Matej Cepl
c21db0430f
bsc#1208471) blocklists bypass via the urllib.parse component when supplying a URL that starts with blank characters OBS-URL: https://build.opensuse.org/package/show/devel:languages:python:Factory/python?expand=0&rev=343
52 lines
2.1 KiB
Diff
52 lines
2.1 KiB
Diff
---
|
|
Lib/test/test_urlparse.py | 20 ++++++++++
|
|
Lib/urlparse.py | 2 -
|
|
Misc/NEWS.d/next/Library/2022-11-12-15-45-51.gh-issue-99418.FxfAXS.rs | 2 +
|
|
3 files changed, 23 insertions(+), 1 deletion(-)
|
|
|
|
--- a/Lib/test/test_urlparse.py
|
|
+++ b/Lib/test/test_urlparse.py
|
|
@@ -592,6 +592,26 @@ class UrlParseTestCase(unittest.TestCase
|
|
self.assertEqual(p.netloc, "www.example.net:foo")
|
|
self.assertRaises(ValueError, lambda: p.port)
|
|
|
|
+ def do_attributes_bad_scheme(self, bytes, parse, scheme):
|
|
+ url = scheme + "://www.example.net"
|
|
+ if bytes:
|
|
+ if url.isascii():
|
|
+ url = url.encode("ascii")
|
|
+ else:
|
|
+ continue
|
|
+ p = parse(url)
|
|
+ if bytes:
|
|
+ self.assertEqual(p.scheme, b"")
|
|
+ else:
|
|
+ self.assertEqual(p.scheme, "")
|
|
+
|
|
+ def test_attributes_bad_scheme(self):
|
|
+ """Check handling of invalid schemes."""
|
|
+ for bytes in (False, True):
|
|
+ for parse in (urlparse.urlsplit, urlparse.urlparse):
|
|
+ for scheme in (".", "+", "-", "0", "http&", "६http"):
|
|
+ self.do_attributes_bad_scheme(bytes, parse, scheme)
|
|
+
|
|
def test_attributes_without_netloc(self):
|
|
# This example is straight from RFC 3261. It looks like it
|
|
# should allow the username, hostname, and port to be filled
|
|
--- a/Lib/urlparse.py
|
|
+++ b/Lib/urlparse.py
|
|
@@ -211,7 +211,7 @@ def urlsplit(url, scheme='', allow_fragm
|
|
clear_cache()
|
|
netloc = query = fragment = ''
|
|
i = url.find(':')
|
|
- if i > 0:
|
|
+ if i > 0 and url[0].isascii() and url[0].isalpha():
|
|
if url[:i] == 'http': # optimize the common case
|
|
scheme = url[:i].lower()
|
|
url = url[i+1:]
|
|
--- /dev/null
|
|
+++ b/Misc/NEWS.d/next/Library/2022-11-12-15-45-51.gh-issue-99418.FxfAXS.rs
|
|
@@ -0,0 +1,2 @@
|
|
+Fix bug in :func:`urllib.parse.urlparse` that causes URL schemes that begin
|
|
+with a digit, a plus sign, or a minus sign to be parsed incorrectly.
|