@@ -668,6 +668,24 @@ def test_attributes_bad_port(self):

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

@@ -460,7 +460,7 @@ def urlsplit(url, scheme='', allow_fragments=True):

allow_fragments = bool(allow_fragments)

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

@@ -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.