FazBrowse GitHub Viewer | Trending |
URL:
| Home
Tools: [Download Repo ZIP]   [Original HTTPS Page]

[3.10] gh-103848: Adds checks to ensure that bracketed hosts found by urlsplit are of IPv6 or IPvFuture format (#103849) by vstinner · Pull Request #126975 · python/cpython · GitHub

/ cpython Public

[3.10] gh-103848: Adds checks to ensure that bracketed hosts found by urlsplit are of IPv6 or IPvFuture format (#103849) #126975

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
ambv merged 1 commit into from
Dec 2, 2024
+43 −1
Conversation 3 Commits 1 Checks 0 Files changed 3
Merged

[3.10] gh-103848: Adds checks to ensure that bracketed hosts found by urlsplit are of IPv6 or IPvFuture format (#103849) #126975

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension .py  (2) .rst  (1) All 2 file types selected
Viewed files
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Unified
Split
Hide whitespace
Diff view
Unified
Split
Hide whitespace
26 changes: 26 additions & 0 deletions Lib/test/test_urlparse.py
Show comments
View file
Open in desktop
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters. Learn more about bidirectional Unicode characters
Show hidden characters
Original file line number Diff line number Diff line change
Expand Up @@ -1138,6 +1138,32 @@ def test_issue14072(self):
self.assertEqual(p2.scheme, 'tel')
self.assertEqual(p2.path, '+31641044153')

def test_invalid_bracketed_hosts(self):
self.assertRaises(ValueError, urllib.parse.urlsplit, 'Scheme://user@[192.0.2.146]/Path?Query')
self.assertRaises(ValueError, urllib.parse.urlsplit, 'Scheme://user@[important.com:8000]/Path?Query')
self.assertRaises(ValueError, urllib.parse.urlsplit, 'Scheme://user@[v123r.IP]/Path?Query')
self.assertRaises(ValueError, urllib.parse.urlsplit, 'Scheme://user@[v12ae]/Path?Query')
self.assertRaises(ValueError, urllib.parse.urlsplit, 'Scheme://user@[v.IP]/Path?Query')
self.assertRaises(ValueError, urllib.parse.urlsplit, 'Scheme://user@[v123.]/Path?Query')
self.assertRaises(ValueError, urllib.parse.urlsplit, 'Scheme://user@[v]/Path?Query')
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')

def test_splitting_bracketed_hosts(self):
p1 = urllib.parse.urlsplit('scheme://user@[v6a.ip]/path?query')
self.assertEqual(p1.hostname, 'v6a.ip')
self.assertEqual(p1.username, 'user')
self.assertEqual(p1.path, '/path')
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')
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')
self.assertEqual(p3.path, '/path')

def test_port_casting_failure_message(self):
message = "Port could not be cast to integer value as 'oracle'"
p1 = urllib.parse.urlparse('http://Server=sde; Service=sde:oracle')
Expand Down
16 changes: 15 additions & 1 deletion Lib/urllib/parse.py
Show comments
View file
Open in desktop
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters. Learn more about bidirectional Unicode characters
Show hidden characters
Original file line number Diff line number Diff line change
Expand Up @@ -36,6 +36,7 @@
import types
import collections
import warnings
import ipaddress

__all__ = ["urlparse", "urlunparse", "urljoin", "urldefrag",
"urlsplit", "urlunsplit", "urlencode", "parse_qs",
Expand Down Expand Up @@ -441,6 +442,17 @@ def _checknetloc(netloc):
raise ValueError("netloc '" + netloc + "' contains invalid " +
"characters under NFKC normalization")

# 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):
if hostname.startswith('v'):
if not re.match(r"\Av[a-fA-F0-9]+\..+\Z", hostname):
raise ValueError(f"IPvFuture address is invalid")
else:
ip = ipaddress.ip_address(hostname) # Throws Value Error if not IPv6 or IPv4
if isinstance(ip, ipaddress.IPv4Address):
raise ValueError(f"An IPv4 address cannot be in brackets")

def urlsplit(url, scheme='', allow_fragments=True):
"""Parse a URL into 5 components:
<scheme>://<netloc>/<path>?<query>#<fragment>
Expand Down Expand Up @@ -487,12 +499,14 @@ def urlsplit(url, scheme='', allow_fragments=True):
break
else:
scheme, url = url[:i].lower(), url[i+1:]

if url[:2] == '//':
netloc, url = _splitnetloc(url, 2)
if (('[' in netloc and ']' not in netloc) or
(']' 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)
if allow_fragments and '#' in url:
url, fragment = url.split('#', 1)
if '?' in url:
Expand Down
2 changes: 2 additions & 0 deletions Misc/NEWS.d/next/Library/2023-04-26-09-54-25.gh-issue-103848.aDSnpR.rst
Show comments
View file
Open in desktop
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters. Learn more about bidirectional Unicode characters
Show hidden characters
Original file line number Diff line number Diff line change
@@ -0,0 +1,2 @@
Add checks to ensure that ``[`` bracketed ``]`` hosts found by
:func:`urllib.parse.urlsplit` are of IPv6 or IPvFuture format.
Back | FazBrowse Home | New Git URL