{{ message }}
-
Notifications
You must be signed in to change notification settings - Fork 8
Expand file tree
/
Copy pathunicodeobject.h
More file actions
executable file
·1413 lines (1085 loc) · 50.9 KB
/
Copy pathunicodeobject.h
File metadata and controls
executable file
·1413 lines (1085 loc) · 50.9 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
#ifndef Py_UNICODEOBJECT_H
#define Py_UNICODEOBJECT_H
#include <stdarg.h>
/*
Unicode implementation based on original code by Fredrik Lundh,
modified by Marc-Andre Lemburg (mal@lemburg.com) according to the
Unicode Integration Proposal (see file Misc/unicode.txt).
Copyright (c) Corporation for National Research Initiatives.
Original header:
--------------------------------------------------------------------
* Yet another Unicode string type for Python. This type supports the
* 16-bit Basic Multilingual Plane (BMP) only.
*
* Written by Fredrik Lundh, January 1999.
*
* Copyright (c) 1999 by Secret Labs AB.
* Copyright (c) 1999 by Fredrik Lundh.
*
* fredrik@pythonware.com
* http://www.pythonware.com
*
* --------------------------------------------------------------------
* This Unicode String Type is
*
* Copyright (c) 1999 by Secret Labs AB
* Copyright (c) 1999 by Fredrik Lundh
*
* By obtaining, using, and/or copying this software and/or its
* associated documentation, you agree that you have read, understood,
* and will comply with the following terms and conditions:
*
* Permission to use, copy, modify, and distribute this software and its
* associated documentation for any purpose and without fee is hereby
* granted, provided that the above copyright notice appears in all
* copies, and that both that copyright notice and this permission notice
* appear in supporting documentation, and that the name of Secret Labs
* AB or the author not be used in advertising or publicity pertaining to
* distribution of the software without specific, written prior
* permission.
*
* SECRET LABS AB AND THE AUTHOR DISCLAIMS ALL WARRANTIES WITH REGARD TO
* THIS SOFTWARE, INCLUDING ALL IMPLIED WARRANTIES OF MERCHANTABILITY AND
* FITNESS. IN NO EVENT SHALL SECRET LABS AB OR THE AUTHOR BE LIABLE FOR
* ANY SPECIAL, INDIRECT OR CONSEQUENTIAL DAMAGES OR ANY DAMAGES
* WHATSOEVER RESULTING FROM LOSS OF USE, DATA OR PROFITS, WHETHER IN AN
* ACTION OF CONTRACT, NEGLIGENCE OR OTHER TORTIOUS ACTION, ARISING OUT
* OF OR IN CONNECTION WITH THE USE OR PERFORMANCE OF THIS SOFTWARE.
* -------------------------------------------------------------------- */
#include <ctype.h>
/* === Internal API ======================================================= */
/* --- Internal Unicode Format -------------------------------------------- */
#ifndef Py_USING_UNICODE
#define PyUnicode_Check(op) 0
#define PyUnicode_CheckExact(op) 0
#else
/* FIXME: MvL's new implementation assumes that Py_UNICODE_SIZE is
properly set, but the default rules below doesn't set it. I'll
sort this out some other day -- fredrik@pythonware.com */
#ifndef Py_UNICODE_SIZE
#error Must define Py_UNICODE_SIZE
#endif
/* Setting Py_UNICODE_WIDE enables UCS-4 storage. Otherwise, Unicode
strings are stored as UCS-2 (with limited support for UTF-16) */
#if Py_UNICODE_SIZE >= 4
#define Py_UNICODE_WIDE
#endif
/* Set these flags if the platform has "wchar.h", "wctype.h" and the
wchar_t type is a 16-bit unsigned type */
/* #define HAVE_WCHAR_H */
/* #define HAVE_USABLE_WCHAR_T */
/* Defaults for various platforms */
#ifndef PY_UNICODE_TYPE
/* Windows has a usable wchar_t type (unless we're using UCS-4) */
# if defined(MS_WIN32) && Py_UNICODE_SIZE == 2
# define HAVE_USABLE_WCHAR_T
# define PY_UNICODE_TYPE wchar_t
# endif
# if defined(Py_UNICODE_WIDE)
# define PY_UNICODE_TYPE Py_UCS4
# endif
#endif
/* If the compiler provides a wchar_t type we try to support it
through the interface functions PyUnicode_FromWideChar() and
PyUnicode_AsWideChar(). */
#ifdef HAVE_USABLE_WCHAR_T
# ifndef HAVE_WCHAR_H
# define HAVE_WCHAR_H
# endif
#endif
#ifdef HAVE_WCHAR_H
/* Work around a cosmetic bug in BSDI 4.x wchar.h; thanks to Thomas Wouters */
# ifdef _HAVE_BSDI
# include <time.h>
# endif
# include <wchar.h>
#endif
/*
* Use this typedef when you need to represent a UTF-16 surrogate pair
* as single unsigned integer.
*/
#if SIZEOF_INT >= 4
typedef unsigned int Py_UCS4;
#elif SIZEOF_LONG >= 4
typedef unsigned long Py_UCS4;
#endif
/* Py_UNICODE is the native Unicode storage format (code unit) used by
Python and represents a single Unicode element in the Unicode
type. */
typedef PY_UNICODE_TYPE Py_UNICODE;
/* --- UCS-2/UCS-4 Name Mangling ------------------------------------------ */
/* Unicode API names are mangled to assure that UCS-2 and UCS-4 builds
produce different external names and thus cause import errors in
case Python interpreters and extensions with mixed compiled in
Unicode width assumptions are combined. */
#ifndef Py_UNICODE_WIDE
# define PyUnicode_AsASCIIString PyUnicodeUCS2_AsASCIIString
# define PyUnicode_AsCharmapString PyUnicodeUCS2_AsCharmapString
# define PyUnicode_AsEncodedObject PyUnicodeUCS2_AsEncodedObject
# define PyUnicode_AsEncodedString PyUnicodeUCS2_AsEncodedString
# define PyUnicode_AsLatin1String PyUnicodeUCS2_AsLatin1String
# define PyUnicode_AsRawUnicodeEscapeString PyUnicodeUCS2_AsRawUnicodeEscapeString
# define PyUnicode_AsUTF32String PyUnicodeUCS2_AsUTF32String
# define PyUnicode_AsUTF16String PyUnicodeUCS2_AsUTF16String
# define PyUnicode_AsUTF8String PyUnicodeUCS2_AsUTF8String
# define PyUnicode_AsUnicode PyUnicodeUCS2_AsUnicode
# define PyUnicode_AsUnicodeEscapeString PyUnicodeUCS2_AsUnicodeEscapeString
# define PyUnicode_AsWideChar PyUnicodeUCS2_AsWideChar
# define PyUnicode_ClearFreeList PyUnicodeUCS2_ClearFreelist
# define PyUnicode_Compare PyUnicodeUCS2_Compare
# define PyUnicode_Concat PyUnicodeUCS2_Concat
# define PyUnicode_Contains PyUnicodeUCS2_Contains
# define PyUnicode_Count PyUnicodeUCS2_Count
# define PyUnicode_Decode PyUnicodeUCS2_Decode
# define PyUnicode_DecodeASCII PyUnicodeUCS2_DecodeASCII
# define PyUnicode_DecodeCharmap PyUnicodeUCS2_DecodeCharmap
# define PyUnicode_DecodeLatin1 PyUnicodeUCS2_DecodeLatin1
# define PyUnicode_DecodeRawUnicodeEscape PyUnicodeUCS2_DecodeRawUnicodeEscape
# define PyUnicode_DecodeUTF32 PyUnicodeUCS2_DecodeUTF32
# define PyUnicode_DecodeUTF32Stateful PyUnicodeUCS2_DecodeUTF32Stateful
# define PyUnicode_DecodeUTF16 PyUnicodeUCS2_DecodeUTF16
# define PyUnicode_DecodeUTF16Stateful PyUnicodeUCS2_DecodeUTF16Stateful
# define PyUnicode_DecodeUTF8 PyUnicodeUCS2_DecodeUTF8
# define PyUnicode_DecodeUTF8Stateful PyUnicodeUCS2_DecodeUTF8Stateful
# define PyUnicode_DecodeUnicodeEscape PyUnicodeUCS2_DecodeUnicodeEscape
# define PyUnicode_Encode PyUnicodeUCS2_Encode
# define PyUnicode_EncodeASCII PyUnicodeUCS2_EncodeASCII
# define PyUnicode_EncodeCharmap PyUnicodeUCS2_EncodeCharmap
# define PyUnicode_EncodeDecimal PyUnicodeUCS2_EncodeDecimal
# define PyUnicode_EncodeLatin1 PyUnicodeUCS2_EncodeLatin1
# define PyUnicode_EncodeRawUnicodeEscape PyUnicodeUCS2_EncodeRawUnicodeEscape
# define PyUnicode_EncodeUTF32 PyUnicodeUCS2_EncodeUTF32
# define PyUnicode_EncodeUTF16 PyUnicodeUCS2_EncodeUTF16
# define PyUnicode_EncodeUTF8 PyUnicodeUCS2_EncodeUTF8
# define PyUnicode_EncodeUnicodeEscape PyUnicodeUCS2_EncodeUnicodeEscape
# define PyUnicode_Find PyUnicodeUCS2_Find
# define PyUnicode_Format PyUnicodeUCS2_Format
# define PyUnicode_FromEncodedObject PyUnicodeUCS2_FromEncodedObject
# define PyUnicode_FromFormat PyUnicodeUCS2_FromFormat
# define PyUnicode_FromFormatV PyUnicodeUCS2_FromFormatV
# define PyUnicode_FromObject PyUnicodeUCS2_FromObject
# define PyUnicode_FromOrdinal PyUnicodeUCS2_FromOrdinal
# define PyUnicode_FromString PyUnicodeUCS2_FromString
# define PyUnicode_FromStringAndSize PyUnicodeUCS2_FromStringAndSize
# define PyUnicode_FromUnicode PyUnicodeUCS2_FromUnicode
# define PyUnicode_FromWideChar PyUnicodeUCS2_FromWideChar
# define PyUnicode_GetDefaultEncoding PyUnicodeUCS2_GetDefaultEncoding
# define PyUnicode_GetMax PyUnicodeUCS2_GetMax
# define PyUnicode_GetSize PyUnicodeUCS2_GetSize
# define PyUnicode_Join PyUnicodeUCS2_Join
# define PyUnicode_Partition PyUnicodeUCS2_Partition
# define PyUnicode_RPartition PyUnicodeUCS2_RPartition
# define PyUnicode_RSplit PyUnicodeUCS2_RSplit
# define PyUnicode_Replace PyUnicodeUCS2_Replace
# define PyUnicode_Resize PyUnicodeUCS2_Resize
# define PyUnicode_RichCompare PyUnicodeUCS2_RichCompare
# define PyUnicode_SetDefaultEncoding PyUnicodeUCS2_SetDefaultEncoding
# define PyUnicode_Split PyUnicodeUCS2_Split
# define PyUnicode_Splitlines PyUnicodeUCS2_Splitlines
# define PyUnicode_Tailmatch PyUnicodeUCS2_Tailmatch
# define PyUnicode_Translate PyUnicodeUCS2_Translate
# define PyUnicode_TranslateCharmap PyUnicodeUCS2_TranslateCharmap
# define _PyUnicode_AsDefaultEncodedString _PyUnicodeUCS2_AsDefaultEncodedString
# define _PyUnicode_Fini _PyUnicodeUCS2_Fini
# define _PyUnicode_Init _PyUnicodeUCS2_Init
# define _PyUnicode_IsAlpha _PyUnicodeUCS2_IsAlpha
# define _PyUnicode_IsDecimalDigit _PyUnicodeUCS2_IsDecimalDigit
# define _PyUnicode_IsDigit _PyUnicodeUCS2_IsDigit
# define _PyUnicode_IsLinebreak _PyUnicodeUCS2_IsLinebreak
# define _PyUnicode_IsLowercase _PyUnicodeUCS2_IsLowercase
# define _PyUnicode_IsNumeric _PyUnicodeUCS2_IsNumeric
# define _PyUnicode_IsTitlecase _PyUnicodeUCS2_IsTitlecase
# define _PyUnicode_IsUppercase _PyUnicodeUCS2_IsUppercase
# define _PyUnicode_IsWhitespace _PyUnicodeUCS2_IsWhitespace
# define _PyUnicode_ToDecimalDigit _PyUnicodeUCS2_ToDecimalDigit
# define _PyUnicode_ToDigit _PyUnicodeUCS2_ToDigit
# define _PyUnicode_ToLowercase _PyUnicodeUCS2_ToLowercase
# define _PyUnicode_ToNumeric _PyUnicodeUCS2_ToNumeric
# define _PyUnicode_ToTitlecase _PyUnicodeUCS2_ToTitlecase
# define _PyUnicode_ToUppercase _PyUnicodeUCS2_ToUppercase
#else
# define PyUnicode_AsASCIIString PyUnicodeUCS4_AsASCIIString
# define PyUnicode_AsCharmapString PyUnicodeUCS4_AsCharmapString
# define PyUnicode_AsEncodedObject PyUnicodeUCS4_AsEncodedObject
# define PyUnicode_AsEncodedString PyUnicodeUCS4_AsEncodedString
# define PyUnicode_AsLatin1String PyUnicodeUCS4_AsLatin1String
# define PyUnicode_AsRawUnicodeEscapeString PyUnicodeUCS4_AsRawUnicodeEscapeString
# define PyUnicode_AsUTF32String PyUnicodeUCS4_AsUTF32String
# define PyUnicode_AsUTF16String PyUnicodeUCS4_AsUTF16String
# define PyUnicode_AsUTF8String PyUnicodeUCS4_AsUTF8String
# define PyUnicode_AsUnicode PyUnicodeUCS4_AsUnicode
# define PyUnicode_AsUnicodeEscapeString PyUnicodeUCS4_AsUnicodeEscapeString
# define PyUnicode_AsWideChar PyUnicodeUCS4_AsWideChar
# define PyUnicode_ClearFreeList PyUnicodeUCS4_ClearFreelist
# define PyUnicode_Compare PyUnicodeUCS4_Compare
# define PyUnicode_Concat PyUnicodeUCS4_Concat
# define PyUnicode_Contains PyUnicodeUCS4_Contains
# define PyUnicode_Count PyUnicodeUCS4_Count
# define PyUnicode_Decode PyUnicodeUCS4_Decode
# define PyUnicode_DecodeASCII PyUnicodeUCS4_DecodeASCII
# define PyUnicode_DecodeCharmap PyUnicodeUCS4_DecodeCharmap
# define PyUnicode_DecodeLatin1 PyUnicodeUCS4_DecodeLatin1
# define PyUnicode_DecodeRawUnicodeEscape PyUnicodeUCS4_DecodeRawUnicodeEscape
# define PyUnicode_DecodeUTF32 PyUnicodeUCS4_DecodeUTF32
# define PyUnicode_DecodeUTF32Stateful PyUnicodeUCS4_DecodeUTF32Stateful
# define PyUnicode_DecodeUTF16 PyUnicodeUCS4_DecodeUTF16
# define PyUnicode_DecodeUTF16Stateful PyUnicodeUCS4_DecodeUTF16Stateful
# define PyUnicode_DecodeUTF8 PyUnicodeUCS4_DecodeUTF8
# define PyUnicode_DecodeUTF8Stateful PyUnicodeUCS4_DecodeUTF8Stateful
# define PyUnicode_DecodeUnicodeEscape PyUnicodeUCS4_DecodeUnicodeEscape
# define PyUnicode_Encode PyUnicodeUCS4_Encode
# define PyUnicode_EncodeASCII PyUnicodeUCS4_EncodeASCII
# define PyUnicode_EncodeCharmap PyUnicodeUCS4_EncodeCharmap
# define PyUnicode_EncodeDecimal PyUnicodeUCS4_EncodeDecimal
# define PyUnicode_EncodeLatin1 PyUnicodeUCS4_EncodeLatin1
# define PyUnicode_EncodeRawUnicodeEscape PyUnicodeUCS4_EncodeRawUnicodeEscape
# define PyUnicode_EncodeUTF32 PyUnicodeUCS4_EncodeUTF32
# define PyUnicode_EncodeUTF16 PyUnicodeUCS4_EncodeUTF16
# define PyUnicode_EncodeUTF8 PyUnicodeUCS4_EncodeUTF8
# define PyUnicode_EncodeUnicodeEscape PyUnicodeUCS4_EncodeUnicodeEscape
# define PyUnicode_Find PyUnicodeUCS4_Find
# define PyUnicode_Format PyUnicodeUCS4_Format
# define PyUnicode_FromEncodedObject PyUnicodeUCS4_FromEncodedObject
# define PyUnicode_FromFormat PyUnicodeUCS4_FromFormat
# define PyUnicode_FromFormatV PyUnicodeUCS4_FromFormatV
# define PyUnicode_FromObject PyUnicodeUCS4_FromObject
# define PyUnicode_FromOrdinal PyUnicodeUCS4_FromOrdinal
# define PyUnicode_FromString PyUnicodeUCS4_FromString
# define PyUnicode_FromStringAndSize PyUnicodeUCS4_FromStringAndSize
# define PyUnicode_FromUnicode PyUnicodeUCS4_FromUnicode
# define PyUnicode_FromWideChar PyUnicodeUCS4_FromWideChar
# define PyUnicode_GetDefaultEncoding PyUnicodeUCS4_GetDefaultEncoding
# define PyUnicode_GetMax PyUnicodeUCS4_GetMax
# define PyUnicode_GetSize PyUnicodeUCS4_GetSize
# define PyUnicode_Join PyUnicodeUCS4_Join
# define PyUnicode_Partition PyUnicodeUCS4_Partition
# define PyUnicode_RPartition PyUnicodeUCS4_RPartition
# define PyUnicode_RSplit PyUnicodeUCS4_RSplit
# define PyUnicode_Replace PyUnicodeUCS4_Replace
# define PyUnicode_Resize PyUnicodeUCS4_Resize
# define PyUnicode_RichCompare PyUnicodeUCS4_RichCompare
# define PyUnicode_SetDefaultEncoding PyUnicodeUCS4_SetDefaultEncoding
# define PyUnicode_Split PyUnicodeUCS4_Split
# define PyUnicode_Splitlines PyUnicodeUCS4_Splitlines
# define PyUnicode_Tailmatch PyUnicodeUCS4_Tailmatch
# define PyUnicode_Translate PyUnicodeUCS4_Translate
# define PyUnicode_TranslateCharmap PyUnicodeUCS4_TranslateCharmap
# define _PyUnicode_AsDefaultEncodedString _PyUnicodeUCS4_AsDefaultEncodedString
# define _PyUnicode_Fini _PyUnicodeUCS4_Fini
# define _PyUnicode_Init _PyUnicodeUCS4_Init
# define _PyUnicode_IsAlpha _PyUnicodeUCS4_IsAlpha
# define _PyUnicode_IsDecimalDigit _PyUnicodeUCS4_IsDecimalDigit
# define _PyUnicode_IsDigit _PyUnicodeUCS4_IsDigit
# define _PyUnicode_IsLinebreak _PyUnicodeUCS4_IsLinebreak
# define _PyUnicode_IsLowercase _PyUnicodeUCS4_IsLowercase
# define _PyUnicode_IsNumeric _PyUnicodeUCS4_IsNumeric
# define _PyUnicode_IsTitlecase _PyUnicodeUCS4_IsTitlecase
# define _PyUnicode_IsUppercase _PyUnicodeUCS4_IsUppercase
# define _PyUnicode_IsWhitespace _PyUnicodeUCS4_IsWhitespace
# define _PyUnicode_ToDecimalDigit _PyUnicodeUCS4_ToDecimalDigit
# define _PyUnicode_ToDigit _PyUnicodeUCS4_ToDigit
# define _PyUnicode_ToLowercase _PyUnicodeUCS4_ToLowercase
# define _PyUnicode_ToNumeric _PyUnicodeUCS4_ToNumeric
# define _PyUnicode_ToTitlecase _PyUnicodeUCS4_ToTitlecase
# define _PyUnicode_ToUppercase _PyUnicodeUCS4_ToUppercase
#endif
/* --- Internal Unicode Operations ---------------------------------------- */
/* If you want Python to use the compiler's wctype.h functions instead
of the ones supplied with Python, define WANT_WCTYPE_FUNCTIONS or
configure Python using --with-wctype-functions. This reduces the
interpreter's code size. */
#if defined(HAVE_USABLE_WCHAR_T) && defined(WANT_WCTYPE_FUNCTIONS)
#include <wctype.h>
#define Py_UNICODE_ISSPACE(ch) iswspace(ch)
#define Py_UNICODE_ISLOWER(ch) iswlower(ch)
#define Py_UNICODE_ISUPPER(ch) iswupper(ch)
#define Py_UNICODE_ISTITLE(ch) _PyUnicode_IsTitlecase(ch)
#define Py_UNICODE_ISLINEBREAK(ch) _PyUnicode_IsLinebreak(ch)
#define Py_UNICODE_TOLOWER(ch) towlower(ch)
#define Py_UNICODE_TOUPPER(ch) towupper(ch)
#define Py_UNICODE_TOTITLE(ch) _PyUnicode_ToTitlecase(ch)
#define Py_UNICODE_ISDECIMAL(ch) _PyUnicode_IsDecimalDigit(ch)
#define Py_UNICODE_ISDIGIT(ch) _PyUnicode_IsDigit(ch)
#define Py_UNICODE_ISNUMERIC(ch) _PyUnicode_IsNumeric(ch)
#define Py_UNICODE_TODECIMAL(ch) _PyUnicode_ToDecimalDigit(ch)
#define Py_UNICODE_TODIGIT(ch) _PyUnicode_ToDigit(ch)
#define Py_UNICODE_TONUMERIC(ch) _PyUnicode_ToNumeric(ch)
#define Py_UNICODE_ISALPHA(ch) iswalpha(ch)
#else
/* Since splitting on whitespace is an important use case, and
whitespace in most situations is solely ASCII whitespace, we
optimize for the common case by using a quick look-up table
_Py_ascii_whitespace (see below) with an inlined check.
*/
#define Py_UNICODE_ISSPACE(ch) \
((ch) < 128U ? _Py_ascii_whitespace[(ch)] : _PyUnicode_IsWhitespace(ch))
#define Py_UNICODE_ISLOWER(ch) _PyUnicode_IsLowercase(ch)
#define Py_UNICODE_ISUPPER(ch) _PyUnicode_IsUppercase(ch)
#define Py_UNICODE_ISTITLE(ch) _PyUnicode_IsTitlecase(ch)
#define Py_UNICODE_ISLINEBREAK(ch) _PyUnicode_IsLinebreak(ch)
#define Py_UNICODE_TOLOWER(ch) _PyUnicode_ToLowercase(ch)
#define Py_UNICODE_TOUPPER(ch) _PyUnicode_ToUppercase(ch)
#define Py_UNICODE_TOTITLE(ch) _PyUnicode_ToTitlecase(ch)
#define Py_UNICODE_ISDECIMAL(ch) _PyUnicode_IsDecimalDigit(ch)
#define Py_UNICODE_ISDIGIT(ch) _PyUnicode_IsDigit(ch)
#define Py_UNICODE_ISNUMERIC(ch) _PyUnicode_IsNumeric(ch)
#define Py_UNICODE_TODECIMAL(ch) _PyUnicode_ToDecimalDigit(ch)
#define Py_UNICODE_TODIGIT(ch) _PyUnicode_ToDigit(ch)
#define Py_UNICODE_TONUMERIC(ch) _PyUnicode_ToNumeric(ch)
#define Py_UNICODE_ISALPHA(ch) _PyUnicode_IsAlpha(ch)
#endif
#define Py_UNICODE_ISALNUM(ch) \
(Py_UNICODE_ISALPHA(ch) || \
Py_UNICODE_ISDECIMAL(ch) || \
Py_UNICODE_ISDIGIT(ch) || \
Py_UNICODE_ISNUMERIC(ch))
#define Py_UNICODE_COPY(target, source, length) \
Py_MEMCPY((target), (source), (length)*sizeof(Py_UNICODE))
#define Py_UNICODE_FILL(target, value, length) \
do {Py_ssize_t i_; Py_UNICODE *t_ = (target); Py_UNICODE v_ = (value);\
for (i_ = 0; i_ < (length); i_++) t_[i_] = v_;\
} while (0)
/* Check if substring matches at given offset. the offset must be
valid, and the substring must not be empty */
#define Py_UNICODE_MATCH(string, offset, substring) \
((*((string)->str + (offset)) == *((substring)->str)) && \
((*((string)->str + (offset) + (substring)->length-1) == *((substring)->str + (substring)->length-1))) && \
!memcmp((string)->str + (offset), (substring)->str, (substring)->length*sizeof(Py_UNICODE)))
#ifdef __cplusplus
extern "C" {
#endif
/* --- Unicode Type ------------------------------------------------------- */
typedef struct {
PyObject_HEAD
Py_ssize_t length; /* Length of raw Unicode data in buffer */
Py_UNICODE *str; /* Raw Unicode buffer */
long hash; /* Hash value; -1 if not set */
PyObject *defenc; /* (Default) Encoded version as Python
string, or NULL; this is used for
implementing the buffer protocol */
} PyUnicodeObject;
PyAPI_DATA(PyTypeObject) PyUnicode_Type;
#define PyUnicode_Check(op) \
PyType_FastSubclass(Py_TYPE(op), Py_TPFLAGS_UNICODE_SUBCLASS)
#define PyUnicode_CheckExact(op) (Py_TYPE(op) == &PyUnicode_Type)
/* Fast access macros */
#define PyUnicode_GET_SIZE(op) \
(((PyUnicodeObject *)(op))->length)
#define PyUnicode_GET_DATA_SIZE(op) \
(((PyUnicodeObject *)(op))->length * sizeof(Py_UNICODE))
#define PyUnicode_AS_UNICODE(op) \
(((PyUnicodeObject *)(op))->str)
#define PyUnicode_AS_DATA(op) \
((const char *)((PyUnicodeObject *)(op))->str)
/* --- Constants ---------------------------------------------------------- */
/* This Unicode character will be used as replacement character during
decoding if the errors argument is set to "replace". Note: the
Unicode character U+FFFD is the official REPLACEMENT CHARACTER in
Unicode 3.0. */
#define Py_UNICODE_REPLACEMENT_CHARACTER ((Py_UNICODE) 0xFFFD)
/* === Public API ========================================================= */
/* --- Plain Py_UNICODE --------------------------------------------------- */
/* Create a Unicode Object from the Py_UNICODE buffer u of the given
size.
u may be NULL which causes the contents to be undefined. It is the
user's responsibility to fill in the needed data afterwards. Note
that modifying the Unicode object contents after construction is
only allowed if u was set to NULL.
The buffer is copied into the new object. */
PyAPI_FUNC(PyObject*) PyUnicode_FromUnicode(
const Py_UNICODE *u, /* Unicode buffer */
Py_ssize_t size /* size of buffer */
);
/* Similar to PyUnicode_FromUnicode(), but u points to Latin-1 encoded bytes */
PyAPI_FUNC(PyObject*) PyUnicode_FromStringAndSize(
const char *u, /* char buffer */
Py_ssize_t size /* size of buffer */
);
/* Similar to PyUnicode_FromUnicode(), but u points to null-terminated
Latin-1 encoded bytes */
PyAPI_FUNC(PyObject*) PyUnicode_FromString(
const char *u /* string */
);
/* Return a read-only pointer to the Unicode object's internal
Py_UNICODE buffer. */
PyAPI_FUNC(Py_UNICODE *) PyUnicode_AsUnicode(
PyObject *unicode /* Unicode object */
);
/* Get the length of the Unicode object. */
PyAPI_FUNC(Py_ssize_t) PyUnicode_GetSize(
PyObject *unicode /* Unicode object */
);
/* Get the maximum ordinal for a Unicode character. */
PyAPI_FUNC(Py_UNICODE) PyUnicode_GetMax(void);
/* Resize an already allocated Unicode object to the new size length.
*unicode is modified to point to the new (resized) object and 0
returned on success.
This API may only be called by the function which also called the
Unicode constructor. The refcount on the object must be 1. Otherwise,
an error is returned.
Error handling is implemented as follows: an exception is set, -1
is returned and *unicode left untouched.
*/
PyAPI_FUNC(int) PyUnicode_Resize(
PyObject **unicode, /* Pointer to the Unicode object */
Py_ssize_t length /* New length */
);
/* Coerce obj to an Unicode object and return a reference with
*incremented* refcount.
Coercion is done in the following way:
1. String and other char buffer compatible objects are decoded
under the assumptions that they contain data using the current
default encoding. Decoding is done in "strict" mode.
2. All other objects (including Unicode objects) raise an
exception.
The API returns NULL in case of an error. The caller is responsible
for decref'ing the returned objects.
*/
PyAPI_FUNC(PyObject*) PyUnicode_FromEncodedObject(
register PyObject *obj, /* Object */
const char *encoding, /* encoding */
const char *errors /* error handling */
);
/* Coerce obj to an Unicode object and return a reference with
*incremented* refcount.
Unicode objects are passed back as-is (subclasses are converted to
true Unicode objects), all other objects are delegated to
PyUnicode_FromEncodedObject(obj, NULL, "strict") which results in
using the default encoding as basis for decoding the object.
The API returns NULL in case of an error. The caller is responsible
for decref'ing the returned objects.
*/
PyAPI_FUNC(PyObject*) PyUnicode_FromObject(
register PyObject *obj /* Object */
);
PyAPI_FUNC(PyObject *) PyUnicode_FromFormatV(const char*, va_list);
PyAPI_FUNC(PyObject *) PyUnicode_FromFormat(const char*, ...);
/* Format the object based on the format_spec, as defined in PEP 3101
(Advanced String Formatting). */
PyAPI_FUNC(PyObject *) _PyUnicode_FormatAdvanced(PyObject *obj,
Py_UNICODE *format_spec,
Py_ssize_t format_spec_len);
/* --- wchar_t support for platforms which support it --------------------- */
#ifdef HAVE_WCHAR_H
/* Create a Unicode Object from the whcar_t buffer w of the given
size.
The buffer is copied into the new object. */
PyAPI_FUNC(PyObject*) PyUnicode_FromWideChar(
register const wchar_t *w, /* wchar_t buffer */
Py_ssize_t size /* size of buffer */
);
/* Copies the Unicode Object contents into the wchar_t buffer w. At
most size wchar_t characters are copied.
Note that the resulting wchar_t string may or may not be
0-terminated. It is the responsibility of the caller to make sure
that the wchar_t string is 0-terminated in case this is required by
the application.
Returns the number of wchar_t characters copied (excluding a
possibly trailing 0-termination character) or -1 in case of an
error. */
PyAPI_FUNC(Py_ssize_t) PyUnicode_AsWideChar(
PyUnicodeObject *unicode, /* Unicode object */
register wchar_t *w, /* wchar_t buffer */
Py_ssize_t size /* size of buffer */
);
#endif
/* --- Unicode ordinals --------------------------------------------------- */
/* Create a Unicode Object from the given Unicode code point ordinal.
The ordinal must be in range(0x10000) on narrow Python builds
(UCS2), and range(0x110000) on wide builds (UCS4). A ValueError is
raised in case it is not.
*/
PyAPI_FUNC(PyObject*) PyUnicode_FromOrdinal(int ordinal);
/* --- Free-list management ----------------------------------------------- */
/* Clear the free list used by the Unicode implementation.
This can be used to release memory used for objects on the free
list back to the Python memory allocator.
*/
PyAPI_FUNC(int) PyUnicode_ClearFreeList(void);
/* === Builtin Codecs =====================================================
Many of these APIs take two arguments encoding and errors. These
parameters encoding and errors have the same semantics as the ones
of the builtin unicode() API.
Setting encoding to NULL causes the default encoding to be used.
Error handling is set by errors which may also be set to NULL
meaning to use the default handling defined for the codec. Default
error handling for all builtin codecs is "strict" (ValueErrors are
raised).
The codecs all use a similar interface. Only deviation from the
generic ones are documented.
*/
/* --- Manage the default encoding ---------------------------------------- */
/* Return a Python string holding the default encoded value of the
Unicode object.
The resulting string is cached in the Unicode object for subsequent
usage by this function. The cached version is needed to implement
the character buffer interface and will live (at least) as long as
the Unicode object itself.
The refcount of the string is *not* incremented.
*** Exported for internal use by the interpreter only !!! ***
*/
PyAPI_FUNC(PyObject *) _PyUnicode_AsDefaultEncodedString(
PyObject *, const char *);
/* Returns the currently active default encoding.
The default encoding is currently implemented as run-time settable
process global. This may change in future versions of the
interpreter to become a parameter which is managed on a per-thread
basis.
*/
PyAPI_FUNC(const char*) PyUnicode_GetDefaultEncoding(void);
/* Sets the currently active default encoding.
Returns 0 on success, -1 in case of an error.
*/
PyAPI_FUNC(int) PyUnicode_SetDefaultEncoding(
const char *encoding /* Encoding name in standard form */
);
/* --- Generic Codecs ----------------------------------------------------- */
/* Create a Unicode object by decoding the encoded string s of the
given size. */
PyAPI_FUNC(PyObject*) PyUnicode_Decode(
const char *s, /* encoded string */
Py_ssize_t size, /* size of buffer */
const char *encoding, /* encoding */
const char *errors /* error handling */
);
/* Encodes a Py_UNICODE buffer of the given size and returns a
Python string object. */
PyAPI_FUNC(PyObject*) PyUnicode_Encode(
const Py_UNICODE *s, /* Unicode char buffer */
Py_ssize_t size, /* number of Py_UNICODE chars to encode */
const char *encoding, /* encoding */
const char *errors /* error handling */
);
/* Encodes a Unicode object and returns the result as Python
object. */
PyAPI_FUNC(PyObject*) PyUnicode_AsEncodedObject(
PyObject *unicode, /* Unicode object */
const char *encoding, /* encoding */
const char *errors /* error handling */
);
/* Encodes a Unicode object and returns the result as Python string
object. */
PyAPI_FUNC(PyObject*) PyUnicode_AsEncodedString(
PyObject *unicode, /* Unicode object */
const char *encoding, /* encoding */
const char *errors /* error handling */
);
PyAPI_FUNC(PyObject*) PyUnicode_BuildEncodingMap(
PyObject* string /* 256 character map */
);
/* --- UTF-7 Codecs ------------------------------------------------------- */
PyAPI_FUNC(PyObject*) PyUnicode_DecodeUTF7(
const char *string, /* UTF-7 encoded string */
Py_ssize_t length, /* size of string */
const char *errors /* error handling */
);
PyAPI_FUNC(PyObject*) PyUnicode_DecodeUTF7Stateful(
const char *string, /* UTF-7 encoded string */
Py_ssize_t length, /* size of string */
const char *errors, /* error handling */
Py_ssize_t *consumed /* bytes consumed */
);
PyAPI_FUNC(PyObject*) PyUnicode_EncodeUTF7(
const Py_UNICODE *data, /* Unicode char buffer */
Py_ssize_t length, /* number of Py_UNICODE chars to encode */
int base64SetO, /* Encode RFC2152 Set O characters in base64 */
int base64WhiteSpace, /* Encode whitespace (sp, ht, nl, cr) in base64 */
const char *errors /* error handling */
);
/* --- UTF-8 Codecs ------------------------------------------------------- */
PyAPI_FUNC(PyObject*) PyUnicode_DecodeUTF8(
const char *string, /* UTF-8 encoded string */
Py_ssize_t length, /* size of string */
const char *errors /* error handling */
);
PyAPI_FUNC(PyObject*) PyUnicode_DecodeUTF8Stateful(
const char *string, /* UTF-8 encoded string */
Py_ssize_t length, /* size of string */
const char *errors, /* error handling */
Py_ssize_t *consumed /* bytes consumed */
);
PyAPI_FUNC(PyObject*) PyUnicode_AsUTF8String(
PyObject *unicode /* Unicode object */
);
PyAPI_FUNC(PyObject*) PyUnicode_EncodeUTF8(
const Py_UNICODE *data, /* Unicode char buffer */
Py_ssize_t length, /* number of Py_UNICODE chars to encode */
const char *errors /* error handling */
);
/* --- UTF-32 Codecs ------------------------------------------------------ */
/* Decodes length bytes from a UTF-32 encoded buffer string and returns
the corresponding Unicode object.
errors (if non-NULL) defines the error handling. It defaults
to "strict".
If byteorder is non-NULL, the decoder starts decoding using the
given byte order:
*byteorder == -1: little endian
*byteorder == 0: native order
*byteorder == 1: big endian
In native mode, the first four bytes of the stream are checked for a
BOM mark. If found, the BOM mark is analysed, the byte order
adjusted and the BOM skipped. In the other modes, no BOM mark
interpretation is done. After completion, *byteorder is set to the
current byte order at the end of input data.
If byteorder is NULL, the codec starts in native order mode.
*/
PyAPI_FUNC(PyObject*) PyUnicode_DecodeUTF32(
const char *string, /* UTF-32 encoded string */
Py_ssize_t length, /* size of string */
const char *errors, /* error handling */
int *byteorder /* pointer to byteorder to use
0=native;-1=LE,1=BE; updated on
exit */
);
PyAPI_FUNC(PyObject*) PyUnicode_DecodeUTF32Stateful(
const char *string, /* UTF-32 encoded string */
Py_ssize_t length, /* size of string */
const char *errors, /* error handling */
int *byteorder, /* pointer to byteorder to use
0=native;-1=LE,1=BE; updated on
exit */
Py_ssize_t *consumed /* bytes consumed */
);
/* Returns a Python string using the UTF-32 encoding in native byte
order. The string always starts with a BOM mark. */
PyAPI_FUNC(PyObject*) PyUnicode_AsUTF32String(
PyObject *unicode /* Unicode object */
);
/* Returns a Python string object holding the UTF-32 encoded value of
the Unicode data.
If byteorder is not 0, output is written according to the following
byte order:
byteorder == -1: little endian
byteorder == 0: native byte order (writes a BOM mark)
byteorder == 1: big endian
If byteorder is 0, the output string will always start with the
Unicode BOM mark (U+FEFF). In the other two modes, no BOM mark is
prepended.
*/
PyAPI_FUNC(PyObject*) PyUnicode_EncodeUTF32(
const Py_UNICODE *data, /* Unicode char buffer */
Py_ssize_t length, /* number of Py_UNICODE chars to encode */
const char *errors, /* error handling */
int byteorder /* byteorder to use 0=BOM+native;-1=LE,1=BE */
);
/* --- UTF-16 Codecs ------------------------------------------------------ */
/* Decodes length bytes from a UTF-16 encoded buffer string and returns
the corresponding Unicode object.
errors (if non-NULL) defines the error handling. It defaults
to "strict".
If byteorder is non-NULL, the decoder starts decoding using the
given byte order:
*byteorder == -1: little endian
*byteorder == 0: native order
*byteorder == 1: big endian
In native mode, the first two bytes of the stream are checked for a
BOM mark. If found, the BOM mark is analysed, the byte order
adjusted and the BOM skipped. In the other modes, no BOM mark
interpretation is done. After completion, *byteorder is set to the
current byte order at the end of input data.
If byteorder is NULL, the codec starts in native order mode.
*/
PyAPI_FUNC(PyObject*) PyUnicode_DecodeUTF16(
const char *string, /* UTF-16 encoded string */
Py_ssize_t length, /* size of string */
const char *errors, /* error handling */
int *byteorder /* pointer to byteorder to use
0=native;-1=LE,1=BE; updated on
exit */
);
PyAPI_FUNC(PyObject*) PyUnicode_DecodeUTF16Stateful(
const char *string, /* UTF-16 encoded string */
Py_ssize_t length, /* size of string */
const char *errors, /* error handling */
int *byteorder, /* pointer to byteorder to use
0=native;-1=LE,1=BE; updated on
exit */
Py_ssize_t *consumed /* bytes consumed */
);
/* Returns a Python string using the UTF-16 encoding in native byte
order. The string always starts with a BOM mark. */
PyAPI_FUNC(PyObject*) PyUnicode_AsUTF16String(
PyObject *unicode /* Unicode object */
);
/* Returns a Python string object holding the UTF-16 encoded value of
the Unicode data.
If byteorder is not 0, output is written according to the following
byte order:
byteorder == -1: little endian
byteorder == 0: native byte order (writes a BOM mark)
byteorder == 1: big endian
If byteorder is 0, the output string will always start with the
Unicode BOM mark (U+FEFF). In the other two modes, no BOM mark is
prepended.
Note that Py_UNICODE data is being interpreted as UTF-16 reduced to
UCS-2. This trick makes it possible to add full UTF-16 capabilities
at a later point without compromising the APIs.
*/
PyAPI_FUNC(PyObject*) PyUnicode_EncodeUTF16(
const Py_UNICODE *data, /* Unicode char buffer */
Py_ssize_t length, /* number of Py_UNICODE chars to encode */
const char *errors, /* error handling */
int byteorder /* byteorder to use 0=BOM+native;-1=LE,1=BE */
);
/* --- Unicode-Escape Codecs ---------------------------------------------- */
PyAPI_FUNC(PyObject*) PyUnicode_DecodeUnicodeEscape(
const char *string, /* Unicode-Escape encoded string */
Py_ssize_t length, /* size of string */
const char *errors /* error handling */
);
PyAPI_FUNC(PyObject*) PyUnicode_AsUnicodeEscapeString(
PyObject *unicode /* Unicode object */
);
PyAPI_FUNC(PyObject*) PyUnicode_EncodeUnicodeEscape(
const Py_UNICODE *data, /* Unicode char buffer */
Py_ssize_t length /* Number of Py_UNICODE chars to encode */
);
/* --- Raw-Unicode-Escape Codecs ------------------------------------------ */
PyAPI_FUNC(PyObject*) PyUnicode_DecodeRawUnicodeEscape(
const char *string, /* Raw-Unicode-Escape encoded string */
Py_ssize_t length, /* size of string */
const char *errors /* error handling */
);
PyAPI_FUNC(PyObject*) PyUnicode_AsRawUnicodeEscapeString(
PyObject *unicode /* Unicode object */
);
PyAPI_FUNC(PyObject*) PyUnicode_EncodeRawUnicodeEscape(
const Py_UNICODE *data, /* Unicode char buffer */
Py_ssize_t length /* Number of Py_UNICODE chars to encode */
);
/* --- Unicode Internal Codec ---------------------------------------------
Only for internal use in _codecsmodule.c */
PyObject *_PyUnicode_DecodeUnicodeInternal(
const char *string,
Py_ssize_t length,
const char *errors
);
/* --- Latin-1 Codecs -----------------------------------------------------
Note: Latin-1 corresponds to the first 256 Unicode ordinals.
*/
PyAPI_FUNC(PyObject*) PyUnicode_DecodeLatin1(
const char *string, /* Latin-1 encoded string */
Py_ssize_t length, /* size of string */
const char *errors /* error handling */
);
PyAPI_FUNC(PyObject*) PyUnicode_AsLatin1String(
PyObject *unicode /* Unicode object */
);
PyAPI_FUNC(PyObject*) PyUnicode_EncodeLatin1(
const Py_UNICODE *data, /* Unicode char buffer */
Py_ssize_t length, /* Number of Py_UNICODE chars to encode */
const char *errors /* error handling */
);
/* --- ASCII Codecs -------------------------------------------------------
Only 7-bit ASCII data is excepted. All other codes generate errors.
*/
PyAPI_FUNC(PyObject*) PyUnicode_DecodeASCII(
const char *string, /* ASCII encoded string */
Py_ssize_t length, /* size of string */
const char *errors /* error handling */
You can’t perform that action at this time.