bpo-43882 - urllib.parse should sanitize urls containing ASCII newline and tabs. (GH-25595)

* issue43882 - urllib.parse should sanitize urls containing ASCII newline and tabs.

Co-authored-by: Gregory P. Smith <greg@krypto.org>
Co-authored-by: Serhiy Storchaka <storchaka@gmail.com>
This commit is contained in:
Senthil Kumaran 2021-04-29 10:16:50 -07:00 committed by GitHub
parent 14fc2bdfab
commit 76cd81d603
No known key found for this signature in database
GPG key ID: 4AEE18F83AFDEB23
4 changed files with 54 additions and 0 deletions

View file

@ -612,6 +612,35 @@ class UrlParseTestCase(unittest.TestCase):
with self.assertRaisesRegex(ValueError, "out of range"):
p.port
def test_urlsplit_remove_unsafe_bytes(self):
# Remove ASCII tabs and newlines from input
url = "http://www.python.org/java\nscript:\talert('msg\r\n')/#frag"
p = urllib.parse.urlsplit(url)
self.assertEqual(p.scheme, "http")
self.assertEqual(p.netloc, "www.python.org")
self.assertEqual(p.path, "/javascript:alert('msg')/")
self.assertEqual(p.query, "")
self.assertEqual(p.fragment, "frag")
self.assertEqual(p.username, None)
self.assertEqual(p.password, None)
self.assertEqual(p.hostname, "www.python.org")
self.assertEqual(p.port, None)
self.assertEqual(p.geturl(), "http://www.python.org/javascript:alert('msg')/#frag")
# Remove ASCII tabs and newlines from input as bytes.
url = b"http://www.python.org/java\nscript:\talert('msg\r\n')/#frag"
p = urllib.parse.urlsplit(url)
self.assertEqual(p.scheme, b"http")
self.assertEqual(p.netloc, b"www.python.org")
self.assertEqual(p.path, b"/javascript:alert('msg')/")
self.assertEqual(p.query, b"")
self.assertEqual(p.fragment, b"frag")
self.assertEqual(p.username, None)
self.assertEqual(p.password, None)
self.assertEqual(p.hostname, b"www.python.org")
self.assertEqual(p.port, None)
self.assertEqual(p.geturl(), b"http://www.python.org/javascript:alert('msg')/#frag")
def test_attributes_bad_port(self):
"""Check handling of invalid ports."""
for bytes in (False, True):