mirror of
https://github.com/python/cpython.git
synced 2025-07-25 12:14:38 +00:00

We're no longer using _Py_IDENTIFIER() (or _Py_static_string()) in any core CPython code. It is still used in a number of non-builtin stdlib modules. The replacement is: PyUnicodeObject (not pointer) fields under _PyRuntimeState, statically initialized as part of _PyRuntime. A new _Py_GET_GLOBAL_IDENTIFIER() macro facilitates lookup of the fields (along with _Py_GET_GLOBAL_STRING() for non-identifier strings). https://bugs.python.org/issue46541#msg411799 explains the rationale for this change. The core of the change is in: * (new) Include/internal/pycore_global_strings.h - the declarations for the global strings, along with the macros * Include/internal/pycore_runtime_init.h - added the static initializers for the global strings * Include/internal/pycore_global_objects.h - where the struct in pycore_global_strings.h is hooked into _PyRuntimeState * Tools/scripts/generate_global_objects.py - added generation of the global string declarations and static initializers I've also added a --check flag to generate_global_objects.py (along with make check-global-objects) to check for unused global strings. That check is added to the PR CI config. The remainder of this change updates the core code to use _Py_GET_GLOBAL_IDENTIFIER() instead of _Py_IDENTIFIER() and the related _Py*Id functions (likewise for _Py_GET_GLOBAL_STRING() instead of _Py_static_string()). This includes adding a few functions where there wasn't already an alternative to _Py*Id(), replacing the _Py_Identifier * parameter with PyObject *. The following are not changed (yet): * stop using _Py_IDENTIFIER() in the stdlib modules * (maybe) get rid of _Py_IDENTIFIER(), etc. entirely -- this may not be doable as at least one package on PyPI using this (private) API * (maybe) intern the strings during runtime init https://bugs.python.org/issue46541
62 lines
1.7 KiB
C
62 lines
1.7 KiB
C
#ifndef Py_INTERNAL_UNICODEOBJECT_H
|
|
#define Py_INTERNAL_UNICODEOBJECT_H
|
|
#ifdef __cplusplus
|
|
extern "C" {
|
|
#endif
|
|
|
|
#ifndef Py_BUILD_CORE
|
|
# error "this header requires Py_BUILD_CORE define"
|
|
#endif
|
|
|
|
#include "pycore_fileutils.h" // _Py_error_handler
|
|
|
|
|
|
/* runtime lifecycle */
|
|
|
|
extern void _PyUnicode_InitState(PyInterpreterState *);
|
|
extern PyStatus _PyUnicode_InitGlobalObjects(PyInterpreterState *);
|
|
extern PyStatus _PyUnicode_InitTypes(PyInterpreterState *);
|
|
extern void _PyUnicode_Fini(PyInterpreterState *);
|
|
extern void _PyUnicode_FiniTypes(PyInterpreterState *);
|
|
|
|
|
|
/* other API */
|
|
|
|
struct _Py_unicode_runtime_ids {
|
|
PyThread_type_lock lock;
|
|
// next_index value must be preserved when Py_Initialize()/Py_Finalize()
|
|
// is called multiple times: see _PyUnicode_FromId() implementation.
|
|
Py_ssize_t next_index;
|
|
};
|
|
|
|
/* fs_codec.encoding is initialized to NULL.
|
|
Later, it is set to a non-NULL string by _PyUnicode_InitEncodings(). */
|
|
struct _Py_unicode_fs_codec {
|
|
char *encoding; // Filesystem encoding (encoded to UTF-8)
|
|
int utf8; // encoding=="utf-8"?
|
|
char *errors; // Filesystem errors (encoded to UTF-8)
|
|
_Py_error_handler error_handler;
|
|
};
|
|
|
|
struct _Py_unicode_ids {
|
|
Py_ssize_t size;
|
|
PyObject **array;
|
|
};
|
|
|
|
struct _Py_unicode_state {
|
|
/* Single character Unicode strings in the Latin-1 range are being
|
|
shared as well. */
|
|
PyObject *latin1[256];
|
|
struct _Py_unicode_fs_codec fs_codec;
|
|
|
|
// Unicode identifiers (_Py_Identifier): see _PyUnicode_FromId()
|
|
struct _Py_unicode_ids ids;
|
|
};
|
|
|
|
extern void _PyUnicode_ClearInterned(PyInterpreterState *interp);
|
|
|
|
|
|
#ifdef __cplusplus
|
|
}
|
|
#endif
|
|
#endif /* !Py_INTERNAL_UNICODEOBJECT_H */
|