GH-127178: convert _sysconfigdata to a JSON file

Lib/sysconfig/__init__.py

@@ -181,6 +181,7 @@ def joinuser(*args):
 # True iff _CONFIG_VARS has been fully initialized.
 _CONFIG_VARS_INITIALIZED = False
 _USER_BASE = None
+_SYSCONFIGDATA = None
 
 
 def _safe_realpath(path):
@@ -334,27 +335,39 @@ def _get_sysconfigdata_name():
         f'_sysconfigdata_{sys.abiflags}_{sys.platform}_{multiarch}',
     )
 
+
+def _get_sysconfigdata():
+    # _sysconfigdata is generated at build time, see _generate_posix_vars()
+    global _SYSCONFIGDATA
+
+    if _SYSCONFIGDATA is None:
+        name = _get_sysconfigdata_name() + '.json'
+        if '_PYTHON_SYSCONFIGDATA_PATH' in os.environ:
+            data_path = os.path.join(os.environ['_PYTHON_SYSCONFIGDATA_PATH'], name)
+        else:
+            # Search sys.path
+            # FIXME: We should not need this if we could reliably identify the project directory on source builds
+            for path in sys.path:
+                data_path = os.path.join(path, name)
+                if os.path.isfile(data_path):
+                    break
+            else:
+                import warnings
+                warnings.warn(f'Could not find {name}', RuntimeWarning)
+                return {}
+
+        import json
+
+        with open(data_path) as f:
+            _SYSCONFIGDATA = json.load(f)
+
+    return _SYSCONFIGDATA
+
+
 def _init_posix(vars):
     """Initialize the module as appropriate for POSIX systems."""
-    # _sysconfigdata is generated at build time, see _generate_posix_vars()
-    name = _get_sysconfigdata_name()
-
-    # For cross builds, the path to the target's sysconfigdata must be specified
-    # so it can be imported. It cannot be in PYTHONPATH, as foreign modules in
-    # sys.path can cause crashes when loaded by the host interpreter.
-    # Rely on truthiness as a valueless env variable is still an empty string.
-    # See OS X note in _generate_posix_vars re _sysconfigdata.
-    if (path := os.environ.get('_PYTHON_SYSCONFIGDATA_PATH')):
-        from importlib.machinery import FileFinder, SourceFileLoader, SOURCE_SUFFIXES
-        from importlib.util import module_from_spec
-        spec = FileFinder(path, (SourceFileLoader, SOURCE_SUFFIXES)).find_spec(name)
-        _temp = module_from_spec(spec)
-        spec.loader.exec_module(_temp)
-    else:
-        _temp = __import__(name, globals(), locals(), ['build_time_vars'], 0)
-    build_time_vars = _temp.build_time_vars
     # GH-126920: Make sure we don't overwrite any of the keys already set
-    vars.update(build_time_vars | vars)
+    vars.update(_get_sysconfigdata() | vars)
 
 def _init_non_posix(vars):
     """Initialize the module as appropriate for NT"""

Lib/sysconfig/__main__.py

@@ -1,5 +1,7 @@
+import json
 import os
 import sys
+import sysconfig
 from sysconfig import (
     _ALWAYS_STR,
     _PYTHON_BUILD,
@@ -192,28 +194,19 @@ def _generate_posix_vars():
     # _sysconfigdata.py module being constructed.  Unfortunately,
     # get_config_vars() eventually calls _init_posix(), which attempts
     # to import _sysconfigdata, which we won't have built yet.  In order
-    # for _init_posix() to work, if we're on Darwin, just mock up the
-    # _sysconfigdata module manually and populate it with the build vars.
-    # This is more than sufficient for ensuring the subsequent call to
-    # get_platform() succeeds.
+    # for _init_posix() to work, we set the _SYSCONFIGDATA cache directly
     name = _get_sysconfigdata_name()
     if 'darwin' in sys.platform:
-        import types
-        module = types.ModuleType(name)
-        module.build_time_vars = vars
-        sys.modules[name] = module
+        sysconfig._SYSCONFIGDATA = vars
 
     pybuilddir = f'build/lib.{get_platform()}-{get_python_version()}'
     if hasattr(sys, "gettotalrefcount"):
         pybuilddir += '-pydebug'
     os.makedirs(pybuilddir, exist_ok=True)
-    destfile = os.path.join(pybuilddir, name + '.py')
+    destfile = os.path.join(pybuilddir, name + '.json')
 
     with open(destfile, 'w', encoding='utf8') as f:
-        f.write('# system configuration generated and used by'
-                ' the sysconfig module\n')
-        f.write('build_time_vars = ')
-        _print_config_dict(vars, stream=f)
+        json.dump(vars, f, indent=2)
 
     # Create file used for sys.path fixup -- see Modules/getpath.c
     with open('pybuilddir.txt', 'w', encoding='utf8') as f:

Makefile.pre.in

@@ -2645,7 +2645,7 @@ libinstall:	all $(srcdir)/Modules/xxmodule.c
 			esac; \
 		done; \
 	done
-	$(INSTALL_DATA) `cat pybuilddir.txt`/_sysconfigdata_$(ABIFLAGS)_$(MACHDEP)_$(MULTIARCH).py \
+	$(INSTALL_DATA) `cat pybuilddir.txt`/_sysconfigdata_$(ABIFLAGS)_$(MACHDEP)_$(MULTIARCH).json \
 		$(DESTDIR)$(LIBDEST); \
 	$(INSTALL_DATA) $(srcdir)/LICENSE $(DESTDIR)$(LIBDEST)/LICENSE.txt
 	@ # If app store compliance has been configured, apply the patch to the

Misc/NEWS.d/next/Library/2024-11-22-23-57-28.gh-issue-127178.2J-NbL.rst

@@ -0,0 +1,2 @@
+The ``_sysconfigdata_*`` module that holds the :mod:`sysconfig` data on
+POSIX has been converted to a JSON file.