gh-84013: normalize directory contents during import

Lib/importlib/_bootstrap_external.py

@@ -1593,6 +1593,7 @@ def __init__(self, path, *loader_details):
         self._path_mtime = -1
         self._path_cache = set()
         self._relaxed_path_cache = set()
+        self._cache_is_normalized = False
 
     def invalidate_caches(self):
         """Invalidate the directory mtime."""
@@ -1618,12 +1619,14 @@ def find_spec(self, fullname, target=None):
             self._fill_cache()
             self._path_mtime = mtime
         # tail_module keeps the original casing, for __file__ and friends
+        if not tail_module.isascii() and not self._cache_is_normalized:
+            self._normalize_cache()
         if _relax_case():
-            cache = self._relaxed_path_cache
             cache_module = tail_module.lower()
+            cache = self._relaxed_path_cache
         else:
-            cache = self._path_cache
             cache_module = tail_module
+            cache = self._path_cache
         # Check if the module is the name of a directory (and thus a package).
         if cache_module in cache:
             base_path = _path_join(self.path, tail_module)
@@ -1685,6 +1688,19 @@ def _fill_cache(self):
         if sys.platform.startswith(_CASE_INSENSITIVE_PLATFORMS):
             self._relaxed_path_cache = {fn.lower() for fn in contents}
 
+        self._cache_is_normalized = False
+
+    def _normalize_cache(self):
+        """
+        Normalize all entries in the caches to NFKC.
+        """
+        from unicodedata import normalize
+
+        self._path_cache = { normalize('NFKC', p) for p in self._path_cache }
+        self._relaxed_path_cache = { normalize('NFKC', p) for p in self._relaxed_path_cache }
+        self._cache_is_normalized = True
+
+
     @classmethod
     def path_hook(cls, *loader_details):
         """A class method which returns a closure to use on sys.path_hook

Lib/test/test_import/__init__.py

@@ -19,6 +19,7 @@
 import threading
 import time
 import types
+import unicodedata
 import unittest
 from unittest import mock
 import _imp
@@ -2701,6 +2702,43 @@ def test_pyimport_addmodule_create(self):
         mod = _testcapi.check_pyimport_addmodule(name)
         self.assertIs(mod, sys.modules[name])
 
+class TestImportAccented(unittest.TestCase):
+    # XXX: There should be tests with PYTHONCASEOK as well
+    #      (for those platforms where this is relevant)
+    dir_name = os.path.abspath(TESTFN)
+
+    def setUp(self):
+        self.sys_path = sys.path[:]
+        os.mkdir(self.dir_name)
+        sys.path.insert(0, self.dir_name)
+        importlib.invalidate_caches()
+
+    def tearDown(self):
+        sys.path[:] = self.sys_path
+        importlib.invalidate_caches()
+        rmtree(self.dir_name)
+
+    def assert_importing_possible(self, name):
+        filename = os.path.join(self.dir_name, f"{name}.py")
+        with open(filename, "w") as stream:
+            stream.write("SPAM = 'spam'\n")
+
+        values = {}
+        exec(f"from {name} import SPAM", values, values)
+        self.assertEqual(values["SPAM"], "spam")
+        del sys.modules[unicodedata.normalize('NFKC', name)]
+
+    def test_import_precomposed(self):
+        name = 'M\u00E4dchen'
+        self.assert_importing_possible(name)
+
+    def test_import_normalized(self):
+        name = 'M\u0061\u0308dchen'
+        self.assert_importing_possible(name)
+
+    def test_import_macos_input(self):
+        name = 'Mädchen'
+        self.assert_importing_possible(name)
 
 if __name__ == '__main__':
     # Test needs to be a package, so we can do relative imports.