deprecate non-ascii

Author: StanFromIreland

Doc/deprecations/pending-removal-in-3.17.rst

@@ -23,6 +23,12 @@ Pending removal in Python 3.17
     (Contributed by Shantanu Jain in :gh:`91896`.)
 
 
+* :mod:`encodings`:
+
+  - Passing non-ascii *encoding* names to :func:`encodings.normalize_encoding`
+    is deprecated and scheduled for removal in Python 3.17.
+    (Contributed by Stan Ulbrych in :gh:`136702`)
+
 * :mod:`typing`:
 
   - Before Python 3.14, old-style unions were implemented using the private class

Lib/encodings/__init__.py

@@ -26,9 +26,10 @@
 
 (c) Copyright CNRI, All Rights Reserved. NO WARRANTY.
 
-"""#"
+"""
 
 import codecs
+import warnings
 import sys
 from . import aliases
 
@@ -55,6 +56,11 @@ def normalize_encoding(encoding):
     if isinstance(encoding, bytes):
         encoding = str(encoding, "ascii")
 
+    if not encoding.isascii():
+        warnings.warn(
+            "Support for non-ascii encoding names will be removed in 3.17",
+            DeprecationWarning, stacklevel=2)
+
     chars = []
     punct = False
     for c in encoding:

Lib/test/test_codecs.py

@@ -3886,22 +3886,26 @@ def search_function(encoding):
         self.assertEqual(codecs.lookup('TEST.AAA 8'), ('test.aaa-8', 2, 3, 4))
         self.assertEqual(codecs.lookup('TEST.AAA---8'), ('test.aaa---8', 2, 3, 4))
         self.assertEqual(codecs.lookup('TEST.AAA   8'), ('test.aaa---8', 2, 3, 4))
-        self.assertEqual(codecs.lookup('TEST.AAA\xe9\u20ac-8'), ('test.aaa\xe9\u20ac-8', 2, 3, 4))
         self.assertEqual(codecs.lookup('TEST.AAA.8'), ('test.aaa.8', 2, 3, 4))
         self.assertEqual(codecs.lookup('TEST.AAA...8'), ('test.aaa...8', 2, 3, 4))
+        with self.assertWarns(DeprecationWarning):
+            self.assertEqual(codecs.lookup('TEST.AAA\xe9\u20ac-8'), ('test.aaa\xe9\u20ac-8', 2, 3, 4))
 
     def test_encodings_normalize_encoding(self):
-        # encodings.normalize_encoding() ignores non-ASCII characters.
         normalize = encodings.normalize_encoding
         self.assertEqual(normalize('utf_8'), 'utf_8')
-        self.assertEqual(normalize('utf\xE9\u20AC\U0010ffff-8'), 'utf_8')
         self.assertEqual(normalize('utf   8'), 'utf_8')
         # encodings.normalize_encoding() doesn't convert
         # characters to lower case.
         self.assertEqual(normalize('UTF 8'), 'UTF_8')
         self.assertEqual(normalize('utf.8'), 'utf.8')
         self.assertEqual(normalize('utf...8'), 'utf...8')
 
+        # Non-ASCII *encoding* is deprecated.
+        with self.assertWarnsRegex(DeprecationWarning,
+                "Support for non-ascii encoding names will be removed in 3.17"):
+            self.assertEqual(normalize('utf\xE9\u20AC\U0010ffff-8'), 'utf_8')
+
 
 if __name__ == "__main__":
     unittest.main()

Misc/NEWS.d/next/Library/2025-10-13-11-25-41.gh-issue-136702.uvLGK1.rst

@@ -0,0 +1,3 @@
+:mod:`encodings`: Deprecate passing a non-ascii *encoding* name to
+:func:`encodings.normalize_encoding` and schedule removal of support for
+Python 3.17.