blob: 9012257fdd8af7f069680b96d659732e2d5c970a [file] [log] [blame]
Guido van Rossumd8225182000-03-10 22:33:05 +00001#ifndef Py_UNICODEOBJECT_H
2#define Py_UNICODEOBJECT_H
Guido van Rossumd8225182000-03-10 22:33:05 +00003
4/*
5
6Unicode implementation based on original code by Fredrik Lundh,
7modified by Marc-Andre Lemburg (mal@lemburg.com) according to the
8Unicode Integration Proposal (see file Misc/unicode.txt).
9
Guido van Rossum16b1ad92000-08-03 16:24:25 +000010Copyright (c) Corporation for National Research Initiatives.
Guido van Rossumd8225182000-03-10 22:33:05 +000011
12
13 Original header:
14 --------------------------------------------------------------------
15
16 * Yet another Unicode string type for Python. This type supports the
17 * 16-bit Basic Multilingual Plane (BMP) only.
18 *
19 * Written by Fredrik Lundh, January 1999.
20 *
21 * Copyright (c) 1999 by Secret Labs AB.
22 * Copyright (c) 1999 by Fredrik Lundh.
23 *
24 * fredrik@pythonware.com
25 * http://www.pythonware.com
26 *
27 * --------------------------------------------------------------------
28 * This Unicode String Type is
29 *
30 * Copyright (c) 1999 by Secret Labs AB
31 * Copyright (c) 1999 by Fredrik Lundh
32 *
33 * By obtaining, using, and/or copying this software and/or its
34 * associated documentation, you agree that you have read, understood,
35 * and will comply with the following terms and conditions:
36 *
37 * Permission to use, copy, modify, and distribute this software and its
38 * associated documentation for any purpose and without fee is hereby
39 * granted, provided that the above copyright notice appears in all
40 * copies, and that both that copyright notice and this permission notice
41 * appear in supporting documentation, and that the name of Secret Labs
42 * AB or the author not be used in advertising or publicity pertaining to
43 * distribution of the software without specific, written prior
44 * permission.
45 *
46 * SECRET LABS AB AND THE AUTHOR DISCLAIMS ALL WARRANTIES WITH REGARD TO
47 * THIS SOFTWARE, INCLUDING ALL IMPLIED WARRANTIES OF MERCHANTABILITY AND
48 * FITNESS. IN NO EVENT SHALL SECRET LABS AB OR THE AUTHOR BE LIABLE FOR
49 * ANY SPECIAL, INDIRECT OR CONSEQUENTIAL DAMAGES OR ANY DAMAGES
50 * WHATSOEVER RESULTING FROM LOSS OF USE, DATA OR PROFITS, WHETHER IN AN
51 * ACTION OF CONTRACT, NEGLIGENCE OR OTHER TORTIOUS ACTION, ARISING OUT
52 * OF OR IN CONNECTION WITH THE USE OR PERFORMANCE OF THIS SOFTWARE.
53 * -------------------------------------------------------------------- */
54
Marc-André Lemburg5e6007c2001-09-19 11:21:03 +000055#include <ctype.h>
Guido van Rossumd8225182000-03-10 22:33:05 +000056
57/* === Internal API ======================================================= */
58
59/* --- Internal Unicode Format -------------------------------------------- */
60
Martin v. Löwis339d0f72001-08-17 18:39:25 +000061#ifndef Py_USING_UNICODE
62
63#define PyUnicode_Check(op) 0
Tim Peters78e0fc72001-09-11 03:07:38 +000064#define PyUnicode_CheckExact(op) 0
Martin v. Löwis339d0f72001-08-17 18:39:25 +000065
66#else
67
Fredrik Lundh9b14ab32001-06-26 22:59:49 +000068/* FIXME: MvL's new implementation assumes that Py_UNICODE_SIZE is
69 properly set, but the default rules below doesn't set it. I'll
70 sort this out some other day -- fredrik@pythonware.com */
71
72#ifndef Py_UNICODE_SIZE
73#error Must define Py_UNICODE_SIZE
74#endif
75
Fredrik Lundh8f455852001-06-27 18:59:43 +000076/* Setting Py_UNICODE_WIDE enables UCS-4 storage. Otherwise, Unicode
77 strings are stored as UCS-2 (with limited support for UTF-16) */
78
79#if Py_UNICODE_SIZE >= 4
80#define Py_UNICODE_WIDE
Martin v. Löwis0ba70cc2001-06-26 22:22:37 +000081#endif
Fredrik Lundh1294ad02001-06-26 17:17:07 +000082
Guido van Rossumd8225182000-03-10 22:33:05 +000083/* Set these flags if the platform has "wchar.h", "wctype.h" and the
84 wchar_t type is a 16-bit unsigned type */
85/* #define HAVE_WCHAR_H */
86/* #define HAVE_USABLE_WCHAR_T */
87
88/* Defaults for various platforms */
Martin v. Löwis0ba70cc2001-06-26 22:22:37 +000089#ifndef PY_UNICODE_TYPE
Guido van Rossumd8225182000-03-10 22:33:05 +000090
Fredrik Lundh1294ad02001-06-26 17:17:07 +000091/* Windows has a usable wchar_t type (unless we're using UCS-4) */
Fredrik Lundh8f455852001-06-27 18:59:43 +000092# if defined(MS_WIN32) && Py_UNICODE_SIZE == 2
Guido van Rossumd8225182000-03-10 22:33:05 +000093# define HAVE_USABLE_WCHAR_T
Martin v. Löwis0ba70cc2001-06-26 22:22:37 +000094# define PY_UNICODE_TYPE wchar_t
95# endif
96
Fredrik Lundh8f455852001-06-27 18:59:43 +000097# if defined(Py_UNICODE_WIDE)
Martin v. Löwis0ba70cc2001-06-26 22:22:37 +000098# define PY_UNICODE_TYPE Py_UCS4
Guido van Rossumd8225182000-03-10 22:33:05 +000099# endif
100
101#endif
102
103/* If the compiler provides a wchar_t type we try to support it
104 through the interface functions PyUnicode_FromWideChar() and
105 PyUnicode_AsWideChar(). */
106
107#ifdef HAVE_USABLE_WCHAR_T
Marc-André Lemburg1a731c62000-08-11 11:43:10 +0000108# ifndef HAVE_WCHAR_H
109# define HAVE_WCHAR_H
110# endif
Guido van Rossumd8225182000-03-10 22:33:05 +0000111#endif
112
113#ifdef HAVE_WCHAR_H
Guido van Rossum24bdb042000-03-28 20:29:59 +0000114/* Work around a cosmetic bug in BSDI 4.x wchar.h; thanks to Thomas Wouters */
115# ifdef _HAVE_BSDI
116# include <time.h>
117# endif
Marc-André Lemburg5e6007c2001-09-19 11:21:03 +0000118# include <wchar.h>
Guido van Rossumd8225182000-03-10 22:33:05 +0000119#endif
120
Martin v. Löwis0ba70cc2001-06-26 22:22:37 +0000121/*
122 * Use this typedef when you need to represent a UTF-16 surrogate pair
123 * as single unsigned integer.
124 */
125#if SIZEOF_INT >= 4
126typedef unsigned int Py_UCS4;
127#elif SIZEOF_LONG >= 4
128typedef unsigned long Py_UCS4;
Guido van Rossumd8225182000-03-10 22:33:05 +0000129#endif
130
Martin v. Löwis0ba70cc2001-06-26 22:22:37 +0000131typedef PY_UNICODE_TYPE Py_UNICODE;
Marc-André Lemburg43279102000-07-07 09:01:41 +0000132
Marc-André Lemburgb5ac6f62001-07-31 14:30:16 +0000133/* --- UCS-2/UCS-4 Name Mangling ------------------------------------------ */
134
135/* Unicode API names are mangled to assure that UCS-2 and UCS-4 builds
136 produce different external names and thus cause import errors in
137 case Python interpreters and extensions with mixed compiled in
138 Unicode width assumptions are combined. */
139
140#ifndef Py_UNICODE_WIDE
141
142# define PyUnicode_AsASCIIString PyUnicodeUCS2_AsASCIIString
143# define PyUnicode_AsCharmapString PyUnicodeUCS2_AsCharmapString
Marc-André Lemburgd2d45982004-07-08 17:57:32 +0000144# define PyUnicode_AsEncodedObject PyUnicodeUCS2_AsEncodedObject
Marc-André Lemburgb5ac6f62001-07-31 14:30:16 +0000145# define PyUnicode_AsEncodedString PyUnicodeUCS2_AsEncodedString
146# define PyUnicode_AsLatin1String PyUnicodeUCS2_AsLatin1String
147# define PyUnicode_AsRawUnicodeEscapeString PyUnicodeUCS2_AsRawUnicodeEscapeString
148# define PyUnicode_AsUTF16String PyUnicodeUCS2_AsUTF16String
149# define PyUnicode_AsUTF8String PyUnicodeUCS2_AsUTF8String
150# define PyUnicode_AsUnicode PyUnicodeUCS2_AsUnicode
151# define PyUnicode_AsUnicodeEscapeString PyUnicodeUCS2_AsUnicodeEscapeString
152# define PyUnicode_AsWideChar PyUnicodeUCS2_AsWideChar
153# define PyUnicode_Compare PyUnicodeUCS2_Compare
154# define PyUnicode_Concat PyUnicodeUCS2_Concat
155# define PyUnicode_Contains PyUnicodeUCS2_Contains
156# define PyUnicode_Count PyUnicodeUCS2_Count
157# define PyUnicode_Decode PyUnicodeUCS2_Decode
158# define PyUnicode_DecodeASCII PyUnicodeUCS2_DecodeASCII
159# define PyUnicode_DecodeCharmap PyUnicodeUCS2_DecodeCharmap
160# define PyUnicode_DecodeLatin1 PyUnicodeUCS2_DecodeLatin1
161# define PyUnicode_DecodeRawUnicodeEscape PyUnicodeUCS2_DecodeRawUnicodeEscape
162# define PyUnicode_DecodeUTF16 PyUnicodeUCS2_DecodeUTF16
Walter Dörwald69652032004-09-07 20:24:22 +0000163# define PyUnicode_DecodeUTF16Stateful PyUnicodeUCS2_DecodeUTF16Stateful
Marc-André Lemburgb5ac6f62001-07-31 14:30:16 +0000164# define PyUnicode_DecodeUTF8 PyUnicodeUCS2_DecodeUTF8
Walter Dörwald69652032004-09-07 20:24:22 +0000165# define PyUnicode_DecodeUTF8Stateful PyUnicodeUCS2_DecodeUTF8Stateful
Marc-André Lemburgb5ac6f62001-07-31 14:30:16 +0000166# define PyUnicode_DecodeUnicodeEscape PyUnicodeUCS2_DecodeUnicodeEscape
167# define PyUnicode_Encode PyUnicodeUCS2_Encode
168# define PyUnicode_EncodeASCII PyUnicodeUCS2_EncodeASCII
169# define PyUnicode_EncodeCharmap PyUnicodeUCS2_EncodeCharmap
170# define PyUnicode_EncodeDecimal PyUnicodeUCS2_EncodeDecimal
171# define PyUnicode_EncodeLatin1 PyUnicodeUCS2_EncodeLatin1
172# define PyUnicode_EncodeRawUnicodeEscape PyUnicodeUCS2_EncodeRawUnicodeEscape
173# define PyUnicode_EncodeUTF16 PyUnicodeUCS2_EncodeUTF16
174# define PyUnicode_EncodeUTF8 PyUnicodeUCS2_EncodeUTF8
175# define PyUnicode_EncodeUnicodeEscape PyUnicodeUCS2_EncodeUnicodeEscape
176# define PyUnicode_Find PyUnicodeUCS2_Find
177# define PyUnicode_Format PyUnicodeUCS2_Format
178# define PyUnicode_FromEncodedObject PyUnicodeUCS2_FromEncodedObject
179# define PyUnicode_FromObject PyUnicodeUCS2_FromObject
Marc-André Lemburg9c329de2002-08-12 08:19:10 +0000180# define PyUnicode_FromOrdinal PyUnicodeUCS2_FromOrdinal
Marc-André Lemburgb5ac6f62001-07-31 14:30:16 +0000181# define PyUnicode_FromUnicode PyUnicodeUCS2_FromUnicode
182# define PyUnicode_FromWideChar PyUnicodeUCS2_FromWideChar
183# define PyUnicode_GetDefaultEncoding PyUnicodeUCS2_GetDefaultEncoding
184# define PyUnicode_GetMax PyUnicodeUCS2_GetMax
185# define PyUnicode_GetSize PyUnicodeUCS2_GetSize
186# define PyUnicode_Join PyUnicodeUCS2_Join
187# define PyUnicode_Replace PyUnicodeUCS2_Replace
188# define PyUnicode_Resize PyUnicodeUCS2_Resize
189# define PyUnicode_SetDefaultEncoding PyUnicodeUCS2_SetDefaultEncoding
190# define PyUnicode_Split PyUnicodeUCS2_Split
Hye-Shik Chang3ae811b2003-12-15 18:49:53 +0000191# define PyUnicode_RSplit PyUnicodeUCS2_RSplit
Marc-André Lemburgb5ac6f62001-07-31 14:30:16 +0000192# define PyUnicode_Splitlines PyUnicodeUCS2_Splitlines
193# define PyUnicode_Tailmatch PyUnicodeUCS2_Tailmatch
194# define PyUnicode_Translate PyUnicodeUCS2_Translate
195# define PyUnicode_TranslateCharmap PyUnicodeUCS2_TranslateCharmap
196# define _PyUnicode_AsDefaultEncodedString _PyUnicodeUCS2_AsDefaultEncodedString
197# define _PyUnicode_Fini _PyUnicodeUCS2_Fini
198# define _PyUnicode_Init _PyUnicodeUCS2_Init
199# define _PyUnicode_IsAlpha _PyUnicodeUCS2_IsAlpha
200# define _PyUnicode_IsDecimalDigit _PyUnicodeUCS2_IsDecimalDigit
201# define _PyUnicode_IsDigit _PyUnicodeUCS2_IsDigit
202# define _PyUnicode_IsLinebreak _PyUnicodeUCS2_IsLinebreak
203# define _PyUnicode_IsLowercase _PyUnicodeUCS2_IsLowercase
204# define _PyUnicode_IsNumeric _PyUnicodeUCS2_IsNumeric
205# define _PyUnicode_IsTitlecase _PyUnicodeUCS2_IsTitlecase
206# define _PyUnicode_IsUppercase _PyUnicodeUCS2_IsUppercase
207# define _PyUnicode_IsWhitespace _PyUnicodeUCS2_IsWhitespace
208# define _PyUnicode_ToDecimalDigit _PyUnicodeUCS2_ToDecimalDigit
209# define _PyUnicode_ToDigit _PyUnicodeUCS2_ToDigit
210# define _PyUnicode_ToLowercase _PyUnicodeUCS2_ToLowercase
211# define _PyUnicode_ToNumeric _PyUnicodeUCS2_ToNumeric
212# define _PyUnicode_ToTitlecase _PyUnicodeUCS2_ToTitlecase
213# define _PyUnicode_ToUppercase _PyUnicodeUCS2_ToUppercase
214
215#else
216
217# define PyUnicode_AsASCIIString PyUnicodeUCS4_AsASCIIString
218# define PyUnicode_AsCharmapString PyUnicodeUCS4_AsCharmapString
Marc-André Lemburgd2d45982004-07-08 17:57:32 +0000219# define PyUnicode_AsEncodedObject PyUnicodeUCS4_AsEncodedObject
Marc-André Lemburgb5ac6f62001-07-31 14:30:16 +0000220# define PyUnicode_AsEncodedString PyUnicodeUCS4_AsEncodedString
221# define PyUnicode_AsLatin1String PyUnicodeUCS4_AsLatin1String
222# define PyUnicode_AsRawUnicodeEscapeString PyUnicodeUCS4_AsRawUnicodeEscapeString
223# define PyUnicode_AsUTF16String PyUnicodeUCS4_AsUTF16String
224# define PyUnicode_AsUTF8String PyUnicodeUCS4_AsUTF8String
225# define PyUnicode_AsUnicode PyUnicodeUCS4_AsUnicode
226# define PyUnicode_AsUnicodeEscapeString PyUnicodeUCS4_AsUnicodeEscapeString
227# define PyUnicode_AsWideChar PyUnicodeUCS4_AsWideChar
228# define PyUnicode_Compare PyUnicodeUCS4_Compare
229# define PyUnicode_Concat PyUnicodeUCS4_Concat
230# define PyUnicode_Contains PyUnicodeUCS4_Contains
231# define PyUnicode_Count PyUnicodeUCS4_Count
232# define PyUnicode_Decode PyUnicodeUCS4_Decode
233# define PyUnicode_DecodeASCII PyUnicodeUCS4_DecodeASCII
234# define PyUnicode_DecodeCharmap PyUnicodeUCS4_DecodeCharmap
235# define PyUnicode_DecodeLatin1 PyUnicodeUCS4_DecodeLatin1
236# define PyUnicode_DecodeRawUnicodeEscape PyUnicodeUCS4_DecodeRawUnicodeEscape
237# define PyUnicode_DecodeUTF16 PyUnicodeUCS4_DecodeUTF16
Walter Dörwald69652032004-09-07 20:24:22 +0000238# define PyUnicode_DecodeUTF16Stateful PyUnicodeUCS4_DecodeUTF16Stateful
Marc-André Lemburgb5ac6f62001-07-31 14:30:16 +0000239# define PyUnicode_DecodeUTF8 PyUnicodeUCS4_DecodeUTF8
Walter Dörwald69652032004-09-07 20:24:22 +0000240# define PyUnicode_DecodeUTF8Stateful PyUnicodeUCS4_DecodeUTF8Stateful
Marc-André Lemburgb5ac6f62001-07-31 14:30:16 +0000241# define PyUnicode_DecodeUnicodeEscape PyUnicodeUCS4_DecodeUnicodeEscape
242# define PyUnicode_Encode PyUnicodeUCS4_Encode
243# define PyUnicode_EncodeASCII PyUnicodeUCS4_EncodeASCII
244# define PyUnicode_EncodeCharmap PyUnicodeUCS4_EncodeCharmap
245# define PyUnicode_EncodeDecimal PyUnicodeUCS4_EncodeDecimal
246# define PyUnicode_EncodeLatin1 PyUnicodeUCS4_EncodeLatin1
247# define PyUnicode_EncodeRawUnicodeEscape PyUnicodeUCS4_EncodeRawUnicodeEscape
248# define PyUnicode_EncodeUTF16 PyUnicodeUCS4_EncodeUTF16
249# define PyUnicode_EncodeUTF8 PyUnicodeUCS4_EncodeUTF8
250# define PyUnicode_EncodeUnicodeEscape PyUnicodeUCS4_EncodeUnicodeEscape
251# define PyUnicode_Find PyUnicodeUCS4_Find
252# define PyUnicode_Format PyUnicodeUCS4_Format
253# define PyUnicode_FromEncodedObject PyUnicodeUCS4_FromEncodedObject
254# define PyUnicode_FromObject PyUnicodeUCS4_FromObject
Marc-André Lemburg9c329de2002-08-12 08:19:10 +0000255# define PyUnicode_FromOrdinal PyUnicodeUCS4_FromOrdinal
Marc-André Lemburgb5ac6f62001-07-31 14:30:16 +0000256# define PyUnicode_FromUnicode PyUnicodeUCS4_FromUnicode
257# define PyUnicode_FromWideChar PyUnicodeUCS4_FromWideChar
258# define PyUnicode_GetDefaultEncoding PyUnicodeUCS4_GetDefaultEncoding
259# define PyUnicode_GetMax PyUnicodeUCS4_GetMax
260# define PyUnicode_GetSize PyUnicodeUCS4_GetSize
261# define PyUnicode_Join PyUnicodeUCS4_Join
262# define PyUnicode_Replace PyUnicodeUCS4_Replace
263# define PyUnicode_Resize PyUnicodeUCS4_Resize
264# define PyUnicode_SetDefaultEncoding PyUnicodeUCS4_SetDefaultEncoding
265# define PyUnicode_Split PyUnicodeUCS4_Split
266# define PyUnicode_Splitlines PyUnicodeUCS4_Splitlines
267# define PyUnicode_Tailmatch PyUnicodeUCS4_Tailmatch
268# define PyUnicode_Translate PyUnicodeUCS4_Translate
269# define PyUnicode_TranslateCharmap PyUnicodeUCS4_TranslateCharmap
270# define _PyUnicode_AsDefaultEncodedString _PyUnicodeUCS4_AsDefaultEncodedString
271# define _PyUnicode_Fini _PyUnicodeUCS4_Fini
272# define _PyUnicode_Init _PyUnicodeUCS4_Init
273# define _PyUnicode_IsAlpha _PyUnicodeUCS4_IsAlpha
274# define _PyUnicode_IsDecimalDigit _PyUnicodeUCS4_IsDecimalDigit
275# define _PyUnicode_IsDigit _PyUnicodeUCS4_IsDigit
276# define _PyUnicode_IsLinebreak _PyUnicodeUCS4_IsLinebreak
277# define _PyUnicode_IsLowercase _PyUnicodeUCS4_IsLowercase
278# define _PyUnicode_IsNumeric _PyUnicodeUCS4_IsNumeric
279# define _PyUnicode_IsTitlecase _PyUnicodeUCS4_IsTitlecase
280# define _PyUnicode_IsUppercase _PyUnicodeUCS4_IsUppercase
281# define _PyUnicode_IsWhitespace _PyUnicodeUCS4_IsWhitespace
282# define _PyUnicode_ToDecimalDigit _PyUnicodeUCS4_ToDecimalDigit
283# define _PyUnicode_ToDigit _PyUnicodeUCS4_ToDigit
284# define _PyUnicode_ToLowercase _PyUnicodeUCS4_ToLowercase
285# define _PyUnicode_ToNumeric _PyUnicodeUCS4_ToNumeric
286# define _PyUnicode_ToTitlecase _PyUnicodeUCS4_ToTitlecase
287# define _PyUnicode_ToUppercase _PyUnicodeUCS4_ToUppercase
288
289
290#endif
291
Guido van Rossumd8225182000-03-10 22:33:05 +0000292/* --- Internal Unicode Operations ---------------------------------------- */
293
294/* If you want Python to use the compiler's wctype.h functions instead
Barry Warsaw51ac5802000-03-20 16:36:48 +0000295 of the ones supplied with Python, define WANT_WCTYPE_FUNCTIONS or
Raymond Hettinger57341c32004-10-31 05:46:59 +0000296 configure Python using --with-wctype-functions. This reduces the
Barry Warsaw51ac5802000-03-20 16:36:48 +0000297 interpreter's code size. */
Guido van Rossumd8225182000-03-10 22:33:05 +0000298
299#if defined(HAVE_USABLE_WCHAR_T) && defined(WANT_WCTYPE_FUNCTIONS)
300
Marc-André Lemburg5e6007c2001-09-19 11:21:03 +0000301#include <wctype.h>
Guido van Rossumd8225182000-03-10 22:33:05 +0000302
303#define Py_UNICODE_ISSPACE(ch) iswspace(ch)
304
305#define Py_UNICODE_ISLOWER(ch) iswlower(ch)
306#define Py_UNICODE_ISUPPER(ch) iswupper(ch)
307#define Py_UNICODE_ISTITLE(ch) _PyUnicode_IsTitlecase(ch)
308#define Py_UNICODE_ISLINEBREAK(ch) _PyUnicode_IsLinebreak(ch)
309
310#define Py_UNICODE_TOLOWER(ch) towlower(ch)
311#define Py_UNICODE_TOUPPER(ch) towupper(ch)
312#define Py_UNICODE_TOTITLE(ch) _PyUnicode_ToTitlecase(ch)
313
314#define Py_UNICODE_ISDECIMAL(ch) _PyUnicode_IsDecimalDigit(ch)
315#define Py_UNICODE_ISDIGIT(ch) _PyUnicode_IsDigit(ch)
316#define Py_UNICODE_ISNUMERIC(ch) _PyUnicode_IsNumeric(ch)
317
318#define Py_UNICODE_TODECIMAL(ch) _PyUnicode_ToDecimalDigit(ch)
319#define Py_UNICODE_TODIGIT(ch) _PyUnicode_ToDigit(ch)
320#define Py_UNICODE_TONUMERIC(ch) _PyUnicode_ToNumeric(ch)
321
Marc-André Lemburgf03e7412000-07-05 09:45:59 +0000322#define Py_UNICODE_ISALPHA(ch) iswalpha(ch)
323
Guido van Rossumd8225182000-03-10 22:33:05 +0000324#else
325
326#define Py_UNICODE_ISSPACE(ch) _PyUnicode_IsWhitespace(ch)
327
328#define Py_UNICODE_ISLOWER(ch) _PyUnicode_IsLowercase(ch)
329#define Py_UNICODE_ISUPPER(ch) _PyUnicode_IsUppercase(ch)
330#define Py_UNICODE_ISTITLE(ch) _PyUnicode_IsTitlecase(ch)
331#define Py_UNICODE_ISLINEBREAK(ch) _PyUnicode_IsLinebreak(ch)
332
333#define Py_UNICODE_TOLOWER(ch) _PyUnicode_ToLowercase(ch)
334#define Py_UNICODE_TOUPPER(ch) _PyUnicode_ToUppercase(ch)
335#define Py_UNICODE_TOTITLE(ch) _PyUnicode_ToTitlecase(ch)
336
337#define Py_UNICODE_ISDECIMAL(ch) _PyUnicode_IsDecimalDigit(ch)
338#define Py_UNICODE_ISDIGIT(ch) _PyUnicode_IsDigit(ch)
339#define Py_UNICODE_ISNUMERIC(ch) _PyUnicode_IsNumeric(ch)
340
341#define Py_UNICODE_TODECIMAL(ch) _PyUnicode_ToDecimalDigit(ch)
342#define Py_UNICODE_TODIGIT(ch) _PyUnicode_ToDigit(ch)
343#define Py_UNICODE_TONUMERIC(ch) _PyUnicode_ToNumeric(ch)
344
Marc-André Lemburgf03e7412000-07-05 09:45:59 +0000345#define Py_UNICODE_ISALPHA(ch) _PyUnicode_IsAlpha(ch)
Guido van Rossumd8225182000-03-10 22:33:05 +0000346
Marc-André Lemburgf03e7412000-07-05 09:45:59 +0000347#endif
Marc-André Lemburga9c103b2000-07-03 10:52:13 +0000348
349#define Py_UNICODE_ISALNUM(ch) \
350 (Py_UNICODE_ISALPHA(ch) || \
351 Py_UNICODE_ISDECIMAL(ch) || \
352 Py_UNICODE_ISDIGIT(ch) || \
353 Py_UNICODE_ISNUMERIC(ch))
354
Guido van Rossumd8225182000-03-10 22:33:05 +0000355#define Py_UNICODE_COPY(target, source, length)\
356 (memcpy((target), (source), (length)*sizeof(Py_UNICODE)))
357
358#define Py_UNICODE_FILL(target, value, length) do\
359 {int i; for (i = 0; i < (length); i++) (target)[i] = (value);}\
360 while (0)
361
362#define Py_UNICODE_MATCH(string, offset, substring)\
Marc-André Lemburg2f4d0e92000-06-18 22:22:27 +0000363 ((*((string)->str + (offset)) == *((substring)->str)) &&\
364 !memcmp((string)->str + (offset), (substring)->str,\
Guido van Rossumd8225182000-03-10 22:33:05 +0000365 (substring)->length*sizeof(Py_UNICODE)))
366
Barry Warsaw51ac5802000-03-20 16:36:48 +0000367#ifdef __cplusplus
368extern "C" {
369#endif
370
Guido van Rossumd8225182000-03-10 22:33:05 +0000371/* --- Unicode Type ------------------------------------------------------- */
372
373typedef struct {
374 PyObject_HEAD
Martin v. Löwis18e16552006-02-15 17:27:45 +0000375 Py_ssize_t length; /* Length of raw Unicode data in buffer */
Guido van Rossumd8225182000-03-10 22:33:05 +0000376 Py_UNICODE *str; /* Raw Unicode buffer */
377 long hash; /* Hash value; -1 if not set */
Marc-André Lemburgbff879c2000-08-03 18:46:08 +0000378 PyObject *defenc; /* (Default) Encoded version as Python
379 string, or NULL; this is used for
380 implementing the buffer protocol */
Guido van Rossumd8225182000-03-10 22:33:05 +0000381} PyUnicodeObject;
382
Mark Hammond91a681d2002-08-12 07:21:58 +0000383PyAPI_DATA(PyTypeObject) PyUnicode_Type;
Guido van Rossumd8225182000-03-10 22:33:05 +0000384
Guido van Rossum5eef77a2001-08-30 03:08:07 +0000385#define PyUnicode_Check(op) PyObject_TypeCheck(op, &PyUnicode_Type)
Tim Peters78e0fc72001-09-11 03:07:38 +0000386#define PyUnicode_CheckExact(op) ((op)->ob_type == &PyUnicode_Type)
Guido van Rossumd8225182000-03-10 22:33:05 +0000387
388/* Fast access macros */
389#define PyUnicode_GET_SIZE(op) \
390 (((PyUnicodeObject *)(op))->length)
391#define PyUnicode_GET_DATA_SIZE(op) \
392 (((PyUnicodeObject *)(op))->length * sizeof(Py_UNICODE))
393#define PyUnicode_AS_UNICODE(op) \
394 (((PyUnicodeObject *)(op))->str)
395#define PyUnicode_AS_DATA(op) \
396 ((const char *)((PyUnicodeObject *)(op))->str)
397
398/* --- Constants ---------------------------------------------------------- */
399
400/* This Unicode character will be used as replacement character during
401 decoding if the errors argument is set to "replace". Note: the
402 Unicode character U+FFFD is the official REPLACEMENT CHARACTER in
403 Unicode 3.0. */
404
405#define Py_UNICODE_REPLACEMENT_CHARACTER ((Py_UNICODE) 0xFFFD)
406
407/* === Public API ========================================================= */
408
409/* --- Plain Py_UNICODE --------------------------------------------------- */
410
411/* Create a Unicode Object from the Py_UNICODE buffer u of the given
Marc-André Lemburg8155e0e2001-04-23 14:44:21 +0000412 size.
413
414 u may be NULL which causes the contents to be undefined. It is the
415 user's responsibility to fill in the needed data afterwards. Note
416 that modifying the Unicode object contents after construction is
417 only allowed if u was set to NULL.
Guido van Rossumd8225182000-03-10 22:33:05 +0000418
419 The buffer is copied into the new object. */
420
Mark Hammond91a681d2002-08-12 07:21:58 +0000421PyAPI_FUNC(PyObject*) PyUnicode_FromUnicode(
Guido van Rossumd8225182000-03-10 22:33:05 +0000422 const Py_UNICODE *u, /* Unicode buffer */
Martin v. Löwis18e16552006-02-15 17:27:45 +0000423 Py_ssize_t size /* size of buffer */
Guido van Rossumd8225182000-03-10 22:33:05 +0000424 );
425
426/* Return a read-only pointer to the Unicode object's internal
427 Py_UNICODE buffer. */
428
Mark Hammond91a681d2002-08-12 07:21:58 +0000429PyAPI_FUNC(Py_UNICODE *) PyUnicode_AsUnicode(
Guido van Rossumd8225182000-03-10 22:33:05 +0000430 PyObject *unicode /* Unicode object */
431 );
432
433/* Get the length of the Unicode object. */
434
Martin v. Löwis18e16552006-02-15 17:27:45 +0000435PyAPI_FUNC(Py_ssize_t) PyUnicode_GetSize(
Guido van Rossumd8225182000-03-10 22:33:05 +0000436 PyObject *unicode /* Unicode object */
437 );
438
Martin v. Löwisce9b5a52001-06-27 06:28:56 +0000439/* Get the maximum ordinal for a Unicode character. */
Mark Hammond91a681d2002-08-12 07:21:58 +0000440PyAPI_FUNC(Py_UNICODE) PyUnicode_GetMax(void);
Martin v. Löwisce9b5a52001-06-27 06:28:56 +0000441
Guido van Rossum52c23592000-04-10 13:41:41 +0000442/* Resize an already allocated Unicode object to the new size length.
443
444 *unicode is modified to point to the new (resized) object and 0
445 returned on success.
446
447 This API may only be called by the function which also called the
448 Unicode constructor. The refcount on the object must be 1. Otherwise,
449 an error is returned.
450
451 Error handling is implemented as follows: an exception is set, -1
452 is returned and *unicode left untouched.
453
454*/
455
Mark Hammond91a681d2002-08-12 07:21:58 +0000456PyAPI_FUNC(int) PyUnicode_Resize(
Guido van Rossum52c23592000-04-10 13:41:41 +0000457 PyObject **unicode, /* Pointer to the Unicode object */
Martin v. Löwis18e16552006-02-15 17:27:45 +0000458 Py_ssize_t length /* New length */
Guido van Rossum52c23592000-04-10 13:41:41 +0000459 );
460
Guido van Rossumd8225182000-03-10 22:33:05 +0000461/* Coerce obj to an Unicode object and return a reference with
462 *incremented* refcount.
463
464 Coercion is done in the following way:
465
Guido van Rossumb8c65bc2001-10-19 02:01:31 +0000466 1. String and other char buffer compatible objects are decoded
Fred Drakecb093fe2000-05-09 19:51:53 +0000467 under the assumptions that they contain data using the current
468 default encoding. Decoding is done in "strict" mode.
Guido van Rossumd8225182000-03-10 22:33:05 +0000469
Guido van Rossumb8c65bc2001-10-19 02:01:31 +0000470 2. All other objects (including Unicode objects) raise an
471 exception.
Guido van Rossumd8225182000-03-10 22:33:05 +0000472
473 The API returns NULL in case of an error. The caller is responsible
474 for decref'ing the returned objects.
475
476*/
477
Mark Hammond91a681d2002-08-12 07:21:58 +0000478PyAPI_FUNC(PyObject*) PyUnicode_FromEncodedObject(
Marc-André Lemburg5a5c81a2000-07-07 13:46:42 +0000479 register PyObject *obj, /* Object */
480 const char *encoding, /* encoding */
481 const char *errors /* error handling */
482 );
483
Guido van Rossumb8c65bc2001-10-19 02:01:31 +0000484/* Coerce obj to an Unicode object and return a reference with
Marc-André Lemburg5a5c81a2000-07-07 13:46:42 +0000485 *incremented* refcount.
Guido van Rossumb8c65bc2001-10-19 02:01:31 +0000486
487 Unicode objects are passed back as-is (subclasses are converted to
488 true Unicode objects), all other objects are delegated to
489 PyUnicode_FromEncodedObject(obj, NULL, "strict") which results in
490 using the default encoding as basis for decoding the object.
Marc-André Lemburg5a5c81a2000-07-07 13:46:42 +0000491
492 The API returns NULL in case of an error. The caller is responsible
493 for decref'ing the returned objects.
494
495*/
496
Mark Hammond91a681d2002-08-12 07:21:58 +0000497PyAPI_FUNC(PyObject*) PyUnicode_FromObject(
Guido van Rossumd8225182000-03-10 22:33:05 +0000498 register PyObject *obj /* Object */
499 );
500
501/* --- wchar_t support for platforms which support it --------------------- */
502
503#ifdef HAVE_WCHAR_H
504
505/* Create a Unicode Object from the whcar_t buffer w of the given
506 size.
507
508 The buffer is copied into the new object. */
509
Mark Hammond91a681d2002-08-12 07:21:58 +0000510PyAPI_FUNC(PyObject*) PyUnicode_FromWideChar(
Guido van Rossumd8225182000-03-10 22:33:05 +0000511 register const wchar_t *w, /* wchar_t buffer */
Martin v. Löwis18e16552006-02-15 17:27:45 +0000512 Py_ssize_t size /* size of buffer */
Guido van Rossumd8225182000-03-10 22:33:05 +0000513 );
514
Marc-André Lemburga9cadcd2004-11-22 13:02:31 +0000515/* Copies the Unicode Object contents into the wchar_t buffer w. At
Guido van Rossumd8225182000-03-10 22:33:05 +0000516 most size wchar_t characters are copied.
517
Marc-André Lemburga9cadcd2004-11-22 13:02:31 +0000518 Note that the resulting wchar_t string may or may not be
519 0-terminated. It is the responsibility of the caller to make sure
520 that the wchar_t string is 0-terminated in case this is required by
521 the application.
522
523 Returns the number of wchar_t characters copied (excluding a
524 possibly trailing 0-termination character) or -1 in case of an
Guido van Rossumd8225182000-03-10 22:33:05 +0000525 error. */
526
Martin v. Löwis18e16552006-02-15 17:27:45 +0000527PyAPI_FUNC(Py_ssize_t) PyUnicode_AsWideChar(
Guido van Rossumd8225182000-03-10 22:33:05 +0000528 PyUnicodeObject *unicode, /* Unicode object */
529 register wchar_t *w, /* wchar_t buffer */
Martin v. Löwis18e16552006-02-15 17:27:45 +0000530 Py_ssize_t size /* size of buffer */
Guido van Rossumd8225182000-03-10 22:33:05 +0000531 );
532
533#endif
534
Marc-André Lemburgcc8764c2002-08-11 12:23:04 +0000535/* --- Unicode ordinals --------------------------------------------------- */
536
537/* Create a Unicode Object from the given Unicode code point ordinal.
538
539 The ordinal must be in range(0x10000) on narrow Python builds
540 (UCS2), and range(0x110000) on wide builds (UCS4). A ValueError is
541 raised in case it is not.
542
543*/
544
Marc-André Lemburg9c329de2002-08-12 08:19:10 +0000545PyAPI_FUNC(PyObject*) PyUnicode_FromOrdinal(int ordinal);
Marc-André Lemburgcc8764c2002-08-11 12:23:04 +0000546
Guido van Rossumd8225182000-03-10 22:33:05 +0000547/* === Builtin Codecs =====================================================
548
549 Many of these APIs take two arguments encoding and errors. These
550 parameters encoding and errors have the same semantics as the ones
551 of the builtin unicode() API.
552
Fred Drakecb093fe2000-05-09 19:51:53 +0000553 Setting encoding to NULL causes the default encoding to be used.
Guido van Rossumd8225182000-03-10 22:33:05 +0000554
555 Error handling is set by errors which may also be set to NULL
556 meaning to use the default handling defined for the codec. Default
557 error handling for all builtin codecs is "strict" (ValueErrors are
558 raised).
559
560 The codecs all use a similar interface. Only deviation from the
561 generic ones are documented.
562
563*/
564
Fred Drakecb093fe2000-05-09 19:51:53 +0000565/* --- Manage the default encoding ---------------------------------------- */
566
Jeremy Hylton3ce45382001-07-30 22:34:24 +0000567/* Return a Python string holding the default encoded value of the
568 Unicode object.
569
570 The resulting string is cached in the Unicode object for subsequent
571 usage by this function. The cached version is needed to implement
572 the character buffer interface and will live (at least) as long as
573 the Unicode object itself.
574
575 The refcount of the string is *not* incremented.
576
577 *** Exported for internal use by the interpreter only !!! ***
578
579*/
580
Mark Hammond91a681d2002-08-12 07:21:58 +0000581PyAPI_FUNC(PyObject *) _PyUnicode_AsDefaultEncodedString(
Jeremy Hylton3ce45382001-07-30 22:34:24 +0000582 PyObject *, const char *);
583
Fred Drakecb093fe2000-05-09 19:51:53 +0000584/* Returns the currently active default encoding.
585
586 The default encoding is currently implemented as run-time settable
587 process global. This may change in future versions of the
588 interpreter to become a parameter which is managed on a per-thread
589 basis.
590
591 */
592
Mark Hammond91a681d2002-08-12 07:21:58 +0000593PyAPI_FUNC(const char*) PyUnicode_GetDefaultEncoding(void);
Fred Drakecb093fe2000-05-09 19:51:53 +0000594
595/* Sets the currently active default encoding.
596
597 Returns 0 on success, -1 in case of an error.
598
599 */
600
Mark Hammond91a681d2002-08-12 07:21:58 +0000601PyAPI_FUNC(int) PyUnicode_SetDefaultEncoding(
Fred Drakecb093fe2000-05-09 19:51:53 +0000602 const char *encoding /* Encoding name in standard form */
603 );
604
Guido van Rossumd8225182000-03-10 22:33:05 +0000605/* --- Generic Codecs ----------------------------------------------------- */
606
607/* Create a Unicode object by decoding the encoded string s of the
608 given size. */
609
Mark Hammond91a681d2002-08-12 07:21:58 +0000610PyAPI_FUNC(PyObject*) PyUnicode_Decode(
Guido van Rossumd8225182000-03-10 22:33:05 +0000611 const char *s, /* encoded string */
Martin v. Löwis18e16552006-02-15 17:27:45 +0000612 Py_ssize_t size, /* size of buffer */
Guido van Rossumd8225182000-03-10 22:33:05 +0000613 const char *encoding, /* encoding */
614 const char *errors /* error handling */
615 );
616
617/* Encodes a Py_UNICODE buffer of the given size and returns a
618 Python string object. */
619
Mark Hammond91a681d2002-08-12 07:21:58 +0000620PyAPI_FUNC(PyObject*) PyUnicode_Encode(
Guido van Rossumd8225182000-03-10 22:33:05 +0000621 const Py_UNICODE *s, /* Unicode char buffer */
Martin v. Löwis18e16552006-02-15 17:27:45 +0000622 Py_ssize_t size, /* number of Py_UNICODE chars to encode */
Guido van Rossumd8225182000-03-10 22:33:05 +0000623 const char *encoding, /* encoding */
624 const char *errors /* error handling */
625 );
626
Marc-André Lemburgd2d45982004-07-08 17:57:32 +0000627/* Encodes a Unicode object and returns the result as Python
628 object. */
629
630PyAPI_FUNC(PyObject*) PyUnicode_AsEncodedObject(
631 PyObject *unicode, /* Unicode object */
632 const char *encoding, /* encoding */
633 const char *errors /* error handling */
634 );
635
Guido van Rossumd8225182000-03-10 22:33:05 +0000636/* Encodes a Unicode object and returns the result as Python string
637 object. */
638
Mark Hammond91a681d2002-08-12 07:21:58 +0000639PyAPI_FUNC(PyObject*) PyUnicode_AsEncodedString(
Guido van Rossumd8225182000-03-10 22:33:05 +0000640 PyObject *unicode, /* Unicode object */
641 const char *encoding, /* encoding */
642 const char *errors /* error handling */
643 );
644
Marc-André Lemburgc60e6f72001-09-20 10:35:46 +0000645/* --- UTF-7 Codecs ------------------------------------------------------- */
646
Mark Hammond91a681d2002-08-12 07:21:58 +0000647PyAPI_FUNC(PyObject*) PyUnicode_DecodeUTF7(
Marc-André Lemburgc60e6f72001-09-20 10:35:46 +0000648 const char *string, /* UTF-7 encoded string */
Martin v. Löwis18e16552006-02-15 17:27:45 +0000649 Py_ssize_t length, /* size of string */
Marc-André Lemburgc60e6f72001-09-20 10:35:46 +0000650 const char *errors /* error handling */
651 );
652
Mark Hammond91a681d2002-08-12 07:21:58 +0000653PyAPI_FUNC(PyObject*) PyUnicode_EncodeUTF7(
Marc-André Lemburgc60e6f72001-09-20 10:35:46 +0000654 const Py_UNICODE *data, /* Unicode char buffer */
Martin v. Löwis18e16552006-02-15 17:27:45 +0000655 Py_ssize_t length, /* number of Py_UNICODE chars to encode */
Marc-André Lemburgc60e6f72001-09-20 10:35:46 +0000656 int encodeSetO, /* force the encoder to encode characters in
657 Set O, as described in RFC2152 */
658 int encodeWhiteSpace, /* force the encoder to encode space, tab,
659 carriage return and linefeed characters */
660 const char *errors /* error handling */
661 );
662
Guido van Rossumd8225182000-03-10 22:33:05 +0000663/* --- UTF-8 Codecs ------------------------------------------------------- */
664
Mark Hammond91a681d2002-08-12 07:21:58 +0000665PyAPI_FUNC(PyObject*) PyUnicode_DecodeUTF8(
Guido van Rossumd8225182000-03-10 22:33:05 +0000666 const char *string, /* UTF-8 encoded string */
Martin v. Löwis18e16552006-02-15 17:27:45 +0000667 Py_ssize_t length, /* size of string */
Guido van Rossumd8225182000-03-10 22:33:05 +0000668 const char *errors /* error handling */
669 );
670
Walter Dörwald69652032004-09-07 20:24:22 +0000671PyAPI_FUNC(PyObject*) PyUnicode_DecodeUTF8Stateful(
672 const char *string, /* UTF-8 encoded string */
Martin v. Löwis18e16552006-02-15 17:27:45 +0000673 Py_ssize_t length, /* size of string */
Walter Dörwald69652032004-09-07 20:24:22 +0000674 const char *errors, /* error handling */
Martin v. Löwis18e16552006-02-15 17:27:45 +0000675 Py_ssize_t *consumed /* bytes consumed */
Walter Dörwald69652032004-09-07 20:24:22 +0000676 );
677
Mark Hammond91a681d2002-08-12 07:21:58 +0000678PyAPI_FUNC(PyObject*) PyUnicode_AsUTF8String(
Guido van Rossumd8225182000-03-10 22:33:05 +0000679 PyObject *unicode /* Unicode object */
680 );
681
Mark Hammond91a681d2002-08-12 07:21:58 +0000682PyAPI_FUNC(PyObject*) PyUnicode_EncodeUTF8(
Guido van Rossumd8225182000-03-10 22:33:05 +0000683 const Py_UNICODE *data, /* Unicode char buffer */
Martin v. Löwis18e16552006-02-15 17:27:45 +0000684 Py_ssize_t length, /* number of Py_UNICODE chars to encode */
Guido van Rossumd8225182000-03-10 22:33:05 +0000685 const char *errors /* error handling */
686 );
687
688/* --- UTF-16 Codecs ------------------------------------------------------ */
689
Guido van Rossum9e896b32000-04-05 20:11:21 +0000690/* Decodes length bytes from a UTF-16 encoded buffer string and returns
Guido van Rossumd8225182000-03-10 22:33:05 +0000691 the corresponding Unicode object.
692
693 errors (if non-NULL) defines the error handling. It defaults
694 to "strict".
695
696 If byteorder is non-NULL, the decoder starts decoding using the
697 given byte order:
698
699 *byteorder == -1: little endian
700 *byteorder == 0: native order
701 *byteorder == 1: big endian
702
Marc-André Lemburg489b56e2001-05-21 20:30:15 +0000703 In native mode, the first two bytes of the stream are checked for a
704 BOM mark. If found, the BOM mark is analysed, the byte order
705 adjusted and the BOM skipped. In the other modes, no BOM mark
706 interpretation is done. After completion, *byteorder is set to the
707 current byte order at the end of input data.
Guido van Rossumd8225182000-03-10 22:33:05 +0000708
709 If byteorder is NULL, the codec starts in native order mode.
710
711*/
712
Mark Hammond91a681d2002-08-12 07:21:58 +0000713PyAPI_FUNC(PyObject*) PyUnicode_DecodeUTF16(
Guido van Rossumd8225182000-03-10 22:33:05 +0000714 const char *string, /* UTF-16 encoded string */
Martin v. Löwis18e16552006-02-15 17:27:45 +0000715 Py_ssize_t length, /* size of string */
Guido van Rossumd8225182000-03-10 22:33:05 +0000716 const char *errors, /* error handling */
717 int *byteorder /* pointer to byteorder to use
718 0=native;-1=LE,1=BE; updated on
719 exit */
720 );
721
Walter Dörwald69652032004-09-07 20:24:22 +0000722PyAPI_FUNC(PyObject*) PyUnicode_DecodeUTF16Stateful(
723 const char *string, /* UTF-16 encoded string */
Martin v. Löwis18e16552006-02-15 17:27:45 +0000724 Py_ssize_t length, /* size of string */
Walter Dörwald69652032004-09-07 20:24:22 +0000725 const char *errors, /* error handling */
726 int *byteorder, /* pointer to byteorder to use
727 0=native;-1=LE,1=BE; updated on
728 exit */
Martin v. Löwis18e16552006-02-15 17:27:45 +0000729 Py_ssize_t *consumed /* bytes consumed */
Walter Dörwald69652032004-09-07 20:24:22 +0000730 );
731
Guido van Rossumd8225182000-03-10 22:33:05 +0000732/* Returns a Python string using the UTF-16 encoding in native byte
733 order. The string always starts with a BOM mark. */
734
Mark Hammond91a681d2002-08-12 07:21:58 +0000735PyAPI_FUNC(PyObject*) PyUnicode_AsUTF16String(
Guido van Rossumd8225182000-03-10 22:33:05 +0000736 PyObject *unicode /* Unicode object */
737 );
738
739/* Returns a Python string object holding the UTF-16 encoded value of
Guido van Rossum9e896b32000-04-05 20:11:21 +0000740 the Unicode data.
Guido van Rossumd8225182000-03-10 22:33:05 +0000741
742 If byteorder is not 0, output is written according to the following
743 byte order:
744
745 byteorder == -1: little endian
746 byteorder == 0: native byte order (writes a BOM mark)
747 byteorder == 1: big endian
748
749 If byteorder is 0, the output string will always start with the
750 Unicode BOM mark (U+FEFF). In the other two modes, no BOM mark is
751 prepended.
752
753 Note that Py_UNICODE data is being interpreted as UTF-16 reduced to
754 UCS-2. This trick makes it possible to add full UTF-16 capabilities
Thomas Wouters7e474022000-07-16 12:04:32 +0000755 at a later point without compromising the APIs.
Guido van Rossumd8225182000-03-10 22:33:05 +0000756
757*/
758
Mark Hammond91a681d2002-08-12 07:21:58 +0000759PyAPI_FUNC(PyObject*) PyUnicode_EncodeUTF16(
Guido van Rossumd8225182000-03-10 22:33:05 +0000760 const Py_UNICODE *data, /* Unicode char buffer */
Martin v. Löwis18e16552006-02-15 17:27:45 +0000761 Py_ssize_t length, /* number of Py_UNICODE chars to encode */
Guido van Rossumd8225182000-03-10 22:33:05 +0000762 const char *errors, /* error handling */
763 int byteorder /* byteorder to use 0=BOM+native;-1=LE,1=BE */
764 );
765
766/* --- Unicode-Escape Codecs ---------------------------------------------- */
767
Mark Hammond91a681d2002-08-12 07:21:58 +0000768PyAPI_FUNC(PyObject*) PyUnicode_DecodeUnicodeEscape(
Guido van Rossumd8225182000-03-10 22:33:05 +0000769 const char *string, /* Unicode-Escape encoded string */
Martin v. Löwis18e16552006-02-15 17:27:45 +0000770 Py_ssize_t length, /* size of string */
Guido van Rossumd8225182000-03-10 22:33:05 +0000771 const char *errors /* error handling */
772 );
773
Mark Hammond91a681d2002-08-12 07:21:58 +0000774PyAPI_FUNC(PyObject*) PyUnicode_AsUnicodeEscapeString(
Guido van Rossumd8225182000-03-10 22:33:05 +0000775 PyObject *unicode /* Unicode object */
776 );
777
Mark Hammond91a681d2002-08-12 07:21:58 +0000778PyAPI_FUNC(PyObject*) PyUnicode_EncodeUnicodeEscape(
Guido van Rossumd8225182000-03-10 22:33:05 +0000779 const Py_UNICODE *data, /* Unicode char buffer */
Martin v. Löwis18e16552006-02-15 17:27:45 +0000780 Py_ssize_t length /* Number of Py_UNICODE chars to encode */
Guido van Rossumd8225182000-03-10 22:33:05 +0000781 );
782
783/* --- Raw-Unicode-Escape Codecs ------------------------------------------ */
784
Mark Hammond91a681d2002-08-12 07:21:58 +0000785PyAPI_FUNC(PyObject*) PyUnicode_DecodeRawUnicodeEscape(
Guido van Rossumd8225182000-03-10 22:33:05 +0000786 const char *string, /* Raw-Unicode-Escape encoded string */
Martin v. Löwis18e16552006-02-15 17:27:45 +0000787 Py_ssize_t length, /* size of string */
Guido van Rossumd8225182000-03-10 22:33:05 +0000788 const char *errors /* error handling */
789 );
790
Mark Hammond91a681d2002-08-12 07:21:58 +0000791PyAPI_FUNC(PyObject*) PyUnicode_AsRawUnicodeEscapeString(
Guido van Rossumd8225182000-03-10 22:33:05 +0000792 PyObject *unicode /* Unicode object */
793 );
794
Mark Hammond91a681d2002-08-12 07:21:58 +0000795PyAPI_FUNC(PyObject*) PyUnicode_EncodeRawUnicodeEscape(
Guido van Rossumd8225182000-03-10 22:33:05 +0000796 const Py_UNICODE *data, /* Unicode char buffer */
Martin v. Löwis18e16552006-02-15 17:27:45 +0000797 Py_ssize_t length /* Number of Py_UNICODE chars to encode */
Guido van Rossumd8225182000-03-10 22:33:05 +0000798 );
799
Walter Dörwalda47d1c02005-08-30 10:23:14 +0000800/* --- Unicode Internal Codec ---------------------------------------------
801
802 Only for internal use in _codecsmodule.c */
803
804PyObject *_PyUnicode_DecodeUnicodeInternal(
805 const char *string,
Martin v. Löwis18e16552006-02-15 17:27:45 +0000806 Py_ssize_t length,
Walter Dörwalda47d1c02005-08-30 10:23:14 +0000807 const char *errors
808 );
809
Guido van Rossumd8225182000-03-10 22:33:05 +0000810/* --- Latin-1 Codecs -----------------------------------------------------
811
812 Note: Latin-1 corresponds to the first 256 Unicode ordinals.
813
814*/
815
Mark Hammond91a681d2002-08-12 07:21:58 +0000816PyAPI_FUNC(PyObject*) PyUnicode_DecodeLatin1(
Guido van Rossumd8225182000-03-10 22:33:05 +0000817 const char *string, /* Latin-1 encoded string */
Martin v. Löwis18e16552006-02-15 17:27:45 +0000818 Py_ssize_t length, /* size of string */
Guido van Rossumd8225182000-03-10 22:33:05 +0000819 const char *errors /* error handling */
820 );
821
Mark Hammond91a681d2002-08-12 07:21:58 +0000822PyAPI_FUNC(PyObject*) PyUnicode_AsLatin1String(
Guido van Rossumd8225182000-03-10 22:33:05 +0000823 PyObject *unicode /* Unicode object */
824 );
825
Mark Hammond91a681d2002-08-12 07:21:58 +0000826PyAPI_FUNC(PyObject*) PyUnicode_EncodeLatin1(
Guido van Rossumd8225182000-03-10 22:33:05 +0000827 const Py_UNICODE *data, /* Unicode char buffer */
Martin v. Löwis18e16552006-02-15 17:27:45 +0000828 Py_ssize_t length, /* Number of Py_UNICODE chars to encode */
Guido van Rossumd8225182000-03-10 22:33:05 +0000829 const char *errors /* error handling */
830 );
831
832/* --- ASCII Codecs -------------------------------------------------------
833
834 Only 7-bit ASCII data is excepted. All other codes generate errors.
835
836*/
837
Mark Hammond91a681d2002-08-12 07:21:58 +0000838PyAPI_FUNC(PyObject*) PyUnicode_DecodeASCII(
Guido van Rossumd8225182000-03-10 22:33:05 +0000839 const char *string, /* ASCII encoded string */
Martin v. Löwis18e16552006-02-15 17:27:45 +0000840 Py_ssize_t length, /* size of string */
Guido van Rossumd8225182000-03-10 22:33:05 +0000841 const char *errors /* error handling */
842 );
843
Mark Hammond91a681d2002-08-12 07:21:58 +0000844PyAPI_FUNC(PyObject*) PyUnicode_AsASCIIString(
Guido van Rossumd8225182000-03-10 22:33:05 +0000845 PyObject *unicode /* Unicode object */
846 );
847
Mark Hammond91a681d2002-08-12 07:21:58 +0000848PyAPI_FUNC(PyObject*) PyUnicode_EncodeASCII(
Guido van Rossumd8225182000-03-10 22:33:05 +0000849 const Py_UNICODE *data, /* Unicode char buffer */
Martin v. Löwis18e16552006-02-15 17:27:45 +0000850 Py_ssize_t length, /* Number of Py_UNICODE chars to encode */
Guido van Rossumd8225182000-03-10 22:33:05 +0000851 const char *errors /* error handling */
852 );
853
854/* --- Character Map Codecs -----------------------------------------------
855
856 This codec uses mappings to encode and decode characters.
857
858 Decoding mappings must map single string characters to single
859 Unicode characters, integers (which are then interpreted as Unicode
860 ordinals) or None (meaning "undefined mapping" and causing an
861 error).
862
863 Encoding mappings must map single Unicode characters to single
864 string characters, integers (which are then interpreted as Latin-1
865 ordinals) or None (meaning "undefined mapping" and causing an
866 error).
867
868 If a character lookup fails with a LookupError, the character is
869 copied as-is meaning that its ordinal value will be interpreted as
870 Unicode or Latin-1 ordinal resp. Because of this mappings only need
871 to contain those mappings which map characters to different code
872 points.
873
874*/
875
Mark Hammond91a681d2002-08-12 07:21:58 +0000876PyAPI_FUNC(PyObject*) PyUnicode_DecodeCharmap(
Guido van Rossumd8225182000-03-10 22:33:05 +0000877 const char *string, /* Encoded string */
Martin v. Löwis18e16552006-02-15 17:27:45 +0000878 Py_ssize_t length, /* size of string */
Guido van Rossumd8225182000-03-10 22:33:05 +0000879 PyObject *mapping, /* character mapping
880 (char ordinal -> unicode ordinal) */
881 const char *errors /* error handling */
882 );
883
Mark Hammond91a681d2002-08-12 07:21:58 +0000884PyAPI_FUNC(PyObject*) PyUnicode_AsCharmapString(
Guido van Rossumd8225182000-03-10 22:33:05 +0000885 PyObject *unicode, /* Unicode object */
886 PyObject *mapping /* character mapping
887 (unicode ordinal -> char ordinal) */
888 );
889
Mark Hammond91a681d2002-08-12 07:21:58 +0000890PyAPI_FUNC(PyObject*) PyUnicode_EncodeCharmap(
Guido van Rossumd8225182000-03-10 22:33:05 +0000891 const Py_UNICODE *data, /* Unicode char buffer */
Martin v. Löwis18e16552006-02-15 17:27:45 +0000892 Py_ssize_t length, /* Number of Py_UNICODE chars to encode */
Guido van Rossumd8225182000-03-10 22:33:05 +0000893 PyObject *mapping, /* character mapping
894 (unicode ordinal -> char ordinal) */
895 const char *errors /* error handling */
896 );
897
898/* Translate a Py_UNICODE buffer of the given length by applying a
899 character mapping table to it and return the resulting Unicode
900 object.
901
902 The mapping table must map Unicode ordinal integers to Unicode
903 ordinal integers or None (causing deletion of the character).
904
905 Mapping tables may be dictionaries or sequences. Unmapped character
906 ordinals (ones which cause a LookupError) are left untouched and
907 are copied as-is.
908
909*/
910
Mark Hammond91a681d2002-08-12 07:21:58 +0000911PyAPI_FUNC(PyObject *) PyUnicode_TranslateCharmap(
Guido van Rossumd8225182000-03-10 22:33:05 +0000912 const Py_UNICODE *data, /* Unicode char buffer */
Martin v. Löwis18e16552006-02-15 17:27:45 +0000913 Py_ssize_t length, /* Number of Py_UNICODE chars to encode */
Guido van Rossumd8225182000-03-10 22:33:05 +0000914 PyObject *table, /* Translate table */
915 const char *errors /* error handling */
916 );
917
Guido van Rossumefec1152000-03-28 02:01:15 +0000918#ifdef MS_WIN32
Guido van Rossum24bdb042000-03-28 20:29:59 +0000919
Guido van Rossumefec1152000-03-28 02:01:15 +0000920/* --- MBCS codecs for Windows -------------------------------------------- */
Guido van Rossum24bdb042000-03-28 20:29:59 +0000921
Mark Hammond91a681d2002-08-12 07:21:58 +0000922PyAPI_FUNC(PyObject*) PyUnicode_DecodeMBCS(
Guido van Rossumefec1152000-03-28 02:01:15 +0000923 const char *string, /* MBCS encoded string */
Martin v. Löwis18e16552006-02-15 17:27:45 +0000924 Py_ssize_t length, /* size of string */
Guido van Rossumefec1152000-03-28 02:01:15 +0000925 const char *errors /* error handling */
926 );
927
Mark Hammond91a681d2002-08-12 07:21:58 +0000928PyAPI_FUNC(PyObject*) PyUnicode_AsMBCSString(
Guido van Rossumefec1152000-03-28 02:01:15 +0000929 PyObject *unicode /* Unicode object */
930 );
931
Mark Hammond91a681d2002-08-12 07:21:58 +0000932PyAPI_FUNC(PyObject*) PyUnicode_EncodeMBCS(
Guido van Rossumefec1152000-03-28 02:01:15 +0000933 const Py_UNICODE *data, /* Unicode char buffer */
Martin v. Löwis18e16552006-02-15 17:27:45 +0000934 Py_ssize_t length, /* Number of Py_UNICODE chars to encode */
Guido van Rossumefec1152000-03-28 02:01:15 +0000935 const char *errors /* error handling */
936 );
937
Guido van Rossumefec1152000-03-28 02:01:15 +0000938#endif /* MS_WIN32 */
Guido van Rossum24bdb042000-03-28 20:29:59 +0000939
Guido van Rossum9e896b32000-04-05 20:11:21 +0000940/* --- Decimal Encoder ---------------------------------------------------- */
941
942/* Takes a Unicode string holding a decimal value and writes it into
943 an output buffer using standard ASCII digit codes.
944
945 The output buffer has to provide at least length+1 bytes of storage
946 area. The output string is 0-terminated.
947
948 The encoder converts whitespace to ' ', decimal characters to their
949 corresponding ASCII digit and all other Latin-1 characters except
950 \0 as-is. Characters outside this range (Unicode ordinals 1-256)
951 are treated as errors. This includes embedded NULL bytes.
952
953 Error handling is defined by the errors argument:
954
955 NULL or "strict": raise a ValueError
956 "ignore": ignore the wrong characters (these are not copied to the
957 output buffer)
958 "replace": replaces illegal characters with '?'
959
960 Returns 0 on success, -1 on failure.
961
962*/
963
Mark Hammond91a681d2002-08-12 07:21:58 +0000964PyAPI_FUNC(int) PyUnicode_EncodeDecimal(
Guido van Rossum9e896b32000-04-05 20:11:21 +0000965 Py_UNICODE *s, /* Unicode buffer */
Martin v. Löwis18e16552006-02-15 17:27:45 +0000966 Py_ssize_t length, /* Number of Py_UNICODE chars to encode */
Guido van Rossum9e896b32000-04-05 20:11:21 +0000967 char *output, /* Output buffer; must have size >= length */
968 const char *errors /* error handling */
969 );
970
Guido van Rossumd8225182000-03-10 22:33:05 +0000971/* --- Methods & Slots ----------------------------------------------------
972
973 These are capable of handling Unicode objects and strings on input
974 (we refer to them as strings in the descriptions) and return
975 Unicode objects or integers as apporpriate. */
976
977/* Concat two strings giving a new Unicode string. */
978
Mark Hammond91a681d2002-08-12 07:21:58 +0000979PyAPI_FUNC(PyObject*) PyUnicode_Concat(
Guido van Rossumd8225182000-03-10 22:33:05 +0000980 PyObject *left, /* Left string */
981 PyObject *right /* Right string */
982 );
983
984/* Split a string giving a list of Unicode strings.
985
986 If sep is NULL, splitting will be done at all whitespace
987 substrings. Otherwise, splits occur at the given separator.
988
989 At most maxsplit splits will be done. If negative, no limit is set.
990
991 Separators are not included in the resulting list.
992
993*/
994
Mark Hammond91a681d2002-08-12 07:21:58 +0000995PyAPI_FUNC(PyObject*) PyUnicode_Split(
Guido van Rossumd8225182000-03-10 22:33:05 +0000996 PyObject *s, /* String to split */
997 PyObject *sep, /* String separator */
Martin v. Löwis18e16552006-02-15 17:27:45 +0000998 Py_ssize_t maxsplit /* Maxsplit count */
Guido van Rossumd8225182000-03-10 22:33:05 +0000999 );
1000
1001/* Dito, but split at line breaks.
1002
1003 CRLF is considered to be one line break. Line breaks are not
1004 included in the resulting list. */
1005
Mark Hammond91a681d2002-08-12 07:21:58 +00001006PyAPI_FUNC(PyObject*) PyUnicode_Splitlines(
Guido van Rossumd8225182000-03-10 22:33:05 +00001007 PyObject *s, /* String to split */
Guido van Rossum004d64f2000-04-11 15:39:46 +00001008 int keepends /* If true, line end markers are included */
Guido van Rossumd8225182000-03-10 22:33:05 +00001009 );
1010
Hye-Shik Chang3ae811b2003-12-15 18:49:53 +00001011/* Split a string giving a list of Unicode strings.
1012
1013 If sep is NULL, splitting will be done at all whitespace
1014 substrings. Otherwise, splits occur at the given separator.
1015
1016 At most maxsplit splits will be done. But unlike PyUnicode_Split
1017 PyUnicode_RSplit splits from the end of the string. If negative,
1018 no limit is set.
1019
1020 Separators are not included in the resulting list.
1021
1022*/
1023
1024PyAPI_FUNC(PyObject*) PyUnicode_RSplit(
1025 PyObject *s, /* String to split */
1026 PyObject *sep, /* String separator */
Martin v. Löwis18e16552006-02-15 17:27:45 +00001027 Py_ssize_t maxsplit /* Maxsplit count */
Hye-Shik Chang3ae811b2003-12-15 18:49:53 +00001028 );
1029
Guido van Rossumd8225182000-03-10 22:33:05 +00001030/* Translate a string by applying a character mapping table to it and
1031 return the resulting Unicode object.
1032
1033 The mapping table must map Unicode ordinal integers to Unicode
1034 ordinal integers or None (causing deletion of the character).
1035
1036 Mapping tables may be dictionaries or sequences. Unmapped character
1037 ordinals (ones which cause a LookupError) are left untouched and
1038 are copied as-is.
1039
1040*/
1041
Mark Hammond91a681d2002-08-12 07:21:58 +00001042PyAPI_FUNC(PyObject *) PyUnicode_Translate(
Guido van Rossumd8225182000-03-10 22:33:05 +00001043 PyObject *str, /* String */
1044 PyObject *table, /* Translate table */
1045 const char *errors /* error handling */
1046 );
1047
1048/* Join a sequence of strings using the given separator and return
1049 the resulting Unicode string. */
1050
Mark Hammond91a681d2002-08-12 07:21:58 +00001051PyAPI_FUNC(PyObject*) PyUnicode_Join(
Guido van Rossumd8225182000-03-10 22:33:05 +00001052 PyObject *separator, /* Separator string */
1053 PyObject *seq /* Sequence object */
1054 );
1055
1056/* Return 1 if substr matches str[start:end] at the given tail end, 0
1057 otherwise. */
1058
Martin v. Löwis18e16552006-02-15 17:27:45 +00001059PyAPI_FUNC(Py_ssize_t) PyUnicode_Tailmatch(
Guido van Rossumd8225182000-03-10 22:33:05 +00001060 PyObject *str, /* String */
1061 PyObject *substr, /* Prefix or Suffix string */
Martin v. Löwis18e16552006-02-15 17:27:45 +00001062 Py_ssize_t start, /* Start index */
1063 Py_ssize_t end, /* Stop index */
Guido van Rossumd8225182000-03-10 22:33:05 +00001064 int direction /* Tail end: -1 prefix, +1 suffix */
1065 );
1066
1067/* Return the first position of substr in str[start:end] using the
Marc-André Lemburg4da6fd62002-05-29 11:33:13 +00001068 given search direction or -1 if not found. -2 is returned in case
1069 an error occurred and an exception is set. */
Guido van Rossumd8225182000-03-10 22:33:05 +00001070
Martin v. Löwis18e16552006-02-15 17:27:45 +00001071PyAPI_FUNC(Py_ssize_t) PyUnicode_Find(
Guido van Rossumd8225182000-03-10 22:33:05 +00001072 PyObject *str, /* String */
1073 PyObject *substr, /* Substring to find */
Martin v. Löwis18e16552006-02-15 17:27:45 +00001074 Py_ssize_t start, /* Start index */
1075 Py_ssize_t end, /* Stop index */
Guido van Rossumd8225182000-03-10 22:33:05 +00001076 int direction /* Find direction: +1 forward, -1 backward */
1077 );
1078
Barry Warsaw51ac5802000-03-20 16:36:48 +00001079/* Count the number of occurrences of substr in str[start:end]. */
Guido van Rossumd8225182000-03-10 22:33:05 +00001080
Martin v. Löwis18e16552006-02-15 17:27:45 +00001081PyAPI_FUNC(Py_ssize_t) PyUnicode_Count(
Guido van Rossumd8225182000-03-10 22:33:05 +00001082 PyObject *str, /* String */
1083 PyObject *substr, /* Substring to count */
Martin v. Löwis18e16552006-02-15 17:27:45 +00001084 Py_ssize_t start, /* Start index */
1085 Py_ssize_t end /* Stop index */
Guido van Rossumd8225182000-03-10 22:33:05 +00001086 );
1087
Barry Warsaw51ac5802000-03-20 16:36:48 +00001088/* Replace at most maxcount occurrences of substr in str with replstr
Guido van Rossumd8225182000-03-10 22:33:05 +00001089 and return the resulting Unicode object. */
1090
Mark Hammond91a681d2002-08-12 07:21:58 +00001091PyAPI_FUNC(PyObject *) PyUnicode_Replace(
Guido van Rossumd8225182000-03-10 22:33:05 +00001092 PyObject *str, /* String */
1093 PyObject *substr, /* Substring to find */
1094 PyObject *replstr, /* Substring to replace */
Martin v. Löwis18e16552006-02-15 17:27:45 +00001095 Py_ssize_t maxcount /* Max. number of replacements to apply;
Guido van Rossumd8225182000-03-10 22:33:05 +00001096 -1 = all */
1097 );
1098
1099/* Compare two strings and return -1, 0, 1 for less than, equal,
1100 greater than resp. */
1101
Mark Hammond91a681d2002-08-12 07:21:58 +00001102PyAPI_FUNC(int) PyUnicode_Compare(
Guido van Rossumd8225182000-03-10 22:33:05 +00001103 PyObject *left, /* Left string */
1104 PyObject *right /* Right string */
1105 );
1106
Thomas Wouters7e474022000-07-16 12:04:32 +00001107/* Apply a argument tuple or dictionary to a format string and return
Guido van Rossumd8225182000-03-10 22:33:05 +00001108 the resulting Unicode string. */
1109
Mark Hammond91a681d2002-08-12 07:21:58 +00001110PyAPI_FUNC(PyObject *) PyUnicode_Format(
Guido van Rossumd8225182000-03-10 22:33:05 +00001111 PyObject *format, /* Format string */
1112 PyObject *args /* Argument tuple or dictionary */
1113 );
1114
Guido van Rossumd0d366b2000-03-13 23:22:24 +00001115/* Checks whether element is contained in container and return 1/0
1116 accordingly.
1117
1118 element has to coerce to an one element Unicode string. -1 is
1119 returned in case of an error. */
1120
Mark Hammond91a681d2002-08-12 07:21:58 +00001121PyAPI_FUNC(int) PyUnicode_Contains(
Guido van Rossumd0d366b2000-03-13 23:22:24 +00001122 PyObject *container, /* Container string */
1123 PyObject *element /* Element string */
1124 );
1125
Walter Dörwaldde02bcb2002-04-22 17:42:37 +00001126/* Externally visible for str.strip(unicode) */
Mark Hammond91a681d2002-08-12 07:21:58 +00001127PyAPI_FUNC(PyObject *) _PyUnicode_XStrip(
Walter Dörwaldde02bcb2002-04-22 17:42:37 +00001128 PyUnicodeObject *self,
1129 int striptype,
1130 PyObject *sepobj
1131 );
1132
Guido van Rossumd8225182000-03-10 22:33:05 +00001133/* === Characters Type APIs =============================================== */
1134
1135/* These should not be used directly. Use the Py_UNICODE_IS* and
1136 Py_UNICODE_TO* macros instead.
1137
1138 These APIs are implemented in Objects/unicodectype.c.
1139
1140*/
1141
Mark Hammond91a681d2002-08-12 07:21:58 +00001142PyAPI_FUNC(int) _PyUnicode_IsLowercase(
Fredrik Lundh72b06852001-06-27 22:08:26 +00001143 Py_UNICODE ch /* Unicode character */
Guido van Rossumd8225182000-03-10 22:33:05 +00001144 );
1145
Mark Hammond91a681d2002-08-12 07:21:58 +00001146PyAPI_FUNC(int) _PyUnicode_IsUppercase(
Fredrik Lundh72b06852001-06-27 22:08:26 +00001147 Py_UNICODE ch /* Unicode character */
Guido van Rossumd8225182000-03-10 22:33:05 +00001148 );
1149
Mark Hammond91a681d2002-08-12 07:21:58 +00001150PyAPI_FUNC(int) _PyUnicode_IsTitlecase(
Fredrik Lundh72b06852001-06-27 22:08:26 +00001151 Py_UNICODE ch /* Unicode character */
Guido van Rossumd8225182000-03-10 22:33:05 +00001152 );
1153
Mark Hammond91a681d2002-08-12 07:21:58 +00001154PyAPI_FUNC(int) _PyUnicode_IsWhitespace(
Tim Peters2576c972005-10-29 02:33:18 +00001155 const Py_UNICODE ch /* Unicode character */
Guido van Rossumd8225182000-03-10 22:33:05 +00001156 );
1157
Mark Hammond91a681d2002-08-12 07:21:58 +00001158PyAPI_FUNC(int) _PyUnicode_IsLinebreak(
Tim Peters2576c972005-10-29 02:33:18 +00001159 const Py_UNICODE ch /* Unicode character */
Guido van Rossumd8225182000-03-10 22:33:05 +00001160 );
1161
Mark Hammond91a681d2002-08-12 07:21:58 +00001162PyAPI_FUNC(Py_UNICODE) _PyUnicode_ToLowercase(
Fredrik Lundh72b06852001-06-27 22:08:26 +00001163 Py_UNICODE ch /* Unicode character */
Guido van Rossumd8225182000-03-10 22:33:05 +00001164 );
1165
Mark Hammond91a681d2002-08-12 07:21:58 +00001166PyAPI_FUNC(Py_UNICODE) _PyUnicode_ToUppercase(
Fredrik Lundh72b06852001-06-27 22:08:26 +00001167 Py_UNICODE ch /* Unicode character */
Guido van Rossumd8225182000-03-10 22:33:05 +00001168 );
1169
Mark Hammond91a681d2002-08-12 07:21:58 +00001170PyAPI_FUNC(Py_UNICODE) _PyUnicode_ToTitlecase(
Fredrik Lundh72b06852001-06-27 22:08:26 +00001171 Py_UNICODE ch /* Unicode character */
Guido van Rossumd8225182000-03-10 22:33:05 +00001172 );
1173
Mark Hammond91a681d2002-08-12 07:21:58 +00001174PyAPI_FUNC(int) _PyUnicode_ToDecimalDigit(
Fredrik Lundh72b06852001-06-27 22:08:26 +00001175 Py_UNICODE ch /* Unicode character */
Guido van Rossumd8225182000-03-10 22:33:05 +00001176 );
1177
Mark Hammond91a681d2002-08-12 07:21:58 +00001178PyAPI_FUNC(int) _PyUnicode_ToDigit(
Fredrik Lundh72b06852001-06-27 22:08:26 +00001179 Py_UNICODE ch /* Unicode character */
Guido van Rossumd8225182000-03-10 22:33:05 +00001180 );
1181
Mark Hammond91a681d2002-08-12 07:21:58 +00001182PyAPI_FUNC(double) _PyUnicode_ToNumeric(
Fredrik Lundh72b06852001-06-27 22:08:26 +00001183 Py_UNICODE ch /* Unicode character */
Guido van Rossumd8225182000-03-10 22:33:05 +00001184 );
1185
Mark Hammond91a681d2002-08-12 07:21:58 +00001186PyAPI_FUNC(int) _PyUnicode_IsDecimalDigit(
Fredrik Lundh72b06852001-06-27 22:08:26 +00001187 Py_UNICODE ch /* Unicode character */
Guido van Rossumd8225182000-03-10 22:33:05 +00001188 );
1189
Mark Hammond91a681d2002-08-12 07:21:58 +00001190PyAPI_FUNC(int) _PyUnicode_IsDigit(
Fredrik Lundh72b06852001-06-27 22:08:26 +00001191 Py_UNICODE ch /* Unicode character */
Guido van Rossumd8225182000-03-10 22:33:05 +00001192 );
1193
Mark Hammond91a681d2002-08-12 07:21:58 +00001194PyAPI_FUNC(int) _PyUnicode_IsNumeric(
Fredrik Lundh72b06852001-06-27 22:08:26 +00001195 Py_UNICODE ch /* Unicode character */
Guido van Rossumd8225182000-03-10 22:33:05 +00001196 );
1197
Mark Hammond91a681d2002-08-12 07:21:58 +00001198PyAPI_FUNC(int) _PyUnicode_IsAlpha(
Fredrik Lundh72b06852001-06-27 22:08:26 +00001199 Py_UNICODE ch /* Unicode character */
Marc-André Lemburgf03e7412000-07-05 09:45:59 +00001200 );
1201
Guido van Rossumd8225182000-03-10 22:33:05 +00001202#ifdef __cplusplus
1203}
1204#endif
Martin v. Löwis339d0f72001-08-17 18:39:25 +00001205#endif /* Py_USING_UNICODE */
Guido van Rossumd8225182000-03-10 22:33:05 +00001206#endif /* !Py_UNICODEOBJECT_H */