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
370
371
372
373
374
375
376
377
378
379
380
|
/* Copyright (c) 2008-2018 Dovecot authors, see the included COPYING file */
#include "lib.h"
#include "str.h"
#include "unichar.h"
#include "imap-utf7.h"
static const char imap_b64enc[] =
"ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789+,";
#define XX 0xff
static const unsigned char imap_b64dec[256] = {
XX,XX,XX,XX, XX,XX,XX,XX, XX,XX,XX,XX, XX,XX,XX,XX,
XX,XX,XX,XX, XX,XX,XX,XX, XX,XX,XX,XX, XX,XX,XX,XX,
XX,XX,XX,XX, XX,XX,XX,XX, XX,XX,XX,62, 63,XX,XX,XX,
52,53,54,55, 56,57,58,59, 60,61,XX,XX, XX,XX,XX,XX,
XX, 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,XX, XX,XX,XX,XX,
XX,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,XX, XX,XX,XX,XX,
XX,XX,XX,XX, XX,XX,XX,XX, XX,XX,XX,XX, XX,XX,XX,XX,
XX,XX,XX,XX, XX,XX,XX,XX, XX,XX,XX,XX, XX,XX,XX,XX,
XX,XX,XX,XX, XX,XX,XX,XX, XX,XX,XX,XX, XX,XX,XX,XX,
XX,XX,XX,XX, XX,XX,XX,XX, XX,XX,XX,XX, XX,XX,XX,XX,
XX,XX,XX,XX, XX,XX,XX,XX, XX,XX,XX,XX, XX,XX,XX,XX,
XX,XX,XX,XX, XX,XX,XX,XX, XX,XX,XX,XX, XX,XX,XX,XX,
XX,XX,XX,XX, XX,XX,XX,XX, XX,XX,XX,XX, XX,XX,XX,XX,
XX,XX,XX,XX, XX,XX,XX,XX, XX,XX,XX,XX, XX,XX,XX,XX
};
static void
mbase64_encode(string_t *dest, const unsigned char *in, size_t len)
{
str_append_c(dest, '&');
while (len >= 3) {
str_append_c(dest, imap_b64enc[in[0] >> 2]);
str_append_c(dest, imap_b64enc[((in[0] & 3) << 4) |
(in[1] >> 4)]);
str_append_c(dest, imap_b64enc[((in[1] & 0x0f) << 2) |
((in[2] & 0xc0) >> 6)]);
str_append_c(dest, imap_b64enc[in[2] & 0x3f]);
in += 3;
len -= 3;
}
if (len > 0) {
str_append_c(dest, imap_b64enc[in[0] >> 2]);
if (len == 1)
str_append_c(dest, imap_b64enc[(in[0] & 0x03) << 4]);
else {
str_append_c(dest, imap_b64enc[((in[0] & 0x03) << 4) |
(in[1] >> 4)]);
str_append_c(dest, imap_b64enc[(in[1] & 0x0f) << 2]);
}
}
str_append_c(dest, '-');
}
static const char *
imap_utf8_first_encode_char(const char *str, char escape_char)
{
const char *p;
for (p = str; *p != '\0'; p++) {
if (*p == '&' || *p < 0x20 || *p >= 0x7f || *p == escape_char)
return p;
}
return NULL;
}
int imap_escaped_utf8_hex_to_char(const char *str, unsigned char *chr_r)
{
unsigned int i = 0;
unsigned char c = 0;
/* NOTE: Only lowercase hex characters are allowed so the output is
reversible. */
for (;;) {
if (str[i] >= '0' && str[i] <= '9')
c += str[i] - '0';
else if (str[i] >= 'a' && str[i] <= 'f')
c += str[i] - 'a' + 10;
else
return -1;
if (++i == 2)
break;
c *= 0x10;
}
*chr_r = c;
return 0;
}
static int
imap_utf8_to_utf7_int(const char *src, char escape_char, string_t *dest)
{
const char *p;
unichar_t chr;
uint8_t *utf16, *u;
uint16_t u16;
unsigned char c;
p = imap_utf8_first_encode_char(src, escape_char);
if (p == NULL) {
/* no characters that need to be encoded */
str_append(dest, src);
return 0;
}
/* at least one encoded character */
str_append_data(dest, src, p-src);
utf16 = t_malloc0(MALLOC_MULTIPLY(strlen(p), 2));
while (*p != '\0') {
if (*p == escape_char &&
imap_escaped_utf8_hex_to_char(p+1, &c) == 0) {
str_append_c(dest, c);
p += 3;
continue;
}
if (*p == '&') {
str_append(dest, "&-");
p++;
continue;
}
if (*p >= 0x20 && *p < 0x7f) {
str_append_c(dest, *p);
p++;
continue;
}
u = utf16;
while (*p != '\0' && (*p < 0x20 || *p >= 0x7f)) {
if (uni_utf8_get_char(p, &chr) <= 0)
return -1;
/* @UNSAFE */
if (chr < UTF16_SURROGATE_BASE) {
*u++ = chr >> 8;
*u++ = chr & 0xff;
} else {
u16 = UTF16_SURROGATE_HIGH(chr);
*u++ = u16 >> 8;
*u++ = u16 & 0xff;
u16 = UTF16_SURROGATE_LOW(chr);
*u++ = u16 >> 8;
*u++ = u16 & 0xff;
}
p += uni_utf8_char_bytes((unsigned char)*p);
}
mbase64_encode(dest, utf16, u-utf16);
}
return 0;
}
int imap_utf8_to_utf7(const char *src, string_t *dest)
{
return imap_utf8_to_utf7_int(src, '\0', dest);
}
int imap_escaped_utf8_to_utf7(const char *src, char escape_char, string_t *dest)
{
i_assert(escape_char != '&');
return imap_utf8_to_utf7_int(src, escape_char, dest);
}
int t_imap_utf8_to_utf7(const char *src, const char **dest_r)
{
string_t *str;
int ret;
if (imap_utf8_first_encode_char(src, '\0') == NULL) {
*dest_r = src;
return 0;
}
str = t_str_new(64);
ret = imap_utf8_to_utf7(src, str);
*dest_r = str_c(str);
return ret;
}
static int utf16buf_to_utf8(string_t *dest, const unsigned char output[4],
unsigned int *_pos, unsigned int len)
{
unsigned int pos = *_pos;
uint16_t high, low;
unichar_t chr;
if (len % 2 != 0)
return -1;
high = (output[pos % 4] << 8) | output[(pos+1) % 4];
if (high < UTF16_SURROGATE_HIGH_FIRST ||
high > UTF16_SURROGATE_HIGH_MAX) {
/* single byte */
size_t oldlen = str_len(dest);
if (high == 0) {
/* Encoded NUL isn't going to work in Dovecot code,
even though it's technically valid. Return failure
so the callers don't even get a chance to handle the
NUL in the string inconsistently. */
return -1;
}
uni_ucs4_to_utf8_c(high, dest);
if (str_len(dest) - oldlen == 1) {
unsigned char last = str_data(dest)[oldlen];
if (last >= 0x20 && last < 0x7f)
return -1;
}
*_pos = (pos + 2) % 4;
return 0;
}
if (high > UTF16_SURROGATE_HIGH_LAST)
return -1;
if (len != 4) {
/* missing the second character */
return -1;
}
low = (output[(pos+2)%4] << 8) | output[(pos+3) % 4];
if (low < UTF16_SURROGATE_LOW_FIRST || low > UTF16_SURROGATE_LOW_LAST)
return -1;
chr = UTF16_SURROGATE_BASE +
(((high & UTF16_SURROGATE_MASK) << UTF16_SURROGATE_SHIFT) |
(low & UTF16_SURROGATE_MASK));
uni_ucs4_to_utf8_c(chr, dest);
return 0;
}
static int mbase64_decode_to_utf8(string_t *dest, const char **_src)
{
const char *src = *_src;
unsigned char input[4], output[4];
unsigned int outstart = 0, outpos = 0;
while (*src != '-') {
input[0] = imap_b64dec[(uint8_t)src[0]];
if (input[0] == 0xff)
return -1;
input[1] = imap_b64dec[(uint8_t)src[1]];
if (input[1] == 0xff)
return -1;
output[outpos % 4] = (input[0] << 2) | (input[1] >> 4);
if (++outpos % 4 == outstart) {
if (utf16buf_to_utf8(dest, output, &outstart, 4) < 0)
return -1;
}
input[2] = imap_b64dec[(uint8_t)src[2]];
if (input[2] == 0xff) {
if (src[2] != '-')
return -1;
src += 2;
break;
}
output[outpos % 4] = ((input[1] << 4) & 0xff) | (input[2] >> 2);
if (++outpos % 4 == outstart) {
if (utf16buf_to_utf8(dest, output, &outstart, 4) < 0)
return -1;
}
input[3] = imap_b64dec[(uint8_t)src[3]];
if (input[3] == 0xff) {
if (src[3] != '-')
return -1;
src += 3;
break;
}
output[outpos % 4] = ((input[2] << 6) & 0xc0) | input[3];
if (++outpos % 4 == outstart) {
if (utf16buf_to_utf8(dest, output, &outstart, 4) < 0)
return -1;
}
src += 4;
}
if (outstart != outpos % 4) {
if (utf16buf_to_utf8(dest, output, &outstart,
(4 + outpos - outstart) % 4) < 0)
return -1;
}
/* Found the ending '-'. Make sure it's not followed by unnecessary
shift. Note that '&' is always escaped as "&-" so it's not an
unnecessary shift. */
if (src[1] == '&' && src[2] != '-')
return -1;
*_src = src + 1;
return 0;
}
static int
imap_utf7_to_utf8_int(const char *src, const char *escape_chars, string_t *dest)
{
const char *p;
for (p = src; *p != '\0'; p++) {
if (*p < 0x20 || *p >= 0x7f) {
if (escape_chars[0] == '\0')
return -1;
break;
}
if (*p == '&' || strchr(escape_chars, *p) != NULL)
break;
}
if (*p == '\0') {
/* no IMAP-UTF-7 encoded characters */
str_append(dest, src);
return 0;
}
/* at least one encoded character */
str_append_data(dest, src, p-src);
while (*p != '\0') {
if (strchr(escape_chars, *p) != NULL ||
*p < 0x20 || *p >= 0x7f) {
str_printfa(dest, "%c%02x", escape_chars[0],
(unsigned char)*p);
p++;
} else if (*p == '&') {
if (*++p == '-') {
str_append_c(dest, '&');
p++;
} else {
size_t orig_size = str_len(dest);
if (mbase64_decode_to_utf8(dest, &p) < 0) {
if (escape_chars[0] == '\0')
return -1;
str_truncate(dest, orig_size);
str_printfa(dest, "%c26", escape_chars[0]);
}
}
} else {
str_append_c(dest, *p++);
}
}
return 0;
}
int imap_utf7_to_utf8(const char *src, string_t *dest)
{
return imap_utf7_to_utf8_int(src, "", dest);
}
void imap_utf7_to_utf8_escaped(const char *src, const char *escape_chars,
string_t *dest)
{
i_assert(escape_chars[0] != '&');
if (imap_utf7_to_utf8_int(src, escape_chars, dest) < 0)
i_unreached();
}
bool imap_utf7_is_valid(const char *src)
{
const char *p;
int ret;
for (p = src; *p != '\0'; p++) {
if (*p < 0x20 || *p >= 0x7f)
return FALSE;
if (*p == '&') {
/* slow scan */
T_BEGIN {
string_t *tmp = t_str_new(128);
ret = imap_utf7_to_utf8(p, tmp);
} T_END;
if (ret < 0)
return FALSE;
}
}
return TRUE;
}
|
