bpo-36742: Corrects fix to handle decomposition in usernames (GH-13812) (GH-13814) (#14772)

(cherry picked from commit 8d0ef0b)

Co-authored-by: Steve Dower <steve.dower@python.org>
(cherry picked from commit fd1771d)

Author: 2 people

Lib/test/test_urlparse.py

@@ -994,11 +994,12 @@ def test_urlsplit_normalization(self):
             urllib.parse.urlsplit('http://\u30d5\u309a\ufe1380')
 
         for scheme in ["http", "https", "ftp"]:
-            for c in denorm_chars:
-                url = "{}://netloc{}false.netloc/path".format(scheme, c)
-                with self.subTest(url=url, char='{:04X}'.format(ord(c))):
-                    with self.assertRaises(ValueError):
-                        urllib.parse.urlsplit(url)
+            for netloc in ["netloc{}false.netloc", "n{}user@netloc"]:
+                for c in denorm_chars:
+                    url = "{}://{}/path".format(scheme, netloc.format(c))
+                    with self.subTest(url=url, char='{:04X}'.format(ord(c))):
+                        with self.assertRaises(ValueError):
+                            urllib.parse.urlsplit(url)
 
 class Utility_Tests(unittest.TestCase):
     """Testcase to test the various utility functions in the urllib."""

Lib/urllib/parse.py

@@ -333,9 +333,9 @@ def _checknetloc(netloc):
     # looking for characters like \u2100 that expand to 'a/c'
     # IDNA uses NFKC equivalence, so normalize for this check
     import unicodedata
-    n = netloc.rpartition('@')[2] # ignore anything to the left of '@'
-    n = n.replace(':', '')        # ignore characters already included
-    n = n.replace('#', '')        # but not the surrounding text
+    n = netloc.replace('@', '')   # ignore characters already included
+    n = n.replace(':', '')        # but not the surrounding text
+    n = n.replace('#', '')
     n = n.replace('?', '')
     netloc2 = unicodedata.normalize('NFKC', n)
     if n == netloc2: