From 095373c32d16df575ba5fcb5f44bf44119b26193 Mon Sep 17 00:00:00 2001 From: Victor Stinner Date: Sat, 7 Sep 2019 08:33:24 +0200 Subject: [PATCH] bpo-36742: Corrects fix to handle decomposition in usernames (GH-13812) (GH-13814) (#14772) (cherry picked from commit 8d0ef0b5edeae52960c7ed05ae8a12388324f87e) Co-authored-by: Steve Dower (cherry picked from commit fd1771dbdd28709716bd531580c40ae5ed814468) --- Lib/test/test_urlparse.py | 11 ++++++----- Lib/urllib/parse.py | 6 +++--- 2 files changed, 9 insertions(+), 8 deletions(-) diff --git a/Lib/test/test_urlparse.py b/Lib/test/test_urlparse.py index 1e90e18609..ebb30ea01c 100644 --- a/Lib/test/test_urlparse.py +++ b/Lib/test/test_urlparse.py @@ -994,11 +994,12 @@ 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 7405d660fc..60fd5e4e0f 100644 --- a/Lib/urllib/parse.py +++ b/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: -- 2.40.0