-
-
Notifications
You must be signed in to change notification settings - Fork 34.2k
Expand file tree
/
Copy pathcodecs.c
More file actions
1204 lines (1068 loc) · 34.2 KB
/
codecs.c
File metadata and controls
1204 lines (1068 loc) · 34.2 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
/* ------------------------------------------------------------------------
Python Codec Registry and support functions
Written by Marc-Andre Lemburg (mal@lemburg.com).
Copyright (c) Corporation for National Research Initiatives.
------------------------------------------------------------------------ */
#include "Python.h"
#include <ctype.h>
const char *Py_hexdigits = "0123456789abcdef";
/* --- Codec Registry ----------------------------------------------------- */
/* Import the standard encodings package which will register the first
codec search function.
This is done in a lazy way so that the Unicode implementation does
not downgrade startup time of scripts not needing it.
ImportErrors are silently ignored by this function. Only one try is
made.
*/
static int _PyCodecRegistry_Init(void); /* Forward */
int PyCodec_Register(PyObject *search_function)
{
PyInterpreterState *interp = PyThreadState_GET()->interp;
if (interp->codec_search_path == NULL && _PyCodecRegistry_Init())
goto onError;
if (search_function == NULL) {
PyErr_BadArgument();
goto onError;
}
if (!PyCallable_Check(search_function)) {
PyErr_SetString(PyExc_TypeError, "argument must be callable");
goto onError;
}
return PyList_Append(interp->codec_search_path, search_function);
onError:
return -1;
}
/* Convert a string to a normalized Python string: all characters are
converted to lower case, spaces are replaced with underscores. */
static
PyObject *normalizestring(const char *string)
{
register size_t i;
size_t len = strlen(string);
char *p;
PyObject *v;
if (len > PY_SSIZE_T_MAX) {
PyErr_SetString(PyExc_OverflowError, "string is too large");
return NULL;
}
p = PyMem_Malloc(len + 1);
if (p == NULL)
return NULL;
for (i = 0; i < len; i++) {
register char ch = string[i];
if (ch == ' ')
ch = '-';
else
ch = Py_TOLOWER(Py_CHARMASK(ch));
p[i] = ch;
}
p[i] = '\0';
v = PyUnicode_FromString(p);
if (v == NULL)
return NULL;
PyMem_Free(p);
return v;
}
/* Lookup the given encoding and return a tuple providing the codec
facilities.
The encoding string is looked up converted to all lower-case
characters. This makes encodings looked up through this mechanism
effectively case-insensitive.
If no codec is found, a LookupError is set and NULL returned.
As side effect, this tries to load the encodings package, if not
yet done. This is part of the lazy load strategy for the encodings
package.
*/
PyObject *_PyCodec_Lookup(const char *encoding)
{
PyInterpreterState *interp;
PyObject *result, *args = NULL, *v;
Py_ssize_t i, len;
if (encoding == NULL) {
PyErr_BadArgument();
goto onError;
}
interp = PyThreadState_GET()->interp;
if (interp->codec_search_path == NULL && _PyCodecRegistry_Init())
goto onError;
/* Convert the encoding to a normalized Python string: all
characters are converted to lower case, spaces and hyphens are
replaced with underscores. */
v = normalizestring(encoding);
if (v == NULL)
goto onError;
PyUnicode_InternInPlace(&v);
/* First, try to lookup the name in the registry dictionary */
result = PyDict_GetItem(interp->codec_search_cache, v);
if (result != NULL) {
Py_INCREF(result);
Py_DECREF(v);
return result;
}
/* Next, scan the search functions in order of registration */
args = PyTuple_New(1);
if (args == NULL)
goto onError;
PyTuple_SET_ITEM(args,0,v);
len = PyList_Size(interp->codec_search_path);
if (len < 0)
goto onError;
if (len == 0) {
PyErr_SetString(PyExc_LookupError,
"no codec search functions registered: "
"can't find encoding");
goto onError;
}
for (i = 0; i < len; i++) {
PyObject *func;
func = PyList_GetItem(interp->codec_search_path, i);
if (func == NULL)
goto onError;
result = PyEval_CallObject(func, args);
if (result == NULL)
goto onError;
if (result == Py_None) {
Py_DECREF(result);
continue;
}
if (!PyTuple_Check(result) || PyTuple_GET_SIZE(result) != 4) {
PyErr_SetString(PyExc_TypeError,
"codec search functions must return 4-tuples");
Py_DECREF(result);
goto onError;
}
break;
}
if (i == len) {
/* XXX Perhaps we should cache misses too ? */
PyErr_Format(PyExc_LookupError,
"unknown encoding: %s", encoding);
goto onError;
}
/* Cache and return the result */
if (PyDict_SetItem(interp->codec_search_cache, v, result) < 0) {
Py_DECREF(result);
goto onError;
}
Py_DECREF(args);
return result;
onError:
Py_XDECREF(args);
return NULL;
}
/* Codec registry encoding check API. */
int PyCodec_KnownEncoding(const char *encoding)
{
PyObject *codecs;
codecs = _PyCodec_Lookup(encoding);
if (!codecs) {
PyErr_Clear();
return 0;
}
else {
Py_DECREF(codecs);
return 1;
}
}
static
PyObject *args_tuple(PyObject *object,
const char *errors)
{
PyObject *args;
args = PyTuple_New(1 + (errors != NULL));
if (args == NULL)
return NULL;
Py_INCREF(object);
PyTuple_SET_ITEM(args,0,object);
if (errors) {
PyObject *v;
v = PyUnicode_FromString(errors);
if (v == NULL) {
Py_DECREF(args);
return NULL;
}
PyTuple_SET_ITEM(args, 1, v);
}
return args;
}
/* Helper function to get a codec item */
static
PyObject *codec_getitem(const char *encoding, int index)
{
PyObject *codecs;
PyObject *v;
codecs = _PyCodec_Lookup(encoding);
if (codecs == NULL)
return NULL;
v = PyTuple_GET_ITEM(codecs, index);
Py_DECREF(codecs);
Py_INCREF(v);
return v;
}
/* Helper functions to create an incremental codec. */
static
PyObject *codec_makeincrementalcodec(PyObject *codec_info,
const char *errors,
const char *attrname)
{
PyObject *ret, *inccodec;
inccodec = PyObject_GetAttrString(codec_info, attrname);
if (inccodec == NULL)
return NULL;
if (errors)
ret = PyObject_CallFunction(inccodec, "s", errors);
else
ret = PyObject_CallFunction(inccodec, NULL);
Py_DECREF(inccodec);
return ret;
}
static
PyObject *codec_getincrementalcodec(const char *encoding,
const char *errors,
const char *attrname)
{
PyObject *codec_info, *ret;
codec_info = _PyCodec_Lookup(encoding);
if (codec_info == NULL)
return NULL;
ret = codec_makeincrementalcodec(codec_info, errors, attrname);
Py_DECREF(codec_info);
return ret;
}
/* Helper function to create a stream codec. */
static
PyObject *codec_getstreamcodec(const char *encoding,
PyObject *stream,
const char *errors,
const int index)
{
PyObject *codecs, *streamcodec, *codeccls;
codecs = _PyCodec_Lookup(encoding);
if (codecs == NULL)
return NULL;
codeccls = PyTuple_GET_ITEM(codecs, index);
if (errors != NULL)
streamcodec = PyObject_CallFunction(codeccls, "Os", stream, errors);
else
streamcodec = PyObject_CallFunction(codeccls, "O", stream);
Py_DECREF(codecs);
return streamcodec;
}
/* Helpers to work with the result of _PyCodec_Lookup
*/
PyObject *_PyCodecInfo_GetIncrementalDecoder(PyObject *codec_info,
const char *errors)
{
return codec_makeincrementalcodec(codec_info, errors,
"incrementaldecoder");
}
PyObject *_PyCodecInfo_GetIncrementalEncoder(PyObject *codec_info,
const char *errors)
{
return codec_makeincrementalcodec(codec_info, errors,
"incrementalencoder");
}
/* Convenience APIs to query the Codec registry.
All APIs return a codec object with incremented refcount.
*/
PyObject *PyCodec_Encoder(const char *encoding)
{
return codec_getitem(encoding, 0);
}
PyObject *PyCodec_Decoder(const char *encoding)
{
return codec_getitem(encoding, 1);
}
PyObject *PyCodec_IncrementalEncoder(const char *encoding,
const char *errors)
{
return codec_getincrementalcodec(encoding, errors, "incrementalencoder");
}
PyObject *PyCodec_IncrementalDecoder(const char *encoding,
const char *errors)
{
return codec_getincrementalcodec(encoding, errors, "incrementaldecoder");
}
PyObject *PyCodec_StreamReader(const char *encoding,
PyObject *stream,
const char *errors)
{
return codec_getstreamcodec(encoding, stream, errors, 2);
}
PyObject *PyCodec_StreamWriter(const char *encoding,
PyObject *stream,
const char *errors)
{
return codec_getstreamcodec(encoding, stream, errors, 3);
}
/* Encode an object (e.g. an Unicode object) using the given encoding
and return the resulting encoded object (usually a Python string).
errors is passed to the encoder factory as argument if non-NULL. */
static PyObject *
_PyCodec_EncodeInternal(PyObject *object,
PyObject *encoder,
const char *encoding,
const char *errors)
{
PyObject *args = NULL, *result = NULL;
PyObject *v = NULL;
args = args_tuple(object, errors);
if (args == NULL)
goto onError;
result = PyEval_CallObject(encoder, args);
if (result == NULL)
goto onError;
if (!PyTuple_Check(result) ||
PyTuple_GET_SIZE(result) != 2) {
PyErr_SetString(PyExc_TypeError,
"encoder must return a tuple (object, integer)");
goto onError;
}
v = PyTuple_GET_ITEM(result,0);
Py_INCREF(v);
/* We don't check or use the second (integer) entry. */
Py_DECREF(args);
Py_DECREF(encoder);
Py_DECREF(result);
return v;
onError:
Py_XDECREF(result);
Py_XDECREF(args);
Py_XDECREF(encoder);
return NULL;
}
/* Decode an object (usually a Python string) using the given encoding
and return an equivalent object (e.g. an Unicode object).
errors is passed to the decoder factory as argument if non-NULL. */
static PyObject *
_PyCodec_DecodeInternal(PyObject *object,
PyObject *decoder,
const char *encoding,
const char *errors)
{
PyObject *args = NULL, *result = NULL;
PyObject *v;
args = args_tuple(object, errors);
if (args == NULL)
goto onError;
result = PyEval_CallObject(decoder,args);
if (result == NULL)
goto onError;
if (!PyTuple_Check(result) ||
PyTuple_GET_SIZE(result) != 2) {
PyErr_SetString(PyExc_TypeError,
"decoder must return a tuple (object,integer)");
goto onError;
}
v = PyTuple_GET_ITEM(result,0);
Py_INCREF(v);
/* We don't check or use the second (integer) entry. */
Py_DECREF(args);
Py_DECREF(decoder);
Py_DECREF(result);
return v;
onError:
Py_XDECREF(args);
Py_XDECREF(decoder);
Py_XDECREF(result);
return NULL;
}
/* Generic encoding/decoding API */
PyObject *PyCodec_Encode(PyObject *object,
const char *encoding,
const char *errors)
{
PyObject *encoder;
encoder = PyCodec_Encoder(encoding);
if (encoder == NULL)
return NULL;
return _PyCodec_EncodeInternal(object, encoder, encoding, errors);
}
PyObject *PyCodec_Decode(PyObject *object,
const char *encoding,
const char *errors)
{
PyObject *decoder;
decoder = PyCodec_Decoder(encoding);
if (decoder == NULL)
return NULL;
return _PyCodec_DecodeInternal(object, decoder, encoding, errors);
}
/* Text encoding/decoding API */
PyObject * _PyCodec_LookupTextEncoding(const char *encoding,
const char *alternate_command)
{
_Py_IDENTIFIER(_is_text_encoding);
PyObject *codec;
PyObject *attr;
int is_text_codec;
codec = _PyCodec_Lookup(encoding);
if (codec == NULL)
return NULL;
/* Backwards compatibility: assume any raw tuple describes a text
* encoding, and the same for anything lacking the private
* attribute.
*/
if (!PyTuple_CheckExact(codec)) {
attr = _PyObject_GetAttrId(codec, &PyId__is_text_encoding);
if (attr == NULL) {
if (PyErr_ExceptionMatches(PyExc_AttributeError)) {
PyErr_Clear();
} else {
Py_DECREF(codec);
return NULL;
}
} else {
is_text_codec = PyObject_IsTrue(attr);
Py_DECREF(attr);
if (!is_text_codec) {
Py_DECREF(codec);
PyErr_Format(PyExc_LookupError,
"'%.400s' is not a text encoding; "
"use %s to handle arbitrary codecs",
encoding, alternate_command);
return NULL;
}
}
}
/* This appears to be a valid text encoding */
return codec;
}
static
PyObject *codec_getitem_checked(const char *encoding,
const char *alternate_command,
int index)
{
PyObject *codec;
PyObject *v;
codec = _PyCodec_LookupTextEncoding(encoding, alternate_command);
if (codec == NULL)
return NULL;
v = PyTuple_GET_ITEM(codec, index);
Py_INCREF(v);
Py_DECREF(codec);
return v;
}
static PyObject * _PyCodec_TextEncoder(const char *encoding)
{
return codec_getitem_checked(encoding, "codecs.encode()", 0);
}
static PyObject * _PyCodec_TextDecoder(const char *encoding)
{
return codec_getitem_checked(encoding, "codecs.decode()", 1);
}
PyObject *_PyCodec_EncodeText(PyObject *object,
const char *encoding,
const char *errors)
{
PyObject *encoder;
encoder = _PyCodec_TextEncoder(encoding);
if (encoder == NULL)
return NULL;
return _PyCodec_EncodeInternal(object, encoder, encoding, errors);
}
PyObject *_PyCodec_DecodeText(PyObject *object,
const char *encoding,
const char *errors)
{
PyObject *decoder;
decoder = _PyCodec_TextDecoder(encoding);
if (decoder == NULL)
return NULL;
return _PyCodec_DecodeInternal(object, decoder, encoding, errors);
}
/* Register the error handling callback function error under the name
name. This function will be called by the codec when it encounters
an unencodable characters/undecodable bytes and doesn't know the
callback name, when name is specified as the error parameter
in the call to the encode/decode function.
Return 0 on success, -1 on error */
int PyCodec_RegisterError(const char *name, PyObject *error)
{
PyInterpreterState *interp = PyThreadState_GET()->interp;
if (interp->codec_search_path == NULL && _PyCodecRegistry_Init())
return -1;
if (!PyCallable_Check(error)) {
PyErr_SetString(PyExc_TypeError, "handler must be callable");
return -1;
}
return PyDict_SetItemString(interp->codec_error_registry,
(char *)name, error);
}
/* Lookup the error handling callback function registered under the
name error. As a special case NULL can be passed, in which case
the error handling callback for strict encoding will be returned. */
PyObject *PyCodec_LookupError(const char *name)
{
PyObject *handler = NULL;
PyInterpreterState *interp = PyThreadState_GET()->interp;
if (interp->codec_search_path == NULL && _PyCodecRegistry_Init())
return NULL;
if (name==NULL)
name = "strict";
handler = PyDict_GetItemString(interp->codec_error_registry, (char *)name);
if (!handler)
PyErr_Format(PyExc_LookupError, "unknown error handler name '%.400s'", name);
else
Py_INCREF(handler);
return handler;
}
static void wrong_exception_type(PyObject *exc)
{
_Py_IDENTIFIER(__class__);
_Py_IDENTIFIER(__name__);
PyObject *type = _PyObject_GetAttrId(exc, &PyId___class__);
if (type != NULL) {
PyObject *name = _PyObject_GetAttrId(type, &PyId___name__);
Py_DECREF(type);
if (name != NULL) {
PyErr_Format(PyExc_TypeError,
"don't know how to handle %S in error callback", name);
Py_DECREF(name);
}
}
}
PyObject *PyCodec_StrictErrors(PyObject *exc)
{
if (PyExceptionInstance_Check(exc))
PyErr_SetObject(PyExceptionInstance_Class(exc), exc);
else
PyErr_SetString(PyExc_TypeError, "codec must pass exception instance");
return NULL;
}
PyObject *PyCodec_IgnoreErrors(PyObject *exc)
{
Py_ssize_t end;
if (PyObject_IsInstance(exc, PyExc_UnicodeEncodeError)) {
if (PyUnicodeEncodeError_GetEnd(exc, &end))
return NULL;
}
else if (PyObject_IsInstance(exc, PyExc_UnicodeDecodeError)) {
if (PyUnicodeDecodeError_GetEnd(exc, &end))
return NULL;
}
else if (PyObject_IsInstance(exc, PyExc_UnicodeTranslateError)) {
if (PyUnicodeTranslateError_GetEnd(exc, &end))
return NULL;
}
else {
wrong_exception_type(exc);
return NULL;
}
return Py_BuildValue("(Nn)", PyUnicode_New(0, 0), end);
}
PyObject *PyCodec_ReplaceErrors(PyObject *exc)
{
Py_ssize_t start, end, i, len;
if (PyObject_IsInstance(exc, PyExc_UnicodeEncodeError)) {
PyObject *res;
int kind;
void *data;
if (PyUnicodeEncodeError_GetStart(exc, &start))
return NULL;
if (PyUnicodeEncodeError_GetEnd(exc, &end))
return NULL;
len = end - start;
res = PyUnicode_New(len, '?');
if (res == NULL)
return NULL;
kind = PyUnicode_KIND(res);
data = PyUnicode_DATA(res);
for (i = 0; i < len; ++i)
PyUnicode_WRITE(kind, data, i, '?');
assert(_PyUnicode_CheckConsistency(res, 1));
return Py_BuildValue("(Nn)", res, end);
}
else if (PyObject_IsInstance(exc, PyExc_UnicodeDecodeError)) {
if (PyUnicodeDecodeError_GetEnd(exc, &end))
return NULL;
return Py_BuildValue("(Cn)",
(int)Py_UNICODE_REPLACEMENT_CHARACTER,
end);
}
else if (PyObject_IsInstance(exc, PyExc_UnicodeTranslateError)) {
PyObject *res;
int kind;
void *data;
if (PyUnicodeTranslateError_GetStart(exc, &start))
return NULL;
if (PyUnicodeTranslateError_GetEnd(exc, &end))
return NULL;
len = end - start;
res = PyUnicode_New(len, Py_UNICODE_REPLACEMENT_CHARACTER);
if (res == NULL)
return NULL;
kind = PyUnicode_KIND(res);
data = PyUnicode_DATA(res);
for (i=0; i < len; i++)
PyUnicode_WRITE(kind, data, i, Py_UNICODE_REPLACEMENT_CHARACTER);
assert(_PyUnicode_CheckConsistency(res, 1));
return Py_BuildValue("(Nn)", res, end);
}
else {
wrong_exception_type(exc);
return NULL;
}
}
PyObject *PyCodec_XMLCharRefReplaceErrors(PyObject *exc)
{
if (PyObject_IsInstance(exc, PyExc_UnicodeEncodeError)) {
PyObject *restuple;
PyObject *object;
Py_ssize_t i;
Py_ssize_t start;
Py_ssize_t end;
PyObject *res;
unsigned char *outp;
Py_ssize_t ressize;
Py_UCS4 ch;
if (PyUnicodeEncodeError_GetStart(exc, &start))
return NULL;
if (PyUnicodeEncodeError_GetEnd(exc, &end))
return NULL;
if (!(object = PyUnicodeEncodeError_GetObject(exc)))
return NULL;
if (end - start > PY_SSIZE_T_MAX / (2+7+1))
end = start + PY_SSIZE_T_MAX / (2+7+1);
for (i = start, ressize = 0; i < end; ++i) {
/* object is guaranteed to be "ready" */
ch = PyUnicode_READ_CHAR(object, i);
if (ch<10)
ressize += 2+1+1;
else if (ch<100)
ressize += 2+2+1;
else if (ch<1000)
ressize += 2+3+1;
else if (ch<10000)
ressize += 2+4+1;
else if (ch<100000)
ressize += 2+5+1;
else if (ch<1000000)
ressize += 2+6+1;
else
ressize += 2+7+1;
}
/* allocate replacement */
res = PyUnicode_New(ressize, 127);
if (res == NULL) {
Py_DECREF(object);
return NULL;
}
outp = PyUnicode_1BYTE_DATA(res);
/* generate replacement */
for (i = start; i < end; ++i) {
int digits;
int base;
ch = PyUnicode_READ_CHAR(object, i);
*outp++ = '&';
*outp++ = '#';
if (ch<10) {
digits = 1;
base = 1;
}
else if (ch<100) {
digits = 2;
base = 10;
}
else if (ch<1000) {
digits = 3;
base = 100;
}
else if (ch<10000) {
digits = 4;
base = 1000;
}
else if (ch<100000) {
digits = 5;
base = 10000;
}
else if (ch<1000000) {
digits = 6;
base = 100000;
}
else {
digits = 7;
base = 1000000;
}
while (digits-->0) {
*outp++ = '0' + ch/base;
ch %= base;
base /= 10;
}
*outp++ = ';';
}
assert(_PyUnicode_CheckConsistency(res, 1));
restuple = Py_BuildValue("(Nn)", res, end);
Py_DECREF(object);
return restuple;
}
else {
wrong_exception_type(exc);
return NULL;
}
}
PyObject *PyCodec_BackslashReplaceErrors(PyObject *exc)
{
if (PyObject_IsInstance(exc, PyExc_UnicodeEncodeError)) {
PyObject *restuple;
PyObject *object;
Py_ssize_t i;
Py_ssize_t start;
Py_ssize_t end;
PyObject *res;
unsigned char *outp;
Py_ssize_t ressize;
Py_UCS4 c;
if (PyUnicodeEncodeError_GetStart(exc, &start))
return NULL;
if (PyUnicodeEncodeError_GetEnd(exc, &end))
return NULL;
if (!(object = PyUnicodeEncodeError_GetObject(exc)))
return NULL;
if (end - start > PY_SSIZE_T_MAX / (1+1+8))
end = start + PY_SSIZE_T_MAX / (1+1+8);
for (i = start, ressize = 0; i < end; ++i) {
/* object is guaranteed to be "ready" */
c = PyUnicode_READ_CHAR(object, i);
if (c >= 0x10000) {
ressize += 1+1+8;
}
else if (c >= 0x100) {
ressize += 1+1+4;
}
else
ressize += 1+1+2;
}
res = PyUnicode_New(ressize, 127);
if (res==NULL)
return NULL;
for (i = start, outp = PyUnicode_1BYTE_DATA(res);
i < end; ++i) {
c = PyUnicode_READ_CHAR(object, i);
*outp++ = '\\';
if (c >= 0x00010000) {
*outp++ = 'U';
*outp++ = Py_hexdigits[(c>>28)&0xf];
*outp++ = Py_hexdigits[(c>>24)&0xf];
*outp++ = Py_hexdigits[(c>>20)&0xf];
*outp++ = Py_hexdigits[(c>>16)&0xf];
*outp++ = Py_hexdigits[(c>>12)&0xf];
*outp++ = Py_hexdigits[(c>>8)&0xf];
}
else if (c >= 0x100) {
*outp++ = 'u';
*outp++ = Py_hexdigits[(c>>12)&0xf];
*outp++ = Py_hexdigits[(c>>8)&0xf];
}
else
*outp++ = 'x';
*outp++ = Py_hexdigits[(c>>4)&0xf];
*outp++ = Py_hexdigits[c&0xf];
}
assert(_PyUnicode_CheckConsistency(res, 1));
restuple = Py_BuildValue("(Nn)", res, end);
Py_DECREF(object);
return restuple;
}
else {
wrong_exception_type(exc);
return NULL;
}
}
/* This handler is declared static until someone demonstrates
a need to call it directly. */
static PyObject *
PyCodec_SurrogatePassErrors(PyObject *exc)
{
PyObject *restuple;
PyObject *object;
Py_ssize_t i;
Py_ssize_t start;
Py_ssize_t end;
PyObject *res;
if (PyObject_IsInstance(exc, PyExc_UnicodeEncodeError)) {
char *outp;
if (PyUnicodeEncodeError_GetStart(exc, &start))
return NULL;
if (PyUnicodeEncodeError_GetEnd(exc, &end))
return NULL;
if (!(object = PyUnicodeEncodeError_GetObject(exc)))
return NULL;
res = PyBytes_FromStringAndSize(NULL, 3*(end-start));
if (!res) {
Py_DECREF(object);
return NULL;
}
outp = PyBytes_AsString(res);
for (i = start; i < end; i++) {
/* object is guaranteed to be "ready" */
Py_UCS4 ch = PyUnicode_READ_CHAR(object, i);
if (ch < 0xd800 || ch > 0xdfff) {
/* Not a surrogate, fail with original exception */
PyErr_SetObject(PyExceptionInstance_Class(exc), exc);
Py_DECREF(res);
Py_DECREF(object);
return NULL;
}
*outp++ = (char)(0xe0 | (ch >> 12));
*outp++ = (char)(0x80 | ((ch >> 6) & 0x3f));
*outp++ = (char)(0x80 | (ch & 0x3f));
}
restuple = Py_BuildValue("(On)", res, end);
Py_DECREF(res);
Py_DECREF(object);
return restuple;
}
else if (PyObject_IsInstance(exc, PyExc_UnicodeDecodeError)) {
unsigned char *p;
Py_UCS4 ch = 0;
if (PyUnicodeDecodeError_GetStart(exc, &start))
return NULL;
if (!(object = PyUnicodeDecodeError_GetObject(exc)))
return NULL;
if (!(p = (unsigned char*)PyBytes_AsString(object))) {
Py_DECREF(object);
return NULL;
}
/* Try decoding a single surrogate character. If
there are more, let the codec call us again. */
p += start;
if (PyBytes_GET_SIZE(object) - start >= 3 &&
(p[0] & 0xf0) == 0xe0 &&
(p[1] & 0xc0) == 0x80 &&
(p[2] & 0xc0) == 0x80) {
/* it's a three-byte code */
ch = ((p[0] & 0x0f) << 12) + ((p[1] & 0x3f) << 6) + (p[2] & 0x3f);
if (ch < 0xd800 || ch > 0xdfff)
/* it's not a surrogate - fail */
ch = 0;
}
Py_DECREF(object);
if (ch == 0) {
PyErr_SetObject(PyExceptionInstance_Class(exc), exc);
return NULL;
}
res = PyUnicode_FromOrdinal(ch);
if (res == NULL)
return NULL;
return Py_BuildValue("(Nn)", res, start+3);
}
else {
wrong_exception_type(exc);
return NULL;
}
}
static PyObject *
PyCodec_SurrogateEscapeErrors(PyObject *exc)
{
PyObject *restuple;
PyObject *object;
Py_ssize_t i;
Py_ssize_t start;
Py_ssize_t end;
PyObject *res;
if (PyObject_IsInstance(exc, PyExc_UnicodeEncodeError)) {
char *outp;
if (PyUnicodeEncodeError_GetStart(exc, &start))
return NULL;
if (PyUnicodeEncodeError_GetEnd(exc, &end))
return NULL;
if (!(object = PyUnicodeEncodeError_GetObject(exc)))
return NULL;
res = PyBytes_FromStringAndSize(NULL, end-start);
if (!res) {
Py_DECREF(object);
return NULL;
}
outp = PyBytes_AsString(res);
for (i = start; i < end; i++) {
/* object is guaranteed to be "ready" */
Py_UCS4 ch = PyUnicode_READ_CHAR(object, i);
if (ch < 0xdc80 || ch > 0xdcff) {
/* Not a UTF-8b surrogate, fail with original exception */
PyErr_SetObject(PyExceptionInstance_Class(exc), exc);