def test_default_ports(self):
for i, o in [
('http://*****:*****@www.example.com:80/index.html',
'http://*****:*****@www.example.com/index.html'),
('http://*****:*****@www.example.com:8080/index.html',
'http://*****:*****@www.example.com:8080/index.html'),
('http://*****:*****@www.example.com:443/index.html',
'http://*****:*****@www.example.com:443/index.html'),
('https://*****:*****@www.example.com:443/index.html',
'https://*****:*****@www.example.com/index.html'),
('https://*****:*****@www.example.com:442/index.html',
'https://*****:*****@www.example.com:442/index.html'),
('https://*****:*****@www.example.com:80/index.html',
'https://*****:*****@www.example.com:80/index.html'),
('ftp://*****:*****@www.example.com:21/file.txt',
'ftp://*****:*****@www.example.com/file.txt'),
('ftp://*****:*****@www.example.com:221/file.txt',
'ftp://*****:*****@www.example.com:221/file.txt'),
]:
self.assertEqual(strip_url(i, strip_default_port=True, strip_credentials=False), o)
def test_default_ports_creds_off(self):
for i, o in [
('http://*****:*****@www.example.com:80/index.html?somekey=somevalue#section',
'http://www.example.com/index.html?somekey=somevalue'),
('http://*****:*****@www.example.com:8080/index.html#section',
'http://www.example.com:8080/index.html'),
('http://*****:*****@www.example.com:443/index.html?somekey=somevalue&someotherkey=sov#section',
'http://www.example.com:443/index.html?somekey=somevalue&someotherkey=sov'),
('https://*****:*****@www.example.com:443/index.html',
'https://www.example.com/index.html'),
('https://*****:*****@www.example.com:442/index.html',
'https://www.example.com:442/index.html'),
('https://*****:*****@www.example.com:80/index.html',
'https://www.example.com:80/index.html'),
('ftp://*****:*****@www.example.com:21/file.txt',
'ftp://www.example.com/file.txt'),
('ftp://*****:*****@www.example.com:221/file.txt',
'ftp://www.example.com:221/file.txt'),
]:
self.assertEqual(strip_url(i), o)
def test_default_ports(self):
for i, o in [
('http://*****:*****@www.example.com:80/index.html',
'http://*****:*****@www.example.com/index.html'),
('http://*****:*****@www.example.com:8080/index.html',
'http://*****:*****@www.example.com:8080/index.html'),
('http://*****:*****@www.example.com:443/index.html',
'http://*****:*****@www.example.com:443/index.html'),
('https://*****:*****@www.example.com:443/index.html',
'https://*****:*****@www.example.com/index.html'),
('https://*****:*****@www.example.com:442/index.html',
'https://*****:*****@www.example.com:442/index.html'),
('https://*****:*****@www.example.com:80/index.html',
'https://*****:*****@www.example.com:80/index.html'),
('ftp://*****:*****@www.example.com:21/file.txt',
'ftp://*****:*****@www.example.com/file.txt'),
('ftp://*****:*****@www.example.com:221/file.txt',
'ftp://*****:*****@www.example.com:221/file.txt'),
]:
self.assertEqual(strip_url(i, strip_default_port=True, strip_credentials=False), o)
def test_default_ports_keep(self):
for i, o in [
('http://*****:*****@www.example.com:80/index.html?somekey=somevalue&someotherkey=sov#section',
'http://*****:*****@www.example.com:80/index.html?somekey=somevalue&someotherkey=sov'),
('http://*****:*****@www.example.com:8080/index.html?somekey=somevalue&someotherkey=sov#section',
'http://*****:*****@www.example.com:8080/index.html?somekey=somevalue&someotherkey=sov'),
('http://*****:*****@www.example.com:443/index.html',
'http://*****:*****@www.example.com:443/index.html'),
('https://*****:*****@www.example.com:443/index.html',
'https://*****:*****@www.example.com:443/index.html'),
('https://*****:*****@www.example.com:442/index.html',
'https://*****:*****@www.example.com:442/index.html'),
('https://*****:*****@www.example.com:80/index.html',
'https://*****:*****@www.example.com:80/index.html'),
('ftp://*****:*****@www.example.com:21/file.txt',
'ftp://*****:*****@www.example.com:21/file.txt'),
('ftp://*****:*****@www.example.com:221/file.txt',
'ftp://*****:*****@www.example.com:221/file.txt'),
]:
self.assertEqual(strip_url(i, strip_default_port=False, strip_credentials=False), o)
def test_default_ports_keep(self):
for i, o in [
('http://*****:*****@www.example.com:80/index.html?somekey=somevalue&someotherkey=sov#section',
'http://*****:*****@www.example.com:80/index.html?somekey=somevalue&someotherkey=sov'),
('http://*****:*****@www.example.com:8080/index.html?somekey=somevalue&someotherkey=sov#section',
'http://*****:*****@www.example.com:8080/index.html?somekey=somevalue&someotherkey=sov'),
('http://*****:*****@www.example.com:443/index.html',
'http://*****:*****@www.example.com:443/index.html'),
('https://*****:*****@www.example.com:443/index.html',
'https://*****:*****@www.example.com:443/index.html'),
('https://*****:*****@www.example.com:442/index.html',
'https://*****:*****@www.example.com:442/index.html'),
('https://*****:*****@www.example.com:80/index.html',
'https://*****:*****@www.example.com:80/index.html'),
('ftp://*****:*****@www.example.com:21/file.txt',
'ftp://*****:*****@www.example.com:21/file.txt'),
('ftp://*****:*****@www.example.com:221/file.txt',
'ftp://*****:*****@www.example.com:221/file.txt'),
]:
self.assertEqual(strip_url(i, strip_default_port=False, strip_credentials=False), o)
def test_default_ports_creds_off(self):
for i, o in [
('http://*****:*****@www.example.com:80/index.html?somekey=somevalue#section',
'http://www.example.com/index.html?somekey=somevalue'),
('http://*****:*****@www.example.com:8080/index.html#section',
'http://www.example.com:8080/index.html'),
('http://*****:*****@www.example.com:443/index.html?somekey=somevalue&someotherkey=sov#section',
'http://www.example.com:443/index.html?somekey=somevalue&someotherkey=sov'),
('https://*****:*****@www.example.com:443/index.html',
'https://www.example.com/index.html'),
('https://*****:*****@www.example.com:442/index.html',
'https://www.example.com:442/index.html'),
('https://*****:*****@www.example.com:80/index.html',
'https://www.example.com:80/index.html'),
('ftp://*****:*****@www.example.com:21/file.txt',
'ftp://www.example.com/file.txt'),
('ftp://*****:*****@www.example.com:221/file.txt',
'ftp://www.example.com:221/file.txt'),
]:
self.assertEqual(strip_url(i), o)
def test_path(self):
for input_url, origin, output_url in [
('http://www.example.com/', False, 'http://www.example.com/'),
('http://www.example.com', False, 'http://www.example.com'),
('http://www.example.com', True, 'http://www.example.com/'),
]:
self.assertEqual(strip_url(input_url, origin_only=origin),
output_url)
def test_credentials(self):
for i, o in [
('http://[email protected]/index.html?somekey=somevalue#section',
'http://www.example.com/index.html?somekey=somevalue'),
('https://username:@www.example.com/index.html?somekey=somevalue#section',
'https://www.example.com/index.html?somekey=somevalue'),
('ftp://*****:*****@www.example.com/index.html?somekey=somevalue#section',
'ftp://www.example.com/index.html?somekey=somevalue'),
]:
self.assertEqual(strip_url(i, strip_credentials=True), o)
def test_origin_only(self):
for i, o in [
('http://*****:*****@www.example.com/index.html',
'http://www.example.com/'),
('http://*****:*****@www.example.com:80/foo/bar?query=value#somefrag',
'http://www.example.com/'),
('http://*****:*****@www.example.com:8008/foo/bar?query=value#somefrag',
'http://www.example.com:8008/'),
('https://*****:*****@www.example.com:443/index.html',
'https://www.example.com/'),
]:
self.assertEqual(strip_url(i, origin_only=True), o)
def test_credentials(self):
for i, o in [
('http://[email protected]/index.html?somekey=somevalue#section',
'http://www.example.com/index.html?somekey=somevalue'),
('https://username:@www.example.com/index.html?somekey=somevalue#section',
'https://www.example.com/index.html?somekey=somevalue'),
('ftp://*****:*****@www.example.com/index.html?somekey=somevalue#section',
'ftp://www.example.com/index.html?somekey=somevalue'),
]:
self.assertEqual(strip_url(i, strip_credentials=True), o)
def test_origin_only(self):
for i, o in [
('http://*****:*****@www.example.com/index.html',
'http://www.example.com/'),
('http://*****:*****@www.example.com:80/foo/bar?query=value#somefrag',
'http://www.example.com/'),
('http://*****:*****@www.example.com:8008/foo/bar?query=value#somefrag',
'http://www.example.com:8008/'),
('https://*****:*****@www.example.com:443/index.html',
'https://www.example.com/'),
]:
self.assertEqual(strip_url(i, origin_only=True), o)
def test_path(self):
for input_url, origin, output_url in [
('http://www.example.com/',
False,
'http://www.example.com/'),
('http://www.example.com',
False,
'http://www.example.com'),
('http://www.example.com',
True,
'http://www.example.com/'),
]:
self.assertEqual(strip_url(input_url, origin_only=origin), output_url)
def test_credentials_encoded_delims(self):
for i, o in [
# user: "******"
# password: none
('http://username%[email protected]/index.html?somekey=somevalue#section',
'http://www.example.com/index.html?somekey=somevalue'),
# user: "******"
# password: ""
('https://username%3Apass:@www.example.com/index.html?somekey=somevalue#section',
'https://www.example.com/index.html?somekey=somevalue'),
# user: "******"
# password: "******"
('ftp://*****:*****@www.example.com/index.html?somekey=somevalue#section',
'ftp://www.example.com/index.html?somekey=somevalue'),
]:
self.assertEqual(strip_url(i, strip_credentials=True), o)
def test_credentials_encoded_delims(self):
for i, o in [
# user: "******"
# password: none
('http://username%[email protected]/index.html?somekey=somevalue#section',
'http://www.example.com/index.html?somekey=somevalue'),
# user: "******"
# password: ""
('https://username%3Apass:@www.example.com/index.html?somekey=somevalue#section',
'https://www.example.com/index.html?somekey=somevalue'),
# user: "******"
# password: "******"
('ftp://*****:*****@www.example.com/index.html?somekey=somevalue#section',
'ftp://www.example.com/index.html?somekey=somevalue'),
]:
self.assertEqual(strip_url(i, strip_credentials=True), o)
def strip_url(self, url, origin_only=False):
"""
https://www.w3.org/TR/referrer-policy/#strip-url
If url is null, return no referrer.
If url's scheme is a local scheme, then return no referrer.
Set url's username to the empty string.
Set url's password to null.
Set url's fragment to null.
If the origin-only flag is true, then:
Set url's path to null.
Set url's query to null.
Return url.
"""
if not url:
return None
return strip_url(url,
strip_credentials=True,
strip_fragment=True,
strip_default_port=True,
origin_only=origin_only)
def strip_url(self, url, origin_only=False):
"""
https://www.w3.org/TR/referrer-policy/#strip-url
If url is null, return no referrer.
If url's scheme is a local scheme, then return no referrer.
Set url's username to the empty string.
Set url's password to null.
Set url's fragment to null.
If the origin-only flag is true, then:
Set url's path to null.
Set url's query to null.
Return url.
"""
if not url:
return None
return strip_url(url,
strip_credentials=True,
strip_fragment=True,
strip_default_port=True,
origin_only=origin_only)
def test_noop(self):
self.assertEqual(strip_url(
'http://www.example.com/index.html'),
'http://www.example.com/index.html')
def test_fragments(self):
self.assertEqual(strip_url(
'http://www.example.com/index.html?somekey=somevalue#section', strip_fragment=False),
'http://www.example.com/index.html?somekey=somevalue#section')
def test_noop_query_string(self):
self.assertEqual(strip_url(
'http://www.example.com/index.html?somekey=somevalue'),
'http://www.example.com/index.html?somekey=somevalue')
def test_noop(self):
self.assertEqual(strip_url(
'http://www.example.com/index.html'),
'http://www.example.com/index.html')
def test_noop_query_string(self):
self.assertEqual(strip_url(
'http://www.example.com/index.html?somekey=somevalue'),
'http://www.example.com/index.html?somekey=somevalue')
def test_fragments(self):
self.assertEqual(strip_url(
'http://www.example.com/index.html?somekey=somevalue#section', strip_fragment=False),
'http://www.example.com/index.html?somekey=somevalue#section')
