From 1331e6cfa422e57d528421644b5bfb4fb045f943 Mon Sep 17 00:00:00 2001 From: Steve Dower Date: Tue, 4 Jun 2019 09:40:16 -0700 Subject: [PATCH 03/24] bpo-36742: Corrects fix to handle decomposition in usernames (GH-13812) --- Lib/test/test_urlparse.py | 13 +++++++------ Lib/urlparse.py | 14 +++++++++----- 2 files changed, 16 insertions(+), 11 deletions(-) diff --git a/Lib/test/test_urlparse.py b/Lib/test/test_urlparse.py index 1830d0b286..669382cba9 100644 --- a/Lib/test/test_urlparse.py +++ b/Lib/test/test_urlparse.py @@ -642,12 +642,13 @@ class UrlParseTestCase(unittest.TestCase): self.assertIn(u'\uFF03', denorm_chars) for scheme in [u"http", u"https", u"ftp"]: - for c in denorm_chars: - url = u"{}://netloc{}false.netloc/path".format(scheme, c) - if test_support.verbose: - print "Checking %r" % url - with self.assertRaises(ValueError): - urlparse.urlsplit(url) + for netloc in [u"netloc{}false.netloc", u"n{}user@netloc"]: + for c in denorm_chars: + url = u"{}://{}/path".format(scheme, netloc.format(c)) + if test_support.verbose: + print "Checking %r" % url + with self.assertRaises(ValueError): + urlparse.urlsplit(url) def test_main(): test_support.run_unittest(UrlParseTestCase) diff --git a/Lib/urlparse.py b/Lib/urlparse.py index 54eda08651..798b467b60 100644 --- a/Lib/urlparse.py +++ b/Lib/urlparse.py @@ -171,14 +171,18 @@ def _checknetloc(netloc): # looking for characters like \u2100 that expand to 'a/c' # IDNA uses NFKC equivalence, so normalize for this check import unicodedata - netloc2 = unicodedata.normalize('NFKC', netloc) - if netloc == netloc2: + n = netloc.replace(u'@', u'') # ignore characters already included + n = n.replace(u':', u'') # but not the surrounding text + n = n.replace(u'#', u'') + n = n.replace(u'?', u'') + netloc2 = unicodedata.normalize('NFKC', n) + if n == netloc2: return - _, _, netloc = netloc.rpartition('@') # anything to the left of '@' is okay for c in '/?#@:': if c in netloc2: - raise ValueError("netloc '" + netloc2 + "' contains invalid " + - "characters under NFKC normalization") + raise ValueError("netloc %r contains invalid characters " + "under NFKC normalization" + % netloc) def urlsplit(url, scheme='', allow_fragments=True): """Parse a URL into 5 components: -- 2.23.0