Issue #17621: Introduce importlib.util.LazyLoader.

Lib/importlib/util.py

@@ -1,5 +1,5 @@
 """Utility code for constructing importers, etc."""
-
+from . import abc
 from ._bootstrap import MAGIC_NUMBER
 from ._bootstrap import cache_from_source
 from ._bootstrap import decode_source
@@ -12,6 +12,7 @@ from ._bootstrap import _find_spec
 from contextlib import contextmanager
 import functools
 import sys
+import types
 import warnings
 
 
@@ -200,3 +201,94 @@ def module_for_loader(fxn):
             return fxn(self, module, *args, **kwargs)
 
     return module_for_loader_wrapper
+
+
+class _Module(types.ModuleType):
+
+    """A subclass of the module type to allow __class__ manipulation."""
+
+
+class _LazyModule(types.ModuleType):
+
+    """A subclass of the module type which triggers loading upon attribute access."""
+
+    def __getattribute__(self, attr):
+        """Trigger the load of the module and return the attribute."""
+        # All module metadata must be garnered from __spec__ in order to avoid
+        # using mutated values.
+        # Stop triggering this method.
+        self.__class__ = _Module
+        # Get the original name to make sure no object substitution occurred
+        # in sys.modules.
+        original_name = self.__spec__.name
+        # Figure out exactly what attributes were mutated between the creation
+        # of the module and now.
+        attrs_then = self.__spec__.loader_state
+        attrs_now = self.__dict__
+        attrs_updated = {}
+        for key, value in attrs_now.items():
+            # Code that set the attribute may have kept a reference to the
+            # assigned object, making identity more important than equality.
+            if key not in attrs_then:
+                attrs_updated[key] = value
+            elif id(attrs_now[key]) != id(attrs_then[key]):
+                attrs_updated[key] = value
+        self.__spec__.loader.exec_module(self)
+        # If exec_module() was used directly there is no guarantee the module
+        # object was put into sys.modules.
+        if original_name in sys.modules:
+            if id(self) != id(sys.modules[original_name]):
+                msg = ('module object for {!r} substituted in sys.modules '
+                       'during a lazy load')
+            raise ValueError(msg.format(original_name))
+        # Update after loading since that's what would happen in an eager
+        # loading situation.
+        self.__dict__.update(attrs_updated)
+        return getattr(self, attr)
+
+    def __delattr__(self, attr):
+        """Trigger the load and then perform the deletion."""
+        # To trigger the load and raise an exception if the attribute
+        # doesn't exist.
+        self.__getattribute__(attr)
+        delattr(self, attr)
+
+
+class LazyLoader(abc.Loader):
+
+    """A loader that creates a module which defers loading until attribute access."""
+
+    @staticmethod
+    def __check_eager_loader(loader):
+        if not hasattr(loader, 'exec_module'):
+            raise TypeError('loader must define exec_module()')
+        elif hasattr(loader.__class__, 'create_module'):
+            if abc.Loader.create_module != loader.__class__.create_module:
+                # Only care if create_module() is overridden in a subclass of
+                # importlib.abc.Loader.
+                raise TypeError('loader cannot define create_module()')
+
+    @classmethod
+    def factory(cls, loader):
+        """Construct a callable which returns the eager loader made lazy."""
+        cls.__check_eager_loader(loader)
+        return lambda *args, **kwargs: cls(loader(*args, **kwargs))
+
+    def __init__(self, loader):
+        self.__check_eager_loader(loader)
+        self.loader = loader
+
+    def create_module(self, spec):
+        """Create a module which can have its __class__ manipulated."""
+        return _Module(spec.name)
+
+    def exec_module(self, module):
+        """Make the module load lazily."""
+        module.__spec__.loader = self.loader
+        module.__loader__ = self.loader
+        # Don't need to worry about deep-copying as trying to set an attribute
+        # on an object would have triggered the load,
+        # e.g. ``module.__spec__.loader = None`` would trigger a load from
+        # trying to access module.__spec__.
+        module.__spec__.loader_state = module.__dict__.copy()
+        module.__class__ = _LazyModule