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

(cherry picked from commit 8d0ef0b5edeae52960c7ed05ae8a12388324f87e)

Co-authored-by: Steve Dower <steve.dower@python.org>

diff --git a/Lib/test/test_urlparse.py b/Lib/test/test_urlparse.py
index c262354494619851cfca4cf81655fd8672188a1e..68f633ca3a7dbcece4bbcb99670e784e3b4e5568 100644 (file)
--- a/Lib/test/test_urlparse.py
+++ b/Lib/test/test_urlparse.py
@@ -1008,11 +1008,12 @@ class UrlParseTestCase(unittest.TestCase):
             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."""

diff --git a/Lib/urllib/parse.py b/Lib/urllib/parse.py
index 791b457bfb8a82946a53dadd31e4c5409ff0a1f9..fa8827a9fa79087f8d41f5e8a0ce0ad0f488f15f 100644 (file)
--- a/Lib/urllib/parse.py
+++ b/Lib/urllib/parse.py
@@ -397,9 +397,9 @@ 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: