diff options
| author | Miss Islington (bot) <31488909+miss-islington@users.noreply.github.com> | 2019-06-04 11:43:52 -0700 |
|---|---|---|
| committer | Ned Deily <nad@python.org> | 2019-06-04 14:43:52 -0400 |
| commit | fd1771dbdd28709716bd531580c40ae5ed814468 (patch) | |
| tree | ed5486ac18e1fa4928eac479a52f2f0457c49ad9 | |
| parent | 4f06dae5d8d4400ba38d8502da620f07d4a5696e (diff) | |
| download | cpython-git-fd1771dbdd28709716bd531580c40ae5ed814468.tar.gz | |
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>
| -rw-r--r-- | Lib/test/test_urlparse.py | 11 | ||||
| -rw-r--r-- | 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 c262354494..68f633ca3a 100644 --- 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 791b457bfb..fa8827a9fa 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: |