[Python-checkins] bpo-36742: Corrects fix to handle decomposition in usernames (GH-13812)

Miss Islington (bot) webhook-mailer at python.org
Tue Jun 4 12:15:28 EDT 2019


https://github.com/python/cpython/commit/250b62acc59921d399f0db47db3b462cd6037e09
commit: 250b62acc59921d399f0db47db3b462cd6037e09
branch: 3.7
author: Miss Islington (bot) <31488909+miss-islington at users.noreply.github.com>
committer: GitHub <noreply at github.com>
date: 2019-06-04T09:15:13-07:00
summary:

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

(cherry picked from commit 8d0ef0b5edeae52960c7ed05ae8a12388324f87e)

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

files:
M Lib/test/test_urlparse.py
M Lib/urllib/parse.py

diff --git a/Lib/test/test_urlparse.py b/Lib/test/test_urlparse.py
index c26235449461..68f633ca3a7d 100644
--- a/Lib/test/test_urlparse.py
+++ b/Lib/test/test_urlparse.py
@@ -1008,11 +1008,12 @@ 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 at 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 f5b3487ea9d6..4c8e77fe3912 100644
--- 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:



More information about the Python-checkins mailing list