def test_urljoin_no_canonicalize(self):
bases = [
'http://example.com',
'http://example.com/',
'http://example.com/white space',
'http://example.com/white space/foo bar/',
'file://example.com/white space',
'file://example.com/'
]
urls = [
'',
'foo/bar',
'white space',
'white space/foo bar',
'http://example2.com/',
'http://example2.com',
'http://example2.com/white space',
'file://a/b/c/d'
]
for base in bases:
for url in urls:
self.assertEqual(scurl.urljoin(base, url),
stdlib.urljoin(base, url))
self.assertEqual(scurl.urljoin(url, base),
stdlib.urljoin(url, base))
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_check_invalid_urls(self):
invalid_urls = [
'foo//example.com/', 'bar//example.com/', 'foobar//example.com/',
'foobar', '#'
]
invalid_urls_2 = ['foobar', 'foo/bar', 'foo/bar/../2']
for invalid_url in invalid_urls:
for invalid_url_2 in invalid_urls_2:
self.assertEqual(scurl.urljoin(invalid_url, invalid_url_2),
stdlib.urljoin(invalid_url, invalid_url_2))
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 checkJoin(self, base, relurl, expected):
self.assertEqual(scurl.urljoin(base, relurl), expected,
(base, relurl, expected))
def checkJoin(self, base, relurl, expected):
str_components = (base, relurl, expected)
self.assertEqual(scurl.urljoin(base, relurl), expected)
bytes_components = baseb, relurlb, expectedb = [
x.encode('ascii') for x in str_components]
self.assertEqual(scurl.urljoin(baseb, relurlb), expectedb)