Skip to content

[3.6] bpo-43882 - urllib.parse should sanitize urls containing ASCII newline and tabs. (GH-25595) #25728

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

Closed
miss-islington wants to merge 3 commits into from
Closed

[3.6] bpo-43882 - urllib.parse should sanitize urls containing ASCII newline and tabs. (GH-25595) #25728

Show file tree
Hide file tree
Changes from 1 commit
Commits
Show all changes
3 commits
Select commit Hold shift + click to select a range
fa537f3
bpo-43882 - urllib.parse should sanitize urls containing ASCII newlin…
orsenthil Apr 29, 2021
c5c33b4
Update version to 3.6.14
orsenthil Apr 29, 2021
630c3b7
Fix 3.6 tests.
orsenthil Apr 30, 2021
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
Prev Previous commit
Fix 3.6 tests.
  • Loading branch information
@orsenthil
orsenthil committed Apr 30, 2021
commit 630c3b7c539fdf2a6d5625cb0245fbf659ebc719
14 changes: 12 additions & 2 deletions Lib/test/test_urlparse.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -613,7 +613,7 @@ def test_urlsplit_attributes(self):
p.port

def test_urlsplit_remove_unsafe_bytes(self):
# Remove ASCII tabs and newlines from input
# Remove ASCII tabs and newlines from input, for http common case scenario.
url = "http://www.python.org/java\nscript:\talert('msg\r\n')/#frag"
p = urllib.parse.urlsplit(url)
self.assertEqual(p.scheme, "http")
Expand All @@ -627,7 +627,7 @@ def test_urlsplit_remove_unsafe_bytes(self):
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.
# Remove ASCII tabs and newlines from input as bytes, for http common case scenario.
url = b"http://www.python.org/java\nscript:\talert('msg\r\n')/#frag"
p = urllib.parse.urlsplit(url)
self.assertEqual(p.scheme, b"http")
Expand All @@ -641,6 +641,16 @@ def test_urlsplit_remove_unsafe_bytes(self):
self.assertEqual(p.port, None)
self.assertEqual(p.geturl(), b"http://www.python.org/javascript:alert('msg')/#frag")

# any scheme
url = "x-new-scheme://www.python.org/java\nscript:\talert('msg\r\n')/#frag"
p = urllib.parse.urlsplit(url)
self.assertEqual(p.geturl(), "x-new-scheme://www.python.org/javascript:alert('msg')/#frag")

# Remove ASCII tabs and newlines from input as bytes, any scheme.
url = b"x-new-scheme://www.python.org/java\nscript:\talert('msg\r\n')/#frag"
p = urllib.parse.urlsplit(url)
self.assertEqual(p.geturl(), b"x-new-scheme://www.python.org/javascript:alert('msg')/#frag")

def test_attributes_bad_port(self):
"""Check handling of invalid ports."""
for bytes in (False, True):
Expand Down
9 changes: 7 additions & 2 deletions Lib/urllib/parse.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -412,6 +412,11 @@ def _checknetloc(netloc):
raise ValueError("netloc '" + netloc + "' contains invalid " +
"characters under NFKC normalization")

def _remove_unsafe_bytes_from_url(url):
for b in _UNSAFE_URL_BYTES_TO_REMOVE:
url = url.replace(b, "")
return url

def urlsplit(url, scheme='', allow_fragments=True):
"""Parse a URL into 5 components:
<scheme>://<netloc>/<path>?<query>#<fragment>
Expand Down Expand Up @@ -442,6 +447,7 @@ def urlsplit(url, scheme='', allow_fragments=True):
if '?' in url:
url, query = url.split('?', 1)
_checknetloc(netloc)
url = _remove_unsafe_bytes_from_url(url)
v = SplitResult(scheme, netloc, url, query, fragment)
_parse_cache[key] = v
return _coerce_result(v)
Expand All @@ -456,8 +462,7 @@ def urlsplit(url, scheme='', allow_fragments=True):
# not a port number
scheme, url = url[:i].lower(), rest

for b in _UNSAFE_URL_BYTES_TO_REMOVE:
url = url.replace(b, "")
url = _remove_unsafe_bytes_from_url(url)

if url[:2] == '//':
netloc, url = _splitnetloc(url, 2)
Expand Down