Python的学习教程（《Python 教程》学习笔记）

#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 */ /* 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 typedef to wchar_t. */ #ifndef Py_LIMITED_API #define PY_UNICODE_TYPE wchar_t typedef wchar_t Py_UNICODE; #endif /* 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 #if defined(MS_WINDOWS) # define HAVE_MBCS #endif #ifdef HAVE_WCHAR_H /* Work around a cosmetic bug in BSDI 4.x wchar.h; thanks to Thomas Wouters */ # ifdef _HAVE_BSDI # include <time.h> # endif # include <wchar.h> #endif /* Py_UCS4 and Py_UCS2 are typedefs for the respective unicode representations. */ #if SIZEOF_INT == 4 typedef unsigned int Py_UCS4; #elif SIZEOF_LONG == 4 typedef unsigned long Py_UCS4; #else #error "Could not find a proper typedef for Py_UCS4" #endif #if SIZEOF_SHORT == 2 typedef unsigned short Py_UCS2; #else #error "Could not find a proper typedef for Py_UCS2" #endif typedef unsigned char Py_UCS1; /* --- 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. */ #ifndef Py_LIMITED_API #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) \ Py_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_;\ } while (0) /* 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 */ #ifdef __cplusplus extern "C" { #endif /* --- Unicode Type ------------------------------------------------------- */ #ifndef Py_LIMITED_API /* 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. */ typedef struct { /* There are 4 forms of Unicode strings: - compact ascii: * structure = PyASCIIObject * test: PyUnicode_IS_COMPACT_ASCII(op) * kind = PyUnicode_1BYTE_KIND * compact = 1 * ascii = 1 * ready = 1 * (length is the length of the utf8 and ws