diff options
| -rw-r--r-- | Lib/test/test_urlparse.py | 18 | ||||
| -rw-r--r-- | Lib/urllib/parse.py | 2 | ||||
| -rw-r--r-- | Misc/NEWS.d/next/Library/2022-11-12-15-45-51.gh-issue-99418.FxfAXS.rst | 2 |
3 files changed, 21 insertions, 1 deletions
diff --git a/Lib/test/test_urlparse.py b/Lib/test/test_urlparse.py index b0aed37de7d..9ae154e5fce 100644 --- a/Lib/test/test_urlparse.py +++ b/Lib/test/test_urlparse.py @@ -727,6 +727,24 @@ class UrlParseTestCase(unittest.TestCase): with self.assertRaises(ValueError): p.port + def test_attributes_bad_scheme(self): + """Check handling of invalid schemes.""" + for bytes in (False, True): + for parse in (urllib.parse.urlsplit, urllib.parse.urlparse): + for scheme in (".", "+", "-", "0", "http&", "६http"): + with self.subTest(bytes=bytes, parse=parse, scheme=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_without_netloc(self): # This example is straight from RFC 3261. It looks like it # should allow the username, hostname, and port to be filled diff --git a/Lib/urllib/parse.py b/Lib/urllib/parse.py index 0ab2023843f..35cca410654 100644 --- a/Lib/urllib/parse.py +++ b/Lib/urllib/parse.py @@ -481,7 +481,7 @@ def urlsplit(url, scheme='', allow_fragments=True): clear_cache() netloc = query = fragment = '' i = url.find(':') - if i > 0: + if i > 0 and url[0].isascii() and url[0].isalpha(): for c in url[:i]: if c not in scheme_chars: break diff --git a/Misc/NEWS.d/next/Library/2022-11-12-15-45-51.gh-issue-99418.FxfAXS.rst b/Misc/NEWS.d/next/Library/2022-11-12-15-45-51.gh-issue-99418.FxfAXS.rst new file mode 100644 index 00000000000..0a06e7c5c6a --- /dev/null +++ b/Misc/NEWS.d/next/Library/2022-11-12-15-45-51.gh-issue-99418.FxfAXS.rst @@ -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. |