jcs.org
mutt stable branch with some hacks
1/*
2 * Copyright (C) 2000,2003 Edmund Grimley Evans <edmundo@rano.org>
3 *
4 * This program is free software; you can redistribute it and/or modify
5 * it under the terms of the GNU General Public License as published by
6 * the Free Software Foundation; either version 2 of the License, or
7 * (at your option) any later version.
8 *
9 * This program is distributed in the hope that it will be useful,
10 * but WITHOUT ANY WARRANTY; without even the implied warranty of
11 * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
12 * GNU General Public License for more details.
13 *
14 * You should have received a copy of the GNU General Public License
15 * along with this program; if not, write to the Free Software
16 * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301, USA.
17 */
18
19#if HAVE_CONFIG_H
20# include "config.h"
21#endif
22
23#include "mutt.h"
24#include "charset.h"
25#include "imap_private.h"
26
27static const int Index_64[128] = {
28 -1,-1,-1,-1, -1,-1,-1,-1, -1,-1,-1,-1, -1,-1,-1,-1,
29 -1,-1,-1,-1, -1,-1,-1,-1, -1,-1,-1,-1, -1,-1,-1,-1,
30 -1,-1,-1,-1, -1,-1,-1,-1, -1,-1,-1,62, 63,-1,-1,-1,
31 52,53,54,55, 56,57,58,59, 60,61,-1,-1, -1,-1,-1,-1,
32 -1, 0, 1, 2, 3, 4, 5, 6, 7, 8, 9,10, 11,12,13,14,
33 15,16,17,18, 19,20,21,22, 23,24,25,-1, -1,-1,-1,-1,
34 -1,26,27,28, 29,30,31,32, 33,34,35,36, 37,38,39,40,
35 41,42,43,44, 45,46,47,48, 49,50,51,-1, -1,-1,-1,-1
36};
37
38static const char B64Chars[64] = {
39 'A', 'B', 'C', 'D', 'E', 'F', 'G', 'H', 'I', 'J', 'K', 'L', 'M', 'N', 'O',
40 'P', 'Q', 'R', 'S', 'T', 'U', 'V', 'W', 'X', 'Y', 'Z', 'a', 'b', 'c', 'd',
41 'e', 'f', 'g', 'h', 'i', 'j', 'k', 'l', 'm', 'n', 'o', 'p', 'q', 'r', 's',
42 't', 'u', 'v', 'w', 'x', 'y', 'z', '0', '1', '2', '3', '4', '5', '6', '7',
43 '8', '9', '+', ','
44};
45
46/*
47 * Convert the data (u7,u7len) from RFC 2060's UTF-7 to UTF-8.
48 * The result is null-terminated and returned, and also stored
49 * in (*u8,*u8len) if u8 or u8len is non-zero.
50 * If input data is invalid, return 0 and don't store anything.
51 * RFC 2060 obviously intends the encoding to be unique (see
52 * point 5 in section 5.1.3), so we reject any non-canonical
53 * form, such as &ACY- (instead of &-) or &AMA-&AMA- (instead
54 * of &AMAAwA-).
55 */
56static char *utf7_to_utf8 (const char *u7, size_t u7len, char **u8,
57 size_t *u8len)
58{
59 char *buf, *p;
60 int b, ch, k;
61
62 p = buf = safe_malloc (u7len + u7len / 8 + 1);
63
64 for (; u7len; u7++, u7len--)
65 {
66 if (*u7 == '&')
67 {
68 u7++, u7len--;
69
70 if (u7len && *u7 == '-')
71 {
72 *p++ = '&';
73 continue;
74 }
75
76 ch = 0;
77 k = 10;
78 for (; u7len; u7++, u7len--)
79 {
80 if ((*u7 & 0x80) || (b = Index_64[(int)*u7]) == -1)
81 break;
82 if (k > 0)
83 {
84 ch |= b << k;
85 k -= 6;
86 }
87 else
88 {
89 ch |= b >> (-k);
90 if (ch < 0x80)
91 {
92 if (0x20 <= ch && ch < 0x7f)
93 /* Printable US-ASCII */
94 goto bail;
95 *p++ = ch;
96 }
97 else if (ch < 0x800)
98 {
99 *p++ = 0xc0 | (ch >> 6);
100 *p++ = 0x80 | (ch & 0x3f);
101 }
102 else
103 {
104 *p++ = 0xe0 | (ch >> 12);
105 *p++ = 0x80 | ((ch >> 6) & 0x3f);
106 *p++ = 0x80 | (ch & 0x3f);
107 }
108 ch = (b << (16 + k)) & 0xffff;
109 k += 10;
110 }
111 }
112 if (ch || k < 6)
113 /* Non-zero or too many extra bits */
114 goto bail;
115 if (!u7len || *u7 != '-')
116 /* BASE64 not properly terminated */
117 goto bail;
118 if (u7len > 2 && u7[1] == '&' && u7[2] != '-')
119 /* Adjacent BASE64 sections */
120 goto bail;
121 }
122 else if (*u7 < 0x20 || *u7 >= 0x7f)
123 /* Not printable US-ASCII */
124 goto bail;
125 else
126 *p++ = *u7;
127 }
128 *p++ = '\0';
129 if (u8len)
130 *u8len = p - buf;
131
132 safe_realloc (&buf, p - buf);
133 if (u8)
134 *u8 = buf;
135 return buf;
136
137bail:
138 FREE (&buf);
139 return 0;
140}
141
142/*
143 * Convert the data (u8,u8len) from UTF-8 to RFC 2060's UTF-7.
144 * The result is null-terminated and returned, and also stored
145 * in (*u7,*u7len) if u7 or u7len is non-zero.
146 * Unicode characters above U+FFFF are replaced by U+FFFE.
147 * If input data is invalid, return 0 and don't store anything.
148 */
149static char *utf8_to_utf7 (const char *u8, size_t u8len, char **u7,
150 size_t *u7len)
151{
152 char *buf, *p;
153 int ch;
154 int n, i, b = 0, k = 0;
155 int base64 = 0;
156
157 /*
158 * In the worst case we convert 2 chars to 7 chars. For example:
159 * "\x10&\x10&..." -> "&ABA-&-&ABA-&-...".
160 */
161 p = buf = safe_malloc ((u8len / 2) * 7 + 6);
162
163 while (u8len)
164 {
165 unsigned char c = *u8;
166
167 if (c < 0x80)
168 ch = c, n = 0;
169 else if (c < 0xc2)
170 goto bail;
171 else if (c < 0xe0)
172 ch = c & 0x1f, n = 1;
173 else if (c < 0xf0)
174 ch = c & 0x0f, n = 2;
175 else if (c < 0xf8)
176 ch = c & 0x07, n = 3;
177 else if (c < 0xfc)
178 ch = c & 0x03, n = 4;
179 else if (c < 0xfe)
180 ch = c & 0x01, n = 5;
181 else
182 goto bail;
183
184 u8++, u8len--;
185 if (n > u8len)
186 goto bail;
187 for (i = 0; i < n; i++)
188 {
189 if ((u8[i] & 0xc0) != 0x80)
190 goto bail;
191 ch = (ch << 6) | (u8[i] & 0x3f);
192 }
193 if (n > 1 && !(ch >> (n * 5 + 1)))
194 goto bail;
195 u8 += n, u8len -= n;
196
197 if (ch < 0x20 || ch >= 0x7f)
198 {
199 if (!base64)
200 {
201 *p++ = '&';
202 base64 = 1;
203 b = 0;
204 k = 10;
205 }
206 if (ch & ~0xffff)
207 ch = 0xfffe;
208 *p++ = B64Chars[b | ch >> k];
209 k -= 6;
210 for (; k >= 0; k -= 6)
211 *p++ = B64Chars[(ch >> k) & 0x3f];
212 b = (ch << (-k)) & 0x3f;
213 k += 16;
214 }
215 else
216 {
217 if (base64)
218 {
219 if (k > 10)
220 *p++ = B64Chars[b];
221 *p++ = '-';
222 base64 = 0;
223 }
224 *p++ = ch;
225 if (ch == '&')
226 *p++ = '-';
227 }
228 }
229
230 if (u8len)
231 {
232 FREE (&buf);
233 return 0;
234 }
235
236 if (base64)
237 {
238 if (k > 10)
239 *p++ = B64Chars[b];
240 *p++ = '-';
241 }
242
243 *p++ = '\0';
244 if (u7len)
245 *u7len = p - buf;
246 safe_realloc (&buf, p - buf);
247 if (u7) *u7 = buf;
248 return buf;
249
250bail:
251 FREE (&buf);
252 return 0;
253}
254
255void imap_utf_encode (IMAP_DATA *idata, char **s)
256{
257 if (Charset)
258 {
259 char *t = safe_strdup (*s);
260 if (t && !mutt_convert_string (&t, Charset, "utf-8", 0))
261 {
262 FREE (s); /* __FREE_CHECKED__ */
263 if (idata->unicode)
264 *s = safe_strdup (t);
265 else
266 *s = utf8_to_utf7 (t, strlen (t), NULL, 0);
267 }
268 FREE (&t);
269 }
270}
271
272void imap_utf_decode (IMAP_DATA *idata, char **s)
273{
274 char *t;
275
276 if (Charset)
277 {
278 if (idata->unicode)
279 t = safe_strdup (*s);
280 else
281 t = utf7_to_utf8 (*s, strlen (*s), 0, 0);
282
283 if (t && !mutt_convert_string (&t, "utf-8", Charset, 0))
284 {
285 FREE (s); /* __FREE_CHECKED__ */
286 *s = t;
287 }
288 else
289 FREE (&t);
290 }
291}