Repository URL to install this package:
#ifndef Py_UNICODEOBJECT_H
#define Py_UNICODEOBJECT_H
#include <stdarg.h>
/*
Unicode implementation based on original code by Fredrik Lundh,
modified by Marc-Andre Lemburg (mal@lemburg.com) according to the
Unicode Integration Proposal. (See
http://www.egenix.com/files/python/unicode-proposal.txt).
Copyright (c) Corporation for National Research Initiatives.
Original header:
--------------------------------------------------------------------
* Yet another Unicode string type for Python. This type supports the
* 16-bit Basic Multilingual Plane (BMP) only.
*
* Written by Fredrik Lundh, January 1999.
*
* Copyright (c) 1999 by Secret Labs AB.
* Copyright (c) 1999 by Fredrik Lundh.
*
* fredrik@pythonware.com
* http://www.pythonware.com
*
* --------------------------------------------------------------------
* This Unicode String Type is
*
* Copyright (c) 1999 by Secret Labs AB
* Copyright (c) 1999 by Fredrik Lundh
*
* By obtaining, using, and/or copying this software and/or its
* associated documentation, you agree that you have read, understood,
* and will comply with the following terms and conditions:
*
* Permission to use, copy, modify, and distribute this software and its
* associated documentation for any purpose and without fee is hereby
* granted, provided that the above copyright notice appears in all
* copies, and that both that copyright notice and this permission notice
* appear in supporting documentation, and that the name of Secret Labs
* AB or the author not be used in advertising or publicity pertaining to
* distribution of the software without specific, written prior
* permission.
*
* SECRET LABS AB AND THE AUTHOR DISCLAIMS ALL WARRANTIES WITH REGARD TO
* THIS SOFTWARE, INCLUDING ALL IMPLIED WARRANTIES OF MERCHANTABILITY AND
* FITNESS. IN NO EVENT SHALL SECRET LABS AB OR THE AUTHOR BE LIABLE FOR
* ANY SPECIAL, INDIRECT OR CONSEQUENTIAL DAMAGES OR ANY DAMAGES
* WHATSOEVER RESULTING FROM LOSS OF USE, DATA OR PROFITS, WHETHER IN AN
* ACTION OF CONTRACT, NEGLIGENCE OR OTHER TORTIOUS ACTION, ARISING OUT
* OF OR IN CONNECTION WITH THE USE OR PERFORMANCE OF THIS SOFTWARE.
* -------------------------------------------------------------------- */
#include <ctype.h>
/* === Internal API ======================================================= */
/* --- Internal Unicode Format -------------------------------------------- */
/* Python 3.x requires unicode */
#define Py_USING_UNICODE
#ifndef SIZEOF_WCHAR_T
#error Must define SIZEOF_WCHAR_T
#endif
#define Py_UNICODE_SIZE SIZEOF_WCHAR_T
/* If wchar_t can be used for UCS-4 storage, set Py_UNICODE_WIDE.
Otherwise, Unicode strings are stored as UCS-2 (with limited support
for UTF-16) */
#if Py_UNICODE_SIZE >= 4
#define Py_UNICODE_WIDE
#endif
/* Set these flags if the platform has "wchar.h" and the
wchar_t type is a 16-bit unsigned type */
/* #define HAVE_WCHAR_H */
/* #define HAVE_USABLE_WCHAR_T */
/* If the compiler provides a wchar_t type we try to support it
through the interface functions PyUnicode_FromWideChar(),
PyUnicode_AsWideChar() and PyUnicode_AsWideCharString(). */
#ifdef HAVE_USABLE_WCHAR_T
# ifndef HAVE_WCHAR_H
# define HAVE_WCHAR_H
# endif
#endif
#ifdef HAVE_WCHAR_H
# include <wchar.h>
#endif
/* Py_UCS4 and Py_UCS2 are typedefs for the respective
unicode representations. */
typedef uint32_t Py_UCS4;
typedef uint16_t Py_UCS2;
typedef uint8_t Py_UCS1;
#ifdef __cplusplus
extern "C" {
#endif
PyAPI_DATA(PyTypeObject) PyUnicode_Type;
PyAPI_DATA(PyTypeObject) PyUnicodeIter_Type;
#define PyUnicode_Check(op) \
PyType_FastSubclass(Py_TYPE(op), Py_TPFLAGS_UNICODE_SUBCLASS)
#define PyUnicode_CheckExact(op) (Py_TYPE(op) == &PyUnicode_Type)
/* --- Constants ---------------------------------------------------------- */
/* This Unicode character will be used as replacement character during
decoding if the errors argument is set to "replace". Note: the
Unicode character U+FFFD is the official REPLACEMENT CHARACTER in
Unicode 3.0. */
#define Py_UNICODE_REPLACEMENT_CHARACTER ((Py_UCS4) 0xFFFD)
/* === Public API ========================================================= */
/* Similar to PyUnicode_FromUnicode(), but u points to UTF-8 encoded bytes */
PyAPI_FUNC(PyObject*) PyUnicode_FromStringAndSize(
const char *u, /* UTF-8 encoded string */
Py_ssize_t size /* size of buffer */
);
/* Similar to PyUnicode_FromUnicode(), but u points to null-terminated
UTF-8 encoded bytes. The size is determined with strlen(). */
PyAPI_FUNC(PyObject*) PyUnicode_FromString(
const char *u /* UTF-8 encoded string */
);
#if !defined(Py_LIMITED_API) || Py_LIMITED_API+0 >= 0x03030000
PyAPI_FUNC(PyObject*) PyUnicode_Substring(
PyObject *str,
Py_ssize_t start,
Py_ssize_t end);
#endif
#if !defined(Py_LIMITED_API) || Py_LIMITED_API+0 >= 0x03030000
/* Copy the string into a UCS4 buffer including the null character if copy_null
is set. Return NULL and raise an exception on error. Raise a SystemError if
the buffer is smaller than the string. Return buffer on success.
buflen is the length of the buffer in (Py_UCS4) characters. */
PyAPI_FUNC(Py_UCS4*) PyUnicode_AsUCS4(
PyObject *unicode,
Py_UCS4* buffer,
Py_ssize_t buflen,
int copy_null);
/* Copy the string into a UCS4 buffer. A new buffer is allocated using
* PyMem_Malloc; if this fails, NULL is returned with a memory error
exception set. */
PyAPI_FUNC(Py_UCS4*) PyUnicode_AsUCS4Copy(PyObject *unicode);
#endif
#if !defined(Py_LIMITED_API) || Py_LIMITED_API+0 >= 0x03030000
/* Get the length of the Unicode object. */
PyAPI_FUNC(Py_ssize_t) PyUnicode_GetLength(
PyObject *unicode
);
#endif
/* Get the number of Py_UNICODE units in the
string representation. */
Py_DEPRECATED(3.3) PyAPI_FUNC(Py_ssize_t) PyUnicode_GetSize(
PyObject *unicode /* Unicode object */
);
#if !defined(Py_LIMITED_API) || Py_LIMITED_API+0 >= 0x03030000
/* Read a character from the string. */
PyAPI_FUNC(Py_UCS4) PyUnicode_ReadChar(
PyObject *unicode,
Py_ssize_t index
);
/* Write a character to the string. The string must have been created through
PyUnicode_New, must not be shared, and must not have been hashed yet.
Return 0 on success, -1 on error. */
PyAPI_FUNC(int) PyUnicode_WriteChar(
PyObject *unicode,
Py_ssize_t index,
Py_UCS4 character
);
#endif
/* Resize a Unicode object. The length is the number of characters, except
if the kind of the string is PyUnicode_WCHAR_KIND: in this case, the length
is the number of Py_UNICODE characters.
*unicode is modified to point to the new (resized) object and 0
returned on success.
Try to resize the string in place (which is usually faster than allocating
a new string and copy characters), or create a new string.
Error handling is implemented as follows: an exception is set, -1
is returned and *unicode left untouched.
WARNING: The function doesn't check string content, the result may not be a
string in canonical representation. */
PyAPI_FUNC(int) PyUnicode_Resize(
PyObject **unicode, /* Pointer to the Unicode object */
Py_ssize_t length /* New length */
);
/* Decode obj to a Unicode object.
bytes, bytearray and other bytes-like objects are decoded according to the
given encoding and error handler. The encoding and error handler can be
NULL to have the interface use UTF-8 and "strict".
All other objects (including Unicode objects) raise an exception.
The API returns NULL in case of an error. The caller is responsible
for decref'ing the returned objects.
*/
PyAPI_FUNC(PyObject*) PyUnicode_FromEncodedObject(
PyObject *obj, /* Object */
const char *encoding, /* encoding */
const char *errors /* error handling */
);
/* Copy an instance of a Unicode subtype to a new true Unicode object if
necessary. If obj is already a true Unicode object (not a subtype), return
the reference with *incremented* refcount.
The API returns NULL in case of an error. The caller is responsible
for decref'ing the returned objects.
*/
PyAPI_FUNC(PyObject*) PyUnicode_FromObject(
PyObject *obj /* Object */
);
PyAPI_FUNC(PyObject *) PyUnicode_FromFormatV(
const char *format, /* ASCII-encoded string */
va_list vargs
);
PyAPI_FUNC(PyObject *) PyUnicode_FromFormat(
const char *format, /* ASCII-encoded string */
...
);
PyAPI_FUNC(void) PyUnicode_InternInPlace(PyObject **);
PyAPI_FUNC(void) PyUnicode_InternImmortal(PyObject **);
PyAPI_FUNC(PyObject *) PyUnicode_InternFromString(
const char *u /* UTF-8 encoded string */
);
/* Use only if you know it's a string */
#define PyUnicode_CHECK_INTERNED(op) \
(((PyASCIIObject *)(op))->state.interned)
/* --- wchar_t support for platforms which support it --------------------- */
#ifdef HAVE_WCHAR_H
/* Create a Unicode Object from the wchar_t buffer w of the given
size.
The buffer is copied into the new object. */
PyAPI_FUNC(PyObject*) PyUnicode_FromWideChar(
const wchar_t *w, /* wchar_t buffer */
Py_ssize_t size /* size of buffer */
);
/* Copies the Unicode Object contents into the wchar_t buffer w. At
most size wchar_t characters are copied.
Note that the resulting wchar_t string may or may not be
0-terminated. It is the responsibility of the caller to make sure
that the wchar_t string is 0-terminated in case this is required by
the application.
Returns the number of wchar_t characters copied (excluding a
possibly trailing 0-termination character) or -1 in case of an
error. */
PyAPI_FUNC(Py_ssize_t) PyUnicode_AsWideChar(
PyObject *unicode, /* Unicode object */
wchar_t *w, /* wchar_t buffer */
Py_ssize_t size /* size of buffer */
);
/* Convert the Unicode object to a wide character string. The output string
always ends with a nul character. If size is not NULL, write the number of
wide characters (excluding the null character) into *size.
Returns a buffer allocated by PyMem_Malloc() (use PyMem_Free() to free it)
on success. On error, returns NULL, *size is undefined and raises a
MemoryError. */
PyAPI_FUNC(wchar_t*) PyUnicode_AsWideCharString(
PyObject *unicode, /* Unicode object */
Py_ssize_t *size /* number of characters of the result */
);
#endif
/* --- Unicode ordinals --------------------------------------------------- */
/* Create a Unicode Object from the given Unicode code point ordinal.
The ordinal must be in range(0x110000). A ValueError is
raised in case it is not.
*/
PyAPI_FUNC(PyObject*) PyUnicode_FromOrdinal(int ordinal);
/* --- Free-list management ----------------------------------------------- */
/* Clear the free list used by the Unicode implementation.
This can be used to release memory used for objects on the free
list back to the Python memory allocator.
*/
PyAPI_FUNC(int) PyUnicode_ClearFreeList(void);
/* === Builtin Codecs =====================================================
Many of these APIs take two arguments encoding and errors. These
parameters encoding and errors have the same semantics as the ones
Loading ...