Skip to content

[3.3] bpo-30500: urllib: Simplify splithost by calling into urlparse. (#1849) #2292

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
ned-deily merged 2 commits into from
Jul 26, 2017
Merged

[3.3] bpo-30500: urllib: Simplify splithost by calling into urlparse. (#1849) #2292

Changes from 1 commit
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
45ac215
Update test_urlparse from Python 3.4
vstinner Jul 25, 2017
eebcbd8
bpo-30500: urllib: Simplify splithost by calling into urlparse. (#184…
vstinner Jul 12, 2017
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
Next Next commit
Update test_urlparse from Python 3.4 
Keep test_main() and remove subTest() (introduced in Python 3.4).
  • Loading branch information
@vstinner
vstinner committed Jul 25, 2017
commit 45ac2150a0993603023eb854b6c81a937fa870b6
220 changes: 173 additions & 47 deletions Lib/test/test_urlparse.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -664,6 +664,45 @@ def test_anyscheme(self):
self.assertEqual(urllib.parse.urlparse(b"x-newscheme://foo.com/stuff?query"),
(b'x-newscheme', b'foo.com', b'/stuff', b'', b'query', b''))

def test_default_scheme(self):
# Exercise the scheme parameter of urlparse() and urlsplit()
for func in (urllib.parse.urlparse, urllib.parse.urlsplit):
result = func("http://example.net/", "ftp")
self.assertEqual(result.scheme, "http")
result = func(b"http://example.net/", b"ftp")
self.assertEqual(result.scheme, b"http")
self.assertEqual(func("path", "ftp").scheme, "ftp")
self.assertEqual(func("path", scheme="ftp").scheme, "ftp")
self.assertEqual(func(b"path", scheme=b"ftp").scheme, b"ftp")
self.assertEqual(func("path").scheme, "")
self.assertEqual(func(b"path").scheme, b"")
self.assertEqual(func(b"path", "").scheme, b"")

def test_parse_fragments(self):
# Exercise the allow_fragments parameter of urlparse() and urlsplit()
tests = (
("http:#frag", "path"),
("//example.net#frag", "path"),
("index.html#frag", "path"),
(";a=b#frag", "params"),
("?a=b#frag", "query"),
("#frag", "path"),
)
for url, attr in tests:
for func in (urllib.parse.urlparse, urllib.parse.urlsplit):
if attr == "params" and func is urllib.parse.urlsplit:
attr = "path"
result = func(url, allow_fragments=False)
self.assertEqual(result.fragment, "")
self.assertTrue(getattr(result, attr).endswith("#frag"))
self.assertEqual(func(url, "", False).fragment, "")

result = func(url, allow_fragments=True)
self.assertEqual(result.fragment, "frag")
self.assertFalse(getattr(result, attr).endswith("frag"))
self.assertEqual(func(url, "", True).fragment, "frag")
self.assertEqual(func(url).fragment, "frag")

def test_mixed_types_rejected(self):
# Several functions that process either strings or ASCII encoded bytes
# accept multiple arguments. Check they reject mixed type input
Expand Down Expand Up @@ -749,52 +788,6 @@ def test_parse_qsl_encoding(self):
errors="ignore")
self.assertEqual(result, [('key', '\u0141-')])

def test_splitport(self):
splitport = urllib.parse.splitport
self.assertEqual(splitport('parrot:88'), ('parrot', '88'))
self.assertEqual(splitport('parrot'), ('parrot', None))
self.assertEqual(splitport('parrot:'), ('parrot', None))
self.assertEqual(splitport('127.0.0.1'), ('127.0.0.1', None))
self.assertEqual(splitport('parrot:cheese'), ('parrot:cheese', None))

def test_splitnport(self):
splitnport = urllib.parse.splitnport
self.assertEqual(splitnport('parrot:88'), ('parrot', 88))
self.assertEqual(splitnport('parrot'), ('parrot', -1))
self.assertEqual(splitnport('parrot', 55), ('parrot', 55))
self.assertEqual(splitnport('parrot:'), ('parrot', -1))
self.assertEqual(splitnport('parrot:', 55), ('parrot', 55))
self.assertEqual(splitnport('127.0.0.1'), ('127.0.0.1', -1))
self.assertEqual(splitnport('127.0.0.1', 55), ('127.0.0.1', 55))
self.assertEqual(splitnport('parrot:cheese'), ('parrot', None))
self.assertEqual(splitnport('parrot:cheese', 55), ('parrot', None))

def test_splitquery(self):
# Normal cases are exercised by other tests; ensure that we also
# catch cases with no port specified (testcase ensuring coverage)
result = urllib.parse.splitquery('http://python.org/fake?foo=bar')
self.assertEqual(result, ('http://python.org/fake', 'foo=bar'))
result = urllib.parse.splitquery('http://python.org/fake?foo=bar?')
self.assertEqual(result, ('http://python.org/fake?foo=bar', ''))
result = urllib.parse.splitquery('http://python.org/fake')
self.assertEqual(result, ('http://python.org/fake', None))

def test_splitvalue(self):
# Normal cases are exercised by other tests; test pathological cases
# with no key/value pairs. (testcase ensuring coverage)
result = urllib.parse.splitvalue('foo=bar')
self.assertEqual(result, ('foo', 'bar'))
result = urllib.parse.splitvalue('foo=')
self.assertEqual(result, ('foo', ''))
result = urllib.parse.splitvalue('foobar')
self.assertEqual(result, ('foobar', None))

def test_to_bytes(self):
result = urllib.parse.to_bytes('http://www.python.org')
self.assertEqual(result, 'http://www.python.org')
self.assertRaises(UnicodeError, urllib.parse.to_bytes,
'http://www.python.org/medi\u00e6val')

def test_urlencode_sequences(self):
# Other tests incidentally urlencode things; test non-covered cases:
# Sequence and object values.
Expand Down Expand Up @@ -863,9 +856,142 @@ def test_telurl_params(self):
self.assertEqual(p1.path, '863-1234')
self.assertEqual(p1.params, 'phone-context=+1-914-555')

def test_Quoter_repr(self):
quoter = urllib.parse.Quoter(urllib.parse._ALWAYS_SAFE)
self.assertIn('Quoter', repr(quoter))


class Utility_Tests(unittest.TestCase):
"""Testcase to test the various utility functions in the urllib."""
# In Python 2 this test class was in test_urllib.

def test_splittype(self):
splittype = urllib.parse.splittype
self.assertEqual(splittype('type:opaquestring'), ('type', 'opaquestring'))
self.assertEqual(splittype('opaquestring'), (None, 'opaquestring'))
self.assertEqual(splittype(':opaquestring'), (None, ':opaquestring'))
self.assertEqual(splittype('type:'), ('type', ''))
self.assertEqual(splittype('type:opaque:string'), ('type', 'opaque:string'))

def test_splithost(self):
splithost = urllib.parse.splithost
self.assertEqual(splithost('//www.example.org:80/foo/bar/baz.html'),
('www.example.org:80', '/foo/bar/baz.html'))
self.assertEqual(splithost('//www.example.org:80'),
('www.example.org:80', ''))
self.assertEqual(splithost('/foo/bar/baz.html'),
(None, '/foo/bar/baz.html'))

def test_splituser(self):
splituser = urllib.parse.splituser
self.assertEqual(splituser('User:Pass@www.python.org:080'),
('User:Pass', 'www.python.org:080'))
self.assertEqual(splituser('@www.python.org:080'),
('', 'www.python.org:080'))
self.assertEqual(splituser('www.python.org:080'),
(None, 'www.python.org:080'))
self.assertEqual(splituser('User:Pass@'),
('User:Pass', ''))
self.assertEqual(splituser('User@example.com:Pass@www.python.org:080'),
('User@example.com:Pass', 'www.python.org:080'))

def test_splitpasswd(self):
# Some of the password examples are not sensible, but it is added to
# confirming to RFC2617 and addressing issue4675.
splitpasswd = urllib.parse.splitpasswd
self.assertEqual(splitpasswd('user:ab'), ('user', 'ab'))
self.assertEqual(splitpasswd('user:a\nb'), ('user', 'a\nb'))
self.assertEqual(splitpasswd('user:a\tb'), ('user', 'a\tb'))
self.assertEqual(splitpasswd('user:a\rb'), ('user', 'a\rb'))
self.assertEqual(splitpasswd('user:a\fb'), ('user', 'a\fb'))
self.assertEqual(splitpasswd('user:a\vb'), ('user', 'a\vb'))
self.assertEqual(splitpasswd('user:a:b'), ('user', 'a:b'))
self.assertEqual(splitpasswd('user:a b'), ('user', 'a b'))
self.assertEqual(splitpasswd('user 2:ab'), ('user 2', 'ab'))
self.assertEqual(splitpasswd('user+1:a+b'), ('user+1', 'a+b'))
self.assertEqual(splitpasswd('user:'), ('user', ''))
self.assertEqual(splitpasswd('user'), ('user', None))
self.assertEqual(splitpasswd(':ab'), ('', 'ab'))

def test_splitport(self):
splitport = urllib.parse.splitport
self.assertEqual(splitport('parrot:88'), ('parrot', '88'))
self.assertEqual(splitport('parrot'), ('parrot', None))
self.assertEqual(splitport('parrot:'), ('parrot', None))
self.assertEqual(splitport('127.0.0.1'), ('127.0.0.1', None))
self.assertEqual(splitport('parrot:cheese'), ('parrot:cheese', None))
self.assertEqual(splitport('[::1]:88'), ('[::1]', '88'))
self.assertEqual(splitport('[::1]'), ('[::1]', None))
self.assertEqual(splitport(':88'), ('', '88'))

def test_splitnport(self):
splitnport = urllib.parse.splitnport
self.assertEqual(splitnport('parrot:88'), ('parrot', 88))
self.assertEqual(splitnport('parrot'), ('parrot', -1))
self.assertEqual(splitnport('parrot', 55), ('parrot', 55))
self.assertEqual(splitnport('parrot:'), ('parrot', -1))
self.assertEqual(splitnport('parrot:', 55), ('parrot', 55))
self.assertEqual(splitnport('127.0.0.1'), ('127.0.0.1', -1))
self.assertEqual(splitnport('127.0.0.1', 55), ('127.0.0.1', 55))
self.assertEqual(splitnport('parrot:cheese'), ('parrot', None))
self.assertEqual(splitnport('parrot:cheese', 55), ('parrot', None))

def test_splitquery(self):
# Normal cases are exercised by other tests; ensure that we also
# catch cases with no port specified (testcase ensuring coverage)
splitquery = urllib.parse.splitquery
self.assertEqual(splitquery('http://python.org/fake?foo=bar'),
('http://python.org/fake', 'foo=bar'))
self.assertEqual(splitquery('http://python.org/fake?foo=bar?'),
('http://python.org/fake?foo=bar', ''))
self.assertEqual(splitquery('http://python.org/fake'),
('http://python.org/fake', None))
self.assertEqual(splitquery('?foo=bar'), ('', 'foo=bar'))

def test_splittag(self):
splittag = urllib.parse.splittag
self.assertEqual(splittag('http://example.com?foo=bar#baz'),
('http://example.com?foo=bar', 'baz'))
self.assertEqual(splittag('http://example.com?foo=bar#'),
('http://example.com?foo=bar', ''))
self.assertEqual(splittag('#baz'), ('', 'baz'))
self.assertEqual(splittag('http://example.com?foo=bar'),
('http://example.com?foo=bar', None))
self.assertEqual(splittag('http://example.com?foo=bar#baz#boo'),
('http://example.com?foo=bar#baz', 'boo'))

def test_splitattr(self):
splitattr = urllib.parse.splitattr
self.assertEqual(splitattr('/path;attr1=value1;attr2=value2'),
('/path', ['attr1=value1', 'attr2=value2']))
self.assertEqual(splitattr('/path;'), ('/path', ['']))
self.assertEqual(splitattr(';attr1=value1;attr2=value2'),
('', ['attr1=value1', 'attr2=value2']))
self.assertEqual(splitattr('/path'), ('/path', []))

def test_splitvalue(self):
# Normal cases are exercised by other tests; test pathological cases
# with no key/value pairs. (testcase ensuring coverage)
splitvalue = urllib.parse.splitvalue
self.assertEqual(splitvalue('foo=bar'), ('foo', 'bar'))
self.assertEqual(splitvalue('foo='), ('foo', ''))
self.assertEqual(splitvalue('=bar'), ('', 'bar'))
self.assertEqual(splitvalue('foobar'), ('foobar', None))
self.assertEqual(splitvalue('foo=bar=baz'), ('foo', 'bar=baz'))

def test_to_bytes(self):
result = urllib.parse.to_bytes('http://www.python.org')
self.assertEqual(result, 'http://www.python.org')
self.assertRaises(UnicodeError, urllib.parse.to_bytes,
'http://www.python.org/medi\u00e6val')

def test_unwrap(self):
url = urllib.parse.unwrap('<URL:type://host/path>')
self.assertEqual(url, 'type://host/path')


def test_main():
support.run_unittest(UrlParseTestCase)
support.run_unittest(UrlParseTestCase, Utility_Tests)

if __name__ == "__main__":
test_main()