def filename(self):
# type: () -> str
_, netloc, path, _, _ = urllib_parse.urlsplit(self.url)
name = posixpath.basename(path.rstrip('/')) or netloc
name = urllib_parse.unquote(name)
assert name, ('URL %r produced no filename' % self.url)
return name
def _transform_url(url, transform_netloc):
purl = urllib_parse.urlsplit(url)
netloc = transform_netloc(purl.netloc)
# stripped url
url_pieces = (
purl.scheme, netloc, purl.path, purl.query, purl.fragment
)
surl = urllib_parse.urlunsplit(url_pieces)
return surl
def __init__(self, url, file_storage_domain):
# type: (str, str) -> None
super(PackageIndex, self).__init__()
self.url = url
self.netloc = urllib_parse.urlsplit(url).netloc
self.simple_url = self._url_for_path('simple')
self.pypi_url = self._url_for_path('pypi')
# This is part of a temporary hack used to block installs of PyPI
# packages which depend on external urls only necessary until PyPI can
# block such packages themselves
self.file_storage_domain = file_storage_domain
def _ensure_html_response(url, session):
# type: (str, PipSession) -> None
"""Send a HEAD request to the URL, and ensure the response contains HTML.
Raises `_NotHTTP` if the URL is not available for a HEAD request, or
`_NotHTML` if the content type is not text/html.
"""
scheme, netloc, path, query, fragment = urllib_parse.urlsplit(url)
if scheme not in {'http', 'https'}:
raise _NotHTTP()
resp = session.head(url, allow_redirects=True)
resp.raise_for_status()
_ensure_html_header(resp)
def url_to_path(url):
# type: (str) -> str
"""
Convert a file: URL to a path.
"""
assert url.startswith('file:'), (
"You can only turn file: urls into filenames (not %r)" % url)
_, netloc, path, _, _ = urllib_parse.urlsplit(url)
# if we have a UNC path, prepend UNC share notation
if netloc:
netloc = '\\\\' + netloc
path = urllib_request.url2pathname(netloc + path)
return path
def get_url_rev_and_auth(self, url):
# type: (str) -> Tuple[str, Optional[str], AuthInfo]
"""
Parse the repository URL to use, and return the URL, revision,
and auth info to use.
Returns: (url, rev, (username, password)).
"""
scheme, netloc, path, query, frag = urllib_parse.urlsplit(url)
if '+' not in scheme:
raise ValueError(
"Sorry, {!r} is a malformed VCS url. "
"The format is <vcs>+<protocol>://<url>, "
"e.g. svn+http://myrepo/svn/MyApp#egg=MyApp".format(url)
)
# Remove the vcs prefix.
scheme = scheme.split('+', 1)[1]
netloc, user_pass = self.get_netloc_and_auth(netloc, scheme)
rev = None
if '@' in path:
path, rev = path.rsplit('@', 1)
url = urllib_parse.urlunsplit((scheme, netloc, path, query, ''))
return url, rev, user_pass
def url_without_fragment(self):
# type: () -> str
scheme, netloc, path, query, fragment = urllib_parse.urlsplit(self.url)
return urllib_parse.urlunsplit((scheme, netloc, path, query, None))
def path(self):
# type: () -> str
return urllib_parse.unquote(urllib_parse.urlsplit(self.url)[2])
def netloc(self):
# type: () -> str
return urllib_parse.urlsplit(self.url)[1]
def scheme(self):
# type: () -> str
return urllib_parse.urlsplit(self.url)[0]
