Repository navigation
Expand file tree
/
Copy pathtextio.c
More file actions
3301 lines (2885 loc) · 96.3 KB
/
Copy pathtextio.c
File metadata and controls
3301 lines (2885 loc) · 96.3 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
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
/*
An implementation of Text I/O as defined by PEP 3116 - "New I/O"
Classes defined here: TextIOBase, IncrementalNewlineDecoder, TextIOWrapper.
Written by Amaury Forgeot d'Arc and Antoine Pitrou
*/
#define PY_SSIZE_T_CLEAN
#include "Python.h"
#include "pycore_interp.h" // PyInterpreterState.fs_codec
#include "pycore_long.h" // _PyLong_GetZero()
#include "pycore_fileutils.h" // _Py_GetLocaleEncoding()
#include "pycore_object.h"
#include "pycore_pystate.h" // _PyInterpreterState_GET()
#include "structmember.h" // PyMemberDef
#include "_iomodule.h"
/*[clinic input]
module _io
class _io.IncrementalNewlineDecoder "nldecoder_object *" "clinic_state()->PyIncrementalNewlineDecoder_Type"
class _io.TextIOWrapper "textio *" "clinic_state()->TextIOWrapper_Type"
class _io._TextIOBase "PyObject *" "&PyTextIOBase_Type"
[clinic start generated code]*/
/*[clinic end generated code: output=da39a3ee5e6b4b0d input=8b7f24fa13bfdd7f]*/
typedef struct nldecoder_object nldecoder_object;
typedef struct textio textio;
#define clinic_state() (find_io_state_by_def(Py_TYPE(self)))
#include "clinic/textio.c.h"
#undef clinic_state
/* TextIOBase */
PyDoc_STRVAR(textiobase_doc,
"Base class for text I/O.\n"
"\n"
"This class provides a character and line based interface to stream\n"
"I/O. There is no readinto method because Python's character strings\n"
"are immutable.\n"
);
static PyObject *
_unsupported(_PyIO_State *state, const char *message)
{
PyErr_SetString(state->unsupported_operation, message);
return NULL;
}
/*[clinic input]
_io._TextIOBase.detach
cls: defining_class
/
Separate the underlying buffer from the TextIOBase and return it.
After the underlying buffer has been detached, the TextIO is in an unusable state.
[clinic start generated code]*/
static PyObject *
_io__TextIOBase_detach_impl(PyObject *self, PyTypeObject *cls)
/*[clinic end generated code: output=50915f40c609eaa4 input=987ca3640d0a3776]*/
{
_PyIO_State *state = get_io_state_by_cls(cls);
return _unsupported(state, "detach");
}
/*[clinic input]
_io._TextIOBase.read
cls: defining_class
size: int(unused=True) = -1
/
Read at most size characters from stream.
Read from underlying buffer until we have size characters or we hit EOF.
If size is negative or omitted, read until EOF.
[clinic start generated code]*/
static PyObject *
_io__TextIOBase_read_impl(PyObject *self, PyTypeObject *cls,
int Py_UNUSED(size))
/*[clinic end generated code: output=51a5178a309ce647 input=f5e37720f9fc563f]*/
{
_PyIO_State *state = get_io_state_by_cls(cls);
return _unsupported(state, "read");
}
/*[clinic input]
_io._TextIOBase.readline
cls: defining_class
size: int(unused=True) = -1
/
Read until newline or EOF.
Return an empty string if EOF is hit immediately.
If size is specified, at most size characters will be read.
[clinic start generated code]*/
static PyObject *
_io__TextIOBase_readline_impl(PyObject *self, PyTypeObject *cls,
int Py_UNUSED(size))
/*[clinic end generated code: output=3f47d7966d6d074e input=42eafec94107fa27]*/
{
_PyIO_State *state = get_io_state_by_cls(cls);
return _unsupported(state, "readline");
}
/*[clinic input]
_io._TextIOBase.write
cls: defining_class
s: str(unused=True)
/
Write string s to stream.
Return the number of characters written
(which is always equal to the length of the string).
[clinic start generated code]*/
static PyObject *
_io__TextIOBase_write_impl(PyObject *self, PyTypeObject *cls,
const char *Py_UNUSED(s))
/*[clinic end generated code: output=18b28231460275de input=e9cabaa5f6732b07]*/
{
_PyIO_State *state = get_io_state_by_cls(cls);
return _unsupported(state, "write");
}
PyDoc_STRVAR(textiobase_encoding_doc,
"Encoding of the text stream.\n"
"\n"
"Subclasses should override.\n"
);
static PyObject *
textiobase_encoding_get(PyObject *self, void *context)
{
Py_RETURN_NONE;
}
PyDoc_STRVAR(textiobase_newlines_doc,
"Line endings translated so far.\n"
"\n"
"Only line endings translated during reading are considered.\n"
"\n"
"Subclasses should override.\n"
);
static PyObject *
textiobase_newlines_get(PyObject *self, void *context)
{
Py_RETURN_NONE;
}
PyDoc_STRVAR(textiobase_errors_doc,
"The error setting of the decoder or encoder.\n"
"\n"
"Subclasses should override.\n"
);
static PyObject *
textiobase_errors_get(PyObject *self, void *context)
{
Py_RETURN_NONE;
}
static PyMethodDef textiobase_methods[] = {
_IO__TEXTIOBASE_DETACH_METHODDEF
_IO__TEXTIOBASE_READ_METHODDEF
_IO__TEXTIOBASE_READLINE_METHODDEF
_IO__TEXTIOBASE_WRITE_METHODDEF
{NULL, NULL}
};
static PyGetSetDef textiobase_getset[] = {
{"encoding", (getter)textiobase_encoding_get, NULL, textiobase_encoding_doc},
{"newlines", (getter)textiobase_newlines_get, NULL, textiobase_newlines_doc},
{"errors", (getter)textiobase_errors_get, NULL, textiobase_errors_doc},
{NULL}
};
static PyType_Slot textiobase_slots[] = {
{Py_tp_doc, (void *)textiobase_doc},
{Py_tp_methods, textiobase_methods},
{Py_tp_getset, textiobase_getset},
{0, NULL},
};
/* Do not set Py_TPFLAGS_HAVE_GC so that tp_traverse and tp_clear are inherited */
PyType_Spec textiobase_spec = {
.name = "_io._TextIOBase",
.flags = (Py_TPFLAGS_DEFAULT | Py_TPFLAGS_BASETYPE |
Py_TPFLAGS_IMMUTABLETYPE),
.slots = textiobase_slots,
};
/* IncrementalNewlineDecoder */
struct nldecoder_object {
PyObject_HEAD
PyObject *decoder;
PyObject *errors;
unsigned int pendingcr: 1;
unsigned int translate: 1;
unsigned int seennl: 3;
};
/*[clinic input]
_io.IncrementalNewlineDecoder.__init__
decoder: object
translate: bool
errors: object(c_default="NULL") = "strict"
Codec used when reading a file in universal newlines mode.
It wraps another incremental decoder, translating \r\n and \r into \n.
It also records the types of newlines encountered. When used with
translate=False, it ensures that the newline sequence is returned in
one piece. When used with decoder=None, it expects unicode strings as
decode input and translates newlines without first invoking an external
decoder.
[clinic start generated code]*/
static int
_io_IncrementalNewlineDecoder___init___impl(nldecoder_object *self,
PyObject *decoder, int translate,
PyObject *errors)
/*[clinic end generated code: output=fbd04d443e764ec2 input=ed547aa257616b0e]*/
{
if (errors == NULL) {
errors = Py_NewRef(&_Py_ID(strict));
}
else {
errors = Py_NewRef(errors);
}
Py_XSETREF(self->errors, errors);
Py_XSETREF(self->decoder, Py_NewRef(decoder));
self->translate = translate ? 1 : 0;
self->seennl = 0;
self->pendingcr = 0;
return 0;
}
static int
incrementalnewlinedecoder_traverse(nldecoder_object *self, visitproc visit,
void *arg)
{
Py_VISIT(Py_TYPE(self));
Py_VISIT(self->decoder);
Py_VISIT(self->errors);
return 0;
}
static int
incrementalnewlinedecoder_clear(nldecoder_object *self)
{
Py_CLEAR(self->decoder);
Py_CLEAR(self->errors);
return 0;
}
static void
incrementalnewlinedecoder_dealloc(nldecoder_object *self)
{
PyTypeObject *tp = Py_TYPE(self);
_PyObject_GC_UNTRACK(self);
(void)incrementalnewlinedecoder_clear(self);
tp->tp_free((PyObject *)self);
Py_DECREF(tp);
}
static int
check_decoded(PyObject *decoded)
{
if (decoded == NULL)
return -1;
if (!PyUnicode_Check(decoded)) {
PyErr_Format(PyExc_TypeError,
"decoder should return a string result, not '%.200s'",
Py_TYPE(decoded)->tp_name);
Py_DECREF(decoded);
return -1;
}
if (PyUnicode_READY(decoded) < 0) {
Py_DECREF(decoded);
return -1;
}
return 0;
}
#define CHECK_INITIALIZED_DECODER(self) \
if (self->errors == NULL) { \
PyErr_SetString(PyExc_ValueError, \
"IncrementalNewlineDecoder.__init__() not called"); \
return NULL; \
}
#define SEEN_CR 1
#define SEEN_LF 2
#define SEEN_CRLF 4
#define SEEN_ALL (SEEN_CR | SEEN_LF | SEEN_CRLF)
PyObject *
_PyIncrementalNewlineDecoder_decode(PyObject *myself,
PyObject *input, int final)
{
PyObject *output;
Py_ssize_t output_len;
nldecoder_object *self = (nldecoder_object *) myself;
CHECK_INITIALIZED_DECODER(self);
/* decode input (with the eventual \r from a previous pass) */
if (self->decoder != Py_None) {
output = PyObject_CallMethodObjArgs(self->decoder,
&_Py_ID(decode), input, final ? Py_True : Py_False, NULL);
}
else {
output = Py_NewRef(input);
}
if (check_decoded(output) < 0)
return NULL;
output_len = PyUnicode_GET_LENGTH(output);
if (self->pendingcr && (final || output_len > 0)) {
/* Prefix output with CR */
int kind;
PyObject *modified;
char *out;
modified = PyUnicode_New(output_len + 1,
PyUnicode_MAX_CHAR_VALUE(output));
if (modified == NULL)
goto error;
kind = PyUnicode_KIND(modified);
out = PyUnicode_DATA(modified);
PyUnicode_WRITE(kind, out, 0, '\r');
memcpy(out + kind, PyUnicode_DATA(output), kind * output_len);
Py_SETREF(output, modified); /* output remains ready */
self->pendingcr = 0;
output_len++;
}
/* retain last \r even when not translating data:
* then readline() is sure to get \r\n in one pass
*/
if (!final) {
if (output_len > 0
&& PyUnicode_READ_CHAR(output, output_len - 1) == '\r')
{
PyObject *modified = PyUnicode_Substring(output, 0, output_len -1);
if (modified == NULL)
goto error;
Py_SETREF(output, modified);
self->pendingcr = 1;
}
}
/* Record which newlines are read and do newline translation if desired,
all in one pass. */
{
const void *in_str;
Py_ssize_t len;
int seennl = self->seennl;
int only_lf = 0;
int kind;
in_str = PyUnicode_DATA(output);
len = PyUnicode_GET_LENGTH(output);
kind = PyUnicode_KIND(output);
if (len == 0)
return output;
/* If, up to now, newlines are consistently \n, do a quick check
for the \r *byte* with the libc's optimized memchr.
*/
if (seennl == SEEN_LF || seennl == 0) {
only_lf = (memchr(in_str, '\r', kind * len) == NULL);
}
if (only_lf) {
/* If not already seen, quick scan for a possible "\n" character.
(there's nothing else to be done, even when in translation mode)
*/
if (seennl == 0 &&
memchr(in_str, '\n', kind * len) != NULL) {
if (kind == PyUnicode_1BYTE_KIND)
seennl |= SEEN_LF;
else {
Py_ssize_t i = 0;
for (;;) {
Py_UCS4 c;
/* Fast loop for non-control characters */
while (PyUnicode_READ(kind, in_str, i) > '\n')
i++;
c = PyUnicode_READ(kind, in_str, i++);
if (c == '\n') {
seennl |= SEEN_LF;
break;
}
if (i >= len)
break;
}
}
}
/* Finished: we have scanned for newlines, and none of them
need translating */
}
else if (!self->translate) {
Py_ssize_t i = 0;
/* We have already seen all newline types, no need to scan again */
if (seennl == SEEN_ALL)
goto endscan;
for (;;) {
Py_UCS4 c;
/* Fast loop for non-control characters */
while (PyUnicode_READ(kind, in_str, i) > '\r')
i++;
c = PyUnicode_READ(kind, in_str, i++);
if (c == '\n')
seennl |= SEEN_LF;
else if (c == '\r') {
if (PyUnicode_READ(kind, in_str, i) == '\n') {
seennl |= SEEN_CRLF;
i++;
}
else
seennl |= SEEN_CR;
}
if (i >= len)
break;
if (seennl == SEEN_ALL)
break;
}
endscan:
;
}
else {
void *translated;
int kind = PyUnicode_KIND(output);
const void *in_str = PyUnicode_DATA(output);
Py_ssize_t in, out;
/* XXX: Previous in-place translation here is disabled as
resizing is not possible anymore */
/* We could try to optimize this so that we only do a copy
when there is something to translate. On the other hand,
we already know there is a \r byte, so chances are high
that something needs to be done. */
translated = PyMem_Malloc(kind * len);
if (translated == NULL) {
PyErr_NoMemory();
goto error;
}
in = out = 0;
for (;;) {
Py_UCS4 c;
/* Fast loop for non-control characters */
while ((c = PyUnicode_READ(kind, in_str, in++)) > '\r')
PyUnicode_WRITE(kind, translated, out++, c);
if (c == '\n') {
PyUnicode_WRITE(kind, translated, out++, c);
seennl |= SEEN_LF;
continue;
}
if (c == '\r') {
if (PyUnicode_READ(kind, in_str, in) == '\n') {
in++;
seennl |= SEEN_CRLF;
}
else
seennl |= SEEN_CR;
PyUnicode_WRITE(kind, translated, out++, '\n');
continue;
}
if (in > len)
break;
PyUnicode_WRITE(kind, translated, out++, c);
}
Py_DECREF(output);
output = PyUnicode_FromKindAndData(kind, translated, out);
PyMem_Free(translated);
if (!output)
return NULL;
}
self->seennl |= seennl;
}
return output;
error:
Py_DECREF(output);
return NULL;
}
/*[clinic input]
_io.IncrementalNewlineDecoder.decode
input: object
final: bool = False
[clinic start generated code]*/
static PyObject *
_io_IncrementalNewlineDecoder_decode_impl(nldecoder_object *self,
PyObject *input, int final)
/*[clinic end generated code: output=0d486755bb37a66e input=90e223c70322c5cd]*/
{
return _PyIncrementalNewlineDecoder_decode((PyObject *) self, input, final);
}
/*[clinic input]
_io.IncrementalNewlineDecoder.getstate
[clinic start generated code]*/
static PyObject *
_io_IncrementalNewlineDecoder_getstate_impl(nldecoder_object *self)
/*[clinic end generated code: output=f0d2c9c136f4e0d0 input=f8ff101825e32e7f]*/
{
PyObject *buffer;
unsigned long long flag;
CHECK_INITIALIZED_DECODER(self);
if (self->decoder != Py_None) {
PyObject *state = PyObject_CallMethodNoArgs(self->decoder,
&_Py_ID(getstate));
if (state == NULL)
return NULL;
if (!PyTuple_Check(state)) {
PyErr_SetString(PyExc_TypeError,
"illegal decoder state");
Py_DECREF(state);
return NULL;
}
if (!PyArg_ParseTuple(state, "OK;illegal decoder state",
&buffer, &flag))
{
Py_DECREF(state);
return NULL;
}
Py_INCREF(buffer);
Py_DECREF(state);
}
else {
buffer = PyBytes_FromString("");
flag = 0;
}
flag <<= 1;
if (self->pendingcr)
flag |= 1;
return Py_BuildValue("NK", buffer, flag);
}
/*[clinic input]
_io.IncrementalNewlineDecoder.setstate
state: object
/
[clinic start generated code]*/
static PyObject *
_io_IncrementalNewlineDecoder_setstate(nldecoder_object *self,
PyObject *state)
/*[clinic end generated code: output=c10c622508b576cb input=c53fb505a76dbbe2]*/
{
PyObject *buffer;
unsigned long long flag;
CHECK_INITIALIZED_DECODER(self);
if (!PyTuple_Check(state)) {
PyErr_SetString(PyExc_TypeError, "state argument must be a tuple");
return NULL;
}
if (!PyArg_ParseTuple(state, "OK;setstate(): illegal state argument",
&buffer, &flag))
{
return NULL;
}
self->pendingcr = (int) (flag & 1);
flag >>= 1;
if (self->decoder != Py_None) {
return _PyObject_CallMethod(self->decoder, &_Py_ID(setstate),
"((OK))", buffer, flag);
}
else {
Py_RETURN_NONE;
}
}
/*[clinic input]
_io.IncrementalNewlineDecoder.reset
[clinic start generated code]*/
static PyObject *
_io_IncrementalNewlineDecoder_reset_impl(nldecoder_object *self)
/*[clinic end generated code: output=32fa40c7462aa8ff input=728678ddaea776df]*/
{
CHECK_INITIALIZED_DECODER(self);
self->seennl = 0;
self->pendingcr = 0;
if (self->decoder != Py_None)
return PyObject_CallMethodNoArgs(self->decoder, &_Py_ID(reset));
else
Py_RETURN_NONE;
}
static PyObject *
incrementalnewlinedecoder_newlines_get(nldecoder_object *self, void *context)
{
CHECK_INITIALIZED_DECODER(self);
switch (self->seennl) {
case SEEN_CR:
return PyUnicode_FromString("\r");
case SEEN_LF:
return PyUnicode_FromString("\n");
case SEEN_CRLF:
return PyUnicode_FromString("\r\n");
case SEEN_CR | SEEN_LF:
return Py_BuildValue("ss", "\r", "\n");
case SEEN_CR | SEEN_CRLF:
return Py_BuildValue("ss", "\r", "\r\n");
case SEEN_LF | SEEN_CRLF:
return Py_BuildValue("ss", "\n", "\r\n");
case SEEN_CR | SEEN_LF | SEEN_CRLF:
return Py_BuildValue("sss", "\r", "\n", "\r\n");
default:
Py_RETURN_NONE;
}
}
/* TextIOWrapper */
typedef PyObject *
(*encodefunc_t)(PyObject *, PyObject *);
struct textio
{
PyObject_HEAD
int ok; /* initialized? */
int detached;
Py_ssize_t chunk_size;
PyObject *buffer;
PyObject *encoding;
PyObject *encoder;
PyObject *decoder;
PyObject *readnl;
PyObject *errors;
const char *writenl; /* ASCII-encoded; NULL stands for \n */
char line_buffering;
char write_through;
char readuniversal;
char readtranslate;
char writetranslate;
char seekable;
char has_read1;
char telling;
char finalizing;
/* Specialized encoding func (see below) */
encodefunc_t encodefunc;
/* Whether or not it's the start of the stream */
char encoding_start_of_stream;
/* Reads and writes are internally buffered in order to speed things up.
However, any read will first flush the write buffer if itsn't empty.
Please also note that text to be written is first encoded before being
buffered. This is necessary so that encoding errors are immediately
reported to the caller, but it unfortunately means that the
IncrementalEncoder (whose encode() method is always written in Python)
becomes a bottleneck for small writes.
*/
PyObject *decoded_chars; /* buffer for text returned from decoder */
Py_ssize_t decoded_chars_used; /* offset into _decoded_chars for read() */
PyObject *pending_bytes; // data waiting to be written.
// ascii unicode, bytes, or list of them.
Py_ssize_t pending_bytes_count;
/* snapshot is either NULL, or a tuple (dec_flags, next_input) where
* dec_flags is the second (integer) item of the decoder state and
* next_input is the chunk of input bytes that comes next after the
* snapshot point. We use this to reconstruct decoder states in tell().
*/
PyObject *snapshot;
/* Bytes-to-characters ratio for the current chunk. Serves as input for
the heuristic in tell(). */
double b2cratio;
/* Cache raw object if it's a FileIO object */
PyObject *raw;
PyObject *weakreflist;
PyObject *dict;
_PyIO_State *state;
};
static void
textiowrapper_set_decoded_chars(textio *self, PyObject *chars);
/* A couple of specialized cases in order to bypass the slow incremental
encoding methods for the most popular encodings. */
static PyObject *
ascii_encode(textio *self, PyObject *text)
{
return _PyUnicode_AsASCIIString(text, PyUnicode_AsUTF8(self->errors));
}
static PyObject *
utf16be_encode(textio *self, PyObject *text)
{
return _PyUnicode_EncodeUTF16(text,
PyUnicode_AsUTF8(self->errors), 1);
}
static PyObject *
utf16le_encode(textio *self, PyObject *text)
{
return _PyUnicode_EncodeUTF16(text,
PyUnicode_AsUTF8(self->errors), -1);
}
static PyObject *
utf16_encode(textio *self, PyObject *text)
{
if (!self->encoding_start_of_stream) {
/* Skip the BOM and use native byte ordering */
#if PY_BIG_ENDIAN
return utf16be_encode(self, text);
#else
return utf16le_encode(self, text);
#endif
}
return _PyUnicode_EncodeUTF16(text,
PyUnicode_AsUTF8(self->errors), 0);
}
static PyObject *
utf32be_encode(textio *self, PyObject *text)
{
return _PyUnicode_EncodeUTF32(text,
PyUnicode_AsUTF8(self->errors), 1);
}
static PyObject *
utf32le_encode(textio *self, PyObject *text)
{
return _PyUnicode_EncodeUTF32(text,
PyUnicode_AsUTF8(self->errors), -1);
}
static PyObject *
utf32_encode(textio *self, PyObject *text)
{
if (!self->encoding_start_of_stream) {
/* Skip the BOM and use native byte ordering */
#if PY_BIG_ENDIAN
return utf32be_encode(self, text);
#else
return utf32le_encode(self, text);
#endif
}
return _PyUnicode_EncodeUTF32(text,
PyUnicode_AsUTF8(self->errors), 0);
}
static PyObject *
utf8_encode(textio *self, PyObject *text)
{
return _PyUnicode_AsUTF8String(text, PyUnicode_AsUTF8(self->errors));
}
static PyObject *
latin1_encode(textio *self, PyObject *text)
{
return _PyUnicode_AsLatin1String(text, PyUnicode_AsUTF8(self->errors));
}
// Return true when encoding can be skipped when text is ascii.
static inline int
is_asciicompat_encoding(encodefunc_t f)
{
return f == (encodefunc_t) ascii_encode
|| f == (encodefunc_t) latin1_encode
|| f == (encodefunc_t) utf8_encode;
}
/* Map normalized encoding names onto the specialized encoding funcs */
typedef struct {
const char *name;
encodefunc_t encodefunc;
} encodefuncentry;
static const encodefuncentry encodefuncs[] = {
{"ascii", (encodefunc_t) ascii_encode},
{"iso8859-1", (encodefunc_t) latin1_encode},
{"utf-8", (encodefunc_t) utf8_encode},
{"utf-16-be", (encodefunc_t) utf16be_encode},
{"utf-16-le", (encodefunc_t) utf16le_encode},
{"utf-16", (encodefunc_t) utf16_encode},
{"utf-32-be", (encodefunc_t) utf32be_encode},
{"utf-32-le", (encodefunc_t) utf32le_encode},
{"utf-32", (encodefunc_t) utf32_encode},
{NULL, NULL}
};
static int
validate_newline(const char *newline)
{
if (newline && newline[0] != '\0'
&& !(newline[0] == '\n' && newline[1] == '\0')
&& !(newline[0] == '\r' && newline[1] == '\0')
&& !(newline[0] == '\r' && newline[1] == '\n' && newline[2] == '\0')) {
PyErr_Format(PyExc_ValueError,
"illegal newline value: %s", newline);
return -1;
}
return 0;
}
static int
set_newline(textio *self, const char *newline)
{
PyObject *old = self->readnl;
if (newline == NULL) {
self->readnl = NULL;
}
else {
self->readnl = PyUnicode_FromString(newline);
if (self->readnl == NULL) {
self->readnl = old;
return -1;
}
}
self->readuniversal = (newline == NULL || newline[0] == '\0');
self->readtranslate = (newline == NULL);
self->writetranslate = (newline == NULL || newline[0] != '\0');
if (!self->readuniversal && self->readnl != NULL) {
// validate_newline() accepts only ASCII newlines.
assert(PyUnicode_KIND(self->readnl) == PyUnicode_1BYTE_KIND);
self->writenl = (const char *)PyUnicode_1BYTE_DATA(self->readnl);
if (strcmp(self->writenl, "\n") == 0) {
self->writenl = NULL;
}
}
else {
#ifdef MS_WINDOWS
self->writenl = "\r\n";
#else
self->writenl = NULL;
#endif
}
Py_XDECREF(old);
return 0;
}
static int
_textiowrapper_set_decoder(textio *self, PyObject *codec_info,
const char *errors)
{
PyObject *res;
int r;
res = PyObject_CallMethodNoArgs(self->buffer, &_Py_ID(readable));
if (res == NULL)
return -1;
r = PyObject_IsTrue(res);
Py_DECREF(res);
if (r == -1)
return -1;
if (r != 1)
return 0;
Py_CLEAR(self->decoder);
self->decoder = _PyCodecInfo_GetIncrementalDecoder(codec_info, errors);
if (self->decoder == NULL)
return -1;
if (self->readuniversal) {
_PyIO_State *state = self->state;
PyObject *incrementalDecoder = PyObject_CallFunctionObjArgs(
(PyObject *)state->PyIncrementalNewlineDecoder_Type,
self->decoder, self->readtranslate ? Py_True : Py_False, NULL);
if (incrementalDecoder == NULL)
return -1;
Py_XSETREF(self->decoder, incrementalDecoder);
}
return 0;
}
static PyObject*
_textiowrapper_decode(_PyIO_State *state, PyObject *decoder, PyObject *bytes,
int eof)
{
PyObject *chars;
if (Py_IS_TYPE(decoder, state->PyIncrementalNewlineDecoder_Type))
chars = _PyIncrementalNewlineDecoder_decode(decoder, bytes, eof);
else
chars = PyObject_CallMethodObjArgs(decoder, &_Py_ID(decode), bytes,
eof ? Py_True : Py_False, NULL);
if (check_decoded(chars) < 0)
// check_decoded already decreases refcount
return NULL;
return chars;
}
static int
_textiowrapper_set_encoder(textio *self, PyObject *codec_info,
const char *errors)
{
PyObject *res;
int r;
res = PyObject_CallMethodNoArgs(self->buffer, &_Py_ID(writable));
if (res == NULL)
return -1;
r = PyObject_IsTrue(res);
Py_DECREF(res);
if (r == -1)
return -1;
if (r != 1)
return 0;
Py_CLEAR(self->encoder);
self->encodefunc = NULL;
self->encoder = _PyCodecInfo_GetIncrementalEncoder(codec_info, errors);
if (self->encoder == NULL)
return -1;
/* Get the normalized named of the codec */
if (_PyObject_LookupAttr(codec_info, &_Py_ID(name), &res) < 0) {
return -1;
}
if (res != NULL && PyUnicode_Check(res)) {
const encodefuncentry *e = encodefuncs;
while (e->name != NULL) {
if (_PyUnicode_EqualToASCIIString(res, e->name)) {
self->encodefunc = e->encodefunc;
break;
}
e++;
}
}
Py_XDECREF(res);
return 0;
}
static int
_textiowrapper_fix_encoder_state(textio *self)
{
if (!self->seekable || !self->encoder) {
return 0;
}
self->encoding_start_of_stream = 1;
PyObject *cookieObj = PyObject_CallMethodNoArgs(
self->buffer, &_Py_ID(tell));
if (cookieObj == NULL) {
return -1;
}
int cmp = PyObject_RichCompareBool(cookieObj, _PyLong_GetZero(), Py_EQ);
Py_DECREF(cookieObj);
if (cmp < 0) {
return -1;
}
if (cmp == 0) {
self->encoding_start_of_stream = 0;
PyObject *res = PyObject_CallMethodOneArg(
self->encoder, &_Py_ID(setstate), _PyLong_GetZero());
if (res == NULL) {
return -1;
}
Py_DECREF(res);
}