forked from python/cpython
-
Notifications
You must be signed in to change notification settings - Fork 0
/
binascii.c
1542 lines (1380 loc) · 50.8 KB
/
binascii.c
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
752
753
754
755
756
757
758
759
760
761
762
763
764
765
766
767
768
769
770
771
772
773
774
775
776
777
778
779
780
781
782
783
784
785
786
787
788
789
790
791
792
793
794
795
796
797
798
799
800
801
802
803
804
805
806
807
808
809
810
811
812
813
814
815
816
817
818
819
820
821
822
823
824
825
826
827
828
829
830
831
832
833
834
835
836
837
838
839
840
841
842
843
844
845
846
847
848
849
850
851
852
853
854
855
856
857
858
859
860
861
862
863
864
865
866
867
868
869
870
871
872
873
874
875
876
877
878
879
880
881
882
883
884
885
886
887
888
889
890
891
892
893
894
895
896
897
898
899
900
901
902
903
904
905
906
907
908
909
910
911
912
913
914
915
916
917
918
919
920
921
922
923
924
925
926
927
928
929
930
931
932
933
934
935
936
937
938
939
940
941
942
943
944
945
946
947
948
949
950
951
952
953
954
955
956
957
958
959
960
961
962
963
964
965
966
967
968
969
970
971
972
973
974
975
976
977
978
979
980
981
982
983
984
985
986
987
988
989
990
991
992
993
994
995
996
997
998
999
1000
/*
** Routines to represent binary data in ASCII and vice-versa
**
** This module currently supports the following encodings:
** uuencode:
** each line encodes 45 bytes (except possibly the last)
** First char encodes (binary) length, rest data
** each char encodes 6 bits, as follows:
** binary: 01234567 abcdefgh ijklmnop
** ascii: 012345 67abcd efghij klmnop
** ASCII encoding method is "excess-space": 000000 is encoded as ' ', etc.
** short binary data is zero-extended (so the bits are always in the
** right place), this does *not* reflect in the length.
** base64:
** Line breaks are insignificant, but lines are at most 76 chars
** each char encodes 6 bits, in similar order as uucode/hqx. Encoding
** is done via a table.
** Short binary data is filled (in ASCII) with '='.
** hqx:
** File starts with introductory text, real data starts and ends
** with colons.
** Data consists of three similar parts: info, datafork, resourcefork.
** Each part is protected (at the end) with a 16-bit crc
** The binary data is run-length encoded, and then ascii-fied:
** binary: 01234567 abcdefgh ijklmnop
** ascii: 012345 67abcd efghij klmnop
** ASCII encoding is table-driven, see the code.
** Short binary data results in the runt ascii-byte being output with
** the bits in the right place.
**
** While I was reading dozens of programs that encode or decode the formats
** here (documentation? hihi:-) I have formulated Jansen's Observation:
**
** Programs that encode binary data in ASCII are written in
** such a style that they are as unreadable as possible. Devices used
** include unnecessary global variables, burying important tables
** in unrelated sourcefiles, putting functions in include files,
** using seemingly-descriptive variable names for different purposes,
** calls to empty subroutines and a host of others.
**
** I have attempted to break with this tradition, but I guess that that
** does make the performance sub-optimal. Oh well, too bad...
**
** Jack Jansen, CWI, July 1995.
**
** Added support for quoted-printable encoding, based on rfc 1521 et al
** quoted-printable encoding specifies that non printable characters (anything
** below 32 and above 126) be encoded as =XX where XX is the hexadecimal value
** of the character. It also specifies some other behavior to enable 8bit data
** in a mail message with little difficulty (maximum line sizes, protecting
** some cases of whitespace, etc).
**
** Brandon Long, September 2001.
*/
#define PY_SSIZE_T_CLEAN
#include "Python.h"
#ifdef USE_ZLIB_CRC32
#include "zlib.h"
#endif
static PyObject *Error;
static PyObject *Incomplete;
/*
** hqx lookup table, ascii->binary.
*/
#define RUNCHAR 0x90
#define DONE 0x7F
#define SKIP 0x7E
#define FAIL 0x7D
static unsigned char table_a2b_hqx[256] = {
/* ^@ ^A ^B ^C ^D ^E ^F ^G */
/* 0*/ FAIL, FAIL, FAIL, FAIL, FAIL, FAIL, FAIL, FAIL,
/* \b \t \n ^K ^L \r ^N ^O */
/* 1*/ FAIL, FAIL, SKIP, FAIL, FAIL, SKIP, FAIL, FAIL,
/* ^P ^Q ^R ^S ^T ^U ^V ^W */
/* 2*/ FAIL, FAIL, FAIL, FAIL, FAIL, FAIL, FAIL, FAIL,
/* ^X ^Y ^Z ^[ ^\ ^] ^^ ^_ */
/* 3*/ FAIL, FAIL, FAIL, FAIL, FAIL, FAIL, FAIL, FAIL,
/* ! " # $ % & ' */
/* 4*/ FAIL, 0x00, 0x01, 0x02, 0x03, 0x04, 0x05, 0x06,
/* ( ) * + , - . / */
/* 5*/ 0x07, 0x08, 0x09, 0x0A, 0x0B, 0x0C, FAIL, FAIL,
/* 0 1 2 3 4 5 6 7 */
/* 6*/ 0x0D, 0x0E, 0x0F, 0x10, 0x11, 0x12, 0x13, FAIL,
/* 8 9 : ; < = > ? */
/* 7*/ 0x14, 0x15, DONE, FAIL, FAIL, FAIL, FAIL, FAIL,
/* @ A B C D E F G */
/* 8*/ 0x16, 0x17, 0x18, 0x19, 0x1A, 0x1B, 0x1C, 0x1D,
/* H I J K L M N O */
/* 9*/ 0x1E, 0x1F, 0x20, 0x21, 0x22, 0x23, 0x24, FAIL,
/* P Q R S T U V W */
/*10*/ 0x25, 0x26, 0x27, 0x28, 0x29, 0x2A, 0x2B, FAIL,
/* X Y Z [ \ ] ^ _ */
/*11*/ 0x2C, 0x2D, 0x2E, 0x2F, FAIL, FAIL, FAIL, FAIL,
/* ` a b c d e f g */
/*12*/ 0x30, 0x31, 0x32, 0x33, 0x34, 0x35, 0x36, FAIL,
/* h i j k l m n o */
/*13*/ 0x37, 0x38, 0x39, 0x3A, 0x3B, 0x3C, FAIL, FAIL,
/* p q r s t u v w */
/*14*/ 0x3D, 0x3E, 0x3F, FAIL, FAIL, FAIL, FAIL, FAIL,
/* x y z { | } ~ ^? */
/*15*/ FAIL, FAIL, FAIL, FAIL, FAIL, FAIL, FAIL, FAIL,
/*16*/ FAIL, FAIL, FAIL, FAIL, FAIL, FAIL, FAIL, FAIL,
FAIL, FAIL, FAIL, FAIL, FAIL, FAIL, FAIL, FAIL,
FAIL, FAIL, FAIL, FAIL, FAIL, FAIL, FAIL, FAIL,
FAIL, FAIL, FAIL, FAIL, FAIL, FAIL, FAIL, FAIL,
FAIL, FAIL, FAIL, FAIL, FAIL, FAIL, FAIL, FAIL,
FAIL, FAIL, FAIL, FAIL, FAIL, FAIL, FAIL, FAIL,
FAIL, FAIL, FAIL, FAIL, FAIL, FAIL, FAIL, FAIL,
FAIL, FAIL, FAIL, FAIL, FAIL, FAIL, FAIL, FAIL,
FAIL, FAIL, FAIL, FAIL, FAIL, FAIL, FAIL, FAIL,
FAIL, FAIL, FAIL, FAIL, FAIL, FAIL, FAIL, FAIL,
FAIL, FAIL, FAIL, FAIL, FAIL, FAIL, FAIL, FAIL,
FAIL, FAIL, FAIL, FAIL, FAIL, FAIL, FAIL, FAIL,
FAIL, FAIL, FAIL, FAIL, FAIL, FAIL, FAIL, FAIL,
FAIL, FAIL, FAIL, FAIL, FAIL, FAIL, FAIL, FAIL,
FAIL, FAIL, FAIL, FAIL, FAIL, FAIL, FAIL, FAIL,
FAIL, FAIL, FAIL, FAIL, FAIL, FAIL, FAIL, FAIL,
};
static unsigned char table_b2a_hqx[] =
"!\"#$%&'()*+,-012345689@ABCDEFGHIJKLMNPQRSTUVXYZ[`abcdefhijklmpqr";
static char table_a2b_base64[] = {
-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, -1,-1,-1,63,
52,53,54,55, 56,57,58,59, 60,61,-1,-1, -1, 0,-1,-1, /* Note PAD->0 */
-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
};
#define BASE64_PAD '='
/* Max binary chunk size; limited only by available memory */
#define BASE64_MAXBIN ((PY_SSIZE_T_MAX - 3) / 2)
static unsigned char table_b2a_base64[] =
"ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789+/";
static unsigned short crctab_hqx[256] = {
0x0000, 0x1021, 0x2042, 0x3063, 0x4084, 0x50a5, 0x60c6, 0x70e7,
0x8108, 0x9129, 0xa14a, 0xb16b, 0xc18c, 0xd1ad, 0xe1ce, 0xf1ef,
0x1231, 0x0210, 0x3273, 0x2252, 0x52b5, 0x4294, 0x72f7, 0x62d6,
0x9339, 0x8318, 0xb37b, 0xa35a, 0xd3bd, 0xc39c, 0xf3ff, 0xe3de,
0x2462, 0x3443, 0x0420, 0x1401, 0x64e6, 0x74c7, 0x44a4, 0x5485,
0xa56a, 0xb54b, 0x8528, 0x9509, 0xe5ee, 0xf5cf, 0xc5ac, 0xd58d,
0x3653, 0x2672, 0x1611, 0x0630, 0x76d7, 0x66f6, 0x5695, 0x46b4,
0xb75b, 0xa77a, 0x9719, 0x8738, 0xf7df, 0xe7fe, 0xd79d, 0xc7bc,
0x48c4, 0x58e5, 0x6886, 0x78a7, 0x0840, 0x1861, 0x2802, 0x3823,
0xc9cc, 0xd9ed, 0xe98e, 0xf9af, 0x8948, 0x9969, 0xa90a, 0xb92b,
0x5af5, 0x4ad4, 0x7ab7, 0x6a96, 0x1a71, 0x0a50, 0x3a33, 0x2a12,
0xdbfd, 0xcbdc, 0xfbbf, 0xeb9e, 0x9b79, 0x8b58, 0xbb3b, 0xab1a,
0x6ca6, 0x7c87, 0x4ce4, 0x5cc5, 0x2c22, 0x3c03, 0x0c60, 0x1c41,
0xedae, 0xfd8f, 0xcdec, 0xddcd, 0xad2a, 0xbd0b, 0x8d68, 0x9d49,
0x7e97, 0x6eb6, 0x5ed5, 0x4ef4, 0x3e13, 0x2e32, 0x1e51, 0x0e70,
0xff9f, 0xefbe, 0xdfdd, 0xcffc, 0xbf1b, 0xaf3a, 0x9f59, 0x8f78,
0x9188, 0x81a9, 0xb1ca, 0xa1eb, 0xd10c, 0xc12d, 0xf14e, 0xe16f,
0x1080, 0x00a1, 0x30c2, 0x20e3, 0x5004, 0x4025, 0x7046, 0x6067,
0x83b9, 0x9398, 0xa3fb, 0xb3da, 0xc33d, 0xd31c, 0xe37f, 0xf35e,
0x02b1, 0x1290, 0x22f3, 0x32d2, 0x4235, 0x5214, 0x6277, 0x7256,
0xb5ea, 0xa5cb, 0x95a8, 0x8589, 0xf56e, 0xe54f, 0xd52c, 0xc50d,
0x34e2, 0x24c3, 0x14a0, 0x0481, 0x7466, 0x6447, 0x5424, 0x4405,
0xa7db, 0xb7fa, 0x8799, 0x97b8, 0xe75f, 0xf77e, 0xc71d, 0xd73c,
0x26d3, 0x36f2, 0x0691, 0x16b0, 0x6657, 0x7676, 0x4615, 0x5634,
0xd94c, 0xc96d, 0xf90e, 0xe92f, 0x99c8, 0x89e9, 0xb98a, 0xa9ab,
0x5844, 0x4865, 0x7806, 0x6827, 0x18c0, 0x08e1, 0x3882, 0x28a3,
0xcb7d, 0xdb5c, 0xeb3f, 0xfb1e, 0x8bf9, 0x9bd8, 0xabbb, 0xbb9a,
0x4a75, 0x5a54, 0x6a37, 0x7a16, 0x0af1, 0x1ad0, 0x2ab3, 0x3a92,
0xfd2e, 0xed0f, 0xdd6c, 0xcd4d, 0xbdaa, 0xad8b, 0x9de8, 0x8dc9,
0x7c26, 0x6c07, 0x5c64, 0x4c45, 0x3ca2, 0x2c83, 0x1ce0, 0x0cc1,
0xef1f, 0xff3e, 0xcf5d, 0xdf7c, 0xaf9b, 0xbfba, 0x8fd9, 0x9ff8,
0x6e17, 0x7e36, 0x4e55, 0x5e74, 0x2e93, 0x3eb2, 0x0ed1, 0x1ef0,
};
PyDoc_STRVAR(doc_a2b_uu, "(ascii) -> bin. Decode a line of uuencoded data");
static PyObject *
binascii_a2b_uu(PyObject *self, PyObject *args)
{
Py_buffer pascii;
unsigned char *ascii_data, *bin_data;
int leftbits = 0;
unsigned char this_ch;
unsigned int leftchar = 0;
PyObject *rv;
Py_ssize_t ascii_len, bin_len;
if ( !PyArg_ParseTuple(args, "y*:a2b_uu", &pascii) )
return NULL;
ascii_data = pascii.buf;
ascii_len = pascii.len;
assert(ascii_len >= 0);
/* First byte: binary data length (in bytes) */
bin_len = (*ascii_data++ - ' ') & 077;
ascii_len--;
/* Allocate the buffer */
if ( (rv=PyBytes_FromStringAndSize(NULL, bin_len)) == NULL ) {
PyBuffer_Release(&pascii);
return NULL;
}
bin_data = (unsigned char *)PyBytes_AS_STRING(rv);
for( ; bin_len > 0 ; ascii_len--, ascii_data++ ) {
/* XXX is it really best to add NULs if there's no more data */
this_ch = (ascii_len > 0) ? *ascii_data : 0;
if ( this_ch == '\n' || this_ch == '\r' || ascii_len <= 0) {
/*
** Whitespace. Assume some spaces got eaten at
** end-of-line. (We check this later)
*/
this_ch = 0;
} else {
/* Check the character for legality
** The 64 in stead of the expected 63 is because
** there are a few uuencodes out there that use
** '`' as zero instead of space.
*/
if ( this_ch < ' ' || this_ch > (' ' + 64)) {
PyErr_SetString(Error, "Illegal char");
PyBuffer_Release(&pascii);
Py_DECREF(rv);
return NULL;
}
this_ch = (this_ch - ' ') & 077;
}
/*
** Shift it in on the low end, and see if there's
** a byte ready for output.
*/
leftchar = (leftchar << 6) | (this_ch);
leftbits += 6;
if ( leftbits >= 8 ) {
leftbits -= 8;
*bin_data++ = (leftchar >> leftbits) & 0xff;
leftchar &= ((1 << leftbits) - 1);
bin_len--;
}
}
/*
** Finally, check that if there's anything left on the line
** that it's whitespace only.
*/
while( ascii_len-- > 0 ) {
this_ch = *ascii_data++;
/* Extra '`' may be written as padding in some cases */
if ( this_ch != ' ' && this_ch != ' '+64 &&
this_ch != '\n' && this_ch != '\r' ) {
PyErr_SetString(Error, "Trailing garbage");
PyBuffer_Release(&pascii);
Py_DECREF(rv);
return NULL;
}
}
PyBuffer_Release(&pascii);
return rv;
}
PyDoc_STRVAR(doc_b2a_uu, "(bin) -> ascii. Uuencode line of data");
static PyObject *
binascii_b2a_uu(PyObject *self, PyObject *args)
{
Py_buffer pbin;
unsigned char *ascii_data, *bin_data;
int leftbits = 0;
unsigned char this_ch;
unsigned int leftchar = 0;
PyObject *rv;
Py_ssize_t bin_len;
if ( !PyArg_ParseTuple(args, "y*:b2a_uu", &pbin) )
return NULL;
bin_data = pbin.buf;
bin_len = pbin.len;
if ( bin_len > 45 ) {
/* The 45 is a limit that appears in all uuencode's */
PyErr_SetString(Error, "At most 45 bytes at once");
PyBuffer_Release(&pbin);
return NULL;
}
/* We're lazy and allocate to much (fixed up later) */
if ( (rv=PyBytes_FromStringAndSize(NULL, 2 + (bin_len+2)/3*4)) == NULL ) {
PyBuffer_Release(&pbin);
return NULL;
}
ascii_data = (unsigned char *)PyBytes_AS_STRING(rv);
/* Store the length */
*ascii_data++ = ' ' + (bin_len & 077);
for( ; bin_len > 0 || leftbits != 0 ; bin_len--, bin_data++ ) {
/* Shift the data (or padding) into our buffer */
if ( bin_len > 0 ) /* Data */
leftchar = (leftchar << 8) | *bin_data;
else /* Padding */
leftchar <<= 8;
leftbits += 8;
/* See if there are 6-bit groups ready */
while ( leftbits >= 6 ) {
this_ch = (leftchar >> (leftbits-6)) & 0x3f;
leftbits -= 6;
*ascii_data++ = this_ch + ' ';
}
}
*ascii_data++ = '\n'; /* Append a courtesy newline */
if (_PyBytes_Resize(&rv,
(ascii_data -
(unsigned char *)PyBytes_AS_STRING(rv))) < 0) {
Py_DECREF(rv);
rv = NULL;
}
PyBuffer_Release(&pbin);
return rv;
}
static int
binascii_find_valid(unsigned char *s, Py_ssize_t slen, int num)
{
/* Finds & returns the (num+1)th
** valid character for base64, or -1 if none.
*/
int ret = -1;
unsigned char c, b64val;
while ((slen > 0) && (ret == -1)) {
c = *s;
b64val = table_a2b_base64[c & 0x7f];
if ( ((c <= 0x7f) && (b64val != (unsigned char)-1)) ) {
if (num == 0)
ret = *s;
num--;
}
s++;
slen--;
}
return ret;
}
PyDoc_STRVAR(doc_a2b_base64, "(ascii) -> bin. Decode a line of base64 data");
static PyObject *
binascii_a2b_base64(PyObject *self, PyObject *args)
{
Py_buffer pascii;
unsigned char *ascii_data, *bin_data;
int leftbits = 0;
unsigned char this_ch;
unsigned int leftchar = 0;
PyObject *rv;
Py_ssize_t ascii_len, bin_len;
int quad_pos = 0;
if ( !PyArg_ParseTuple(args, "y*:a2b_base64", &pascii) )
return NULL;
ascii_data = pascii.buf;
ascii_len = pascii.len;
assert(ascii_len >= 0);
if (ascii_len > PY_SSIZE_T_MAX - 3) {
PyBuffer_Release(&pascii);
return PyErr_NoMemory();
}
bin_len = ((ascii_len+3)/4)*3; /* Upper bound, corrected later */
/* Allocate the buffer */
if ( (rv=PyBytes_FromStringAndSize(NULL, bin_len)) == NULL ) {
PyBuffer_Release(&pascii);
return NULL;
}
bin_data = (unsigned char *)PyBytes_AS_STRING(rv);
bin_len = 0;
for( ; ascii_len > 0; ascii_len--, ascii_data++) {
this_ch = *ascii_data;
if (this_ch > 0x7f ||
this_ch == '\r' || this_ch == '\n' || this_ch == ' ')
continue;
/* Check for pad sequences and ignore
** the invalid ones.
*/
if (this_ch == BASE64_PAD) {
if ( (quad_pos < 2) ||
((quad_pos == 2) &&
(binascii_find_valid(ascii_data, ascii_len, 1)
!= BASE64_PAD)) )
{
continue;
}
else {
/* A pad sequence means no more input.
** We've already interpreted the data
** from the quad at this point.
*/
leftbits = 0;
break;
}
}
this_ch = table_a2b_base64[*ascii_data];
if ( this_ch == (unsigned char) -1 )
continue;
/*
** Shift it in on the low end, and see if there's
** a byte ready for output.
*/
quad_pos = (quad_pos + 1) & 0x03;
leftchar = (leftchar << 6) | (this_ch);
leftbits += 6;
if ( leftbits >= 8 ) {
leftbits -= 8;
*bin_data++ = (leftchar >> leftbits) & 0xff;
bin_len++;
leftchar &= ((1 << leftbits) - 1);
}
}
if (leftbits != 0) {
PyBuffer_Release(&pascii);
PyErr_SetString(Error, "Incorrect padding");
Py_DECREF(rv);
return NULL;
}
/* And set string size correctly. If the result string is empty
** (because the input was all invalid) return the shared empty
** string instead; _PyBytes_Resize() won't do this for us.
*/
if (bin_len > 0) {
if (_PyBytes_Resize(&rv, bin_len) < 0) {
Py_DECREF(rv);
rv = NULL;
}
}
else {
Py_DECREF(rv);
rv = PyBytes_FromStringAndSize("", 0);
}
PyBuffer_Release(&pascii);
return rv;
}
PyDoc_STRVAR(doc_b2a_base64, "(bin) -> ascii. Base64-code line of data");
static PyObject *
binascii_b2a_base64(PyObject *self, PyObject *args)
{
Py_buffer pbuf;
unsigned char *ascii_data, *bin_data;
int leftbits = 0;
unsigned char this_ch;
unsigned int leftchar = 0;
PyObject *rv;
Py_ssize_t bin_len;
if ( !PyArg_ParseTuple(args, "y*:b2a_base64", &pbuf) )
return NULL;
bin_data = pbuf.buf;
bin_len = pbuf.len;
assert(bin_len >= 0);
if ( bin_len > BASE64_MAXBIN ) {
PyErr_SetString(Error, "Too much data for base64 line");
PyBuffer_Release(&pbuf);
return NULL;
}
/* We're lazy and allocate too much (fixed up later).
"+3" leaves room for up to two pad characters and a trailing
newline. Note that 'b' gets encoded as 'Yg==\n' (1 in, 5 out). */
if ( (rv=PyBytes_FromStringAndSize(NULL, bin_len*2 + 3)) == NULL ) {
PyBuffer_Release(&pbuf);
return NULL;
}
ascii_data = (unsigned char *)PyBytes_AS_STRING(rv);
for( ; bin_len > 0 ; bin_len--, bin_data++ ) {
/* Shift the data into our buffer */
leftchar = (leftchar << 8) | *bin_data;
leftbits += 8;
/* See if there are 6-bit groups ready */
while ( leftbits >= 6 ) {
this_ch = (leftchar >> (leftbits-6)) & 0x3f;
leftbits -= 6;
*ascii_data++ = table_b2a_base64[this_ch];
}
}
if ( leftbits == 2 ) {
*ascii_data++ = table_b2a_base64[(leftchar&3) << 4];
*ascii_data++ = BASE64_PAD;
*ascii_data++ = BASE64_PAD;
} else if ( leftbits == 4 ) {
*ascii_data++ = table_b2a_base64[(leftchar&0xf) << 2];
*ascii_data++ = BASE64_PAD;
}
*ascii_data++ = '\n'; /* Append a courtesy newline */
if (_PyBytes_Resize(&rv,
(ascii_data -
(unsigned char *)PyBytes_AS_STRING(rv))) < 0) {
Py_DECREF(rv);
rv = NULL;
}
PyBuffer_Release(&pbuf);
return rv;
}
PyDoc_STRVAR(doc_a2b_hqx, "ascii -> bin, done. Decode .hqx coding");
static PyObject *
binascii_a2b_hqx(PyObject *self, PyObject *args)
{
Py_buffer pascii;
unsigned char *ascii_data, *bin_data;
int leftbits = 0;
unsigned char this_ch;
unsigned int leftchar = 0;
PyObject *rv;
Py_ssize_t len;
int done = 0;
if ( !PyArg_ParseTuple(args, "y*:a2b_hqx", &pascii) )
return NULL;
ascii_data = pascii.buf;
len = pascii.len;
assert(len >= 0);
if (len > PY_SSIZE_T_MAX - 2) {
PyBuffer_Release(&pascii);
return PyErr_NoMemory();
}
/* Allocate a string that is too big (fixed later)
Add two to the initial length to prevent interning which
would preclude subsequent resizing. */
if ( (rv=PyBytes_FromStringAndSize(NULL, len+2)) == NULL ) {
PyBuffer_Release(&pascii);
return NULL;
}
bin_data = (unsigned char *)PyBytes_AS_STRING(rv);
for( ; len > 0 ; len--, ascii_data++ ) {
/* Get the byte and look it up */
this_ch = table_a2b_hqx[*ascii_data];
if ( this_ch == SKIP )
continue;
if ( this_ch == FAIL ) {
PyErr_SetString(Error, "Illegal char");
PyBuffer_Release(&pascii);
Py_DECREF(rv);
return NULL;
}
if ( this_ch == DONE ) {
/* The terminating colon */
done = 1;
break;
}
/* Shift it into the buffer and see if any bytes are ready */
leftchar = (leftchar << 6) | (this_ch);
leftbits += 6;
if ( leftbits >= 8 ) {
leftbits -= 8;
*bin_data++ = (leftchar >> leftbits) & 0xff;
leftchar &= ((1 << leftbits) - 1);
}
}
if ( leftbits && !done ) {
PyErr_SetString(Incomplete,
"String has incomplete number of bytes");
PyBuffer_Release(&pascii);
Py_DECREF(rv);
return NULL;
}
if (_PyBytes_Resize(&rv,
(bin_data -
(unsigned char *)PyBytes_AS_STRING(rv))) < 0) {
Py_DECREF(rv);
rv = NULL;
}
if (rv) {
PyObject *rrv = Py_BuildValue("Oi", rv, done);
PyBuffer_Release(&pascii);
Py_DECREF(rv);
return rrv;
}
PyBuffer_Release(&pascii);
return NULL;
}
PyDoc_STRVAR(doc_rlecode_hqx, "Binhex RLE-code binary data");
static PyObject *
binascii_rlecode_hqx(PyObject *self, PyObject *args)
{
Py_buffer pbuf;
unsigned char *in_data, *out_data;
PyObject *rv;
unsigned char ch;
Py_ssize_t in, inend, len;
if ( !PyArg_ParseTuple(args, "y*:rlecode_hqx", &pbuf) )
return NULL;
in_data = pbuf.buf;
len = pbuf.len;
assert(len >= 0);
if (len > PY_SSIZE_T_MAX / 2 - 2) {
PyBuffer_Release(&pbuf);
return PyErr_NoMemory();
}
/* Worst case: output is twice as big as input (fixed later) */
if ( (rv=PyBytes_FromStringAndSize(NULL, len*2+2)) == NULL ) {
PyBuffer_Release(&pbuf);
return NULL;
}
out_data = (unsigned char *)PyBytes_AS_STRING(rv);
for( in=0; in<len; in++) {
ch = in_data[in];
if ( ch == RUNCHAR ) {
/* RUNCHAR. Escape it. */
*out_data++ = RUNCHAR;
*out_data++ = 0;
} else {
/* Check how many following are the same */
for(inend=in+1;
inend<len && in_data[inend] == ch &&
inend < in+255;
inend++) ;
if ( inend - in > 3 ) {
/* More than 3 in a row. Output RLE. */
*out_data++ = ch;
*out_data++ = RUNCHAR;
*out_data++ = (unsigned char) (inend-in);
in = inend-1;
} else {
/* Less than 3. Output the byte itself */
*out_data++ = ch;
}
}
}
if (_PyBytes_Resize(&rv,
(out_data -
(unsigned char *)PyBytes_AS_STRING(rv))) < 0) {
Py_DECREF(rv);
rv = NULL;
}
PyBuffer_Release(&pbuf);
return rv;
}
PyDoc_STRVAR(doc_b2a_hqx, "Encode .hqx data");
static PyObject *
binascii_b2a_hqx(PyObject *self, PyObject *args)
{
Py_buffer pbin;
unsigned char *ascii_data, *bin_data;
int leftbits = 0;
unsigned char this_ch;
unsigned int leftchar = 0;
PyObject *rv;
Py_ssize_t len;
if ( !PyArg_ParseTuple(args, "y*:b2a_hqx", &pbin) )
return NULL;
bin_data = pbin.buf;
len = pbin.len;
assert(len >= 0);
if (len > PY_SSIZE_T_MAX / 2 - 2) {
PyBuffer_Release(&pbin);
return PyErr_NoMemory();
}
/* Allocate a buffer that is at least large enough */
if ( (rv=PyBytes_FromStringAndSize(NULL, len*2+2)) == NULL ) {
PyBuffer_Release(&pbin);
return NULL;
}
ascii_data = (unsigned char *)PyBytes_AS_STRING(rv);
for( ; len > 0 ; len--, bin_data++ ) {
/* Shift into our buffer, and output any 6bits ready */
leftchar = (leftchar << 8) | *bin_data;
leftbits += 8;
while ( leftbits >= 6 ) {
this_ch = (leftchar >> (leftbits-6)) & 0x3f;
leftbits -= 6;
*ascii_data++ = table_b2a_hqx[this_ch];
}
}
/* Output a possible runt byte */
if ( leftbits ) {
leftchar <<= (6-leftbits);
*ascii_data++ = table_b2a_hqx[leftchar & 0x3f];
}
if (_PyBytes_Resize(&rv,
(ascii_data -
(unsigned char *)PyBytes_AS_STRING(rv))) < 0) {
Py_DECREF(rv);
rv = NULL;
}
PyBuffer_Release(&pbin);
return rv;
}
PyDoc_STRVAR(doc_rledecode_hqx, "Decode hexbin RLE-coded string");
static PyObject *
binascii_rledecode_hqx(PyObject *self, PyObject *args)
{
Py_buffer pin;
unsigned char *in_data, *out_data;
unsigned char in_byte, in_repeat;
PyObject *rv;
Py_ssize_t in_len, out_len, out_len_left;
if ( !PyArg_ParseTuple(args, "y*:rledecode_hqx", &pin) )
return NULL;
in_data = pin.buf;
in_len = pin.len;
assert(in_len >= 0);
/* Empty string is a special case */
if ( in_len == 0 ) {
PyBuffer_Release(&pin);
return PyBytes_FromStringAndSize("", 0);
}
else if (in_len > PY_SSIZE_T_MAX / 2) {
PyBuffer_Release(&pin);
return PyErr_NoMemory();
}
/* Allocate a buffer of reasonable size. Resized when needed */
out_len = in_len*2;
if ( (rv=PyBytes_FromStringAndSize(NULL, out_len)) == NULL ) {
PyBuffer_Release(&pin);
return NULL;
}
out_len_left = out_len;
out_data = (unsigned char *)PyBytes_AS_STRING(rv);
/*
** We need two macros here to get/put bytes and handle
** end-of-buffer for input and output strings.
*/
#define INBYTE(b) \
do { \
if ( --in_len < 0 ) { \
PyErr_SetString(Incomplete, ""); \
Py_DECREF(rv); \
PyBuffer_Release(&pin); \
return NULL; \
} \
b = *in_data++; \
} while(0)
#define OUTBYTE(b) \
do { \
if ( --out_len_left < 0 ) { \
if ( out_len > PY_SSIZE_T_MAX / 2) return PyErr_NoMemory(); \
if (_PyBytes_Resize(&rv, 2*out_len) < 0) \
{ Py_DECREF(rv); PyBuffer_Release(&pin); return NULL; } \
out_data = (unsigned char *)PyBytes_AS_STRING(rv) \
+ out_len; \
out_len_left = out_len-1; \
out_len = out_len * 2; \
} \
*out_data++ = b; \
} while(0)
/*
** Handle first byte separately (since we have to get angry
** in case of an orphaned RLE code).
*/
INBYTE(in_byte);
if (in_byte == RUNCHAR) {
INBYTE(in_repeat);
if (in_repeat != 0) {
/* Note Error, not Incomplete (which is at the end
** of the string only). This is a programmer error.
*/
PyErr_SetString(Error, "Orphaned RLE code at start");
PyBuffer_Release(&pin);
Py_DECREF(rv);
return NULL;
}
OUTBYTE(RUNCHAR);
} else {
OUTBYTE(in_byte);
}
while( in_len > 0 ) {
INBYTE(in_byte);
if (in_byte == RUNCHAR) {
INBYTE(in_repeat);
if ( in_repeat == 0 ) {
/* Just an escaped RUNCHAR value */
OUTBYTE(RUNCHAR);
} else {
/* Pick up value and output a sequence of it */
in_byte = out_data[-1];
while ( --in_repeat > 0 )
OUTBYTE(in_byte);
}
} else {
/* Normal byte */
OUTBYTE(in_byte);
}
}
if (_PyBytes_Resize(&rv,
(out_data -
(unsigned char *)PyBytes_AS_STRING(rv))) < 0) {
Py_DECREF(rv);
rv = NULL;
}
PyBuffer_Release(&pin);
return rv;
}
PyDoc_STRVAR(doc_crc_hqx,
"(data, oldcrc) -> newcrc. Compute hqx CRC incrementally");
static PyObject *
binascii_crc_hqx(PyObject *self, PyObject *args)
{
Py_buffer pin;
unsigned char *bin_data;
unsigned int crc;
Py_ssize_t len;
if ( !PyArg_ParseTuple(args, "y*i:crc_hqx", &pin, &crc) )
return NULL;
bin_data = pin.buf;
len = pin.len;
while(len-- > 0) {
crc=((crc<<8)&0xff00)^crctab_hqx[((crc>>8)&0xff)^*bin_data++];
}
PyBuffer_Release(&pin);
return Py_BuildValue("i", crc);
}
PyDoc_STRVAR(doc_crc32,
"(data, oldcrc = 0) -> newcrc. Compute CRC-32 incrementally");
#ifdef USE_ZLIB_CRC32
/* This was taken from zlibmodule.c PyZlib_crc32 (but is PY_SSIZE_T_CLEAN) */
static PyObject *
binascii_crc32(PyObject *self, PyObject *args)
{
unsigned int crc32val = 0; /* crc32(0L, Z_NULL, 0) */
Py_buffer pbuf;
Byte *buf;
Py_ssize_t len;
int signed_val;
if (!PyArg_ParseTuple(args, "y*|I:crc32", &pbuf, &crc32val))
return NULL;
buf = (Byte*)pbuf.buf;
len = pbuf.len;
signed_val = crc32(crc32val, buf, len);
PyBuffer_Release(&pbuf);
return PyLong_FromUnsignedLong(signed_val & 0xffffffffU);
}
#else /* USE_ZLIB_CRC32 */
/* Crc - 32 BIT ANSI X3.66 CRC checksum files
Also known as: ISO 3307
**********************************************************************|
* *|
* Demonstration program to compute the 32-bit CRC used as the frame *|
* check sequence in ADCCP (ANSI X3.66, also known as FIPS PUB 71 *|
* and FED-STD-1003, the U.S. versions of CCITT's X.25 link-level *|
* protocol). The 32-bit FCS was added via the Federal Register, *|
* 1 June 1982, p.23798. I presume but don't know for certain that *|
* this polynomial is or will be included in CCITT V.41, which *|
* defines the 16-bit CRC (often called CRC-CCITT) polynomial. FIPS *|
* PUB 78 says that the 32-bit FCS reduces otherwise undetected *|
* errors by a factor of 10^-5 over 16-bit FCS. *|
* *|
**********************************************************************|
Copyright (C) 1986 Gary S. Brown. You may use this program, or
code or tables extracted from it, as desired without restriction.
First, the polynomial itself and its table of feedback terms. The
polynomial is
X^32+X^26+X^23+X^22+X^16+X^12+X^11+X^10+X^8+X^7+X^5+X^4+X^2+X^1+X^0
Note that we take it "backwards" and put the highest-order term in
the lowest-order bit. The X^32 term is "implied"; the LSB is the
X^31 term, etc. The X^0 term (usually shown as "+1") results in
the MSB being 1.
Note that the usual hardware shift register implementation, which
is what we're using (we're merely optimizing it by doing eight-bit
chunks at a time) shifts bits into the lowest-order term. In our
implementation, that means shifting towards the right. Why do we
do it this way? Because the calculated CRC must be transmitted in
order from highest-order term to lowest-order term. UARTs transmit
characters in order from LSB to MSB. By storing the CRC this way,
we hand it to the UART in the order low-byte to high-byte; the UART
sends each low-bit to hight-bit; and the result is transmission bit
by bit from highest- to lowest-order term without requiring any bit
shuffling on our part. Reception works similarly.
The feedback terms table consists of 256, 32-bit entries. Notes:
1. The table can be generated at runtime if desired; code to do so
is shown later. It might not be obvious, but the feedback
terms simply represent the results of eight shift/xor opera-
tions for all combinations of data and CRC register values.
2. The CRC accumulation logic is the same for all CRC polynomials,
be they sixteen or thirty-two bits wide. You simply choose the
appropriate table. Alternatively, because the table can be
generated at runtime, you can start by generating the table for
the polynomial in question and use exactly the same "updcrc",
if your application needn't simultaneously handle two CRC
polynomials. (Note, however, that XMODEM is strange.)
3. For 16-bit CRCs, the table entries need be only 16 bits wide;
of course, 32-bit entries work OK if the high 16 bits are zero.
4. The values must be right-shifted by eight bits by the "updcrc"
logic; the shift must be unsigned (bring in zeroes). On some
hardware you could probably optimize the shift in assembler by
using byte-swap instructions.
********************************************************************/
static unsigned int crc_32_tab[256] = {
0x00000000U, 0x77073096U, 0xee0e612cU, 0x990951baU, 0x076dc419U,
0x706af48fU, 0xe963a535U, 0x9e6495a3U, 0x0edb8832U, 0x79dcb8a4U,
0xe0d5e91eU, 0x97d2d988U, 0x09b64c2bU, 0x7eb17cbdU, 0xe7b82d07U,
0x90bf1d91U, 0x1db71064U, 0x6ab020f2U, 0xf3b97148U, 0x84be41deU,
0x1adad47dU, 0x6ddde4ebU, 0xf4d4b551U, 0x83d385c7U, 0x136c9856U,
0x646ba8c0U, 0xfd62f97aU, 0x8a65c9ecU, 0x14015c4fU, 0x63066cd9U,
0xfa0f3d63U, 0x8d080df5U, 0x3b6e20c8U, 0x4c69105eU, 0xd56041e4U,
0xa2677172U, 0x3c03e4d1U, 0x4b04d447U, 0xd20d85fdU, 0xa50ab56bU,
0x35b5a8faU, 0x42b2986cU, 0xdbbbc9d6U, 0xacbcf940U, 0x32d86ce3U,
0x45df5c75U, 0xdcd60dcfU, 0xabd13d59U, 0x26d930acU, 0x51de003aU,
0xc8d75180U, 0xbfd06116U, 0x21b4f4b5U, 0x56b3c423U, 0xcfba9599U,
0xb8bda50fU, 0x2802b89eU, 0x5f058808U, 0xc60cd9b2U, 0xb10be924U,
0x2f6f7c87U, 0x58684c11U, 0xc1611dabU, 0xb6662d3dU, 0x76dc4190U,
0x01db7106U, 0x98d220bcU, 0xefd5102aU, 0x71b18589U, 0x06b6b51fU,
0x9fbfe4a5U, 0xe8b8d433U, 0x7807c9a2U, 0x0f00f934U, 0x9609a88eU,
0xe10e9818U, 0x7f6a0dbbU, 0x086d3d2dU, 0x91646c97U, 0xe6635c01U,
0x6b6b51f4U, 0x1c6c6162U, 0x856530d8U, 0xf262004eU, 0x6c0695edU,
0x1b01a57bU, 0x8208f4c1U, 0xf50fc457U, 0x65b0d9c6U, 0x12b7e950U,
0x8bbeb8eaU, 0xfcb9887cU, 0x62dd1ddfU, 0x15da2d49U, 0x8cd37cf3U,
0xfbd44c65U, 0x4db26158U, 0x3ab551ceU, 0xa3bc0074U, 0xd4bb30e2U,
0x4adfa541U, 0x3dd895d7U, 0xa4d1c46dU, 0xd3d6f4fbU, 0x4369e96aU,
0x346ed9fcU, 0xad678846U, 0xda60b8d0U, 0x44042d73U, 0x33031de5U,
0xaa0a4c5fU, 0xdd0d7cc9U, 0x5005713cU, 0x270241aaU, 0xbe0b1010U,
0xc90c2086U, 0x5768b525U, 0x206f85b3U, 0xb966d409U, 0xce61e49fU,
0x5edef90eU, 0x29d9c998U, 0xb0d09822U, 0xc7d7a8b4U, 0x59b33d17U,
0x2eb40d81U, 0xb7bd5c3bU, 0xc0ba6cadU, 0xedb88320U, 0x9abfb3b6U,
0x03b6e20cU, 0x74b1d29aU, 0xead54739U, 0x9dd277afU, 0x04db2615U,
0x73dc1683U, 0xe3630b12U, 0x94643b84U, 0x0d6d6a3eU, 0x7a6a5aa8U,
0xe40ecf0bU, 0x9309ff9dU, 0x0a00ae27U, 0x7d079eb1U, 0xf00f9344U,
0x8708a3d2U, 0x1e01f268U, 0x6906c2feU, 0xf762575dU, 0x806567cbU,
0x196c3671U, 0x6e6b06e7U, 0xfed41b76U, 0x89d32be0U, 0x10da7a5aU,