Take the first step in resolving the messy pkgutil vs importlib edge cases by basing pkgutil explicitly on importlib, deprecating its internal import emulation and setting __main__.__loader__ correctly so that runpy still works (Affects #15343, #15314, #15357)

Author: ncoghlan

Doc/library/pkgutil.rst

@@ -56,21 +56,32 @@ support.
    Note that :class:`ImpImporter` does not currently support being used by
    placement on :data:`sys.meta_path`.
 
+   .. deprecated:: 3.3
+      This emulation is no longer needed, as the standard import mechanism
+      is now fully PEP 302 compliant and available in :mod:`importlib`
+
 
 .. class:: ImpLoader(fullname, file, filename, etc)
 
    :pep:`302` Loader that wraps Python's "classic" import algorithm.
 
+   .. deprecated:: 3.3
+      This emulation is no longer needed, as the standard import mechanism
+      is now fully PEP 302 compliant and available in :mod:`importlib`
+
 
 .. function:: find_loader(fullname)
 
-   Find a :pep:`302` "loader" object for *fullname*.
+   Retrieve a :pep:`302` module loader for the given *fullname*.
 
-   If *fullname* contains dots, path must be the containing package's
-   ``__path__``.  Returns ``None`` if the module cannot be found or imported.
-   This function uses :func:`iter_importers`, and is thus subject to the same
-   limitations regarding platform-specific special import locations such as the
-   Windows registry.
+   This is a convenience wrapper around :func:`importlib.find_loader` that
+   sets the *path* argument correctly when searching for submodules, and
+   also ensures parent packages (if any) are imported before searching for
+   submodules.
+
+   .. versionchanged:: 3.3
+      Updated to be based directly on :mod:`importlib` rather than relying
+      on a package internal PEP 302 import emulation.
 
 
 .. function:: get_importer(path_item)
@@ -80,13 +91,13 @@ support.
    The returned importer is cached in :data:`sys.path_importer_cache` if it was
    newly created by a path hook.
 
-   If there is no importer, a wrapper around the basic import machinery is
-   returned.  This wrapper is never inserted into the importer cache (``None``
-   is inserted instead).
-
    The cache (or part of it) can be cleared manually if a rescan of
    :data:`sys.path_hooks` is necessary.
 
+   .. versionchanged:: 3.3
+      Updated to be based directly on :mod:`importlib` rather than relying
+      on a package internal PEP 302 import emulation.
+
 
 .. function:: get_loader(module_or_name)
 
@@ -102,31 +113,27 @@ support.
    limitations regarding platform-specific special import locations such as the
    Windows registry.
 
+   .. versionchanged:: 3.3
+      Updated to be based directly on :mod:`importlib` rather than relying
+      on a package internal PEP 302 import emulation.
+
 
 .. function:: iter_importers(fullname='')
 
    Yield :pep:`302` importers for the given module name.
 
-   If fullname contains a '.', the importers will be for the package containing
-   fullname, otherwise they will be importers for :data:`sys.meta_path`,
-   :data:`sys.path`, and Python's "classic" import machinery, in that order.  If
-   the named module is in a package, that package is imported as a side effect
-   of invoking this function.
-
-   Non-:pep:`302` mechanisms (e.g. the Windows registry) used by the standard
-   import machinery to find files in alternative locations are partially
-   supported, but are searched *after* :data:`sys.path`.  Normally, these
-   locations are searched *before* :data:`sys.path`, preventing :data:`sys.path`
-   entries from shadowing them.
-
-   For this to cause a visible difference in behaviour, there must be a module
-   or package name that is accessible via both :data:`sys.path` and one of the
-   non-:pep:`302` file system mechanisms.  In this case, the emulation will find
-   the former version, while the builtin import mechanism will find the latter.
-
-   Items of the following types can be affected by this discrepancy:
-   ``imp.C_EXTENSION``, ``imp.PY_SOURCE``, ``imp.PY_COMPILED``,
-   ``imp.PKG_DIRECTORY``.
+   If fullname contains a '.', the importers will be for the package
+   containing fullname, otherwise they will be all registered top level
+   importers (i.e. those on both sys.meta_path and sys.path_hooks).
+
+   If the named module is in a package, that package is imported as a side
+   effect of invoking this function.
+
+   If no module name is specified, all top level importers are produced.
+
+   .. versionchanged:: 3.3
+      Updated to be based directly on :mod:`importlib` rather than relying
+      on a package internal PEP 302 import emulation.
 
 
 .. function:: iter_modules(path=None, prefix='')

Lib/pkgutil.py

@@ -3,7 +3,9 @@
 import os
 import sys
 import imp
+import importlib
 import os.path
+from warnings import warn
 from types import ModuleType
 
 __all__ = [
@@ -168,6 +170,8 @@ class ImpImporter:
     """
 
     def __init__(self, path=None):
+        warn("This emulation is deprecated, use 'importlib' instead",
+             DeprecationWarning)
         self.path = path
 
     def find_module(self, fullname, path=None):
@@ -232,6 +236,8 @@ class ImpLoader:
     code = source = None
 
     def __init__(self, fullname, file, filename, etc):
+        warn("This emulation is deprecated, use 'importlib' instead",
+             DeprecationWarning)
         self.file = file
         self.filename = filename
         self.fullname = fullname
@@ -366,10 +372,6 @@ def get_importer(path_item):
     The returned importer is cached in sys.path_importer_cache
     if it was newly created by a path hook.
 
-    If there is no importer, a wrapper around the basic import
-    machinery is returned. This wrapper is never inserted into
-    the importer cache (None is inserted instead).
-
     The cache (or part of it) can be cleared manually if a
     rescan of sys.path_hooks is necessary.
     """
@@ -384,66 +386,45 @@ def get_importer(path_item):
             except ImportError:
                 pass
         else:
-            try:
-                importer = ImpImporter(path_item)
-            except ImportError:
-                importer = None
+            importer = None
     return importer
 
 
 def iter_importers(fullname=""):
     """Yield PEP 302 importers for the given module name
 
     If fullname contains a '.', the importers will be for the package
-    containing fullname, otherwise they will be importers for sys.meta_path,
-    sys.path, and Python's "classic" import machinery, in that order.  If
-    the named module is in a package, that package is imported as a side
-    effect of invoking this function.
+    containing fullname, otherwise they will be all registered top level
+    importers (i.e. those on both sys.meta_path and sys.path_hooks).
 
-    Non PEP 302 mechanisms (e.g. the Windows registry) used by the
-    standard import machinery to find files in alternative locations
-    are partially supported, but are searched AFTER sys.path. Normally,
-    these locations are searched BEFORE sys.path, preventing sys.path
-    entries from shadowing them.
-
-    For this to cause a visible difference in behaviour, there must
-    be a module or package name that is accessible via both sys.path
-    and one of the non PEP 302 file system mechanisms. In this case,
-    the emulation will find the former version, while the builtin
-    import mechanism will find the latter.
+    If the named module is in a package, that package is imported as a side
+    effect of invoking this function.
 
-    Items of the following types can be affected by this discrepancy:
-        imp.C_EXTENSION, imp.PY_SOURCE, imp.PY_COMPILED, imp.PKG_DIRECTORY
+    If no module name is specified, all top level importers are produced.
     """
     if fullname.startswith('.'):
-        raise ImportError("Relative module names not supported")
+        msg = "Relative module name {!r} not supported".format(fullname)
+        raise ImportError(msg)
     if '.' in fullname:
         # Get the containing package's __path__
-        pkg = '.'.join(fullname.split('.')[:-1])
-        if pkg not in sys.modules:
-            __import__(pkg)
-        path = getattr(sys.modules[pkg], '__path__', None) or []
+        pkg_name = fullname.rpartition(".")[0]
+        pkg = importlib.import_module(pkg)
+        path = getattr(sys.modules[pkg], '__path__', None)
+        if path is None:
+            return
     else:
         for importer in sys.meta_path:
             yield importer
         path = sys.path
     for item in path:
         yield get_importer(item)
-    if '.' not in fullname:
-        yield ImpImporter()
 
 def get_loader(module_or_name):
     """Get a PEP 302 "loader" object for module_or_name
 
-    If the module or package is accessible via the normal import
-    mechanism, a wrapper around the relevant part of that machinery
-    is returned.  Returns None if the module cannot be found or imported.
+    Returns None if the module cannot be found or imported.
     If the named module is not already imported, its containing package
     (if any) is imported, in order to establish the package __path__.
-
-    This function uses iter_importers(), and is thus subject to the same
-    limitations regarding platform-specific special import locations such
-    as the Windows registry.
     """
     if module_or_name in sys.modules:
         module_or_name = sys.modules[module_or_name]
@@ -457,22 +438,33 @@ def get_loader(module_or_name):
         fullname = module_or_name
     return find_loader(fullname)
 
+
 def find_loader(fullname):
     """Find a PEP 302 "loader" object for fullname
 
-    If fullname contains dots, path must be the containing package's __path__.
-    Returns None if the module cannot be found or imported. This function uses
-    iter_importers(), and is thus subject to the same limitations regarding
-    platform-specific special import locations such as the Windows registry.
+    This is s convenience wrapper around :func:`importlib.find_loader` that
+    sets the *path* argument correctly when searching for submodules, and
+    also ensures parent packages (if any) are imported before searching for
+    submodules.
     """
-    for importer in iter_importers(fullname):
-        if importer is None:
-            continue
-        loader = importer.find_module(fullname)
-        if loader is not None:
-            return loader
-
-    return None
+    if fullname.startswith('.'):
+        msg = "Relative module name {!r} not supported".format(fullname)
+        raise ImportError(msg)
+    path = None
+    pkg_name = fullname.rpartition(".")[0]
+    if pkg_name:
+        pkg = importlib.import_module(pkg_name)
+        path = getattr(pkg, "__path__", None)
+        if path is None:
+            return None
+    try:
+        return importlib.find_loader(fullname, path)
+    except (ImportError, AttributeError, TypeError, ValueError) as ex:
+        # This hack fixes an impedance mismatch between pkgutil and
+        # importlib, where the latter throws other errors for cases where
+        # pkgutil previously threw ImportError
+        msg = "Error while finding loader for {!r} ({}: {})"
+        raise ImportError(msg.format(fullname, type(ex), ex)) from ex
 
 
 def extend_path(path, name):

Lib/runpy.py

@@ -13,11 +13,8 @@
 import os
 import sys
 import imp
-from pkgutil import read_code
-try:
-    from imp import get_loader
-except ImportError:
-    from pkgutil import get_loader
+import importlib.machinery
+from pkgutil import read_code, get_loader, get_importer
 
 __all__ = [
     "run_module", "run_path",
@@ -154,6 +151,7 @@ def _run_module_as_main(mod_name, alter_argv=True):
             # know what the code was looking for
             info = "can't find '__main__' module in %r" % sys.argv[0]
         msg = "%s: %s" % (sys.executable, info)
+        raise
         sys.exit(msg)
     pkg_name = mod_name.rpartition('.')[0]
     main_globals = sys.modules["__main__"].__dict__
@@ -183,44 +181,34 @@ def run_module(mod_name, init_globals=None,
 def _get_main_module_details():
     # Helper that gives a nicer error message when attempting to
     # execute a zipfile or directory by invoking __main__.py
+    # Also moves the standard __main__ out of the way so that the
+    # preexisting __loader__ entry doesn't cause issues
     main_name = "__main__"
+    saved_main = sys.modules[main_name]
+    del sys.modules[main_name]
     try:
         return _get_module_details(main_name)
     except ImportError as exc:
         if main_name in str(exc):
             raise ImportError("can't find %r module in %r" %
-                              (main_name, sys.path[0]))
+                              (main_name, sys.path[0])) from exc
         raise
+    finally:
+        sys.modules[main_name] = saved_main
 
 
-# XXX (ncoghlan): Perhaps expose the C API function
-# as imp.get_importer instead of reimplementing it in Python?
-def _get_importer(path_name):
-    """Python version of PyImport_GetImporter C API function"""
-    cache = sys.path_importer_cache
-    try:
-        importer = cache[path_name]
-    except KeyError:
-        for hook in sys.path_hooks:
-            try:
-                importer = hook(path_name)
-                break
-            except ImportError:
-                pass
-        else:
-            importer = None
-        cache[path_name] = importer
-    return importer
-
-def _get_code_from_file(fname):
+def _get_code_from_file(run_name, fname):
     # Check for a compiled file first
     with open(fname, "rb") as f:
         code = read_code(f)
     if code is None:
         # That didn't work, so try it as normal source code
         with open(fname, "rb") as f:
             code = compile(f.read(), fname, 'exec')
-    return code
+            loader = importlib.machinery.SourceFileLoader(run_name, fname)
+    else:
+        loader = importlib.machinery.SourcelessFileLoader(run_name, fname)
+    return code, loader
 
 def run_path(path_name, init_globals=None, run_name=None):
     """Execute code located at the specified filesystem location
@@ -235,13 +223,13 @@ def run_path(path_name, init_globals=None, run_name=None):
     if run_name is None:
         run_name = "<run_path>"
     pkg_name = run_name.rpartition(".")[0]
-    importer = _get_importer(path_name)
+    importer = get_importer(path_name)
     if isinstance(importer, (type(None), imp.NullImporter)):
         # Not a valid sys.path entry, so run the code directly
         # execfile() doesn't help as we want to allow compiled files
-        code = _get_code_from_file(path_name)
+        code, mod_loader = _get_code_from_file(run_name, path_name)
         return _run_module_code(code, init_globals, run_name, path_name,
-                                pkg_name=pkg_name)
+                                mod_loader, pkg_name)
     else:
         # Importer is defined for path, so add it to
         # the start of sys.path
@@ -253,13 +241,7 @@ def run_path(path_name, init_globals=None, run_name=None):
             # have no choice and we have to remove it even while we read the
             # code. If we don't do this, a __loader__ attribute in the
             # existing __main__ module may prevent location of the new module.
-            main_name = "__main__"
-            saved_main = sys.modules[main_name]
-            del sys.modules[main_name]
-            try:
-                mod_name, loader, code, fname = _get_main_module_details()
-            finally:
-                sys.modules[main_name] = saved_main
+            mod_name, loader, code, fname = _get_main_module_details()
             with _TempModule(run_name) as temp_module, \
                  _ModifiedArgv0(path_name):
                 mod_globals = temp_module.module.__dict__