def _parseURL(url):
try:
url = urinorm.urinorm(url)
except ValueError:
return None
proto, netloc, path, params, query, frag = urlparse(url)
if not path:
# Python <2.4 does not parse URLs with no path properly
if not query and '?' in netloc:
netloc, query = netloc.split('?', 1)
path = '/'
path = urlunparse(('', '', path, params, query, frag))
if ':' in netloc:
try:
host, port = netloc.split(':')
except ValueError:
return None
if not re.match(r'\d+$', port):
return None
else:
host = netloc
port = ''
host = host.lower()
if not host_segment_re.match(host):
return None
return proto, host, port, path
def normalizeURL(url):
"""Normalize a URL, converting normalization failures to
DiscoveryFailure"""
try:
normalized = urinorm.urinorm(url)
except ValueError, why:
raise DiscoveryFailure("Normalizing identifier: %s" % (why[0],), None)
def normalizeURL(url):
"""Normalize a URL, converting normalization failures to
DiscoveryFailure"""
try:
normalized = urinorm.urinorm(url)
except ValueError, why:
raise DiscoveryFailure('Normalizing identifier: %s' % (why[0], ), None)
def _parseURL(url):
try:
url = urinorm.urinorm(url)
except ValueError:
return None
proto, netloc, path, params, query, frag = urlparse(url)
if not path:
# Python <2.4 does not parse URLs with no path properly
if not query and '?' in netloc:
netloc, query = netloc.split('?', 1)
path = '/'
path = urlunparse(('', '', path, params, query, frag))
if ':' in netloc:
try:
host, port = netloc.split(':')
except ValueError:
return None
if not re.match(r'\d+$', port):
return None
else:
host = netloc
port = ''
host = host.lower()
if not host_segment_re.match(host):
return None
return proto, host, port, path
def runTest(self):
try:
actual = urinorm.urinorm(self.case)
except ValueError, why:
self.assertEqual(self.expected, 'fail', why)
