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"):
urllib_parse.urlparse("www.python.org", b"http")
with self.assertRaisesRegex(TypeError, "Cannot mix str"):
urllib_parse.urlparse(b"www.python.org", "http")
with self.assertRaisesRegex(TypeError, "Cannot mix str"):
urllib_parse.urlsplit("www.python.org", b"http")
with self.assertRaisesRegex(TypeError, "Cannot mix str"):
urllib_parse.urlsplit(b"www.python.org", "http")
with self.assertRaisesRegex(TypeError, "Cannot mix str"):
urllib_parse.urlunparse(
(b"http", "www.python.org", "", "", "", ""))
with self.assertRaisesRegex(TypeError, "Cannot mix str"):
urllib_parse.urlunparse(
("http", b"www.python.org", "", "", "", ""))
with self.assertRaisesRegex(TypeError, "Cannot mix str"):
urllib_parse.urlunsplit((b"http", "www.python.org", "", "", ""))
with self.assertRaisesRegex(TypeError, "Cannot mix str"):
urllib_parse.urlunsplit(("http", b"www.python.org", "", "", ""))
with self.assertRaisesRegex(TypeError, "Cannot mix str"):
urllib_parse.urljoin("http://python.org", b"http://python.org")
with self.assertRaisesRegex(TypeError, "Cannot mix str"):
urllib_parse.urljoin(b"http://python.org", "http://python.org")
def checkRoundtrips(self, url, parsed, split):
result = urllib_parse.urlparse(url)
self.assertEqual(result, parsed)
t = (result.scheme, result.netloc, result.path,
result.params, result.query, result.fragment)
self.assertEqual(t, parsed)
# put it back together and it should be the same
result2 = urllib_parse.urlunparse(result)
self.assertEqual(result2, url)
self.assertEqual(result2, result.geturl())
# the result of geturl() is a fixpoint; we can always parse it
# again to get the same result:
result3 = urllib_parse.urlparse(result.geturl())
self.assertEqual(result3.geturl(), result.geturl())
self.assertEqual(result3, result)
self.assertEqual(result3.scheme, result.scheme)
self.assertEqual(result3.netloc, result.netloc)
self.assertEqual(result3.path, result.path)
self.assertEqual(result3.params, result.params)
self.assertEqual(result3.query, result.query)
self.assertEqual(result3.fragment, result.fragment)
self.assertEqual(result3.username, result.username)
self.assertEqual(result3.password, result.password)
self.assertEqual(result3.hostname, result.hostname)
self.assertEqual(result3.port, result.port)
# check the roundtrip using urlsplit() as well
result = urllib_parse.urlsplit(url)
self.assertEqual(result, split)
t = (result.scheme, result.netloc, result.path,
result.query, result.fragment)
self.assertEqual(t, split)
result2 = urllib_parse.urlunsplit(result)
self.assertEqual(result2, url)
self.assertEqual(result2, result.geturl())
# check the fixpoint property of re-parsing the result of geturl()
result3 = urllib_parse.urlsplit(result.geturl())
self.assertEqual(result3.geturl(), result.geturl())
self.assertEqual(result3, result)
self.assertEqual(result3.scheme, result.scheme)
self.assertEqual(result3.netloc, result.netloc)
self.assertEqual(result3.path, result.path)
self.assertEqual(result3.query, result.query)
self.assertEqual(result3.fragment, result.fragment)
self.assertEqual(result3.username, result.username)
self.assertEqual(result3.password, result.password)
self.assertEqual(result3.hostname, result.hostname)
self.assertEqual(result3.port, result.port)
def test_issue14072(self):
p1 = urllib_parse.urlsplit('tel:+31-641044153')
self.assertEqual(p1.scheme, 'tel')
self.assertEqual(p1.path, '+31-641044153')
p2 = urllib_parse.urlsplit('tel:+31641044153')
self.assertEqual(p2.scheme, 'tel')
self.assertEqual(p2.path, '+31641044153')
# assert the behavior for urlparse
p1 = urllib_parse.urlparse('tel:+31-641044153')
self.assertEqual(p1.scheme, 'tel')
self.assertEqual(p1.path, '+31-641044153')
p2 = urllib_parse.urlparse('tel:+31641044153')
self.assertEqual(p2.scheme, 'tel')
self.assertEqual(p2.path, '+31641044153')
def checkRoundtrips(self, url, parsed, split):
result = urllib_parse.urlparse(url)
self.assertEqual(result, parsed)
t = (result.scheme, result.netloc, result.path,
result.params, result.query, result.fragment)
self.assertEqual(t, parsed)
# put it back together and it should be the same
result2 = urllib_parse.urlunparse(result)
self.assertEqual(result2, url)
self.assertEqual(result2, result.geturl())
# the result of geturl() is a fixpoint; we can always parse it
# again to get the same result:
result3 = urllib_parse.urlparse(result.geturl())
self.assertEqual(result3.geturl(), result.geturl())
self.assertEqual(result3, result)
self.assertEqual(result3.scheme, result.scheme)
self.assertEqual(result3.netloc, result.netloc)
self.assertEqual(result3.path, result.path)
self.assertEqual(result3.params, result.params)
self.assertEqual(result3.query, result.query)
self.assertEqual(result3.fragment, result.fragment)
self.assertEqual(result3.username, result.username)
self.assertEqual(result3.password, result.password)
self.assertEqual(result3.hostname, result.hostname)
self.assertEqual(result3.port, result.port)
# check the roundtrip using urlsplit() as well
result = urllib_parse.urlsplit(url)
self.assertEqual(result, split)
t = (result.scheme, result.netloc, result.path,
result.query, result.fragment)
self.assertEqual(t, split)
result2 = urllib_parse.urlunsplit(result)
self.assertEqual(result2, url)
self.assertEqual(result2, result.geturl())
# check the fixpoint property of re-parsing the result of geturl()
result3 = urllib_parse.urlsplit(result.geturl())
self.assertEqual(result3.geturl(), result.geturl())
self.assertEqual(result3, result)
self.assertEqual(result3.scheme, result.scheme)
self.assertEqual(result3.netloc, result.netloc)
self.assertEqual(result3.path, result.path)
self.assertEqual(result3.query, result.query)
self.assertEqual(result3.fragment, result.fragment)
self.assertEqual(result3.username, result.username)
self.assertEqual(result3.password, result.password)
self.assertEqual(result3.hostname, result.hostname)
self.assertEqual(result3.port, result.port)
def test_issue14072(self):
p1 = urllib_parse.urlsplit('tel:+31-641044153')
self.assertEqual(p1.scheme, 'tel')
self.assertEqual(p1.path, '+31-641044153')
p2 = urllib_parse.urlsplit('tel:+31641044153')
self.assertEqual(p2.scheme, 'tel')
self.assertEqual(p2.path, '+31641044153')
# assert the behavior for urlparse
p1 = urllib_parse.urlparse('tel:+31-641044153')
self.assertEqual(p1.scheme, 'tel')
self.assertEqual(p1.path, '+31-641044153')
p2 = urllib_parse.urlparse('tel:+31641044153')
self.assertEqual(p2.scheme, 'tel')
self.assertEqual(p2.path, '+31641044153')
def _get_encoded_url(self):
"""Convert any UTF-8 char in :obj:`File.file_path` into a url encoded ASCII string."""
sres = urllib_parse.urlsplit(self.file_path)
return urllib_parse.urlunsplit(
urllib_parse.SplitResult(sres.scheme, sres.netloc,
urllib_parse.quote(sres.path), sres.query,
sres.fragment))
def test_attributes_bad_port(self):
"""Check handling of non-integer ports."""
p = urllib_parse.urlsplit("http://www.example.net:foo")
self.assertEqual(p.netloc, "www.example.net:foo")
self.assertRaises(ValueError, lambda: p.port)
p = urllib_parse.urlparse("http://www.example.net:foo")
self.assertEqual(p.netloc, "www.example.net:foo")
self.assertRaises(ValueError, lambda: p.port)
# Once again, repeat ourselves to test bytes
p = urllib_parse.urlsplit(b"http://www.example.net:foo")
self.assertEqual(p.netloc, b"www.example.net:foo")
self.assertRaises(ValueError, lambda: p.port)
p = urllib_parse.urlparse(b"http://www.example.net:foo")
self.assertEqual(p.netloc, b"www.example.net:foo")
self.assertRaises(ValueError, lambda: p.port)
def test_attributes_bad_port(self):
"""Check handling of non-integer ports."""
p = urllib_parse.urlsplit("http://www.example.net:foo")
self.assertEqual(p.netloc, "www.example.net:foo")
self.assertRaises(ValueError, lambda: p.port)
p = urllib_parse.urlparse("http://www.example.net:foo")
self.assertEqual(p.netloc, "www.example.net:foo")
self.assertRaises(ValueError, lambda: p.port)
# Once again, repeat ourselves to test bytes
p = urllib_parse.urlsplit(b"http://www.example.net:foo")
self.assertEqual(p.netloc, b"www.example.net:foo")
self.assertRaises(ValueError, lambda: p.port)
p = urllib_parse.urlparse(b"http://www.example.net:foo")
self.assertEqual(p.netloc, b"www.example.net:foo")
self.assertRaises(ValueError, lambda: p.port)
def test_attributes_without_netloc(self):
# This example is straight from RFC 3261. It looks like it
# should allow the username, hostname, and port to be filled
# in, but doesn't. Since it's a URI and doesn't use the
# scheme://netloc syntax, the netloc and related attributes
# should be left empty.
uri = "sip:[email protected];maddr=239.255.255.1;ttl=15"
p = urllib_parse.urlsplit(uri)
self.assertEqual(p.netloc, "")
self.assertEqual(p.username, None)
self.assertEqual(p.password, None)
self.assertEqual(p.hostname, None)
self.assertEqual(p.port, None)
self.assertEqual(p.geturl(), uri)
p = urllib_parse.urlparse(uri)
self.assertEqual(p.netloc, "")
self.assertEqual(p.username, None)
self.assertEqual(p.password, None)
self.assertEqual(p.hostname, None)
self.assertEqual(p.port, None)
self.assertEqual(p.geturl(), uri)
# You guessed it, repeating the test with bytes input
uri = b"sip:[email protected];maddr=239.255.255.1;ttl=15"
p = urllib_parse.urlsplit(uri)
self.assertEqual(p.netloc, b"")
self.assertEqual(p.username, None)
self.assertEqual(p.password, None)
self.assertEqual(p.hostname, None)
self.assertEqual(p.port, None)
self.assertEqual(p.geturl(), uri)
p = urllib_parse.urlparse(uri)
self.assertEqual(p.netloc, b"")
self.assertEqual(p.username, None)
self.assertEqual(p.password, None)
self.assertEqual(p.hostname, None)
self.assertEqual(p.port, None)
self.assertEqual(p.geturl(), uri)
def test_attributes_without_netloc(self):
# This example is straight from RFC 3261. It looks like it
# should allow the username, hostname, and port to be filled
# in, but doesn't. Since it's a URI and doesn't use the
# scheme://netloc syntax, the netloc and related attributes
# should be left empty.
uri = "sip:[email protected];maddr=239.255.255.1;ttl=15"
p = urllib_parse.urlsplit(uri)
self.assertEqual(p.netloc, "")
self.assertEqual(p.username, None)
self.assertEqual(p.password, None)
self.assertEqual(p.hostname, None)
self.assertEqual(p.port, None)
self.assertEqual(p.geturl(), uri)
p = urllib_parse.urlparse(uri)
self.assertEqual(p.netloc, "")
self.assertEqual(p.username, None)
self.assertEqual(p.password, None)
self.assertEqual(p.hostname, None)
self.assertEqual(p.port, None)
self.assertEqual(p.geturl(), uri)
# You guessed it, repeating the test with bytes input
uri = b"sip:[email protected];maddr=239.255.255.1;ttl=15"
p = urllib_parse.urlsplit(uri)
self.assertEqual(p.netloc, b"")
self.assertEqual(p.username, None)
self.assertEqual(p.password, None)
self.assertEqual(p.hostname, None)
self.assertEqual(p.port, None)
self.assertEqual(p.geturl(), uri)
p = urllib_parse.urlparse(uri)
self.assertEqual(p.netloc, b"")
self.assertEqual(p.username, None)
self.assertEqual(p.password, None)
self.assertEqual(p.hostname, None)
self.assertEqual(p.port, None)
self.assertEqual(p.geturl(), uri)
def get_or_post(uri,
method,
req,
content_type=DEFAULT_POST_CONTENT_TYPE,
accept=None,
**kwargs):
"""
:param uri:
:param method:
:param req:
:param content_type:
:param accept:
:param kwargs:
:return:
"""
if method in ["GET", "DELETE"]:
if req.keys():
_req = req.copy()
comp = urlsplit(str(uri))
if comp.query:
_req.update(parse_qs(comp.query))
_query = str(_req.to_urlencoded())
path = urlunsplit(
(comp.scheme, comp.netloc, comp.path, _query, comp.fragment))
else:
path = uri
body = None
elif method in ["POST", "PUT"]:
path = uri
if content_type == URL_ENCODED:
body = req.to_urlencoded()
elif content_type == JSON_ENCODED:
body = req.to_json()
else:
raise UnSupported("Unsupported content type: '%s'" % content_type)
header_ext = {"Content-Type": content_type}
if accept:
header_ext = {"Accept": accept}
if "headers" in kwargs.keys():
kwargs["headers"].update(header_ext)
else:
kwargs["headers"] = header_ext
else:
raise UnSupported("Unsupported HTTP method: '%s'" % method)
return path, body, kwargs
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"):
urllib_parse.urlparse("www.python.org", b"http")
with self.assertRaisesRegex(TypeError, "Cannot mix str"):
urllib_parse.urlparse(b"www.python.org", "http")
with self.assertRaisesRegex(TypeError, "Cannot mix str"):
urllib_parse.urlsplit("www.python.org", b"http")
with self.assertRaisesRegex(TypeError, "Cannot mix str"):
urllib_parse.urlsplit(b"www.python.org", "http")
with self.assertRaisesRegex(TypeError, "Cannot mix str"):
urllib_parse.urlunparse(( b"http", "www.python.org","","","",""))
with self.assertRaisesRegex(TypeError, "Cannot mix str"):
urllib_parse.urlunparse(("http", b"www.python.org","","","",""))
with self.assertRaisesRegex(TypeError, "Cannot mix str"):
urllib_parse.urlunsplit((b"http", "www.python.org","","",""))
with self.assertRaisesRegex(TypeError, "Cannot mix str"):
urllib_parse.urlunsplit(("http", b"www.python.org","","",""))
with self.assertRaisesRegex(TypeError, "Cannot mix str"):
urllib_parse.urljoin("http://python.org", b"http://python.org")
with self.assertRaisesRegex(TypeError, "Cannot mix str"):
urllib_parse.urljoin(b"http://python.org", "http://python.org")
def test_unparse_parse(self):
str_cases = [
'Python',
'./Python',
'x-newscheme://foo.com/stuff',
'x://y',
'x:/y',
'x:/',
'/',
]
bytes_cases = [x.encode('ascii') for x in str_cases]
for u in str_cases + bytes_cases:
self.assertEqual(urllib_parse.urlunsplit(urllib_parse.urlsplit(u)),
u)
self.assertEqual(urllib_parse.urlunparse(urllib_parse.urlparse(u)),
u)
def get_or_post(uri, method, req, content_type=DEFAULT_POST_CONTENT_TYPE,
accept=None, **kwargs):
"""
:param uri:
:param method:
:param req:
:param content_type:
:param accept:
:param kwargs:
:return:
"""
if method in ["GET", "DELETE"]:
if req.keys():
_req = req.copy()
comp = urlsplit(str(uri))
if comp.query:
_req.update(parse_qs(comp.query))
_query = str(_req.to_urlencoded())
path = urlunsplit((comp.scheme, comp.netloc, comp.path,
_query, comp.fragment))
else:
path = uri
body = None
elif method in ["POST", "PUT"]:
path = uri
if content_type == URL_ENCODED:
body = req.to_urlencoded()
elif content_type == JSON_ENCODED:
body = req.to_json()
else:
raise UnSupported(
"Unsupported content type: '%s'" % content_type)
header_ext = {"Content-Type": content_type}
if accept:
header_ext = {"Accept": accept}
if "headers" in kwargs.keys():
kwargs["headers"].update(header_ext)
else:
kwargs["headers"] = header_ext
else:
raise UnSupported("Unsupported HTTP method: '%s'" % method)
return path, body, kwargs
def download(self, custom_path=None, out=None, timeout=None):
"""
Download this file. By default, the file is saved in the current working directory with its
original filename as reported by Telegram. If a :attr:`custom_path` is supplied, it will be
saved to that path instead. If :attr:`out` is defined, the file contents will be saved to
that object using the ``out.write`` method.
Note:
`custom_path` and `out` are mutually exclusive.
Args:
custom_path (:obj:`str`, optional): Custom path.
out (:obj:`object`, optional): A file-like object. Must be opened in binary mode, if
applicable.
timeout (:obj:`int` | :obj:`float`, optional): If this value is specified, use it as
the read timeout from the server (instead of the one specified during creation of
the connection pool).
Raises:
ValueError: If both ``custom_path`` and ``out`` are passed.
"""
if custom_path is not None and out is not None:
raise ValueError('custom_path and out are mutually exclusive')
# Convert any UTF-8 char into a url encoded ASCII string.
sres = urllib_parse.urlsplit(self.file_path)
url = urllib_parse.urlunsplit(
urllib_parse.SplitResult(sres.scheme, sres.netloc,
urllib_parse.quote(sres.path), sres.query,
sres.fragment))
if out:
buf = self.bot.request.retrieve(url)
out.write(buf)
else:
if custom_path:
filename = custom_path
else:
filename = basename(self.file_path)
self.bot.request.download(url, filename, timeout=timeout)
def download(self, custom_path=None, out=None, timeout=None):
"""
Download this file. By default, the file is saved in the current working directory with its
original filename as reported by Telegram. If a :attr:`custom_path` is supplied, it will be
saved to that path instead. If :attr:`out` is defined, the file contents will be saved to
that object using the ``out.write`` method.
Note:
`custom_path` and `out` are mutually exclusive.
Args:
custom_path (:obj:`str`, optional): Custom path.
out (:obj:`object`, optional): A file-like object. Must be opened in binary mode, if
applicable.
timeout (:obj:`int` | :obj:`float`, optional): If this value is specified, use it as
the read timeout from the server (instead of the one specified during creation of
the connection pool).
Raises:
ValueError: If both ``custom_path`` and ``out`` are passed.
"""
if custom_path is not None and out is not None:
raise ValueError('custom_path and out are mutually exclusive')
# Convert any UTF-8 char into a url encoded ASCII string.
sres = urllib_parse.urlsplit(self.file_path)
url = urllib_parse.urlunsplit(urllib_parse.SplitResult(
sres.scheme, sres.netloc, urllib_parse.quote(sres.path), sres.query, sres.fragment))
if out:
buf = self.bot.request.retrieve(url)
out.write(buf)
else:
if custom_path:
filename = custom_path
else:
filename = basename(self.file_path)
self.bot.request.download(url, filename, timeout=timeout)
def create_return_url(base, query, **kwargs):
"""
Add a query string plus extra parameters to a base URL which may contain
a query part already.
:param base: redirect_uri may contain a query part, no fragment allowed.
:param query: Old query part as a string
:param kwargs: extra query parameters
:return:
"""
part = urlsplit(base)
if part.fragment:
raise ValueError("Base URL contained parts it shouldn't")
for key, values in parse_qs(query).items():
if key in kwargs:
if isinstance(kwargs[key], six.string_types):
kwargs[key] = [kwargs[key]]
kwargs[key].extend(values)
else:
kwargs[key] = values
if part.query:
for key, values in parse_qs(part.query).items():
if key in kwargs:
if isinstance(kwargs[key], six.string_types):
kwargs[key] = [kwargs[key]]
kwargs[key].extend(values)
else:
kwargs[key] = values
_pre = base.split("?")[0]
else:
_pre = base
logger.debug("kwargs: %s" % sanitize(kwargs))
if kwargs:
return "%s?%s" % (_pre, url_encode_params(kwargs))
else:
return _pre
def create_return_url(base, query, **kwargs):
"""
Add a query string plus extra parameters to a base URL which may contain
a query part already.
:param base: redirect_uri may contain a query part, no fragment allowed.
:param query: Old query part as a string
:param kwargs: extra query parameters
:return:
"""
part = urlsplit(base)
if part.fragment:
raise ValueError("Base URL contained parts it shouldn't")
for key, values in parse_qs(query).items():
if key in kwargs:
if isinstance(kwargs[key], six.string_types):
kwargs[key] = [kwargs[key]]
kwargs[key].extend(values)
else:
kwargs[key] = values
if part.query:
for key, values in parse_qs(part.query).items():
if key in kwargs:
if isinstance(kwargs[key], six.string_types):
kwargs[key] = [kwargs[key]]
kwargs[key].extend(values)
else:
kwargs[key] = values
_pre = base.split("?")[0]
else:
_pre = base
logger.debug("kwargs: %s" % kwargs)
if kwargs:
return "%s?%s" % (_pre, url_encode_params(kwargs))
else:
return _pre
def key_export(baseurl, local_path, vault, keyjar, **kwargs):
"""
:param baseurl: The base URL to which the key file names are added
:param local_path: Where on the machine the export files are kept
:param vault: Where the keys are kept
:param keyjar: Where to store the exported keys
:return: 2-tuple: result of urlsplit and a dictionary with
parameter name as key and url and value
"""
part = urlsplit(baseurl)
# deal with the export directory
if part.path.endswith("/"):
_path = part.path[:-1]
else:
_path = part.path[:]
local_path = proper_path("%s/%s" % (_path, local_path))
if not os.path.exists(local_path):
os.makedirs(local_path)
kb = key_setup(vault, **kwargs)
try:
keyjar[""].append(kb)
except KeyError:
keyjar[""] = kb
# the local filename
_export_filename = os.path.join(local_path, "jwks")
with open(_export_filename, "w") as f:
f.write(str(kb))
_url = "%s://%s%s" % (part.scheme, part.netloc,
_export_filename[1:])
return _url
def key_export(baseurl, local_path, vault, keyjar, **kwargs):
"""
:param baseurl: The base URL to which the key file names are added
:param local_path: Where on the machine the export files are kept
:param vault: Where the keys are kept
:param keyjar: Where to store the exported keys
:return: 2-tuple: result of urlsplit and a dictionary with
parameter name as key and url and value
"""
part = urlsplit(baseurl)
# deal with the export directory
if part.path.endswith("/"):
_path = part.path[:-1]
else:
_path = part.path[:]
local_path = proper_path("%s/%s" % (_path, local_path))
if not os.path.exists(local_path):
os.makedirs(local_path)
kb = key_setup(vault, **kwargs)
try:
keyjar[""].append(kb)
except KeyError:
keyjar[""] = kb
# the local filename
_export_filename = os.path.join(local_path, "jwks")
with open(_export_filename, "w") as f:
f.write(str(kb))
_url = "%s://%s%s" % (part.scheme, part.netloc,
_export_filename[1:])
return _url
def generate_return_url(self, return_to, uid, path=""):
"""
:param return_to: If it starts with '/' it's an absolute path otherwise
a relative path.
:param uid:
:param path: The verify path
"""
if return_to.startswith("http"):
up = urlsplit(return_to)
_path = up.path
else:
up = None
_path = return_to
if not _path.startswith("/"):
p = path.split("/")
p[-1] = _path
_path = "/".join(p)
if up:
_path = urlunsplit([up[0], up[1], _path, up[3], up[4]])
return create_return_url(_path, uid, **{self.query_param: "true"})
def generate_return_url(self, return_to, uid, path=""):
"""
:param return_to: If it starts with '/' it's an absolute path otherwise
a relative path.
:param uid:
:param path: The verify path
"""
if return_to.startswith("http"):
up = urlsplit(return_to)
_path = up.path
else:
up = None
_path = return_to
if not _path.startswith("/"):
p = path.split("/")
p[-1] = _path
_path = "/".join(p)
if up:
_path = urlunsplit([up[0], up[1], _path, up[3], up[4]])
return create_return_url(_path, uid, **{self.query_param: "true"})
def putrequest(self, method, url, skip_host=0, skip_accept_encoding=0):
"""Send a request to the server.
`method' specifies an HTTP request method, e.g. 'GET'.
`url' specifies the object being requested, e.g. '/index.html'.
`skip_host' if True does not add automatically a 'Host:' header
`skip_accept_encoding' if True does not add automatically an
'Accept-Encoding:' header
"""
# if a prior response has been completed, then forget about it.
if self.__response and self.__response.isclosed():
self.__response = None
# in certain cases, we cannot issue another request on this connection.
# this occurs when:
# 1) we are in the process of sending a request. (_CS_REQ_STARTED)
# 2) a response to a previous request has signalled that it is going
# to close the connection upon completion.
# 3) the headers for the previous response have not been read, thus
# we cannot determine whether point (2) is true. (_CS_REQ_SENT)
#
# if there is no prior response, then we can request at will.
#
# if point (2) is true, then we will have passed the socket to the
# response (effectively meaning, "there is no prior response"), and
# will open a new one when a new request is made.
#
# Note: if a prior response exists, then we *can* start a new request.
# We are not allowed to begin fetching the response to this new
# request, however, until that prior response is complete.
#
if self.__state == _CS_IDLE:
self.__state = _CS_REQ_STARTED
else:
raise CannotSendRequest(self.__state)
# Save the method we use, we need it later in the response phase
self._method = method
if not url:
url = '/'
request = '%s %s %s' % (method, url, self._http_vsn_str)
# Non-ASCII characters should have been eliminated earlier
self._output(request.encode('ascii'))
if self._http_vsn == 11:
# Issue some standard headers for better HTTP/1.1 compliance
if not skip_host:
# this header is issued *only* for HTTP/1.1
# connections. more specifically, this means it is
# only issued when the client uses the new
# HTTPConnection() class. backwards-compat clients
# will be using HTTP/1.0 and those clients may be
# issuing this header themselves. we should NOT issue
# it twice; some web servers (such as Apache) barf
# when they see two Host: headers
# If we need a non-standard port,include it in the
# header. If the request is going through a proxy,
# but the host of the actual URL, not the host of the
# proxy.
netloc = ''
if url.startswith('http'):
nil, netloc, nil, nil, nil = urlsplit(url)
if netloc:
try:
netloc_enc = netloc.encode("ascii")
except UnicodeEncodeError:
netloc_enc = netloc.encode("idna")
self.putheader('Host', netloc_enc)
else:
try:
host_enc = self.host.encode("ascii")
except UnicodeEncodeError:
host_enc = self.host.encode("idna")
# As per RFC 273, IPv6 address should be wrapped with []
# when used as Host header
if self.host.find(':') >= 0:
host_enc = bytes(b'[' + host_enc + b']')
if self.port == self.default_port:
self.putheader('Host', host_enc)
else:
host_enc = host_enc.decode("ascii")
self.putheader('Host', "%s:%s" % (host_enc, self.port))
# note: we are assuming that clients will not attempt to set these
# headers since *this* library must deal with the
# consequences. this also means that when the supporting
# libraries are updated to recognize other forms, then this
# code should be changed (removed or updated).
# we only want a Content-Encoding of "identity" since we don't
# support encodings such as x-gzip or x-deflate.
if not skip_accept_encoding:
self.putheader('Accept-Encoding', 'identity')
# we can accept "chunked" Transfer-Encodings, but no others
# NOTE: no TE header implies *only* "chunked"
#self.putheader('TE', 'chunked')
# if TE is supplied in the header, then it must appear in a
# Connection header.
#self.putheader('Connection', 'TE')
else:
# For HTTP/1.0, the server will assume "not chunked"
pass
def get_path(self, redirect_uris, issuer):
for ruri in redirect_uris:
p = urlsplit(ruri)
self.path[p.path[1:]] = issuer
def test_urlsplit_attributes(self):
url = "HTTP://WWW.PYTHON.ORG/doc/#frag"
p = urllib_parse.urlsplit(url)
self.assertEqual(p.scheme, "http")
self.assertEqual(p.netloc, "WWW.PYTHON.ORG")
self.assertEqual(p.path, "/doc/")
self.assertEqual(p.query, "")
self.assertEqual(p.fragment, "frag")
self.assertEqual(p.username, None)
self.assertEqual(p.password, None)
self.assertEqual(p.hostname, "www.python.org")
self.assertEqual(p.port, None)
# geturl() won't return exactly the original URL in this case
# since the scheme is always case-normalized
# We handle this by ignoring the first 4 characters of the URL
self.assertEqual(p.geturl()[4:], url[4:])
url = "http://*****:*****@www.python.org:080/doc/?query=yes#frag"
p = urllib_parse.urlsplit(url)
self.assertEqual(p.scheme, "http")
self.assertEqual(p.netloc, "User:[email protected]:080")
self.assertEqual(p.path, "/doc/")
self.assertEqual(p.query, "query=yes")
self.assertEqual(p.fragment, "frag")
self.assertEqual(p.username, "User")
self.assertEqual(p.password, "Pass")
self.assertEqual(p.hostname, "www.python.org")
self.assertEqual(p.port, 80)
self.assertEqual(p.geturl(), url)
# Addressing issue1698, which suggests Username can contain
# "@" characters. Though not RFC compliant, many ftp sites allow
# and request email addresses as usernames.
url = "http://[email protected]:[email protected]:080/doc/?query=yes#frag"
p = urllib_parse.urlsplit(url)
self.assertEqual(p.scheme, "http")
self.assertEqual(p.netloc, "[email protected]:[email protected]:080")
self.assertEqual(p.path, "/doc/")
self.assertEqual(p.query, "query=yes")
self.assertEqual(p.fragment, "frag")
self.assertEqual(p.username, "*****@*****.**")
self.assertEqual(p.password, "Pass")
self.assertEqual(p.hostname, "www.python.org")
self.assertEqual(p.port, 80)
self.assertEqual(p.geturl(), url)
# And check them all again, only with bytes this time
url = b"HTTP://WWW.PYTHON.ORG/doc/#frag"
p = urllib_parse.urlsplit(url)
self.assertEqual(p.scheme, b"http")
self.assertEqual(p.netloc, b"WWW.PYTHON.ORG")
self.assertEqual(p.path, b"/doc/")
self.assertEqual(p.query, b"")
self.assertEqual(p.fragment, b"frag")
self.assertEqual(p.username, None)
self.assertEqual(p.password, None)
self.assertEqual(p.hostname, b"www.python.org")
self.assertEqual(p.port, None)
self.assertEqual(p.geturl()[4:], url[4:])
url = b"http://*****:*****@www.python.org:080/doc/?query=yes#frag"
p = urllib_parse.urlsplit(url)
self.assertEqual(p.scheme, b"http")
self.assertEqual(p.netloc, b"User:[email protected]:080")
self.assertEqual(p.path, b"/doc/")
self.assertEqual(p.query, b"query=yes")
self.assertEqual(p.fragment, b"frag")
self.assertEqual(p.username, b"User")
self.assertEqual(p.password, b"Pass")
self.assertEqual(p.hostname, b"www.python.org")
self.assertEqual(p.port, 80)
self.assertEqual(p.geturl(), url)
url = b"http://[email protected]:[email protected]:080/doc/?query=yes#frag"
p = urllib_parse.urlsplit(url)
self.assertEqual(p.scheme, b"http")
self.assertEqual(p.netloc, b"[email protected]:[email protected]:080")
self.assertEqual(p.path, b"/doc/")
self.assertEqual(p.query, b"query=yes")
self.assertEqual(p.fragment, b"frag")
self.assertEqual(p.username, b"*****@*****.**")
self.assertEqual(p.password, b"Pass")
self.assertEqual(p.hostname, b"www.python.org")
self.assertEqual(p.port, 80)
self.assertEqual(p.geturl(), url)
# Verify an illegal port is returned as None
url = b"HTTP://WWW.PYTHON.ORG:65536/doc/#frag"
p = urllib_parse.urlsplit(url)
self.assertEqual(p.port, None)
def filename(self):
return os.path.basename(
self.file.name if self.file else urlsplit(self.hyperlink).path)
def test_urlsplit_attributes(self):
url = "HTTP://WWW.PYTHON.ORG/doc/#frag"
p = urllib_parse.urlsplit(url)
self.assertEqual(p.scheme, "http")
self.assertEqual(p.netloc, "WWW.PYTHON.ORG")
self.assertEqual(p.path, "/doc/")
self.assertEqual(p.query, "")
self.assertEqual(p.fragment, "frag")
self.assertEqual(p.username, None)
self.assertEqual(p.password, None)
self.assertEqual(p.hostname, "www.python.org")
self.assertEqual(p.port, None)
# geturl() won't return exactly the original URL in this case
# since the scheme is always case-normalized
# We handle this by ignoring the first 4 characters of the URL
self.assertEqual(p.geturl()[4:], url[4:])
url = "http://*****:*****@www.python.org:080/doc/?query=yes#frag"
p = urllib_parse.urlsplit(url)
self.assertEqual(p.scheme, "http")
self.assertEqual(p.netloc, "User:[email protected]:080")
self.assertEqual(p.path, "/doc/")
self.assertEqual(p.query, "query=yes")
self.assertEqual(p.fragment, "frag")
self.assertEqual(p.username, "User")
self.assertEqual(p.password, "Pass")
self.assertEqual(p.hostname, "www.python.org")
self.assertEqual(p.port, 80)
self.assertEqual(p.geturl(), url)
# Addressing issue1698, which suggests Username can contain
# "@" characters. Though not RFC compliant, many ftp sites allow
# and request email addresses as usernames.
url = "http://[email protected]:[email protected]:080/doc/?query=yes#frag"
p = urllib_parse.urlsplit(url)
self.assertEqual(p.scheme, "http")
self.assertEqual(p.netloc, "[email protected]:[email protected]:080")
self.assertEqual(p.path, "/doc/")
self.assertEqual(p.query, "query=yes")
self.assertEqual(p.fragment, "frag")
self.assertEqual(p.username, "*****@*****.**")
self.assertEqual(p.password, "Pass")
self.assertEqual(p.hostname, "www.python.org")
self.assertEqual(p.port, 80)
self.assertEqual(p.geturl(), url)
# And check them all again, only with bytes this time
url = b"HTTP://WWW.PYTHON.ORG/doc/#frag"
p = urllib_parse.urlsplit(url)
self.assertEqual(p.scheme, b"http")
self.assertEqual(p.netloc, b"WWW.PYTHON.ORG")
self.assertEqual(p.path, b"/doc/")
self.assertEqual(p.query, b"")
self.assertEqual(p.fragment, b"frag")
self.assertEqual(p.username, None)
self.assertEqual(p.password, None)
self.assertEqual(p.hostname, b"www.python.org")
self.assertEqual(p.port, None)
self.assertEqual(p.geturl()[4:], url[4:])
url = b"http://*****:*****@www.python.org:080/doc/?query=yes#frag"
p = urllib_parse.urlsplit(url)
self.assertEqual(p.scheme, b"http")
self.assertEqual(p.netloc, b"User:[email protected]:080")
self.assertEqual(p.path, b"/doc/")
self.assertEqual(p.query, b"query=yes")
self.assertEqual(p.fragment, b"frag")
self.assertEqual(p.username, b"User")
self.assertEqual(p.password, b"Pass")
self.assertEqual(p.hostname, b"www.python.org")
self.assertEqual(p.port, 80)
self.assertEqual(p.geturl(), url)
url = b"http://[email protected]:[email protected]:080/doc/?query=yes#frag"
p = urllib_parse.urlsplit(url)
self.assertEqual(p.scheme, b"http")
self.assertEqual(p.netloc, b"[email protected]:[email protected]:080")
self.assertEqual(p.path, b"/doc/")
self.assertEqual(p.query, b"query=yes")
self.assertEqual(p.fragment, b"frag")
self.assertEqual(p.username, b"*****@*****.**")
self.assertEqual(p.password, b"Pass")
self.assertEqual(p.hostname, b"www.python.org")
self.assertEqual(p.port, 80)
self.assertEqual(p.geturl(), url)
# Verify an illegal port is returned as None
url = b"HTTP://WWW.PYTHON.ORG:65536/doc/#frag"
p = urllib_parse.urlsplit(url)
self.assertEqual(p.port, None)
def test_unparse_parse(self):
str_cases = ['Python', './Python','x-newscheme://foo.com/stuff','x://y','x:/y','x:/','/',]
bytes_cases = [x.encode('ascii') for x in str_cases]
for u in str_cases + bytes_cases:
self.assertEqual(urllib_parse.urlunsplit(urllib_parse.urlsplit(u)), u)
self.assertEqual(urllib_parse.urlunparse(urllib_parse.urlparse(u)), u)
def _get_encoded_url(self):
"""Convert any UTF-8 char in :obj:`File.file_path` into a url encoded ASCII string."""
sres = urllib_parse.urlsplit(self.file_path)
return urllib_parse.urlunsplit(urllib_parse.SplitResult(
sres.scheme, sres.netloc, urllib_parse.quote(sres.path), sres.query, sres.fragment))
def get_path(self, redirect_uris, issuer):
for ruri in redirect_uris:
p = urlsplit(ruri)
self.path[p.path[1:]] = issuer
