#ifndef Py_CPYTHON_UNICODEOBJECT_H # error "this header file must not be included directly" #endif /* 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. */ Py_DEPRECATED(…) PY_UNICODE_TYPE; Py_DEPRECATED(…) Py_UNICODE; /* --- Internal Unicode Operations ---------------------------------------- */ // Static inline functions to work with surrogates static inline int Py_UNICODE_IS_SURROGATE(Py_UCS4 ch) { … } static inline int Py_UNICODE_IS_HIGH_SURROGATE(Py_UCS4 ch) { … } static inline int Py_UNICODE_IS_LOW_SURROGATE(Py_UCS4 ch) { … } // Join two surrogate characters and return a single Py_UCS4 value. static inline Py_UCS4 Py_UNICODE_JOIN_SURROGATES(Py_UCS4 high, Py_UCS4 low) { … } // High surrogate = top 10 bits added to 0xD800. // The character must be in the range [U+10000; U+10ffff]. static inline Py_UCS4 Py_UNICODE_HIGH_SURROGATE(Py_UCS4 ch) { … } // Low surrogate = bottom 10 bits added to 0xDC00. // The character must be in the range [U+10000; U+10ffff]. static inline Py_UCS4 Py_UNICODE_LOW_SURROGATE(Py_UCS4 ch) { … } /* --- 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 can be found in the length field; the utf8 pointer is equal to the data pointer. */ PyASCIIObject; /* Non-ASCII strings allocated through PyUnicode_New use the PyCompactUnicodeObject structure. state.compact is set, and the data immediately follow the structure. */ PyCompactUnicodeObject; /* Object format for Unicode subclasses. */ PyUnicodeObject; #define _PyASCIIObject_CAST(op) … #define _PyCompactUnicodeObject_CAST(op) … #define _PyUnicodeObject_CAST(op) … /* --- Flexible String Representation Helper Macros (PEP 393) -------------- */ /* Values for PyASCIIObject.state: */ /* Interning state. */ #define SSTATE_NOT_INTERNED … #define SSTATE_INTERNED_MORTAL … #define SSTATE_INTERNED_IMMORTAL … #define SSTATE_INTERNED_IMMORTAL_STATIC … /* Use only if you know it's a string */ static inline unsigned int PyUnicode_CHECK_INTERNED(PyObject *op) { … } #define PyUnicode_CHECK_INTERNED(op) … /* For backward compatibility */ static inline unsigned int PyUnicode_IS_READY(PyObject* Py_UNUSED(op)) { … } #define PyUnicode_IS_READY(op) … /* 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 ready. */ static inline unsigned int PyUnicode_IS_ASCII(PyObject *op) { … } #define PyUnicode_IS_ASCII(op) … /* Return true if the string is compact or 0 if not. No type checks or Ready calls are performed. */ static inline unsigned int PyUnicode_IS_COMPACT(PyObject *op) { … } #define PyUnicode_IS_COMPACT(op) … /* 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. */ static inline int PyUnicode_IS_COMPACT_ASCII(PyObject *op) { … } #define PyUnicode_IS_COMPACT_ASCII(op) … enum PyUnicode_Kind { … }; // PyUnicode_KIND(): Return one of the PyUnicode_*_KIND values defined above. // // gh-89653: Converting this macro to a static inline function would introduce // new compiler warnings on "kind < PyUnicode_KIND(str)" (compare signed and // unsigned numbers) where kind type is an int or on // "unsigned int kind = PyUnicode_KIND(str)" (cast signed to unsigned). #define PyUnicode_KIND(op) … /* Return a void pointer to the raw unicode buffer. */ static inline void* _PyUnicode_COMPACT_DATA(PyObject *op) { … } static inline void* _PyUnicode_NONCOMPACT_DATA(PyObject *op) { … } static inline void* PyUnicode_DATA(PyObject *op) { … } #define PyUnicode_DATA(op) … /* 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) … #define PyUnicode_2BYTE_DATA(op) … #define PyUnicode_4BYTE_DATA(op) … /* Returns the length of the unicode string. */ static inline Py_ssize_t PyUnicode_GET_LENGTH(PyObject *op) { … } #define PyUnicode_GET_LENGTH(op) … /* Write into the canonical representation, this function 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 function 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. */ static inline void PyUnicode_WRITE(int kind, void *data, Py_ssize_t index, Py_UCS4 value) { … } #define PyUnicode_WRITE(kind, data, index, value) … /* Read a code point from the string's canonical representation. No checks or ready calls are performed. */ static inline Py_UCS4 PyUnicode_READ(int kind, const void *data, Py_ssize_t index) { … } #define PyUnicode_READ(kind, data, index) … /* PyUnicode_READ_CHAR() is less efficient than PyUnicode_READ() because it calls PyUnicode_KIND() and might call it twice. For single reads, use PyUnicode_READ_CHAR, for multiple consecutive reads callers should cache kind and use PyUnicode_READ instead. */ static inline Py_UCS4 PyUnicode_READ_CHAR(PyObject *unicode, Py_ssize_t index) { … } #define PyUnicode_READ_CHAR(unicode, index) … /* Return a maximum character value which is suitable for creating another string based on op. This is always an approximation but more efficient than iterating over the string. */ static inline Py_UCS4 PyUnicode_MAX_CHAR_VALUE(PyObject *op) { … } #define PyUnicode_MAX_CHAR_VALUE(op) … /* === Public API ========================================================= */ /* With PEP 393, this is the recommended way to allocate a new unicode object. This function will allocate the object and its buffer in a single memory block. Objects created using this function are not resizable. */ PyAPI_FUNC(PyObject*) PyUnicode_New( Py_ssize_t size, /* Number of code points in the new string */ Py_UCS4 maxchar /* maximum code point value in the string */ ); /* For backward compatibility */ static inline int PyUnicode_READY(PyObject* Py_UNUSED(op)) { … } #define PyUnicode_READY(op) … /* Copy character from one unicode object into another, this function performs character conversion when necessary and falls back to memcpy() if possible. Fail if to is too small (smaller than *how_many* or smaller than len(from)-from_start), or if kind(from[from_start:from_start+how_many]) > kind(to), or if *to* has more than 1 reference. Return the number of written character, or return -1 and raise an exception on error. Pseudo-code: how_many = min(how_many, len(from) - from_start) to[to_start:to_start+how_many] = from[from_start:from_start+how_many] return how_many Note: The function doesn't write a terminating null character. */ PyAPI_FUNC(Py_ssize_t) PyUnicode_CopyCharacters( PyObject *to, Py_ssize_t to_start, PyObject *from, Py_ssize_t from_start, Py_ssize_t how_many ); /* Fill a string with a character: write fill_char into unicode[start:start+length]. Fail if fill_char is bigger than the string maximum character, or if the string has more than 1 reference. Return the number of written character, or return -1 and raise an exception on error. */ PyAPI_FUNC(Py_ssize_t) PyUnicode_Fill( PyObject *unicode, Py_ssize_t start, Py_ssize_t length, Py_UCS4 fill_char ); /* Create a new string from a buffer of Py_UCS1, Py_UCS2 or Py_UCS4 characters. Scan the string to find the maximum character. */ PyAPI_FUNC(PyObject*) PyUnicode_FromKindAndData( int kind, const void *buffer, Py_ssize_t size); /* --- Public PyUnicodeWriter API ----------------------------------------- */ PyUnicodeWriter; PyAPI_FUNC(PyUnicodeWriter*) PyUnicodeWriter_Create(Py_ssize_t length); PyAPI_FUNC(void) PyUnicodeWriter_Discard(PyUnicodeWriter *writer); PyAPI_FUNC(PyObject*) PyUnicodeWriter_Finish(PyUnicodeWriter *writer); PyAPI_FUNC(int) PyUnicodeWriter_WriteChar( PyUnicodeWriter *writer, Py_UCS4 ch); PyAPI_FUNC(int) PyUnicodeWriter_WriteUTF8( PyUnicodeWriter *writer, const char *str, Py_ssize_t size); PyAPI_FUNC(int) PyUnicodeWriter_WriteWideChar( PyUnicodeWriter *writer, const wchar_t *str, Py_ssize_t size); PyAPI_FUNC(int) PyUnicodeWriter_WriteUCS4( PyUnicodeWriter *writer, Py_UCS4 *str, Py_ssize_t size); PyAPI_FUNC(int) PyUnicodeWriter_WriteStr( PyUnicodeWriter *writer, PyObject *obj); PyAPI_FUNC(int) PyUnicodeWriter_WriteRepr( PyUnicodeWriter *writer, PyObject *obj); PyAPI_FUNC(int) PyUnicodeWriter_WriteSubstring( PyUnicodeWriter *writer, PyObject *str, Py_ssize_t start, Py_ssize_t end); PyAPI_FUNC(int) PyUnicodeWriter_Format( PyUnicodeWriter *writer, const char *format, ...); PyAPI_FUNC(int) PyUnicodeWriter_DecodeUTF8Stateful( PyUnicodeWriter *writer, const char *string, /* UTF-8 encoded string */ Py_ssize_t length, /* size of string */ const char *errors, /* error handling */ Py_ssize_t *consumed); /* bytes consumed */ /* --- Private _PyUnicodeWriter API --------------------------------------- */ _PyUnicodeWriter; // Initialize a Unicode writer. // // By default, the minimum buffer size is 0 character and overallocation is // disabled. Set min_length, min_char and overallocate attributes to control // the allocation of the buffer. PyAPI_FUNC(void) _PyUnicodeWriter_Init(_PyUnicodeWriter *writer); /* Prepare the buffer to write 'length' characters with the specified maximum character. Return 0 on success, raise an exception and return -1 on error. */ #define _PyUnicodeWriter_Prepare(WRITER, LENGTH, MAXCHAR) … /* Don't call this function directly, use the _PyUnicodeWriter_Prepare() macro instead. */ PyAPI_FUNC(int) _PyUnicodeWriter_PrepareInternal(_PyUnicodeWriter *writer, Py_ssize_t length, Py_UCS4 maxchar); /* Prepare the buffer to have at least the kind KIND. For example, kind=PyUnicode_2BYTE_KIND ensures that the writer will support characters in range U+000-U+FFFF. Return 0 on success, raise an exception and return -1 on error. */ #define _PyUnicodeWriter_PrepareKind(WRITER, KIND) … /* Don't call this function directly, use the _PyUnicodeWriter_PrepareKind() macro instead. */ PyAPI_FUNC(int) _PyUnicodeWriter_PrepareKindInternal(_PyUnicodeWriter *writer, int kind); /* Append a Unicode character. Return 0 on success, raise an exception and return -1 on error. */ PyAPI_FUNC(int) _PyUnicodeWriter_WriteChar(_PyUnicodeWriter *writer, Py_UCS4 ch ); /* Append a Unicode string. Return 0 on success, raise an exception and return -1 on error. */ PyAPI_FUNC(int) _PyUnicodeWriter_WriteStr(_PyUnicodeWriter *writer, PyObject *str /* Unicode string */ ); /* Append a substring of a Unicode string. Return 0 on success, raise an exception and return -1 on error. */ PyAPI_FUNC(int) _PyUnicodeWriter_WriteSubstring(_PyUnicodeWriter *writer, PyObject *str, /* Unicode string */ Py_ssize_t start, Py_ssize_t end ); /* Append an ASCII-encoded byte string. Return 0 on success, raise an exception and return -1 on error. */ PyAPI_FUNC(int) _PyUnicodeWriter_WriteASCIIString(_PyUnicodeWriter *writer, const char *str, /* ASCII-encoded byte string */ Py_ssize_t len /* number of bytes, or -1 if unknown */ ); /* Append a latin1-encoded byte string. Return 0 on success, raise an exception and return -1 on error. */ PyAPI_FUNC(int) _PyUnicodeWriter_WriteLatin1String(_PyUnicodeWriter *writer, const char *str, /* latin1-encoded byte string */ Py_ssize_t len /* length in bytes */ ); /* Get the value of the writer as a Unicode string. Clear the buffer of the writer. Raise an exception and return NULL on error. */ PyAPI_FUNC(PyObject *) _PyUnicodeWriter_Finish(_PyUnicodeWriter *writer); /* Deallocate memory of a writer (clear its internal buffer). */ PyAPI_FUNC(void) _PyUnicodeWriter_Dealloc(_PyUnicodeWriter *writer); /* --- Manage the default encoding ---------------------------------------- */ /* Returns a pointer to the default encoding (UTF-8) of the Unicode object unicode. Like PyUnicode_AsUTF8AndSize(), this also caches the UTF-8 representation in the unicodeobject. _PyUnicode_AsString is a #define for PyUnicode_AsUTF8 to support the previous internal function with the same behaviour. Use of this API is DEPRECATED since no size information can be extracted from the returned data. */ PyAPI_FUNC(const char *) PyUnicode_AsUTF8(PyObject *unicode); // Alias kept for backward compatibility #define _PyUnicode_AsString … /* === Characters Type APIs =============================================== */ /* These should not be used directly. Use the Py_UNICODE_IS* and Py_UNICODE_TO* macros instead. These APIs are implemented in Objects/unicodectype.c. */ PyAPI_FUNC(int) _PyUnicode_IsLowercase( Py_UCS4 ch /* Unicode character */ ); PyAPI_FUNC(int) _PyUnicode_IsUppercase( Py_UCS4 ch /* Unicode character */ ); PyAPI_FUNC(int) _PyUnicode_IsTitlecase( Py_UCS4 ch /* Unicode character */ ); PyAPI_FUNC(int) _PyUnicode_IsWhitespace( const Py_UCS4 ch /* Unicode character */ ); PyAPI_FUNC(int) _PyUnicode_IsLinebreak( const Py_UCS4 ch /* Unicode character */ ); PyAPI_FUNC(Py_UCS4) _PyUnicode_ToLowercase( Py_UCS4 ch /* Unicode character */ ); PyAPI_FUNC(Py_UCS4) _PyUnicode_ToUppercase( Py_UCS4 ch /* Unicode character */ ); PyAPI_FUNC(Py_UCS4) _PyUnicode_ToTitlecase( Py_UCS4 ch /* Unicode character */ ); PyAPI_FUNC(int) _PyUnicode_ToDecimalDigit( Py_UCS4 ch /* Unicode character */ ); PyAPI_FUNC(int) _PyUnicode_ToDigit( Py_UCS4 ch /* Unicode character */ ); PyAPI_FUNC(double) _PyUnicode_ToNumeric( Py_UCS4 ch /* Unicode character */ ); PyAPI_FUNC(int) _PyUnicode_IsDecimalDigit( Py_UCS4 ch /* Unicode character */ ); PyAPI_FUNC(int) _PyUnicode_IsDigit( Py_UCS4 ch /* Unicode character */ ); PyAPI_FUNC(int) _PyUnicode_IsNumeric( Py_UCS4 ch /* Unicode character */ ); PyAPI_FUNC(int) _PyUnicode_IsPrintable( Py_UCS4 ch /* Unicode character */ ); PyAPI_FUNC(int) _PyUnicode_IsAlpha( Py_UCS4 ch /* Unicode character */ ); // Helper array used by Py_UNICODE_ISSPACE(). PyAPI_DATA(const unsigned char) _Py_ascii_whitespace[]; // 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. static inline int Py_UNICODE_ISSPACE(Py_UCS4 ch) { … } #define Py_UNICODE_ISLOWER(ch) … #define Py_UNICODE_ISUPPER(ch) … #define Py_UNICODE_ISTITLE(ch) … #define Py_UNICODE_ISLINEBREAK(ch) … #define Py_UNICODE_TOLOWER(ch) … #define Py_UNICODE_TOUPPER(ch) … #define Py_UNICODE_TOTITLE(ch) … #define Py_UNICODE_ISDECIMAL(ch) … #define Py_UNICODE_ISDIGIT(ch) … #define Py_UNICODE_ISNUMERIC(ch) … #define Py_UNICODE_ISPRINTABLE(ch) … #define Py_UNICODE_TODECIMAL(ch) … #define Py_UNICODE_TODIGIT(ch) … #define Py_UNICODE_TONUMERIC(ch) … #define Py_UNICODE_ISALPHA(ch) … static inline int Py_UNICODE_ISALNUM(Py_UCS4 ch) { … } /* === Misc functions ===================================================== */ // Return an interned Unicode object for an Identifier; may fail if there is no // memory. PyAPI_FUNC(PyObject*) _PyUnicode_FromId(_Py_Identifier*);
Codebase Browser
cpython