Guido van Rossum | d822518 | 2000-03-10 22:33:05 +0000 | [diff] [blame] | 1 | #ifndef Py_UNICODEOBJECT_H |
| 2 | #define Py_UNICODEOBJECT_H |
Guido van Rossum | d822518 | 2000-03-10 22:33:05 +0000 | [diff] [blame] | 3 | |
| 4 | /* |
| 5 | |
| 6 | Unicode implementation based on original code by Fredrik Lundh, |
| 7 | modified by Marc-Andre Lemburg (mal@lemburg.com) according to the |
| 8 | Unicode Integration Proposal (see file Misc/unicode.txt). |
| 9 | |
Guido van Rossum | 16b1ad9 | 2000-08-03 16:24:25 +0000 | [diff] [blame] | 10 | Copyright (c) Corporation for National Research Initiatives. |
Guido van Rossum | d822518 | 2000-03-10 22:33:05 +0000 | [diff] [blame] | 11 | |
| 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 Lemburg | 5e6007c | 2001-09-19 11:21:03 +0000 | [diff] [blame] | 55 | #include <ctype.h> |
Guido van Rossum | d822518 | 2000-03-10 22:33:05 +0000 | [diff] [blame] | 56 | |
| 57 | /* === Internal API ======================================================= */ |
| 58 | |
| 59 | /* --- Internal Unicode Format -------------------------------------------- */ |
| 60 | |
Fredrik Lundh | 9b14ab3 | 2001-06-26 22:59:49 +0000 | [diff] [blame] | 61 | /* FIXME: MvL's new implementation assumes that Py_UNICODE_SIZE is |
| 62 | properly set, but the default rules below doesn't set it. I'll |
| 63 | sort this out some other day -- fredrik@pythonware.com */ |
| 64 | |
| 65 | #ifndef Py_UNICODE_SIZE |
| 66 | #error Must define Py_UNICODE_SIZE |
| 67 | #endif |
| 68 | |
Fredrik Lundh | 8f45585 | 2001-06-27 18:59:43 +0000 | [diff] [blame] | 69 | /* Setting Py_UNICODE_WIDE enables UCS-4 storage. Otherwise, Unicode |
| 70 | strings are stored as UCS-2 (with limited support for UTF-16) */ |
| 71 | |
| 72 | #if Py_UNICODE_SIZE >= 4 |
| 73 | #define Py_UNICODE_WIDE |
Martin v. Löwis | 0ba70cc | 2001-06-26 22:22:37 +0000 | [diff] [blame] | 74 | #endif |
Fredrik Lundh | 1294ad0 | 2001-06-26 17:17:07 +0000 | [diff] [blame] | 75 | |
Guido van Rossum | d822518 | 2000-03-10 22:33:05 +0000 | [diff] [blame] | 76 | /* Set these flags if the platform has "wchar.h", "wctype.h" and the |
| 77 | wchar_t type is a 16-bit unsigned type */ |
| 78 | /* #define HAVE_WCHAR_H */ |
| 79 | /* #define HAVE_USABLE_WCHAR_T */ |
| 80 | |
| 81 | /* Defaults for various platforms */ |
Martin v. Löwis | 0ba70cc | 2001-06-26 22:22:37 +0000 | [diff] [blame] | 82 | #ifndef PY_UNICODE_TYPE |
Guido van Rossum | d822518 | 2000-03-10 22:33:05 +0000 | [diff] [blame] | 83 | |
Fredrik Lundh | 1294ad0 | 2001-06-26 17:17:07 +0000 | [diff] [blame] | 84 | /* Windows has a usable wchar_t type (unless we're using UCS-4) */ |
Fredrik Lundh | 8f45585 | 2001-06-27 18:59:43 +0000 | [diff] [blame] | 85 | # if defined(MS_WIN32) && Py_UNICODE_SIZE == 2 |
Guido van Rossum | d822518 | 2000-03-10 22:33:05 +0000 | [diff] [blame] | 86 | # define HAVE_USABLE_WCHAR_T |
Martin v. Löwis | 0ba70cc | 2001-06-26 22:22:37 +0000 | [diff] [blame] | 87 | # define PY_UNICODE_TYPE wchar_t |
| 88 | # endif |
| 89 | |
Fredrik Lundh | 8f45585 | 2001-06-27 18:59:43 +0000 | [diff] [blame] | 90 | # if defined(Py_UNICODE_WIDE) |
Martin v. Löwis | 0ba70cc | 2001-06-26 22:22:37 +0000 | [diff] [blame] | 91 | # define PY_UNICODE_TYPE Py_UCS4 |
Guido van Rossum | d822518 | 2000-03-10 22:33:05 +0000 | [diff] [blame] | 92 | # endif |
| 93 | |
| 94 | #endif |
| 95 | |
| 96 | /* If the compiler provides a wchar_t type we try to support it |
| 97 | through the interface functions PyUnicode_FromWideChar() and |
| 98 | PyUnicode_AsWideChar(). */ |
| 99 | |
| 100 | #ifdef HAVE_USABLE_WCHAR_T |
Marc-André Lemburg | 1a731c6 | 2000-08-11 11:43:10 +0000 | [diff] [blame] | 101 | # ifndef HAVE_WCHAR_H |
| 102 | # define HAVE_WCHAR_H |
| 103 | # endif |
Guido van Rossum | d822518 | 2000-03-10 22:33:05 +0000 | [diff] [blame] | 104 | #endif |
| 105 | |
| 106 | #ifdef HAVE_WCHAR_H |
Guido van Rossum | 24bdb04 | 2000-03-28 20:29:59 +0000 | [diff] [blame] | 107 | /* Work around a cosmetic bug in BSDI 4.x wchar.h; thanks to Thomas Wouters */ |
| 108 | # ifdef _HAVE_BSDI |
| 109 | # include <time.h> |
| 110 | # endif |
Marc-André Lemburg | 5e6007c | 2001-09-19 11:21:03 +0000 | [diff] [blame] | 111 | # include <wchar.h> |
Guido van Rossum | d822518 | 2000-03-10 22:33:05 +0000 | [diff] [blame] | 112 | #endif |
| 113 | |
Martin v. Löwis | 0ba70cc | 2001-06-26 22:22:37 +0000 | [diff] [blame] | 114 | /* |
| 115 | * Use this typedef when you need to represent a UTF-16 surrogate pair |
| 116 | * as single unsigned integer. |
| 117 | */ |
| 118 | #if SIZEOF_INT >= 4 |
| 119 | typedef unsigned int Py_UCS4; |
| 120 | #elif SIZEOF_LONG >= 4 |
| 121 | typedef unsigned long Py_UCS4; |
Guido van Rossum | d822518 | 2000-03-10 22:33:05 +0000 | [diff] [blame] | 122 | #endif |
| 123 | |
Martin v. Löwis | 0ba70cc | 2001-06-26 22:22:37 +0000 | [diff] [blame] | 124 | typedef PY_UNICODE_TYPE Py_UNICODE; |
Marc-André Lemburg | 4327910 | 2000-07-07 09:01:41 +0000 | [diff] [blame] | 125 | |
Marc-André Lemburg | b5ac6f6 | 2001-07-31 14:30:16 +0000 | [diff] [blame] | 126 | /* --- UCS-2/UCS-4 Name Mangling ------------------------------------------ */ |
| 127 | |
| 128 | /* Unicode API names are mangled to assure that UCS-2 and UCS-4 builds |
| 129 | produce different external names and thus cause import errors in |
| 130 | case Python interpreters and extensions with mixed compiled in |
| 131 | Unicode width assumptions are combined. */ |
| 132 | |
| 133 | #ifndef Py_UNICODE_WIDE |
| 134 | |
| 135 | # define PyUnicode_AsASCIIString PyUnicodeUCS2_AsASCIIString |
| 136 | # define PyUnicode_AsCharmapString PyUnicodeUCS2_AsCharmapString |
Marc-André Lemburg | d2d4598 | 2004-07-08 17:57:32 +0000 | [diff] [blame] | 137 | # define PyUnicode_AsEncodedObject PyUnicodeUCS2_AsEncodedObject |
Marc-André Lemburg | b5ac6f6 | 2001-07-31 14:30:16 +0000 | [diff] [blame] | 138 | # define PyUnicode_AsEncodedString PyUnicodeUCS2_AsEncodedString |
| 139 | # define PyUnicode_AsLatin1String PyUnicodeUCS2_AsLatin1String |
| 140 | # define PyUnicode_AsRawUnicodeEscapeString PyUnicodeUCS2_AsRawUnicodeEscapeString |
| 141 | # define PyUnicode_AsUTF16String PyUnicodeUCS2_AsUTF16String |
| 142 | # define PyUnicode_AsUTF8String PyUnicodeUCS2_AsUTF8String |
| 143 | # define PyUnicode_AsUnicode PyUnicodeUCS2_AsUnicode |
| 144 | # define PyUnicode_AsUnicodeEscapeString PyUnicodeUCS2_AsUnicodeEscapeString |
| 145 | # define PyUnicode_AsWideChar PyUnicodeUCS2_AsWideChar |
| 146 | # define PyUnicode_Compare PyUnicodeUCS2_Compare |
| 147 | # define PyUnicode_Concat PyUnicodeUCS2_Concat |
| 148 | # define PyUnicode_Contains PyUnicodeUCS2_Contains |
| 149 | # define PyUnicode_Count PyUnicodeUCS2_Count |
| 150 | # define PyUnicode_Decode PyUnicodeUCS2_Decode |
| 151 | # define PyUnicode_DecodeASCII PyUnicodeUCS2_DecodeASCII |
| 152 | # define PyUnicode_DecodeCharmap PyUnicodeUCS2_DecodeCharmap |
| 153 | # define PyUnicode_DecodeLatin1 PyUnicodeUCS2_DecodeLatin1 |
| 154 | # define PyUnicode_DecodeRawUnicodeEscape PyUnicodeUCS2_DecodeRawUnicodeEscape |
| 155 | # define PyUnicode_DecodeUTF16 PyUnicodeUCS2_DecodeUTF16 |
Walter Dörwald | 6965203 | 2004-09-07 20:24:22 +0000 | [diff] [blame] | 156 | # define PyUnicode_DecodeUTF16Stateful PyUnicodeUCS2_DecodeUTF16Stateful |
Marc-André Lemburg | b5ac6f6 | 2001-07-31 14:30:16 +0000 | [diff] [blame] | 157 | # define PyUnicode_DecodeUTF8 PyUnicodeUCS2_DecodeUTF8 |
Walter Dörwald | 6965203 | 2004-09-07 20:24:22 +0000 | [diff] [blame] | 158 | # define PyUnicode_DecodeUTF8Stateful PyUnicodeUCS2_DecodeUTF8Stateful |
Marc-André Lemburg | b5ac6f6 | 2001-07-31 14:30:16 +0000 | [diff] [blame] | 159 | # define PyUnicode_DecodeUnicodeEscape PyUnicodeUCS2_DecodeUnicodeEscape |
| 160 | # define PyUnicode_Encode PyUnicodeUCS2_Encode |
| 161 | # define PyUnicode_EncodeASCII PyUnicodeUCS2_EncodeASCII |
| 162 | # define PyUnicode_EncodeCharmap PyUnicodeUCS2_EncodeCharmap |
| 163 | # define PyUnicode_EncodeDecimal PyUnicodeUCS2_EncodeDecimal |
| 164 | # define PyUnicode_EncodeLatin1 PyUnicodeUCS2_EncodeLatin1 |
| 165 | # define PyUnicode_EncodeRawUnicodeEscape PyUnicodeUCS2_EncodeRawUnicodeEscape |
| 166 | # define PyUnicode_EncodeUTF16 PyUnicodeUCS2_EncodeUTF16 |
| 167 | # define PyUnicode_EncodeUTF8 PyUnicodeUCS2_EncodeUTF8 |
| 168 | # define PyUnicode_EncodeUnicodeEscape PyUnicodeUCS2_EncodeUnicodeEscape |
| 169 | # define PyUnicode_Find PyUnicodeUCS2_Find |
| 170 | # define PyUnicode_Format PyUnicodeUCS2_Format |
| 171 | # define PyUnicode_FromEncodedObject PyUnicodeUCS2_FromEncodedObject |
| 172 | # define PyUnicode_FromObject PyUnicodeUCS2_FromObject |
Marc-André Lemburg | 9c329de | 2002-08-12 08:19:10 +0000 | [diff] [blame] | 173 | # define PyUnicode_FromOrdinal PyUnicodeUCS2_FromOrdinal |
Marc-André Lemburg | b5ac6f6 | 2001-07-31 14:30:16 +0000 | [diff] [blame] | 174 | # define PyUnicode_FromUnicode PyUnicodeUCS2_FromUnicode |
Walter Dörwald | acaa5a1 | 2007-05-05 12:00:46 +0000 | [diff] [blame] | 175 | # define PyUnicode_FromString PyUnicodeUCS2_FromString |
Marc-André Lemburg | b5ac6f6 | 2001-07-31 14:30:16 +0000 | [diff] [blame] | 176 | # define PyUnicode_FromWideChar PyUnicodeUCS2_FromWideChar |
| 177 | # define PyUnicode_GetDefaultEncoding PyUnicodeUCS2_GetDefaultEncoding |
| 178 | # define PyUnicode_GetMax PyUnicodeUCS2_GetMax |
| 179 | # define PyUnicode_GetSize PyUnicodeUCS2_GetSize |
| 180 | # define PyUnicode_Join PyUnicodeUCS2_Join |
Thomas Wouters | 477c8d5 | 2006-05-27 19:21:47 +0000 | [diff] [blame] | 181 | # define PyUnicode_Partition PyUnicodeUCS2_Partition |
| 182 | # define PyUnicode_RPartition PyUnicodeUCS2_RPartition |
| 183 | # define PyUnicode_RSplit PyUnicodeUCS2_RSplit |
Marc-André Lemburg | b5ac6f6 | 2001-07-31 14:30:16 +0000 | [diff] [blame] | 184 | # define PyUnicode_Replace PyUnicodeUCS2_Replace |
| 185 | # define PyUnicode_Resize PyUnicodeUCS2_Resize |
Thomas Wouters | 00ee7ba | 2006-08-21 19:07:27 +0000 | [diff] [blame] | 186 | # define PyUnicode_RichCompare PyUnicodeUCS2_RichCompare |
Marc-André Lemburg | b5ac6f6 | 2001-07-31 14:30:16 +0000 | [diff] [blame] | 187 | # define PyUnicode_SetDefaultEncoding PyUnicodeUCS2_SetDefaultEncoding |
| 188 | # define PyUnicode_Split PyUnicodeUCS2_Split |
| 189 | # define PyUnicode_Splitlines PyUnicodeUCS2_Splitlines |
| 190 | # define PyUnicode_Tailmatch PyUnicodeUCS2_Tailmatch |
| 191 | # define PyUnicode_Translate PyUnicodeUCS2_Translate |
| 192 | # define PyUnicode_TranslateCharmap PyUnicodeUCS2_TranslateCharmap |
| 193 | # define _PyUnicode_AsDefaultEncodedString _PyUnicodeUCS2_AsDefaultEncodedString |
| 194 | # define _PyUnicode_Fini _PyUnicodeUCS2_Fini |
| 195 | # define _PyUnicode_Init _PyUnicodeUCS2_Init |
| 196 | # define _PyUnicode_IsAlpha _PyUnicodeUCS2_IsAlpha |
| 197 | # define _PyUnicode_IsDecimalDigit _PyUnicodeUCS2_IsDecimalDigit |
| 198 | # define _PyUnicode_IsDigit _PyUnicodeUCS2_IsDigit |
| 199 | # define _PyUnicode_IsLinebreak _PyUnicodeUCS2_IsLinebreak |
| 200 | # define _PyUnicode_IsLowercase _PyUnicodeUCS2_IsLowercase |
| 201 | # define _PyUnicode_IsNumeric _PyUnicodeUCS2_IsNumeric |
| 202 | # define _PyUnicode_IsTitlecase _PyUnicodeUCS2_IsTitlecase |
| 203 | # define _PyUnicode_IsUppercase _PyUnicodeUCS2_IsUppercase |
| 204 | # define _PyUnicode_IsWhitespace _PyUnicodeUCS2_IsWhitespace |
| 205 | # define _PyUnicode_ToDecimalDigit _PyUnicodeUCS2_ToDecimalDigit |
| 206 | # define _PyUnicode_ToDigit _PyUnicodeUCS2_ToDigit |
| 207 | # define _PyUnicode_ToLowercase _PyUnicodeUCS2_ToLowercase |
| 208 | # define _PyUnicode_ToNumeric _PyUnicodeUCS2_ToNumeric |
| 209 | # define _PyUnicode_ToTitlecase _PyUnicodeUCS2_ToTitlecase |
| 210 | # define _PyUnicode_ToUppercase _PyUnicodeUCS2_ToUppercase |
| 211 | |
| 212 | #else |
| 213 | |
| 214 | # define PyUnicode_AsASCIIString PyUnicodeUCS4_AsASCIIString |
| 215 | # define PyUnicode_AsCharmapString PyUnicodeUCS4_AsCharmapString |
Marc-André Lemburg | d2d4598 | 2004-07-08 17:57:32 +0000 | [diff] [blame] | 216 | # define PyUnicode_AsEncodedObject PyUnicodeUCS4_AsEncodedObject |
Marc-André Lemburg | b5ac6f6 | 2001-07-31 14:30:16 +0000 | [diff] [blame] | 217 | # define PyUnicode_AsEncodedString PyUnicodeUCS4_AsEncodedString |
| 218 | # define PyUnicode_AsLatin1String PyUnicodeUCS4_AsLatin1String |
| 219 | # define PyUnicode_AsRawUnicodeEscapeString PyUnicodeUCS4_AsRawUnicodeEscapeString |
| 220 | # define PyUnicode_AsUTF16String PyUnicodeUCS4_AsUTF16String |
| 221 | # define PyUnicode_AsUTF8String PyUnicodeUCS4_AsUTF8String |
| 222 | # define PyUnicode_AsUnicode PyUnicodeUCS4_AsUnicode |
| 223 | # define PyUnicode_AsUnicodeEscapeString PyUnicodeUCS4_AsUnicodeEscapeString |
| 224 | # define PyUnicode_AsWideChar PyUnicodeUCS4_AsWideChar |
| 225 | # define PyUnicode_Compare PyUnicodeUCS4_Compare |
| 226 | # define PyUnicode_Concat PyUnicodeUCS4_Concat |
| 227 | # define PyUnicode_Contains PyUnicodeUCS4_Contains |
| 228 | # define PyUnicode_Count PyUnicodeUCS4_Count |
| 229 | # define PyUnicode_Decode PyUnicodeUCS4_Decode |
| 230 | # define PyUnicode_DecodeASCII PyUnicodeUCS4_DecodeASCII |
| 231 | # define PyUnicode_DecodeCharmap PyUnicodeUCS4_DecodeCharmap |
| 232 | # define PyUnicode_DecodeLatin1 PyUnicodeUCS4_DecodeLatin1 |
| 233 | # define PyUnicode_DecodeRawUnicodeEscape PyUnicodeUCS4_DecodeRawUnicodeEscape |
| 234 | # define PyUnicode_DecodeUTF16 PyUnicodeUCS4_DecodeUTF16 |
Walter Dörwald | 6965203 | 2004-09-07 20:24:22 +0000 | [diff] [blame] | 235 | # define PyUnicode_DecodeUTF16Stateful PyUnicodeUCS4_DecodeUTF16Stateful |
Marc-André Lemburg | b5ac6f6 | 2001-07-31 14:30:16 +0000 | [diff] [blame] | 236 | # define PyUnicode_DecodeUTF8 PyUnicodeUCS4_DecodeUTF8 |
Walter Dörwald | 6965203 | 2004-09-07 20:24:22 +0000 | [diff] [blame] | 237 | # define PyUnicode_DecodeUTF8Stateful PyUnicodeUCS4_DecodeUTF8Stateful |
Marc-André Lemburg | b5ac6f6 | 2001-07-31 14:30:16 +0000 | [diff] [blame] | 238 | # define PyUnicode_DecodeUnicodeEscape PyUnicodeUCS4_DecodeUnicodeEscape |
| 239 | # define PyUnicode_Encode PyUnicodeUCS4_Encode |
| 240 | # define PyUnicode_EncodeASCII PyUnicodeUCS4_EncodeASCII |
| 241 | # define PyUnicode_EncodeCharmap PyUnicodeUCS4_EncodeCharmap |
| 242 | # define PyUnicode_EncodeDecimal PyUnicodeUCS4_EncodeDecimal |
| 243 | # define PyUnicode_EncodeLatin1 PyUnicodeUCS4_EncodeLatin1 |
| 244 | # define PyUnicode_EncodeRawUnicodeEscape PyUnicodeUCS4_EncodeRawUnicodeEscape |
| 245 | # define PyUnicode_EncodeUTF16 PyUnicodeUCS4_EncodeUTF16 |
| 246 | # define PyUnicode_EncodeUTF8 PyUnicodeUCS4_EncodeUTF8 |
| 247 | # define PyUnicode_EncodeUnicodeEscape PyUnicodeUCS4_EncodeUnicodeEscape |
| 248 | # define PyUnicode_Find PyUnicodeUCS4_Find |
| 249 | # define PyUnicode_Format PyUnicodeUCS4_Format |
| 250 | # define PyUnicode_FromEncodedObject PyUnicodeUCS4_FromEncodedObject |
| 251 | # define PyUnicode_FromObject PyUnicodeUCS4_FromObject |
Marc-André Lemburg | 9c329de | 2002-08-12 08:19:10 +0000 | [diff] [blame] | 252 | # define PyUnicode_FromOrdinal PyUnicodeUCS4_FromOrdinal |
Marc-André Lemburg | b5ac6f6 | 2001-07-31 14:30:16 +0000 | [diff] [blame] | 253 | # define PyUnicode_FromUnicode PyUnicodeUCS4_FromUnicode |
Walter Dörwald | acaa5a1 | 2007-05-05 12:00:46 +0000 | [diff] [blame] | 254 | # define PyUnicode_FromString PyUnicodeUCS4_FromString |
Marc-André Lemburg | b5ac6f6 | 2001-07-31 14:30:16 +0000 | [diff] [blame] | 255 | # define PyUnicode_FromWideChar PyUnicodeUCS4_FromWideChar |
| 256 | # define PyUnicode_GetDefaultEncoding PyUnicodeUCS4_GetDefaultEncoding |
| 257 | # define PyUnicode_GetMax PyUnicodeUCS4_GetMax |
| 258 | # define PyUnicode_GetSize PyUnicodeUCS4_GetSize |
| 259 | # define PyUnicode_Join PyUnicodeUCS4_Join |
Thomas Wouters | 477c8d5 | 2006-05-27 19:21:47 +0000 | [diff] [blame] | 260 | # define PyUnicode_Partition PyUnicodeUCS4_Partition |
| 261 | # define PyUnicode_RPartition PyUnicodeUCS4_RPartition |
| 262 | # define PyUnicode_RSplit PyUnicodeUCS4_RSplit |
Marc-André Lemburg | b5ac6f6 | 2001-07-31 14:30:16 +0000 | [diff] [blame] | 263 | # define PyUnicode_Replace PyUnicodeUCS4_Replace |
| 264 | # define PyUnicode_Resize PyUnicodeUCS4_Resize |
Thomas Wouters | 00ee7ba | 2006-08-21 19:07:27 +0000 | [diff] [blame] | 265 | # define PyUnicode_RichCompare PyUnicodeUCS4_RichCompare |
Marc-André Lemburg | b5ac6f6 | 2001-07-31 14:30:16 +0000 | [diff] [blame] | 266 | # define PyUnicode_SetDefaultEncoding PyUnicodeUCS4_SetDefaultEncoding |
| 267 | # define PyUnicode_Split PyUnicodeUCS4_Split |
| 268 | # define PyUnicode_Splitlines PyUnicodeUCS4_Splitlines |
| 269 | # define PyUnicode_Tailmatch PyUnicodeUCS4_Tailmatch |
| 270 | # define PyUnicode_Translate PyUnicodeUCS4_Translate |
| 271 | # define PyUnicode_TranslateCharmap PyUnicodeUCS4_TranslateCharmap |
| 272 | # define _PyUnicode_AsDefaultEncodedString _PyUnicodeUCS4_AsDefaultEncodedString |
| 273 | # define _PyUnicode_Fini _PyUnicodeUCS4_Fini |
| 274 | # define _PyUnicode_Init _PyUnicodeUCS4_Init |
| 275 | # define _PyUnicode_IsAlpha _PyUnicodeUCS4_IsAlpha |
| 276 | # define _PyUnicode_IsDecimalDigit _PyUnicodeUCS4_IsDecimalDigit |
| 277 | # define _PyUnicode_IsDigit _PyUnicodeUCS4_IsDigit |
| 278 | # define _PyUnicode_IsLinebreak _PyUnicodeUCS4_IsLinebreak |
| 279 | # define _PyUnicode_IsLowercase _PyUnicodeUCS4_IsLowercase |
| 280 | # define _PyUnicode_IsNumeric _PyUnicodeUCS4_IsNumeric |
| 281 | # define _PyUnicode_IsTitlecase _PyUnicodeUCS4_IsTitlecase |
| 282 | # define _PyUnicode_IsUppercase _PyUnicodeUCS4_IsUppercase |
| 283 | # define _PyUnicode_IsWhitespace _PyUnicodeUCS4_IsWhitespace |
| 284 | # define _PyUnicode_ToDecimalDigit _PyUnicodeUCS4_ToDecimalDigit |
| 285 | # define _PyUnicode_ToDigit _PyUnicodeUCS4_ToDigit |
| 286 | # define _PyUnicode_ToLowercase _PyUnicodeUCS4_ToLowercase |
| 287 | # define _PyUnicode_ToNumeric _PyUnicodeUCS4_ToNumeric |
| 288 | # define _PyUnicode_ToTitlecase _PyUnicodeUCS4_ToTitlecase |
| 289 | # define _PyUnicode_ToUppercase _PyUnicodeUCS4_ToUppercase |
| 290 | |
| 291 | |
| 292 | #endif |
| 293 | |
Guido van Rossum | d822518 | 2000-03-10 22:33:05 +0000 | [diff] [blame] | 294 | /* --- Internal Unicode Operations ---------------------------------------- */ |
| 295 | |
| 296 | /* If you want Python to use the compiler's wctype.h functions instead |
Barry Warsaw | 51ac580 | 2000-03-20 16:36:48 +0000 | [diff] [blame] | 297 | of the ones supplied with Python, define WANT_WCTYPE_FUNCTIONS or |
Raymond Hettinger | 57341c3 | 2004-10-31 05:46:59 +0000 | [diff] [blame] | 298 | configure Python using --with-wctype-functions. This reduces the |
Barry Warsaw | 51ac580 | 2000-03-20 16:36:48 +0000 | [diff] [blame] | 299 | interpreter's code size. */ |
Guido van Rossum | d822518 | 2000-03-10 22:33:05 +0000 | [diff] [blame] | 300 | |
| 301 | #if defined(HAVE_USABLE_WCHAR_T) && defined(WANT_WCTYPE_FUNCTIONS) |
| 302 | |
Marc-André Lemburg | 5e6007c | 2001-09-19 11:21:03 +0000 | [diff] [blame] | 303 | #include <wctype.h> |
Guido van Rossum | d822518 | 2000-03-10 22:33:05 +0000 | [diff] [blame] | 304 | |
| 305 | #define Py_UNICODE_ISSPACE(ch) iswspace(ch) |
| 306 | |
| 307 | #define Py_UNICODE_ISLOWER(ch) iswlower(ch) |
| 308 | #define Py_UNICODE_ISUPPER(ch) iswupper(ch) |
| 309 | #define Py_UNICODE_ISTITLE(ch) _PyUnicode_IsTitlecase(ch) |
| 310 | #define Py_UNICODE_ISLINEBREAK(ch) _PyUnicode_IsLinebreak(ch) |
| 311 | |
| 312 | #define Py_UNICODE_TOLOWER(ch) towlower(ch) |
| 313 | #define Py_UNICODE_TOUPPER(ch) towupper(ch) |
| 314 | #define Py_UNICODE_TOTITLE(ch) _PyUnicode_ToTitlecase(ch) |
| 315 | |
| 316 | #define Py_UNICODE_ISDECIMAL(ch) _PyUnicode_IsDecimalDigit(ch) |
| 317 | #define Py_UNICODE_ISDIGIT(ch) _PyUnicode_IsDigit(ch) |
| 318 | #define Py_UNICODE_ISNUMERIC(ch) _PyUnicode_IsNumeric(ch) |
| 319 | |
| 320 | #define Py_UNICODE_TODECIMAL(ch) _PyUnicode_ToDecimalDigit(ch) |
| 321 | #define Py_UNICODE_TODIGIT(ch) _PyUnicode_ToDigit(ch) |
| 322 | #define Py_UNICODE_TONUMERIC(ch) _PyUnicode_ToNumeric(ch) |
| 323 | |
Marc-André Lemburg | f03e741 | 2000-07-05 09:45:59 +0000 | [diff] [blame] | 324 | #define Py_UNICODE_ISALPHA(ch) iswalpha(ch) |
| 325 | |
Guido van Rossum | d822518 | 2000-03-10 22:33:05 +0000 | [diff] [blame] | 326 | #else |
| 327 | |
| 328 | #define Py_UNICODE_ISSPACE(ch) _PyUnicode_IsWhitespace(ch) |
| 329 | |
| 330 | #define Py_UNICODE_ISLOWER(ch) _PyUnicode_IsLowercase(ch) |
| 331 | #define Py_UNICODE_ISUPPER(ch) _PyUnicode_IsUppercase(ch) |
| 332 | #define Py_UNICODE_ISTITLE(ch) _PyUnicode_IsTitlecase(ch) |
| 333 | #define Py_UNICODE_ISLINEBREAK(ch) _PyUnicode_IsLinebreak(ch) |
| 334 | |
| 335 | #define Py_UNICODE_TOLOWER(ch) _PyUnicode_ToLowercase(ch) |
| 336 | #define Py_UNICODE_TOUPPER(ch) _PyUnicode_ToUppercase(ch) |
| 337 | #define Py_UNICODE_TOTITLE(ch) _PyUnicode_ToTitlecase(ch) |
| 338 | |
| 339 | #define Py_UNICODE_ISDECIMAL(ch) _PyUnicode_IsDecimalDigit(ch) |
| 340 | #define Py_UNICODE_ISDIGIT(ch) _PyUnicode_IsDigit(ch) |
| 341 | #define Py_UNICODE_ISNUMERIC(ch) _PyUnicode_IsNumeric(ch) |
| 342 | |
| 343 | #define Py_UNICODE_TODECIMAL(ch) _PyUnicode_ToDecimalDigit(ch) |
| 344 | #define Py_UNICODE_TODIGIT(ch) _PyUnicode_ToDigit(ch) |
| 345 | #define Py_UNICODE_TONUMERIC(ch) _PyUnicode_ToNumeric(ch) |
| 346 | |
Marc-André Lemburg | f03e741 | 2000-07-05 09:45:59 +0000 | [diff] [blame] | 347 | #define Py_UNICODE_ISALPHA(ch) _PyUnicode_IsAlpha(ch) |
Guido van Rossum | d822518 | 2000-03-10 22:33:05 +0000 | [diff] [blame] | 348 | |
Marc-André Lemburg | f03e741 | 2000-07-05 09:45:59 +0000 | [diff] [blame] | 349 | #endif |
Marc-André Lemburg | a9c103b | 2000-07-03 10:52:13 +0000 | [diff] [blame] | 350 | |
| 351 | #define Py_UNICODE_ISALNUM(ch) \ |
| 352 | (Py_UNICODE_ISALPHA(ch) || \ |
| 353 | Py_UNICODE_ISDECIMAL(ch) || \ |
| 354 | Py_UNICODE_ISDIGIT(ch) || \ |
| 355 | Py_UNICODE_ISNUMERIC(ch)) |
| 356 | |
Thomas Wouters | 4d70c3d | 2006-06-08 14:42:34 +0000 | [diff] [blame] | 357 | #define Py_UNICODE_COPY(target, source, length) \ |
| 358 | Py_MEMCPY((target), (source), (length)*sizeof(Py_UNICODE)) |
Guido van Rossum | d822518 | 2000-03-10 22:33:05 +0000 | [diff] [blame] | 359 | |
| 360 | #define Py_UNICODE_FILL(target, value, length) do\ |
Thomas Wouters | 477c8d5 | 2006-05-27 19:21:47 +0000 | [diff] [blame] | 361 | {Py_ssize_t i_; Py_UNICODE *t_ = (target); Py_UNICODE v_ = (value);\ |
| 362 | for (i_ = 0; i_ < (length); i_++) t_[i_] = v_;\ |
| 363 | } while (0) |
Guido van Rossum | d822518 | 2000-03-10 22:33:05 +0000 | [diff] [blame] | 364 | |
Thomas Wouters | 477c8d5 | 2006-05-27 19:21:47 +0000 | [diff] [blame] | 365 | /* check if substring matches at given offset. the offset must be |
| 366 | valid, and the substring must not be empty */ |
| 367 | #define Py_UNICODE_MATCH(string, offset, substring) \ |
| 368 | ((*((string)->str + (offset)) == *((substring)->str)) && \ |
| 369 | ((*((string)->str + (offset) + (substring)->length-1) == *((substring)->str + (substring)->length-1))) && \ |
| 370 | !memcmp((string)->str + (offset), (substring)->str, (substring)->length*sizeof(Py_UNICODE))) |
Guido van Rossum | d822518 | 2000-03-10 22:33:05 +0000 | [diff] [blame] | 371 | |
Barry Warsaw | 51ac580 | 2000-03-20 16:36:48 +0000 | [diff] [blame] | 372 | #ifdef __cplusplus |
| 373 | extern "C" { |
| 374 | #endif |
| 375 | |
Guido van Rossum | d822518 | 2000-03-10 22:33:05 +0000 | [diff] [blame] | 376 | /* --- Unicode Type ------------------------------------------------------- */ |
| 377 | |
| 378 | typedef struct { |
| 379 | PyObject_HEAD |
Martin v. Löwis | 18e1655 | 2006-02-15 17:27:45 +0000 | [diff] [blame] | 380 | Py_ssize_t length; /* Length of raw Unicode data in buffer */ |
Guido van Rossum | d822518 | 2000-03-10 22:33:05 +0000 | [diff] [blame] | 381 | Py_UNICODE *str; /* Raw Unicode buffer */ |
| 382 | long hash; /* Hash value; -1 if not set */ |
Marc-André Lemburg | bff879c | 2000-08-03 18:46:08 +0000 | [diff] [blame] | 383 | PyObject *defenc; /* (Default) Encoded version as Python |
| 384 | string, or NULL; this is used for |
| 385 | implementing the buffer protocol */ |
Guido van Rossum | d822518 | 2000-03-10 22:33:05 +0000 | [diff] [blame] | 386 | } PyUnicodeObject; |
| 387 | |
Mark Hammond | 91a681d | 2002-08-12 07:21:58 +0000 | [diff] [blame] | 388 | PyAPI_DATA(PyTypeObject) PyUnicode_Type; |
Guido van Rossum | d822518 | 2000-03-10 22:33:05 +0000 | [diff] [blame] | 389 | |
Thomas Wouters | 27d517b | 2007-02-25 20:39:11 +0000 | [diff] [blame] | 390 | #define PyUnicode_Check(op) \ |
| 391 | PyType_FastSubclass((op)->ob_type, Py_TPFLAGS_UNICODE_SUBCLASS) |
Tim Peters | 78e0fc7 | 2001-09-11 03:07:38 +0000 | [diff] [blame] | 392 | #define PyUnicode_CheckExact(op) ((op)->ob_type == &PyUnicode_Type) |
Guido van Rossum | d822518 | 2000-03-10 22:33:05 +0000 | [diff] [blame] | 393 | |
| 394 | /* Fast access macros */ |
| 395 | #define PyUnicode_GET_SIZE(op) \ |
| 396 | (((PyUnicodeObject *)(op))->length) |
| 397 | #define PyUnicode_GET_DATA_SIZE(op) \ |
| 398 | (((PyUnicodeObject *)(op))->length * sizeof(Py_UNICODE)) |
| 399 | #define PyUnicode_AS_UNICODE(op) \ |
| 400 | (((PyUnicodeObject *)(op))->str) |
| 401 | #define PyUnicode_AS_DATA(op) \ |
| 402 | ((const char *)((PyUnicodeObject *)(op))->str) |
| 403 | |
| 404 | /* --- Constants ---------------------------------------------------------- */ |
| 405 | |
| 406 | /* This Unicode character will be used as replacement character during |
| 407 | decoding if the errors argument is set to "replace". Note: the |
| 408 | Unicode character U+FFFD is the official REPLACEMENT CHARACTER in |
| 409 | Unicode 3.0. */ |
| 410 | |
| 411 | #define Py_UNICODE_REPLACEMENT_CHARACTER ((Py_UNICODE) 0xFFFD) |
| 412 | |
| 413 | /* === Public API ========================================================= */ |
| 414 | |
| 415 | /* --- Plain Py_UNICODE --------------------------------------------------- */ |
| 416 | |
| 417 | /* Create a Unicode Object from the Py_UNICODE buffer u of the given |
Marc-André Lemburg | 8155e0e | 2001-04-23 14:44:21 +0000 | [diff] [blame] | 418 | size. |
| 419 | |
| 420 | u may be NULL which causes the contents to be undefined. It is the |
| 421 | user's responsibility to fill in the needed data afterwards. Note |
| 422 | that modifying the Unicode object contents after construction is |
| 423 | only allowed if u was set to NULL. |
Guido van Rossum | d822518 | 2000-03-10 22:33:05 +0000 | [diff] [blame] | 424 | |
| 425 | The buffer is copied into the new object. */ |
| 426 | |
Mark Hammond | 91a681d | 2002-08-12 07:21:58 +0000 | [diff] [blame] | 427 | PyAPI_FUNC(PyObject*) PyUnicode_FromUnicode( |
Guido van Rossum | d822518 | 2000-03-10 22:33:05 +0000 | [diff] [blame] | 428 | const Py_UNICODE *u, /* Unicode buffer */ |
Martin v. Löwis | 18e1655 | 2006-02-15 17:27:45 +0000 | [diff] [blame] | 429 | Py_ssize_t size /* size of buffer */ |
Guido van Rossum | d822518 | 2000-03-10 22:33:05 +0000 | [diff] [blame] | 430 | ); |
| 431 | |
Walter Dörwald | acaa5a1 | 2007-05-05 12:00:46 +0000 | [diff] [blame] | 432 | /* Similar to PyUnicode_FromUnicode(), but u points to null-terminated |
| 433 | Latin-1 encoded bytes */ |
| 434 | PyAPI_FUNC(PyObject*) PyUnicode_FromString( |
| 435 | const char *u /* string */ |
| 436 | ); |
| 437 | |
Guido van Rossum | d822518 | 2000-03-10 22:33:05 +0000 | [diff] [blame] | 438 | /* Return a read-only pointer to the Unicode object's internal |
| 439 | Py_UNICODE buffer. */ |
| 440 | |
Mark Hammond | 91a681d | 2002-08-12 07:21:58 +0000 | [diff] [blame] | 441 | PyAPI_FUNC(Py_UNICODE *) PyUnicode_AsUnicode( |
Guido van Rossum | d822518 | 2000-03-10 22:33:05 +0000 | [diff] [blame] | 442 | PyObject *unicode /* Unicode object */ |
| 443 | ); |
| 444 | |
| 445 | /* Get the length of the Unicode object. */ |
| 446 | |
Martin v. Löwis | 18e1655 | 2006-02-15 17:27:45 +0000 | [diff] [blame] | 447 | PyAPI_FUNC(Py_ssize_t) PyUnicode_GetSize( |
Guido van Rossum | d822518 | 2000-03-10 22:33:05 +0000 | [diff] [blame] | 448 | PyObject *unicode /* Unicode object */ |
| 449 | ); |
| 450 | |
Martin v. Löwis | ce9b5a5 | 2001-06-27 06:28:56 +0000 | [diff] [blame] | 451 | /* Get the maximum ordinal for a Unicode character. */ |
Mark Hammond | 91a681d | 2002-08-12 07:21:58 +0000 | [diff] [blame] | 452 | PyAPI_FUNC(Py_UNICODE) PyUnicode_GetMax(void); |
Martin v. Löwis | ce9b5a5 | 2001-06-27 06:28:56 +0000 | [diff] [blame] | 453 | |
Guido van Rossum | 52c2359 | 2000-04-10 13:41:41 +0000 | [diff] [blame] | 454 | /* Resize an already allocated Unicode object to the new size length. |
| 455 | |
| 456 | *unicode is modified to point to the new (resized) object and 0 |
| 457 | returned on success. |
| 458 | |
| 459 | This API may only be called by the function which also called the |
| 460 | Unicode constructor. The refcount on the object must be 1. Otherwise, |
| 461 | an error is returned. |
| 462 | |
| 463 | Error handling is implemented as follows: an exception is set, -1 |
| 464 | is returned and *unicode left untouched. |
| 465 | |
| 466 | */ |
| 467 | |
Mark Hammond | 91a681d | 2002-08-12 07:21:58 +0000 | [diff] [blame] | 468 | PyAPI_FUNC(int) PyUnicode_Resize( |
Guido van Rossum | 52c2359 | 2000-04-10 13:41:41 +0000 | [diff] [blame] | 469 | PyObject **unicode, /* Pointer to the Unicode object */ |
Martin v. Löwis | 18e1655 | 2006-02-15 17:27:45 +0000 | [diff] [blame] | 470 | Py_ssize_t length /* New length */ |
Guido van Rossum | 52c2359 | 2000-04-10 13:41:41 +0000 | [diff] [blame] | 471 | ); |
| 472 | |
Guido van Rossum | d822518 | 2000-03-10 22:33:05 +0000 | [diff] [blame] | 473 | /* Coerce obj to an Unicode object and return a reference with |
| 474 | *incremented* refcount. |
| 475 | |
| 476 | Coercion is done in the following way: |
| 477 | |
Guido van Rossum | b8c65bc | 2001-10-19 02:01:31 +0000 | [diff] [blame] | 478 | 1. String and other char buffer compatible objects are decoded |
Fred Drake | cb093fe | 2000-05-09 19:51:53 +0000 | [diff] [blame] | 479 | under the assumptions that they contain data using the current |
| 480 | default encoding. Decoding is done in "strict" mode. |
Guido van Rossum | d822518 | 2000-03-10 22:33:05 +0000 | [diff] [blame] | 481 | |
Guido van Rossum | b8c65bc | 2001-10-19 02:01:31 +0000 | [diff] [blame] | 482 | 2. All other objects (including Unicode objects) raise an |
| 483 | exception. |
Guido van Rossum | d822518 | 2000-03-10 22:33:05 +0000 | [diff] [blame] | 484 | |
| 485 | The API returns NULL in case of an error. The caller is responsible |
| 486 | for decref'ing the returned objects. |
| 487 | |
| 488 | */ |
| 489 | |
Mark Hammond | 91a681d | 2002-08-12 07:21:58 +0000 | [diff] [blame] | 490 | PyAPI_FUNC(PyObject*) PyUnicode_FromEncodedObject( |
Marc-André Lemburg | 5a5c81a | 2000-07-07 13:46:42 +0000 | [diff] [blame] | 491 | register PyObject *obj, /* Object */ |
| 492 | const char *encoding, /* encoding */ |
| 493 | const char *errors /* error handling */ |
| 494 | ); |
| 495 | |
Guido van Rossum | b8c65bc | 2001-10-19 02:01:31 +0000 | [diff] [blame] | 496 | /* Coerce obj to an Unicode object and return a reference with |
Marc-André Lemburg | 5a5c81a | 2000-07-07 13:46:42 +0000 | [diff] [blame] | 497 | *incremented* refcount. |
Guido van Rossum | b8c65bc | 2001-10-19 02:01:31 +0000 | [diff] [blame] | 498 | |
| 499 | Unicode objects are passed back as-is (subclasses are converted to |
| 500 | true Unicode objects), all other objects are delegated to |
| 501 | PyUnicode_FromEncodedObject(obj, NULL, "strict") which results in |
| 502 | using the default encoding as basis for decoding the object. |
Marc-André Lemburg | 5a5c81a | 2000-07-07 13:46:42 +0000 | [diff] [blame] | 503 | |
| 504 | The API returns NULL in case of an error. The caller is responsible |
| 505 | for decref'ing the returned objects. |
| 506 | |
| 507 | */ |
| 508 | |
Mark Hammond | 91a681d | 2002-08-12 07:21:58 +0000 | [diff] [blame] | 509 | PyAPI_FUNC(PyObject*) PyUnicode_FromObject( |
Guido van Rossum | d822518 | 2000-03-10 22:33:05 +0000 | [diff] [blame] | 510 | register PyObject *obj /* Object */ |
| 511 | ); |
| 512 | |
| 513 | /* --- wchar_t support for platforms which support it --------------------- */ |
| 514 | |
| 515 | #ifdef HAVE_WCHAR_H |
| 516 | |
| 517 | /* Create a Unicode Object from the whcar_t buffer w of the given |
| 518 | size. |
| 519 | |
| 520 | The buffer is copied into the new object. */ |
| 521 | |
Mark Hammond | 91a681d | 2002-08-12 07:21:58 +0000 | [diff] [blame] | 522 | PyAPI_FUNC(PyObject*) PyUnicode_FromWideChar( |
Guido van Rossum | d822518 | 2000-03-10 22:33:05 +0000 | [diff] [blame] | 523 | register const wchar_t *w, /* wchar_t buffer */ |
Martin v. Löwis | 18e1655 | 2006-02-15 17:27:45 +0000 | [diff] [blame] | 524 | Py_ssize_t size /* size of buffer */ |
Guido van Rossum | d822518 | 2000-03-10 22:33:05 +0000 | [diff] [blame] | 525 | ); |
| 526 | |
Marc-André Lemburg | a9cadcd | 2004-11-22 13:02:31 +0000 | [diff] [blame] | 527 | /* Copies the Unicode Object contents into the wchar_t buffer w. At |
Guido van Rossum | d822518 | 2000-03-10 22:33:05 +0000 | [diff] [blame] | 528 | most size wchar_t characters are copied. |
| 529 | |
Marc-André Lemburg | a9cadcd | 2004-11-22 13:02:31 +0000 | [diff] [blame] | 530 | Note that the resulting wchar_t string may or may not be |
| 531 | 0-terminated. It is the responsibility of the caller to make sure |
| 532 | that the wchar_t string is 0-terminated in case this is required by |
| 533 | the application. |
| 534 | |
| 535 | Returns the number of wchar_t characters copied (excluding a |
| 536 | possibly trailing 0-termination character) or -1 in case of an |
Guido van Rossum | d822518 | 2000-03-10 22:33:05 +0000 | [diff] [blame] | 537 | error. */ |
| 538 | |
Martin v. Löwis | 18e1655 | 2006-02-15 17:27:45 +0000 | [diff] [blame] | 539 | PyAPI_FUNC(Py_ssize_t) PyUnicode_AsWideChar( |
Guido van Rossum | d822518 | 2000-03-10 22:33:05 +0000 | [diff] [blame] | 540 | PyUnicodeObject *unicode, /* Unicode object */ |
| 541 | register wchar_t *w, /* wchar_t buffer */ |
Martin v. Löwis | 18e1655 | 2006-02-15 17:27:45 +0000 | [diff] [blame] | 542 | Py_ssize_t size /* size of buffer */ |
Guido van Rossum | d822518 | 2000-03-10 22:33:05 +0000 | [diff] [blame] | 543 | ); |
| 544 | |
| 545 | #endif |
| 546 | |
Marc-André Lemburg | cc8764c | 2002-08-11 12:23:04 +0000 | [diff] [blame] | 547 | /* --- Unicode ordinals --------------------------------------------------- */ |
| 548 | |
| 549 | /* Create a Unicode Object from the given Unicode code point ordinal. |
| 550 | |
| 551 | The ordinal must be in range(0x10000) on narrow Python builds |
| 552 | (UCS2), and range(0x110000) on wide builds (UCS4). A ValueError is |
| 553 | raised in case it is not. |
| 554 | |
| 555 | */ |
| 556 | |
Marc-André Lemburg | 9c329de | 2002-08-12 08:19:10 +0000 | [diff] [blame] | 557 | PyAPI_FUNC(PyObject*) PyUnicode_FromOrdinal(int ordinal); |
Marc-André Lemburg | cc8764c | 2002-08-11 12:23:04 +0000 | [diff] [blame] | 558 | |
Guido van Rossum | d822518 | 2000-03-10 22:33:05 +0000 | [diff] [blame] | 559 | /* === Builtin Codecs ===================================================== |
| 560 | |
| 561 | Many of these APIs take two arguments encoding and errors. These |
| 562 | parameters encoding and errors have the same semantics as the ones |
| 563 | of the builtin unicode() API. |
| 564 | |
Fred Drake | cb093fe | 2000-05-09 19:51:53 +0000 | [diff] [blame] | 565 | Setting encoding to NULL causes the default encoding to be used. |
Guido van Rossum | d822518 | 2000-03-10 22:33:05 +0000 | [diff] [blame] | 566 | |
| 567 | Error handling is set by errors which may also be set to NULL |
| 568 | meaning to use the default handling defined for the codec. Default |
| 569 | error handling for all builtin codecs is "strict" (ValueErrors are |
| 570 | raised). |
| 571 | |
| 572 | The codecs all use a similar interface. Only deviation from the |
| 573 | generic ones are documented. |
| 574 | |
| 575 | */ |
| 576 | |
Fred Drake | cb093fe | 2000-05-09 19:51:53 +0000 | [diff] [blame] | 577 | /* --- Manage the default encoding ---------------------------------------- */ |
| 578 | |
Jeremy Hylton | 3ce4538 | 2001-07-30 22:34:24 +0000 | [diff] [blame] | 579 | /* Return a Python string holding the default encoded value of the |
| 580 | Unicode object. |
| 581 | |
| 582 | The resulting string is cached in the Unicode object for subsequent |
| 583 | usage by this function. The cached version is needed to implement |
| 584 | the character buffer interface and will live (at least) as long as |
| 585 | the Unicode object itself. |
| 586 | |
| 587 | The refcount of the string is *not* incremented. |
| 588 | |
| 589 | *** Exported for internal use by the interpreter only !!! *** |
| 590 | |
| 591 | */ |
| 592 | |
Mark Hammond | 91a681d | 2002-08-12 07:21:58 +0000 | [diff] [blame] | 593 | PyAPI_FUNC(PyObject *) _PyUnicode_AsDefaultEncodedString( |
Jeremy Hylton | 3ce4538 | 2001-07-30 22:34:24 +0000 | [diff] [blame] | 594 | PyObject *, const char *); |
| 595 | |
Fred Drake | cb093fe | 2000-05-09 19:51:53 +0000 | [diff] [blame] | 596 | /* Returns the currently active default encoding. |
| 597 | |
| 598 | The default encoding is currently implemented as run-time settable |
| 599 | process global. This may change in future versions of the |
| 600 | interpreter to become a parameter which is managed on a per-thread |
| 601 | basis. |
| 602 | |
| 603 | */ |
| 604 | |
Mark Hammond | 91a681d | 2002-08-12 07:21:58 +0000 | [diff] [blame] | 605 | PyAPI_FUNC(const char*) PyUnicode_GetDefaultEncoding(void); |
Fred Drake | cb093fe | 2000-05-09 19:51:53 +0000 | [diff] [blame] | 606 | |
| 607 | /* Sets the currently active default encoding. |
| 608 | |
| 609 | Returns 0 on success, -1 in case of an error. |
| 610 | |
| 611 | */ |
| 612 | |
Mark Hammond | 91a681d | 2002-08-12 07:21:58 +0000 | [diff] [blame] | 613 | PyAPI_FUNC(int) PyUnicode_SetDefaultEncoding( |
Fred Drake | cb093fe | 2000-05-09 19:51:53 +0000 | [diff] [blame] | 614 | const char *encoding /* Encoding name in standard form */ |
| 615 | ); |
| 616 | |
Guido van Rossum | d822518 | 2000-03-10 22:33:05 +0000 | [diff] [blame] | 617 | /* --- Generic Codecs ----------------------------------------------------- */ |
| 618 | |
| 619 | /* Create a Unicode object by decoding the encoded string s of the |
| 620 | given size. */ |
| 621 | |
Mark Hammond | 91a681d | 2002-08-12 07:21:58 +0000 | [diff] [blame] | 622 | PyAPI_FUNC(PyObject*) PyUnicode_Decode( |
Guido van Rossum | d822518 | 2000-03-10 22:33:05 +0000 | [diff] [blame] | 623 | const char *s, /* encoded string */ |
Martin v. Löwis | 18e1655 | 2006-02-15 17:27:45 +0000 | [diff] [blame] | 624 | Py_ssize_t size, /* size of buffer */ |
Guido van Rossum | d822518 | 2000-03-10 22:33:05 +0000 | [diff] [blame] | 625 | const char *encoding, /* encoding */ |
| 626 | const char *errors /* error handling */ |
| 627 | ); |
| 628 | |
| 629 | /* Encodes a Py_UNICODE buffer of the given size and returns a |
| 630 | Python string object. */ |
| 631 | |
Mark Hammond | 91a681d | 2002-08-12 07:21:58 +0000 | [diff] [blame] | 632 | PyAPI_FUNC(PyObject*) PyUnicode_Encode( |
Guido van Rossum | d822518 | 2000-03-10 22:33:05 +0000 | [diff] [blame] | 633 | const Py_UNICODE *s, /* Unicode char buffer */ |
Martin v. Löwis | 18e1655 | 2006-02-15 17:27:45 +0000 | [diff] [blame] | 634 | Py_ssize_t size, /* number of Py_UNICODE chars to encode */ |
Guido van Rossum | d822518 | 2000-03-10 22:33:05 +0000 | [diff] [blame] | 635 | const char *encoding, /* encoding */ |
| 636 | const char *errors /* error handling */ |
| 637 | ); |
| 638 | |
Marc-André Lemburg | d2d4598 | 2004-07-08 17:57:32 +0000 | [diff] [blame] | 639 | /* Encodes a Unicode object and returns the result as Python |
| 640 | object. */ |
| 641 | |
| 642 | PyAPI_FUNC(PyObject*) PyUnicode_AsEncodedObject( |
| 643 | PyObject *unicode, /* Unicode object */ |
| 644 | const char *encoding, /* encoding */ |
| 645 | const char *errors /* error handling */ |
| 646 | ); |
| 647 | |
Guido van Rossum | d822518 | 2000-03-10 22:33:05 +0000 | [diff] [blame] | 648 | /* Encodes a Unicode object and returns the result as Python string |
| 649 | object. */ |
| 650 | |
Mark Hammond | 91a681d | 2002-08-12 07:21:58 +0000 | [diff] [blame] | 651 | PyAPI_FUNC(PyObject*) PyUnicode_AsEncodedString( |
Guido van Rossum | d822518 | 2000-03-10 22:33:05 +0000 | [diff] [blame] | 652 | PyObject *unicode, /* Unicode object */ |
| 653 | const char *encoding, /* encoding */ |
| 654 | const char *errors /* error handling */ |
| 655 | ); |
| 656 | |
Thomas Wouters | 73e5a5b | 2006-06-08 15:35:45 +0000 | [diff] [blame] | 657 | PyAPI_FUNC(PyObject*) PyUnicode_BuildEncodingMap( |
| 658 | PyObject* string /* 256 character map */ |
| 659 | ); |
| 660 | |
| 661 | |
Marc-André Lemburg | c60e6f7 | 2001-09-20 10:35:46 +0000 | [diff] [blame] | 662 | /* --- UTF-7 Codecs ------------------------------------------------------- */ |
| 663 | |
Mark Hammond | 91a681d | 2002-08-12 07:21:58 +0000 | [diff] [blame] | 664 | PyAPI_FUNC(PyObject*) PyUnicode_DecodeUTF7( |
Marc-André Lemburg | c60e6f7 | 2001-09-20 10:35:46 +0000 | [diff] [blame] | 665 | const char *string, /* UTF-7 encoded string */ |
Martin v. Löwis | 18e1655 | 2006-02-15 17:27:45 +0000 | [diff] [blame] | 666 | Py_ssize_t length, /* size of string */ |
Marc-André Lemburg | c60e6f7 | 2001-09-20 10:35:46 +0000 | [diff] [blame] | 667 | const char *errors /* error handling */ |
| 668 | ); |
| 669 | |
Mark Hammond | 91a681d | 2002-08-12 07:21:58 +0000 | [diff] [blame] | 670 | PyAPI_FUNC(PyObject*) PyUnicode_EncodeUTF7( |
Marc-André Lemburg | c60e6f7 | 2001-09-20 10:35:46 +0000 | [diff] [blame] | 671 | const Py_UNICODE *data, /* Unicode char buffer */ |
Martin v. Löwis | 18e1655 | 2006-02-15 17:27:45 +0000 | [diff] [blame] | 672 | Py_ssize_t length, /* number of Py_UNICODE chars to encode */ |
Marc-André Lemburg | c60e6f7 | 2001-09-20 10:35:46 +0000 | [diff] [blame] | 673 | int encodeSetO, /* force the encoder to encode characters in |
| 674 | Set O, as described in RFC2152 */ |
| 675 | int encodeWhiteSpace, /* force the encoder to encode space, tab, |
| 676 | carriage return and linefeed characters */ |
| 677 | const char *errors /* error handling */ |
| 678 | ); |
| 679 | |
Guido van Rossum | d822518 | 2000-03-10 22:33:05 +0000 | [diff] [blame] | 680 | /* --- UTF-8 Codecs ------------------------------------------------------- */ |
| 681 | |
Mark Hammond | 91a681d | 2002-08-12 07:21:58 +0000 | [diff] [blame] | 682 | PyAPI_FUNC(PyObject*) PyUnicode_DecodeUTF8( |
Guido van Rossum | d822518 | 2000-03-10 22:33:05 +0000 | [diff] [blame] | 683 | const char *string, /* UTF-8 encoded string */ |
Martin v. Löwis | 18e1655 | 2006-02-15 17:27:45 +0000 | [diff] [blame] | 684 | Py_ssize_t length, /* size of string */ |
Guido van Rossum | d822518 | 2000-03-10 22:33:05 +0000 | [diff] [blame] | 685 | const char *errors /* error handling */ |
| 686 | ); |
| 687 | |
Walter Dörwald | 6965203 | 2004-09-07 20:24:22 +0000 | [diff] [blame] | 688 | PyAPI_FUNC(PyObject*) PyUnicode_DecodeUTF8Stateful( |
| 689 | const char *string, /* UTF-8 encoded string */ |
Martin v. Löwis | 18e1655 | 2006-02-15 17:27:45 +0000 | [diff] [blame] | 690 | Py_ssize_t length, /* size of string */ |
Walter Dörwald | 6965203 | 2004-09-07 20:24:22 +0000 | [diff] [blame] | 691 | const char *errors, /* error handling */ |
Martin v. Löwis | 18e1655 | 2006-02-15 17:27:45 +0000 | [diff] [blame] | 692 | Py_ssize_t *consumed /* bytes consumed */ |
Walter Dörwald | 6965203 | 2004-09-07 20:24:22 +0000 | [diff] [blame] | 693 | ); |
| 694 | |
Mark Hammond | 91a681d | 2002-08-12 07:21:58 +0000 | [diff] [blame] | 695 | PyAPI_FUNC(PyObject*) PyUnicode_AsUTF8String( |
Guido van Rossum | d822518 | 2000-03-10 22:33:05 +0000 | [diff] [blame] | 696 | PyObject *unicode /* Unicode object */ |
| 697 | ); |
| 698 | |
Mark Hammond | 91a681d | 2002-08-12 07:21:58 +0000 | [diff] [blame] | 699 | PyAPI_FUNC(PyObject*) PyUnicode_EncodeUTF8( |
Guido van Rossum | d822518 | 2000-03-10 22:33:05 +0000 | [diff] [blame] | 700 | const Py_UNICODE *data, /* Unicode char buffer */ |
Martin v. Löwis | 18e1655 | 2006-02-15 17:27:45 +0000 | [diff] [blame] | 701 | Py_ssize_t length, /* number of Py_UNICODE chars to encode */ |
Guido van Rossum | d822518 | 2000-03-10 22:33:05 +0000 | [diff] [blame] | 702 | const char *errors /* error handling */ |
| 703 | ); |
| 704 | |
| 705 | /* --- UTF-16 Codecs ------------------------------------------------------ */ |
| 706 | |
Guido van Rossum | 9e896b3 | 2000-04-05 20:11:21 +0000 | [diff] [blame] | 707 | /* Decodes length bytes from a UTF-16 encoded buffer string and returns |
Guido van Rossum | d822518 | 2000-03-10 22:33:05 +0000 | [diff] [blame] | 708 | the corresponding Unicode object. |
| 709 | |
| 710 | errors (if non-NULL) defines the error handling. It defaults |
| 711 | to "strict". |
| 712 | |
| 713 | If byteorder is non-NULL, the decoder starts decoding using the |
| 714 | given byte order: |
| 715 | |
| 716 | *byteorder == -1: little endian |
| 717 | *byteorder == 0: native order |
| 718 | *byteorder == 1: big endian |
| 719 | |
Marc-André Lemburg | 489b56e | 2001-05-21 20:30:15 +0000 | [diff] [blame] | 720 | In native mode, the first two bytes of the stream are checked for a |
| 721 | BOM mark. If found, the BOM mark is analysed, the byte order |
| 722 | adjusted and the BOM skipped. In the other modes, no BOM mark |
| 723 | interpretation is done. After completion, *byteorder is set to the |
| 724 | current byte order at the end of input data. |
Guido van Rossum | d822518 | 2000-03-10 22:33:05 +0000 | [diff] [blame] | 725 | |
| 726 | If byteorder is NULL, the codec starts in native order mode. |
| 727 | |
| 728 | */ |
| 729 | |
Mark Hammond | 91a681d | 2002-08-12 07:21:58 +0000 | [diff] [blame] | 730 | PyAPI_FUNC(PyObject*) PyUnicode_DecodeUTF16( |
Guido van Rossum | d822518 | 2000-03-10 22:33:05 +0000 | [diff] [blame] | 731 | const char *string, /* UTF-16 encoded string */ |
Martin v. Löwis | 18e1655 | 2006-02-15 17:27:45 +0000 | [diff] [blame] | 732 | Py_ssize_t length, /* size of string */ |
Guido van Rossum | d822518 | 2000-03-10 22:33:05 +0000 | [diff] [blame] | 733 | const char *errors, /* error handling */ |
| 734 | int *byteorder /* pointer to byteorder to use |
| 735 | 0=native;-1=LE,1=BE; updated on |
| 736 | exit */ |
| 737 | ); |
| 738 | |
Walter Dörwald | 6965203 | 2004-09-07 20:24:22 +0000 | [diff] [blame] | 739 | PyAPI_FUNC(PyObject*) PyUnicode_DecodeUTF16Stateful( |
| 740 | const char *string, /* UTF-16 encoded string */ |
Martin v. Löwis | 18e1655 | 2006-02-15 17:27:45 +0000 | [diff] [blame] | 741 | Py_ssize_t length, /* size of string */ |
Walter Dörwald | 6965203 | 2004-09-07 20:24:22 +0000 | [diff] [blame] | 742 | const char *errors, /* error handling */ |
| 743 | int *byteorder, /* pointer to byteorder to use |
| 744 | 0=native;-1=LE,1=BE; updated on |
| 745 | exit */ |
Martin v. Löwis | 18e1655 | 2006-02-15 17:27:45 +0000 | [diff] [blame] | 746 | Py_ssize_t *consumed /* bytes consumed */ |
Walter Dörwald | 6965203 | 2004-09-07 20:24:22 +0000 | [diff] [blame] | 747 | ); |
| 748 | |
Guido van Rossum | d822518 | 2000-03-10 22:33:05 +0000 | [diff] [blame] | 749 | /* Returns a Python string using the UTF-16 encoding in native byte |
| 750 | order. The string always starts with a BOM mark. */ |
| 751 | |
Mark Hammond | 91a681d | 2002-08-12 07:21:58 +0000 | [diff] [blame] | 752 | PyAPI_FUNC(PyObject*) PyUnicode_AsUTF16String( |
Guido van Rossum | d822518 | 2000-03-10 22:33:05 +0000 | [diff] [blame] | 753 | PyObject *unicode /* Unicode object */ |
| 754 | ); |
| 755 | |
| 756 | /* Returns a Python string object holding the UTF-16 encoded value of |
Guido van Rossum | 9e896b3 | 2000-04-05 20:11:21 +0000 | [diff] [blame] | 757 | the Unicode data. |
Guido van Rossum | d822518 | 2000-03-10 22:33:05 +0000 | [diff] [blame] | 758 | |
| 759 | If byteorder is not 0, output is written according to the following |
| 760 | byte order: |
| 761 | |
| 762 | byteorder == -1: little endian |
| 763 | byteorder == 0: native byte order (writes a BOM mark) |
| 764 | byteorder == 1: big endian |
| 765 | |
| 766 | If byteorder is 0, the output string will always start with the |
| 767 | Unicode BOM mark (U+FEFF). In the other two modes, no BOM mark is |
| 768 | prepended. |
| 769 | |
| 770 | Note that Py_UNICODE data is being interpreted as UTF-16 reduced to |
| 771 | UCS-2. This trick makes it possible to add full UTF-16 capabilities |
Thomas Wouters | 7e47402 | 2000-07-16 12:04:32 +0000 | [diff] [blame] | 772 | at a later point without compromising the APIs. |
Guido van Rossum | d822518 | 2000-03-10 22:33:05 +0000 | [diff] [blame] | 773 | |
| 774 | */ |
| 775 | |
Mark Hammond | 91a681d | 2002-08-12 07:21:58 +0000 | [diff] [blame] | 776 | PyAPI_FUNC(PyObject*) PyUnicode_EncodeUTF16( |
Guido van Rossum | d822518 | 2000-03-10 22:33:05 +0000 | [diff] [blame] | 777 | const Py_UNICODE *data, /* Unicode char buffer */ |
Martin v. Löwis | 18e1655 | 2006-02-15 17:27:45 +0000 | [diff] [blame] | 778 | Py_ssize_t length, /* number of Py_UNICODE chars to encode */ |
Guido van Rossum | d822518 | 2000-03-10 22:33:05 +0000 | [diff] [blame] | 779 | const char *errors, /* error handling */ |
| 780 | int byteorder /* byteorder to use 0=BOM+native;-1=LE,1=BE */ |
| 781 | ); |
| 782 | |
| 783 | /* --- Unicode-Escape Codecs ---------------------------------------------- */ |
| 784 | |
Mark Hammond | 91a681d | 2002-08-12 07:21:58 +0000 | [diff] [blame] | 785 | PyAPI_FUNC(PyObject*) PyUnicode_DecodeUnicodeEscape( |
Guido van Rossum | d822518 | 2000-03-10 22:33:05 +0000 | [diff] [blame] | 786 | const char *string, /* Unicode-Escape encoded string */ |
Martin v. Löwis | 18e1655 | 2006-02-15 17:27:45 +0000 | [diff] [blame] | 787 | Py_ssize_t length, /* size of string */ |
Guido van Rossum | d822518 | 2000-03-10 22:33:05 +0000 | [diff] [blame] | 788 | const char *errors /* error handling */ |
| 789 | ); |
| 790 | |
Mark Hammond | 91a681d | 2002-08-12 07:21:58 +0000 | [diff] [blame] | 791 | PyAPI_FUNC(PyObject*) PyUnicode_AsUnicodeEscapeString( |
Guido van Rossum | d822518 | 2000-03-10 22:33:05 +0000 | [diff] [blame] | 792 | PyObject *unicode /* Unicode object */ |
| 793 | ); |
| 794 | |
Mark Hammond | 91a681d | 2002-08-12 07:21:58 +0000 | [diff] [blame] | 795 | PyAPI_FUNC(PyObject*) PyUnicode_EncodeUnicodeEscape( |
Guido van Rossum | d822518 | 2000-03-10 22:33:05 +0000 | [diff] [blame] | 796 | const Py_UNICODE *data, /* Unicode char buffer */ |
Martin v. Löwis | 18e1655 | 2006-02-15 17:27:45 +0000 | [diff] [blame] | 797 | Py_ssize_t length /* Number of Py_UNICODE chars to encode */ |
Guido van Rossum | d822518 | 2000-03-10 22:33:05 +0000 | [diff] [blame] | 798 | ); |
| 799 | |
| 800 | /* --- Raw-Unicode-Escape Codecs ------------------------------------------ */ |
| 801 | |
Mark Hammond | 91a681d | 2002-08-12 07:21:58 +0000 | [diff] [blame] | 802 | PyAPI_FUNC(PyObject*) PyUnicode_DecodeRawUnicodeEscape( |
Guido van Rossum | d822518 | 2000-03-10 22:33:05 +0000 | [diff] [blame] | 803 | const char *string, /* Raw-Unicode-Escape encoded string */ |
Martin v. Löwis | 18e1655 | 2006-02-15 17:27:45 +0000 | [diff] [blame] | 804 | Py_ssize_t length, /* size of string */ |
Guido van Rossum | d822518 | 2000-03-10 22:33:05 +0000 | [diff] [blame] | 805 | const char *errors /* error handling */ |
| 806 | ); |
| 807 | |
Mark Hammond | 91a681d | 2002-08-12 07:21:58 +0000 | [diff] [blame] | 808 | PyAPI_FUNC(PyObject*) PyUnicode_AsRawUnicodeEscapeString( |
Guido van Rossum | d822518 | 2000-03-10 22:33:05 +0000 | [diff] [blame] | 809 | PyObject *unicode /* Unicode object */ |
| 810 | ); |
| 811 | |
Mark Hammond | 91a681d | 2002-08-12 07:21:58 +0000 | [diff] [blame] | 812 | PyAPI_FUNC(PyObject*) PyUnicode_EncodeRawUnicodeEscape( |
Guido van Rossum | d822518 | 2000-03-10 22:33:05 +0000 | [diff] [blame] | 813 | const Py_UNICODE *data, /* Unicode char buffer */ |
Martin v. Löwis | 18e1655 | 2006-02-15 17:27:45 +0000 | [diff] [blame] | 814 | Py_ssize_t length /* Number of Py_UNICODE chars to encode */ |
Guido van Rossum | d822518 | 2000-03-10 22:33:05 +0000 | [diff] [blame] | 815 | ); |
| 816 | |
Walter Dörwald | a47d1c0 | 2005-08-30 10:23:14 +0000 | [diff] [blame] | 817 | /* --- Unicode Internal Codec --------------------------------------------- |
| 818 | |
| 819 | Only for internal use in _codecsmodule.c */ |
| 820 | |
| 821 | PyObject *_PyUnicode_DecodeUnicodeInternal( |
| 822 | const char *string, |
Martin v. Löwis | 18e1655 | 2006-02-15 17:27:45 +0000 | [diff] [blame] | 823 | Py_ssize_t length, |
Walter Dörwald | a47d1c0 | 2005-08-30 10:23:14 +0000 | [diff] [blame] | 824 | const char *errors |
| 825 | ); |
| 826 | |
Guido van Rossum | d822518 | 2000-03-10 22:33:05 +0000 | [diff] [blame] | 827 | /* --- Latin-1 Codecs ----------------------------------------------------- |
| 828 | |
| 829 | Note: Latin-1 corresponds to the first 256 Unicode ordinals. |
| 830 | |
| 831 | */ |
| 832 | |
Mark Hammond | 91a681d | 2002-08-12 07:21:58 +0000 | [diff] [blame] | 833 | PyAPI_FUNC(PyObject*) PyUnicode_DecodeLatin1( |
Guido van Rossum | d822518 | 2000-03-10 22:33:05 +0000 | [diff] [blame] | 834 | const char *string, /* Latin-1 encoded string */ |
Martin v. Löwis | 18e1655 | 2006-02-15 17:27:45 +0000 | [diff] [blame] | 835 | Py_ssize_t length, /* size of string */ |
Guido van Rossum | d822518 | 2000-03-10 22:33:05 +0000 | [diff] [blame] | 836 | const char *errors /* error handling */ |
| 837 | ); |
| 838 | |
Mark Hammond | 91a681d | 2002-08-12 07:21:58 +0000 | [diff] [blame] | 839 | PyAPI_FUNC(PyObject*) PyUnicode_AsLatin1String( |
Guido van Rossum | d822518 | 2000-03-10 22:33:05 +0000 | [diff] [blame] | 840 | PyObject *unicode /* Unicode object */ |
| 841 | ); |
| 842 | |
Mark Hammond | 91a681d | 2002-08-12 07:21:58 +0000 | [diff] [blame] | 843 | PyAPI_FUNC(PyObject*) PyUnicode_EncodeLatin1( |
Guido van Rossum | d822518 | 2000-03-10 22:33:05 +0000 | [diff] [blame] | 844 | const Py_UNICODE *data, /* Unicode char buffer */ |
Martin v. Löwis | 18e1655 | 2006-02-15 17:27:45 +0000 | [diff] [blame] | 845 | Py_ssize_t length, /* Number of Py_UNICODE chars to encode */ |
Guido van Rossum | d822518 | 2000-03-10 22:33:05 +0000 | [diff] [blame] | 846 | const char *errors /* error handling */ |
| 847 | ); |
| 848 | |
| 849 | /* --- ASCII Codecs ------------------------------------------------------- |
| 850 | |
| 851 | Only 7-bit ASCII data is excepted. All other codes generate errors. |
| 852 | |
| 853 | */ |
| 854 | |
Mark Hammond | 91a681d | 2002-08-12 07:21:58 +0000 | [diff] [blame] | 855 | PyAPI_FUNC(PyObject*) PyUnicode_DecodeASCII( |
Guido van Rossum | d822518 | 2000-03-10 22:33:05 +0000 | [diff] [blame] | 856 | const char *string, /* ASCII encoded string */ |
Martin v. Löwis | 18e1655 | 2006-02-15 17:27:45 +0000 | [diff] [blame] | 857 | Py_ssize_t length, /* size of string */ |
Guido van Rossum | d822518 | 2000-03-10 22:33:05 +0000 | [diff] [blame] | 858 | const char *errors /* error handling */ |
| 859 | ); |
| 860 | |
Mark Hammond | 91a681d | 2002-08-12 07:21:58 +0000 | [diff] [blame] | 861 | PyAPI_FUNC(PyObject*) PyUnicode_AsASCIIString( |
Guido van Rossum | d822518 | 2000-03-10 22:33:05 +0000 | [diff] [blame] | 862 | PyObject *unicode /* Unicode object */ |
| 863 | ); |
| 864 | |
Mark Hammond | 91a681d | 2002-08-12 07:21:58 +0000 | [diff] [blame] | 865 | PyAPI_FUNC(PyObject*) PyUnicode_EncodeASCII( |
Guido van Rossum | d822518 | 2000-03-10 22:33:05 +0000 | [diff] [blame] | 866 | const Py_UNICODE *data, /* Unicode char buffer */ |
Martin v. Löwis | 18e1655 | 2006-02-15 17:27:45 +0000 | [diff] [blame] | 867 | Py_ssize_t length, /* Number of Py_UNICODE chars to encode */ |
Guido van Rossum | d822518 | 2000-03-10 22:33:05 +0000 | [diff] [blame] | 868 | const char *errors /* error handling */ |
| 869 | ); |
| 870 | |
| 871 | /* --- Character Map Codecs ----------------------------------------------- |
| 872 | |
| 873 | This codec uses mappings to encode and decode characters. |
| 874 | |
| 875 | Decoding mappings must map single string characters to single |
| 876 | Unicode characters, integers (which are then interpreted as Unicode |
| 877 | ordinals) or None (meaning "undefined mapping" and causing an |
| 878 | error). |
| 879 | |
| 880 | Encoding mappings must map single Unicode characters to single |
| 881 | string characters, integers (which are then interpreted as Latin-1 |
| 882 | ordinals) or None (meaning "undefined mapping" and causing an |
| 883 | error). |
| 884 | |
| 885 | If a character lookup fails with a LookupError, the character is |
| 886 | copied as-is meaning that its ordinal value will be interpreted as |
| 887 | Unicode or Latin-1 ordinal resp. Because of this mappings only need |
| 888 | to contain those mappings which map characters to different code |
| 889 | points. |
| 890 | |
| 891 | */ |
| 892 | |
Mark Hammond | 91a681d | 2002-08-12 07:21:58 +0000 | [diff] [blame] | 893 | PyAPI_FUNC(PyObject*) PyUnicode_DecodeCharmap( |
Guido van Rossum | d822518 | 2000-03-10 22:33:05 +0000 | [diff] [blame] | 894 | const char *string, /* Encoded string */ |
Martin v. Löwis | 18e1655 | 2006-02-15 17:27:45 +0000 | [diff] [blame] | 895 | Py_ssize_t length, /* size of string */ |
Guido van Rossum | d822518 | 2000-03-10 22:33:05 +0000 | [diff] [blame] | 896 | PyObject *mapping, /* character mapping |
| 897 | (char ordinal -> unicode ordinal) */ |
| 898 | const char *errors /* error handling */ |
| 899 | ); |
| 900 | |
Mark Hammond | 91a681d | 2002-08-12 07:21:58 +0000 | [diff] [blame] | 901 | PyAPI_FUNC(PyObject*) PyUnicode_AsCharmapString( |
Guido van Rossum | d822518 | 2000-03-10 22:33:05 +0000 | [diff] [blame] | 902 | PyObject *unicode, /* Unicode object */ |
| 903 | PyObject *mapping /* character mapping |
| 904 | (unicode ordinal -> char ordinal) */ |
| 905 | ); |
| 906 | |
Mark Hammond | 91a681d | 2002-08-12 07:21:58 +0000 | [diff] [blame] | 907 | PyAPI_FUNC(PyObject*) PyUnicode_EncodeCharmap( |
Guido van Rossum | d822518 | 2000-03-10 22:33:05 +0000 | [diff] [blame] | 908 | const Py_UNICODE *data, /* Unicode char buffer */ |
Martin v. Löwis | 18e1655 | 2006-02-15 17:27:45 +0000 | [diff] [blame] | 909 | Py_ssize_t length, /* Number of Py_UNICODE chars to encode */ |
Guido van Rossum | d822518 | 2000-03-10 22:33:05 +0000 | [diff] [blame] | 910 | PyObject *mapping, /* character mapping |
| 911 | (unicode ordinal -> char ordinal) */ |
| 912 | const char *errors /* error handling */ |
| 913 | ); |
| 914 | |
| 915 | /* Translate a Py_UNICODE buffer of the given length by applying a |
| 916 | character mapping table to it and return the resulting Unicode |
| 917 | object. |
| 918 | |
| 919 | The mapping table must map Unicode ordinal integers to Unicode |
| 920 | ordinal integers or None (causing deletion of the character). |
| 921 | |
| 922 | Mapping tables may be dictionaries or sequences. Unmapped character |
| 923 | ordinals (ones which cause a LookupError) are left untouched and |
| 924 | are copied as-is. |
| 925 | |
| 926 | */ |
| 927 | |
Mark Hammond | 91a681d | 2002-08-12 07:21:58 +0000 | [diff] [blame] | 928 | PyAPI_FUNC(PyObject *) PyUnicode_TranslateCharmap( |
Guido van Rossum | d822518 | 2000-03-10 22:33:05 +0000 | [diff] [blame] | 929 | const Py_UNICODE *data, /* Unicode char buffer */ |
Martin v. Löwis | 18e1655 | 2006-02-15 17:27:45 +0000 | [diff] [blame] | 930 | Py_ssize_t length, /* Number of Py_UNICODE chars to encode */ |
Guido van Rossum | d822518 | 2000-03-10 22:33:05 +0000 | [diff] [blame] | 931 | PyObject *table, /* Translate table */ |
| 932 | const char *errors /* error handling */ |
| 933 | ); |
| 934 | |
Guido van Rossum | efec115 | 2000-03-28 02:01:15 +0000 | [diff] [blame] | 935 | #ifdef MS_WIN32 |
Guido van Rossum | 24bdb04 | 2000-03-28 20:29:59 +0000 | [diff] [blame] | 936 | |
Guido van Rossum | efec115 | 2000-03-28 02:01:15 +0000 | [diff] [blame] | 937 | /* --- MBCS codecs for Windows -------------------------------------------- */ |
Guido van Rossum | 24bdb04 | 2000-03-28 20:29:59 +0000 | [diff] [blame] | 938 | |
Mark Hammond | 91a681d | 2002-08-12 07:21:58 +0000 | [diff] [blame] | 939 | PyAPI_FUNC(PyObject*) PyUnicode_DecodeMBCS( |
Guido van Rossum | efec115 | 2000-03-28 02:01:15 +0000 | [diff] [blame] | 940 | const char *string, /* MBCS encoded string */ |
Martin v. Löwis | 18e1655 | 2006-02-15 17:27:45 +0000 | [diff] [blame] | 941 | Py_ssize_t length, /* size of string */ |
Guido van Rossum | efec115 | 2000-03-28 02:01:15 +0000 | [diff] [blame] | 942 | const char *errors /* error handling */ |
| 943 | ); |
| 944 | |
Thomas Wouters | 0e3f591 | 2006-08-11 14:57:12 +0000 | [diff] [blame] | 945 | PyAPI_FUNC(PyObject*) PyUnicode_DecodeMBCSStateful( |
| 946 | const char *string, /* MBCS encoded string */ |
| 947 | Py_ssize_t length, /* size of string */ |
| 948 | const char *errors, /* error handling */ |
| 949 | Py_ssize_t *consumed /* bytes consumed */ |
| 950 | ); |
| 951 | |
Mark Hammond | 91a681d | 2002-08-12 07:21:58 +0000 | [diff] [blame] | 952 | PyAPI_FUNC(PyObject*) PyUnicode_AsMBCSString( |
Guido van Rossum | efec115 | 2000-03-28 02:01:15 +0000 | [diff] [blame] | 953 | PyObject *unicode /* Unicode object */ |
| 954 | ); |
| 955 | |
Mark Hammond | 91a681d | 2002-08-12 07:21:58 +0000 | [diff] [blame] | 956 | PyAPI_FUNC(PyObject*) PyUnicode_EncodeMBCS( |
Guido van Rossum | efec115 | 2000-03-28 02:01:15 +0000 | [diff] [blame] | 957 | const Py_UNICODE *data, /* Unicode char buffer */ |
Martin v. Löwis | 18e1655 | 2006-02-15 17:27:45 +0000 | [diff] [blame] | 958 | Py_ssize_t length, /* Number of Py_UNICODE chars to encode */ |
Guido van Rossum | efec115 | 2000-03-28 02:01:15 +0000 | [diff] [blame] | 959 | const char *errors /* error handling */ |
| 960 | ); |
| 961 | |
Guido van Rossum | efec115 | 2000-03-28 02:01:15 +0000 | [diff] [blame] | 962 | #endif /* MS_WIN32 */ |
Guido van Rossum | 24bdb04 | 2000-03-28 20:29:59 +0000 | [diff] [blame] | 963 | |
Guido van Rossum | 9e896b3 | 2000-04-05 20:11:21 +0000 | [diff] [blame] | 964 | /* --- Decimal Encoder ---------------------------------------------------- */ |
| 965 | |
| 966 | /* Takes a Unicode string holding a decimal value and writes it into |
| 967 | an output buffer using standard ASCII digit codes. |
| 968 | |
| 969 | The output buffer has to provide at least length+1 bytes of storage |
| 970 | area. The output string is 0-terminated. |
| 971 | |
| 972 | The encoder converts whitespace to ' ', decimal characters to their |
| 973 | corresponding ASCII digit and all other Latin-1 characters except |
| 974 | \0 as-is. Characters outside this range (Unicode ordinals 1-256) |
| 975 | are treated as errors. This includes embedded NULL bytes. |
| 976 | |
| 977 | Error handling is defined by the errors argument: |
| 978 | |
| 979 | NULL or "strict": raise a ValueError |
| 980 | "ignore": ignore the wrong characters (these are not copied to the |
| 981 | output buffer) |
| 982 | "replace": replaces illegal characters with '?' |
| 983 | |
| 984 | Returns 0 on success, -1 on failure. |
| 985 | |
| 986 | */ |
| 987 | |
Mark Hammond | 91a681d | 2002-08-12 07:21:58 +0000 | [diff] [blame] | 988 | PyAPI_FUNC(int) PyUnicode_EncodeDecimal( |
Guido van Rossum | 9e896b3 | 2000-04-05 20:11:21 +0000 | [diff] [blame] | 989 | Py_UNICODE *s, /* Unicode buffer */ |
Martin v. Löwis | 18e1655 | 2006-02-15 17:27:45 +0000 | [diff] [blame] | 990 | Py_ssize_t length, /* Number of Py_UNICODE chars to encode */ |
Guido van Rossum | 9e896b3 | 2000-04-05 20:11:21 +0000 | [diff] [blame] | 991 | char *output, /* Output buffer; must have size >= length */ |
| 992 | const char *errors /* error handling */ |
| 993 | ); |
| 994 | |
Guido van Rossum | d822518 | 2000-03-10 22:33:05 +0000 | [diff] [blame] | 995 | /* --- Methods & Slots ---------------------------------------------------- |
| 996 | |
| 997 | These are capable of handling Unicode objects and strings on input |
| 998 | (we refer to them as strings in the descriptions) and return |
| 999 | Unicode objects or integers as apporpriate. */ |
| 1000 | |
| 1001 | /* Concat two strings giving a new Unicode string. */ |
| 1002 | |
Mark Hammond | 91a681d | 2002-08-12 07:21:58 +0000 | [diff] [blame] | 1003 | PyAPI_FUNC(PyObject*) PyUnicode_Concat( |
Guido van Rossum | d822518 | 2000-03-10 22:33:05 +0000 | [diff] [blame] | 1004 | PyObject *left, /* Left string */ |
| 1005 | PyObject *right /* Right string */ |
| 1006 | ); |
| 1007 | |
| 1008 | /* Split a string giving a list of Unicode strings. |
| 1009 | |
| 1010 | If sep is NULL, splitting will be done at all whitespace |
| 1011 | substrings. Otherwise, splits occur at the given separator. |
| 1012 | |
| 1013 | At most maxsplit splits will be done. If negative, no limit is set. |
| 1014 | |
| 1015 | Separators are not included in the resulting list. |
| 1016 | |
| 1017 | */ |
| 1018 | |
Mark Hammond | 91a681d | 2002-08-12 07:21:58 +0000 | [diff] [blame] | 1019 | PyAPI_FUNC(PyObject*) PyUnicode_Split( |
Guido van Rossum | d822518 | 2000-03-10 22:33:05 +0000 | [diff] [blame] | 1020 | PyObject *s, /* String to split */ |
| 1021 | PyObject *sep, /* String separator */ |
Martin v. Löwis | 18e1655 | 2006-02-15 17:27:45 +0000 | [diff] [blame] | 1022 | Py_ssize_t maxsplit /* Maxsplit count */ |
Guido van Rossum | d822518 | 2000-03-10 22:33:05 +0000 | [diff] [blame] | 1023 | ); |
| 1024 | |
| 1025 | /* Dito, but split at line breaks. |
| 1026 | |
| 1027 | CRLF is considered to be one line break. Line breaks are not |
| 1028 | included in the resulting list. */ |
| 1029 | |
Mark Hammond | 91a681d | 2002-08-12 07:21:58 +0000 | [diff] [blame] | 1030 | PyAPI_FUNC(PyObject*) PyUnicode_Splitlines( |
Guido van Rossum | d822518 | 2000-03-10 22:33:05 +0000 | [diff] [blame] | 1031 | PyObject *s, /* String to split */ |
Guido van Rossum | 004d64f | 2000-04-11 15:39:46 +0000 | [diff] [blame] | 1032 | int keepends /* If true, line end markers are included */ |
Guido van Rossum | d822518 | 2000-03-10 22:33:05 +0000 | [diff] [blame] | 1033 | ); |
| 1034 | |
Thomas Wouters | 477c8d5 | 2006-05-27 19:21:47 +0000 | [diff] [blame] | 1035 | /* Partition a string using a given separator. */ |
| 1036 | |
| 1037 | PyAPI_FUNC(PyObject*) PyUnicode_Partition( |
| 1038 | PyObject *s, /* String to partition */ |
| 1039 | PyObject *sep /* String separator */ |
| 1040 | ); |
| 1041 | |
| 1042 | /* Partition a string using a given separator, searching from the end of the |
| 1043 | string. */ |
| 1044 | |
| 1045 | PyAPI_FUNC(PyObject*) PyUnicode_RPartition( |
| 1046 | PyObject *s, /* String to partition */ |
| 1047 | PyObject *sep /* String separator */ |
| 1048 | ); |
| 1049 | |
Hye-Shik Chang | 3ae811b | 2003-12-15 18:49:53 +0000 | [diff] [blame] | 1050 | /* Split a string giving a list of Unicode strings. |
| 1051 | |
| 1052 | If sep is NULL, splitting will be done at all whitespace |
| 1053 | substrings. Otherwise, splits occur at the given separator. |
| 1054 | |
| 1055 | At most maxsplit splits will be done. But unlike PyUnicode_Split |
| 1056 | PyUnicode_RSplit splits from the end of the string. If negative, |
| 1057 | no limit is set. |
| 1058 | |
| 1059 | Separators are not included in the resulting list. |
| 1060 | |
| 1061 | */ |
| 1062 | |
| 1063 | PyAPI_FUNC(PyObject*) PyUnicode_RSplit( |
| 1064 | PyObject *s, /* String to split */ |
| 1065 | PyObject *sep, /* String separator */ |
Martin v. Löwis | 18e1655 | 2006-02-15 17:27:45 +0000 | [diff] [blame] | 1066 | Py_ssize_t maxsplit /* Maxsplit count */ |
Hye-Shik Chang | 3ae811b | 2003-12-15 18:49:53 +0000 | [diff] [blame] | 1067 | ); |
| 1068 | |
Guido van Rossum | d822518 | 2000-03-10 22:33:05 +0000 | [diff] [blame] | 1069 | /* Translate a string by applying a character mapping table to it and |
| 1070 | return the resulting Unicode object. |
| 1071 | |
| 1072 | The mapping table must map Unicode ordinal integers to Unicode |
| 1073 | ordinal integers or None (causing deletion of the character). |
| 1074 | |
| 1075 | Mapping tables may be dictionaries or sequences. Unmapped character |
| 1076 | ordinals (ones which cause a LookupError) are left untouched and |
| 1077 | are copied as-is. |
| 1078 | |
| 1079 | */ |
| 1080 | |
Mark Hammond | 91a681d | 2002-08-12 07:21:58 +0000 | [diff] [blame] | 1081 | PyAPI_FUNC(PyObject *) PyUnicode_Translate( |
Guido van Rossum | d822518 | 2000-03-10 22:33:05 +0000 | [diff] [blame] | 1082 | PyObject *str, /* String */ |
| 1083 | PyObject *table, /* Translate table */ |
| 1084 | const char *errors /* error handling */ |
| 1085 | ); |
| 1086 | |
| 1087 | /* Join a sequence of strings using the given separator and return |
| 1088 | the resulting Unicode string. */ |
| 1089 | |
Mark Hammond | 91a681d | 2002-08-12 07:21:58 +0000 | [diff] [blame] | 1090 | PyAPI_FUNC(PyObject*) PyUnicode_Join( |
Guido van Rossum | d822518 | 2000-03-10 22:33:05 +0000 | [diff] [blame] | 1091 | PyObject *separator, /* Separator string */ |
| 1092 | PyObject *seq /* Sequence object */ |
| 1093 | ); |
| 1094 | |
| 1095 | /* Return 1 if substr matches str[start:end] at the given tail end, 0 |
| 1096 | otherwise. */ |
| 1097 | |
Martin v. Löwis | 18e1655 | 2006-02-15 17:27:45 +0000 | [diff] [blame] | 1098 | PyAPI_FUNC(Py_ssize_t) PyUnicode_Tailmatch( |
Guido van Rossum | d822518 | 2000-03-10 22:33:05 +0000 | [diff] [blame] | 1099 | PyObject *str, /* String */ |
| 1100 | PyObject *substr, /* Prefix or Suffix string */ |
Martin v. Löwis | 18e1655 | 2006-02-15 17:27:45 +0000 | [diff] [blame] | 1101 | Py_ssize_t start, /* Start index */ |
| 1102 | Py_ssize_t end, /* Stop index */ |
Guido van Rossum | d822518 | 2000-03-10 22:33:05 +0000 | [diff] [blame] | 1103 | int direction /* Tail end: -1 prefix, +1 suffix */ |
| 1104 | ); |
| 1105 | |
| 1106 | /* Return the first position of substr in str[start:end] using the |
Marc-André Lemburg | 4da6fd6 | 2002-05-29 11:33:13 +0000 | [diff] [blame] | 1107 | given search direction or -1 if not found. -2 is returned in case |
| 1108 | an error occurred and an exception is set. */ |
Guido van Rossum | d822518 | 2000-03-10 22:33:05 +0000 | [diff] [blame] | 1109 | |
Martin v. Löwis | 18e1655 | 2006-02-15 17:27:45 +0000 | [diff] [blame] | 1110 | PyAPI_FUNC(Py_ssize_t) PyUnicode_Find( |
Guido van Rossum | d822518 | 2000-03-10 22:33:05 +0000 | [diff] [blame] | 1111 | PyObject *str, /* String */ |
| 1112 | PyObject *substr, /* Substring to find */ |
Martin v. Löwis | 18e1655 | 2006-02-15 17:27:45 +0000 | [diff] [blame] | 1113 | Py_ssize_t start, /* Start index */ |
| 1114 | Py_ssize_t end, /* Stop index */ |
Guido van Rossum | d822518 | 2000-03-10 22:33:05 +0000 | [diff] [blame] | 1115 | int direction /* Find direction: +1 forward, -1 backward */ |
| 1116 | ); |
| 1117 | |
Barry Warsaw | 51ac580 | 2000-03-20 16:36:48 +0000 | [diff] [blame] | 1118 | /* Count the number of occurrences of substr in str[start:end]. */ |
Guido van Rossum | d822518 | 2000-03-10 22:33:05 +0000 | [diff] [blame] | 1119 | |
Martin v. Löwis | 18e1655 | 2006-02-15 17:27:45 +0000 | [diff] [blame] | 1120 | PyAPI_FUNC(Py_ssize_t) PyUnicode_Count( |
Guido van Rossum | d822518 | 2000-03-10 22:33:05 +0000 | [diff] [blame] | 1121 | PyObject *str, /* String */ |
| 1122 | PyObject *substr, /* Substring to count */ |
Martin v. Löwis | 18e1655 | 2006-02-15 17:27:45 +0000 | [diff] [blame] | 1123 | Py_ssize_t start, /* Start index */ |
| 1124 | Py_ssize_t end /* Stop index */ |
Guido van Rossum | d822518 | 2000-03-10 22:33:05 +0000 | [diff] [blame] | 1125 | ); |
| 1126 | |
Barry Warsaw | 51ac580 | 2000-03-20 16:36:48 +0000 | [diff] [blame] | 1127 | /* Replace at most maxcount occurrences of substr in str with replstr |
Guido van Rossum | d822518 | 2000-03-10 22:33:05 +0000 | [diff] [blame] | 1128 | and return the resulting Unicode object. */ |
| 1129 | |
Mark Hammond | 91a681d | 2002-08-12 07:21:58 +0000 | [diff] [blame] | 1130 | PyAPI_FUNC(PyObject *) PyUnicode_Replace( |
Guido van Rossum | d822518 | 2000-03-10 22:33:05 +0000 | [diff] [blame] | 1131 | PyObject *str, /* String */ |
| 1132 | PyObject *substr, /* Substring to find */ |
| 1133 | PyObject *replstr, /* Substring to replace */ |
Martin v. Löwis | 18e1655 | 2006-02-15 17:27:45 +0000 | [diff] [blame] | 1134 | Py_ssize_t maxcount /* Max. number of replacements to apply; |
Guido van Rossum | d822518 | 2000-03-10 22:33:05 +0000 | [diff] [blame] | 1135 | -1 = all */ |
| 1136 | ); |
| 1137 | |
| 1138 | /* Compare two strings and return -1, 0, 1 for less than, equal, |
| 1139 | greater than resp. */ |
| 1140 | |
Mark Hammond | 91a681d | 2002-08-12 07:21:58 +0000 | [diff] [blame] | 1141 | PyAPI_FUNC(int) PyUnicode_Compare( |
Guido van Rossum | d822518 | 2000-03-10 22:33:05 +0000 | [diff] [blame] | 1142 | PyObject *left, /* Left string */ |
| 1143 | PyObject *right /* Right string */ |
| 1144 | ); |
| 1145 | |
Thomas Wouters | 00ee7ba | 2006-08-21 19:07:27 +0000 | [diff] [blame] | 1146 | /* Rich compare two strings and return one of the following: |
| 1147 | |
| 1148 | - NULL in case an exception was raised |
| 1149 | - Py_True or Py_False for successfuly comparisons |
| 1150 | - Py_NotImplemented in case the type combination is unknown |
| 1151 | |
| 1152 | Note that Py_EQ and Py_NE comparisons can cause a UnicodeWarning in |
| 1153 | case the conversion of the arguments to Unicode fails with a |
| 1154 | UnicodeDecodeError. |
| 1155 | |
| 1156 | Possible values for op: |
| 1157 | |
| 1158 | Py_GT, Py_GE, Py_EQ, Py_NE, Py_LT, Py_LE |
| 1159 | |
| 1160 | */ |
| 1161 | |
| 1162 | PyAPI_FUNC(PyObject *) PyUnicode_RichCompare( |
| 1163 | PyObject *left, /* Left string */ |
| 1164 | PyObject *right, /* Right string */ |
| 1165 | int op /* Operation: Py_EQ, Py_NE, Py_GT, etc. */ |
| 1166 | ); |
| 1167 | |
Thomas Wouters | 7e47402 | 2000-07-16 12:04:32 +0000 | [diff] [blame] | 1168 | /* Apply a argument tuple or dictionary to a format string and return |
Guido van Rossum | d822518 | 2000-03-10 22:33:05 +0000 | [diff] [blame] | 1169 | the resulting Unicode string. */ |
| 1170 | |
Mark Hammond | 91a681d | 2002-08-12 07:21:58 +0000 | [diff] [blame] | 1171 | PyAPI_FUNC(PyObject *) PyUnicode_Format( |
Guido van Rossum | d822518 | 2000-03-10 22:33:05 +0000 | [diff] [blame] | 1172 | PyObject *format, /* Format string */ |
| 1173 | PyObject *args /* Argument tuple or dictionary */ |
| 1174 | ); |
| 1175 | |
Guido van Rossum | d0d366b | 2000-03-13 23:22:24 +0000 | [diff] [blame] | 1176 | /* Checks whether element is contained in container and return 1/0 |
| 1177 | accordingly. |
| 1178 | |
| 1179 | element has to coerce to an one element Unicode string. -1 is |
| 1180 | returned in case of an error. */ |
| 1181 | |
Mark Hammond | 91a681d | 2002-08-12 07:21:58 +0000 | [diff] [blame] | 1182 | PyAPI_FUNC(int) PyUnicode_Contains( |
Guido van Rossum | d0d366b | 2000-03-13 23:22:24 +0000 | [diff] [blame] | 1183 | PyObject *container, /* Container string */ |
| 1184 | PyObject *element /* Element string */ |
| 1185 | ); |
| 1186 | |
Walter Dörwald | de02bcb | 2002-04-22 17:42:37 +0000 | [diff] [blame] | 1187 | /* Externally visible for str.strip(unicode) */ |
Mark Hammond | 91a681d | 2002-08-12 07:21:58 +0000 | [diff] [blame] | 1188 | PyAPI_FUNC(PyObject *) _PyUnicode_XStrip( |
Walter Dörwald | de02bcb | 2002-04-22 17:42:37 +0000 | [diff] [blame] | 1189 | PyUnicodeObject *self, |
| 1190 | int striptype, |
| 1191 | PyObject *sepobj |
| 1192 | ); |
| 1193 | |
Guido van Rossum | d822518 | 2000-03-10 22:33:05 +0000 | [diff] [blame] | 1194 | /* === Characters Type APIs =============================================== */ |
| 1195 | |
| 1196 | /* These should not be used directly. Use the Py_UNICODE_IS* and |
| 1197 | Py_UNICODE_TO* macros instead. |
| 1198 | |
| 1199 | These APIs are implemented in Objects/unicodectype.c. |
| 1200 | |
| 1201 | */ |
| 1202 | |
Mark Hammond | 91a681d | 2002-08-12 07:21:58 +0000 | [diff] [blame] | 1203 | PyAPI_FUNC(int) _PyUnicode_IsLowercase( |
Fredrik Lundh | 72b0685 | 2001-06-27 22:08:26 +0000 | [diff] [blame] | 1204 | Py_UNICODE ch /* Unicode character */ |
Guido van Rossum | d822518 | 2000-03-10 22:33:05 +0000 | [diff] [blame] | 1205 | ); |
| 1206 | |
Mark Hammond | 91a681d | 2002-08-12 07:21:58 +0000 | [diff] [blame] | 1207 | PyAPI_FUNC(int) _PyUnicode_IsUppercase( |
Fredrik Lundh | 72b0685 | 2001-06-27 22:08:26 +0000 | [diff] [blame] | 1208 | Py_UNICODE ch /* Unicode character */ |
Guido van Rossum | d822518 | 2000-03-10 22:33:05 +0000 | [diff] [blame] | 1209 | ); |
| 1210 | |
Mark Hammond | 91a681d | 2002-08-12 07:21:58 +0000 | [diff] [blame] | 1211 | PyAPI_FUNC(int) _PyUnicode_IsTitlecase( |
Fredrik Lundh | 72b0685 | 2001-06-27 22:08:26 +0000 | [diff] [blame] | 1212 | Py_UNICODE ch /* Unicode character */ |
Guido van Rossum | d822518 | 2000-03-10 22:33:05 +0000 | [diff] [blame] | 1213 | ); |
| 1214 | |
Mark Hammond | 91a681d | 2002-08-12 07:21:58 +0000 | [diff] [blame] | 1215 | PyAPI_FUNC(int) _PyUnicode_IsWhitespace( |
Tim Peters | 2576c97 | 2005-10-29 02:33:18 +0000 | [diff] [blame] | 1216 | const Py_UNICODE ch /* Unicode character */ |
Guido van Rossum | d822518 | 2000-03-10 22:33:05 +0000 | [diff] [blame] | 1217 | ); |
| 1218 | |
Mark Hammond | 91a681d | 2002-08-12 07:21:58 +0000 | [diff] [blame] | 1219 | PyAPI_FUNC(int) _PyUnicode_IsLinebreak( |
Tim Peters | 2576c97 | 2005-10-29 02:33:18 +0000 | [diff] [blame] | 1220 | const Py_UNICODE ch /* Unicode character */ |
Guido van Rossum | d822518 | 2000-03-10 22:33:05 +0000 | [diff] [blame] | 1221 | ); |
| 1222 | |
Mark Hammond | 91a681d | 2002-08-12 07:21:58 +0000 | [diff] [blame] | 1223 | PyAPI_FUNC(Py_UNICODE) _PyUnicode_ToLowercase( |
Fredrik Lundh | 72b0685 | 2001-06-27 22:08:26 +0000 | [diff] [blame] | 1224 | Py_UNICODE ch /* Unicode character */ |
Guido van Rossum | d822518 | 2000-03-10 22:33:05 +0000 | [diff] [blame] | 1225 | ); |
| 1226 | |
Mark Hammond | 91a681d | 2002-08-12 07:21:58 +0000 | [diff] [blame] | 1227 | PyAPI_FUNC(Py_UNICODE) _PyUnicode_ToUppercase( |
Fredrik Lundh | 72b0685 | 2001-06-27 22:08:26 +0000 | [diff] [blame] | 1228 | Py_UNICODE ch /* Unicode character */ |
Guido van Rossum | d822518 | 2000-03-10 22:33:05 +0000 | [diff] [blame] | 1229 | ); |
| 1230 | |
Mark Hammond | 91a681d | 2002-08-12 07:21:58 +0000 | [diff] [blame] | 1231 | PyAPI_FUNC(Py_UNICODE) _PyUnicode_ToTitlecase( |
Fredrik Lundh | 72b0685 | 2001-06-27 22:08:26 +0000 | [diff] [blame] | 1232 | Py_UNICODE ch /* Unicode character */ |
Guido van Rossum | d822518 | 2000-03-10 22:33:05 +0000 | [diff] [blame] | 1233 | ); |
| 1234 | |
Mark Hammond | 91a681d | 2002-08-12 07:21:58 +0000 | [diff] [blame] | 1235 | PyAPI_FUNC(int) _PyUnicode_ToDecimalDigit( |
Fredrik Lundh | 72b0685 | 2001-06-27 22:08:26 +0000 | [diff] [blame] | 1236 | Py_UNICODE ch /* Unicode character */ |
Guido van Rossum | d822518 | 2000-03-10 22:33:05 +0000 | [diff] [blame] | 1237 | ); |
| 1238 | |
Mark Hammond | 91a681d | 2002-08-12 07:21:58 +0000 | [diff] [blame] | 1239 | PyAPI_FUNC(int) _PyUnicode_ToDigit( |
Fredrik Lundh | 72b0685 | 2001-06-27 22:08:26 +0000 | [diff] [blame] | 1240 | Py_UNICODE ch /* Unicode character */ |
Guido van Rossum | d822518 | 2000-03-10 22:33:05 +0000 | [diff] [blame] | 1241 | ); |
| 1242 | |
Mark Hammond | 91a681d | 2002-08-12 07:21:58 +0000 | [diff] [blame] | 1243 | PyAPI_FUNC(double) _PyUnicode_ToNumeric( |
Fredrik Lundh | 72b0685 | 2001-06-27 22:08:26 +0000 | [diff] [blame] | 1244 | Py_UNICODE ch /* Unicode character */ |
Guido van Rossum | d822518 | 2000-03-10 22:33:05 +0000 | [diff] [blame] | 1245 | ); |
| 1246 | |
Mark Hammond | 91a681d | 2002-08-12 07:21:58 +0000 | [diff] [blame] | 1247 | PyAPI_FUNC(int) _PyUnicode_IsDecimalDigit( |
Fredrik Lundh | 72b0685 | 2001-06-27 22:08:26 +0000 | [diff] [blame] | 1248 | Py_UNICODE ch /* Unicode character */ |
Guido van Rossum | d822518 | 2000-03-10 22:33:05 +0000 | [diff] [blame] | 1249 | ); |
| 1250 | |
Mark Hammond | 91a681d | 2002-08-12 07:21:58 +0000 | [diff] [blame] | 1251 | PyAPI_FUNC(int) _PyUnicode_IsDigit( |
Fredrik Lundh | 72b0685 | 2001-06-27 22:08:26 +0000 | [diff] [blame] | 1252 | Py_UNICODE ch /* Unicode character */ |
Guido van Rossum | d822518 | 2000-03-10 22:33:05 +0000 | [diff] [blame] | 1253 | ); |
| 1254 | |
Mark Hammond | 91a681d | 2002-08-12 07:21:58 +0000 | [diff] [blame] | 1255 | PyAPI_FUNC(int) _PyUnicode_IsNumeric( |
Fredrik Lundh | 72b0685 | 2001-06-27 22:08:26 +0000 | [diff] [blame] | 1256 | Py_UNICODE ch /* Unicode character */ |
Guido van Rossum | d822518 | 2000-03-10 22:33:05 +0000 | [diff] [blame] | 1257 | ); |
| 1258 | |
Mark Hammond | 91a681d | 2002-08-12 07:21:58 +0000 | [diff] [blame] | 1259 | PyAPI_FUNC(int) _PyUnicode_IsAlpha( |
Fredrik Lundh | 72b0685 | 2001-06-27 22:08:26 +0000 | [diff] [blame] | 1260 | Py_UNICODE ch /* Unicode character */ |
Marc-André Lemburg | f03e741 | 2000-07-05 09:45:59 +0000 | [diff] [blame] | 1261 | ); |
| 1262 | |
Guido van Rossum | d822518 | 2000-03-10 22:33:05 +0000 | [diff] [blame] | 1263 | #ifdef __cplusplus |
| 1264 | } |
| 1265 | #endif |
Guido van Rossum | d822518 | 2000-03-10 22:33:05 +0000 | [diff] [blame] | 1266 | #endif /* !Py_UNICODEOBJECT_H */ |