bpo-21736: Set __file__ on frozen stdlib modules. (gh-28656)

Currently frozen modules do not have __file__ set.  In their spec, origin is set to "frozen" and they are marked as not having a location.  (Similarly, for frozen packages __path__ is set to an empty list.)  However, for frozen stdlib modules we are able to extrapolate __file__ as long as we can determine the stdlib directory at runtime.  (We now do so since gh-28586.)  Having __file__ set is helpful for a number of reasons.  Likewise, having a non-empty __path__ means we can import submodules of a frozen package from the filesystem (e.g. we could partially freeze the encodings module).

This change sets __file__ (and adds to __path__) for frozen stdlib modules.  It uses sys._stdlibdir (from gh-28586) and the frozen module alias information (from gh-28655).  All that work is done in FrozenImporter (in Lib/importlib/_bootstrap.py). 
 Also, if a frozen module is imported before importlib is bootstrapped (during interpreter initialization) then we fix up that module and its spec during the importlib bootstrapping step (i.e. imporlib._bootstrap._setup()) to match what gets set by FrozenImporter, including setting the file info (if the stdlib dir is known).  To facilitate this, modules imported using PyImport_ImportFrozenModule() have __origname__ set using the frozen module alias info.  __origname__ is popped off during importlib bootstrap.

(To be clear, even with this change the new code to set __file__ during fixups in imporlib._bootstrap._setup() doesn't actually get triggered yet.  This is because sys._stdlibdir hasn't been set yet in interpreter initialization at the point importlib is bootstrapped.  However, we do fix up such modules at that point to otherwise match the result of importing through FrozenImporter, just not the __file__ and __path__ parts.  Doing so will require changes in the order in which things happen during interpreter initialization.  That can be addressed separately.  Once it is, the file-related fixup code from this PR will kick in.)

Here are things this change does not do:

* set __file__ for non-stdlib modules (no way of knowing the parent dir)
* set __file__ if the stdlib dir is not known (nor assume the expense of finding it)
* relatedly, set __file__ if the stdlib is in a zip file
* verify that the filename set to __file__ actually exists (too expensive)
* update __path__ for frozen packages that alias a non-package (since there is no package dir)

Other things this change skips, but we may do later:

* set __file__ on modules imported using PyImport_ImportFrozenModule()
* set co_filename when we unmarshal the frozen code object while importing the module (e.g. in FrozenImporter.exec_module()) -- this would allow tracebacks to show source lines
* implement FrozenImporter.get_filename() and FrozenImporter.get_source()

https://bugs.python.org/issue21736

4 files changed, 172 insertions, 69 deletions

diff --git a/Lib/importlib/_bootstrap.py b/Lib/importlib/_bootstrap.py
index 49f0881..889f08f 100644
--- a/Lib/importlib/_bootstrap.py
+++ b/Lib/importlib/_bootstrap.py
@@ -421,7 +421,10 @@ class ModuleSpec:
 
 def spec_from_loader(name, loader, *, origin=None, is_package=None):
     """Return a module spec based on various loader methods."""
-    if hasattr(loader, 'get_filename'):
+    if origin is None:
+        origin = getattr(loader, '_ORIGIN', None)
+
+    if not origin and hasattr(loader, 'get_filename'):
         if _bootstrap_external is None:
             raise NotImplementedError
         spec_from_file_location = _bootstrap_external.spec_from_file_location
@@ -467,12 +470,9 @@ def _spec_from_module(module, loader=None, origin=None):
     except AttributeError:
         location = None
     if origin is None:
-        if location is None:
-            try:
-                origin = loader._ORIGIN
-            except AttributeError:
-                origin = None
-        else:
+        if loader is not None:
+            origin = getattr(loader, '_ORIGIN', None)
+        if not origin and location is not None:
             origin = location
     try:
         cached = module.__cached__
@@ -484,7 +484,7 @@ def _spec_from_module(module, loader=None, origin=None):
         submodule_search_locations = None
 
     spec = ModuleSpec(name, loader, origin=origin)
-    spec._set_fileattr = False if location is None else True
+    spec._set_fileattr = False if location is None else (origin == location)
     spec.cached = cached
     spec.submodule_search_locations = submodule_search_locations
     return spec
@@ -541,6 +541,7 @@ def _init_module_attrs(spec, module, *, override=False):
     # __path__
     if override or getattr(module, '__path__', None) is None:
         if spec.submodule_search_locations is not None:
+            # XXX We should extend __path__ if it's already a list.
             try:
                 module.__path__ = spec.submodule_search_locations
             except AttributeError:
@@ -825,38 +826,127 @@ class FrozenImporter:
         return '<module {!r} ({})>'.format(m.__name__, FrozenImporter._ORIGIN)
 
     @classmethod
-    def _setup_module(cls, module):
-        assert not hasattr(module, '__file__'), module.__file__
-        ispkg = hasattr(module, '__path__')
-        assert not ispkg or not module.__path__, module.__path__
+    def _fix_up_module(cls, module):
         spec = module.__spec__
-        assert not ispkg or not spec.submodule_search_locations
+        state = spec.loader_state
+        if state is None:
+            # The module is missing FrozenImporter-specific values.
 
-        if spec.loader_state is None:
-            spec.loader_state = type(sys.implementation)(
-                data=None,
-                origname=None,
-            )
-        elif not hasattr(spec.loader_state, 'data'):
-            spec.loader_state.data = None
-        if not getattr(spec.loader_state, 'origname', None):
+            # Fix up the spec attrs.
             origname = vars(module).pop('__origname__', None)
             assert origname, 'see PyImport_ImportFrozenModuleObject()'
-            spec.loader_state.origname = origname
+            ispkg = hasattr(module, '__path__')
+            assert _imp.is_frozen_package(module.__name__) == ispkg, ispkg
+            filename, pkgdir = cls._resolve_filename(origname, spec.name, ispkg)
+            spec.loader_state = type(sys.implementation)(
+                filename=filename,
+                origname=origname,
+            )
+            __path__ = spec.submodule_search_locations
+            if ispkg:
+                assert __path__ == [], __path__
+                if pkgdir:
+                    spec.submodule_search_locations.insert(0, pkgdir)
+            else:
+                assert __path__ is None, __path__
+
+            # Fix up the module attrs (the bare minimum).
+            assert not hasattr(module, '__file__'), module.__file__
+            if filename:
+                try:
+                    module.__file__ = filename
+                except AttributeError:
+                    pass
+            if ispkg:
+                if module.__path__ != __path__:
+                    assert module.__path__ == [], module.__path__
+                    module.__path__.extend(__path__)
+        else:
+            # These checks ensure that _fix_up_module() is only called
+            # in the right places.
+            __path__ = spec.submodule_search_locations
+            ispkg = __path__ is not None
+            # Check the loader state.
+            assert sorted(vars(state)) == ['filename', 'origname'], state
+            if state.origname:
+                # The only frozen modules with "origname" set are stdlib modules.
+                (__file__, pkgdir,
+                 ) = cls._resolve_filename(state.origname, spec.name, ispkg)
+                assert state.filename == __file__, (state.filename, __file__)
+                if pkgdir:
+                    assert __path__ == [pkgdir], (__path__, pkgdir)
+                else:
+                    assert __path__ == ([] if ispkg else None), __path__
+            else:
+                __file__ = None
+                assert state.filename is None, state.filename
+                assert __path__ == ([] if ispkg else None), __path__
+            # Check the file attrs.
+            if __file__:
+                assert hasattr(module, '__file__')
+                assert module.__file__ == __file__, (module.__file__, __file__)
+            else:
+                assert not hasattr(module, '__file__'), module.__file__
+            if ispkg:
+                assert hasattr(module, '__path__')
+                assert module.__path__ == __path__, (module.__path__, __path__)
+            else:
+                assert not hasattr(module, '__path__'), module.__path__
+        assert not spec.has_location
+
+    @classmethod
+    def _resolve_filename(cls, fullname, alias=None, ispkg=False):
+        if not fullname or not getattr(sys, '_stdlib_dir', None):
+            return None, None
+        try:
+            sep = cls._SEP
+        except AttributeError:
+            sep = cls._SEP = '\\' if sys.platform == 'win32' else '/'
+
+        if fullname != alias:
+            if fullname.startswith('<'):
+                fullname = fullname[1:]
+                if not ispkg:
+                    fullname = f'{fullname}.__init__'
+            else:
+                ispkg = False
+        relfile = fullname.replace('.', sep)
+        if ispkg:
+            pkgdir = f'{sys._stdlib_dir}{sep}{relfile}'
+            filename = f'{pkgdir}{sep}__init__.py'
+        else:
+            pkgdir = None
+            filename = f'{sys._stdlib_dir}{sep}{relfile}.py'
+        return filename, pkgdir
 
     @classmethod
     def find_spec(cls, fullname, path=None, target=None):
         info = _call_with_frames_removed(_imp.find_frozen, fullname)
         if info is None:
             return None
-        data, ispkg, origname = info
+        # We get the marshaled data in exec_module() (the loader
+        # part of the importer), instead of here (the finder part).
+        # The loader is the usual place to get the data that will
+        # be loaded into the module.  (For example, see _LoaderBasics
+        # in _bootstra_external.py.)  Most importantly, this importer
+        # is simpler if we wait to get the data.
+        # However, getting as much data in the finder as possible
+        # to later load the module is okay, and sometimes important.
+        # (That's why ModuleSpec.loader_state exists.)  This is
+        # especially true if it avoids throwing away expensive data
+        # the loader would otherwise duplicate later and can be done
+        # efficiently.  In this case it isn't worth it.
+        _, ispkg, origname = info
         spec = spec_from_loader(fullname, cls,
                                 origin=cls._ORIGIN,
                                 is_package=ispkg)
+        filename, pkgdir = cls._resolve_filename(origname, fullname, ispkg)
         spec.loader_state = type(sys.implementation)(
-            data=data,
+            filename=filename,
             origname=origname,
         )
+        if pkgdir:
+            spec.submodule_search_locations.insert(0, pkgdir)
         return spec
 
     @classmethod
@@ -873,26 +963,22 @@ class FrozenImporter:
 
     @staticmethod
     def create_module(spec):
-        """Use default semantics for module creation."""
+        """Set __file__, if able."""
+        module = _new_module(spec.name)
+        try:
+            filename = spec.loader_state.filename
+        except AttributeError:
+            pass
+        else:
+            if filename:
+                module.__file__ = filename
+        return module
 
     @staticmethod
     def exec_module(module):
         spec = module.__spec__
         name = spec.name
-        try:
-            data = spec.loader_state.data
-        except AttributeError:
-            if not _imp.is_frozen(name):
-                raise ImportError('{!r} is not a frozen module'.format(name),
-                                  name=name)
-            data = None
-        else:
-            # We clear the extra data we got from the finder, to save memory.
-            # Note that if this method is called again (e.g. by
-            # importlib.reload()) then _imp.get_frozen_object() will notice
-            # no data was provided and will look it up.
-            spec.loader_state.data = None
-        code = _call_with_frames_removed(_imp.get_frozen_object, name, data)
+        code = _call_with_frames_removed(_imp.get_frozen_object, name)
         exec(code, module.__dict__)
 
     @classmethod
@@ -903,7 +989,16 @@ class FrozenImporter:
 
         """
         # Warning about deprecation implemented in _load_module_shim().
-        return _load_module_shim(cls, fullname)
+        module = _load_module_shim(cls, fullname)
+        info = _imp.find_frozen(fullname)
+        assert info is not None
+        _, ispkg, origname = info
+        module.__origname__ = origname
+        vars(module).pop('__file__', None)
+        if ispkg:
+            module.__path__ = []
+        cls._fix_up_module(module)
+        return module
 
     @classmethod
     @_requires_frozen
@@ -1244,7 +1339,7 @@ def _setup(sys_module, _imp_module):
             spec = _spec_from_module(module, loader)
             _init_module_attrs(spec, module)
             if loader is FrozenImporter:
-                loader._setup_module(module)
+                loader._fix_up_module(module)
 
     # Directly load built-in modules needed during bootstrap.
     self_module = sys.modules[__name__]
diff --git a/Lib/test/test_frozen.py b/Lib/test/test_frozen.py
index 029fd06..0b4a12b 100644
--- a/Lib/test/test_frozen.py
+++ b/Lib/test/test_frozen.py
@@ -39,9 +39,6 @@ class TestFrozen(unittest.TestCase):
         self.assertIs(spam.__spec__.loader,
                       importlib.machinery.FrozenImporter)
 
-    # This is not possible until frozen packages have __path__ set properly.
-    # See https://bugs.python.org/issue21736.
-    @unittest.expectedFailure
     def test_unfrozen_submodule_in_frozen_package(self):
         with import_helper.CleanImport('__phello__', '__phello__.spam'):
             with import_helper.frozen_modules(enabled=True):
diff --git a/Lib/test/test_importlib/frozen/test_finder.py b/Lib/test/test_importlib/frozen/test_finder.py
index cd5586d..66080b2 100644
--- a/Lib/test/test_importlib/frozen/test_finder.py
+++ b/Lib/test/test_importlib/frozen/test_finder.py
@@ -44,30 +44,31 @@ class FindSpecTests(abc.FinderTests):
         if not filename:
             if not origname:
                 origname = spec.name
+            filename = resolve_stdlib_file(origname)
 
         actual = dict(vars(spec.loader_state))
 
-        # Check the code object used to import the frozen module.
-        # We can't compare the marshaled data directly because
-        # marshal.dumps() would mark "expected" (below) as a ref,
-        # which slightly changes the output.
-        # (See https://bugs.python.org/issue34093.)
-        data = actual.pop('data')
-        with import_helper.frozen_modules():
-            expected = _imp.get_frozen_object(spec.name)
-        code = marshal.loads(data)
-        self.assertEqual(code, expected)
-
         # Check the rest of spec.loader_state.
         expected = dict(
             origname=origname,
+            filename=filename if origname else None,
         )
         self.assertDictEqual(actual, expected)
 
     def check_search_locations(self, spec):
-        # Frozen packages do not have any path entries.
-        # (See https://bugs.python.org/issue21736.)
-        expected = []
+        """This is only called when testing packages."""
+        missing = object()
+        filename = getattr(spec.loader_state, 'filename', missing)
+        origname = getattr(spec.loader_state, 'origname', None)
+        if not origname or filename is missing:
+            # We deal with this in check_loader_state().
+            return
+        if not filename:
+            expected = []
+        elif origname != spec.name and not origname.startswith('<'):
+            expected = []
+        else:
+            expected = [os.path.dirname(filename)]
         self.assertListEqual(spec.submodule_search_locations, expected)
 
     def test_module(self):
diff --git a/Lib/test/test_importlib/frozen/test_loader.py b/Lib/test/test_importlib/frozen/test_loader.py
index d6f39fa..f1ccb8a 100644
--- a/Lib/test/test_importlib/frozen/test_loader.py
+++ b/Lib/test/test_importlib/frozen/test_loader.py
@@ -3,10 +3,11 @@ from .. import util
 
 machinery = util.import_importlib('importlib.machinery')
 
-from test.support import captured_stdout, import_helper
+from test.support import captured_stdout, import_helper, STDLIB_DIR
 import _imp
 import contextlib
 import marshal
+import os.path
 import types
 import unittest
 import warnings
@@ -30,20 +31,27 @@ def fresh(name, *, oldapi=False):
                 yield
 
 
+def resolve_stdlib_file(name, ispkg=False):
+    assert name
+    if ispkg:
+        return os.path.join(STDLIB_DIR, *name.split('.'), '__init__.py')
+    else:
+        return os.path.join(STDLIB_DIR, *name.split('.')) + '.py'
+
+
 class ExecModuleTests(abc.LoaderTests):
 
     def exec_module(self, name, origname=None):
         with import_helper.frozen_modules():
             is_package = self.machinery.FrozenImporter.is_package(name)
-            code = _imp.get_frozen_object(name)
         spec = self.machinery.ModuleSpec(
             name,
             self.machinery.FrozenImporter,
             origin='frozen',
             is_package=is_package,
             loader_state=types.SimpleNamespace(
-                data=marshal.dumps(code),
                 origname=origname or name,
+                filename=resolve_stdlib_file(origname or name, is_package),
             ),
         )
         module = types.ModuleType(name)
@@ -68,7 +76,6 @@ class ExecModuleTests(abc.LoaderTests):
             self.assertEqual(getattr(module, attr), value)
         self.assertEqual(output, 'Hello world!\n')
         self.assertTrue(hasattr(module, '__spec__'))
-        self.assertIsNone(module.__spec__.loader_state.data)
         self.assertEqual(module.__spec__.loader_state.origname, name)
 
     def test_package(self):
@@ -82,7 +89,6 @@ class ExecModuleTests(abc.LoaderTests):
                                  name=name, attr=attr, given=attr_value,
                                  expected=value))
         self.assertEqual(output, 'Hello world!\n')
-        self.assertIsNone(module.__spec__.loader_state.data)
         self.assertEqual(module.__spec__.loader_state.origname, name)
 
     def test_lacking_parent(self):
@@ -139,36 +145,41 @@ class LoaderTests(abc.LoaderTests):
 
     def test_module(self):
         module, stdout = self.load_module('__hello__')
+        filename = resolve_stdlib_file('__hello__')
         check = {'__name__': '__hello__',
                 '__package__': '',
                 '__loader__': self.machinery.FrozenImporter,
+                '__file__': filename,
                 }
         for attr, value in check.items():
-            self.assertEqual(getattr(module, attr), value)
+            self.assertEqual(getattr(module, attr, None), value)
         self.assertEqual(stdout.getvalue(), 'Hello world!\n')
-        self.assertFalse(hasattr(module, '__file__'))
 
     def test_package(self):
         module, stdout = self.load_module('__phello__')
+        filename = resolve_stdlib_file('__phello__', ispkg=True)
+        pkgdir = os.path.dirname(filename)
         check = {'__name__': '__phello__',
                  '__package__': '__phello__',
-                 '__path__': [],
+                 '__path__': [pkgdir],
                  '__loader__': self.machinery.FrozenImporter,
+                 '__file__': filename,
                  }
         for attr, value in check.items():
-            attr_value = getattr(module, attr)
+            attr_value = getattr(module, attr, None)
             self.assertEqual(attr_value, value,
                              "for __phello__.%s, %r != %r" %
                              (attr, attr_value, value))
         self.assertEqual(stdout.getvalue(), 'Hello world!\n')
-        self.assertFalse(hasattr(module, '__file__'))
 
     def test_lacking_parent(self):
         with util.uncache('__phello__'):
             module, stdout = self.load_module('__phello__.spam')
+        filename = resolve_stdlib_file('__phello__.spam')
         check = {'__name__': '__phello__.spam',
                 '__package__': '__phello__',
                 '__loader__': self.machinery.FrozenImporter,
+                '__file__': filename,
                 }
         for attr, value in check.items():
             attr_value = getattr(module, attr)
@@ -176,7 +187,6 @@ class LoaderTests(abc.LoaderTests):
                              "for __phello__.spam.%s, %r != %r" %
                              (attr, attr_value, value))
         self.assertEqual(stdout.getvalue(), 'Hello world!\n')
-        self.assertFalse(hasattr(module, '__file__'))
 
     def test_module_reuse(self):
         with fresh('__hello__', oldapi=True):