summaryrefslogtreecommitdiffstats
path: root/Include/unicodeobject.h
blob: 37f2b0d3f479a86281e4f32ce88d8d65c9164bc8 (plain)
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
#ifndef Py_UNICODEOBJECT_H
#define Py_UNICODEOBJECT_H
#ifdef __cplusplus
extern "C" {
#endif

/*

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).

(c) Copyright CNRI, All Rights Reserved. NO WARRANTY.


 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 -------------------------------------------- */

/* 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 HAVE_USABLE_WCHAR_T

/* Windows has a usable wchar_t type */
# if defined(MS_WIN32)
#  define HAVE_USABLE_WCHAR_T
# 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
# define HAVE_WCHAR_H
#endif

#ifdef HAVE_WCHAR_H
# include "wchar.h"
#endif

#ifdef HAVE_USABLE_WCHAR_T

/* If the compiler defines whcar_t as a 16-bit unsigned type we can
   use the compiler type directly.  Works fine with all modern Windows
   platforms. */

typedef wchar_t Py_UNICODE;

#else

/* Use if you have a standard ANSI compiler, without wchar_t support.
   If a short is not 16 bits on your platform, you have to fix the
   typedef below, or the module initialization code will complain. */

typedef unsigned short Py_UNICODE;

#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.
   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)

#else

#define Py_UNICODE_ISSPACE(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)

#endif

#define Py_UNICODE_COPY(target, source, length)\
    (memcpy((target), (source), (length)*sizeof(Py_UNICODE)))

#define Py_UNICODE_FILL(target, value, length) do\
    {int i; for (i = 0; i < (length); i++) (target)[i] = (value);}\
    while (0)

#define Py_UNICODE_MATCH(string, offset, substring)\
    (!memcmp((string)->str + (offset), (substring)->str,\
             (substring)->length*sizeof(Py_UNICODE)))

/* --- Unicode Type ------------------------------------------------------- */

typedef struct {
    PyObject_HEAD
    int length;			/* Length of raw Unicode data in buffer */
    Py_UNICODE *str;		/* Raw Unicode buffer */
    long hash;			/* Hash value; -1 if not set */
    PyObject *utf8str;		/* UTF-8 encoded version as Python string,
				   or NULL */
} PyUnicodeObject;

extern DL_IMPORT(PyTypeObject) PyUnicode_Type;

#define PyUnicode_Check(op) (((op)->ob_type == &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.

   The buffer is copied into the new object. */

extern DL_IMPORT(PyObject*) PyUnicode_FromUnicode(
    const Py_UNICODE *u,        /* Unicode buffer */
    int size                    /* size of buffer */
    );

/* Return a read-only pointer to the Unicode object's internal
   Py_UNICODE buffer. */

extern DL_IMPORT(Py_UNICODE *) PyUnicode_AsUnicode(
    PyObject *unicode	 	/* Unicode object */
    );

/* Get the length of the Unicode object. */

extern DL_IMPORT(int) PyUnicode_GetSize(
    PyObject *unicode	 	/* Unicode object */
    );

/* Coerce obj to an Unicode object and return a reference with
   *incremented* refcount.

   Coercion is done in the following way:

   1. Unicode objects are passed back as-is with incremented
      refcount.

   2. String and other char buffer compatible objects are decoded
      under the assumptions that they contain UTF-8 data. Decoding
      is done in "strict" mode.

   3. All other objects raise an exception.

   The API returns NULL in case of an error. The caller is responsible
   for decref'ing the returned objects.

*/

extern DL_IMPORT(PyObject*) PyUnicode_FromObject(
    register PyObject *obj 	/* Object */
    );

/* --- 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. */

extern DL_IMPORT(PyObject*) PyUnicode_FromWideChar(
    register const wchar_t *w,  /* wchar_t buffer */
    int size                    /* size of buffer */
    );

/* Copies the Unicode Object contents into the whcar_t buffer w.  At
   most size wchar_t characters are copied.

   Returns the number of wchar_t characters copied or -1 in case of an
   error. */

extern DL_IMPORT(int) PyUnicode_AsWideChar(
    PyUnicodeObject *unicode,   /* Unicode object */
    register wchar_t *w,        /* wchar_t buffer */
    int size                    /* size of buffer */
    );

#endif

/* === 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
   which is UTF-8.

   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.

*/

/* --- Generic Codecs ----------------------------------------------------- */

/* Create a Unicode object by decoding the encoded string s of the
   given size. */

extern DL_IMPORT(PyObject*) PyUnicode_Decode(
    const char *s,              /* encoded string */
    int 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. */

extern DL_IMPORT(PyObject*) PyUnicode_Encode(
    const Py_UNICODE *s,        /* Unicode char buffer */
    int 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 string
   object. */

extern DL_IMPORT(PyObject*) PyUnicode_AsEncodedString(
    PyObject *unicode,	 	/* Unicode object */
    const char *encoding,	/* encoding */
    const char *errors		/* error handling */
    );

/* --- UTF-8 Codecs ------------------------------------------------------- */

extern DL_IMPORT(PyObject*) PyUnicode_DecodeUTF8(
    const char *string, 	/* UTF-8 encoded string */
    int length,	 		/* size of string */
    const char *errors		/* error handling */
    );

extern DL_IMPORT(PyObject*) PyUnicode_AsUTF8String(
    PyObject *unicode	 	/* Unicode object */
    );

extern DL_IMPORT(PyObject*) PyUnicode_EncodeUTF8(
    const Py_UNICODE *data, 	/* Unicode char buffer */
    int length,	 		/* number of Py_UNICODE chars to encode */
    const char *errors		/* error handling */
    );

/* --- UTF-16 Codecs ------------------------------------------------------ */

/* Decodes length bytes from a UTF-16 encoded buffer string and return
   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

   and then switches according to all BOM marks it finds in the input
   data. BOM marks are not copied into the resulting Unicode string.
   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.

*/

extern DL_IMPORT(PyObject*) PyUnicode_DecodeUTF16(
    const char *string, 	/* UTF-16 encoded string */
    int 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 */
    );

/* Returns a Python string using the UTF-16 encoding in native byte
   order. The string always starts with a BOM mark.  */

extern DL_IMPORT(PyObject*) PyUnicode_AsUTF16String(
    PyObject *unicode	 	/* Unicode object */
    );

/* Returns a Python string object holding the UTF-16 encoded value of
   the Unicode data in s.

   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 comprimising the APIs.

*/

extern DL_IMPORT(PyObject*) PyUnicode_EncodeUTF16(
    const Py_UNICODE *data, 	/* Unicode char buffer */
    int 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 ---------------------------------------------- */

extern DL_IMPORT(PyObject*) PyUnicode_DecodeUnicodeEscape(
    const char *string, 	/* Unicode-Escape encoded string */
    int length,	 		/* size of string */
    const char *errors		/* error handling */
    );

extern DL_IMPORT(PyObject*) PyUnicode_AsUnicodeEscapeString(
    PyObject *unicode	 	/* Unicode object */
    );

extern DL_IMPORT(PyObject*) PyUnicode_EncodeUnicodeEscape(
    const Py_UNICODE *data, 	/* Unicode char buffer */
    int length	 		/* Number of Py_UNICODE chars to encode */
    );

/* --- Raw-Unicode-Escape Codecs ------------------------------------------ */

extern DL_IMPORT(PyObject*) PyUnicode_DecodeRawUnicodeEscape(
    const char *string, 	/* Raw-Unicode-Escape encoded string */
    int length,	 		/* size of string */
    const char *errors		/* error handling */
    );

extern DL_IMPORT(PyObject*) PyUnicode_AsRawUnicodeEscapeString(
    PyObject *unicode	 	/* Unicode object */
    );

extern DL_IMPORT(PyObject*) PyUnicode_EncodeRawUnicodeEscape(
    const Py_UNICODE *data, 	/* Unicode char buffer */
    int length	 		/* Number of Py_UNICODE chars to encode */
    );

/* --- Latin-1 Codecs ----------------------------------------------------- 

   Note: Latin-1 corresponds to the first 256 Unicode ordinals.

*/

extern DL_IMPORT(PyObject*) PyUnicode_DecodeLatin1(
    const char *string, 	/* Latin-1 encoded string */
    int length,	 		/* size of string */
    const char *errors		/* error handling */
    );

extern DL_IMPORT(PyObject*) PyUnicode_AsLatin1String(
    PyObject *unicode	 	/* Unicode object */
    );

extern DL_IMPORT(PyObject*) PyUnicode_EncodeLatin1(
    const Py_UNICODE *data, 	/* Unicode char buffer */
    int 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.

*/

extern DL_IMPORT(PyObject*) PyUnicode_DecodeASCII(
    const char *string, 	/* ASCII encoded string */
    int length,	 		/* size of string */
    const char *errors		/* error handling */
    );

extern DL_IMPORT(PyObject*) PyUnicode_AsASCIIString(
    PyObject *unicode	 	/* Unicode object */
    );

extern DL_IMPORT(PyObject*) PyUnicode_EncodeASCII(
    const Py_UNICODE *data, 	/* Unicode char buffer */
    int length,	 		/* Number of Py_UNICODE chars to encode */
    const char *errors		/* error handling */
    );

/* --- Character Map Codecs ----------------------------------------------- 

   This codec uses mappings to encode and decode characters. 

   Decoding mappings must map single string characters to single
   Unicode characters, integers (which are then interpreted as Unicode
   ordinals) or None (meaning "undefined mapping" and causing an
   error).

   Encoding mappings must map single Unicode characters to single
   string characters, integers (which are then interpreted as Latin-1
   ordinals) or None (meaning "undefined mapping" and causing an
   error).

   If a character lookup fails with a LookupError, the character is
   copied as-is meaning that its ordinal value will be interpreted as
   Unicode or Latin-1 ordinal resp. Because of this mappings only need
   to contain those mappings which map characters to different code
   points.

*/

extern DL_IMPORT(PyObject*) PyUnicode_DecodeCharmap(
    const char *string, 	/* Encoded string */
    int length,	 		/* size of string */
    PyObject *mapping,		/* character mapping 
				   (char ordinal -> unicode ordinal) */
    const char *errors		/* error handling */
    );

extern DL_IMPORT(PyObject*) PyUnicode_AsCharmapString(
    PyObject *unicode,	 	/* Unicode object */
    PyObject *mapping		/* character mapping 
				   (unicode ordinal -> char ordinal) */
    );

extern DL_IMPORT(PyObject*) PyUnicode_EncodeCharmap(
    const Py_UNICODE *data, 	/* Unicode char buffer */
    int length,	 		/* Number of Py_UNICODE chars to encode */
    PyObject *mapping,		/* character mapping 
				   (unicode ordinal -> char ordinal) */
    const char *errors		/* error handling */
    );

/* Translate a Py_UNICODE buffer of the given length by applying a
   character mapping table to it and return the resulting Unicode
   object.

   The mapping table must map Unicode ordinal integers to Unicode
   ordinal integers or None (causing deletion of the character). 

   Mapping tables may be dictionaries or sequences. Unmapped character
   ordinals (ones which cause a LookupError) are left untouched and
   are copied as-is.

*/

extern DL_IMPORT(PyObject *) PyUnicode_TranslateCharmap(
    const Py_UNICODE *data, 	/* Unicode char buffer */
    int length,	 		/* Number of Py_UNICODE chars to encode */
    PyObject *table,		/* Translate table */
    const char *errors		/* error handling */
    );

/* --- Methods & Slots ----------------------------------------------------

   These are capable of handling Unicode objects and strings on input
   (we refer to them as strings in the descriptions) and return
   Unicode objects or integers as apporpriate. */

/* Concat two strings giving a new Unicode string. */

extern DL_IMPORT(PyObject*) PyUnicode_Concat(
    PyObject *left,	 	/* Left string */
    PyObject *right	 	/* Right string */
    );

/* Split a string giving a list of Unicode strings.

   If sep is NULL, splitting will be done at all whitespace
   substrings. Otherwise, splits occur at the given separator.

   At most maxsplit splits will be done. If negative, no limit is set.

   Separators are not included in the resulting list.

*/

extern DL_IMPORT(PyObject*) PyUnicode_Split(
    PyObject *s,		/* String to split */
    PyObject *sep,		/* String separator */
    int maxsplit		/* Maxsplit count */
    );		

/* Dito, but split at line breaks.

   CRLF is considered to be one line break. Line breaks are not
   included in the resulting list. */
    
extern DL_IMPORT(PyObject*) PyUnicode_Splitlines(
    PyObject *s,		/* String to split */
    int maxsplit		/* Maxsplit count */
    );		

/* Translate a string by applying a character mapping table to it and
   return the resulting Unicode object.

   The mapping table must map Unicode ordinal integers to Unicode
   ordinal integers or None (causing deletion of the character). 

   Mapping tables may be dictionaries or sequences. Unmapped character
   ordinals (ones which cause a LookupError) are left untouched and
   are copied as-is.

*/

extern DL_IMPORT(PyObject *) PyUnicode_Translate(
    PyObject *str,		/* String */ 
    PyObject *table,		/* Translate table */
    const char *errors		/* error handling */
    );

/* Join a sequence of strings using the given separator and return
   the resulting Unicode string. */
    
extern DL_IMPORT(PyObject*) PyUnicode_Join(
    PyObject *separator, 	/* Separator string */
    PyObject *seq	 	/* Sequence object */
    );

/* Return 1 if substr matches str[start:end] at the given tail end, 0
   otherwise. */

extern DL_IMPORT(int) PyUnicode_Tailmatch(
    PyObject *str,		/* String */ 
    PyObject *substr,		/* Prefix or Suffix string */
    int start,			/* Start index */
    int end,			/* Stop index */
    int direction		/* Tail end: -1 prefix, +1 suffix */
    );

/* Return the first position of substr in str[start:end] using the
   given search direction or -1 if not found. */

extern DL_IMPORT(int) PyUnicode_Find(
    PyObject *str,		/* String */ 
    PyObject *substr,		/* Substring to find */
    int start,			/* Start index */
    int end,			/* Stop index */
    int direction		/* Find direction: +1 forward, -1 backward */
    );

/* Count the number of occurances of substr in str[start:end]. */

extern DL_IMPORT(int) PyUnicode_Count(
    PyObject *str,		/* String */ 
    PyObject *substr,		/* Substring to count */
    int start,			/* Start index */
    int end			/* Stop index */
    );

/* Replace at most maxcount occurances of substr in str with replstr
   and return the resulting Unicode object. */

extern DL_IMPORT(PyObject *) PyUnicode_Replace(
    PyObject *str,		/* String */ 
    PyObject *substr,		/* Substring to find */
    PyObject *replstr,		/* Substring to replace */
    int maxcount		/* Max. number of replacements to apply;
				   -1 = all */
    );

/* Compare two strings and return -1, 0, 1 for less than, equal,
   greater than resp. */

extern DL_IMPORT(int) PyUnicode_Compare(
    PyObject *left,		/* Left string */ 
    PyObject *right		/* Right string */
    );

/* Apply a argument tuple or dictionar to a format string and return
   the resulting Unicode string. */

extern DL_IMPORT(PyObject *) PyUnicode_Format(
    PyObject *format,		/* Format string */ 
    PyObject *args		/* Argument tuple or dictionary */
    );

/* Checks whether element is contained in container and return 1/0
   accordingly.

   element has to coerce to an one element Unicode string. -1 is
   returned in case of an error. */

extern DL_IMPORT(int) PyUnicode_Contains(
    PyObject *container,	/* Container string */ 
    PyObject *element		/* Element string */
    );

/* === Characters Type APIs =============================================== */

/* These should not be used directly. Use the Py_UNICODE_IS* and
   Py_UNICODE_TO* macros instead. 

   These APIs are implemented in Objects/unicodectype.c.

*/

extern DL_IMPORT(int) _PyUnicode_IsLowercase(
    register const Py_UNICODE ch 	/* Unicode character */
    );

extern DL_IMPORT(int) _PyUnicode_IsUppercase(
    register const Py_UNICODE ch 	/* Unicode character */
    );

extern DL_IMPORT(int) _PyUnicode_IsTitlecase(
    register const Py_UNICODE ch 	/* Unicode character */
    );

extern DL_IMPORT(int) _PyUnicode_IsWhitespace(
    register const Py_UNICODE ch 	/* Unicode character */
    );

extern DL_IMPORT(int) _PyUnicode_IsLinebreak(
    register const Py_UNICODE ch 	/* Unicode character */
    );

extern DL_IMPORT(Py_UNICODE) _PyUnicode_ToLowercase(
    register const Py_UNICODE ch 	/* Unicode character */
    );

extern DL_IMPORT(Py_UNICODE) _PyUnicode_ToUppercase(
    register const Py_UNICODE ch 	/* Unicode character */
    );

extern DL_IMPORT(Py_UNICODE) _PyUnicode_ToTitlecase(
    register const Py_UNICODE ch 	/* Unicode character */
    );

extern DL_IMPORT(int) _PyUnicode_ToDecimalDigit(
    register const Py_UNICODE ch 	/* Unicode character */
    );

extern DL_IMPORT(int) _PyUnicode_ToDigit(
    register const Py_UNICODE ch 	/* Unicode character */
    );

extern DL_IMPORT(double) _PyUnicode_ToNumeric(
    register const Py_UNICODE ch 	/* Unicode character */
    );

extern DL_IMPORT(int) _PyUnicode_IsDecimalDigit(
    register const Py_UNICODE ch 	/* Unicode character */
    );

extern DL_IMPORT(int) _PyUnicode_IsDigit(
    register const Py_UNICODE ch 	/* Unicode character */
    );

extern DL_IMPORT(int) _PyUnicode_IsNumeric(
    register const Py_UNICODE ch 	/* Unicode character */
    );

#ifdef __cplusplus
}
#endif
#endif /* !Py_UNICODEOBJECT_H */