forked from python/cpython
-
Notifications
You must be signed in to change notification settings - Fork 0
/
Copy path_lzmamodule.c
1488 lines (1260 loc) · 46 KB
/
_lzmamodule.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
/* _lzma - Low-level Python interface to liblzma.
Initial implementation by Per Øyvind Karlsen.
Rewritten by Nadeem Vawda.
*/
#define PY_SSIZE_T_CLEAN
#include "Python.h"
#include "structmember.h"
#include "pythread.h"
#include <stdarg.h>
#include <string.h>
#include <lzma.h>
#define ACQUIRE_LOCK(obj) do { \
if (!PyThread_acquire_lock((obj)->lock, 0)) { \
Py_BEGIN_ALLOW_THREADS \
PyThread_acquire_lock((obj)->lock, 1); \
Py_END_ALLOW_THREADS \
} } while (0)
#define RELEASE_LOCK(obj) PyThread_release_lock((obj)->lock)
/* Container formats: */
enum {
FORMAT_AUTO,
FORMAT_XZ,
FORMAT_ALONE,
FORMAT_RAW,
};
#define LZMA_CHECK_UNKNOWN (LZMA_CHECK_ID_MAX + 1)
typedef struct {
PyObject_HEAD
lzma_allocator alloc;
lzma_stream lzs;
int flushed;
PyThread_type_lock lock;
} Compressor;
typedef struct {
PyObject_HEAD
lzma_allocator alloc;
lzma_stream lzs;
int check;
char eof;
PyObject *unused_data;
char needs_input;
uint8_t *input_buffer;
size_t input_buffer_size;
PyThread_type_lock lock;
} Decompressor;
/* LZMAError class object. */
static PyObject *Error;
/* An empty tuple, used by the filter specifier parsing code. */
static PyObject *empty_tuple;
/* Helper functions. */
static int
catch_lzma_error(lzma_ret lzret)
{
switch (lzret) {
case LZMA_OK:
case LZMA_GET_CHECK:
case LZMA_NO_CHECK:
case LZMA_STREAM_END:
return 0;
case LZMA_UNSUPPORTED_CHECK:
PyErr_SetString(Error, "Unsupported integrity check");
return 1;
case LZMA_MEM_ERROR:
PyErr_NoMemory();
return 1;
case LZMA_MEMLIMIT_ERROR:
PyErr_SetString(Error, "Memory usage limit exceeded");
return 1;
case LZMA_FORMAT_ERROR:
PyErr_SetString(Error, "Input format not supported by decoder");
return 1;
case LZMA_OPTIONS_ERROR:
PyErr_SetString(Error, "Invalid or unsupported options");
return 1;
case LZMA_DATA_ERROR:
PyErr_SetString(Error, "Corrupt input data");
return 1;
case LZMA_BUF_ERROR:
PyErr_SetString(Error, "Insufficient buffer space");
return 1;
case LZMA_PROG_ERROR:
PyErr_SetString(Error, "Internal error");
return 1;
default:
PyErr_Format(Error, "Unrecognized error from liblzma: %d", lzret);
return 1;
}
}
static void*
PyLzma_Malloc(void *opaque, size_t items, size_t size)
{
if (size != 0 && items > (size_t)PY_SSIZE_T_MAX / size)
return NULL;
/* PyMem_Malloc() cannot be used:
the GIL is not held when lzma_code() is called */
return PyMem_RawMalloc(items * size);
}
static void
PyLzma_Free(void *opaque, void *ptr)
{
PyMem_RawFree(ptr);
}
#if BUFSIZ < 8192
#define INITIAL_BUFFER_SIZE 8192
#else
#define INITIAL_BUFFER_SIZE BUFSIZ
#endif
static int
grow_buffer(PyObject **buf, Py_ssize_t max_length)
{
Py_ssize_t size = PyBytes_GET_SIZE(*buf);
Py_ssize_t newsize = size + (size >> 3) + 6;
if (max_length > 0 && newsize > max_length)
newsize = max_length;
return _PyBytes_Resize(buf, newsize);
}
/* Some custom type conversions for PyArg_ParseTupleAndKeywords(),
since the predefined conversion specifiers do not suit our needs:
uint32_t - the "I" (unsigned int) specifier is the right size, but
silently ignores overflows on conversion.
lzma_vli - the "K" (unsigned long long) specifier is the right
size, but like "I" it silently ignores overflows on conversion.
lzma_mode and lzma_match_finder - these are enumeration types, and
so the size of each is implementation-defined. Worse, different
enum types can be of different sizes within the same program, so
to be strictly correct, we need to define two separate converters.
*/
#define INT_TYPE_CONVERTER_FUNC(TYPE, FUNCNAME) \
static int \
FUNCNAME(PyObject *obj, void *ptr) \
{ \
unsigned long long val; \
\
val = PyLong_AsUnsignedLongLong(obj); \
if (PyErr_Occurred()) \
return 0; \
if ((unsigned long long)(TYPE)val != val) { \
PyErr_SetString(PyExc_OverflowError, \
"Value too large for " #TYPE " type"); \
return 0; \
} \
*(TYPE *)ptr = (TYPE)val; \
return 1; \
}
INT_TYPE_CONVERTER_FUNC(uint32_t, uint32_converter)
INT_TYPE_CONVERTER_FUNC(lzma_vli, lzma_vli_converter)
INT_TYPE_CONVERTER_FUNC(lzma_mode, lzma_mode_converter)
INT_TYPE_CONVERTER_FUNC(lzma_match_finder, lzma_mf_converter)
#undef INT_TYPE_CONVERTER_FUNC
/* Filter specifier parsing.
This code handles converting filter specifiers (Python dicts) into
the C lzma_filter structs expected by liblzma. */
static void *
parse_filter_spec_lzma(PyObject *spec)
{
static char *optnames[] = {"id", "preset", "dict_size", "lc", "lp",
"pb", "mode", "nice_len", "mf", "depth", NULL};
PyObject *id;
PyObject *preset_obj;
uint32_t preset = LZMA_PRESET_DEFAULT;
lzma_options_lzma *options;
/* First, fill in default values for all the options using a preset.
Then, override the defaults with any values given by the caller. */
preset_obj = PyMapping_GetItemString(spec, "preset");
if (preset_obj == NULL) {
if (PyErr_ExceptionMatches(PyExc_KeyError))
PyErr_Clear();
else
return NULL;
} else {
int ok = uint32_converter(preset_obj, &preset);
Py_DECREF(preset_obj);
if (!ok)
return NULL;
}
options = (lzma_options_lzma *)PyMem_Malloc(sizeof *options);
if (options == NULL)
return PyErr_NoMemory();
memset(options, 0, sizeof *options);
if (lzma_lzma_preset(options, preset)) {
PyMem_Free(options);
PyErr_Format(Error, "Invalid compression preset: %u", preset);
return NULL;
}
if (!PyArg_ParseTupleAndKeywords(empty_tuple, spec,
"|OOO&O&O&O&O&O&O&O&", optnames,
&id, &preset_obj,
uint32_converter, &options->dict_size,
uint32_converter, &options->lc,
uint32_converter, &options->lp,
uint32_converter, &options->pb,
lzma_mode_converter, &options->mode,
uint32_converter, &options->nice_len,
lzma_mf_converter, &options->mf,
uint32_converter, &options->depth)) {
PyErr_SetString(PyExc_ValueError,
"Invalid filter specifier for LZMA filter");
PyMem_Free(options);
options = NULL;
}
return options;
}
static void *
parse_filter_spec_delta(PyObject *spec)
{
static char *optnames[] = {"id", "dist", NULL};
PyObject *id;
uint32_t dist = 1;
lzma_options_delta *options;
if (!PyArg_ParseTupleAndKeywords(empty_tuple, spec, "|OO&", optnames,
&id, uint32_converter, &dist)) {
PyErr_SetString(PyExc_ValueError,
"Invalid filter specifier for delta filter");
return NULL;
}
options = (lzma_options_delta *)PyMem_Malloc(sizeof *options);
if (options == NULL)
return PyErr_NoMemory();
memset(options, 0, sizeof *options);
options->type = LZMA_DELTA_TYPE_BYTE;
options->dist = dist;
return options;
}
static void *
parse_filter_spec_bcj(PyObject *spec)
{
static char *optnames[] = {"id", "start_offset", NULL};
PyObject *id;
uint32_t start_offset = 0;
lzma_options_bcj *options;
if (!PyArg_ParseTupleAndKeywords(empty_tuple, spec, "|OO&", optnames,
&id, uint32_converter, &start_offset)) {
PyErr_SetString(PyExc_ValueError,
"Invalid filter specifier for BCJ filter");
return NULL;
}
options = (lzma_options_bcj *)PyMem_Malloc(sizeof *options);
if (options == NULL)
return PyErr_NoMemory();
memset(options, 0, sizeof *options);
options->start_offset = start_offset;
return options;
}
static int
lzma_filter_converter(PyObject *spec, void *ptr)
{
lzma_filter *f = (lzma_filter *)ptr;
PyObject *id_obj;
if (!PyMapping_Check(spec)) {
PyErr_SetString(PyExc_TypeError,
"Filter specifier must be a dict or dict-like object");
return 0;
}
id_obj = PyMapping_GetItemString(spec, "id");
if (id_obj == NULL) {
if (PyErr_ExceptionMatches(PyExc_KeyError))
PyErr_SetString(PyExc_ValueError,
"Filter specifier must have an \"id\" entry");
return 0;
}
f->id = PyLong_AsUnsignedLongLong(id_obj);
Py_DECREF(id_obj);
if (PyErr_Occurred())
return 0;
switch (f->id) {
case LZMA_FILTER_LZMA1:
case LZMA_FILTER_LZMA2:
f->options = parse_filter_spec_lzma(spec);
return f->options != NULL;
case LZMA_FILTER_DELTA:
f->options = parse_filter_spec_delta(spec);
return f->options != NULL;
case LZMA_FILTER_X86:
case LZMA_FILTER_POWERPC:
case LZMA_FILTER_IA64:
case LZMA_FILTER_ARM:
case LZMA_FILTER_ARMTHUMB:
case LZMA_FILTER_SPARC:
f->options = parse_filter_spec_bcj(spec);
return f->options != NULL;
default:
PyErr_Format(PyExc_ValueError, "Invalid filter ID: %llu", f->id);
return 0;
}
}
static void
free_filter_chain(lzma_filter filters[])
{
int i;
for (i = 0; filters[i].id != LZMA_VLI_UNKNOWN; i++)
PyMem_Free(filters[i].options);
}
static int
parse_filter_chain_spec(lzma_filter filters[], PyObject *filterspecs)
{
Py_ssize_t i, num_filters;
num_filters = PySequence_Length(filterspecs);
if (num_filters == -1)
return -1;
if (num_filters > LZMA_FILTERS_MAX) {
PyErr_Format(PyExc_ValueError,
"Too many filters - liblzma supports a maximum of %d",
LZMA_FILTERS_MAX);
return -1;
}
for (i = 0; i < num_filters; i++) {
int ok = 1;
PyObject *spec = PySequence_GetItem(filterspecs, i);
if (spec == NULL || !lzma_filter_converter(spec, &filters[i]))
ok = 0;
Py_XDECREF(spec);
if (!ok) {
filters[i].id = LZMA_VLI_UNKNOWN;
free_filter_chain(filters);
return -1;
}
}
filters[num_filters].id = LZMA_VLI_UNKNOWN;
return 0;
}
/* Filter specifier construction.
This code handles converting C lzma_filter structs into
Python-level filter specifiers (represented as dicts). */
static int
spec_add_field(PyObject *spec, _Py_Identifier *key, unsigned long long value)
{
int status;
PyObject *value_object;
value_object = PyLong_FromUnsignedLongLong(value);
if (value_object == NULL)
return -1;
status = _PyDict_SetItemId(spec, key, value_object);
Py_DECREF(value_object);
return status;
}
static PyObject *
build_filter_spec(const lzma_filter *f)
{
PyObject *spec;
spec = PyDict_New();
if (spec == NULL)
return NULL;
#define ADD_FIELD(SOURCE, FIELD) \
do { \
_Py_IDENTIFIER(FIELD); \
if (spec_add_field(spec, &PyId_##FIELD, SOURCE->FIELD) == -1) \
goto error;\
} while (0)
ADD_FIELD(f, id);
switch (f->id) {
/* For LZMA1 filters, lzma_properties_{encode,decode}() only look at the
lc, lp, pb, and dict_size fields. For LZMA2 filters, only the
dict_size field is used. */
case LZMA_FILTER_LZMA1: {
lzma_options_lzma *options = f->options;
ADD_FIELD(options, lc);
ADD_FIELD(options, lp);
ADD_FIELD(options, pb);
ADD_FIELD(options, dict_size);
break;
}
case LZMA_FILTER_LZMA2: {
lzma_options_lzma *options = f->options;
ADD_FIELD(options, dict_size);
break;
}
case LZMA_FILTER_DELTA: {
lzma_options_delta *options = f->options;
ADD_FIELD(options, dist);
break;
}
case LZMA_FILTER_X86:
case LZMA_FILTER_POWERPC:
case LZMA_FILTER_IA64:
case LZMA_FILTER_ARM:
case LZMA_FILTER_ARMTHUMB:
case LZMA_FILTER_SPARC: {
lzma_options_bcj *options = f->options;
ADD_FIELD(options, start_offset);
break;
}
default:
PyErr_Format(PyExc_ValueError, "Invalid filter ID: %llu", f->id);
goto error;
}
#undef ADD_FIELD
return spec;
error:
Py_DECREF(spec);
return NULL;
}
/*[clinic input]
module _lzma
class _lzma.LZMACompressor "Compressor *" "&Compressor_type"
class _lzma.LZMADecompressor "Decompressor *" "&Decompressor_type"
[clinic start generated code]*/
/*[clinic end generated code: output=da39a3ee5e6b4b0d input=2c14bbe05ff0c147]*/
#include "clinic/_lzmamodule.c.h"
/*[python input]
class lzma_vli_converter(CConverter):
type = 'lzma_vli'
converter = 'lzma_vli_converter'
class lzma_filter_converter(CConverter):
type = 'lzma_filter'
converter = 'lzma_filter_converter'
c_default = c_ignored_default = "{LZMA_VLI_UNKNOWN, NULL}"
def cleanup(self):
name = ensure_legal_c_identifier(self.name)
return ('if (%(name)s.id != LZMA_VLI_UNKNOWN)\n'
' PyMem_Free(%(name)s.options);\n') % {'name': name}
[python start generated code]*/
/*[python end generated code: output=da39a3ee5e6b4b0d input=74fe7631ce377a94]*/
/* LZMACompressor class. */
static PyObject *
compress(Compressor *c, uint8_t *data, size_t len, lzma_action action)
{
Py_ssize_t data_size = 0;
PyObject *result;
result = PyBytes_FromStringAndSize(NULL, INITIAL_BUFFER_SIZE);
if (result == NULL)
return NULL;
c->lzs.next_in = data;
c->lzs.avail_in = len;
c->lzs.next_out = (uint8_t *)PyBytes_AS_STRING(result);
c->lzs.avail_out = PyBytes_GET_SIZE(result);
for (;;) {
lzma_ret lzret;
Py_BEGIN_ALLOW_THREADS
lzret = lzma_code(&c->lzs, action);
data_size = (char *)c->lzs.next_out - PyBytes_AS_STRING(result);
if (lzret == LZMA_BUF_ERROR && len == 0 && c->lzs.avail_out > 0)
lzret = LZMA_OK; /* That wasn't a real error */
Py_END_ALLOW_THREADS
if (catch_lzma_error(lzret))
goto error;
if ((action == LZMA_RUN && c->lzs.avail_in == 0) ||
(action == LZMA_FINISH && lzret == LZMA_STREAM_END)) {
break;
} else if (c->lzs.avail_out == 0) {
if (grow_buffer(&result, -1) == -1)
goto error;
c->lzs.next_out = (uint8_t *)PyBytes_AS_STRING(result) + data_size;
c->lzs.avail_out = PyBytes_GET_SIZE(result) - data_size;
}
}
if (data_size != PyBytes_GET_SIZE(result))
if (_PyBytes_Resize(&result, data_size) == -1)
goto error;
return result;
error:
Py_XDECREF(result);
return NULL;
}
/*[clinic input]
_lzma.LZMACompressor.compress
data: Py_buffer
/
Provide data to the compressor object.
Returns a chunk of compressed data if possible, or b'' otherwise.
When you have finished providing data to the compressor, call the
flush() method to finish the compression process.
[clinic start generated code]*/
static PyObject *
_lzma_LZMACompressor_compress_impl(Compressor *self, Py_buffer *data)
/*[clinic end generated code: output=31f615136963e00f input=64019eac7f2cc8d0]*/
{
PyObject *result = NULL;
ACQUIRE_LOCK(self);
if (self->flushed)
PyErr_SetString(PyExc_ValueError, "Compressor has been flushed");
else
result = compress(self, data->buf, data->len, LZMA_RUN);
RELEASE_LOCK(self);
return result;
}
/*[clinic input]
_lzma.LZMACompressor.flush
Finish the compression process.
Returns the compressed data left in internal buffers.
The compressor object may not be used after this method is called.
[clinic start generated code]*/
static PyObject *
_lzma_LZMACompressor_flush_impl(Compressor *self)
/*[clinic end generated code: output=fec21f3e22504f50 input=6b369303f67ad0a8]*/
{
PyObject *result = NULL;
ACQUIRE_LOCK(self);
if (self->flushed) {
PyErr_SetString(PyExc_ValueError, "Repeated call to flush()");
} else {
self->flushed = 1;
result = compress(self, NULL, 0, LZMA_FINISH);
}
RELEASE_LOCK(self);
return result;
}
static int
Compressor_init_xz(lzma_stream *lzs, int check, uint32_t preset,
PyObject *filterspecs)
{
lzma_ret lzret;
if (filterspecs == Py_None) {
lzret = lzma_easy_encoder(lzs, preset, check);
} else {
lzma_filter filters[LZMA_FILTERS_MAX + 1];
if (parse_filter_chain_spec(filters, filterspecs) == -1)
return -1;
lzret = lzma_stream_encoder(lzs, filters, check);
free_filter_chain(filters);
}
if (catch_lzma_error(lzret))
return -1;
else
return 0;
}
static int
Compressor_init_alone(lzma_stream *lzs, uint32_t preset, PyObject *filterspecs)
{
lzma_ret lzret;
if (filterspecs == Py_None) {
lzma_options_lzma options;
if (lzma_lzma_preset(&options, preset)) {
PyErr_Format(Error, "Invalid compression preset: %u", preset);
return -1;
}
lzret = lzma_alone_encoder(lzs, &options);
} else {
lzma_filter filters[LZMA_FILTERS_MAX + 1];
if (parse_filter_chain_spec(filters, filterspecs) == -1)
return -1;
if (filters[0].id == LZMA_FILTER_LZMA1 &&
filters[1].id == LZMA_VLI_UNKNOWN) {
lzret = lzma_alone_encoder(lzs, filters[0].options);
} else {
PyErr_SetString(PyExc_ValueError,
"Invalid filter chain for FORMAT_ALONE - "
"must be a single LZMA1 filter");
lzret = LZMA_PROG_ERROR;
}
free_filter_chain(filters);
}
if (PyErr_Occurred() || catch_lzma_error(lzret))
return -1;
else
return 0;
}
static int
Compressor_init_raw(lzma_stream *lzs, PyObject *filterspecs)
{
lzma_filter filters[LZMA_FILTERS_MAX + 1];
lzma_ret lzret;
if (filterspecs == Py_None) {
PyErr_SetString(PyExc_ValueError,
"Must specify filters for FORMAT_RAW");
return -1;
}
if (parse_filter_chain_spec(filters, filterspecs) == -1)
return -1;
lzret = lzma_raw_encoder(lzs, filters);
free_filter_chain(filters);
if (catch_lzma_error(lzret))
return -1;
else
return 0;
}
/*[-clinic input]
_lzma.LZMACompressor.__init__
format: int(c_default="FORMAT_XZ") = FORMAT_XZ
The container format to use for the output. This can
be FORMAT_XZ (default), FORMAT_ALONE, or FORMAT_RAW.
check: int(c_default="-1") = unspecified
The integrity check to use. For FORMAT_XZ, the default
is CHECK_CRC64. FORMAT_ALONE and FORMAT_RAW do not support integrity
checks; for these formats, check must be omitted, or be CHECK_NONE.
preset: object = None
If provided should be an integer in the range 0-9, optionally
OR-ed with the constant PRESET_EXTREME.
filters: object = None
If provided should be a sequence of dicts. Each dict should
have an entry for "id" indicating the ID of the filter, plus
additional entries for options to the filter.
Create a compressor object for compressing data incrementally.
The settings used by the compressor can be specified either as a
preset compression level (with the 'preset' argument), or in detail
as a custom filter chain (with the 'filters' argument). For FORMAT_XZ
and FORMAT_ALONE, the default is to use the PRESET_DEFAULT preset
level. For FORMAT_RAW, the caller must always specify a filter chain;
the raw compressor does not support preset compression levels.
For one-shot compression, use the compress() function instead.
[-clinic start generated code]*/
static int
Compressor_init(Compressor *self, PyObject *args, PyObject *kwargs)
{
static char *arg_names[] = {"format", "check", "preset", "filters", NULL};
int format = FORMAT_XZ;
int check = -1;
uint32_t preset = LZMA_PRESET_DEFAULT;
PyObject *preset_obj = Py_None;
PyObject *filterspecs = Py_None;
if (!PyArg_ParseTupleAndKeywords(args, kwargs,
"|iiOO:LZMACompressor", arg_names,
&format, &check, &preset_obj,
&filterspecs))
return -1;
if (format != FORMAT_XZ && check != -1 && check != LZMA_CHECK_NONE) {
PyErr_SetString(PyExc_ValueError,
"Integrity checks are only supported by FORMAT_XZ");
return -1;
}
if (preset_obj != Py_None && filterspecs != Py_None) {
PyErr_SetString(PyExc_ValueError,
"Cannot specify both preset and filter chain");
return -1;
}
if (preset_obj != Py_None)
if (!uint32_converter(preset_obj, &preset))
return -1;
self->alloc.opaque = NULL;
self->alloc.alloc = PyLzma_Malloc;
self->alloc.free = PyLzma_Free;
self->lzs.allocator = &self->alloc;
self->lock = PyThread_allocate_lock();
if (self->lock == NULL) {
PyErr_SetString(PyExc_MemoryError, "Unable to allocate lock");
return -1;
}
self->flushed = 0;
switch (format) {
case FORMAT_XZ:
if (check == -1)
check = LZMA_CHECK_CRC64;
if (Compressor_init_xz(&self->lzs, check, preset, filterspecs) != 0)
break;
return 0;
case FORMAT_ALONE:
if (Compressor_init_alone(&self->lzs, preset, filterspecs) != 0)
break;
return 0;
case FORMAT_RAW:
if (Compressor_init_raw(&self->lzs, filterspecs) != 0)
break;
return 0;
default:
PyErr_Format(PyExc_ValueError,
"Invalid container format: %d", format);
break;
}
PyThread_free_lock(self->lock);
self->lock = NULL;
return -1;
}
static void
Compressor_dealloc(Compressor *self)
{
lzma_end(&self->lzs);
if (self->lock != NULL)
PyThread_free_lock(self->lock);
Py_TYPE(self)->tp_free((PyObject *)self);
}
static PyMethodDef Compressor_methods[] = {
_LZMA_LZMACOMPRESSOR_COMPRESS_METHODDEF
_LZMA_LZMACOMPRESSOR_FLUSH_METHODDEF
{NULL}
};
PyDoc_STRVAR(Compressor_doc,
"LZMACompressor(format=FORMAT_XZ, check=-1, preset=None, filters=None)\n"
"\n"
"Create a compressor object for compressing data incrementally.\n"
"\n"
"format specifies the container format to use for the output. This can\n"
"be FORMAT_XZ (default), FORMAT_ALONE, or FORMAT_RAW.\n"
"\n"
"check specifies the integrity check to use. For FORMAT_XZ, the default\n"
"is CHECK_CRC64. FORMAT_ALONE and FORMAT_RAW do not support integrity\n"
"checks; for these formats, check must be omitted, or be CHECK_NONE.\n"
"\n"
"The settings used by the compressor can be specified either as a\n"
"preset compression level (with the 'preset' argument), or in detail\n"
"as a custom filter chain (with the 'filters' argument). For FORMAT_XZ\n"
"and FORMAT_ALONE, the default is to use the PRESET_DEFAULT preset\n"
"level. For FORMAT_RAW, the caller must always specify a filter chain;\n"
"the raw compressor does not support preset compression levels.\n"
"\n"
"preset (if provided) should be an integer in the range 0-9, optionally\n"
"OR-ed with the constant PRESET_EXTREME.\n"
"\n"
"filters (if provided) should be a sequence of dicts. Each dict should\n"
"have an entry for \"id\" indicating the ID of the filter, plus\n"
"additional entries for options to the filter.\n"
"\n"
"For one-shot compression, use the compress() function instead.\n");
static PyTypeObject Compressor_type = {
PyVarObject_HEAD_INIT(NULL, 0)
"_lzma.LZMACompressor", /* tp_name */
sizeof(Compressor), /* tp_basicsize */
0, /* tp_itemsize */
(destructor)Compressor_dealloc, /* tp_dealloc */
0, /* tp_print */
0, /* tp_getattr */
0, /* tp_setattr */
0, /* tp_reserved */
0, /* tp_repr */
0, /* tp_as_number */
0, /* tp_as_sequence */
0, /* tp_as_mapping */
0, /* tp_hash */
0, /* tp_call */
0, /* tp_str */
0, /* tp_getattro */
0, /* tp_setattro */
0, /* tp_as_buffer */
Py_TPFLAGS_DEFAULT, /* tp_flags */
Compressor_doc, /* tp_doc */
0, /* tp_traverse */
0, /* tp_clear */
0, /* tp_richcompare */
0, /* tp_weaklistoffset */
0, /* tp_iter */
0, /* tp_iternext */
Compressor_methods, /* tp_methods */
0, /* tp_members */
0, /* tp_getset */
0, /* tp_base */
0, /* tp_dict */
0, /* tp_descr_get */
0, /* tp_descr_set */
0, /* tp_dictoffset */
(initproc)Compressor_init, /* tp_init */
0, /* tp_alloc */
PyType_GenericNew, /* tp_new */
};
/* LZMADecompressor class. */
/* Decompress data of length d->lzs.avail_in in d->lzs.next_in. The output
buffer is allocated dynamically and returned. At most max_length bytes are
returned, so some of the input may not be consumed. d->lzs.next_in and
d->lzs.avail_in are updated to reflect the consumed input. */
static PyObject*
decompress_buf(Decompressor *d, Py_ssize_t max_length)
{
Py_ssize_t data_size = 0;
PyObject *result;
lzma_stream *lzs = &d->lzs;
if (lzs->avail_in == 0)
return PyBytes_FromStringAndSize(NULL, 0);
if (max_length < 0 || max_length >= INITIAL_BUFFER_SIZE)
result = PyBytes_FromStringAndSize(NULL, INITIAL_BUFFER_SIZE);
else
result = PyBytes_FromStringAndSize(NULL, max_length);
if (result == NULL)
return NULL;
lzs->next_out = (uint8_t *)PyBytes_AS_STRING(result);
lzs->avail_out = PyBytes_GET_SIZE(result);
for (;;) {
lzma_ret lzret;
Py_BEGIN_ALLOW_THREADS
lzret = lzma_code(lzs, LZMA_RUN);
data_size = (char *)lzs->next_out - PyBytes_AS_STRING(result);
Py_END_ALLOW_THREADS
if (catch_lzma_error(lzret))
goto error;
if (lzret == LZMA_GET_CHECK || lzret == LZMA_NO_CHECK)
d->check = lzma_get_check(&d->lzs);
if (lzret == LZMA_STREAM_END) {
d->eof = 1;
break;
} else if (lzs->avail_in == 0) {
break;
} else if (lzs->avail_out == 0) {
if (data_size == max_length)
break;
if (grow_buffer(&result, max_length) == -1)
goto error;
lzs->next_out = (uint8_t *)PyBytes_AS_STRING(result) + data_size;
lzs->avail_out = PyBytes_GET_SIZE(result) - data_size;
}
}
if (data_size != PyBytes_GET_SIZE(result))
if (_PyBytes_Resize(&result, data_size) == -1)
goto error;
return result;
error:
Py_XDECREF(result);
return NULL;
}
static PyObject *
decompress(Decompressor *d, uint8_t *data, size_t len, Py_ssize_t max_length)
{
char input_buffer_in_use;
PyObject *result;
lzma_stream *lzs = &d->lzs;
/* Prepend unconsumed input if necessary */
if (lzs->next_in != NULL) {
size_t avail_now, avail_total;
/* Number of bytes we can append to input buffer */
avail_now = (d->input_buffer + d->input_buffer_size)
- (lzs->next_in + lzs->avail_in);
/* Number of bytes we can append if we move existing
contents to beginning of buffer (overwriting
consumed input) */
avail_total = d->input_buffer_size - lzs->avail_in;
if (avail_total < len) {
size_t offset = lzs->next_in - d->input_buffer;
uint8_t *tmp;
size_t new_size = d->input_buffer_size + len - avail_now;
/* Assign to temporary variable first, so we don't
lose address of allocated buffer if realloc fails */
tmp = PyMem_Realloc(d->input_buffer, new_size);
if (tmp == NULL) {
PyErr_SetNone(PyExc_MemoryError);
return NULL;
}
d->input_buffer = tmp;
d->input_buffer_size = new_size;
lzs->next_in = d->input_buffer + offset;
}
else if (avail_now < len) {
memmove(d->input_buffer, lzs->next_in,
lzs->avail_in);
lzs->next_in = d->input_buffer;
}
memcpy((void*)(lzs->next_in + lzs->avail_in), data, len);
lzs->avail_in += len;
input_buffer_in_use = 1;
}
else {
lzs->next_in = data;
lzs->avail_in = len;
input_buffer_in_use = 0;
}
result = decompress_buf(d, max_length);
if (result == NULL) {
lzs->next_in = NULL;
return NULL;
}
if (d->eof) {
d->needs_input = 0;
if (lzs->avail_in > 0) {
Py_XSETREF(d->unused_data,
PyBytes_FromStringAndSize((char *)lzs->next_in, lzs->avail_in));
if (d->unused_data == NULL)
goto error;
}
}
else if (lzs->avail_in == 0) {
lzs->next_in = NULL;
d->needs_input = 1;
}
else {
d->needs_input = 0;
/* If we did not use the input buffer, we now have
to copy the tail from the caller's buffer into the
input buffer */