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 _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_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 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 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_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 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 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))
