GitHub Viewer
#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(3.13) typedef wchar_t PY_UNICODE_TYPE;
Py_DEPRECATED(3.13) typedef wchar_t Py_UNICODE;
/* --- Internal Unicode Operations ---------------------------------------- */
// Static inline functions to work with surrogates
static inline int Py_UNICODE_IS_SURROGATE(Py_UCS4 ch) {
return (0xD800 data.any;
assert(data != NULL);
return data;
}
PyAPI_FUNC(void*) PyUnicode_DATA(PyObject *op);
static inline void* _PyUnicode_DATA(PyObject *op) {
if (PyUnicode_IS_COMPACT(op)) {
return _PyUnicode_COMPACT_DATA(op);
}
return _PyUnicode_NONCOMPACT_DATA(op);
}
#define PyUnicode_DATA(op) _PyUnicode_DATA(_PyObject_CAST(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) _Py_STATIC_CAST(Py_UCS1*, PyUnicode_DATA(op))
#define PyUnicode_2BYTE_DATA(op) _Py_STATIC_CAST(Py_UCS2*, PyUnicode_DATA(op))
#define PyUnicode_4BYTE_DATA(op) _Py_STATIC_CAST(Py_UCS4*, PyUnicode_DATA(op))
/* Returns the length of the unicode string. */
static inline Py_ssize_t PyUnicode_GET_LENGTH(PyObject *op) {
return _PyASCIIObject_CAST(op)->length;
}
#define PyUnicode_GET_LENGTH(op) PyUnicode_GET_LENGTH(_PyObject_CAST(op))
/* Returns the cached hash, or -1 if not cached yet. */
static inline Py_hash_t
PyUnstable_Unicode_GET_CACHED_HASH(PyObject *op) {
#ifdef Py_GIL_DISABLED
return _Py_atomic_load_ssize_relaxed(&_PyASCIIObject_CAST(op)->hash);
#else
return _PyASCIIObject_CAST(op)->hash;
#endif
}
/* 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)
{
assert(index >= 0);
if (kind == PyUnicode_1BYTE_KIND) {
assert(value