#ifndef Py_UNICODEOBJECT_H
#define Py_UNICODEOBJECT_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.
--------------------------------------------------------------------
* 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.
* 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
* 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.
* -------------------------------------------------------------------- */
/* === Internal API ======================================================= */
/* --- Internal Unicode Format -------------------------------------------- */
/* Python 3.x requires unicode */
#error Must define SIZEOF_WCHAR_T
#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
/* 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 */
/* Py_UNICODE was the native Unicode storage format (code unit) used by
Python and represents a single Unicode element in the Unicode type.
With PEP 393, Py_UNICODE is deprecated and replaced with a
#define PY_UNICODE_TYPE wchar_t
typedef wchar_t Py_UNICODE;
/* 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
/* Work around a cosmetic bug in BSDI 4.x wchar.h; thanks to Thomas Wouters */
/* Py_UCS4 and Py_UCS2 are typedefs for the respective
unicode representations. */
typedef uint32_t Py_UCS4;
typedef uint16_t Py_UCS2;
/* --- Internal Unicode Operations ---------------------------------------- */
/* Since splitting on whitespace is an important use case, and
whitespace in most situations is solely ASCII whitespace, we
optimize for the common case by using a quick look-up table
_Py_ascii_whitespace (see below) with an inlined check.
#define Py_UNICODE_ISSPACE(ch) \
((ch) < 128U ? _Py_ascii_whitespace[(ch)] : _PyUnicode_IsWhitespace(ch))
#define Py_UNICODE_ISLOWER(ch) _PyUnicode_IsLowercase(ch)
#define Py_UNICODE_ISUPPER(ch) _PyUnicode_IsUppercase(ch)
#define Py_UNICODE_ISTITLE(ch) _PyUnicode_IsTitlecase(ch)
#define Py_UNICODE_ISLINEBREAK(ch) _PyUnicode_IsLinebreak(ch)
#define Py_UNICODE_TOLOWER(ch) _PyUnicode_ToLowercase(ch)
#define Py_UNICODE_TOUPPER(ch) _PyUnicode_ToUppercase(ch)
#define Py_UNICODE_TOTITLE(ch) _PyUnicode_ToTitlecase(ch)
#define Py_UNICODE_ISDECIMAL(ch) _PyUnicode_IsDecimalDigit(ch)
#define Py_UNICODE_ISDIGIT(ch) _PyUnicode_IsDigit(ch)
#define Py_UNICODE_ISNUMERIC(ch) _PyUnicode_IsNumeric(ch)
#define Py_UNICODE_ISPRINTABLE(ch) _PyUnicode_IsPrintable(ch)
#define Py_UNICODE_TODECIMAL(ch) _PyUnicode_ToDecimalDigit(ch)
#define Py_UNICODE_TODIGIT(ch) _PyUnicode_ToDigit(ch)
#define Py_UNICODE_TONUMERIC(ch) _PyUnicode_ToNumeric(ch)
#define Py_UNICODE_ISALPHA(ch) _PyUnicode_IsAlpha(ch)
#define Py_UNICODE_ISALNUM(ch) \
(Py_UNICODE_ISALPHA(ch) || \
Py_UNICODE_ISDECIMAL(ch) || \
Py_UNICODE_ISDIGIT(ch) || \
Py_UNICODE_ISNUMERIC(ch))
#define Py_UNICODE_COPY(target, source, length) \
memcpy((target), (source), (length)*sizeof(Py_UNICODE))
#define Py_UNICODE_FILL(target, value, length) \
do {Py_ssize_t i_; Py_UNICODE *t_ = (target); Py_UNICODE v_ = (value);\
for (i_ = 0; i_ < (length); i_++) t_[i_] = v_;\
/* macros to work with surrogates */
#define Py_UNICODE_IS_SURROGATE(ch) (0xD800 <= (ch) && (ch) <= 0xDFFF)
#define Py_UNICODE_IS_HIGH_SURROGATE(ch) (0xD800 <= (ch) && (ch) <= 0xDBFF)
#define Py_UNICODE_IS_LOW_SURROGATE(ch) (0xDC00 <= (ch) && (ch) <= 0xDFFF)
/* Join two surrogate characters and return a single Py_UCS4 value. */
#define Py_UNICODE_JOIN_SURROGATES(high, low) \
(((((Py_UCS4)(high) & 0x03FF) << 10) | \
((Py_UCS4)(low) & 0x03FF)) + 0x10000)
/* high surrogate = top 10 bits added to D800 */
#define Py_UNICODE_HIGH_SURROGATE(ch) (0xD800 - (0x10000 >> 10) + ((ch) >> 10))
/* low surrogate = bottom 10 bits added to DC00 */
#define Py_UNICODE_LOW_SURROGATE(ch) (0xDC00 + ((ch) & 0x3FF))
/* Check if substring matches at given offset. The offset must be
valid, and the substring must not be empty. */
#define Py_UNICODE_MATCH(string, offset, substring) \
((*((string)->wstr + (offset)) == *((substring)->wstr)) && \
((*((string)->wstr + (offset) + (substring)->wstr_length-1) == *((substring)->wstr + (substring)->wstr_length-1))) && \
!memcmp((string)->wstr + (offset), (substring)->wstr, (substring)->wstr_length*sizeof(Py_UNICODE)))
#endif /* Py_LIMITED_API */
/* --- Unicode Type ------------------------------------------------------- */
/* ASCII-only strings created through PyUnicode_New use the PyASCIIObject
structure. state.ascii and state.compact are set, and the data
immediately follow the structure. utf8_length and wstr_length can be found
in the length field; the utf8 pointer is equal to the data pointer. */
/* There are 4 forms of Unicode strings:
* structure = PyASCIIObject
* test: PyUnicode_IS_COMPACT_ASCII(op)
* kind = PyUnicode_1BYTE_KIND
* (length is the length of the utf8 and wstr strings)
* (data starts just after the structure)
* (since ASCII is decoded from UTF-8, the utf8 string are the data)
* structure = PyCompactUnicodeObject
* test: PyUnicode_IS_COMPACT(op) && !PyUnicode_IS_ASCII(op)
* kind = PyUnicode_1BYTE_KIND, PyUnicode_2BYTE_KIND or
* utf8 is not shared with data
* utf8_length = 0 if utf8 is NULL
* wstr is shared with data and wstr_length=length
if kind=PyUnicode_2BYTE_KIND and sizeof(wchar_t)=2
or if kind=PyUnicode_4BYTE_KIND and sizeof(wchar_t)=4
* wstr_length = 0 if wstr is NULL
* (data starts just after the structure)
- legacy string, not ready:
* structure = PyUnicodeObject
* test: kind == PyUnicode_WCHAR_KIND
* length = 0 (use wstr_length)
* kind = PyUnicode_WCHAR_KIND
* interned = SSTATE_NOT_INTERNED
* structure = PyUnicodeObject structure
* test: !PyUnicode_IS_COMPACT(op) && kind != PyUnicode_WCHAR_KIND
* kind = PyUnicode_1BYTE_KIND, PyUnicode_2BYTE_KIND or
* utf8 is shared and utf8_length = length with data.any if ascii = 1
* utf8_length = 0 if utf8 is NULL
* wstr is shared with data.any and wstr_length = length
if kind=PyUnicode_2BYTE_KIND and sizeof(wchar_t)=2
or if kind=PyUnicode_4BYTE_KIND and sizeof(wchar_4)=4
* wstr_length = 0 if wstr is NULL
Compact strings use only one memory block (structure + characters),
whereas legacy strings use one block for the structure and one block
Legacy strings are created by PyUnicode_FromUnicode() and
PyUnicode_FromStringAndSize(NULL, size) functions. They become ready
when PyUnicode_READY() is called.
See also _PyUnicode_CheckConsistency().
Py_ssize_t length; /* Number of code points in the string */
Py_hash_t hash; /* Hash value; -1 if not set */
SSTATE_INTERNED_MORTAL (1)
SSTATE_INTERNED_IMMORTAL (2)
If interned != SSTATE_NOT_INTERNED, the two references from the
dictionary to this object are *not* counted in ob_refcnt.
- PyUnicode_WCHAR_KIND (0):
* character type = wchar_t (16 or 32 bits, depending on the
- PyUnicode_1BYTE_KIND (1):
* character type = Py_UCS1 (8 bits, unsigned)
* all characters are in the range U+0000-U+00FF (latin1)
* if ascii is set, all characters are in the range U+0000-U+007F
(ASCII), otherwise at least one character is in the range
- PyUnicode_2BYTE_KIND (2):
* character type = Py_UCS2 (16 bits, unsigned)
* all characters are in the range U+0000-U+FFFF (BMP)
* at least one character is in the range U+0100-U+FFFF
- PyUnicode_4BYTE_KIND (4):
* character type = Py_UCS4 (32 bits, unsigned)
* all characters are in the range U+0000-U+10FFFF
* at least one character is in the range U+10000-U+10FFFF
/* Compact is with respect to the allocation scheme. Compact unicode
objects only require one memory block while non-compact objects use
one block for the PyUnicodeObject struct and another for its data
/* The string only contains characters in the range U+0000-U+007F (ASCII)
and the kind is PyUnicode_1BYTE_KIND. If ascii is set and compact is
set, use the PyASCIIObject structure. */
/* The ready flag indicates whether the object layout is initialized
completely. This means that this is either a compact object, or
the data pointer is filled out. The bit is redundant, and helps
to minimize the test in PyUnicode_IS_READY(). */
/* Padding to ensure that PyUnicode_DATA() is always aligned to
4 bytes (see issue #19537 on m68k). */
wchar_t *wstr; /* wchar_t representation (null-terminated) */
/* Non-ASCII strings allocated through PyUnicode_New use the
PyCompactUnicodeObject structure. state.compact is set, and the data
immediately follow the structure. */
Py_ssize_t utf8_length; /* Number of bytes in utf8, excluding the
char *utf8; /* UTF-8 representation (null-terminated) */
Py_ssize_t wstr_length; /* Number of code points in wstr, possible
* surrogates count as two code points. */
} PyCompactUnicodeObject;
/* Strings allocated through PyUnicode_FromUnicode(NULL, len) use the
PyUnicodeObject structure. The actual string data is initially in the wstr
block, and copied into the data block using _PyUnicode_Ready. */
PyCompactUnicodeObject _base;
} data; /* Canonical, smallest-form Unicode buffer */
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)
#define PyUnicode_WSTR_LENGTH(op) \
(PyUnicode_IS_COMPACT_ASCII(op) ? \
((PyASCIIObject*)op)->length : \
((PyCompactUnicodeObject*)op)->wstr_length)
/* Returns the deprecated Py_UNICODE representation's size in code units
(this includes surrogate pairs as 2 units).
If the Py_UNICODE representation is not available, it will be computed
on request. Use PyUnicode_GET_LENGTH() for the length in code points. */
#define PyUnicode_GET_SIZE(op) \
(assert(PyUnicode_Check(op)), \
(((PyASCIIObject *)(op))->wstr) ? \
PyUnicode_WSTR_LENGTH(op) : \
((void)PyUnicode_AsUnicode((PyObject *)(op)), \
assert(((PyASCIIObject *)(op))->wstr), \
PyUnicode_WSTR_LENGTH(op)))
#define PyUnicode_GET_DATA_SIZE(op) \
(PyUnicode_GET_SIZE(op) * Py_UNICODE_SIZE)
/* Alias for PyUnicode_AsUnicode(). This will create a wchar_t/Py_UNICODE
representation on demand. Using this macro is very inefficient now,
try to port your code to use the new PyUnicode_*BYTE_DATA() macros or
use PyUnicode_WRITE() and PyUnicode_READ(). */
#define PyUnicode_AS_UNICODE(op) \
(assert(PyUnicode_Check(op)), \
(((PyASCIIObject *)(op))->wstr) ? (((PyASCIIObject *)(op))->wstr) : \
PyUnicode_AsUnicode((PyObject *)(op)))
#define PyUnicode_AS_DATA(op) \
((const char *)(PyUnicode_AS_UNICODE(op)))
/* --- Flexible String Representation Helper Macros (PEP 393) -------------- */
/* Values for PyASCIIObject.state: */
#define SSTATE_NOT_INTERNED 0
#define SSTATE_INTERNED_MORTAL 1
#define SSTATE_INTERNED_IMMORTAL 2
/* Return true if the string contains only ASCII characters, or 0 if not. The
string may be compact (PyUnicode_IS_COMPACT_ASCII) or not, but must be
#define PyUnicode_IS_ASCII(op) \
(assert(PyUnicode_Check(op)), \
assert(PyUnicode_IS_READY(op)), \
((PyASCIIObject*)op)->state.ascii)
/* Return true if the string is compact or 0 if not.
No type checks or Ready calls are performed. */
#define PyUnicode_IS_COMPACT(op) \
(((PyASCIIObject*)(op))->state.compact)
/* Return true if the string is a compact ASCII string (use PyASCIIObject
structure), or 0 if not. No type checks or Ready calls are performed. */
#define PyUnicode_IS_COMPACT_ASCII(op) \
(((PyASCIIObject*)op)->state.ascii && PyUnicode_IS_COMPACT(op))
/* String contains only wstr byte characters. This is only possible
when the string was created with a legacy API and _PyUnicode_Ready()
has not been called yet. */
PyUnicode_WCHAR_KIND = 0,
/* Return values of the PyUnicode_KIND() macro: */
PyUnicode_1BYTE_KIND = 1,
PyUnicode_2BYTE_KIND = 2,
/* Return pointers to the canonical representation cast to unsigned char,
Py_UCS2, or Py_UCS4 for direct character access.
No checks are performed, use PyUnicode_KIND() before to ensure
these will work correctly. */
#define PyUnicode_1BYTE_DATA(op) ((Py_UCS1*)PyUnicode_DATA(op))
#define PyUnicode_2BYTE_DATA(op) ((Py_UCS2*)PyUnicode_DATA(op))
#define PyUnicode_4BYTE_DATA(op) ((Py_UCS4*)PyUnicode_DATA(op))
/* Return one of the PyUnicode_*_KIND values defined above. */
#define PyUnicode_KIND(op) \
(assert(PyUnicode_Check(op)), \
assert(PyUnicode_IS_READY(op)), \
((PyASCIIObject *)(op))->state.kind)
/* Return a void pointer to the raw unicode buffer. */
#define _PyUnicode_COMPACT_DATA(op) \
(PyUnicode_IS_ASCII(op) ? \
((void*)((PyASCIIObject*)(op) + 1)) : \
((void*)((PyCompactUnicodeObject*)(op) + 1)))
#define _PyUnicode_NONCOMPACT_DATA(op) \
(assert(((PyUnicodeObject*)(op))->data.any), \
((((PyUnicodeObject *)(op))->data.any)))
#define PyUnicode_DATA(op) \
(assert(PyUnicode_Check(op)), \
PyUnicode_IS_COMPACT(op) ? _PyUnicode_COMPACT_DATA(op) : \
_PyUnicode_NONCOMPACT_DATA(op))
/* In the access macros below, "kind" may be evaluated more than once.
All other macro parameters are evaluated exactly once, so it is safe
to put side effects into them (such as increasing the index). */
/* Write into the canonical representation, this macro does not do any sanity
checks and is intended for usage in loops. The caller should cache the
kind and data pointers obtained from other macro calls.
index is the index in the string (starts at 0) and value is the new
code point value which should be written to that location. */
#define PyUnicode_WRITE(kind, data, index, value) \
case PyUnicode_1BYTE_KIND: { \
((Py_UCS1 *)(data))[(index)] = (Py_UCS1)(value); \
case PyUnicode_2BYTE_KIND: { \
((Py_UCS2 *)(data))[(index)] = (Py_UCS2)(value); \
assert((kind) == PyUnicode_4BYTE_KIND); \
((Py_UCS4 *)(data))[(index)] = (Py_UCS4)(value); \
It is recommended that you Edit text format, this type of Fix handles quite a lot in one request
