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))
url = urllib_parse.urljoin('file:', urllib_request.pathname2url(path))
return url
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))
url = urllib_parse.urljoin('file:', urllib_request.pathname2url(path))
return url
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 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 path_to_url(path):
# type: (Union[str, Text]) -> str
"""
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))
url = urllib_parse.urljoin("file:", urllib_request.pathname2url(path))
return url
def _clean_file_url_path(part):
# type: (str) -> str
"""
Clean the first part of a URL path that corresponds to a local
filesystem path (i.e. the first part after splitting on "@" characters).
"""
# We unquote prior to quoting to make sure nothing is double quoted.
# Also, on Windows the path part might contain a drive letter which
# should not be quoted. On Linux where drive letters do not
# exist, the colon should be quoted. We rely on urllib.request
# to do the right thing here.
return urllib_request.pathname2url(urllib_request.url2pathname(part))
def test_get_html_page_directory_append_index(tmpdir):
"""`_get_html_page()` should append "index.html" to a directory URL.
"""
dirpath = tmpdir.mkdir("something")
dir_url = "file:///{}".format(
urllib_request.pathname2url(dirpath).lstrip("/"), )
session = mock.Mock(PipSession)
with mock.patch("pip._internal.collector._get_html_response") as mock_func:
_get_html_page(Link(dir_url), session=session)
assert mock_func.mock_calls == [
mock.call(
"{}/index.html".format(dir_url.rstrip("/")),
session=session,
),
]
def test_get_html_page_directory_append_index(tmpdir):
"""`_get_html_page()` should append "index.html" to a directory URL.
"""
dirpath = tmpdir.mkdir("something")
dir_url = "file:///{}".format(
urllib_request.pathname2url(dirpath).lstrip("/"),
)
session = mock.Mock(PipSession)
with mock.patch("pip._internal.index._get_html_response") as mock_func:
_get_html_page(Link(dir_url), session=session)
assert mock_func.mock_calls == [
mock.call(
"{}/index.html".format(dir_url.rstrip("/")),
session=session,
),
]
def test_get_html_page_directory_append_index(tmpdir):
"""`_get_html_page()` should append "index.html" to a directory URL.
"""
dirpath = tmpdir.mkdir("something")
dir_url = "file:///{}".format(
urllib_request.pathname2url(dirpath).lstrip("/"), )
expected_url = "{}/index.html".format(dir_url.rstrip("/"))
session = mock.Mock(PipSession)
fake_response = make_fake_html_response(expected_url)
with mock.patch("pip._internal.collector._get_html_response") as mock_func:
mock_func.return_value = fake_response
actual = _get_html_page(Link(dir_url), session=session)
assert mock_func.mock_calls == [
mock.call(expected_url, session=session),
], 'actual calls: {}'.format(mock_func.mock_calls)
assert actual.content == fake_response.content
assert actual.encoding is None
assert actual.url == expected_url
def _clean_link(url):
# type: (str) -> str
"""Makes sure a link is fully encoded. That is, if a ' ' shows up in
the link, it will be rewritten to %20 (while not over-quoting
% or other characters)."""
# Split the URL into parts according to the general structure
# `scheme://netloc/path;parameters?query#fragment`. Note that the
# `netloc` can be empty and the URI will then refer to a local
# filesystem path.
result = urllib_parse.urlparse(url)
# In both cases below we unquote prior to quoting to make sure
# nothing is double quoted.
if result.netloc == "":
# On Windows the path part might contain a drive letter which
# should not be quoted. On Linux where drive letters do not
# exist, the colon should be quoted. We rely on urllib.request
# to do the right thing here.
path = urllib_request.pathname2url(
urllib_request.url2pathname(result.path))
else:
path = urllib_parse.quote(urllib_parse.unquote(result.path))
return urllib_parse.urlunparse(result._replace(path=path))
def _clean_link(url):
# type: (str) -> str
"""Makes sure a link is fully encoded. That is, if a ' ' shows up in
the link, it will be rewritten to %20 (while not over-quoting
% or other characters)."""
# Split the URL into parts according to the general structure
# `scheme://netloc/path;parameters?query#fragment`. Note that the
# `netloc` can be empty and the URI will then refer to a local
# filesystem path.
result = urllib_parse.urlparse(url)
# In both cases below we unquote prior to quoting to make sure
# nothing is double quoted.
if result.netloc == "":
# On Windows the path part might contain a drive letter which
# should not be quoted. On Linux where drive letters do not
# exist, the colon should be quoted. We rely on urllib.request
# to do the right thing here.
path = urllib_request.pathname2url(
urllib_request.url2pathname(result.path))
else:
path = urllib_parse.quote(urllib_parse.unquote(result.path))
return urllib_parse.urlunparse(result._replace(path=path))
def test_path_to_url_unix():
assert path_to_url("/tmp/file") == "file:///tmp/file"
path = os.path.join(os.getcwd(), "file")
assert path_to_url("file") == "file://" + urllib_request.pathname2url(path)
def test_path_to_url_unix():
assert path_to_url('/tmp/file') == 'file:///tmp/file'
path = os.path.join(os.getcwd(), 'file')
assert path_to_url('file') == 'file://' + urllib_request.pathname2url(path)
def test_path_to_url_win():
assert path_to_url('c:/tmp/file') == 'file:///C:/tmp/file'
assert path_to_url('c:\\tmp\\file') == 'file:///C:/tmp/file'
assert path_to_url(r'\\unc\as\path') == 'file://unc/as/path'
path = os.path.join(os.getcwd(), 'file')
assert path_to_url('file') == 'file:' + urllib_request.pathname2url(path)
def test_path_to_url_win():
assert path_to_url('c:/tmp/file') == 'file:///C:/tmp/file'
assert path_to_url('c:\\tmp\\file') == 'file:///C:/tmp/file'
assert path_to_url(r'\\unc\as\path') == 'file://unc/as/path'
path = os.path.join(os.getcwd(), 'file')
assert path_to_url('file') == 'file:' + urllib_request.pathname2url(path)
def test_path_to_url_unix():
assert path_to_url('/tmp/file') == 'file:///tmp/file'
path = os.path.join(os.getcwd(), 'file')
assert path_to_url('file') == 'file://' + urllib_request.pathname2url(path)
def test_path_to_url_win():
assert path_to_url("c:/tmp/file") == "file:///C:/tmp/file"
assert path_to_url("c:\\tmp\\file") == "file:///C:/tmp/file"
assert path_to_url(r"\\unc\as\path") == "file://unc/as/path"
path = os.path.join(os.getcwd(), "file")
assert path_to_url("file") == "file:" + urllib_request.pathname2url(path)