def test_urlsplit_scoped_IPv6(self):
p = scurl.urlsplit('http://[FE80::822a:a8ff:fe49:470c%tESt]:1234')
self.assertEqual(p.hostname, "fe80::822a:a8ff:fe49:470c%tESt")
self.assertEqual(p.netloc, '[FE80::822a:a8ff:fe49:470c%tESt]:1234')
p = scurl.urlsplit(b'http://[FE80::822a:a8ff:fe49:470c%tESt]:1234')
self.assertEqual(p.hostname, b"fe80::822a:a8ff:fe49:470c%tESt")
self.assertEqual(p.netloc, b'[FE80::822a:a8ff:fe49:470c%tESt]:1234')
def test_urlsplit_attributes(self):
url = "HTTP://WWW.PYTHON.ORG/doc/#frag"
p = scurl.urlsplit(url)
self.assertEqual(p.scheme, "http")
self.assertEqual(p.netloc, "WWW.PYTHON.ORG")
self.assertEqual(p.path, "/doc/")
self.assertEqual(p.query, "")
self.assertEqual(p.fragment, "frag")
self.assertEqual(p.username, None)
self.assertEqual(p.password, None)
self.assertEqual(p.hostname, "www.python.org")
self.assertEqual(p.port, None)
# geturl() won't return exactly the original URL in this case
# since the scheme is always case-normalized
#self.assertEqual(p.geturl(), url)
url = "http://*****:*****@www.python.org:080/doc/?query=yes#frag"
p = scurl.urlsplit(url)
self.assertEqual(p.scheme, "http")
self.assertEqual(p.netloc, "User:[email protected]:080")
self.assertEqual(p.path, "/doc/")
self.assertEqual(p.query, "query=yes")
self.assertEqual(p.fragment, "frag")
self.assertEqual(p.username, "User")
self.assertEqual(p.password, "Pass")
self.assertEqual(p.hostname, "www.python.org")
self.assertEqual(p.port, 80)
self.assertEqual(p.geturl(), url)
# Addressing issue1698, which suggests Username can contain
# "@" characters. Though not RFC compliant, many ftp sites allow
# and request email addresses as usernames.
url = "http://[email protected]:[email protected]:080/doc/?query=yes#frag"
p = scurl.urlsplit(url)
self.assertEqual(p.scheme, "http")
self.assertEqual(p.netloc, "[email protected]:[email protected]:080")
self.assertEqual(p.path, "/doc/")
self.assertEqual(p.query, "query=yes")
self.assertEqual(p.fragment, "frag")
self.assertEqual(p.username, "*****@*****.**")
self.assertEqual(p.password, "Pass")
self.assertEqual(p.hostname, "www.python.org")
self.assertEqual(p.port, 80)
self.assertEqual(p.geturl(), url)
# Verify an illegal port of value greater than 65535 is set as None
# NOTE: this should raise the Value error since port is out of range (just like in py3)
# SCURL has changed this test case
url = "http://www.python.org:65536"
p = scurl.urlsplit(url)
with self.assertRaises(ValueError):
p.port
def checkRoundtrips(self, url, parsed, split):
result = scurl.urlparse(url)
self.assertEqual(result, parsed)
t = (result.scheme, result.netloc, result.path, result.params,
result.query, result.fragment)
self.assertEqual(t, parsed)
# put it back together and it should be the same
result2 = scurl.urlunparse(result)
self.assertEqual(result2, url)
self.assertEqual(result2, result.geturl())
# the result of geturl() is a fixpoint; we can always parse it
# again to get the same result:
result3 = scurl.urlparse(result.geturl())
self.assertEqual(result3.geturl(), result.geturl())
self.assertEqual(result3, result)
self.assertEqual(result3.scheme, result.scheme)
self.assertEqual(result3.netloc, result.netloc)
self.assertEqual(result3.path, result.path)
self.assertEqual(result3.params, result.params)
self.assertEqual(result3.query, result.query)
self.assertEqual(result3.fragment, result.fragment)
self.assertEqual(result3.username, result.username)
self.assertEqual(result3.password, result.password)
self.assertEqual(result3.hostname, result.hostname)
self.assertEqual(result3.port, result.port)
# check the roundtrip using urlsplit() as well
result = scurl.urlsplit(url)
self.assertEqual(result, split)
t = (result.scheme, result.netloc, result.path, result.query,
result.fragment)
self.assertEqual(t, split)
result2 = scurl.urlunsplit(result)
self.assertEqual(result2, url)
self.assertEqual(result2, result.geturl())
# check the fixpoint property of re-parsing the result of geturl()
result3 = scurl.urlsplit(result.geturl())
self.assertEqual(result3.geturl(), result.geturl())
self.assertEqual(result3, result)
self.assertEqual(result3.scheme, result.scheme)
self.assertEqual(result3.netloc, result.netloc)
self.assertEqual(result3.path, result.path)
self.assertEqual(result3.query, result.query)
self.assertEqual(result3.fragment, result.fragment)
self.assertEqual(result3.username, result.username)
self.assertEqual(result3.password, result.password)
self.assertEqual(result3.hostname, result.hostname)
self.assertEqual(result3.port, result.port)
def test_issue14072(self):
p1 = scurl.urlsplit('tel:+31-641044153')
self.assertEqual(p1.scheme, 'tel')
self.assertEqual(p1.path, '+31-641044153')
p2 = scurl.urlsplit('tel:+31641044153')
self.assertEqual(p2.scheme, 'tel')
self.assertEqual(p2.path, '+31641044153')
# assert the behavior for urlparse
p1 = scurl.urlparse('tel:+31-641044153')
self.assertEqual(p1.scheme, 'tel')
self.assertEqual(p1.path, '+31-641044153')
p2 = scurl.urlparse('tel:+31641044153')
self.assertEqual(p2.scheme, 'tel')
self.assertEqual(p2.path, '+31641044153')
def main():
parser = argparse.ArgumentParser(
description='Measure the time of urlsplit and urljoin')
parser.add_argument('--encode',
action='store_true',
help='encode the urls (default: False)')
args = parser.parse_args()
encode = args.encode
urlparse_time = 0
for i in range(5):
with open('benchmarks/urls/chromiumUrls.txt') as f:
for url in f:
if encode:
url = url.encode()
start = timer()
a = urlparse(url)
end = timer()
urlparse_time += end - start
print("the urlparse time is", urlparse_time / 5, "seconds")
urlsplit_time = 0
for i in range(5):
with open('benchmarks/urls/chromiumUrls.txt') as f:
for url in f:
if encode:
url = url.encode()
start = timer()
a = urlsplit(url)
end = timer()
urlsplit_time += end - start
print("the urlsplit time is", urlsplit_time / 5, "seconds")
urljoin_time = 0
for i in range(5):
with open('benchmarks/urls/chromiumUrls.txt') as f:
for url in f:
partial_url = "/asd"
if encode:
url = url.encode()
partial_url = partial_url.encode()
start = timer()
a = urljoin(url, partial_url)
end = timer()
urljoin_time += end - start
print("the urljoin time is", urljoin_time / 5, "seconds")
def test_attributes_bad_port(self):
"""Check handling of non-integer ports."""
p = scurl.urlsplit("http://www.example.net:foo")
self.assertEqual(p.netloc, "www.example.net:foo")
self.assertRaises(ValueError, lambda: p.port)
p = scurl.urlparse("http://www.example.net:foo")
self.assertEqual(p.netloc, "www.example.net:foo")
self.assertRaises(ValueError, lambda: p.port)
def test_port_casting_failure_message(self):
message = "Port could not be"
p1 = scurl.urlparse('http://Server=sde; Service=sde:oracle')
with self.assertRaisesRegex(ValueError, message):
p1.port
p2 = scurl.urlsplit('http://Server=sde; Service=sde:oracle')
with self.assertRaisesRegex(ValueError, message):
p2.port
def test_unparse_parse(self):
for u in [
'Python',
'./Python',
'x-newscheme://foo.com/stuff',
'x://y',
'x:/y',
'x:/',
'/',
]:
self.assertEqual(scurl.urlunsplit(scurl.urlsplit(u)), u)
self.assertEqual(scurl.urlunparse(scurl.urlparse(u)), u)
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
# in, but doesn't. Since it's a URI and doesn't use the
# scheme://netloc syntax, the netloc and related attributes
# should be left empty.
uri = "sip:[email protected];maddr=239.255.255.1;ttl=15"
p = scurl.urlsplit(uri)
self.assertEqual(p.netloc, "")
self.assertEqual(p.username, None)
self.assertEqual(p.password, None)
self.assertEqual(p.hostname, None)
self.assertEqual(p.port, None)
self.assertEqual(p.geturl(), uri)
p = scurl.urlparse(uri)
self.assertEqual(p.netloc, "")
self.assertEqual(p.username, None)
self.assertEqual(p.password, None)
self.assertEqual(p.hostname, None)
self.assertEqual(p.port, None)
self.assertEqual(p.geturl(), uri)
# You guessed it, repeating the test with bytes input
uri = b"sip:[email protected];maddr=239.255.255.1;ttl=15"
p = scurl.urlsplit(uri)
self.assertEqual(p.netloc, b"")
self.assertEqual(p.username, None)
self.assertEqual(p.password, None)
self.assertEqual(p.hostname, None)
self.assertEqual(p.port, None)
self.assertEqual(p.geturl(), uri)
p = scurl.urlparse(uri)
self.assertEqual(p.netloc, b"")
self.assertEqual(p.username, None)
self.assertEqual(p.password, None)
self.assertEqual(p.hostname, None)
self.assertEqual(p.port, None)
self.assertEqual(p.geturl(), uri)
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
with self.assertRaisesRegex(TypeError, "Cannot mix str"):
scurl.urlparse("www.python.org", b"http")
with self.assertRaisesRegex(TypeError, "Cannot mix str"):
scurl.urlparse(b"www.python.org", "http")
with self.assertRaisesRegex(TypeError, "Cannot mix str"):
scurl.urlsplit("www.python.org", b"http")
with self.assertRaisesRegex(TypeError, "Cannot mix str"):
scurl.urlsplit(b"www.python.org", "http")
with self.assertRaisesRegex(TypeError, "Cannot mix str"):
scurl.urlunparse(( b"http", "www.python.org","","","",""))
with self.assertRaisesRegex(TypeError, "Cannot mix str"):
scurl.urlunparse(("http", b"www.python.org","","","",""))
with self.assertRaisesRegex(TypeError, "Cannot mix str"):
scurl.urlunsplit((b"http", "www.python.org","","",""))
with self.assertRaisesRegex(TypeError, "Cannot mix str"):
scurl.urlunsplit(("http", b"www.python.org","","",""))
with self.assertRaisesRegex(TypeError, "Cannot mix str"):
scurl.urljoin("http://python.org", b"http://python.org")
with self.assertRaisesRegex(TypeError, "Cannot mix str"):
scurl.urljoin(b"http://python.org", "http://python.org")
def run_urlsplit(urls):
for url in urls:
a = scurl.urlsplit(url)
def test_urlsplit_attributes(self):
url = "HTTP://WWW.PYTHON.ORG/doc/#frag"
p = scurl.urlsplit(url)
self.assertEqual(p.scheme, "http")
self.assertEqual(p.netloc, "WWW.PYTHON.ORG")
self.assertEqual(p.path, "/doc/")
self.assertEqual(p.query, "")
self.assertEqual(p.fragment, "frag")
self.assertEqual(p.username, None)
self.assertEqual(p.password, None)
self.assertEqual(p.hostname, "www.python.org")
self.assertEqual(p.port, None)
# geturl() won't return exactly the original URL in this case
# since the scheme is always case-normalized
# We handle this by ignoring the first 4 characters of the URL
self.assertEqual(p.geturl()[4:], url[4:])
url = "http://*****:*****@www.python.org:080/doc/?query=yes#frag"
p = scurl.urlsplit(url)
self.assertEqual(p.scheme, "http")
self.assertEqual(p.netloc, "User:[email protected]:080")
self.assertEqual(p.path, "/doc/")
self.assertEqual(p.query, "query=yes")
self.assertEqual(p.fragment, "frag")
self.assertEqual(p.username, "User")
self.assertEqual(p.password, "Pass")
self.assertEqual(p.hostname, "www.python.org")
self.assertEqual(p.port, 80)
self.assertEqual(p.geturl(), url)
# Addressing issue1698, which suggests Username can contain
# "@" characters. Though not RFC compliant, many ftp sites allow
# and request email addresses as usernames.
url = "http://[email protected]:[email protected]:080/doc/?query=yes#frag"
p = scurl.urlsplit(url)
self.assertEqual(p.scheme, "http")
self.assertEqual(p.netloc, "[email protected]:[email protected]:080")
self.assertEqual(p.path, "/doc/")
self.assertEqual(p.query, "query=yes")
self.assertEqual(p.fragment, "frag")
self.assertEqual(p.username, "*****@*****.**")
self.assertEqual(p.password, "Pass")
self.assertEqual(p.hostname, "www.python.org")
self.assertEqual(p.port, 80)
self.assertEqual(p.geturl(), url)
# And check them all again, only with bytes this time
url = b"HTTP://WWW.PYTHON.ORG/doc/#frag"
p = scurl.urlsplit(url)
self.assertEqual(p.scheme, b"http")
self.assertEqual(p.netloc, b"WWW.PYTHON.ORG")
self.assertEqual(p.path, b"/doc/")
self.assertEqual(p.query, b"")
self.assertEqual(p.fragment, b"frag")
self.assertEqual(p.username, None)
self.assertEqual(p.password, None)
self.assertEqual(p.hostname, b"www.python.org")
self.assertEqual(p.port, None)
self.assertEqual(p.geturl()[4:], url[4:])
url = b"http://*****:*****@www.python.org:080/doc/?query=yes#frag"
p = scurl.urlsplit(url)
self.assertEqual(p.scheme, b"http")
self.assertEqual(p.netloc, b"User:[email protected]:080")
self.assertEqual(p.path, b"/doc/")
self.assertEqual(p.query, b"query=yes")
self.assertEqual(p.fragment, b"frag")
self.assertEqual(p.username, b"User")
self.assertEqual(p.password, b"Pass")
self.assertEqual(p.hostname, b"www.python.org")
self.assertEqual(p.port, 80)
self.assertEqual(p.geturl(), url)
url = b"http://[email protected]:[email protected]:080/doc/?query=yes#frag"
p = scurl.urlsplit(url)
self.assertEqual(p.scheme, b"http")
self.assertEqual(p.netloc, b"[email protected]:[email protected]:080")
self.assertEqual(p.path, b"/doc/")
self.assertEqual(p.query, b"query=yes")
self.assertEqual(p.fragment, b"frag")
self.assertEqual(p.username, b"*****@*****.**")
self.assertEqual(p.password, b"Pass")
self.assertEqual(p.hostname, b"www.python.org")
self.assertEqual(p.port, 80)
self.assertEqual(p.geturl(), url)
# Verify an illegal port raises ValueError
url = b"HTTP://WWW.PYTHON.ORG:65536/doc/#frag"
p = scurl.urlsplit(url)
with self.assertRaisesRegex(ValueError, "out of range"):
p.port
def test_unparse_parse(self):
str_cases = ['Python', './Python','x-newscheme://foo.com/stuff','x://y','x:/y','x:/','/',]
bytes_cases = [x.encode('ascii') for x in str_cases]
for u in str_cases + bytes_cases:
self.assertEqual(scurl.urlunsplit(scurl.urlsplit(u)), u)
self.assertEqual(scurl.urlunparse(scurl.urlparse(u)), u)