def test_iri_support(self):
self.assertEqual(
urls.uri_to_iri('http://xn--n3h.net/'),
'http://\u2603.net/'
)
self.assertEqual(
urls.uri_to_iri(
'http://%C3%BCser:p%C3%[email protected]/p%C3%A5th'
),
'http://\xfcser:p\xe4ssword@\u2603.net/p\xe5th'
)
self.assertEqual(
urls.iri_to_uri('http://☃.net/'),
'http://xn--n3h.net/'
)
self.assertEqual(
urls.iri_to_uri('http://üser:pässword@☃.net/påth'),
'http://%C3%BCser:p%C3%[email protected]/p%C3%A5th'
)
self.assertEqual(
urls.uri_to_iri('http://test.com/%3Fmeh?foo=%26%2F'),
'http://test.com/%3Fmeh?foo=%26%2F'
)
self.assertEqual(urls.iri_to_uri('/foo'), '/foo')
self.assertEqual(
urls.iri_to_uri('http://föö.com:8080/bam/baz'),
'http://xn--f-1gaa.com:8080/bam/baz'
)
def test_iri_support(self):
self.assertEqual(
urls.uri_to_iri('http://xn--n3h.net/'),
'http://\u2603.net/'
)
self.assertEqual(
urls.uri_to_iri(
'http://%C3%BCser:p%C3%[email protected]/p%C3%A5th'
),
'http://\xfcser:p\xe4ssword@\u2603.net/p\xe5th'
)
self.assertEqual(
urls.iri_to_uri('http://☃.net/'),
'http://xn--n3h.net/'
)
self.assertEqual(
urls.iri_to_uri('http://üser:pässword@☃.net/påth'),
'http://%C3%BCser:p%C3%[email protected]/p%C3%A5th'
)
self.assertEqual(
urls.uri_to_iri('http://test.com/%3Fmeh?foo=%26%2F'),
'http://test.com/%3Fmeh?foo=%26%2F'
)
self.assertEqual(urls.iri_to_uri('/foo'), '/foo')
self.assertEqual(
urls.iri_to_uri('http://föö.com:8080/bam/baz'),
'http://xn--f-1gaa.com:8080/bam/baz'
)
def get_current_url(
environ, root_only=False, strip_querystring=False,
host_only=False, trusted_hosts=None,
):
"""A handy helper function that recreates the full URL as IRI for the
current request or parts of it. Here an example:
>>> from verktyg.test import create_environ
>>> env = create_environ("/?param=foo", "http://localhost/script")
>>> get_current_url(env)
'http://localhost/script/?param=foo'
>>> get_current_url(env, root_only=True)
'http://localhost/script/'
>>> get_current_url(env, host_only=True)
'http://localhost/'
>>> get_current_url(env, strip_querystring=True)
'http://localhost/script/'
This optionally it verifies that the host is in a list of trusted hosts.
If the host is not in there it will raise a
:exc:`~verktyg.exceptions.SecurityError`.
Note that the string returned might contain unicode characters as the
representation is an IRI not an URI. If you need an ASCII only
representation you can use the :func:`~verktyg.urls.iri_to_uri`
function:
>>> from verktyg.urls import iri_to_uri
>>> iri_to_uri(get_current_url(env))
'http://localhost/script/?param=foo'
:param environ:
The WSGI environment to get the current URL from.
:param root_only:
Set `True` if you only want the root URL.
:param strip_querystring:
Set to `True` if you don't want the querystring.
:param host_only:
Set to `True` if the host URL should be returned.
:param trusted_hosts:
A list of trusted hosts, see :func:`host_is_trusted` for more
information.
"""
tmp = [environ['wsgi.url_scheme'], '://', get_host(environ, trusted_hosts)]
cat = tmp.append
if host_only:
return uri_to_iri(''.join(tmp) + '/')
cat(urlquote(wsgi_get_bytes(environ.get('SCRIPT_NAME', ''))).rstrip('/'))
cat('/')
if not root_only:
cat(urlquote(
wsgi_get_bytes(environ.get('PATH_INFO', '')).lstrip(b'/')
))
if not strip_querystring:
qs = get_query_string(environ)
if qs:
cat('?' + qs)
return uri_to_iri(''.join(tmp))
def get_current_url(environ,
root_only=False,
strip_querystring=False,
host_only=False,
trusted_hosts=None):
"""A handy helper function that recreates the full URL as IRI for the
current request or parts of it. Here an example:
>>> from verktyg.test import create_environ
>>> env = create_environ("/?param=foo", "http://localhost/script")
>>> get_current_url(env)
'http://localhost/script/?param=foo'
>>> get_current_url(env, root_only=True)
'http://localhost/script/'
>>> get_current_url(env, host_only=True)
'http://localhost/'
>>> get_current_url(env, strip_querystring=True)
'http://localhost/script/'
This optionally it verifies that the host is in a list of trusted hosts.
If the host is not in there it will raise a
:exc:`~verktyg.exceptions.SecurityError`.
Note that the string returned might contain unicode characters as the
representation is an IRI not an URI. If you need an ASCII only
representation you can use the :func:`~verktyg.urls.iri_to_uri`
function:
>>> from verktyg.urls import iri_to_uri
>>> iri_to_uri(get_current_url(env))
'http://localhost/script/?param=foo'
:param environ: the WSGI environment to get the current URL from.
:param root_only: set `True` if you only want the root URL.
:param strip_querystring: set to `True` if you don't want the querystring.
:param host_only: set to `True` if the host URL should be returned.
:param trusted_hosts: a list of trusted hosts, see :func:`host_is_trusted`
for more information.
"""
tmp = [environ['wsgi.url_scheme'], '://', get_host(environ, trusted_hosts)]
cat = tmp.append
if host_only:
return uri_to_iri(''.join(tmp) + '/')
cat(urlquote(wsgi_get_bytes(environ.get('SCRIPT_NAME', ''))).rstrip('/'))
cat('/')
if not root_only:
cat(urlquote(
wsgi_get_bytes(environ.get('PATH_INFO', '')).lstrip(b'/')))
if not strip_querystring:
qs = get_query_string(environ)
if qs:
cat('?' + qs)
return uri_to_iri(''.join(tmp))
def test_uri_iri_normalization(self):
uri = 'http://xn--f-rgao.com/%E2%98%90/fred?utf8=%E2%9C%93'
iri = 'http://föñ.com/\N{BALLOT BOX}/fred?utf8=\u2713'
tests = [
'http://föñ.com/\N{BALLOT BOX}/fred?utf8=\u2713',
'http://xn--f-rgao.com/\u2610/fred?utf8=\N{CHECK MARK}',
'http://xn--f-rgao.com/%E2%98%90/fred?utf8=%E2%9C%93',
'http://xn--f-rgao.com/%E2%98%90/fred?utf8=%E2%9C%93',
'http://föñ.com/\u2610/fred?utf8=%E2%9C%93',
]
for test in tests:
self.assertEqual(urls.uri_to_iri(test), iri)
self.assertEqual(urls.iri_to_uri(test), uri)
self.assertEqual(urls.uri_to_iri(urls.iri_to_uri(test)), iri)
self.assertEqual(urls.iri_to_uri(urls.uri_to_iri(test)), uri)
self.assertEqual(urls.uri_to_iri(urls.uri_to_iri(test)), iri)
self.assertEqual(urls.iri_to_uri(urls.iri_to_uri(test)), uri)
def test_uri_iri_normalization(self):
uri = 'http://xn--f-rgao.com/%E2%98%90/fred?utf8=%E2%9C%93'
iri = 'http://föñ.com/\N{BALLOT BOX}/fred?utf8=\u2713'
tests = [
'http://föñ.com/\N{BALLOT BOX}/fred?utf8=\u2713',
'http://xn--f-rgao.com/\u2610/fred?utf8=\N{CHECK MARK}',
'http://xn--f-rgao.com/%E2%98%90/fred?utf8=%E2%9C%93',
'http://xn--f-rgao.com/%E2%98%90/fred?utf8=%E2%9C%93',
'http://föñ.com/\u2610/fred?utf8=%E2%9C%93',
]
for test in tests:
self.assertEqual(urls.uri_to_iri(test), iri)
self.assertEqual(urls.iri_to_uri(test), uri)
self.assertEqual(urls.uri_to_iri(urls.iri_to_uri(test)), iri)
self.assertEqual(urls.iri_to_uri(urls.uri_to_iri(test)), uri)
self.assertEqual(urls.uri_to_iri(urls.uri_to_iri(test)), iri)
self.assertEqual(urls.iri_to_uri(urls.iri_to_uri(test)), uri)
def test_uri_to_iri_to_uri(self):
uri = 'http://xn--f-rgao.com/%C3%9E'
iri = urls.uri_to_iri(uri)
self.assertEqual(urls.iri_to_uri(iri), uri)
def test_iri_to_uri_to_iri(self):
iri = 'http://föö.com/'
uri = urls.iri_to_uri(iri)
self.assertEqual(urls.uri_to_iri(uri), iri)
def test_uri_to_iri_idempotence_non_ascii(self):
uri = 'http://xn--n3h/%E2%98%83'
uri = urls.uri_to_iri(uri)
self.assertEqual(urls.uri_to_iri(uri), uri)
def test_uri_to_iri_idempotence_ascii_only(self):
uri = 'http://www.idempoten.ce'
uri = urls.uri_to_iri(uri)
self.assertEqual(urls.uri_to_iri(uri), uri)
def test_uri_to_iri_idempotence_ascii_only(self):
uri = 'http://www.idempoten.ce'
uri = urls.uri_to_iri(uri)
self.assertEqual(urls.uri_to_iri(uri), uri)
def test_uri_to_iri_to_uri(self):
uri = 'http://xn--f-rgao.com/%C3%9E'
iri = urls.uri_to_iri(uri)
self.assertEqual(urls.iri_to_uri(iri), uri)
def test_iri_to_uri_to_iri(self):
iri = 'http://föö.com/'
uri = urls.iri_to_uri(iri)
self.assertEqual(urls.uri_to_iri(uri), iri)
def test_uri_to_iri_idempotence_non_ascii(self):
uri = 'http://xn--n3h/%E2%98%83'
uri = urls.uri_to_iri(uri)
self.assertEqual(urls.uri_to_iri(uri), uri)
def extract_path_info(environ_or_baseurl,
path_or_url,
errors='replace',
collapse_http_schemes=True):
"""Extracts the path info from the given URL (or WSGI environment) and
path. The path info returned is a unicode string, not a bytestring
suitable for a WSGI environment. The URLs might also be IRIs.
If the path info could not be determined, `None` is returned.
Some examples:
>>> extract_path_info('http://example.com/app', '/app/hello')
u'/hello'
>>> extract_path_info('http://example.com/app',
... 'https://example.com/app/hello')
u'/hello'
>>> extract_path_info('http://example.com/app',
... 'https://example.com/app/hello',
... collapse_http_schemes=False) is None
True
Instead of providing a base URL you can also pass a WSGI environment.
:param environ_or_baseurl:
A WSGI environment dict, a base URL or base IRI. This is the root of
the application.
:param path_or_url:
An absolute path from the server root, a relative path (in which case
it's the path info) or a full URL. Also accepts IRIs and unicode
parameters.
:param errors:
The error handling on decode.
:param collapse_http_schemes:
If set to `False` the algorithm does not assume that http and https on
the same server point to the same resource.
"""
def _normalize_netloc(scheme, netloc):
parts = netloc.split(u'@', 1)[-1].split(u':', 1)
if len(parts) == 2:
netloc, port = parts
if ((scheme == u'http' and port == u'80')
or (scheme == u'https' and port == u'443')):
port = None
else:
netloc = parts[0]
port = None
if port is not None:
netloc += u':' + port
return netloc
# make sure whatever we are working on is a IRI and parse it
path = uri_to_iri(path_or_url, errors=errors)
if isinstance(environ_or_baseurl, dict):
environ_or_baseurl = get_current_url(environ_or_baseurl,
root_only=True)
base_iri = uri_to_iri(environ_or_baseurl, errors=errors)
base_scheme, base_netloc, base_path = urlsplit(base_iri)[:3]
cur_scheme, cur_netloc, cur_path, = urlsplit(urljoin(base_iri, path))[:3]
# normalize the network location
base_netloc = _normalize_netloc(base_scheme, base_netloc)
cur_netloc = _normalize_netloc(cur_scheme, cur_netloc)
# is that IRI even on a known HTTP scheme?
if collapse_http_schemes:
for scheme in base_scheme, cur_scheme:
if scheme not in (u'http', u'https'):
return None
else:
if not (base_scheme in (u'http', u'https')
and base_scheme == cur_scheme):
return None
# are the netlocs compatible?
if base_netloc != cur_netloc:
return None
# are we below the application path?
base_path = base_path.rstrip(u'/')
if not cur_path.startswith(base_path):
return None
return u'/' + cur_path[len(base_path):].lstrip(u'/')
def test_iri_safe_quoting(self):
uri = 'http://xn--f-1gaa.com/%2F%25?q=%C3%B6&x=%3D%25#%25'
iri = 'http://föö.com/%2F%25?q=ö&x=%3D%25#%25'
self.assertEqual(urls.uri_to_iri(uri), iri)
self.assertEqual(urls.iri_to_uri(urls.uri_to_iri(uri)), uri)
def test_iri_safe_quoting(self):
uri = 'http://xn--f-1gaa.com/%2F%25?q=%C3%B6&x=%3D%25#%25'
iri = 'http://föö.com/%2F%25?q=ö&x=%3D%25#%25'
self.assertEqual(urls.uri_to_iri(uri), iri)
self.assertEqual(urls.iri_to_uri(urls.uri_to_iri(uri)), uri)
