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
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
|
/*
* CDDL HEADER START
*
* The contents of this file are subject to the terms of the
* Common Development and Distribution License (the "License").
* You may not use this file except in compliance with the License.
*
* You can obtain a copy of the license at src/OPENSOLARIS.LICENSE
* or http://www.opensolaris.org/os/licensing.
* See the License for the specific language governing permissions
* and limitations under the License.
*
* When distributing Covered Code, include this CDDL HEADER in each
* file and include the License file at src/OPENSOLARIS.LICENSE.
* If applicable, add the following below this CDDL HEADER, with the
* fields enclosed by brackets "[]" replaced with your own identifying
* information: Portions Copyright [yyyy] [name of copyright owner]
*
* CDDL HEADER END
*/
/*
* Copyright(c) 1998 Sun Microsystems, Inc.
* All rights reserved.
*/
#include <stdio.h>
#include <stdlib.h>
#include <errno.h>
#include <sys/types.h>
#include <sys/isa_defs.h>
#include <gb2312_unicode.h>
#include "common_defs.h"
#define MSB 0x80
#define UTF8_NON_ID_CHAR1 0xEF
#define UTF8_NON_ID_CHAR2 0xBF
#define UTF8_NON_ID_CHAR3 0xBD
#define EUC_BYTE1_LOWER 0xA1
#define EUC_BYTE1_UPPER 0xFE
#define EUC_BYTE2_LOWER EUC_BYTE1_LOWER
#define EUC_BYTE2_UPPER EUC_BYTE1_UPPER
#define UCHAR unsigned char
typedef struct _icv_state {
char _lastc;
short _gstate;
boolean little_endian;
boolean bom_written;
} _iconv_st;
enum _GSTATE { G0, G1 };
static int is_valid_gb2312(UCHAR, UCHAR);
int
gb_to_unicode(_iconv_st *st, char in_byte2, char *buf, int buflen, int *uconv_num);
/*
* Open; called from iconv_open()
*/
void *
_icv_open()
{
_iconv_st *st;
if ((st = (_iconv_st *)malloc(sizeof(_iconv_st))) == NULL) {
errno = ENOMEM;
return ((void *) -1);
}
st->_gstate = G0;
st->little_endian = false;
st->bom_written = false;
#if defined(UCS_2LE)
st->little_endian = true;
st->bom_written = true;
#endif
return ((void *)st);
}
/*
* Close; called from iconv_close()
*/
void
_icv_close(_iconv_st *st)
{
if (st == NULL)
errno = EBADF;
else
free(st);
}
/*
* Actual conversion; called from iconv()
*/
size_t
_icv_iconv(_iconv_st *st, char **inbuf, size_t*inbytesleft,
char **outbuf, size_t*outbytesleft)
{
int n;
int uconv_num = 0;
if (st == NULL) {
errno = EBADF;
return (size_t)-1;
}
if (inbuf == NULL || *inbuf == NULL) { /* Reset request. */
st->_gstate = G0;
return (size_t)0;
}
errno = 0;
while (*inbytesleft > 0 && *outbytesleft > 0) {
switch (st->_gstate) {
case G0:
if ( **inbuf & MSB ) {
st->_lastc = **inbuf;
st->_gstate = G1;
} else { /* ASCII */
/*
* code conversion for UCS-2LE to support Samba
*/
if (st->little_endian) {
if (!st->bom_written) {
if (*outbytesleft < 4)
errno = E2BIG;
else {
*(*outbuf)++ = (uchar_t)0xff;
*(*outbuf)++ = (uchar_t)0xfe;
st->bom_written = true;
*outbytesleft -= 2;
}
}
if (*outbytesleft < 2)
errno = E2BIG;
else {
*(*outbuf)++ = **inbuf;
*(*outbuf)++ = (uchar_t)0x0;
*outbytesleft -= 2;
}
} else {
**outbuf = **inbuf;
(*outbuf)++, (*outbytesleft)--;
}
}
break;
case G1:
if (**inbuf & MSB ) {
int uconv_num_internal = 0;
/* bugfix - 4669831 iconv from zh_CN.euc to UTF-8 dumps core on Intel. */
if ( !is_valid_gb2312((UCHAR)st->_lastc, (UCHAR)**inbuf))
{
errno = EILSEQ;
break;
}
n = gb_to_unicode(st, **inbuf, *outbuf,
*outbytesleft, &uconv_num_internal);
if (n > 0) {
(*outbuf) += n, (*outbytesleft) -= n;
uconv_num += uconv_num_internal;
st->_gstate = G0;
} else {
errno = E2BIG;
}
} else {
errno = EILSEQ;
}
break;
}
if (errno) break;
(*inbuf)++, (*inbytesleft)--;
}
if (*inbytesleft == 0 && st->_gstate != G0)
errno = EINVAL;
if (*inbytesleft > 0 && *outbytesleft == 0)
errno = E2BIG;
if (errno) {
/*
* if error, *inbuf points to the byte following the last byte
* successfully used in the conversion.
*/
*inbuf -= (st->_gstate - G0);
*inbytesleft += (st->_gstate - G0);
st->_gstate = G0;
return ((size_t) -1);
}
return uconv_num;
}
static int
is_valid_gb2312(UCHAR byte1, UCHAR byte2)
{
if ( (byte1 < EUC_BYTE1_LOWER || byte1 > EUC_BYTE1_UPPER) ||
(byte2 < EUC_BYTE2_LOWER || byte2 > EUC_BYTE2_UPPER) ) {
return 0;
}
return 1;
}
/*
* return: > 0 - converted with enough space
* = 0 - no space in outbuf
*/
int
gb_to_unicode(st, in_byte2, buf, buflen, uconv_num)
_iconv_st *st;
char in_byte2;
char *buf;
int buflen;
int *uconv_num;
{
int idx;
int unicode;
char in_byte1 = st->_lastc;
idx = (((in_byte1 & 0xff) - 0xa1) * 94) + (in_byte2 & 0xff) - 0xa1;
/*
* code conversion for UCS-2LE to support samba in Solaris
*/
if (st->little_endian) {
int size = 0;
if (idx < 0 || idx >= GBMAX) {
unicode = ICV_CHAR_UCS2_REPLACEMENT;
*uconv_num = 1;
} else
unicode = Unicode[idx];
if (!st->bom_written) {
if (buflen < 4)
return 0;
*(buf + size++) = (uchar_t)0xff;
*(buf + size++) = (uchar_t)0xfe;
st->bom_written = true;
}
if (buflen < 2)
return 0;
*(buf + size++) = (uchar_t)(unicode & 0xff);
*(buf + size++) = (uchar_t)((unicode >> 8) & 0xff);
return size;
}
/* bugfix - 4669831 iconv from zh_CN.euc to UTF-8 dumps core on Intel. */
if (idx >= 0 && idx < GBMAX ) {
unicode = Unicode[idx];
if (unicode >= 0x0080 && unicode <= 0x07ff) {
if ( buflen < 2 )
return 0;
*buf = ((unicode >> 6) & 0x1f) | 0xc0;
*(buf+1) = (unicode & 0x3f) | MSB;
return 2;
}
if (unicode >= 0x0800 && unicode <= 0xffff) {
if ( buflen < 3 )
return 0;
*buf = ((unicode >> 12) & 0x0f) | 0xe0;
*(buf+1) = ((unicode >> 6) & 0x3f) | MSB;
*(buf+2) = (unicode & 0x3f) | MSB;
return 3;
}
}
if ( buflen < 3 )
return 0;
*buf = UTF8_NON_ID_CHAR1;
*(buf+1) = UTF8_NON_ID_CHAR2;
*(buf+2) = UTF8_NON_ID_CHAR3;
/* non-identical conversion */
*uconv_num = 1;
return 3;
}
|