forked from python/cpython
-
Notifications
You must be signed in to change notification settings - Fork 0
/
Copy pathbz2module.c
2169 lines (1905 loc) · 51.7 KB
/
bz2module.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
/*
python-bz2 - python bz2 library interface
Copyright (c) 2002 Gustavo Niemeyer <[email protected]>
Copyright (c) 2002 Python Software Foundation; All Rights Reserved
*/
#include "Python.h"
#include <stdio.h>
#include <bzlib.h>
#include "structmember.h"
#ifdef WITH_THREAD
#include "pythread.h"
#endif
static char __author__[] =
"The bz2 python module was written by:\n\
\n\
Gustavo Niemeyer <[email protected]>\n\
";
#define BUF(v) PyString_AS_STRING((PyStringObject *)v)
#define MODE_CLOSED 0
#define MODE_READ 1
#define MODE_READ_EOF 2
#define MODE_WRITE 3
#define BZ2FileObject_Check(v) ((v)->ob_type == &BZ2File_Type)
#ifdef BZ_CONFIG_ERROR
#if SIZEOF_LONG >= 8
#define BZS_TOTAL_OUT(bzs) \
(((long)bzs->total_out_hi32 << 32) + bzs->total_out_lo32)
#elif SIZEOF_LONG_LONG >= 8
#define BZS_TOTAL_OUT(bzs) \
(((PY_LONG_LONG)bzs->total_out_hi32 << 32) + bzs->total_out_lo32)
#else
#define BZS_TOTAL_OUT(bzs) \
bzs->total_out_lo32;
#endif
#else /* ! BZ_CONFIG_ERROR */
#define BZ2_bzRead bzRead
#define BZ2_bzReadOpen bzReadOpen
#define BZ2_bzReadClose bzReadClose
#define BZ2_bzWrite bzWrite
#define BZ2_bzWriteOpen bzWriteOpen
#define BZ2_bzWriteClose bzWriteClose
#define BZ2_bzCompress bzCompress
#define BZ2_bzCompressInit bzCompressInit
#define BZ2_bzCompressEnd bzCompressEnd
#define BZ2_bzDecompress bzDecompress
#define BZ2_bzDecompressInit bzDecompressInit
#define BZ2_bzDecompressEnd bzDecompressEnd
#define BZS_TOTAL_OUT(bzs) bzs->total_out
#endif /* ! BZ_CONFIG_ERROR */
#ifdef WITH_THREAD
#define ACQUIRE_LOCK(obj) PyThread_acquire_lock(obj->lock, 1)
#define RELEASE_LOCK(obj) PyThread_release_lock(obj->lock)
#else
#define ACQUIRE_LOCK(obj)
#define RELEASE_LOCK(obj)
#endif
/* Bits in f_newlinetypes */
#define NEWLINE_UNKNOWN 0 /* No newline seen, yet */
#define NEWLINE_CR 1 /* \r newline seen */
#define NEWLINE_LF 2 /* \n newline seen */
#define NEWLINE_CRLF 4 /* \r\n newline seen */
/* ===================================================================== */
/* Structure definitions. */
typedef struct {
PyObject_HEAD
PyObject *file;
char* f_buf; /* Allocated readahead buffer */
char* f_bufend; /* Points after last occupied position */
char* f_bufptr; /* Current buffer position */
int f_softspace; /* Flag used by 'print' command */
int f_univ_newline; /* Handle any newline convention */
int f_newlinetypes; /* Types of newlines seen */
int f_skipnextlf; /* Skip next \n */
BZFILE *fp;
int mode;
long pos;
long size;
#ifdef WITH_THREAD
PyThread_type_lock lock;
#endif
} BZ2FileObject;
typedef struct {
PyObject_HEAD
bz_stream bzs;
int running;
#ifdef WITH_THREAD
PyThread_type_lock lock;
#endif
} BZ2CompObject;
typedef struct {
PyObject_HEAD
bz_stream bzs;
int running;
PyObject *unused_data;
#ifdef WITH_THREAD
PyThread_type_lock lock;
#endif
} BZ2DecompObject;
/* ===================================================================== */
/* Utility functions. */
static int
Util_CatchBZ2Error(int bzerror)
{
int ret = 0;
switch(bzerror) {
case BZ_OK:
case BZ_STREAM_END:
break;
#ifdef BZ_CONFIG_ERROR
case BZ_CONFIG_ERROR:
PyErr_SetString(PyExc_SystemError,
"the bz2 library was not compiled "
"correctly");
ret = 1;
break;
#endif
case BZ_PARAM_ERROR:
PyErr_SetString(PyExc_ValueError,
"the bz2 library has received wrong "
"parameters");
ret = 1;
break;
case BZ_MEM_ERROR:
PyErr_NoMemory();
ret = 1;
break;
case BZ_DATA_ERROR:
case BZ_DATA_ERROR_MAGIC:
PyErr_SetString(PyExc_IOError, "invalid data stream");
ret = 1;
break;
case BZ_IO_ERROR:
PyErr_SetString(PyExc_IOError, "unknown IO error");
ret = 1;
break;
case BZ_UNEXPECTED_EOF:
PyErr_SetString(PyExc_EOFError,
"compressed file ended before the "
"logical end-of-stream was detected");
ret = 1;
break;
case BZ_SEQUENCE_ERROR:
PyErr_SetString(PyExc_RuntimeError,
"wrong sequence of bz2 library "
"commands used");
ret = 1;
break;
}
return ret;
}
#if BUFSIZ < 8192
#define SMALLCHUNK 8192
#else
#define SMALLCHUNK BUFSIZ
#endif
#if SIZEOF_INT < 4
#define BIGCHUNK (512 * 32)
#else
#define BIGCHUNK (512 * 1024)
#endif
/* This is a hacked version of Python's fileobject.c:new_buffersize(). */
static size_t
Util_NewBufferSize(size_t currentsize)
{
if (currentsize > SMALLCHUNK) {
/* Keep doubling until we reach BIGCHUNK;
then keep adding BIGCHUNK. */
if (currentsize <= BIGCHUNK)
return currentsize + currentsize;
else
return currentsize + BIGCHUNK;
}
return currentsize + SMALLCHUNK;
}
/* This is a hacked version of Python's fileobject.c:get_line(). */
static PyObject *
Util_GetLine(BZ2FileObject *f, int n)
{
char c;
char *buf, *end;
size_t total_v_size; /* total # of slots in buffer */
size_t used_v_size; /* # used slots in buffer */
size_t increment; /* amount to increment the buffer */
PyObject *v;
int bzerror;
int newlinetypes = f->f_newlinetypes;
int skipnextlf = f->f_skipnextlf;
int univ_newline = f->f_univ_newline;
total_v_size = n > 0 ? n : 100;
v = PyString_FromStringAndSize((char *)NULL, total_v_size);
if (v == NULL)
return NULL;
buf = BUF(v);
end = buf + total_v_size;
for (;;) {
Py_BEGIN_ALLOW_THREADS
if (univ_newline) {
while (1) {
BZ2_bzRead(&bzerror, f->fp, &c, 1);
f->pos++;
if (bzerror != BZ_OK || buf == end)
break;
if (skipnextlf) {
skipnextlf = 0;
if (c == '\n') {
/* Seeing a \n here with
* skipnextlf true means we
* saw a \r before.
*/
newlinetypes |= NEWLINE_CRLF;
BZ2_bzRead(&bzerror, f->fp,
&c, 1);
if (bzerror != BZ_OK)
break;
} else {
newlinetypes |= NEWLINE_CR;
}
}
if (c == '\r') {
skipnextlf = 1;
c = '\n';
} else if ( c == '\n')
newlinetypes |= NEWLINE_LF;
*buf++ = c;
if (c == '\n') break;
}
if (bzerror == BZ_STREAM_END && skipnextlf)
newlinetypes |= NEWLINE_CR;
} else /* If not universal newlines use the normal loop */
do {
BZ2_bzRead(&bzerror, f->fp, &c, 1);
f->pos++;
*buf++ = c;
} while (bzerror == BZ_OK && c != '\n' && buf != end);
Py_END_ALLOW_THREADS
f->f_newlinetypes = newlinetypes;
f->f_skipnextlf = skipnextlf;
if (bzerror == BZ_STREAM_END) {
f->size = f->pos;
f->mode = MODE_READ_EOF;
break;
} else if (bzerror != BZ_OK) {
Util_CatchBZ2Error(bzerror);
Py_DECREF(v);
return NULL;
}
if (c == '\n')
break;
/* Must be because buf == end */
if (n > 0)
break;
used_v_size = total_v_size;
increment = total_v_size >> 2; /* mild exponential growth */
total_v_size += increment;
if (total_v_size > INT_MAX) {
PyErr_SetString(PyExc_OverflowError,
"line is longer than a Python string can hold");
Py_DECREF(v);
return NULL;
}
if (_PyString_Resize(&v, total_v_size) < 0)
return NULL;
buf = BUF(v) + used_v_size;
end = BUF(v) + total_v_size;
}
used_v_size = buf - BUF(v);
if (used_v_size != total_v_size)
_PyString_Resize(&v, used_v_size);
return v;
}
/* This is a hacked version of Python's
* fileobject.c:Py_UniversalNewlineFread(). */
size_t
Util_UnivNewlineRead(int *bzerror, BZFILE *stream,
char* buf, size_t n, BZ2FileObject *f)
{
char *dst = buf;
int newlinetypes, skipnextlf;
assert(buf != NULL);
assert(stream != NULL);
if (!f->f_univ_newline)
return BZ2_bzRead(bzerror, stream, buf, n);
newlinetypes = f->f_newlinetypes;
skipnextlf = f->f_skipnextlf;
/* Invariant: n is the number of bytes remaining to be filled
* in the buffer.
*/
while (n) {
size_t nread;
int shortread;
char *src = dst;
nread = BZ2_bzRead(bzerror, stream, dst, n);
assert(nread <= n);
n -= nread; /* assuming 1 byte out for each in; will adjust */
shortread = n != 0; /* true iff EOF or error */
while (nread--) {
char c = *src++;
if (c == '\r') {
/* Save as LF and set flag to skip next LF. */
*dst++ = '\n';
skipnextlf = 1;
}
else if (skipnextlf && c == '\n') {
/* Skip LF, and remember we saw CR LF. */
skipnextlf = 0;
newlinetypes |= NEWLINE_CRLF;
++n;
}
else {
/* Normal char to be stored in buffer. Also
* update the newlinetypes flag if either this
* is an LF or the previous char was a CR.
*/
if (c == '\n')
newlinetypes |= NEWLINE_LF;
else if (skipnextlf)
newlinetypes |= NEWLINE_CR;
*dst++ = c;
skipnextlf = 0;
}
}
if (shortread) {
/* If this is EOF, update type flags. */
if (skipnextlf && *bzerror == BZ_STREAM_END)
newlinetypes |= NEWLINE_CR;
break;
}
}
f->f_newlinetypes = newlinetypes;
f->f_skipnextlf = skipnextlf;
return dst - buf;
}
/* This is a hacked version of Python's fileobject.c:drop_readahead(). */
static void
Util_DropReadAhead(BZ2FileObject *f)
{
if (f->f_buf != NULL) {
PyMem_Free(f->f_buf);
f->f_buf = NULL;
}
}
/* This is a hacked version of Python's fileobject.c:readahead(). */
static int
Util_ReadAhead(BZ2FileObject *f, int bufsize)
{
int chunksize;
int bzerror;
if (f->f_buf != NULL) {
if((f->f_bufend - f->f_bufptr) >= 1)
return 0;
else
Util_DropReadAhead(f);
}
if (f->mode == MODE_READ_EOF) {
return -1;
}
if ((f->f_buf = PyMem_Malloc(bufsize)) == NULL) {
return -1;
}
Py_BEGIN_ALLOW_THREADS
chunksize = Util_UnivNewlineRead(&bzerror, f->fp, f->f_buf,
bufsize, f);
Py_END_ALLOW_THREADS
f->pos += chunksize;
if (bzerror == BZ_STREAM_END) {
f->size = f->pos;
f->mode = MODE_READ_EOF;
} else if (bzerror != BZ_OK) {
Util_CatchBZ2Error(bzerror);
Util_DropReadAhead(f);
return -1;
}
f->f_bufptr = f->f_buf;
f->f_bufend = f->f_buf + chunksize;
return 0;
}
/* This is a hacked version of Python's
* fileobject.c:readahead_get_line_skip(). */
static PyStringObject *
Util_ReadAheadGetLineSkip(BZ2FileObject *f, int skip, int bufsize)
{
PyStringObject* s;
char *bufptr;
char *buf;
int len;
if (f->f_buf == NULL)
if (Util_ReadAhead(f, bufsize) < 0)
return NULL;
len = f->f_bufend - f->f_bufptr;
if (len == 0)
return (PyStringObject *)
PyString_FromStringAndSize(NULL, skip);
bufptr = memchr(f->f_bufptr, '\n', len);
if (bufptr != NULL) {
bufptr++; /* Count the '\n' */
len = bufptr - f->f_bufptr;
s = (PyStringObject *)
PyString_FromStringAndSize(NULL, skip+len);
if (s == NULL)
return NULL;
memcpy(PyString_AS_STRING(s)+skip, f->f_bufptr, len);
f->f_bufptr = bufptr;
if (bufptr == f->f_bufend)
Util_DropReadAhead(f);
} else {
bufptr = f->f_bufptr;
buf = f->f_buf;
f->f_buf = NULL; /* Force new readahead buffer */
s = Util_ReadAheadGetLineSkip(f, skip+len,
bufsize + (bufsize>>2));
if (s == NULL) {
PyMem_Free(buf);
return NULL;
}
memcpy(PyString_AS_STRING(s)+skip, bufptr, len);
PyMem_Free(buf);
}
return s;
}
/* ===================================================================== */
/* Methods of BZ2File. */
PyDoc_STRVAR(BZ2File_read__doc__,
"read([size]) -> string\n\
\n\
Read at most size uncompressed bytes, returned as a string. If the size\n\
argument is negative or omitted, read until EOF is reached.\n\
");
/* This is a hacked version of Python's fileobject.c:file_read(). */
static PyObject *
BZ2File_read(BZ2FileObject *self, PyObject *args)
{
long bytesrequested = -1;
size_t bytesread, buffersize, chunksize;
int bzerror;
PyObject *ret = NULL;
if (!PyArg_ParseTuple(args, "|l:read", &bytesrequested))
return NULL;
ACQUIRE_LOCK(self);
switch (self->mode) {
case MODE_READ:
break;
case MODE_READ_EOF:
ret = PyString_FromString("");
goto cleanup;
case MODE_CLOSED:
PyErr_SetString(PyExc_ValueError,
"I/O operation on closed file");
goto cleanup;
default:
PyErr_SetString(PyExc_IOError,
"file is not ready for reading");
goto cleanup;
}
if (bytesrequested < 0)
buffersize = Util_NewBufferSize((size_t)0);
else
buffersize = bytesrequested;
if (buffersize > INT_MAX) {
PyErr_SetString(PyExc_OverflowError,
"requested number of bytes is "
"more than a Python string can hold");
goto cleanup;
}
ret = PyString_FromStringAndSize((char *)NULL, buffersize);
if (ret == NULL)
goto cleanup;
bytesread = 0;
for (;;) {
Py_BEGIN_ALLOW_THREADS
chunksize = Util_UnivNewlineRead(&bzerror, self->fp,
BUF(ret)+bytesread,
buffersize-bytesread,
self);
self->pos += chunksize;
Py_END_ALLOW_THREADS
bytesread += chunksize;
if (bzerror == BZ_STREAM_END) {
self->size = self->pos;
self->mode = MODE_READ_EOF;
break;
} else if (bzerror != BZ_OK) {
Util_CatchBZ2Error(bzerror);
Py_DECREF(ret);
ret = NULL;
goto cleanup;
}
if (bytesrequested < 0) {
buffersize = Util_NewBufferSize(buffersize);
if (_PyString_Resize(&ret, buffersize) < 0)
goto cleanup;
} else {
break;
}
}
if (bytesread != buffersize)
_PyString_Resize(&ret, bytesread);
cleanup:
RELEASE_LOCK(self);
return ret;
}
PyDoc_STRVAR(BZ2File_readline__doc__,
"readline([size]) -> string\n\
\n\
Return the next line from the file, as a string, retaining newline.\n\
A non-negative size argument will limit the maximum number of bytes to\n\
return (an incomplete line may be returned then). Return an empty\n\
string at EOF.\n\
");
static PyObject *
BZ2File_readline(BZ2FileObject *self, PyObject *args)
{
PyObject *ret = NULL;
int sizehint = -1;
if (!PyArg_ParseTuple(args, "|i:readline", &sizehint))
return NULL;
ACQUIRE_LOCK(self);
switch (self->mode) {
case MODE_READ:
break;
case MODE_READ_EOF:
ret = PyString_FromString("");
goto cleanup;
case MODE_CLOSED:
PyErr_SetString(PyExc_ValueError,
"I/O operation on closed file");
goto cleanup;
default:
PyErr_SetString(PyExc_IOError,
"file is not ready for reading");
goto cleanup;
}
if (sizehint == 0)
ret = PyString_FromString("");
else
ret = Util_GetLine(self, (sizehint < 0) ? 0 : sizehint);
cleanup:
RELEASE_LOCK(self);
return ret;
}
PyDoc_STRVAR(BZ2File_readlines__doc__,
"readlines([size]) -> list\n\
\n\
Call readline() repeatedly and return a list of lines read.\n\
The optional size argument, if given, is an approximate bound on the\n\
total number of bytes in the lines returned.\n\
");
/* This is a hacked version of Python's fileobject.c:file_readlines(). */
static PyObject *
BZ2File_readlines(BZ2FileObject *self, PyObject *args)
{
long sizehint = 0;
PyObject *list = NULL;
PyObject *line;
char small_buffer[SMALLCHUNK];
char *buffer = small_buffer;
size_t buffersize = SMALLCHUNK;
PyObject *big_buffer = NULL;
size_t nfilled = 0;
size_t nread;
size_t totalread = 0;
char *p, *q, *end;
int err;
int shortread = 0;
int bzerror;
if (!PyArg_ParseTuple(args, "|l:readlines", &sizehint))
return NULL;
ACQUIRE_LOCK(self);
switch (self->mode) {
case MODE_READ:
break;
case MODE_READ_EOF:
list = PyList_New(0);
goto cleanup;
case MODE_CLOSED:
PyErr_SetString(PyExc_ValueError,
"I/O operation on closed file");
goto cleanup;
default:
PyErr_SetString(PyExc_IOError,
"file is not ready for reading");
goto cleanup;
}
if ((list = PyList_New(0)) == NULL)
goto cleanup;
for (;;) {
Py_BEGIN_ALLOW_THREADS
nread = Util_UnivNewlineRead(&bzerror, self->fp,
buffer+nfilled,
buffersize-nfilled, self);
self->pos += nread;
Py_END_ALLOW_THREADS
if (bzerror == BZ_STREAM_END) {
self->size = self->pos;
self->mode = MODE_READ_EOF;
if (nread == 0) {
sizehint = 0;
break;
}
shortread = 1;
} else if (bzerror != BZ_OK) {
Util_CatchBZ2Error(bzerror);
error:
Py_DECREF(list);
list = NULL;
goto cleanup;
}
totalread += nread;
p = memchr(buffer+nfilled, '\n', nread);
if (p == NULL) {
/* Need a larger buffer to fit this line */
nfilled += nread;
buffersize *= 2;
if (buffersize > INT_MAX) {
PyErr_SetString(PyExc_OverflowError,
"line is longer than a Python string can hold");
goto error;
}
if (big_buffer == NULL) {
/* Create the big buffer */
big_buffer = PyString_FromStringAndSize(
NULL, buffersize);
if (big_buffer == NULL)
goto error;
buffer = PyString_AS_STRING(big_buffer);
memcpy(buffer, small_buffer, nfilled);
}
else {
/* Grow the big buffer */
_PyString_Resize(&big_buffer, buffersize);
buffer = PyString_AS_STRING(big_buffer);
}
continue;
}
end = buffer+nfilled+nread;
q = buffer;
do {
/* Process complete lines */
p++;
line = PyString_FromStringAndSize(q, p-q);
if (line == NULL)
goto error;
err = PyList_Append(list, line);
Py_DECREF(line);
if (err != 0)
goto error;
q = p;
p = memchr(q, '\n', end-q);
} while (p != NULL);
/* Move the remaining incomplete line to the start */
nfilled = end-q;
memmove(buffer, q, nfilled);
if (sizehint > 0)
if (totalread >= (size_t)sizehint)
break;
if (shortread) {
sizehint = 0;
break;
}
}
if (nfilled != 0) {
/* Partial last line */
line = PyString_FromStringAndSize(buffer, nfilled);
if (line == NULL)
goto error;
if (sizehint > 0) {
/* Need to complete the last line */
PyObject *rest = Util_GetLine(self, 0);
if (rest == NULL) {
Py_DECREF(line);
goto error;
}
PyString_Concat(&line, rest);
Py_DECREF(rest);
if (line == NULL)
goto error;
}
err = PyList_Append(list, line);
Py_DECREF(line);
if (err != 0)
goto error;
}
cleanup:
RELEASE_LOCK(self);
if (big_buffer) {
Py_DECREF(big_buffer);
}
return list;
}
PyDoc_STRVAR(BZ2File_xreadlines__doc__,
"xreadlines() -> self\n\
\n\
For backward compatibility. BZ2File objects now include the performance\n\
optimizations previously implemented in the xreadlines module.\n\
");
PyDoc_STRVAR(BZ2File_write__doc__,
"write(data) -> None\n\
\n\
Write the 'data' string to file. Note that due to buffering, close() may\n\
be needed before the file on disk reflects the data written.\n\
");
/* This is a hacked version of Python's fileobject.c:file_write(). */
static PyObject *
BZ2File_write(BZ2FileObject *self, PyObject *args)
{
PyObject *ret = NULL;
char *buf;
int len;
int bzerror;
if (!PyArg_ParseTuple(args, "s#", &buf, &len))
return NULL;
ACQUIRE_LOCK(self);
switch (self->mode) {
case MODE_WRITE:
break;
case MODE_CLOSED:
PyErr_SetString(PyExc_ValueError,
"I/O operation on closed file");
goto cleanup;;
default:
PyErr_SetString(PyExc_IOError,
"file is not ready for writing");
goto cleanup;;
}
self->f_softspace = 0;
Py_BEGIN_ALLOW_THREADS
BZ2_bzWrite (&bzerror, self->fp, buf, len);
self->pos += len;
Py_END_ALLOW_THREADS
if (bzerror != BZ_OK) {
Util_CatchBZ2Error(bzerror);
goto cleanup;
}
Py_INCREF(Py_None);
ret = Py_None;
cleanup:
RELEASE_LOCK(self);
return ret;
}
PyDoc_STRVAR(BZ2File_writelines__doc__,
"writelines(sequence_of_strings) -> None\n\
\n\
Write the sequence of strings to the file. Note that newlines are not\n\
added. The sequence can be any iterable object producing strings. This is\n\
equivalent to calling write() for each string.\n\
");
/* This is a hacked version of Python's fileobject.c:file_writelines(). */
static PyObject *
BZ2File_writelines(BZ2FileObject *self, PyObject *seq)
{
#define CHUNKSIZE 1000
PyObject *list = NULL;
PyObject *iter = NULL;
PyObject *ret = NULL;
PyObject *line;
int i, j, index, len, islist;
int bzerror;
ACQUIRE_LOCK(self);
islist = PyList_Check(seq);
if (!islist) {
iter = PyObject_GetIter(seq);
if (iter == NULL) {
PyErr_SetString(PyExc_TypeError,
"writelines() requires an iterable argument");
goto error;
}
list = PyList_New(CHUNKSIZE);
if (list == NULL)
goto error;
}
/* Strategy: slurp CHUNKSIZE lines into a private list,
checking that they are all strings, then write that list
without holding the interpreter lock, then come back for more. */
for (index = 0; ; index += CHUNKSIZE) {
if (islist) {
Py_XDECREF(list);
list = PyList_GetSlice(seq, index, index+CHUNKSIZE);
if (list == NULL)
goto error;
j = PyList_GET_SIZE(list);
}
else {
for (j = 0; j < CHUNKSIZE; j++) {
line = PyIter_Next(iter);
if (line == NULL) {
if (PyErr_Occurred())
goto error;
break;
}
PyList_SetItem(list, j, line);
}
}
if (j == 0)
break;
/* Check that all entries are indeed strings. If not,
apply the same rules as for file.write() and
convert the rets to strings. This is slow, but
seems to be the only way since all conversion APIs
could potentially execute Python code. */
for (i = 0; i < j; i++) {
PyObject *v = PyList_GET_ITEM(list, i);
if (!PyString_Check(v)) {
const char *buffer;
int len;
if (PyObject_AsCharBuffer(v, &buffer, &len)) {
PyErr_SetString(PyExc_TypeError,
"writelines() "
"argument must be "
"a sequence of "
"strings");
goto error;
}
line = PyString_FromStringAndSize(buffer,
len);
if (line == NULL)
goto error;
Py_DECREF(v);
PyList_SET_ITEM(list, i, line);
}
}
self->f_softspace = 0;
/* Since we are releasing the global lock, the
following code may *not* execute Python code. */
Py_BEGIN_ALLOW_THREADS
for (i = 0; i < j; i++) {
line = PyList_GET_ITEM(list, i);
len = PyString_GET_SIZE(line);
BZ2_bzWrite (&bzerror, self->fp,
PyString_AS_STRING(line), len);
if (bzerror != BZ_OK) {
Py_BLOCK_THREADS
Util_CatchBZ2Error(bzerror);
goto error;
}
}
Py_END_ALLOW_THREADS
if (j < CHUNKSIZE)
break;
}
Py_INCREF(Py_None);
ret = Py_None;
error:
RELEASE_LOCK(self);
Py_XDECREF(list);
Py_XDECREF(iter);
return ret;
#undef CHUNKSIZE
}
PyDoc_STRVAR(BZ2File_seek__doc__,
"seek(offset [, whence]) -> None\n\
\n\
Move to new file position. Argument offset is a byte count. Optional\n\
argument whence defaults to 0 (offset from start of file, offset\n\
should be >= 0); other values are 1 (move relative to current position,\n\
positive or negative), and 2 (move relative to end of file, usually\n\
negative, although many platforms allow seeking beyond the end of a file).\n\
\n\
Note that seeking of bz2 files is emulated, and depending on the parameters\n\
the operation may be extremely slow.\n\
");
static PyObject *
BZ2File_seek(BZ2FileObject *self, PyObject *args)
{
int where = 0;
long offset;
char small_buffer[SMALLCHUNK];
char *buffer = small_buffer;
size_t buffersize = SMALLCHUNK;
int bytesread = 0;
int readsize;
int chunksize;
int bzerror;
int rewind = 0;
PyObject *ret = NULL;
if (!PyArg_ParseTuple(args, "l|i:seek", &offset, &where))
return NULL;
ACQUIRE_LOCK(self);
Util_DropReadAhead(self);
switch (self->mode) {
case MODE_READ:
case MODE_READ_EOF:
break;
case MODE_CLOSED:
PyErr_SetString(PyExc_ValueError,
"I/O operation on closed file");
goto cleanup;;
default:
PyErr_SetString(PyExc_IOError,
"seek works only while reading");
goto cleanup;;
}
if (offset < 0) {
if (where == 1) {
offset = self->pos + offset;
rewind = 1;