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
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
|
/*
* Copyright (C) 1999-2001 Free Software Foundation, Inc.
* This file is part of the GNU LIBICONV Library.
*
* The GNU LIBICONV Library is free software; you can redistribute it
* and/or modify it under the terms of the GNU Library General Public
* License as published by the Free Software Foundation; either version 2
* of the License, or (at your option) any later version.
*
* The GNU LIBICONV 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
* Library General Public License for more details.
*
* You should have received a copy of the GNU Library General Public
* License along with the GNU LIBICONV Library; see the file COPYING.LIB.
* If not, write to the Free Software Foundation, Inc., 59 Temple Place -
* Suite 330, Boston, MA 02111-1307, USA.
*/
/*
* UTF-7
*/
/* Specification: RFC 2152 (and old RFC 1641, RFC 1642) */
/* The original Base64 encoding is defined in RFC 2045. */
/* Set of direct characters:
* A-Z a-z 0-9 ' ( ) , - . / : ? space tab lf cr
*/
static const unsigned char direct_tab[128/8] = {
0x00, 0x26, 0x00, 0x00, 0x81, 0xf3, 0xff, 0x87,
0xfe, 0xff, 0xff, 0x07, 0xfe, 0xff, 0xff, 0x07,
};
#define isdirect(ch) ((ch) < 128 && ((direct_tab[(ch)>>3] >> (ch & 7)) & 1))
/* Set of direct and optional direct characters:
* A-Z a-z 0-9 ' ( ) , - . / : ? space tab lf cr
* ! " # $ % & * ; < = > @ [ ] ^ _ ` { | }
*/
static const unsigned char xdirect_tab[128/8] = {
0x00, 0x26, 0x00, 0x00, 0xff, 0xf7, 0xff, 0xff,
0xff, 0xff, 0xff, 0xef, 0xff, 0xff, 0xff, 0x3f,
};
#define isxdirect(ch) ((ch) < 128 && ((xdirect_tab[(ch)>>3] >> (ch & 7)) & 1))
/* Set of base64 characters, extended:
* A-Z a-z 0-9 + / -
*/
static const unsigned char xbase64_tab[128/8] = {
0x00, 0x00, 0x00, 0x00, 0x00, 0xa8, 0xff, 0x03,
0xfe, 0xff, 0xff, 0x07, 0xfe, 0xff, 0xff, 0x07,
};
#define isxbase64(ch) ((ch) < 128 && ((xbase64_tab[(ch)>>3] >> (ch & 7)) & 1))
/*
* The state is structured as follows:
* bit 1..0: shift
* bit 7..2: data
* Precise meaning:
* shift data
* 0 0 not inside base64 encoding
* 1 0 inside base64, no pending bits
* 2 XXXX00 inside base64, 4 bits remain from 2nd byte
* 3 XX0000 inside base64, 2 bits remain from 3rd byte
*/
static int
utf7_mbtowc (conv_t conv, ucs4_t *pwc, const unsigned char *s, int n)
{
state_t state = conv->istate;
int count = 0; /* number of input bytes already read */
if (state & 3)
goto active;
else
goto inactive;
inactive:
{
/* Here (state & 3) == 0 */
if (n < count+1)
goto none;
{
unsigned char c = *s;
if (isxdirect(c)) {
*pwc = (ucs4_t) c;
conv->istate = state;
return count+1;
}
if (c == '+') {
if (n < count+2)
goto none;
if (s[1] == '-') {
*pwc = (ucs4_t) '+';
conv->istate = state;
return count+2;
}
s++; count++;
state = 1;
goto active;
}
return RET_ILSEQ;
}
}
active:
{
/* base64 encoding active */
unsigned int wc = 0;
state_t base64state = state;
unsigned int kmax = 2; /* number of payload bytes to read */
unsigned int k = 0; /* number of payload bytes already read */
unsigned int base64count = 0; /* number of base64 bytes already read */
for (;;) {
unsigned char c = *s;
unsigned int i;
if (c >= 'A' && c <= 'Z')
i = c-'A';
else if (c >= 'a' && c <= 'z')
i = c-'a'+26;
else if (c >= '0' && c <= '9')
i = c-'0'+52;
else if (c == '+')
i = 62;
else if (c == '/')
i = 63;
else {
/* c terminates base64 encoding */
if (base64state & -4)
return RET_ILSEQ; /* data must be 0, otherwise illegal */
if (base64count)
return RET_ILSEQ; /* partial UTF-16 characters are invalid */
if (c == '-') {
s++; count++;
}
state = 0;
goto inactive;
}
s++; base64count++;
/* read 6 bits: 0 <= i < 64 */
switch (base64state & 3) {
case 1: /* inside base64, no pending bits */
base64state = (i << 2) | 0; break;
case 0: /* inside base64, 6 bits remain from 1st byte */
wc = (wc << 8) | (base64state & -4) | (i >> 4); k++;
base64state = ((i & 15) << 4) | 2; break;
case 2: /* inside base64, 4 bits remain from 2nd byte */
wc = (wc << 8) | (base64state & -4) | (i >> 2); k++;
base64state = ((i & 3) << 6) | 3; break;
case 3: /* inside base64, 2 bits remain from 3rd byte */
wc = (wc << 8) | (base64state & -4) | i; k++;
base64state = 1; break;
}
if (k == kmax) {
/* UTF-16: When we see a High Surrogate, we must also decode
the following Low Surrogate. */
if (kmax == 2 && (wc >= 0xd800 && wc < 0xdc00))
kmax = 4;
else
break;
}
if (n < count+base64count+1)
goto none;
}
/* Here k = kmax > 0, hence base64count > 0. */
if ((base64state & 3) == 0) abort();
if (kmax == 4) {
ucs4_t wc1 = wc >> 16;
ucs4_t wc2 = wc & 0xffff;
if (!(wc1 >= 0xd800 && wc1 < 0xdc00)) abort();
if (!(wc2 >= 0xdc00 && wc2 < 0xe000)) return RET_ILSEQ;
*pwc = 0x10000 + ((wc1 - 0xd800) << 10) + (wc2 - 0xdc00);
} else {
*pwc = wc;
}
conv->istate = base64state;
return count+base64count;
}
none:
conv->istate = state;
return RET_TOOFEW(count);
}
/*
* The state is structured as follows:
* bit 1..0: shift
* bit 7..2: data
* Precise meaning:
* shift data
* 0 0 not inside base64 encoding
* 1 0 inside base64, no pending bits
* 2 XX00 inside base64, 2 bits known for 2nd byte
* 3 XXXX inside base64, 4 bits known for 3rd byte
*/
/* Define this to 1 if you want the so-called "optional direct" characters
! " # $ % & * ; < = > @ [ ] ^ _ ` { | }
to be encoded. Define to 0 if you want them to be passed straight through,
like the so-called "direct" characters.
We set this to 1 because it's safer.
*/
#define UTF7_ENCODE_OPTIONAL_CHARS 1
static int
utf7_wctomb (conv_t conv, unsigned char *r, ucs4_t iwc, int n)
{
state_t state = conv->ostate;
unsigned int wc = iwc;
int count = 0;
if (state & 3)
goto active;
/*inactive:*/
{
if (UTF7_ENCODE_OPTIONAL_CHARS ? isdirect(wc) : isxdirect(wc)) {
r[0] = (unsigned char) wc;
/*conv->ostate = state;*/
return 1;
} else {
*r++ = '+';
if (wc == '+') {
if (n < 2)
return RET_TOOSMALL;
*r = '-';
/*conv->ostate = state;*/
return 2;
}
count = 1;
state = 1;
goto active;
}
}
active:
{
/* base64 encoding active */
if (UTF7_ENCODE_OPTIONAL_CHARS ? isdirect(wc) : isxdirect(wc)) {
/* deactivate base64 encoding */
count += ((state & 3) >= 2 ? 1 : 0) + (isxbase64(wc) ? 1 : 0) + 1;
if (n < count)
return RET_TOOSMALL;
if ((state & 3) >= 2) {
unsigned int i = state & -4;
unsigned char c;
if (i < 26)
c = i+'A';
else if (i < 52)
c = i-26+'a';
else if (i < 62)
c = i-52+'0';
else if (i == 62)
c = '+';
else if (i == 63)
c = '/';
else
abort();
*r++ = c;
}
if (isxbase64(wc))
*r++ = '-';
state = 0;
*r++ = (unsigned char) wc;
conv->ostate = state;
return count;
} else {
unsigned int k; /* number of payload bytes to write */
if (wc < 0x10000) {
k = 2;
count += ((state & 3) >= 2 ? 3 : 2);
} else if (wc < 0x110000) {
unsigned int wc1 = 0xd800 + ((wc - 0x10000) >> 10);
unsigned int wc2 = 0xdc00 + ((wc - 0x10000) & 0x3ff);
wc = (wc1 << 16) | wc2;
k = 4;
count += ((state & 3) >= 3 ? 6 : 5);
} else
return RET_ILUNI;
if (n < count)
return RET_TOOSMALL;
for (;;) {
unsigned int i;
unsigned char c;
switch (state & 3) {
case 0: /* inside base64, 6 bits known for 4th byte */
c = (state & -4) >> 2; state = 1; break;
case 1: /* inside base64, no pending bits */
i = (wc >> (8 * --k)) & 0xff;
c = i >> 2; state = ((i & 3) << 4) | 2; break;
case 2: /* inside base64, 2 bits known for 2nd byte */
i = (wc >> (8 * --k)) & 0xff;
c = (state & -4) | (i >> 4); state = ((i & 15) << 2) | 3; break;
case 3: /* inside base64, 4 bits known for 3rd byte */
i = (wc >> (8 * --k)) & 0xff;
c = (state & -4) | (i >> 6); state = ((i & 63) << 2) | 0; break;
default: abort(); /* stupid gcc */
}
if (c < 26)
c = c+'A';
else if (c < 52)
c = c-26+'a';
else if (c < 62)
c = c-52+'0';
else if (c == 62)
c = '+';
else if (c == 63)
c = '/';
else
abort();
*r++ = c;
if ((state & 3) && (k == 0))
break;
}
conv->ostate = state;
return count;
}
}
}
static int
utf7_reset (conv_t conv, unsigned char *r, int n)
{
state_t state = conv->ostate;
if (state & 3) {
/* deactivate base64 encoding */
unsigned int count = ((state & 3) >= 2 ? 1 : 0) + 1;
if (n < count)
return RET_TOOSMALL;
if ((state & 3) >= 2) {
unsigned int i = state & -4;
unsigned char c;
if (i < 26)
c = i+'A';
else if (i < 52)
c = i-26+'a';
else if (i < 62)
c = i-52+'0';
else if (i == 62)
c = '+';
else if (i == 63)
c = '/';
else
abort();
*r++ = c;
}
*r++ = '-';
/* conv->ostate = 0; will be done by the caller */
return count;
} else
return 0;
}
|