gh-136736: Fix handling alphanumerical non-ASCII characters in encodings.normalize_encoding()

Author: serhiy-storchaka

Lib/encodings/__init__.py

@@ -58,11 +58,10 @@ def normalize_encoding(encoding):
     chars = []
     punct = False
     for c in encoding:
-        if c.isalnum() or c == '.':
+        if c.isascii() and (c.isalnum() or c == '.'):
             if punct and chars:
                 chars.append('_')
-            if c.isascii():
-                chars.append(c)
+            chars.append(c)
             punct = False
         else:
             punct = True

Lib/test/test_codecs.py

@@ -3888,6 +3888,12 @@ def search_function(encoding):
         self.assertEqual(FOUND, codecs.lookup('AAA---8'))
         self.assertEqual(FOUND, codecs.lookup('AAA   8'))
         self.assertEqual(FOUND, codecs.lookup('aaa\xe9\u20ac-8'))
+        self.assertEqual(FOUND, codecs.lookup('aaa\xe98'))
+        self.assertEqual(FOUND, codecs.lookup('aaa\u20ac8'))
+        self.assertEqual(FOUND, codecs.lookup('aaa-\xe9-8'))
+        self.assertEqual(FOUND, codecs.lookup('aaa-\u20ac-8'))
+        self.assertEqual(FOUND, codecs.lookup('aaa-8-\xe9'))
+        self.assertEqual(FOUND, codecs.lookup('aaa-8-\u20ac'))
         self.assertEqual(NOT_FOUND, codecs.lookup('AAA.8'))
         self.assertEqual(NOT_FOUND, codecs.lookup('AAA...8'))
         self.assertEqual(NOT_FOUND, codecs.lookup('BBB-8'))
@@ -3899,6 +3905,12 @@ def test_encodings_normalize_encoding(self):
         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\xe98'), 'utf_8')
+        self.assertEqual(normalize('utf\u20ac8'), 'utf_8')
+        self.assertEqual(normalize('utf-\xe9-8'), 'utf_8')
+        self.assertEqual(normalize('utf-\u20ac-8'), 'utf_8')
+        self.assertEqual(normalize('utf-8-\xe9'), 'utf_8')
+        self.assertEqual(normalize('utf-8-\u20ac'), 'utf_8')
         self.assertEqual(normalize('utf   8'), 'utf_8')
         # encodings.normalize_encoding() doesn't convert
         # characters to lower case.

Misc/NEWS.d/next/Library/2025-07-17-11-59-10.gh-issue-136736.kzQ_dY.rst

@@ -0,0 +1,2 @@
+Fix handling alphanumerical non-ASCII characters in
+:func:`encodings.normalize_encoding`.