def test_iri_equality_special_cases():
assert rfc3986.iri_reference(u"http://Bü:ẞ@βόλος.com/β/ό?λ#ος") == (
u"http",
u"Bü:ẞ@βόλος.com",
u"/%CE%B2/%CF%8C",
u"%CE%BB",
u"%CE%BF%CF%82",
)
with pytest.raises(TypeError):
rfc3986.iri_reference(u"http://ẞ.com") == 1
def __init__(self,
url: URLTypes = "",
params: QueryParamTypes = None) -> None:
if isinstance(url, str):
try:
self._uri_reference = rfc3986.iri_reference(url).encode()
except rfc3986.exceptions.InvalidAuthority as exc:
raise InvalidURL(message=str(exc)) from None
if self.is_absolute_url:
# We don't want to normalize relative URLs, since doing so
# removes any leading `../` portion.
self._uri_reference = self._uri_reference.normalize()
elif isinstance(url, URL):
self._uri_reference = url._uri_reference
else:
raise TypeError(
f"Invalid type for url. Expected str or httpx.URL, got {type(url)}"
)
# Add any query parameters, merging with any in the URL if needed.
if params:
if self._uri_reference.query:
url_params = QueryParams(self._uri_reference.query)
url_params.update(params)
query_string = str(url_params)
else:
query_string = str(QueryParams(params))
self._uri_reference = self._uri_reference.copy_with(
query=query_string)
def __init__(self,
url: typing.Union["URL", str, RawURL] = "",
**kwargs: typing.Any) -> None:
if isinstance(url, (str, tuple)):
if isinstance(url, tuple):
raw_scheme, raw_host, port, raw_path = url
scheme = raw_scheme.decode("ascii")
host = raw_host.decode("ascii")
if host and ":" in host and host[0] != "[":
# it's an IPv6 address, so it should be enclosed in "[" and "]"
# ref: https://tools.ietf.org/html/rfc2732#section-2
# ref: https://tools.ietf.org/html/rfc3986#section-3.2.2
host = f"[{host}]"
port_str = "" if port is None else f":{port}"
path = raw_path.decode("ascii")
url = f"{scheme}://{host}{port_str}{path}"
try:
self._uri_reference = rfc3986.iri_reference(url).encode()
except rfc3986.exceptions.InvalidAuthority as exc:
raise InvalidURL(message=str(exc)) from None
if self.is_absolute_url:
# We don't want to normalize relative URLs, since doing so
# removes any leading `../` portion.
self._uri_reference = self._uri_reference.normalize()
elif isinstance(url, URL):
self._uri_reference = url._uri_reference
else:
raise TypeError(
f"Invalid type for url. Expected str or httpx.URL, got {type(url)}: {url!r}"
)
# Perform port normalization, following the WHATWG spec for default ports.
#
# See:
# * https://tools.ietf.org/html/rfc3986#section-3.2.3
# * https://url.spec.whatwg.org/#url-miscellaneous
# * https://url.spec.whatwg.org/#scheme-state
default_port = {
"ftp": ":21",
"http": ":80",
"https": ":443",
"ws": ":80",
"wss": ":443",
}.get(self._uri_reference.scheme, "")
authority = self._uri_reference.authority or ""
if default_port and authority.endswith(default_port):
authority = authority[:-len(default_port)]
self._uri_reference = self._uri_reference.copy_with(
authority=authority)
if kwargs:
self._uri_reference = self.copy_with(**kwargs)._uri_reference
def url_validator(_, attribute: attr.Attribute, urls: URLS):
if not isinstance(urls, (set, list, tuple)):
message = f'{attribute.name} is not a set, list or tuple instance: {urls}'
logger.exception(message)
raise TypeError(message)
if not all(isinstance(url, str) for url in urls):
message = f'not all items in urls are a string: {urls}'
logger.exception(message)
raise TypeError(message)
validator = validators.Validator()
allowed_schemes = ['https', 'http', 'file']
validator.allow_schemes(*allowed_schemes)
validator.check_validity_of('scheme', 'host', 'path', 'query', 'fragment')
for url in urls:
uri = iri_reference(url).encode()
try:
validator.validate(uri)
except exceptions.UnpermittedComponentError:
message = f'{url} does not have a scheme in {allowed_schemes}'
logger.exception(message)
raise ValueError(message)
except exceptions.InvalidComponentsError:
# not sure this error can happen if we use uri_reference with a string, but let's be careful
message = f'{url} is not a valid url'
logger.exception(message)
raise ValueError(message)
if uri.scheme in ('http', 'https') and uri.host is None:
message = f'url {url} must provide a host part'
logger.exception(message)
raise ValueError(message)
if uri.scheme == 'file' and uri.path is None:
message = f'url {url} must provide a path to a local file'
logger.exception(message)
raise ValueError(message)
def __init__(
self, url: typing.Union["URL", str, RawURL] = "", params: QueryParamTypes = None
) -> None:
if isinstance(url, (str, tuple)):
if isinstance(url, tuple):
raw_scheme, raw_host, port, raw_path = url
scheme = raw_scheme.decode("ascii")
host = raw_host.decode("ascii")
port_str = "" if port is None else f":{port}"
path = raw_path.decode("ascii")
url = f"{scheme}://{host}{port_str}{path}"
try:
self._uri_reference = rfc3986.iri_reference(url).encode()
except rfc3986.exceptions.InvalidAuthority as exc:
raise InvalidURL(message=str(exc)) from None
if self.is_absolute_url:
# We don't want to normalize relative URLs, since doing so
# removes any leading `../` portion.
self._uri_reference = self._uri_reference.normalize()
elif isinstance(url, URL):
self._uri_reference = url._uri_reference
else:
raise TypeError(
f"Invalid type for url. Expected str or httpx.URL, got {type(url)}"
)
# Add any query parameters, merging with any in the URL if needed.
if params:
if self._uri_reference.query:
url_params = QueryParams(self._uri_reference.query)
url_params.update(params)
query_string = str(url_params)
else:
query_string = str(QueryParams(params))
self._uri_reference = self._uri_reference.copy_with(query=query_string)
def test_encode_invalid_iri(iri):
iri_ref = rfc3986.iri_reference(iri)
with pytest.raises(InvalidAuthority):
iri_ref.encode()
def test_iri_equality(iri, uri):
assert rfc3986.iri_reference(iri) == iri
def test_encode_iri(iri, uri):
assert rfc3986.iri_reference(iri).encode().unsplit() == uri
def test_encode_invalid_iri(iri):
iri_ref = rfc3986.iri_reference(iri)
with pytest.raises(InvalidAuthority):
iri_ref.encode()
def test_iri_equality_special_cases():
assert rfc3986.iri_reference(u"http://Bü:ẞ@βόλος.com/β/ό?λ#ος") == \
(u"http", u"Bü:ẞ@βόλος.com", u"/%CE%B2/%CF%8C", u"%CE%BB", u"%CE%BF%CF%82")
with pytest.raises(TypeError):
rfc3986.iri_reference(u"http://ẞ.com") == 1
def test_iri_equality(iri, uri):
assert rfc3986.iri_reference(iri) == iri
def test_encode_iri(iri, uri):
assert rfc3986.iri_reference(iri).encode().unsplit() == uri