bpo-46541: Replace core use of _Py_IDENTIFIER() with statically initialized global objects. (gh-30928)

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

1 files changed, 14 insertions, 12 deletions

diff --git a/Python/traceback.c b/Python/traceback.c
index 4d6cbaa..f2ae38e 100644
--- a/Python/traceback.c
+++ b/Python/traceback.c
@@ -6,6 +6,7 @@
 #include "code.h"                 // PyCode_Addr2Line etc
 #include "frameobject.h"          // PyFrame_GetBack()
 #include "pycore_ast.h"           // asdl_seq_*
+#include "pycore_call.h"          // _PyObject_CallMethodFormat()
 #include "pycore_compile.h"       // _PyAST_Optimize
 #include "pycore_fileutils.h"     // _Py_BEGIN_SUPPRESS_IPH
 #include "pycore_frame.h"         // _PyFrame_GetCode()
@@ -32,11 +33,6 @@
 /* Function from Parser/tokenizer.c */
 extern char* _PyTokenizer_FindEncodingFilename(int, PyObject *);
 
-_Py_IDENTIFIER(TextIOWrapper);
-_Py_IDENTIFIER(close);
-_Py_IDENTIFIER(open);
-_Py_IDENTIFIER(path);
-
 /*[clinic input]
 class TracebackType "PyTracebackObject *" "&PyTraceback_Type"
 [clinic start generated code]*/
@@ -317,6 +313,7 @@ _Py_FindSourceFile(PyObject *filename, char* namebuf, size_t namelen, PyObject *
     const char* filepath;
     Py_ssize_t len;
     PyObject* result;
+    PyObject *open = NULL;
 
     filebytes = PyUnicode_EncodeFSDefault(filename);
     if (filebytes == NULL) {
@@ -333,11 +330,13 @@ _Py_FindSourceFile(PyObject *filename, char* namebuf, size_t namelen, PyObject *
         tail++;
     taillen = strlen(tail);
 
-    syspath = _PySys_GetObjectId(&PyId_path);
+    PyThreadState *tstate = _PyThreadState_GET();
+    syspath = _PySys_GetAttr(tstate, &_Py_ID(path));
     if (syspath == NULL || !PyList_Check(syspath))
         goto error;
     npath = PyList_Size(syspath);
 
+    open = PyObject_GetAttr(io, &_Py_ID(open));
     for (i = 0; i < npath; i++) {
         v = PyList_GetItem(syspath, i);
         if (v == NULL) {
@@ -364,7 +363,7 @@ _Py_FindSourceFile(PyObject *filename, char* namebuf, size_t namelen, PyObject *
             namebuf[len++] = SEP;
         strcpy(namebuf+len, tail);
 
-        binary = _PyObject_CallMethodId(io, &PyId_open, "ss", namebuf, "rb");
+        binary = _PyObject_CallMethodFormat(tstate, open, "ss", namebuf, "rb");
         if (binary != NULL) {
             result = binary;
             goto finally;
@@ -376,6 +375,7 @@ _Py_FindSourceFile(PyObject *filename, char* namebuf, size_t namelen, PyObject *
 error:
     result = NULL;
 finally:
+    Py_XDECREF(open);
     Py_DECREF(filebytes);
     return result;
 }
@@ -448,10 +448,11 @@ display_source_line_with_margin(PyObject *f, PyObject *filename, int lineno, int
     }
 
     io = PyImport_ImportModule("io");
-    if (io == NULL)
+    if (io == NULL) {
         return -1;
-    binary = _PyObject_CallMethodId(io, &PyId_open, "Os", filename, "rb");
+    }
 
+    binary = _PyObject_CallMethod(io, &_Py_ID(open), "Os", filename, "rb");
     if (binary == NULL) {
         PyErr_Clear();
 
@@ -480,14 +481,15 @@ display_source_line_with_margin(PyObject *f, PyObject *filename, int lineno, int
         PyMem_Free(found_encoding);
         return 0;
     }
-    fob = _PyObject_CallMethodId(io, &PyId_TextIOWrapper, "Os", binary, encoding);
+    fob = _PyObject_CallMethod(io, &_Py_ID(TextIOWrapper),
+                               "Os", binary, encoding);
     Py_DECREF(io);
     PyMem_Free(found_encoding);
 
     if (fob == NULL) {
         PyErr_Clear();
 
-        res = _PyObject_CallMethodIdNoArgs(binary, &PyId_close);
+        res = PyObject_CallMethodNoArgs(binary, &_Py_ID(close));
         Py_DECREF(binary);
         if (res)
             Py_DECREF(res);
@@ -506,7 +508,7 @@ display_source_line_with_margin(PyObject *f, PyObject *filename, int lineno, int
             break;
         }
     }
-    res = _PyObject_CallMethodIdNoArgs(fob, &PyId_close);
+    res = PyObject_CallMethodNoArgs(fob, &_Py_ID(close));
     if (res) {
         Py_DECREF(res);
     }