Skip to content

gh-105704: Disallow square brackets ([ and ]) in domain names for parsed URLs #129418

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
merged 4 commits into from
Jan 31, 2025
Merged

gh-105704: Disallow square brackets ([ and ]) in domain names for parsed URLs #129418

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
4 commits
Select commit Hold shift + click to select a range
6204ab9
gh-105704: Disallow square brackets ( and ) in domain names for parse…
sethmlarson Jan 28, 2025
3ab35e8
Use Sphinx references
sethmlarson Jan 30, 2025
ebf92bb
Add mismatched bracket test cases, fix news format
sethmlarson Jan 30, 2025
2817b2e
Add more test coverage for ports
sethmlarson Jan 30, 2025
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
37 changes: 36 additions & 1 deletion Lib/test/test_urlparse.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -1412,16 +1412,51 @@ def test_invalid_bracketed_hosts(self):
self.assertRaises(ValueError, urllib.parse.urlsplit, 'Scheme://user@[0439:23af::2309::fae7:1234]/Path?Query')
self.assertRaises(ValueError, urllib.parse.urlsplit, 'Scheme://user@[0439:23af:2309::fae7:1234:2342:438e:192.0.2.146]/Path?Query')
self.assertRaises(ValueError, urllib.parse.urlsplit, 'Scheme://user@]v6a.ip[/Path')
self.assertRaises(ValueError, urllib.parse.urlsplit, 'scheme://prefix.[v6a.ip]')
self.assertRaises(ValueError, urllib.parse.urlsplit, 'scheme://[v6a.ip].suffix')
self.assertRaises(ValueError, urllib.parse.urlsplit, 'scheme://prefix.[v6a.ip]/')
self.assertRaises(ValueError, urllib.parse.urlsplit, 'scheme://[v6a.ip].suffix/')
self.assertRaises(ValueError, urllib.parse.urlsplit, 'scheme://prefix.[v6a.ip]?')
self.assertRaises(ValueError, urllib.parse.urlsplit, 'scheme://[v6a.ip].suffix?')
self.assertRaises(ValueError, urllib.parse.urlsplit, 'scheme://prefix.[::1]')
self.assertRaises(ValueError, urllib.parse.urlsplit, 'scheme://[::1].suffix')
self.assertRaises(ValueError, urllib.parse.urlsplit, 'scheme://prefix.[::1]/')
self.assertRaises(ValueError, urllib.parse.urlsplit, 'scheme://[::1].suffix/')
self.assertRaises(ValueError, urllib.parse.urlsplit, 'scheme://prefix.[::1]?')
self.assertRaises(ValueError, urllib.parse.urlsplit, 'scheme://[::1].suffix?')
self.assertRaises(ValueError, urllib.parse.urlsplit, 'scheme://prefix.[::1]:a')
self.assertRaises(ValueError, urllib.parse.urlsplit, 'scheme://[::1].suffix:a')
self.assertRaises(ValueError, urllib.parse.urlsplit, 'scheme://prefix.[::1]:a1')
self.assertRaises(ValueError, urllib.parse.urlsplit, 'scheme://[::1].suffix:a1')
self.assertRaises(ValueError, urllib.parse.urlsplit, 'scheme://prefix.[::1]:1a')
self.assertRaises(ValueError, urllib.parse.urlsplit, 'scheme://[::1].suffix:1a')
self.assertRaises(ValueError, urllib.parse.urlsplit, 'scheme://prefix.[::1]:')
self.assertRaises(ValueError, urllib.parse.urlsplit, 'scheme://[::1].suffix:/')
self.assertRaises(ValueError, urllib.parse.urlsplit, 'scheme://prefix.[::1]:?')
self.assertRaises(ValueError, urllib.parse.urlsplit, 'scheme://user@prefix.[v6a.ip]')
self.assertRaises(ValueError, urllib.parse.urlsplit, 'scheme://user@[v6a.ip].suffix')
Copy link
Member

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

It might be helpful to add tests only with [, and tests only with ]. Such URL is also invalid, no?

Copy link
Contributor Author

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Yeah, I'll add tests with that structure too! Thanks :)

Copy link
Contributor Author

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Added in ebf92bb

self.assertRaises(ValueError, urllib.parse.urlsplit, 'scheme://[v6a.ip')
self.assertRaises(ValueError, urllib.parse.urlsplit, 'scheme://v6a.ip]')
self.assertRaises(ValueError, urllib.parse.urlsplit, 'scheme://]v6a.ip[')
self.assertRaises(ValueError, urllib.parse.urlsplit, 'scheme://]v6a.ip')
self.assertRaises(ValueError, urllib.parse.urlsplit, 'scheme://v6a.ip[')
self.assertRaises(ValueError, urllib.parse.urlsplit, 'scheme://prefix.[v6a.ip')
self.assertRaises(ValueError, urllib.parse.urlsplit, 'scheme://v6a.ip].suffix')
self.assertRaises(ValueError, urllib.parse.urlsplit, 'scheme://prefix]v6a.ip[suffix')
self.assertRaises(ValueError, urllib.parse.urlsplit, 'scheme://prefix]v6a.ip')
self.assertRaises(ValueError, urllib.parse.urlsplit, 'scheme://v6a.ip[suffix')

def test_splitting_bracketed_hosts(self):
p1 = urllib.parse.urlsplit('scheme://user@[v6a.ip]/path?query')
p1 = urllib.parse.urlsplit('scheme://user@[v6a.ip]:1234/path?query')
self.assertEqual(p1.hostname, 'v6a.ip')
self.assertEqual(p1.username, 'user')
self.assertEqual(p1.path, '/path')
self.assertEqual(p1.port, 1234)
p2 = urllib.parse.urlsplit('scheme://user@[0439:23af:2309::fae7%test]/path?query')
self.assertEqual(p2.hostname, '0439:23af:2309::fae7%test')
self.assertEqual(p2.username, 'user')
self.assertEqual(p2.path, '/path')
self.assertIs(p2.port, None)
p3 = urllib.parse.urlsplit('scheme://user@[0439:23af:2309::fae7:1234:192.0.2.146%test]/path?query')
self.assertEqual(p3.hostname, '0439:23af:2309::fae7:1234:192.0.2.146%test')
self.assertEqual(p3.username, 'user')
Expand Down
20 changes: 18 additions & 2 deletions Lib/urllib/parse.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -439,6 +439,23 @@ def _checknetloc(netloc):
raise ValueError("netloc '" + netloc + "' contains invalid " +
"characters under NFKC normalization")

def _check_bracketed_netloc(netloc):
# Note that this function must mirror the splitting
# done in NetlocResultMixins._hostinfo().
hostname_and_port = netloc.rpartition('@')[2]
before_bracket, have_open_br, bracketed = hostname_and_port.partition('[')
if have_open_br:
# No data is allowed before a bracket.
if before_bracket:
raise ValueError("Invalid IPv6 URL")
hostname, _, port = bracketed.partition(']')
# No data is allowed after the bracket but before the port delimiter.
if port and not port.startswith(":"):
raise ValueError("Invalid IPv6 URL")
else:
hostname, _, port = hostname_and_port.partition(':')
_check_bracketed_host(hostname)

# Valid bracketed hosts are defined in
# https://www.rfc-editor.org/rfc/rfc3986#page-49 and https://url.spec.whatwg.org/
def _check_bracketed_host(hostname):
Expand Down Expand Up @@ -505,8 +522,7 @@ def _urlsplit(url, scheme=None, allow_fragments=True):
(']' in netloc and '[' not in netloc)):
raise ValueError("Invalid IPv6 URL")
if '[' in netloc and ']' in netloc:
bracketed_host = netloc.partition('[')[2].partition(']')[0]
_check_bracketed_host(bracketed_host)
_check_bracketed_netloc(netloc)
if allow_fragments and '#' in url:
url, fragment = url.split('#', 1)
if '?' in url:
Expand Down
4 changes: 4 additions & 0 deletions Misc/NEWS.d/next/Security/2025-01-28-14-08-03.gh-issue-105704.EnhHxu.rst
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -0,0 +1,4 @@
When using :func:`urllib.parse.urlsplit` and :func:`urllib.parse.urlparse` host
parsing would not reject domain names containing square brackets (``[`` and
``]``). Square brackets are only valid for IPv6 and IPvFuture hosts according to
`RFC 3986 Section 3.2.2 <https://www.rfc-editor.org/rfc/rfc3986#section-3.2.2>`__.
Loading