blob: 8c39cfe2d637a6e3c3553fd55db81cce2f12c899 [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
Thomas Wouters477c8d52006-05-27 19:21:47 +0000187# define PyUnicode_Partition PyUnicodeUCS2_Partition
188# define PyUnicode_RPartition PyUnicodeUCS2_RPartition
189# define PyUnicode_RSplit PyUnicodeUCS2_RSplit
Marc-André Lemburgb5ac6f62001-07-31 14:30:16 +0000190# define PyUnicode_Replace PyUnicodeUCS2_Replace
191# define PyUnicode_Resize PyUnicodeUCS2_Resize
192# define PyUnicode_SetDefaultEncoding PyUnicodeUCS2_SetDefaultEncoding
193# define PyUnicode_Split PyUnicodeUCS2_Split
194# define PyUnicode_Splitlines PyUnicodeUCS2_Splitlines
195# define PyUnicode_Tailmatch PyUnicodeUCS2_Tailmatch
196# define PyUnicode_Translate PyUnicodeUCS2_Translate
197# define PyUnicode_TranslateCharmap PyUnicodeUCS2_TranslateCharmap
198# define _PyUnicode_AsDefaultEncodedString _PyUnicodeUCS2_AsDefaultEncodedString
199# define _PyUnicode_Fini _PyUnicodeUCS2_Fini
200# define _PyUnicode_Init _PyUnicodeUCS2_Init
201# define _PyUnicode_IsAlpha _PyUnicodeUCS2_IsAlpha
202# define _PyUnicode_IsDecimalDigit _PyUnicodeUCS2_IsDecimalDigit
203# define _PyUnicode_IsDigit _PyUnicodeUCS2_IsDigit
204# define _PyUnicode_IsLinebreak _PyUnicodeUCS2_IsLinebreak
205# define _PyUnicode_IsLowercase _PyUnicodeUCS2_IsLowercase
206# define _PyUnicode_IsNumeric _PyUnicodeUCS2_IsNumeric
207# define _PyUnicode_IsTitlecase _PyUnicodeUCS2_IsTitlecase
208# define _PyUnicode_IsUppercase _PyUnicodeUCS2_IsUppercase
209# define _PyUnicode_IsWhitespace _PyUnicodeUCS2_IsWhitespace
210# define _PyUnicode_ToDecimalDigit _PyUnicodeUCS2_ToDecimalDigit
211# define _PyUnicode_ToDigit _PyUnicodeUCS2_ToDigit
212# define _PyUnicode_ToLowercase _PyUnicodeUCS2_ToLowercase
213# define _PyUnicode_ToNumeric _PyUnicodeUCS2_ToNumeric
214# define _PyUnicode_ToTitlecase _PyUnicodeUCS2_ToTitlecase
215# define _PyUnicode_ToUppercase _PyUnicodeUCS2_ToUppercase
216
217#else
218
219# define PyUnicode_AsASCIIString PyUnicodeUCS4_AsASCIIString
220# define PyUnicode_AsCharmapString PyUnicodeUCS4_AsCharmapString
Marc-André Lemburgd2d45982004-07-08 17:57:32 +0000221# define PyUnicode_AsEncodedObject PyUnicodeUCS4_AsEncodedObject
Marc-André Lemburgb5ac6f62001-07-31 14:30:16 +0000222# define PyUnicode_AsEncodedString PyUnicodeUCS4_AsEncodedString
223# define PyUnicode_AsLatin1String PyUnicodeUCS4_AsLatin1String
224# define PyUnicode_AsRawUnicodeEscapeString PyUnicodeUCS4_AsRawUnicodeEscapeString
225# define PyUnicode_AsUTF16String PyUnicodeUCS4_AsUTF16String
226# define PyUnicode_AsUTF8String PyUnicodeUCS4_AsUTF8String
227# define PyUnicode_AsUnicode PyUnicodeUCS4_AsUnicode
228# define PyUnicode_AsUnicodeEscapeString PyUnicodeUCS4_AsUnicodeEscapeString
229# define PyUnicode_AsWideChar PyUnicodeUCS4_AsWideChar
230# define PyUnicode_Compare PyUnicodeUCS4_Compare
231# define PyUnicode_Concat PyUnicodeUCS4_Concat
232# define PyUnicode_Contains PyUnicodeUCS4_Contains
233# define PyUnicode_Count PyUnicodeUCS4_Count
234# define PyUnicode_Decode PyUnicodeUCS4_Decode
235# define PyUnicode_DecodeASCII PyUnicodeUCS4_DecodeASCII
236# define PyUnicode_DecodeCharmap PyUnicodeUCS4_DecodeCharmap
237# define PyUnicode_DecodeLatin1 PyUnicodeUCS4_DecodeLatin1
238# define PyUnicode_DecodeRawUnicodeEscape PyUnicodeUCS4_DecodeRawUnicodeEscape
239# define PyUnicode_DecodeUTF16 PyUnicodeUCS4_DecodeUTF16
Walter Dörwald69652032004-09-07 20:24:22 +0000240# define PyUnicode_DecodeUTF16Stateful PyUnicodeUCS4_DecodeUTF16Stateful
Marc-André Lemburgb5ac6f62001-07-31 14:30:16 +0000241# define PyUnicode_DecodeUTF8 PyUnicodeUCS4_DecodeUTF8
Walter Dörwald69652032004-09-07 20:24:22 +0000242# define PyUnicode_DecodeUTF8Stateful PyUnicodeUCS4_DecodeUTF8Stateful
Marc-André Lemburgb5ac6f62001-07-31 14:30:16 +0000243# define PyUnicode_DecodeUnicodeEscape PyUnicodeUCS4_DecodeUnicodeEscape
244# define PyUnicode_Encode PyUnicodeUCS4_Encode
245# define PyUnicode_EncodeASCII PyUnicodeUCS4_EncodeASCII
246# define PyUnicode_EncodeCharmap PyUnicodeUCS4_EncodeCharmap
247# define PyUnicode_EncodeDecimal PyUnicodeUCS4_EncodeDecimal
248# define PyUnicode_EncodeLatin1 PyUnicodeUCS4_EncodeLatin1
249# define PyUnicode_EncodeRawUnicodeEscape PyUnicodeUCS4_EncodeRawUnicodeEscape
250# define PyUnicode_EncodeUTF16 PyUnicodeUCS4_EncodeUTF16
251# define PyUnicode_EncodeUTF8 PyUnicodeUCS4_EncodeUTF8
252# define PyUnicode_EncodeUnicodeEscape PyUnicodeUCS4_EncodeUnicodeEscape
253# define PyUnicode_Find PyUnicodeUCS4_Find
254# define PyUnicode_Format PyUnicodeUCS4_Format
255# define PyUnicode_FromEncodedObject PyUnicodeUCS4_FromEncodedObject
256# define PyUnicode_FromObject PyUnicodeUCS4_FromObject
Marc-André Lemburg9c329de2002-08-12 08:19:10 +0000257# define PyUnicode_FromOrdinal PyUnicodeUCS4_FromOrdinal
Marc-André Lemburgb5ac6f62001-07-31 14:30:16 +0000258# define PyUnicode_FromUnicode PyUnicodeUCS4_FromUnicode
259# define PyUnicode_FromWideChar PyUnicodeUCS4_FromWideChar
260# define PyUnicode_GetDefaultEncoding PyUnicodeUCS4_GetDefaultEncoding
261# define PyUnicode_GetMax PyUnicodeUCS4_GetMax
262# define PyUnicode_GetSize PyUnicodeUCS4_GetSize
263# define PyUnicode_Join PyUnicodeUCS4_Join
Thomas Wouters477c8d52006-05-27 19:21:47 +0000264# define PyUnicode_Partition PyUnicodeUCS4_Partition
265# define PyUnicode_RPartition PyUnicodeUCS4_RPartition
266# define PyUnicode_RSplit PyUnicodeUCS4_RSplit
Marc-André Lemburgb5ac6f62001-07-31 14:30:16 +0000267# define PyUnicode_Replace PyUnicodeUCS4_Replace
268# define PyUnicode_Resize PyUnicodeUCS4_Resize
269# define PyUnicode_SetDefaultEncoding PyUnicodeUCS4_SetDefaultEncoding
270# define PyUnicode_Split PyUnicodeUCS4_Split
271# define PyUnicode_Splitlines PyUnicodeUCS4_Splitlines
272# define PyUnicode_Tailmatch PyUnicodeUCS4_Tailmatch
273# define PyUnicode_Translate PyUnicodeUCS4_Translate
274# define PyUnicode_TranslateCharmap PyUnicodeUCS4_TranslateCharmap
275# define _PyUnicode_AsDefaultEncodedString _PyUnicodeUCS4_AsDefaultEncodedString
276# define _PyUnicode_Fini _PyUnicodeUCS4_Fini
277# define _PyUnicode_Init _PyUnicodeUCS4_Init
278# define _PyUnicode_IsAlpha _PyUnicodeUCS4_IsAlpha
279# define _PyUnicode_IsDecimalDigit _PyUnicodeUCS4_IsDecimalDigit
280# define _PyUnicode_IsDigit _PyUnicodeUCS4_IsDigit
281# define _PyUnicode_IsLinebreak _PyUnicodeUCS4_IsLinebreak
282# define _PyUnicode_IsLowercase _PyUnicodeUCS4_IsLowercase
283# define _PyUnicode_IsNumeric _PyUnicodeUCS4_IsNumeric
284# define _PyUnicode_IsTitlecase _PyUnicodeUCS4_IsTitlecase
285# define _PyUnicode_IsUppercase _PyUnicodeUCS4_IsUppercase
286# define _PyUnicode_IsWhitespace _PyUnicodeUCS4_IsWhitespace
287# define _PyUnicode_ToDecimalDigit _PyUnicodeUCS4_ToDecimalDigit
288# define _PyUnicode_ToDigit _PyUnicodeUCS4_ToDigit
289# define _PyUnicode_ToLowercase _PyUnicodeUCS4_ToLowercase
290# define _PyUnicode_ToNumeric _PyUnicodeUCS4_ToNumeric
291# define _PyUnicode_ToTitlecase _PyUnicodeUCS4_ToTitlecase
292# define _PyUnicode_ToUppercase _PyUnicodeUCS4_ToUppercase
293
294
295#endif
296
Guido van Rossumd8225182000-03-10 22:33:05 +0000297/* --- Internal Unicode Operations ---------------------------------------- */
298
299/* If you want Python to use the compiler's wctype.h functions instead
Barry Warsaw51ac5802000-03-20 16:36:48 +0000300 of the ones supplied with Python, define WANT_WCTYPE_FUNCTIONS or
Raymond Hettinger57341c32004-10-31 05:46:59 +0000301 configure Python using --with-wctype-functions. This reduces the
Barry Warsaw51ac5802000-03-20 16:36:48 +0000302 interpreter's code size. */
Guido van Rossumd8225182000-03-10 22:33:05 +0000303
304#if defined(HAVE_USABLE_WCHAR_T) && defined(WANT_WCTYPE_FUNCTIONS)
305
Marc-André Lemburg5e6007c2001-09-19 11:21:03 +0000306#include <wctype.h>
Guido van Rossumd8225182000-03-10 22:33:05 +0000307
308#define Py_UNICODE_ISSPACE(ch) iswspace(ch)
309
310#define Py_UNICODE_ISLOWER(ch) iswlower(ch)
311#define Py_UNICODE_ISUPPER(ch) iswupper(ch)
312#define Py_UNICODE_ISTITLE(ch) _PyUnicode_IsTitlecase(ch)
313#define Py_UNICODE_ISLINEBREAK(ch) _PyUnicode_IsLinebreak(ch)
314
315#define Py_UNICODE_TOLOWER(ch) towlower(ch)
316#define Py_UNICODE_TOUPPER(ch) towupper(ch)
317#define Py_UNICODE_TOTITLE(ch) _PyUnicode_ToTitlecase(ch)
318
319#define Py_UNICODE_ISDECIMAL(ch) _PyUnicode_IsDecimalDigit(ch)
320#define Py_UNICODE_ISDIGIT(ch) _PyUnicode_IsDigit(ch)
321#define Py_UNICODE_ISNUMERIC(ch) _PyUnicode_IsNumeric(ch)
322
323#define Py_UNICODE_TODECIMAL(ch) _PyUnicode_ToDecimalDigit(ch)
324#define Py_UNICODE_TODIGIT(ch) _PyUnicode_ToDigit(ch)
325#define Py_UNICODE_TONUMERIC(ch) _PyUnicode_ToNumeric(ch)
326
Marc-André Lemburgf03e7412000-07-05 09:45:59 +0000327#define Py_UNICODE_ISALPHA(ch) iswalpha(ch)
328
Guido van Rossumd8225182000-03-10 22:33:05 +0000329#else
330
331#define Py_UNICODE_ISSPACE(ch) _PyUnicode_IsWhitespace(ch)
332
333#define Py_UNICODE_ISLOWER(ch) _PyUnicode_IsLowercase(ch)
334#define Py_UNICODE_ISUPPER(ch) _PyUnicode_IsUppercase(ch)
335#define Py_UNICODE_ISTITLE(ch) _PyUnicode_IsTitlecase(ch)
336#define Py_UNICODE_ISLINEBREAK(ch) _PyUnicode_IsLinebreak(ch)
337
338#define Py_UNICODE_TOLOWER(ch) _PyUnicode_ToLowercase(ch)
339#define Py_UNICODE_TOUPPER(ch) _PyUnicode_ToUppercase(ch)
340#define Py_UNICODE_TOTITLE(ch) _PyUnicode_ToTitlecase(ch)
341
342#define Py_UNICODE_ISDECIMAL(ch) _PyUnicode_IsDecimalDigit(ch)
343#define Py_UNICODE_ISDIGIT(ch) _PyUnicode_IsDigit(ch)
344#define Py_UNICODE_ISNUMERIC(ch) _PyUnicode_IsNumeric(ch)
345
346#define Py_UNICODE_TODECIMAL(ch) _PyUnicode_ToDecimalDigit(ch)
347#define Py_UNICODE_TODIGIT(ch) _PyUnicode_ToDigit(ch)
348#define Py_UNICODE_TONUMERIC(ch) _PyUnicode_ToNumeric(ch)
349
Marc-André Lemburgf03e7412000-07-05 09:45:59 +0000350#define Py_UNICODE_ISALPHA(ch) _PyUnicode_IsAlpha(ch)
Guido van Rossumd8225182000-03-10 22:33:05 +0000351
Marc-André Lemburgf03e7412000-07-05 09:45:59 +0000352#endif
Marc-André Lemburga9c103b2000-07-03 10:52:13 +0000353
354#define Py_UNICODE_ISALNUM(ch) \
355 (Py_UNICODE_ISALPHA(ch) || \
356 Py_UNICODE_ISDECIMAL(ch) || \
357 Py_UNICODE_ISDIGIT(ch) || \
358 Py_UNICODE_ISNUMERIC(ch))
359
Thomas Wouters4d70c3d2006-06-08 14:42:34 +0000360#define Py_UNICODE_COPY(target, source, length) \
361 Py_MEMCPY((target), (source), (length)*sizeof(Py_UNICODE))
Guido van Rossumd8225182000-03-10 22:33:05 +0000362
363#define Py_UNICODE_FILL(target, value, length) do\
Thomas Wouters477c8d52006-05-27 19:21:47 +0000364 {Py_ssize_t i_; Py_UNICODE *t_ = (target); Py_UNICODE v_ = (value);\
365 for (i_ = 0; i_ < (length); i_++) t_[i_] = v_;\
366 } while (0)
Guido van Rossumd8225182000-03-10 22:33:05 +0000367
Thomas Wouters477c8d52006-05-27 19:21:47 +0000368/* check if substring matches at given offset. the offset must be
369 valid, and the substring must not be empty */
370#define Py_UNICODE_MATCH(string, offset, substring) \
371 ((*((string)->str + (offset)) == *((substring)->str)) && \
372 ((*((string)->str + (offset) + (substring)->length-1) == *((substring)->str + (substring)->length-1))) && \
373 !memcmp((string)->str + (offset), (substring)->str, (substring)->length*sizeof(Py_UNICODE)))
Guido van Rossumd8225182000-03-10 22:33:05 +0000374
Barry Warsaw51ac5802000-03-20 16:36:48 +0000375#ifdef __cplusplus
376extern "C" {
377#endif
378
Guido van Rossumd8225182000-03-10 22:33:05 +0000379/* --- Unicode Type ------------------------------------------------------- */
380
381typedef struct {
382 PyObject_HEAD
Martin v. Löwis18e16552006-02-15 17:27:45 +0000383 Py_ssize_t length; /* Length of raw Unicode data in buffer */
Guido van Rossumd8225182000-03-10 22:33:05 +0000384 Py_UNICODE *str; /* Raw Unicode buffer */
385 long hash; /* Hash value; -1 if not set */
Marc-André Lemburgbff879c2000-08-03 18:46:08 +0000386 PyObject *defenc; /* (Default) Encoded version as Python
387 string, or NULL; this is used for
388 implementing the buffer protocol */
Guido van Rossumd8225182000-03-10 22:33:05 +0000389} PyUnicodeObject;
390
Mark Hammond91a681d2002-08-12 07:21:58 +0000391PyAPI_DATA(PyTypeObject) PyUnicode_Type;
Guido van Rossumd8225182000-03-10 22:33:05 +0000392
Guido van Rossum5eef77a2001-08-30 03:08:07 +0000393#define PyUnicode_Check(op) PyObject_TypeCheck(op, &PyUnicode_Type)
Tim Peters78e0fc72001-09-11 03:07:38 +0000394#define PyUnicode_CheckExact(op) ((op)->ob_type == &PyUnicode_Type)
Guido van Rossumd8225182000-03-10 22:33:05 +0000395
396/* Fast access macros */
397#define PyUnicode_GET_SIZE(op) \
398 (((PyUnicodeObject *)(op))->length)
399#define PyUnicode_GET_DATA_SIZE(op) \
400 (((PyUnicodeObject *)(op))->length * sizeof(Py_UNICODE))
401#define PyUnicode_AS_UNICODE(op) \
402 (((PyUnicodeObject *)(op))->str)
403#define PyUnicode_AS_DATA(op) \
404 ((const char *)((PyUnicodeObject *)(op))->str)
405
406/* --- Constants ---------------------------------------------------------- */
407
408/* This Unicode character will be used as replacement character during
409 decoding if the errors argument is set to "replace". Note: the
410 Unicode character U+FFFD is the official REPLACEMENT CHARACTER in
411 Unicode 3.0. */
412
413#define Py_UNICODE_REPLACEMENT_CHARACTER ((Py_UNICODE) 0xFFFD)
414
415/* === Public API ========================================================= */
416
417/* --- Plain Py_UNICODE --------------------------------------------------- */
418
419/* Create a Unicode Object from the Py_UNICODE buffer u of the given
Marc-André Lemburg8155e0e2001-04-23 14:44:21 +0000420 size.
421
422 u may be NULL which causes the contents to be undefined. It is the
423 user's responsibility to fill in the needed data afterwards. Note
424 that modifying the Unicode object contents after construction is
425 only allowed if u was set to NULL.
Guido van Rossumd8225182000-03-10 22:33:05 +0000426
427 The buffer is copied into the new object. */
428
Mark Hammond91a681d2002-08-12 07:21:58 +0000429PyAPI_FUNC(PyObject*) PyUnicode_FromUnicode(
Guido van Rossumd8225182000-03-10 22:33:05 +0000430 const Py_UNICODE *u, /* Unicode buffer */
Martin v. Löwis18e16552006-02-15 17:27:45 +0000431 Py_ssize_t size /* size of buffer */
Guido van Rossumd8225182000-03-10 22:33:05 +0000432 );
433
434/* Return a read-only pointer to the Unicode object's internal
435 Py_UNICODE buffer. */
436
Mark Hammond91a681d2002-08-12 07:21:58 +0000437PyAPI_FUNC(Py_UNICODE *) PyUnicode_AsUnicode(
Guido van Rossumd8225182000-03-10 22:33:05 +0000438 PyObject *unicode /* Unicode object */
439 );
440
441/* Get the length of the Unicode object. */
442
Martin v. Löwis18e16552006-02-15 17:27:45 +0000443PyAPI_FUNC(Py_ssize_t) PyUnicode_GetSize(
Guido van Rossumd8225182000-03-10 22:33:05 +0000444 PyObject *unicode /* Unicode object */
445 );
446
Martin v. Löwisce9b5a52001-06-27 06:28:56 +0000447/* Get the maximum ordinal for a Unicode character. */
Mark Hammond91a681d2002-08-12 07:21:58 +0000448PyAPI_FUNC(Py_UNICODE) PyUnicode_GetMax(void);
Martin v. Löwisce9b5a52001-06-27 06:28:56 +0000449
Guido van Rossum52c23592000-04-10 13:41:41 +0000450/* Resize an already allocated Unicode object to the new size length.
451
452 *unicode is modified to point to the new (resized) object and 0
453 returned on success.
454
455 This API may only be called by the function which also called the
456 Unicode constructor. The refcount on the object must be 1. Otherwise,
457 an error is returned.
458
459 Error handling is implemented as follows: an exception is set, -1
460 is returned and *unicode left untouched.
461
462*/
463
Mark Hammond91a681d2002-08-12 07:21:58 +0000464PyAPI_FUNC(int) PyUnicode_Resize(
Guido van Rossum52c23592000-04-10 13:41:41 +0000465 PyObject **unicode, /* Pointer to the Unicode object */
Martin v. Löwis18e16552006-02-15 17:27:45 +0000466 Py_ssize_t length /* New length */
Guido van Rossum52c23592000-04-10 13:41:41 +0000467 );
468
Guido van Rossumd8225182000-03-10 22:33:05 +0000469/* Coerce obj to an Unicode object and return a reference with
470 *incremented* refcount.
471
472 Coercion is done in the following way:
473
Guido van Rossumb8c65bc2001-10-19 02:01:31 +0000474 1. String and other char buffer compatible objects are decoded
Fred Drakecb093fe2000-05-09 19:51:53 +0000475 under the assumptions that they contain data using the current
476 default encoding. Decoding is done in "strict" mode.
Guido van Rossumd8225182000-03-10 22:33:05 +0000477
Guido van Rossumb8c65bc2001-10-19 02:01:31 +0000478 2. All other objects (including Unicode objects) raise an
479 exception.
Guido van Rossumd8225182000-03-10 22:33:05 +0000480
481 The API returns NULL in case of an error. The caller is responsible
482 for decref'ing the returned objects.
483
484*/
485
Mark Hammond91a681d2002-08-12 07:21:58 +0000486PyAPI_FUNC(PyObject*) PyUnicode_FromEncodedObject(
Marc-André Lemburg5a5c81a2000-07-07 13:46:42 +0000487 register PyObject *obj, /* Object */
488 const char *encoding, /* encoding */
489 const char *errors /* error handling */
490 );
491
Guido van Rossumb8c65bc2001-10-19 02:01:31 +0000492/* Coerce obj to an Unicode object and return a reference with
Marc-André Lemburg5a5c81a2000-07-07 13:46:42 +0000493 *incremented* refcount.
Guido van Rossumb8c65bc2001-10-19 02:01:31 +0000494
495 Unicode objects are passed back as-is (subclasses are converted to
496 true Unicode objects), all other objects are delegated to
497 PyUnicode_FromEncodedObject(obj, NULL, "strict") which results in
498 using the default encoding as basis for decoding the object.
Marc-André Lemburg5a5c81a2000-07-07 13:46:42 +0000499
500 The API returns NULL in case of an error. The caller is responsible
501 for decref'ing the returned objects.
502
503*/
504
Mark Hammond91a681d2002-08-12 07:21:58 +0000505PyAPI_FUNC(PyObject*) PyUnicode_FromObject(
Guido van Rossumd8225182000-03-10 22:33:05 +0000506 register PyObject *obj /* Object */
507 );
508
509/* --- wchar_t support for platforms which support it --------------------- */
510
511#ifdef HAVE_WCHAR_H
512
513/* Create a Unicode Object from the whcar_t buffer w of the given
514 size.
515
516 The buffer is copied into the new object. */
517
Mark Hammond91a681d2002-08-12 07:21:58 +0000518PyAPI_FUNC(PyObject*) PyUnicode_FromWideChar(
Guido van Rossumd8225182000-03-10 22:33:05 +0000519 register const wchar_t *w, /* wchar_t buffer */
Martin v. Löwis18e16552006-02-15 17:27:45 +0000520 Py_ssize_t size /* size of buffer */
Guido van Rossumd8225182000-03-10 22:33:05 +0000521 );
522
Marc-André Lemburga9cadcd2004-11-22 13:02:31 +0000523/* Copies the Unicode Object contents into the wchar_t buffer w. At
Guido van Rossumd8225182000-03-10 22:33:05 +0000524 most size wchar_t characters are copied.
525
Marc-André Lemburga9cadcd2004-11-22 13:02:31 +0000526 Note that the resulting wchar_t string may or may not be
527 0-terminated. It is the responsibility of the caller to make sure
528 that the wchar_t string is 0-terminated in case this is required by
529 the application.
530
531 Returns the number of wchar_t characters copied (excluding a
532 possibly trailing 0-termination character) or -1 in case of an
Guido van Rossumd8225182000-03-10 22:33:05 +0000533 error. */
534
Martin v. Löwis18e16552006-02-15 17:27:45 +0000535PyAPI_FUNC(Py_ssize_t) PyUnicode_AsWideChar(
Guido van Rossumd8225182000-03-10 22:33:05 +0000536 PyUnicodeObject *unicode, /* Unicode object */
537 register wchar_t *w, /* wchar_t buffer */
Martin v. Löwis18e16552006-02-15 17:27:45 +0000538 Py_ssize_t size /* size of buffer */
Guido van Rossumd8225182000-03-10 22:33:05 +0000539 );
540
541#endif
542
Marc-André Lemburgcc8764c2002-08-11 12:23:04 +0000543/* --- Unicode ordinals --------------------------------------------------- */
544
545/* Create a Unicode Object from the given Unicode code point ordinal.
546
547 The ordinal must be in range(0x10000) on narrow Python builds
548 (UCS2), and range(0x110000) on wide builds (UCS4). A ValueError is
549 raised in case it is not.
550
551*/
552
Marc-André Lemburg9c329de2002-08-12 08:19:10 +0000553PyAPI_FUNC(PyObject*) PyUnicode_FromOrdinal(int ordinal);
Marc-André Lemburgcc8764c2002-08-11 12:23:04 +0000554
Guido van Rossumd8225182000-03-10 22:33:05 +0000555/* === Builtin Codecs =====================================================
556
557 Many of these APIs take two arguments encoding and errors. These
558 parameters encoding and errors have the same semantics as the ones
559 of the builtin unicode() API.
560
Fred Drakecb093fe2000-05-09 19:51:53 +0000561 Setting encoding to NULL causes the default encoding to be used.
Guido van Rossumd8225182000-03-10 22:33:05 +0000562
563 Error handling is set by errors which may also be set to NULL
564 meaning to use the default handling defined for the codec. Default
565 error handling for all builtin codecs is "strict" (ValueErrors are
566 raised).
567
568 The codecs all use a similar interface. Only deviation from the
569 generic ones are documented.
570
571*/
572
Fred Drakecb093fe2000-05-09 19:51:53 +0000573/* --- Manage the default encoding ---------------------------------------- */
574
Jeremy Hylton3ce45382001-07-30 22:34:24 +0000575/* Return a Python string holding the default encoded value of the
576 Unicode object.
577
578 The resulting string is cached in the Unicode object for subsequent
579 usage by this function. The cached version is needed to implement
580 the character buffer interface and will live (at least) as long as
581 the Unicode object itself.
582
583 The refcount of the string is *not* incremented.
584
585 *** Exported for internal use by the interpreter only !!! ***
586
587*/
588
Mark Hammond91a681d2002-08-12 07:21:58 +0000589PyAPI_FUNC(PyObject *) _PyUnicode_AsDefaultEncodedString(
Jeremy Hylton3ce45382001-07-30 22:34:24 +0000590 PyObject *, const char *);
591
Fred Drakecb093fe2000-05-09 19:51:53 +0000592/* Returns the currently active default encoding.
593
594 The default encoding is currently implemented as run-time settable
595 process global. This may change in future versions of the
596 interpreter to become a parameter which is managed on a per-thread
597 basis.
598
599 */
600
Mark Hammond91a681d2002-08-12 07:21:58 +0000601PyAPI_FUNC(const char*) PyUnicode_GetDefaultEncoding(void);
Fred Drakecb093fe2000-05-09 19:51:53 +0000602
603/* Sets the currently active default encoding.
604
605 Returns 0 on success, -1 in case of an error.
606
607 */
608
Mark Hammond91a681d2002-08-12 07:21:58 +0000609PyAPI_FUNC(int) PyUnicode_SetDefaultEncoding(
Fred Drakecb093fe2000-05-09 19:51:53 +0000610 const char *encoding /* Encoding name in standard form */
611 );
612
Guido van Rossumd8225182000-03-10 22:33:05 +0000613/* --- Generic Codecs ----------------------------------------------------- */
614
615/* Create a Unicode object by decoding the encoded string s of the
616 given size. */
617
Mark Hammond91a681d2002-08-12 07:21:58 +0000618PyAPI_FUNC(PyObject*) PyUnicode_Decode(
Guido van Rossumd8225182000-03-10 22:33:05 +0000619 const char *s, /* encoded string */
Martin v. Löwis18e16552006-02-15 17:27:45 +0000620 Py_ssize_t size, /* size of buffer */
Guido van Rossumd8225182000-03-10 22:33:05 +0000621 const char *encoding, /* encoding */
622 const char *errors /* error handling */
623 );
624
625/* Encodes a Py_UNICODE buffer of the given size and returns a
626 Python string object. */
627
Mark Hammond91a681d2002-08-12 07:21:58 +0000628PyAPI_FUNC(PyObject*) PyUnicode_Encode(
Guido van Rossumd8225182000-03-10 22:33:05 +0000629 const Py_UNICODE *s, /* Unicode char buffer */
Martin v. Löwis18e16552006-02-15 17:27:45 +0000630 Py_ssize_t size, /* number of Py_UNICODE chars to encode */
Guido van Rossumd8225182000-03-10 22:33:05 +0000631 const char *encoding, /* encoding */
632 const char *errors /* error handling */
633 );
634
Marc-André Lemburgd2d45982004-07-08 17:57:32 +0000635/* Encodes a Unicode object and returns the result as Python
636 object. */
637
638PyAPI_FUNC(PyObject*) PyUnicode_AsEncodedObject(
639 PyObject *unicode, /* Unicode object */
640 const char *encoding, /* encoding */
641 const char *errors /* error handling */
642 );
643
Guido van Rossumd8225182000-03-10 22:33:05 +0000644/* Encodes a Unicode object and returns the result as Python string
645 object. */
646
Mark Hammond91a681d2002-08-12 07:21:58 +0000647PyAPI_FUNC(PyObject*) PyUnicode_AsEncodedString(
Guido van Rossumd8225182000-03-10 22:33:05 +0000648 PyObject *unicode, /* Unicode object */
649 const char *encoding, /* encoding */
650 const char *errors /* error handling */
651 );
652
Marc-André Lemburgc60e6f72001-09-20 10:35:46 +0000653/* --- UTF-7 Codecs ------------------------------------------------------- */
654
Mark Hammond91a681d2002-08-12 07:21:58 +0000655PyAPI_FUNC(PyObject*) PyUnicode_DecodeUTF7(
Marc-André Lemburgc60e6f72001-09-20 10:35:46 +0000656 const char *string, /* UTF-7 encoded string */
Martin v. Löwis18e16552006-02-15 17:27:45 +0000657 Py_ssize_t length, /* size of string */
Marc-André Lemburgc60e6f72001-09-20 10:35:46 +0000658 const char *errors /* error handling */
659 );
660
Mark Hammond91a681d2002-08-12 07:21:58 +0000661PyAPI_FUNC(PyObject*) PyUnicode_EncodeUTF7(
Marc-André Lemburgc60e6f72001-09-20 10:35:46 +0000662 const Py_UNICODE *data, /* Unicode char buffer */
Martin v. Löwis18e16552006-02-15 17:27:45 +0000663 Py_ssize_t length, /* number of Py_UNICODE chars to encode */
Marc-André Lemburgc60e6f72001-09-20 10:35:46 +0000664 int encodeSetO, /* force the encoder to encode characters in
665 Set O, as described in RFC2152 */
666 int encodeWhiteSpace, /* force the encoder to encode space, tab,
667 carriage return and linefeed characters */
668 const char *errors /* error handling */
669 );
670
Guido van Rossumd8225182000-03-10 22:33:05 +0000671/* --- UTF-8 Codecs ------------------------------------------------------- */
672
Mark Hammond91a681d2002-08-12 07:21:58 +0000673PyAPI_FUNC(PyObject*) PyUnicode_DecodeUTF8(
Guido van Rossumd8225182000-03-10 22:33:05 +0000674 const char *string, /* UTF-8 encoded string */
Martin v. Löwis18e16552006-02-15 17:27:45 +0000675 Py_ssize_t length, /* size of string */
Guido van Rossumd8225182000-03-10 22:33:05 +0000676 const char *errors /* error handling */
677 );
678
Walter Dörwald69652032004-09-07 20:24:22 +0000679PyAPI_FUNC(PyObject*) PyUnicode_DecodeUTF8Stateful(
680 const char *string, /* UTF-8 encoded string */
Martin v. Löwis18e16552006-02-15 17:27:45 +0000681 Py_ssize_t length, /* size of string */
Walter Dörwald69652032004-09-07 20:24:22 +0000682 const char *errors, /* error handling */
Martin v. Löwis18e16552006-02-15 17:27:45 +0000683 Py_ssize_t *consumed /* bytes consumed */
Walter Dörwald69652032004-09-07 20:24:22 +0000684 );
685
Mark Hammond91a681d2002-08-12 07:21:58 +0000686PyAPI_FUNC(PyObject*) PyUnicode_AsUTF8String(
Guido van Rossumd8225182000-03-10 22:33:05 +0000687 PyObject *unicode /* Unicode object */
688 );
689
Mark Hammond91a681d2002-08-12 07:21:58 +0000690PyAPI_FUNC(PyObject*) PyUnicode_EncodeUTF8(
Guido van Rossumd8225182000-03-10 22:33:05 +0000691 const Py_UNICODE *data, /* Unicode char buffer */
Martin v. Löwis18e16552006-02-15 17:27:45 +0000692 Py_ssize_t length, /* number of Py_UNICODE chars to encode */
Guido van Rossumd8225182000-03-10 22:33:05 +0000693 const char *errors /* error handling */
694 );
695
696/* --- UTF-16 Codecs ------------------------------------------------------ */
697
Guido van Rossum9e896b32000-04-05 20:11:21 +0000698/* Decodes length bytes from a UTF-16 encoded buffer string and returns
Guido van Rossumd8225182000-03-10 22:33:05 +0000699 the corresponding Unicode object.
700
701 errors (if non-NULL) defines the error handling. It defaults
702 to "strict".
703
704 If byteorder is non-NULL, the decoder starts decoding using the
705 given byte order:
706
707 *byteorder == -1: little endian
708 *byteorder == 0: native order
709 *byteorder == 1: big endian
710
Marc-André Lemburg489b56e2001-05-21 20:30:15 +0000711 In native mode, the first two bytes of the stream are checked for a
712 BOM mark. If found, the BOM mark is analysed, the byte order
713 adjusted and the BOM skipped. In the other modes, no BOM mark
714 interpretation is done. After completion, *byteorder is set to the
715 current byte order at the end of input data.
Guido van Rossumd8225182000-03-10 22:33:05 +0000716
717 If byteorder is NULL, the codec starts in native order mode.
718
719*/
720
Mark Hammond91a681d2002-08-12 07:21:58 +0000721PyAPI_FUNC(PyObject*) PyUnicode_DecodeUTF16(
Guido van Rossumd8225182000-03-10 22:33:05 +0000722 const char *string, /* UTF-16 encoded string */
Martin v. Löwis18e16552006-02-15 17:27:45 +0000723 Py_ssize_t length, /* size of string */
Guido van Rossumd8225182000-03-10 22:33:05 +0000724 const char *errors, /* error handling */
725 int *byteorder /* pointer to byteorder to use
726 0=native;-1=LE,1=BE; updated on
727 exit */
728 );
729
Walter Dörwald69652032004-09-07 20:24:22 +0000730PyAPI_FUNC(PyObject*) PyUnicode_DecodeUTF16Stateful(
731 const char *string, /* UTF-16 encoded string */
Martin v. Löwis18e16552006-02-15 17:27:45 +0000732 Py_ssize_t length, /* size of string */
Walter Dörwald69652032004-09-07 20:24:22 +0000733 const char *errors, /* error handling */
734 int *byteorder, /* pointer to byteorder to use
735 0=native;-1=LE,1=BE; updated on
736 exit */
Martin v. Löwis18e16552006-02-15 17:27:45 +0000737 Py_ssize_t *consumed /* bytes consumed */
Walter Dörwald69652032004-09-07 20:24:22 +0000738 );
739
Guido van Rossumd8225182000-03-10 22:33:05 +0000740/* Returns a Python string using the UTF-16 encoding in native byte
741 order. The string always starts with a BOM mark. */
742
Mark Hammond91a681d2002-08-12 07:21:58 +0000743PyAPI_FUNC(PyObject*) PyUnicode_AsUTF16String(
Guido van Rossumd8225182000-03-10 22:33:05 +0000744 PyObject *unicode /* Unicode object */
745 );
746
747/* Returns a Python string object holding the UTF-16 encoded value of
Guido van Rossum9e896b32000-04-05 20:11:21 +0000748 the Unicode data.
Guido van Rossumd8225182000-03-10 22:33:05 +0000749
750 If byteorder is not 0, output is written according to the following
751 byte order:
752
753 byteorder == -1: little endian
754 byteorder == 0: native byte order (writes a BOM mark)
755 byteorder == 1: big endian
756
757 If byteorder is 0, the output string will always start with the
758 Unicode BOM mark (U+FEFF). In the other two modes, no BOM mark is
759 prepended.
760
761 Note that Py_UNICODE data is being interpreted as UTF-16 reduced to
762 UCS-2. This trick makes it possible to add full UTF-16 capabilities
Thomas Wouters7e474022000-07-16 12:04:32 +0000763 at a later point without compromising the APIs.
Guido van Rossumd8225182000-03-10 22:33:05 +0000764
765*/
766
Mark Hammond91a681d2002-08-12 07:21:58 +0000767PyAPI_FUNC(PyObject*) PyUnicode_EncodeUTF16(
Guido van Rossumd8225182000-03-10 22:33:05 +0000768 const Py_UNICODE *data, /* Unicode char buffer */
Martin v. Löwis18e16552006-02-15 17:27:45 +0000769 Py_ssize_t length, /* number of Py_UNICODE chars to encode */
Guido van Rossumd8225182000-03-10 22:33:05 +0000770 const char *errors, /* error handling */
771 int byteorder /* byteorder to use 0=BOM+native;-1=LE,1=BE */
772 );
773
774/* --- Unicode-Escape Codecs ---------------------------------------------- */
775
Mark Hammond91a681d2002-08-12 07:21:58 +0000776PyAPI_FUNC(PyObject*) PyUnicode_DecodeUnicodeEscape(
Guido van Rossumd8225182000-03-10 22:33:05 +0000777 const char *string, /* Unicode-Escape encoded string */
Martin v. Löwis18e16552006-02-15 17:27:45 +0000778 Py_ssize_t length, /* size of string */
Guido van Rossumd8225182000-03-10 22:33:05 +0000779 const char *errors /* error handling */
780 );
781
Mark Hammond91a681d2002-08-12 07:21:58 +0000782PyAPI_FUNC(PyObject*) PyUnicode_AsUnicodeEscapeString(
Guido van Rossumd8225182000-03-10 22:33:05 +0000783 PyObject *unicode /* Unicode object */
784 );
785
Mark Hammond91a681d2002-08-12 07:21:58 +0000786PyAPI_FUNC(PyObject*) PyUnicode_EncodeUnicodeEscape(
Guido van Rossumd8225182000-03-10 22:33:05 +0000787 const Py_UNICODE *data, /* Unicode char buffer */
Martin v. Löwis18e16552006-02-15 17:27:45 +0000788 Py_ssize_t length /* Number of Py_UNICODE chars to encode */
Guido van Rossumd8225182000-03-10 22:33:05 +0000789 );
790
791/* --- Raw-Unicode-Escape Codecs ------------------------------------------ */
792
Mark Hammond91a681d2002-08-12 07:21:58 +0000793PyAPI_FUNC(PyObject*) PyUnicode_DecodeRawUnicodeEscape(
Guido van Rossumd8225182000-03-10 22:33:05 +0000794 const char *string, /* Raw-Unicode-Escape encoded string */
Martin v. Löwis18e16552006-02-15 17:27:45 +0000795 Py_ssize_t length, /* size of string */
Guido van Rossumd8225182000-03-10 22:33:05 +0000796 const char *errors /* error handling */
797 );
798
Mark Hammond91a681d2002-08-12 07:21:58 +0000799PyAPI_FUNC(PyObject*) PyUnicode_AsRawUnicodeEscapeString(
Guido van Rossumd8225182000-03-10 22:33:05 +0000800 PyObject *unicode /* Unicode object */
801 );
802
Mark Hammond91a681d2002-08-12 07:21:58 +0000803PyAPI_FUNC(PyObject*) PyUnicode_EncodeRawUnicodeEscape(
Guido van Rossumd8225182000-03-10 22:33:05 +0000804 const Py_UNICODE *data, /* Unicode char buffer */
Martin v. Löwis18e16552006-02-15 17:27:45 +0000805 Py_ssize_t length /* Number of Py_UNICODE chars to encode */
Guido van Rossumd8225182000-03-10 22:33:05 +0000806 );
807
Walter Dörwalda47d1c02005-08-30 10:23:14 +0000808/* --- Unicode Internal Codec ---------------------------------------------
809
810 Only for internal use in _codecsmodule.c */
811
812PyObject *_PyUnicode_DecodeUnicodeInternal(
813 const char *string,
Martin v. Löwis18e16552006-02-15 17:27:45 +0000814 Py_ssize_t length,
Walter Dörwalda47d1c02005-08-30 10:23:14 +0000815 const char *errors
816 );
817
Guido van Rossumd8225182000-03-10 22:33:05 +0000818/* --- Latin-1 Codecs -----------------------------------------------------
819
820 Note: Latin-1 corresponds to the first 256 Unicode ordinals.
821
822*/
823
Mark Hammond91a681d2002-08-12 07:21:58 +0000824PyAPI_FUNC(PyObject*) PyUnicode_DecodeLatin1(
Guido van Rossumd8225182000-03-10 22:33:05 +0000825 const char *string, /* Latin-1 encoded string */
Martin v. Löwis18e16552006-02-15 17:27:45 +0000826 Py_ssize_t length, /* size of string */
Guido van Rossumd8225182000-03-10 22:33:05 +0000827 const char *errors /* error handling */
828 );
829
Mark Hammond91a681d2002-08-12 07:21:58 +0000830PyAPI_FUNC(PyObject*) PyUnicode_AsLatin1String(
Guido van Rossumd8225182000-03-10 22:33:05 +0000831 PyObject *unicode /* Unicode object */
832 );
833
Mark Hammond91a681d2002-08-12 07:21:58 +0000834PyAPI_FUNC(PyObject*) PyUnicode_EncodeLatin1(
Guido van Rossumd8225182000-03-10 22:33:05 +0000835 const Py_UNICODE *data, /* Unicode char buffer */
Martin v. Löwis18e16552006-02-15 17:27:45 +0000836 Py_ssize_t length, /* Number of Py_UNICODE chars to encode */
Guido van Rossumd8225182000-03-10 22:33:05 +0000837 const char *errors /* error handling */
838 );
839
840/* --- ASCII Codecs -------------------------------------------------------
841
842 Only 7-bit ASCII data is excepted. All other codes generate errors.
843
844*/
845
Mark Hammond91a681d2002-08-12 07:21:58 +0000846PyAPI_FUNC(PyObject*) PyUnicode_DecodeASCII(
Guido van Rossumd8225182000-03-10 22:33:05 +0000847 const char *string, /* ASCII encoded string */
Martin v. Löwis18e16552006-02-15 17:27:45 +0000848 Py_ssize_t length, /* size of string */
Guido van Rossumd8225182000-03-10 22:33:05 +0000849 const char *errors /* error handling */
850 );
851
Mark Hammond91a681d2002-08-12 07:21:58 +0000852PyAPI_FUNC(PyObject*) PyUnicode_AsASCIIString(
Guido van Rossumd8225182000-03-10 22:33:05 +0000853 PyObject *unicode /* Unicode object */
854 );
855
Mark Hammond91a681d2002-08-12 07:21:58 +0000856PyAPI_FUNC(PyObject*) PyUnicode_EncodeASCII(
Guido van Rossumd8225182000-03-10 22:33:05 +0000857 const Py_UNICODE *data, /* Unicode char buffer */
Martin v. Löwis18e16552006-02-15 17:27:45 +0000858 Py_ssize_t length, /* Number of Py_UNICODE chars to encode */
Guido van Rossumd8225182000-03-10 22:33:05 +0000859 const char *errors /* error handling */
860 );
861
862/* --- Character Map Codecs -----------------------------------------------
863
864 This codec uses mappings to encode and decode characters.
865
866 Decoding mappings must map single string characters to single
867 Unicode characters, integers (which are then interpreted as Unicode
868 ordinals) or None (meaning "undefined mapping" and causing an
869 error).
870
871 Encoding mappings must map single Unicode characters to single
872 string characters, integers (which are then interpreted as Latin-1
873 ordinals) or None (meaning "undefined mapping" and causing an
874 error).
875
876 If a character lookup fails with a LookupError, the character is
877 copied as-is meaning that its ordinal value will be interpreted as
878 Unicode or Latin-1 ordinal resp. Because of this mappings only need
879 to contain those mappings which map characters to different code
880 points.
881
882*/
883
Mark Hammond91a681d2002-08-12 07:21:58 +0000884PyAPI_FUNC(PyObject*) PyUnicode_DecodeCharmap(
Guido van Rossumd8225182000-03-10 22:33:05 +0000885 const char *string, /* Encoded string */
Martin v. Löwis18e16552006-02-15 17:27:45 +0000886 Py_ssize_t length, /* size of string */
Guido van Rossumd8225182000-03-10 22:33:05 +0000887 PyObject *mapping, /* character mapping
888 (char ordinal -> unicode ordinal) */
889 const char *errors /* error handling */
890 );
891
Mark Hammond91a681d2002-08-12 07:21:58 +0000892PyAPI_FUNC(PyObject*) PyUnicode_AsCharmapString(
Guido van Rossumd8225182000-03-10 22:33:05 +0000893 PyObject *unicode, /* Unicode object */
894 PyObject *mapping /* character mapping
895 (unicode ordinal -> char ordinal) */
896 );
897
Mark Hammond91a681d2002-08-12 07:21:58 +0000898PyAPI_FUNC(PyObject*) PyUnicode_EncodeCharmap(
Guido van Rossumd8225182000-03-10 22:33:05 +0000899 const Py_UNICODE *data, /* Unicode char buffer */
Martin v. Löwis18e16552006-02-15 17:27:45 +0000900 Py_ssize_t length, /* Number of Py_UNICODE chars to encode */
Guido van Rossumd8225182000-03-10 22:33:05 +0000901 PyObject *mapping, /* character mapping
902 (unicode ordinal -> char ordinal) */
903 const char *errors /* error handling */
904 );
905
906/* Translate a Py_UNICODE buffer of the given length by applying a
907 character mapping table to it and return the resulting Unicode
908 object.
909
910 The mapping table must map Unicode ordinal integers to Unicode
911 ordinal integers or None (causing deletion of the character).
912
913 Mapping tables may be dictionaries or sequences. Unmapped character
914 ordinals (ones which cause a LookupError) are left untouched and
915 are copied as-is.
916
917*/
918
Mark Hammond91a681d2002-08-12 07:21:58 +0000919PyAPI_FUNC(PyObject *) PyUnicode_TranslateCharmap(
Guido van Rossumd8225182000-03-10 22:33:05 +0000920 const Py_UNICODE *data, /* Unicode char buffer */
Martin v. Löwis18e16552006-02-15 17:27:45 +0000921 Py_ssize_t length, /* Number of Py_UNICODE chars to encode */
Guido van Rossumd8225182000-03-10 22:33:05 +0000922 PyObject *table, /* Translate table */
923 const char *errors /* error handling */
924 );
925
Guido van Rossumefec1152000-03-28 02:01:15 +0000926#ifdef MS_WIN32
Guido van Rossum24bdb042000-03-28 20:29:59 +0000927
Guido van Rossumefec1152000-03-28 02:01:15 +0000928/* --- MBCS codecs for Windows -------------------------------------------- */
Guido van Rossum24bdb042000-03-28 20:29:59 +0000929
Mark Hammond91a681d2002-08-12 07:21:58 +0000930PyAPI_FUNC(PyObject*) PyUnicode_DecodeMBCS(
Guido van Rossumefec1152000-03-28 02:01:15 +0000931 const char *string, /* MBCS encoded string */
Martin v. Löwis18e16552006-02-15 17:27:45 +0000932 Py_ssize_t length, /* size of string */
Guido van Rossumefec1152000-03-28 02:01:15 +0000933 const char *errors /* error handling */
934 );
935
Mark Hammond91a681d2002-08-12 07:21:58 +0000936PyAPI_FUNC(PyObject*) PyUnicode_AsMBCSString(
Guido van Rossumefec1152000-03-28 02:01:15 +0000937 PyObject *unicode /* Unicode object */
938 );
939
Mark Hammond91a681d2002-08-12 07:21:58 +0000940PyAPI_FUNC(PyObject*) PyUnicode_EncodeMBCS(
Guido van Rossumefec1152000-03-28 02:01:15 +0000941 const Py_UNICODE *data, /* Unicode char buffer */
Martin v. Löwis18e16552006-02-15 17:27:45 +0000942 Py_ssize_t length, /* Number of Py_UNICODE chars to encode */
Guido van Rossumefec1152000-03-28 02:01:15 +0000943 const char *errors /* error handling */
944 );
945
Guido van Rossumefec1152000-03-28 02:01:15 +0000946#endif /* MS_WIN32 */
Guido van Rossum24bdb042000-03-28 20:29:59 +0000947
Guido van Rossum9e896b32000-04-05 20:11:21 +0000948/* --- Decimal Encoder ---------------------------------------------------- */
949
950/* Takes a Unicode string holding a decimal value and writes it into
951 an output buffer using standard ASCII digit codes.
952
953 The output buffer has to provide at least length+1 bytes of storage
954 area. The output string is 0-terminated.
955
956 The encoder converts whitespace to ' ', decimal characters to their
957 corresponding ASCII digit and all other Latin-1 characters except
958 \0 as-is. Characters outside this range (Unicode ordinals 1-256)
959 are treated as errors. This includes embedded NULL bytes.
960
961 Error handling is defined by the errors argument:
962
963 NULL or "strict": raise a ValueError
964 "ignore": ignore the wrong characters (these are not copied to the
965 output buffer)
966 "replace": replaces illegal characters with '?'
967
968 Returns 0 on success, -1 on failure.
969
970*/
971
Mark Hammond91a681d2002-08-12 07:21:58 +0000972PyAPI_FUNC(int) PyUnicode_EncodeDecimal(
Guido van Rossum9e896b32000-04-05 20:11:21 +0000973 Py_UNICODE *s, /* Unicode buffer */
Martin v. Löwis18e16552006-02-15 17:27:45 +0000974 Py_ssize_t length, /* Number of Py_UNICODE chars to encode */
Guido van Rossum9e896b32000-04-05 20:11:21 +0000975 char *output, /* Output buffer; must have size >= length */
976 const char *errors /* error handling */
977 );
978
Guido van Rossumd8225182000-03-10 22:33:05 +0000979/* --- Methods & Slots ----------------------------------------------------
980
981 These are capable of handling Unicode objects and strings on input
982 (we refer to them as strings in the descriptions) and return
983 Unicode objects or integers as apporpriate. */
984
985/* Concat two strings giving a new Unicode string. */
986
Mark Hammond91a681d2002-08-12 07:21:58 +0000987PyAPI_FUNC(PyObject*) PyUnicode_Concat(
Guido van Rossumd8225182000-03-10 22:33:05 +0000988 PyObject *left, /* Left string */
989 PyObject *right /* Right string */
990 );
991
992/* Split a string giving a list of Unicode strings.
993
994 If sep is NULL, splitting will be done at all whitespace
995 substrings. Otherwise, splits occur at the given separator.
996
997 At most maxsplit splits will be done. If negative, no limit is set.
998
999 Separators are not included in the resulting list.
1000
1001*/
1002
Mark Hammond91a681d2002-08-12 07:21:58 +00001003PyAPI_FUNC(PyObject*) PyUnicode_Split(
Guido van Rossumd8225182000-03-10 22:33:05 +00001004 PyObject *s, /* String to split */
1005 PyObject *sep, /* String separator */
Martin v. Löwis18e16552006-02-15 17:27:45 +00001006 Py_ssize_t maxsplit /* Maxsplit count */
Guido van Rossumd8225182000-03-10 22:33:05 +00001007 );
1008
1009/* Dito, but split at line breaks.
1010
1011 CRLF is considered to be one line break. Line breaks are not
1012 included in the resulting list. */
1013
Mark Hammond91a681d2002-08-12 07:21:58 +00001014PyAPI_FUNC(PyObject*) PyUnicode_Splitlines(
Guido van Rossumd8225182000-03-10 22:33:05 +00001015 PyObject *s, /* String to split */
Guido van Rossum004d64f2000-04-11 15:39:46 +00001016 int keepends /* If true, line end markers are included */
Guido van Rossumd8225182000-03-10 22:33:05 +00001017 );
1018
Thomas Wouters477c8d52006-05-27 19:21:47 +00001019/* Partition a string using a given separator. */
1020
1021PyAPI_FUNC(PyObject*) PyUnicode_Partition(
1022 PyObject *s, /* String to partition */
1023 PyObject *sep /* String separator */
1024 );
1025
1026/* Partition a string using a given separator, searching from the end of the
1027 string. */
1028
1029PyAPI_FUNC(PyObject*) PyUnicode_RPartition(
1030 PyObject *s, /* String to partition */
1031 PyObject *sep /* String separator */
1032 );
1033
Hye-Shik Chang3ae811b2003-12-15 18:49:53 +00001034/* Split a string giving a list of Unicode strings.
1035
1036 If sep is NULL, splitting will be done at all whitespace
1037 substrings. Otherwise, splits occur at the given separator.
1038
1039 At most maxsplit splits will be done. But unlike PyUnicode_Split
1040 PyUnicode_RSplit splits from the end of the string. If negative,
1041 no limit is set.
1042
1043 Separators are not included in the resulting list.
1044
1045*/
1046
1047PyAPI_FUNC(PyObject*) PyUnicode_RSplit(
1048 PyObject *s, /* String to split */
1049 PyObject *sep, /* String separator */
Martin v. Löwis18e16552006-02-15 17:27:45 +00001050 Py_ssize_t maxsplit /* Maxsplit count */
Hye-Shik Chang3ae811b2003-12-15 18:49:53 +00001051 );
1052
Guido van Rossumd8225182000-03-10 22:33:05 +00001053/* Translate a string by applying a character mapping table to it and
1054 return the resulting Unicode object.
1055
1056 The mapping table must map Unicode ordinal integers to Unicode
1057 ordinal integers or None (causing deletion of the character).
1058
1059 Mapping tables may be dictionaries or sequences. Unmapped character
1060 ordinals (ones which cause a LookupError) are left untouched and
1061 are copied as-is.
1062
1063*/
1064
Mark Hammond91a681d2002-08-12 07:21:58 +00001065PyAPI_FUNC(PyObject *) PyUnicode_Translate(
Guido van Rossumd8225182000-03-10 22:33:05 +00001066 PyObject *str, /* String */
1067 PyObject *table, /* Translate table */
1068 const char *errors /* error handling */
1069 );
1070
1071/* Join a sequence of strings using the given separator and return
1072 the resulting Unicode string. */
1073
Mark Hammond91a681d2002-08-12 07:21:58 +00001074PyAPI_FUNC(PyObject*) PyUnicode_Join(
Guido van Rossumd8225182000-03-10 22:33:05 +00001075 PyObject *separator, /* Separator string */
1076 PyObject *seq /* Sequence object */
1077 );
1078
1079/* Return 1 if substr matches str[start:end] at the given tail end, 0
1080 otherwise. */
1081
Martin v. Löwis18e16552006-02-15 17:27:45 +00001082PyAPI_FUNC(Py_ssize_t) PyUnicode_Tailmatch(
Guido van Rossumd8225182000-03-10 22:33:05 +00001083 PyObject *str, /* String */
1084 PyObject *substr, /* Prefix or Suffix string */
Martin v. Löwis18e16552006-02-15 17:27:45 +00001085 Py_ssize_t start, /* Start index */
1086 Py_ssize_t end, /* Stop index */
Guido van Rossumd8225182000-03-10 22:33:05 +00001087 int direction /* Tail end: -1 prefix, +1 suffix */
1088 );
1089
1090/* Return the first position of substr in str[start:end] using the
Marc-André Lemburg4da6fd62002-05-29 11:33:13 +00001091 given search direction or -1 if not found. -2 is returned in case
1092 an error occurred and an exception is set. */
Guido van Rossumd8225182000-03-10 22:33:05 +00001093
Martin v. Löwis18e16552006-02-15 17:27:45 +00001094PyAPI_FUNC(Py_ssize_t) PyUnicode_Find(
Guido van Rossumd8225182000-03-10 22:33:05 +00001095 PyObject *str, /* String */
1096 PyObject *substr, /* Substring to find */
Martin v. Löwis18e16552006-02-15 17:27:45 +00001097 Py_ssize_t start, /* Start index */
1098 Py_ssize_t end, /* Stop index */
Guido van Rossumd8225182000-03-10 22:33:05 +00001099 int direction /* Find direction: +1 forward, -1 backward */
1100 );
1101
Barry Warsaw51ac5802000-03-20 16:36:48 +00001102/* Count the number of occurrences of substr in str[start:end]. */
Guido van Rossumd8225182000-03-10 22:33:05 +00001103
Martin v. Löwis18e16552006-02-15 17:27:45 +00001104PyAPI_FUNC(Py_ssize_t) PyUnicode_Count(
Guido van Rossumd8225182000-03-10 22:33:05 +00001105 PyObject *str, /* String */
1106 PyObject *substr, /* Substring to count */
Martin v. Löwis18e16552006-02-15 17:27:45 +00001107 Py_ssize_t start, /* Start index */
1108 Py_ssize_t end /* Stop index */
Guido van Rossumd8225182000-03-10 22:33:05 +00001109 );
1110
Barry Warsaw51ac5802000-03-20 16:36:48 +00001111/* Replace at most maxcount occurrences of substr in str with replstr
Guido van Rossumd8225182000-03-10 22:33:05 +00001112 and return the resulting Unicode object. */
1113
Mark Hammond91a681d2002-08-12 07:21:58 +00001114PyAPI_FUNC(PyObject *) PyUnicode_Replace(
Guido van Rossumd8225182000-03-10 22:33:05 +00001115 PyObject *str, /* String */
1116 PyObject *substr, /* Substring to find */
1117 PyObject *replstr, /* Substring to replace */
Martin v. Löwis18e16552006-02-15 17:27:45 +00001118 Py_ssize_t maxcount /* Max. number of replacements to apply;
Guido van Rossumd8225182000-03-10 22:33:05 +00001119 -1 = all */
1120 );
1121
1122/* Compare two strings and return -1, 0, 1 for less than, equal,
1123 greater than resp. */
1124
Mark Hammond91a681d2002-08-12 07:21:58 +00001125PyAPI_FUNC(int) PyUnicode_Compare(
Guido van Rossumd8225182000-03-10 22:33:05 +00001126 PyObject *left, /* Left string */
1127 PyObject *right /* Right string */
1128 );
1129
Thomas Wouters7e474022000-07-16 12:04:32 +00001130/* Apply a argument tuple or dictionary to a format string and return
Guido van Rossumd8225182000-03-10 22:33:05 +00001131 the resulting Unicode string. */
1132
Mark Hammond91a681d2002-08-12 07:21:58 +00001133PyAPI_FUNC(PyObject *) PyUnicode_Format(
Guido van Rossumd8225182000-03-10 22:33:05 +00001134 PyObject *format, /* Format string */
1135 PyObject *args /* Argument tuple or dictionary */
1136 );
1137
Guido van Rossumd0d366b2000-03-13 23:22:24 +00001138/* Checks whether element is contained in container and return 1/0
1139 accordingly.
1140
1141 element has to coerce to an one element Unicode string. -1 is
1142 returned in case of an error. */
1143
Mark Hammond91a681d2002-08-12 07:21:58 +00001144PyAPI_FUNC(int) PyUnicode_Contains(
Guido van Rossumd0d366b2000-03-13 23:22:24 +00001145 PyObject *container, /* Container string */
1146 PyObject *element /* Element string */
1147 );
1148
Walter Dörwaldde02bcb2002-04-22 17:42:37 +00001149/* Externally visible for str.strip(unicode) */
Mark Hammond91a681d2002-08-12 07:21:58 +00001150PyAPI_FUNC(PyObject *) _PyUnicode_XStrip(
Walter Dörwaldde02bcb2002-04-22 17:42:37 +00001151 PyUnicodeObject *self,
1152 int striptype,
1153 PyObject *sepobj
1154 );
1155
Guido van Rossumd8225182000-03-10 22:33:05 +00001156/* === Characters Type APIs =============================================== */
1157
1158/* These should not be used directly. Use the Py_UNICODE_IS* and
1159 Py_UNICODE_TO* macros instead.
1160
1161 These APIs are implemented in Objects/unicodectype.c.
1162
1163*/
1164
Mark Hammond91a681d2002-08-12 07:21:58 +00001165PyAPI_FUNC(int) _PyUnicode_IsLowercase(
Fredrik Lundh72b06852001-06-27 22:08:26 +00001166 Py_UNICODE ch /* Unicode character */
Guido van Rossumd8225182000-03-10 22:33:05 +00001167 );
1168
Mark Hammond91a681d2002-08-12 07:21:58 +00001169PyAPI_FUNC(int) _PyUnicode_IsUppercase(
Fredrik Lundh72b06852001-06-27 22:08:26 +00001170 Py_UNICODE ch /* Unicode character */
Guido van Rossumd8225182000-03-10 22:33:05 +00001171 );
1172
Mark Hammond91a681d2002-08-12 07:21:58 +00001173PyAPI_FUNC(int) _PyUnicode_IsTitlecase(
Fredrik Lundh72b06852001-06-27 22:08:26 +00001174 Py_UNICODE ch /* Unicode character */
Guido van Rossumd8225182000-03-10 22:33:05 +00001175 );
1176
Mark Hammond91a681d2002-08-12 07:21:58 +00001177PyAPI_FUNC(int) _PyUnicode_IsWhitespace(
Tim Peters2576c972005-10-29 02:33:18 +00001178 const Py_UNICODE ch /* Unicode character */
Guido van Rossumd8225182000-03-10 22:33:05 +00001179 );
1180
Mark Hammond91a681d2002-08-12 07:21:58 +00001181PyAPI_FUNC(int) _PyUnicode_IsLinebreak(
Tim Peters2576c972005-10-29 02:33:18 +00001182 const Py_UNICODE ch /* Unicode character */
Guido van Rossumd8225182000-03-10 22:33:05 +00001183 );
1184
Mark Hammond91a681d2002-08-12 07:21:58 +00001185PyAPI_FUNC(Py_UNICODE) _PyUnicode_ToLowercase(
Fredrik Lundh72b06852001-06-27 22:08:26 +00001186 Py_UNICODE ch /* Unicode character */
Guido van Rossumd8225182000-03-10 22:33:05 +00001187 );
1188
Mark Hammond91a681d2002-08-12 07:21:58 +00001189PyAPI_FUNC(Py_UNICODE) _PyUnicode_ToUppercase(
Fredrik Lundh72b06852001-06-27 22:08:26 +00001190 Py_UNICODE ch /* Unicode character */
Guido van Rossumd8225182000-03-10 22:33:05 +00001191 );
1192
Mark Hammond91a681d2002-08-12 07:21:58 +00001193PyAPI_FUNC(Py_UNICODE) _PyUnicode_ToTitlecase(
Fredrik Lundh72b06852001-06-27 22:08:26 +00001194 Py_UNICODE ch /* Unicode character */
Guido van Rossumd8225182000-03-10 22:33:05 +00001195 );
1196
Mark Hammond91a681d2002-08-12 07:21:58 +00001197PyAPI_FUNC(int) _PyUnicode_ToDecimalDigit(
Fredrik Lundh72b06852001-06-27 22:08:26 +00001198 Py_UNICODE ch /* Unicode character */
Guido van Rossumd8225182000-03-10 22:33:05 +00001199 );
1200
Mark Hammond91a681d2002-08-12 07:21:58 +00001201PyAPI_FUNC(int) _PyUnicode_ToDigit(
Fredrik Lundh72b06852001-06-27 22:08:26 +00001202 Py_UNICODE ch /* Unicode character */
Guido van Rossumd8225182000-03-10 22:33:05 +00001203 );
1204
Mark Hammond91a681d2002-08-12 07:21:58 +00001205PyAPI_FUNC(double) _PyUnicode_ToNumeric(
Fredrik Lundh72b06852001-06-27 22:08:26 +00001206 Py_UNICODE ch /* Unicode character */
Guido van Rossumd8225182000-03-10 22:33:05 +00001207 );
1208
Mark Hammond91a681d2002-08-12 07:21:58 +00001209PyAPI_FUNC(int) _PyUnicode_IsDecimalDigit(
Fredrik Lundh72b06852001-06-27 22:08:26 +00001210 Py_UNICODE ch /* Unicode character */
Guido van Rossumd8225182000-03-10 22:33:05 +00001211 );
1212
Mark Hammond91a681d2002-08-12 07:21:58 +00001213PyAPI_FUNC(int) _PyUnicode_IsDigit(
Fredrik Lundh72b06852001-06-27 22:08:26 +00001214 Py_UNICODE ch /* Unicode character */
Guido van Rossumd8225182000-03-10 22:33:05 +00001215 );
1216
Mark Hammond91a681d2002-08-12 07:21:58 +00001217PyAPI_FUNC(int) _PyUnicode_IsNumeric(
Fredrik Lundh72b06852001-06-27 22:08:26 +00001218 Py_UNICODE ch /* Unicode character */
Guido van Rossumd8225182000-03-10 22:33:05 +00001219 );
1220
Mark Hammond91a681d2002-08-12 07:21:58 +00001221PyAPI_FUNC(int) _PyUnicode_IsAlpha(
Fredrik Lundh72b06852001-06-27 22:08:26 +00001222 Py_UNICODE ch /* Unicode character */
Marc-André Lemburgf03e7412000-07-05 09:45:59 +00001223 );
1224
Guido van Rossumd8225182000-03-10 22:33:05 +00001225#ifdef __cplusplus
1226}
1227#endif
Martin v. Löwis339d0f72001-08-17 18:39:25 +00001228#endif /* Py_USING_UNICODE */
Guido van Rossumd8225182000-03-10 22:33:05 +00001229#endif /* !Py_UNICODEOBJECT_H */