58d0bc2f29
Fixes CVE-2019-9636: urlsplit does not handle NFKC normalization https://bugs.python.org/issue36216 The fix unfortunately introduced regressions, so also apply the followup fixes. https://bugs.python.org/issue36742 Signed-off-by: Peter Korsgaard <peter@korsgaard.com> Signed-off-by: Thomas Petazzoni <thomas.petazzoni@bootlin.com>
68 lines
2.8 KiB
Diff
68 lines
2.8 KiB
Diff
From f61599b050c621386a3fc6bc480359e2d3bb93de Mon Sep 17 00:00:00 2001
|
|
From: Steve Dower <steve.dower@python.org>
|
|
Date: Tue, 4 Jun 2019 09:40:16 -0700
|
|
Subject: [PATCH] bpo-36742: Corrects fix to handle decomposition in usernames
|
|
(GH-13812)
|
|
|
|
Signed-off-by: Peter Korsgaard <peter@korsgaard.com>
|
|
---
|
|
Lib/test/test_urlparse.py | 13 +++++++------
|
|
Lib/urlparse.py | 12 ++++++------
|
|
2 files changed, 13 insertions(+), 12 deletions(-)
|
|
|
|
diff --git a/Lib/test/test_urlparse.py b/Lib/test/test_urlparse.py
|
|
index 6fd1071bf7..857ed96d92 100644
|
|
--- a/Lib/test/test_urlparse.py
|
|
+++ b/Lib/test/test_urlparse.py
|
|
@@ -648,12 +648,13 @@ class UrlParseTestCase(unittest.TestCase):
|
|
urlparse.urlsplit(u'http://\u30d5\u309a\ufe1380')
|
|
|
|
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 f08e0fe584..6834f3c179 100644
|
|
--- a/Lib/urlparse.py
|
|
+++ b/Lib/urlparse.py
|
|
@@ -171,17 +171,17 @@ 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 = n.replace('?', '')
|
|
+ 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
|
|
for c in '/?#@:':
|
|
if c in netloc2:
|
|
- raise ValueError("netloc '" + netloc + "' contains invalid " +
|
|
- "characters under NFKC normalization")
|
|
+ raise ValueError(u"netloc '" + netloc + u"' contains invalid " +
|
|
+ u"characters under NFKC normalization")
|
|
|
|
def urlsplit(url, scheme='', allow_fragments=True):
|
|
"""Parse a URL into 5 components:
|
|
--
|
|
2.11.0
|
|
|