def get_rev_options(url, rev):
if rev:
rev_options = ['-r', rev]
else:
rev_options = []
r = urllib_parse.urlsplit(url)
if hasattr(r, 'username'):
# >= Python-2.5
username, password = r.username, r.password
else:
netloc = r[1]
if '@' in netloc:
auth = netloc.split('@')[0]
if ':' in auth:
username, password = auth.split(':', 1)
else:
username, password = auth, None
else:
username, password = None, None
if username:
rev_options += ['--username', username]
if password:
rev_options += ['--password', password]
return rev_options
def get_rev_options(url, rev):
if rev:
rev_options = ["-r", rev]
else:
rev_options = []
r = urllib_parse.urlsplit(url)
if hasattr(r, "username"):
# >= Python-2.5
username, password = r.username, r.password
else:
netloc = r[1]
if "@" in netloc:
auth = netloc.split("@")[0]
if ":" in auth:
username, password = auth.split(":", 1)
else:
username, password = auth, None
else:
username, password = None, None
if username:
rev_options += ["--username", username]
if password:
rev_options += ["--password", password]
return rev_options
def get_rev_options(vcs, url, rev):
"""
Return a RevOptions object.
"""
r = urllib_parse.urlsplit(url)
if hasattr(r, 'username'):
# >= Python-2.5
username, password = r.username, r.password
else:
netloc = r[1]
if '@' in netloc:
auth = netloc.split('@')[0]
if ':' in auth:
username, password = auth.split(':', 1)
else:
username, password = auth, None
else:
username, password = None, None
extra_args = []
if username:
extra_args += ['--username', username]
if password:
extra_args += ['--password', password]
return vcs.make_rev_options(rev, extra_args=extra_args)
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 get_rev_options_args(url):
"""
Return the extra arguments to pass to RevOptions.
"""
r = urllib_parse.urlsplit(url)
if hasattr(r, 'username'):
# >= Python-2.5
username, password = r.username, r.password
else:
netloc = r[1]
if '@' in netloc:
auth = netloc.split('@')[0]
if ':' in auth:
username, password = auth.split(':', 1)
else:
username, password = auth, None
else:
username, password = None, None
extra_args = []
if username:
extra_args += ['--username', username]
if password:
extra_args += ['--password', password]
return extra_args
def normalize(self):
parsed = urllib_parse.urlsplit(self.url)
if parsed.scheme == 'file':
path = urllib_request.url2pathname(parsed.path)
path = normalize_path(path)
path = urllib_request.pathname2url(path)
self.url = urllib_parse.urlunsplit(
(parsed.scheme, parsed.netloc,
path, parsed.query, parsed.fragment))
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):
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 _get_content_type(url, session):
"""Get the Content-Type of the given url, using a HEAD request"""
scheme, netloc, path, query, fragment = urllib_parse.urlsplit(url)
if scheme not in {'http', 'https'}:
# FIXME: some warning or something?
# assertion error?
return ''
resp = session.head(url, allow_redirects=True)
resp.raise_for_status()
return resp.headers.get("Content-Type", "")
def _ensure_html_response(url, session):
"""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):
"""
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 remove_auth_from_url(url):
# Return a copy of url with 'username:password@' removed.
# username/pass params are passed to subversion through flags
# and are not recognized in the url.
# parsed url
purl = urllib_parse.urlsplit(url)
netloc, user_pass = split_auth_from_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 get_url_rev(self):
"""
Returns the correct repository URL and revision by parsing the given
repository URL
"""
error_message = (
"Sorry, '%s' is a malformed VCS url. "
"The format is <vcs>+<protocol>://<url>, "
"e.g. svn+http://myrepo/svn/MyApp#egg=MyApp"
)
assert '+' in self.url, error_message % self.url
url = self.url.split('+', 1)[1]
scheme, netloc, path, query, frag = urllib_parse.urlsplit(url)
rev = None
if '@' in path:
path, rev = path.rsplit('@', 1)
url = urllib_parse.urlunsplit((scheme, netloc, path, query, ''))
return url, rev
def _transform_url(url, transform_netloc):
"""Transform and replace netloc in a url.
transform_netloc is a function taking the netloc and returning a
tuple. The first element of this tuple is the new netloc. The
entire tuple is returned.
Returns a tuple containing the transformed url as item 0 and the
original tuple returned by transform_netloc as item 1.
"""
purl = urllib_parse.urlsplit(url)
netloc_tuple = transform_netloc(purl.netloc)
# stripped url
url_pieces = (
purl.scheme, netloc_tuple[0], purl.path, purl.query, purl.fragment
)
surl = urllib_parse.urlunsplit(url_pieces)
return surl, netloc_tuple
def get_url_rev_and_auth(self, url):
"""
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_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 not netloc or netloc == 'localhost':
# According to RFC 8089, same as empty authority.
netloc = ''
elif sys.platform == 'win32':
# If we have a UNC path, prepend UNC share notation.
netloc = '\\\\' + netloc
else:
raise ValueError(
'non-local file URIs are not supported on this platform: %r'
% url
)
path = urllib_request.url2pathname(netloc + path)
return path
def __init__(self, url):
self.url = url
self.netloc = urllib_parse.urlsplit(url).netloc
self.simple_url = self.url_to_path('simple')
self.pypi_url = self.url_to_path('pypi')
def filejame(self):
# type: () -> str
_, netloc, path, _, _ = urllib_parse.urlsplit(self.url)
def url_without_fragment(self):
# type: () -> str
scheme, netloc, path, query, fragment = urllib_parse.urlsplit(self.url)
def filename(self):
_, 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 __init__(self, url):
self.url = url
self.netloc = urllib_parse.urlsplit(url).netloc
self.simple_url = self.url_to_path('simple')
self.pypi_url = self.url_to_path('pypi')
self.pip_json_url = self.url_to_path('pypi/pip/json')
"""
raise NotImplementedError
def get_url_rev(self):
"""
Returns the correct repository URL and revision by parsing the given
repository URL
"""
error_message = (
"Sorry, '%s' is a malformed VCS url. "
"The format is <vcs>+<protocol>://<url>, "
"e.g. svn+http://myrepo/svn/MyApp#egg=MyApp"
)
assert '+' in self.url, error_message % self.url
url = self.url.split('+', 1)[1]
scheme, netloc, path, query, frag = urllib_parse.urlsplit(url)
rev = None
if '@' in path:
path, rev = path.rsplit('@', 1)
url = urllib_parse.urlunsplit((scheme, netloc, path, query, ''))
return url, rev
def get_info(self, location):
"""
Returns (url, revision), where both are strings
"""
assert not location.rstrip('/').endswith(self.dirname), \
'Bad directory: %s' % location
return self.get_url(location), self.get_revision(location)
def normalize_url(self, url):
def scheme(self):
# type: () -> str
return urllib_parse.urlsplit(self.url)[0]
def url_without_fragment(self):
scheme, netloc, path, query, fragment = urllib_parse.urlsplit(self.url)
return urllib_parse.urlunsplit((scheme, netloc, path, query, None))
def netloc(self):
# type: () -> str
return urllib_parse.urlsplit(self.url)[1]
def url_without_fragment(self):
scheme, netloc, path, query, fragment = urllib_parse.urlsplit(self.url)
return urllib_parse.urlunsplit((scheme, netloc, path, query, None))
def netloc(self):
return urllib_parse.urlsplit(self.url)[1]
def path(self):
# type: () -> str
return urllib_parse.unquote(urllib_parse.urlsplit(self.url)[2])
def is_url(name):
"""Returns true if the name looks like a URL"""
if ':' not in name:
return False
scheme = name.split(':', 1)[0].lower()
return scheme in ['http', 'https', 'file', 'ftp'] + vcs.all_schemes
def url_to_path(url):
"""
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 path_to_url(path):
"""
Convert a path to a file: URL. The path will be made absolute and have
quoted path parts.
"""
path = os.path.normpath(os.path.abspath(path))
def filename(self):
_, 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 __init__(self, url):
self.url = url
self.netloc = urllib_parse.urlsplit(url).netloc
self.simple_url = self.url_to_path("simple")
self.pypi_url = self.url_to_path("pypi")
def scheme(self):
return urllib_parse.urlsplit(self.url)[0]
def scheme(self):
return urllib_parse.urlsplit(self.url)[0]
def path(self):
return urllib_parse.unquote(urllib_parse.urlsplit(self.url)[2])
def netloc(self):
return urllib_parse.urlsplit(self.url)[1]
def path(self):
return urllib_parse.unquote(urllib_parse.urlsplit(self.url)[2])
'Looking in indexes: {}'.format(', '.join(
redact_password_from_url(url) for url in self.index_urls))
)
if self.find_links:
lines.append(
'Looking in links: {}'.format(', '.join(
redact_password_from_url(url) for url in self.find_links))
=======
redacted_index_urls = []
if self.index_urls and self.index_urls != [PyPI.simple_url]:
for url in self.index_urls:
redacted_index_url = redact_auth_from_url(url)
# Parse the URL
purl = urllib_parse.urlsplit(redacted_index_url)
# URL is generally invalid if scheme and netloc is missing
# there are issues with Python and URL parsing, so this test
# is a bit crude. See bpo-20271, bpo-23505. Python doesn't
# always parse invalid URLs correctly - it should raise
# exceptions for malformed URLs
if not purl.scheme and not purl.netloc:
logger.warning(
'The index url "{}" seems invalid, '
'please provide a scheme.'.format(redacted_index_url))
redacted_index_urls.append(redacted_index_url)
lines.append('Looking in indexes: {}'.format(
', '.join(redacted_index_urls)))