h>
#include "winnls.h"
#include "wine/unicode.h"
/* number of following bytes in sequence based on first byte value (for bytes above 0x7f) */
static const char utf8_length[128] =
{
0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0, /* 0x80-0x8f */
0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0, /* 0x90-0x9f */
0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0, /* 0xa0-0xaf */
0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0, /* 0xb0-0xbf */
1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1, /* 0xc0-0xcf */
1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1, /* 0xd0-0xdf */
2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2, /* 0xe0-0xef */
3,3,3,3,3,3,3,3,4,4,4,4,5,5,0,0 /* 0xf0-0xff */
};
/* first byte mask depending on UTF-8 sequence length */
static const unsigned char utf8_mask[6] = { 0x7f, 0x1f, 0x0f, 0x07, 0x03, 0x01 };
/* minimum Unicode value depending on UTF-8 sequence length */
static const unsigned int utf8_minval[6] = { 0x0, 0x80, 0x800, 0x10000, 0x200000, 0x4000000 };
/* query necessary dst length for src string */
inline static int get_length_wcs_utf8( const WCHAR *src, unsigned int srclen )
{
int len;
for (len = 0; srclen; srclen--, src++, len++)
{
if (*src >= 0x80)
{
len++;
if (*src >= 0x800) len++;
}
}
return len;
}
/* wide char to UTF-8 string conversion */
/* return -1 on dst buffer overflow */
int utf8_wcstombs( const WCHAR *src, int srclen, char *dst, int dstlen )
{
int ret = srclen;
if (!dstlen) return get_length_wcs_utf8( src, srclen );
for (ret = srclen; srclen; srclen--, src++)
{
WCHAR ch = *src;
if (ch < 0x80) /* 0x00-0x7f: 1 byte */
{
if (!dstlen--) return -1; /* overflow */
*dst++ = ch;
continue;
}
if (ch < 0x800) /* 0x80-0x7ff: 2 bytes */
{
if ((dstlen -= 2) < 0) return -1; /* overflow */
dst[1] = 0x80 | (ch & 0x3f);
ch >>= 6;
dst[0] = 0xc0 | ch;
dst += 2;
continue;
}
/* 0x800-0xffff: 3 bytes */
if ((dstlen -= 3) < 0) return -1; /* overflow */
dst[2] = 0x80 | (ch & 0x3f);
ch >>= 6;
dst[1] = 0x80 | (ch & 0x3f);
ch >>= 6;
dst[0] = 0xe0 | ch;
dst += 3;
}
return ret;
}
/* query necessary dst length for src string */
inline static int get_length_mbs_utf8( const unsigned char *src, int srclen )
{
int ret;
const unsigned char *srcend = src + srclen;
for (ret = 0; src < srcend; ret++)
{
unsigned char ch = *src++;
if (ch < 0xc0) continue;
switch(utf8_length[ch-0x80])
{
case 5:
if (src >= srcend) return ret; /* ignore partial char */
if ((ch = *src ^ 0x80) >= 0x40) continue;
src++;
case 4:
if (src >= srcend) return ret; /* ignore partial char */
if ((ch = *src ^ 0x80) >= 0x40) continue;
src++;
case 3:
if (src >= srcend) return ret; /* ignore partial char */
if ((ch = *src ^ 0x80) >= 0x40) continue;
src++;
case 2:
if (src >= srcend) return ret; /* ignore partial char */
if ((ch = *src ^ 0x80) >= 0x40) continue;
src++;
case 1:
if (src >= srcend) return ret; /* ignore partial char */
if ((ch = *src ^ 0x80) >= 0x40) continue;
src++;
}
}
return ret;
}
/* UTF-8 to wide char string conversion */
/* return -1 on dst buffer overflow, -2 on invalid input char */
int utf8_mbstowcs( int flags, const char *src, int srclen, WCHAR *dst, int dstlen )
{
int len, count;
unsigned int res;
const char *srcend = src + srclen;
if (!dstlen) return get_length_mbs_utf8( src, srclen );
for (count = dstlen; count && (src < srcend); count--, dst++)
{
unsigned char ch = *src++;
if (ch < 0x80) /* special fast case for 7-bit ASCII */
{
*dst = ch;
continue;
}
len = utf8_length[ch-0x80];
res = ch & utf8_mask[len];
switch(len)
{
case 5:
if (src >= srcend) goto done; /* ignore partial char */
if ((ch = *src ^ 0x80) >= 0x40) goto bad;
res = (res << 6) | ch;
src++;
case 4:
if (src >= srcend) goto done; /* ignore partial char */
if ((ch = *src ^ 0x80) >= 0x40) goto bad;
res = (res << 6) | ch;
src++;
case 3:
if (src >= srcend) goto done; /* ignore partial char */
if ((ch = *src ^ 0x80) >= 0x40) goto bad;
res = (res << 6) | ch;
src++;
case 2:
if (src >= srcend) goto done; /* ignore partial char */
if ((ch = *src ^ 0x80) >= 0x40) goto bad;
res = (res << 6) | ch;
src++;
case 1:
if (src >= srcend) goto done; /* ignore partial char */
if ((ch = *src ^ 0x80) >= 0x40) goto bad;
res = (res << 6) | ch;
src++;
if (res < utf8_minval[len]) goto bad;
if (res >= 0x10000) goto bad; /* FIXME: maybe we should do surrogates here */
*dst = res;
continue;
}
bad:
if (flags & MB_ERR_INVALID_CHARS) return -2; /* bad char */
*dst = (WCHAR)'?';
}
if (src < srcend) return -1; /* overflow */
done:
return dstlen - count;
}
|
