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
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
|
/*
* Copyright (C) 2000,2003 Edmund Grimley Evans <edmundo@rano.org>
*
* This program is free software; you can redistribute it and/or modify
* it under the terms of the GNU General Public License as published by
* the Free Software Foundation; either version 2 of the License, or
* (at your option) any later version.
*
* This program 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 General Public License for more details.
*
* You should have received a copy of the GNU General Public License
* along with this program; if not, write to the Free Software
* Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301, USA.
*/
/* This file converts between modified UTF-7 and UTF-8.
* Modified UTF-7 is described in RFC 3501 section 5.1.3.
* Regular UTF-7 is decribed in RFC 2152.
*
* In modified UTF-7:
* - printable ascii 0x20-0x25 and 0x27-0x7e represents itself.
* - "&" (0x26) is represented by the two-octet sequence "&-"
* - other values use the UTF-16 representation of the code point
* and encode it using a modified version of BASE64.
* - BASE64 mode is enabled by "&" and disabled by "-".
*
* Note that UTF-16:
* - Represents U+0000-U+D7FF and U+E000-U+FFFF directly as the binary
* 2-byte value.
* - Reserves U+D800-U+DFFF (so they aren't valid code points.)
* - Values above U+FFFF need to be encoded using a surrogate pair of
* two 16-bit values:
* - subtract 0x10000 from the code point
* - take the top 10 bits and add 0xd800 to get the first (high) pair.
* - take the bottom 10 bits and add 0xdc00 for the second (low) pair.
*/
#if HAVE_CONFIG_H
# include "config.h"
#endif
#include "mutt.h"
#include "charset.h"
#include "imap_private.h"
static const int Index_64[128] = {
-1,-1,-1,-1, -1,-1,-1,-1, -1,-1,-1,-1, -1,-1,-1,-1,
-1,-1,-1,-1, -1,-1,-1,-1, -1,-1,-1,-1, -1,-1,-1,-1,
-1,-1,-1,-1, -1,-1,-1,-1, -1,-1,-1,62, 63,-1,-1,-1,
52,53,54,55, 56,57,58,59, 60,61,-1,-1, -1,-1,-1,-1,
-1, 0, 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,-1, -1,-1,-1,-1,
-1,26,27,28, 29,30,31,32, 33,34,35,36, 37,38,39,40,
41,42,43,44, 45,46,47,48, 49,50,51,-1, -1,-1,-1,-1
};
static const char B64Chars[64] = {
'A', 'B', 'C', 'D', 'E', 'F', 'G', 'H', 'I', 'J', 'K', 'L', 'M', 'N', 'O',
'P', 'Q', 'R', 'S', 'T', 'U', 'V', 'W', 'X', 'Y', 'Z', 'a', 'b', 'c', 'd',
'e', 'f', 'g', 'h', 'i', 'j', 'k', 'l', 'm', 'n', 'o', 'p', 'q', 'r', 's',
't', 'u', 'v', 'w', 'x', 'y', 'z', '0', '1', '2', '3', '4', '5', '6', '7',
'8', '9', '+', ','
};
/*
* Convert the data (u7,u7len) from RFC 2060's UTF-7 to UTF-8.
* The result is null-terminated and returned, and also stored
* in (*u8,*u8len) if u8 or u8len is non-zero.
* If input data is invalid, return 0 and don't store anything.
* RFC 2060 obviously intends the encoding to be unique (see
* point 5 in section 5.1.3), so we reject any non-canonical
* form, such as &ACY- (instead of &-) or &AMA-&AMA- (instead
* of &AMAAwA-).
*/
static char *utf7_to_utf8 (const char *u7, size_t u7len, char **u8,
size_t *u8len)
{
char *buf, *p;
int b, ch, k;
int pair1 = 0;
p = buf = safe_malloc (u7len + u7len / 8 + 1);
for (; u7len; u7++, u7len--)
{
if (*u7 == '&')
{
u7++, u7len--;
if (u7len && *u7 == '-')
{
*p++ = '&';
continue;
}
ch = 0;
k = 10;
for (; u7len; u7++, u7len--)
{
if ((*u7 & 0x80) || (b = Index_64[(int)*u7]) == -1)
break;
if (k > 0)
{
ch |= b << k;
k -= 6;
}
else
{
ch |= b >> (-k);
if (ch < 0x80)
{
if (0x20 <= ch && ch < 0x7f)
/* Printable US-ASCII */
goto bail;
*p++ = ch;
}
else if (ch < 0x800)
{
*p++ = 0xc0 | (ch >> 6);
*p++ = 0x80 | (ch & 0x3f);
}
else
{
/* High surrogate pair */
if ((ch & ~0x3ff) == 0xd800)
{
if (pair1)
goto bail;
pair1 = ch;
}
else
{
/* Low surrogate pair */
if ((ch & ~0x3ff) == 0xdc00)
{
if (!pair1)
goto bail;
ch = ((pair1 - 0xd800) << 10) + (ch - 0xdc00) + 0x10000;
pair1 = 0;
}
if (pair1)
goto bail;
if (ch < 0x10000)
{
*p++ = 0xe0 | (ch >> 12);
*p++ = 0x80 | ((ch >> 6) & 0x3f);
*p++ = 0x80 | (ch & 0x3f);
}
else
{
*p++ = 0xf0 | (ch >> 18);
*p++ = 0x80 | ((ch >> 12) & 0x3f);
*p++ = 0x80 | ((ch >> 6) & 0x3f);
*p++ = 0x80 | (ch & 0x3f);
}
}
}
ch = (b << (16 + k)) & 0xffff;
k += 10;
}
}
if (ch || k < 6)
/* Non-zero or too many extra bits */
goto bail;
if (!u7len || *u7 != '-')
/* BASE64 not properly terminated */
goto bail;
if (u7len > 2 && u7[1] == '&' && u7[2] != '-')
/* Adjacent BASE64 sections */
goto bail;
}
else if (*u7 < 0x20 || *u7 >= 0x7f)
/* Not printable US-ASCII */
goto bail;
else
*p++ = *u7;
}
*p++ = '\0';
if (u8len)
*u8len = p - buf;
safe_realloc (&buf, p - buf);
if (u8)
*u8 = buf;
return buf;
bail:
FREE (&buf);
return 0;
}
/*
* Convert the data (u8,u8len) from UTF-8 to RFC 2060's UTF-7.
* The result is null-terminated and returned, and also stored
* in (*u7,*u7len) if u7 or u7len is non-zero.
* Unicode characters above U+FFFF converted to a UTF-16 surrogate pair.
* If input data is invalid, return 0 and don't store anything.
*/
static char *utf8_to_utf7 (const char *u8, size_t u8len, char **u7,
size_t *u7len)
{
char *buf, *p;
int ch;
int n, i, b = 0, k = 0;
int base64 = 0;
/*
* In the worst case we convert 2 chars to 7 chars. For example:
* "\x10&\x10&..." -> "&ABA-&-&ABA-&-...".
*/
p = buf = safe_malloc ((u8len / 2) * 7 + 6);
while
|