filter_trans.c
15.4 KB
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
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
649
650
651
652
653
654
655
656
657
658
659
660
661
662
663
664
665
666
667
668
669
670
671
672
673
674
675
676
677
678
679
680
681
682
683
684
685
686
687
688
689
690
691
692
693
694
695
696
697
698
699
700
701
702
703
704
705
706
707
708
709
710
711
712
713
714
715
716
717
718
719
720
721
722
723
724
725
726
727
728
729
730
731
732
733
734
735
736
737
738
739
740
741
742
743
744
745
746
747
748
749
750
751
/* GNU Mailutils -- a suite of utilities for electronic mail
Copyright (C) 1999, 2000, 2001, 2004, 2005 Free Software Foundation, Inc.
This library is free software; you can redistribute it and/or
modify it under the terms of the GNU Lesser General Public
License as published by the Free Software Foundation; either
version 2 of the License, or (at your option) any later version.
This 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
Lesser General Public License for more details.
You should have received a copy of the GNU Lesser General
Public License along with this library; if not, write to the
Free Software Foundation, Inc., 51 Franklin Street, Fifth Floor,
Boston, MA 02110-1301 USA */
/* Notes:
First Draft: Dave Inglis.
*/
#ifdef HAVE_CONFIG_H
# include <config.h>
#endif
#include <errno.h>
#include <stdio.h>
#include <stdlib.h>
#include <string.h>
#include <mailutils/stream.h>
#include <mailutils/errno.h>
#include <filter0.h>
#define MU_TRANS_DECODE 1
#define MU_TRANS_ENCODE 2
#define MU_TRANS_BSIZE 2048
/* General-purpose implementation */
struct _trans_stream
{
int t_offset; /* Orignal stream offset. */
size_t min_size;
int s_offset;
char *s_buf; /* Used when read if not big enough to handle min_size
for decoder/encoder */
int offset; /* Current stream offset */
int line_len;
int w_rhd; /* Working buffer read ahead */
int w_whd; /* Working buffer write ahead */
char w_buf[MU_TRANS_BSIZE]; /* working source/dest buffer */
int (*transcoder) (const char *iptr, size_t isize, char *optr,
size_t osize, size_t *nbytes, int *line_len);
};
static void
trans_destroy (filter_t filter)
{
struct _trans_stream *ts = filter->data;
if (ts->s_buf)
free (ts->s_buf);
free (ts);
}
static int
trans_read (filter_t filter, char *optr, size_t osize, off_t offset,
size_t *n_bytes)
{
struct _trans_stream *ts = filter->data;
size_t obytes, wbytes = 0;
int ret = 0, i;
size_t bytes, *nbytes = &bytes;
if (optr == NULL)
return MU_ERR_OUT_NULL;
if (osize == 0)
return EINVAL;
if (n_bytes)
nbytes = n_bytes;
*nbytes = 0;
if (offset && ts->t_offset != offset)
return ESPIPE;
if (offset == 0)
ts->s_offset = ts->t_offset = ts->w_whd = ts->w_rhd =
ts->offset = ts->line_len = 0;
while (*nbytes < osize)
{
if ((ts->w_rhd + (int)ts->min_size) >= ts->w_whd)
{
memmove (ts->w_buf, ts->w_buf + ts->w_rhd, ts->w_whd - ts->w_rhd);
ts->w_whd = ts->w_whd - ts->w_rhd;
ts->w_rhd = 0;
ret = stream_read (filter->stream, ts->w_buf + ts->w_whd,
MU_TRANS_BSIZE - ts->w_whd, ts->offset,
&wbytes );
if (ret != 0)
break;
ts->offset += wbytes;
ts->w_whd += wbytes;
}
if ((osize - *nbytes) >= ts->min_size
&& ts->s_offset == 0
&& ts->w_whd - ts->w_rhd)
{
ts->w_rhd += ts->transcoder (ts->w_buf + ts->w_rhd,
ts->w_whd - ts->w_rhd,
optr + *nbytes, osize - *nbytes,
&obytes, &ts->line_len);
if (ts->w_rhd > ts->w_whd) /* over shot due to padding */
ts->w_rhd = ts->w_whd;
*nbytes += obytes;
ts->t_offset += obytes;
}
else
{
if (ts->s_offset == 0 && ts->w_whd - ts->w_rhd)
{
ts->w_rhd += ts->transcoder (ts->w_buf + ts->w_rhd,
ts->w_whd - ts->w_rhd, ts->s_buf,
ts->min_size, &obytes,
&ts->line_len);
if (ts->w_rhd > ts->w_whd) /* over shot due to padding */
ts->w_rhd = ts->w_whd;
ts->s_offset = obytes;
}
for (i = ts->s_offset; i > 0; i--)
{
optr[(*nbytes)++] = ts->s_buf[ts->s_offset - i];
ts->t_offset++;
if (*nbytes >= osize)
{
i--;
memmove (ts->s_buf, &ts->s_buf[ts->s_offset - i], i);
break;
}
}
ts->s_offset = i;
}
if (wbytes == 0 && ts->s_offset == 0)
break;
}
return ret;
}
/*------------------------------------------------------
* quoted-printable decoder/encoder
*------------------------------------------------------*/
static const char _hexdigits[] = "0123456789ABCDEF";
#define QP_LINE_MAX 76
#define ISWS(c) ((c)==' ' || (c)=='\t')
static int
qp_decode (const char *iptr, size_t isize, char *optr, size_t osize,
size_t *nbytes, int *line_len ARG_UNUSED)
{
char c;
int last_char = 0;
size_t consumed = 0;
size_t wscount = 0;
*nbytes = 0;
while (consumed < isize && *nbytes < osize)
{
c = *iptr++;
if (ISWS (c))
{
wscount++;
consumed++;
}
else
{
/* Octets with values of 9 and 32 MAY be
represented as US-ASCII TAB (HT) and SPACE characters,
respectively, but MUST NOT be so represented at the end
of an encoded line. Any TAB (HT) or SPACE characters
on an encoded line MUST thus be followed on that line
by a printable character. */
if (wscount)
{
if (c != '\r' && c != '\n')
{
size_t sz;
if (consumed >= isize)
break;
if (*nbytes + wscount > osize)
sz = osize - *nbytes;
else
sz = wscount;
memcpy (optr, iptr - wscount - 1, sz);
optr += sz;
(*nbytes) += sz;
if (wscount > sz)
{
wscount -= sz;
break;
}
}
wscount = 0;
if (*nbytes == osize)
break;
}
if (c == '=')
{
/* There must be 2 more characters before I consume this. */
if (consumed + 2 >= isize)
break;
else
{
/* you get =XX where XX are hex characters. */
char chr[3];
int new_c;
chr[2] = 0;
chr[0] = *iptr++;
/* Ignore LF. */
if (chr[0] != '\n')
{
chr[1] = *iptr++;
new_c = strtoul (chr, NULL, 16);
*optr++ = new_c;
(*nbytes)++;
consumed += 3;
}
else
consumed += 2;
}
}
/* CR character. */
else if (c == '\r')
{
/* There must be at least 1 more character before
I consume this. */
if (consumed + 1 >= isize)
break;
else
{
iptr++; /* Skip the CR character. */
*optr++ = '\n';
(*nbytes)++;
consumed += 2;
}
}
else
{
*optr++ = c;
(*nbytes)++;
consumed++;
}
}
last_char = c;
}
return consumed - wscount;
}
#define SOFTBRK() \
/* check if we have enough room for the soft linebreak */\
if (*nbytes + 2 > osize) \
break;\
*optr++ = '=';\
*optr++ = '\n';\
(*nbytes) += 2;\
*line_len = 0;
static int
qp_encode (const char *iptr, size_t isize, char *optr, size_t osize,
size_t *nbytes, int *line_len)
{
unsigned int c;
size_t consumed = 0;
*nbytes = 0;
/* Strategy: check if we have enough room in the output buffer only
once the required size has been computed. If there is not enough,
return and hope that the caller will free up the output buffer a
bit. */
while (consumed < isize)
{
int simple_char;
/* candidate byte to convert */
c = *(unsigned char*) iptr;
simple_char = (c >= 32 && c <= 60)
|| (c >= 62 && c <= 126)
|| c == '\t'
|| c == '\n';
if (*line_len == QP_LINE_MAX
|| (c == '\n' && consumed && ISWS (optr[-1]))
|| (!simple_char && *line_len >= (QP_LINE_MAX - 3)))
{
/* to cut a qp line requires two bytes */
if (*nbytes + 2 > osize)
break;
*optr++ = '=';
*optr++ = '\n';
(*nbytes) += 2;
*line_len = 0;
}
if (simple_char)
{
/* a non-quoted character uses up one byte */
if (*nbytes + 1 > osize)
break;
*optr++ = c;
(*nbytes)++;
(*line_len)++;
iptr++;
consumed++;
if (c == '\n')
*line_len = 0;
}
else
{
/* a quoted character uses up three bytes */
if ((*nbytes) + 3 > osize)
break;
*optr++ = '=';
*optr++ = _hexdigits[(c >> 4) & 0xf];
*optr++ = _hexdigits[c & 0xf];
(*nbytes) += 3;
(*line_len) += 3;
/* we've actuall used up one byte of input */
iptr++;
consumed++;
}
}
return consumed;
}
static int
qp_init (filter_t filter)
{
struct _trans_stream *ts;
ts = calloc (sizeof (*ts), 1);
if (ts == NULL)
return ENOMEM;
ts->min_size = QP_LINE_MAX;
ts->s_buf = calloc (ts->min_size, 1);
if (ts->s_buf == NULL)
{
free (ts);
return ENOMEM;
}
ts->transcoder = (filter->type == MU_FILTER_DECODE) ? qp_decode : qp_encode;
filter->_read = trans_read;
filter->_destroy = trans_destroy;
filter->data = ts;
return 0;
}
static struct _filter_record _qp_filter =
{
"quoted-printable",
qp_init,
NULL,
NULL,
NULL
};
/*------------------------------------------------------
* base64 encode/decode
*----------------------------------------------------*/
static int
b64_input (char c)
{
const char table[64] =
"ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789+/";
int i;
for (i = 0; i < 64; i++)
{
if (table[i] == c)
return i;
}
return -1;
}
static int
base64_decode (const char *iptr, size_t isize, char *optr, size_t osize,
size_t *nbytes, int *line_len ARG_UNUSED)
{
int i = 0, tmp = 0, pad = 0;
size_t consumed = 0;
unsigned char data[4];
*nbytes = 0;
while (consumed < isize && (*nbytes)+3 < osize)
{
while (( i < 4 ) && (consumed < isize))
{
tmp = b64_input (*iptr++);
consumed++;
if (tmp != -1)
data[i++] = tmp;
else if (*(iptr-1) == '=')
{
data[i++] = '\0';
pad++;
}
}
/* I have a entire block of data 32 bits get the output data. */
if (i == 4)
{
*optr++ = (data[0] << 2) | ((data[1] & 0x30) >> 4);
*optr++ = ((data[1] & 0xf) << 4) | ((data[2] & 0x3c) >> 2);
*optr++ = ((data[2] & 0x3) << 6) | data[3];
(*nbytes) += 3 - pad;
}
else
{
/* I did not get all the data. */
consumed -= i;
return consumed;
}
i = 0;
}
return consumed;
}
#define BASE64_LINE_MAX 77
static int
base64_encode (const char *iptr, size_t isize, char *optr, size_t osize,
size_t *nbytes, int *line_len)
{
size_t consumed = 0;
int pad = 0;
const char *b64 =
"ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789+/";
const unsigned char* ptr = (const unsigned char*) iptr;
*nbytes = 0;
if (isize <= 3)
pad = 1;
while (((consumed + 3) <= isize && (*nbytes + 4) <= osize) || pad)
{
if (*line_len == 76)
{
*optr++ = '\n';
(*nbytes)++;
(*line_len) = 0;
if ((*nbytes + 4) > osize)
return consumed;
}
*optr++ = b64[ptr[0] >> 2];
*optr++ = b64[((ptr[0] << 4) + (--isize ? (ptr[1] >> 4): 0)) & 0x3f];
*optr++ = isize ? b64[((ptr[1] << 2) + (--isize ? (ptr[2] >> 6) : 0 )) & 0x3f] : '=';
*optr++ = isize ? b64[ptr[2] & 0x3f] : '=';
ptr += 3;
consumed += 3;
(*nbytes) += 4;
(*line_len) +=4;
pad = 0;
}
return consumed;
}
static int
base64_init (filter_t filter)
{
struct _trans_stream *ts;
ts = calloc (sizeof (*ts), 1);
if (ts == NULL)
return ENOMEM;
ts->min_size = 4;
ts->s_buf = calloc (ts->min_size, 1);
if (ts->s_buf == NULL)
{
free (ts);
return ENOMEM;
}
ts->transcoder = (filter->type == MU_FILTER_DECODE) ? base64_decode : base64_encode;
filter->_read = trans_read;
filter->_destroy = trans_destroy;
filter->data = ts;
return 0;
}
static struct _filter_record _base64_filter =
{
"base64",
base64_init,
NULL,
NULL,
NULL
};
/* RFC 2047 "Q" Encoding */
static int
Q_decode (const char *iptr, size_t isize, char *optr, size_t osize,
size_t *nbytes, int *line_len ARG_UNUSED)
{
char c;
size_t consumed = 0;
*nbytes = 0;
while (consumed < isize && *nbytes < osize)
{
c = *iptr++;
if (c == '=')
{
/* There must be 2 more characters before I consume this. */
if (consumed + 2 >= isize)
break;
else
{
/* you get =XX where XX are hex characters. */
char chr[3];
int new_c;
chr[2] = 0;
chr[0] = *iptr++;
/* Ignore LF. */
if (chr[0] != '\n')
{
chr[1] = *iptr++;
new_c = strtoul (chr, NULL, 16);
*optr++ = new_c;
(*nbytes)++;
consumed += 3;
}
else
consumed += 2;
}
}
/* CR character. */
else if (c == '\r')
{
/* There must be at least 1 more character before
I consume this. */
if (consumed + 1 >= isize)
break;
else
{
iptr++; /* Skip the CR character. */
*optr++ = '\n';
(*nbytes)++;
consumed += 2;
}
}
else if (c == '_')
{
*optr++ = ' ';
(*nbytes)++;
consumed++;
}
else
{
*optr++ = c;
(*nbytes)++;
consumed++;
}
}
return consumed;
}
static int
Q_printable_char_p (unsigned c)
{
switch (c)
{
/* FIXME: This is not quite so. Says RFC 2047:
(3) 8-bit values which correspond to printable ASCII characters other
than "=", "?", and "_" (underscore), MAY be represented as those
characters. (But see section 5 for restrictions.) In
particular, SPACE and TAB MUST NOT be represented as themselves
within encoded words. (see Page 6)*/
case '=':
case '?':
case '_':
case ' ':
case '\t':
return 0;
default:
return 1;
}
}
static int
Q_encode (const char *iptr, size_t isize, char *optr, size_t osize,
size_t *nbytes, int *line_len)
{
unsigned int c;
size_t consumed = 0;
*nbytes = 0;
while (consumed < isize)
{
c = *(unsigned char*) iptr;
if (Q_printable_char_p (c))
{
/* a non-quoted character uses up one byte */
if (*nbytes + 1 > osize)
break;
*optr++ = c;
(*nbytes)++;
(*line_len)++;
iptr++;
consumed++;
}
else if (c == 0x20)
{
/* RFC2047, 4.2.2:
Note that the "_"
always represents hexadecimal 20, even if the SPACE character
occupies a different code position in the character set in use. */
*optr++ = '_';
(*nbytes)++;
(*line_len)++;
iptr++;
consumed++;
}
else
{
/* a quoted character uses up three bytes */
if ((*nbytes) + 3 > osize)
break;
*optr++ = '=';
*optr++ = _hexdigits[(c >> 4) & 0xf];
*optr++ = _hexdigits[c & 0xf];
(*nbytes) += 3;
(*line_len) += 3;
/* we've actuall used up one byte of input */
iptr++;
consumed++;
}
}
return consumed;
}
static int
Q_init (filter_t filter)
{
struct _trans_stream *ts;
ts = calloc (sizeof (*ts), 1);
if (ts == NULL)
return ENOMEM;
ts->min_size = QP_LINE_MAX;
ts->s_buf = calloc (ts->min_size, 1);
if (ts->s_buf == NULL)
{
free (ts);
return ENOMEM;
}
ts->transcoder = (filter->type == MU_FILTER_DECODE) ? Q_decode : Q_encode;
filter->_read = trans_read;
filter->_destroy = trans_destroy;
filter->data = ts;
return 0;
}
static struct _filter_record _Q_filter =
{
"Q",
Q_init,
NULL,
NULL,
NULL
};
/* Pass-through encodings */
static struct _filter_record _bit8_filter =
{
"8bit",
NULL,
NULL,
NULL,
NULL
};
static struct _filter_record _bit7_filter =
{
"7bit",
NULL,
NULL,
NULL,
NULL
};
static struct _filter_record _binary_filter =
{
"binary",
NULL,
NULL,
NULL,
NULL
};
/* Export. */
filter_record_t qp_filter = &_qp_filter;
filter_record_t base64_filter = &_base64_filter;
filter_record_t binary_filter = &_binary_filter;
filter_record_t bit8_filter = &_bit8_filter;
filter_record_t bit7_filter = &_bit7_filter;
filter_record_t rfc_2047_Q_filter = &_Q_filter;