#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 /* runtime lifecycle */ extern void _PyUnicode_InitState(PyInterpreterState *); extern PyStatus _PyUnicode_InitGlobalObjects(PyInterpreterState *); extern PyStatus _PyUnicode_InitTypes(PyInterpreterState *); extern void _PyUnicode_Fini(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 { // The empty Unicode object is a singleton to improve performance. PyObject *empty_string; /* Single character Unicode strings in the Latin-1 range are being shared as well. */ PyObject *latin1[256]; struct _Py_unicode_fs_codec fs_codec; /* This dictionary holds all interned unicode strings. Note that references to strings in this dictionary are *not* counted in the string's ob_refcnt. When the interned string reaches a refcnt of 0 the string deallocation function will delete the reference from this dictionary. Another way to look at this is that to say that the actual reference count of a string is: s->ob_refcnt + (s->state ? 2 : 0) */ PyObject *interned; // Unicode identifiers (_Py_Identifier): see _PyUnicode_FromId() struct _Py_unicode_ids ids; }; extern void _PyUnicode_ClearInterned(PyInterpreterState *); #ifdef __cplusplus } #endif #endif /* !Py_INTERNAL_UNICODEOBJECT_H */