Repository navigation
Expand file tree
/
Copy pathunicodeobject.h
More file actions
2137 lines (1667 loc) · 72.2 KB
/
Copy pathunicodeobject.h
File metadata and controls
2137 lines (1667 loc) · 72.2 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
#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
http://www.egenix.com/files/python/unicode-proposal.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 -------------------------------------------- */
/* Python 3.x requires unicode */
#define Py_USING_UNICODE
#ifndef SIZEOF_WCHAR_T
#error Must define SIZEOF_WCHAR_T
#endif
#define Py_UNICODE_SIZE SIZEOF_WCHAR_T
/* If wchar_t can be used for UCS-4 storage, set Py_UNICODE_WIDE.
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" and the
wchar_t type is a 16-bit unsigned type */
/* #define HAVE_WCHAR_H */
/* #define HAVE_USABLE_WCHAR_T */
/* Py_UNICODE was the native Unicode storage format (code unit) used by
Python and represents a single Unicode element in the Unicode type.
With PEP 393, Py_UNICODE is deprecated and replaced with a
typedef to wchar_t. */
#ifndef Py_LIMITED_API
#define PY_UNICODE_TYPE wchar_t
typedef wchar_t Py_UNICODE;
#endif
/* If the compiler provides a wchar_t type we try to support it
through the interface functions PyUnicode_FromWideChar(),
PyUnicode_AsWideChar() and PyUnicode_AsWideCharString(). */
#ifdef HAVE_USABLE_WCHAR_T
# ifndef HAVE_WCHAR_H
# define HAVE_WCHAR_H
# endif
#endif
#if defined(MS_WINDOWS)
# define HAVE_MBCS
#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
/* Py_UCS4 and Py_UCS2 are typedefs for the respective
unicode representations. */
#if SIZEOF_INT == 4
typedef unsigned int Py_UCS4;
#elif SIZEOF_LONG == 4
typedef unsigned long Py_UCS4;
#else
#error "Could not find a proper typedef for Py_UCS4"
#endif
#if SIZEOF_SHORT == 2
typedef unsigned short Py_UCS2;
#else
#error "Could not find a proper typedef for Py_UCS2"
#endif
typedef unsigned char Py_UCS1;
/* --- Internal Unicode Operations ---------------------------------------- */
/* 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.
*/
#ifndef Py_LIMITED_API
#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_ISPRINTABLE(ch) _PyUnicode_IsPrintable(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)
#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)
/* macros to work with surrogates */
#define Py_UNICODE_IS_SURROGATE(ch) (0xD800 <= ch && ch <= 0xDFFF)
#define Py_UNICODE_IS_HIGH_SURROGATE(ch) (0xD800 <= ch && ch <= 0xDBFF)
#define Py_UNICODE_IS_LOW_SURROGATE(ch) (0xDC00 <= ch && ch <= 0xDFFF)
/* Join two surrogate characters and return a single Py_UCS4 value. */
#define Py_UNICODE_JOIN_SURROGATES(high, low) \
(((((Py_UCS4)(high) & 0x03FF) << 10) | \
((Py_UCS4)(low) & 0x03FF)) + 0x10000)
/* high surrogate = top 10 bits added to D800 */
#define Py_UNICODE_HIGH_SURROGATE(ch) (0xD800 | (((ch) - 0x10000) >> 10))
/* low surrogate = bottom 10 bits added to DC00 */
#define Py_UNICODE_LOW_SURROGATE(ch) (0xDC00 | (((ch) - 0x10000) & 0x3FF))
/* 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)->wstr + (offset)) == *((substring)->wstr)) && \
((*((string)->wstr + (offset) + (substring)->wstr_length-1) == *((substring)->wstr + (substring)->wstr_length-1))) && \
!memcmp((string)->wstr + (offset), (substring)->wstr, (substring)->wstr_length*sizeof(Py_UNICODE)))
#endif /* Py_LIMITED_API */
#ifdef __cplusplus
extern "C" {
#endif
/* --- Unicode Type ------------------------------------------------------- */
#ifndef Py_LIMITED_API
/* ASCII-only strings created through PyUnicode_New use the PyASCIIObject
structure. state.ascii and state.compact are set, and the data
immediately follow the structure. utf8_length and wstr_length can be found
in the length field; the utf8 pointer is equal to the data pointer. */
typedef struct {
/* There are 4 forms of Unicode strings:
- compact ascii:
* structure = PyASCIIObject
* test: PyUnicode_IS_COMPACT_ASCII(op)
* kind = PyUnicode_1BYTE_KIND
* compact = 1
* ascii = 1
* ready = 1
* (length is the length of the utf8 and wstr strings)
* (data starts just after the structure)
* (since ASCII is decoded from UTF-8, the utf8 string are the data)
- compact:
* structure = PyCompactUnicodeObject
* test: PyUnicode_IS_COMPACT(op) && !PyUnicode_IS_ASCII(op)
* kind = PyUnicode_1BYTE_KIND, PyUnicode_2BYTE_KIND or
PyUnicode_4BYTE_KIND
* compact = 1
* ready = 1
* ascii = 0
* utf8 is not shared with data
* utf8_length = 0 if utf8 is NULL
* wstr is shared with data and wstr_length=length
if kind=PyUnicode_2BYTE_KIND and sizeof(wchar_t)=2
or if kind=PyUnicode_4BYTE_KIND and sizeof(wchar_t)=4
* wstr_length = 0 if wstr is NULL
* (data starts just after the structure)
- legacy string, not ready:
* structure = PyUnicodeObject
* test: kind == PyUnicode_WCHAR_KIND
* length = 0 (use wstr_length)
* hash = -1
* kind = PyUnicode_WCHAR_KIND
* compact = 0
* ascii = 0
* ready = 0
* interned = SSTATE_NOT_INTERNED
* wstr is not NULL
* data.any is NULL
* utf8 is NULL
* utf8_length = 0
- legacy string, ready:
* structure = PyUnicodeObject structure
* test: !PyUnicode_IS_COMPACT(op) && kind != PyUnicode_WCHAR_KIND
* kind = PyUnicode_1BYTE_KIND, PyUnicode_2BYTE_KIND or
PyUnicode_4BYTE_KIND
* compact = 0
* ready = 1
* data.any is not NULL
* utf8 is shared and utf8_length = length with data.any if ascii = 1
* utf8_length = 0 if utf8 is NULL
* wstr is shared with data.any and wstr_length = length
if kind=PyUnicode_2BYTE_KIND and sizeof(wchar_t)=2
or if kind=PyUnicode_4BYTE_KIND and sizeof(wchar_4)=4
* wstr_length = 0 if wstr is NULL
Compact strings use only one memory block (structure + characters),
whereas legacy strings use one block for the structure and one block
for characters.
Legacy strings are created by PyUnicode_FromUnicode() and
PyUnicode_FromStringAndSize(NULL, size) functions. They become ready
when PyUnicode_READY() is called.
See also _PyUnicode_CheckConsistency().
*/
PyObject_HEAD
Py_ssize_t length; /* Number of code points in the string */
Py_hash_t hash; /* Hash value; -1 if not set */
struct {
/*
SSTATE_NOT_INTERNED (0)
SSTATE_INTERNED_MORTAL (1)
SSTATE_INTERNED_IMMORTAL (2)
If interned != SSTATE_NOT_INTERNED, the two references from the
dictionary to this object are *not* counted in ob_refcnt.
*/
unsigned int interned:2;
/* Character size:
- PyUnicode_WCHAR_KIND (0):
* character type = wchar_t (16 or 32 bits, depending on the
platform)
- PyUnicode_1BYTE_KIND (1):
* character type = Py_UCS1 (8 bits, unsigned)
* all characters are in the range U+0000-U+00FF (latin1)
* if ascii is set, all characters are in the range U+0000-U+007F
(ASCII), otherwise at least one character is in the range
U+0080-U+00FF
- PyUnicode_2BYTE_KIND (2):
* character type = Py_UCS2 (16 bits, unsigned)
* all characters are in the range U+0000-U+FFFF (BMP)
* at least one character is in the range U+0100-U+FFFF
- PyUnicode_4BYTE_KIND (4):
* character type = Py_UCS4 (32 bits, unsigned)
* all characters are in the range U+0000-U+10FFFF
* at least one character is in the range U+10000-U+10FFFF
*/
unsigned int kind:3;
/* Compact is with respect to the allocation scheme. Compact unicode
objects only require one memory block while non-compact objects use
one block for the PyUnicodeObject struct and another for its data
buffer. */
unsigned int compact:1;
/* The string only contains characters in the range U+0000-U+007F (ASCII)
and the kind is PyUnicode_1BYTE_KIND. If ascii is set and compact is
set, use the PyASCIIObject structure. */
unsigned int ascii:1;
/* The ready flag indicates whether the object layout is initialized
completely. This means that this is either a compact object, or
the data pointer is filled out. The bit is redundant, and helps
to minimize the test in PyUnicode_IS_READY(). */
unsigned int ready:1;
} state;
wchar_t *wstr; /* wchar_t representation (null-terminated) */
} PyASCIIObject;
/* Non-ASCII strings allocated through PyUnicode_New use the
PyCompactUnicodeObject structure. state.compact is set, and the data
immediately follow the structure. */
typedef struct {
PyASCIIObject _base;
Py_ssize_t utf8_length; /* Number of bytes in utf8, excluding the
* terminating \0. */
char *utf8; /* UTF-8 representation (null-terminated) */
Py_ssize_t wstr_length; /* Number of code points in wstr, possible
* surrogates count as two code points. */
} PyCompactUnicodeObject;
/* Strings allocated through PyUnicode_FromUnicode(NULL, len) use the
PyUnicodeObject structure. The actual string data is initially in the wstr
block, and copied into the data block using _PyUnicode_Ready. */
typedef struct {
PyCompactUnicodeObject _base;
union {
void *any;
Py_UCS1 *latin1;
Py_UCS2 *ucs2;
Py_UCS4 *ucs4;
} data; /* Canonical, smallest-form Unicode buffer */
} PyUnicodeObject;
#endif
PyAPI_DATA(PyTypeObject) PyUnicode_Type;
PyAPI_DATA(PyTypeObject) PyUnicodeIter_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 */
#ifndef Py_LIMITED_API
#define PyUnicode_WSTR_LENGTH(op) \
(PyUnicode_IS_COMPACT_ASCII(op) ? \
((PyASCIIObject*)op)->length : \
((PyCompactUnicodeObject*)op)->wstr_length)
/* Returns the deprecated Py_UNICODE representation's size in code units
(this includes surrogate pairs as 2 units).
If the Py_UNICODE representation is not available, it will be computed
on request. Use PyUnicode_GET_LENGTH() for the length in code points. */
#define PyUnicode_GET_SIZE(op) \
(assert(PyUnicode_Check(op)), \
(((PyASCIIObject *)(op))->wstr) ? \
PyUnicode_WSTR_LENGTH(op) : \
((void)PyUnicode_AsUnicode((PyObject *)(op)), \
assert(((PyASCIIObject *)(op))->wstr), \
PyUnicode_WSTR_LENGTH(op)))
#define PyUnicode_GET_DATA_SIZE(op) \
(PyUnicode_GET_SIZE(op) * Py_UNICODE_SIZE)
/* Alias for PyUnicode_AsUnicode(). This will create a wchar_t/Py_UNICODE
representation on demand. Using this macro is very inefficient now,
try to port your code to use the new PyUnicode_*BYTE_DATA() macros or
use PyUnicode_WRITE() and PyUnicode_READ(). */
#define PyUnicode_AS_UNICODE(op) \
(assert(PyUnicode_Check(op)), \
(((PyASCIIObject *)(op))->wstr) ? (((PyASCIIObject *)(op))->wstr) : \
PyUnicode_AsUnicode((PyObject *)(op)))
#define PyUnicode_AS_DATA(op) \
((const char *)(PyUnicode_AS_UNICODE(op)))
/* --- Flexible String Representation Helper Macros (PEP 393) -------------- */
/* Values for PyASCIIObject.state: */
/* Interning state. */
#define SSTATE_NOT_INTERNED 0
#define SSTATE_INTERNED_MORTAL 1
#define SSTATE_INTERNED_IMMORTAL 2
/* Return true if the string contains only ASCII characters, or 0 if not. The
string may be compact (PyUnicode_IS_COMPACT_ASCII) or not, but must be
ready. */
#define PyUnicode_IS_ASCII(op) \
(assert(PyUnicode_Check(op)), \
assert(PyUnicode_IS_READY(op)), \
((PyASCIIObject*)op)->state.ascii)
/* Return true if the string is compact or 0 if not.
No type checks or Ready calls are performed. */
#define PyUnicode_IS_COMPACT(op) \
(((PyASCIIObject*)(op))->state.compact)
/* Return true if the string is a compact ASCII string (use PyASCIIObject
structure), or 0 if not. No type checks or Ready calls are performed. */
#define PyUnicode_IS_COMPACT_ASCII(op) \
(((PyASCIIObject*)op)->state.ascii && PyUnicode_IS_COMPACT(op))
enum PyUnicode_Kind {
/* String contains only wstr byte characters. This is only possible
when the string was created with a legacy API and _PyUnicode_Ready()
has not been called yet. */
PyUnicode_WCHAR_KIND = 0,
/* Return values of the PyUnicode_KIND() macro: */
PyUnicode_1BYTE_KIND = 1,
PyUnicode_2BYTE_KIND = 2,
PyUnicode_4BYTE_KIND = 4
};
/* Return pointers to the canonical representation cast to unsigned char,
Py_UCS2, or Py_UCS4 for direct character access.
No checks are performed, use PyUnicode_KIND() before to ensure
these will work correctly. */
#define PyUnicode_1BYTE_DATA(op) ((Py_UCS1*)PyUnicode_DATA(op))
#define PyUnicode_2BYTE_DATA(op) ((Py_UCS2*)PyUnicode_DATA(op))
#define PyUnicode_4BYTE_DATA(op) ((Py_UCS4*)PyUnicode_DATA(op))
/* Return one of the PyUnicode_*_KIND values defined above. */
#define PyUnicode_KIND(op) \
(assert(PyUnicode_Check(op)), \
assert(PyUnicode_IS_READY(op)), \
((PyASCIIObject *)(op))->state.kind)
/* Return a void pointer to the raw unicode buffer. */
#define _PyUnicode_COMPACT_DATA(op) \
(PyUnicode_IS_ASCII(op) ? \
((void*)((PyASCIIObject*)(op) + 1)) : \
((void*)((PyCompactUnicodeObject*)(op) + 1)))
#define _PyUnicode_NONCOMPACT_DATA(op) \
(assert(((PyUnicodeObject*)(op))->data.any), \
((((PyUnicodeObject *)(op))->data.any)))
#define PyUnicode_DATA(op) \
(assert(PyUnicode_Check(op)), \
PyUnicode_IS_COMPACT(op) ? _PyUnicode_COMPACT_DATA(op) : \
_PyUnicode_NONCOMPACT_DATA(op))
/* In the access macros below, "kind" may be evaluated more than once.
All other macro parameters are evaluated exactly once, so it is safe
to put side effects into them (such as increasing the index). */
/* Write into the canonical representation, this macro does not do any sanity
checks and is intended for usage in loops. The caller should cache the
kind and data pointers obtained from other macro calls.
index is the index in the string (starts at 0) and value is the new
code point value which should be written to that location. */
#define PyUnicode_WRITE(kind, data, index, value) \
do { \
switch ((kind)) { \
case PyUnicode_1BYTE_KIND: { \
((Py_UCS1 *)(data))[(index)] = (Py_UCS1)(value); \
break; \
} \
case PyUnicode_2BYTE_KIND: { \
((Py_UCS2 *)(data))[(index)] = (Py_UCS2)(value); \
break; \
} \
default: { \
assert((kind) == PyUnicode_4BYTE_KIND); \
((Py_UCS4 *)(data))[(index)] = (Py_UCS4)(value); \
} \
} \
} while (0)
/* Read a code point from the string's canonical representation. No checks
or ready calls are performed. */
#define PyUnicode_READ(kind, data, index) \
((Py_UCS4) \
((kind) == PyUnicode_1BYTE_KIND ? \
((const Py_UCS1 *)(data))[(index)] : \
((kind) == PyUnicode_2BYTE_KIND ? \
((const Py_UCS2 *)(data))[(index)] : \
((const Py_UCS4 *)(data))[(index)] \
) \
))
/* PyUnicode_READ_CHAR() is less efficient than PyUnicode_READ() because it
calls PyUnicode_KIND() and might call it twice. For single reads, use
PyUnicode_READ_CHAR, for multiple consecutive reads callers should
cache kind and use PyUnicode_READ instead. */
#define PyUnicode_READ_CHAR(unicode, index) \
(assert(PyUnicode_Check(unicode)), \
assert(PyUnicode_IS_READY(unicode)), \
(Py_UCS4) \
(PyUnicode_KIND((unicode)) == PyUnicode_1BYTE_KIND ? \
((const Py_UCS1 *)(PyUnicode_DATA((unicode))))[(index)] : \
(PyUnicode_KIND((unicode)) == PyUnicode_2BYTE_KIND ? \
((const Py_UCS2 *)(PyUnicode_DATA((unicode))))[(index)] : \
((const Py_UCS4 *)(PyUnicode_DATA((unicode))))[(index)] \
) \
))
/* Returns the length of the unicode string. The caller has to make sure that
the string has it's canonical representation set before calling
this macro. Call PyUnicode_(FAST_)Ready to ensure that. */
#define PyUnicode_GET_LENGTH(op) \
(assert(PyUnicode_Check(op)), \
assert(PyUnicode_IS_READY(op)), \
((PyASCIIObject *)(op))->length)
/* Fast check to determine whether an object is ready. Equivalent to
PyUnicode_IS_COMPACT(op) || ((PyUnicodeObject*)(op))->data.any) */
#define PyUnicode_IS_READY(op) (((PyASCIIObject*)op)->state.ready)
/* PyUnicode_READY() does less work than _PyUnicode_Ready() in the best
case. If the canonical representation is not yet set, it will still call
_PyUnicode_Ready().
Returns 0 on success and -1 on errors. */
#define PyUnicode_READY(op) \
(assert(PyUnicode_Check(op)), \
(PyUnicode_IS_READY(op) ? \
0 : _PyUnicode_Ready((PyObject *)(op))))
/* Return a maximum character value which is suitable for creating another
string based on op. This is always an approximation but more efficient
than iterating over the string. */
#define PyUnicode_MAX_CHAR_VALUE(op) \
(assert(PyUnicode_IS_READY(op)), \
(PyUnicode_IS_ASCII(op) ? \
(0x7f) : \
(PyUnicode_KIND(op) == PyUnicode_1BYTE_KIND ? \
(0xffU) : \
(PyUnicode_KIND(op) == PyUnicode_2BYTE_KIND ? \
(0xffffU) : \
(0x10ffffU)))))
#endif
/* --- 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_UCS4) 0xFFFD)
/* === Public API ========================================================= */
/* --- Plain Py_UNICODE --------------------------------------------------- */
/* With PEP 393, this is the recommended way to allocate a new unicode object.
This function will allocate the object and its buffer in a single memory
block. Objects created using this function are not resizable. */
#ifndef Py_LIMITED_API
PyAPI_FUNC(PyObject*) PyUnicode_New(
Py_ssize_t size, /* Number of code points in the new string */
Py_UCS4 maxchar /* maximum code point value in the string */
);
#endif
/* Initializes the canonical string representation from a the deprecated
wstr/Py_UNICODE representation. This function is used to convert Unicode
objects which were created using the old API to the new flexible format
introduced with PEP 393.
Don't call this function directly, use the public PyUnicode_READY() macro
instead. */
#ifndef Py_LIMITED_API
PyAPI_FUNC(int) _PyUnicode_Ready(
PyObject *unicode /* Unicode object */
);
#endif
/* Get a copy of a Unicode string. */
#ifndef Py_LIMITED_API
PyAPI_FUNC(PyObject*) _PyUnicode_Copy(
PyObject *unicode
);
#endif
/* Copy character from one unicode object into another, this function performs
character conversion when necessary and falls back to memcpy() if possible.
Fail if to is too small (smaller than *how_many* or smaller than
len(from)-from_start), or if kind(from[from_start:from_start+how_many]) >
kind(to), or if *to* has more than 1 reference.
Return the number of written character, or return -1 and raise an exception
on error.
Pseudo-code:
how_many = min(how_many, len(from) - from_start)
to[to_start:to_start+how_many] = from[from_start:from_start+how_many]
return how_many
Note: The function doesn't write a terminating null character.
*/
#ifndef Py_LIMITED_API
PyAPI_FUNC(Py_ssize_t) PyUnicode_CopyCharacters(
PyObject *to,
Py_ssize_t to_start,
PyObject *from,
Py_ssize_t from_start,
Py_ssize_t how_many
);
#endif
/* Fill a string with a character: write fill_char into
unicode[start:start+length].
Fail if fill_char is bigger than the string maximum character, or if the
string has more than 1 reference.
Return the number of written character, or return -1 and raise an exception
on error. */
#ifndef Py_LIMITED_API
PyAPI_FUNC(Py_ssize_t) PyUnicode_Fill(
PyObject *unicode,
Py_ssize_t start,
Py_ssize_t length,
Py_UCS4 fill_char
);
#endif
/* 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. */
#ifndef Py_LIMITED_API
PyAPI_FUNC(PyObject*) PyUnicode_FromUnicode(
const Py_UNICODE *u, /* Unicode buffer */
Py_ssize_t size /* size of buffer */
);
#endif
/* Similar to PyUnicode_FromUnicode(), but u points to UTF-8 encoded bytes */
PyAPI_FUNC(PyObject*) PyUnicode_FromStringAndSize(
const char *u, /* UTF-8 encoded string */
Py_ssize_t size /* size of buffer */
);
/* Similar to PyUnicode_FromUnicode(), but u points to null-terminated
UTF-8 encoded bytes. The size is determined with strlen(). */
PyAPI_FUNC(PyObject*) PyUnicode_FromString(
const char *u /* UTF-8 encoded string */
);
/* Create a new string from a buffer of Py_UCS1, Py_UCS2 or Py_UCS4 characters.
Scan the string to find the maximum character. */
#ifndef Py_LIMITED_API
PyAPI_FUNC(PyObject*) PyUnicode_FromKindAndData(
int kind,
const void *buffer,
Py_ssize_t size);
#endif
PyAPI_FUNC(PyObject*) PyUnicode_Substring(
PyObject *str,
Py_ssize_t start,
Py_ssize_t end);
/* Copy the string into a UCS4 buffer including the null character if copy_null
is set. Return NULL and raise an exception on error. Raise a ValueError if
the buffer is smaller than the string. Return buffer on success.
buflen is the length of the buffer in (Py_UCS4) characters. */
PyAPI_FUNC(Py_UCS4*) PyUnicode_AsUCS4(
PyObject *unicode,
Py_UCS4* buffer,
Py_ssize_t buflen,
int copy_null);
/* Copy the string into a UCS4 buffer. A new buffer is allocated using
* PyMem_Malloc; if this fails, NULL is returned with a memory error
exception set. */
PyAPI_FUNC(Py_UCS4*) PyUnicode_AsUCS4Copy(PyObject *unicode);
/* Return a read-only pointer to the Unicode object's internal
Py_UNICODE buffer.
If the wchar_t/Py_UNICODE representation is not yet available, this
function will calculate it. */
#ifndef Py_LIMITED_API
PyAPI_FUNC(Py_UNICODE *) PyUnicode_AsUnicode(
PyObject *unicode /* Unicode object */
);
#endif
/* Return a read-only pointer to the Unicode object's internal
Py_UNICODE buffer and save the length at size.
If the wchar_t/Py_UNICODE representation is not yet available, this
function will calculate it. */
#ifndef Py_LIMITED_API
PyAPI_FUNC(Py_UNICODE *) PyUnicode_AsUnicodeAndSize(
PyObject *unicode, /* Unicode object */
Py_ssize_t *size /* location where to save the length */
);
#endif
/* Get the length of the Unicode object. */
PyAPI_FUNC(Py_ssize_t) PyUnicode_GetLength(
PyObject *unicode
);
/* Get the number of Py_UNICODE units in the
string representation. */
PyAPI_FUNC(Py_ssize_t) PyUnicode_GetSize(
PyObject *unicode /* Unicode object */
);
/* Read a character from the string. */
PyAPI_FUNC(Py_UCS4) PyUnicode_ReadChar(
PyObject *unicode,
Py_ssize_t index
);
/* Write a character to the string. The string must have been created through
PyUnicode_New, must not be shared, and must not have been hashed yet.
Return 0 on success, -1 on error. */
PyAPI_FUNC(int) PyUnicode_WriteChar(
PyObject *unicode,
Py_ssize_t index,
Py_UCS4 character
);
#ifndef Py_LIMITED_API
/* Get the maximum ordinal for a Unicode character. */
PyAPI_FUNC(Py_UNICODE) PyUnicode_GetMax(void);
#endif
/* Resize an Unicode object. The length is the number of characters, except
if the kind of the string is PyUnicode_WCHAR_KIND: in this case, the length
is the number of Py_UNICODE characters.
*unicode is modified to point to the new (resized) object and 0
returned on success.
Try to resize the string in place (which is usually faster than allocating
a new string and copy characters), or create a new string.
Error handling is implemented as follows: an exception is set, -1
is returned and *unicode left untouched.
WARNING: The function doesn't check string content, the result may not be a
string in canonical representation. */
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. bytes, bytearray and other char buffer compatible objects are decoded
under the assumptions that they contain data using the UTF-8
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 UTF-8 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 *format, /* ASCII-encoded string */
va_list vargs
);
PyAPI_FUNC(PyObject *) PyUnicode_FromFormat(
const char *format, /* ASCII-encoded string */
...
);
#ifndef Py_LIMITED_API
/* Format the object based on the format_spec, as defined in PEP 3101
(Advanced String Formatting). */
PyAPI_FUNC(PyObject *) _PyUnicode_FormatAdvanced(PyObject *obj,
PyObject *format_spec,
Py_ssize_t start,
Py_ssize_t end);
#endif
PyAPI_FUNC(void) PyUnicode_InternInPlace(PyObject **);
PyAPI_FUNC(void) PyUnicode_InternImmortal(PyObject **);
PyAPI_FUNC(PyObject *) PyUnicode_InternFromString(
const char *u /* UTF-8 encoded string */
);
#ifndef Py_LIMITED_API
PyAPI_FUNC(void) _Py_ReleaseInternedUnicodeStrings(void);
#endif
/* Use only if you know it's a string */
#define PyUnicode_CHECK_INTERNED(op) \
(((PyASCIIObject *)(op))->state.interned)
/* --- wchar_t support for platforms which support it --------------------- */
#ifdef HAVE_WCHAR_H
/* Create a Unicode Object from the wchar_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(
PyObject *unicode, /* Unicode object */
register wchar_t *w, /* wchar_t buffer */
Py_ssize_t size /* size of buffer */
);
/* Convert the Unicode object to a wide character string. The output string
always ends with a nul character. If size is not NULL, write the number of
wide characters (excluding the null character) into *size.
Returns a buffer allocated by PyMem_Alloc() (use PyMem_Free() to free it)
on success. On error, returns NULL, *size is undefined and raises a
MemoryError. */
PyAPI_FUNC(wchar_t*) PyUnicode_AsWideCharString(
PyObject *unicode, /* Unicode object */
Py_ssize_t *size /* number of characters of the result */
);
#ifndef Py_LIMITED_API
PyAPI_FUNC(void*) _PyUnicode_AsKind(PyObject *s, unsigned int kind);
#endif
#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 str() API.
Setting encoding to NULL causes the default encoding (UTF-8) 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 ---------------------------------------- */
/* Returns a pointer to the default encoding (UTF-8) of the
Unicode object unicode and the size of the encoded representation
in bytes stored in *size.
In case of an error, no *size is set.
This function caches the UTF-8 encoded string in the unicodeobject
and subsequent calls will return the same string. The memory is released
when the unicodeobject is deallocated.
_PyUnicode_AsStringAndSize is a #define for PyUnicode_AsUTF8AndSize to
support the previous internal function with the same behaviour.
*** This API is for interpreter INTERNAL USE ONLY and will likely
*** be removed or changed in the future.
*** If you need to access the Unicode object as UTF-8 bytes string,
*** please use PyUnicode_AsUTF8String() instead.
*/
#ifndef Py_LIMITED_API
PyAPI_FUNC(char *) PyUnicode_AsUTF8AndSize(
PyObject *unicode,
Py_ssize_t *size);
#define _PyUnicode_AsStringAndSize PyUnicode_AsUTF8AndSize
#endif