From 4d723e76e1ad17e9e7d5e828e59bb47e76f2174b Mon Sep 17 00:00:00 2001 From: "Miss Islington (bot)" <31488909+miss-islington@users.noreply.github.com> Date: Tue, 30 Apr 2019 05:21:02 -0700 Subject: [PATCH] bpo-36742: Fixes handling of pre-normalization characters in urlsplit() (GH-13017) (cherry picked from commit d537ab0ff9767ef024f26246899728f0116b1ec3) Co-authored-by: Steve Dower Signed-off-by: Peter Korsgaard --- Lib/test/test_urlparse.py | 6 ++++++ Lib/urllib/parse.py | 11 +++++++---- .../next/Security/2019-04-29-15-34-59.bpo-36742.QCUY0i.rst | 1 + 3 files changed, 14 insertions(+), 4 deletions(-) create mode 100644 Misc/NEWS.d/next/Security/2019-04-29-15-34-59.bpo-36742.QCUY0i.rst diff --git a/Lib/test/test_urlparse.py b/Lib/test/test_urlparse.py index e6638aee22..c262354494 100644 --- a/Lib/test/test_urlparse.py +++ b/Lib/test/test_urlparse.py @@ -1001,6 +1001,12 @@ class UrlParseTestCase(unittest.TestCase): self.assertIn('\u2100', denorm_chars) self.assertIn('\uFF03', denorm_chars) + # bpo-36742: Verify port separators are ignored when they + # existed prior to decomposition + urllib.parse.urlsplit('http://\u30d5\u309a:80') + with self.assertRaises(ValueError): + 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) diff --git a/Lib/urllib/parse.py b/Lib/urllib/parse.py index 1eec26e0f1..f5b3487ea9 100644 --- a/Lib/urllib/parse.py +++ b/Lib/urllib/parse.py @@ -397,13 +397,16 @@ 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.rpartition('@')[2] # ignore anything to the left of '@' + n = n.replace(':', '') # ignore characters already included + n = n.replace('#', '') # but not the surrounding text + n = n.replace('?', '') + 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 " + + raise ValueError("netloc '" + netloc + "' contains invalid " + "characters under NFKC normalization") def urlsplit(url, scheme='', allow_fragments=True): diff --git a/Misc/NEWS.d/next/Security/2019-04-29-15-34-59.bpo-36742.QCUY0i.rst b/Misc/NEWS.d/next/Security/2019-04-29-15-34-59.bpo-36742.QCUY0i.rst new file mode 100644 index 0000000000..d729ed2f3c --- /dev/null +++ b/Misc/NEWS.d/next/Security/2019-04-29-15-34-59.bpo-36742.QCUY0i.rst @@ -0,0 +1 @@ +Fixes mishandling of pre-normalization characters in urlsplit(). -- 2.11.0