def parse_url()

in mlops-template-gitlab/lambda_functions/lambda-seedcode-checkin-gitlab/urllib3/util/url.py [0:0]

• 55 lines of code
• 27 McCabe index (conditional complexity)

def parse_url(url):
    """
    Given a url, return a parsed :class:`.Url` namedtuple. Best-effort is
    performed to parse incomplete urls. Fields not provided will be None.
    This parser is RFC 3986 compliant.

    The parser logic and helper functions are based heavily on
    work done in the ``rfc3986`` module.

    :param str url: URL to parse into a :class:`.Url` namedtuple.

    Partly backwards-compatible with :mod:`urlparse`.

    Example::

        >>> parse_url('http://google.com/mail/')
        Url(scheme='http', host='google.com', port=None, path='/mail/', ...)
        >>> parse_url('google.com:80')
        Url(scheme=None, host='google.com', port=80, path=None, ...)
        >>> parse_url('/foo?bar')
        Url(scheme=None, host=None, port=None, path='/foo', query='bar', ...)
    """
    if not url:
        # Empty
        return Url()

    source_url = url
    if not SCHEME_RE.search(url):
        url = "//" + url

    try:
        scheme, authority, path, query, fragment = URI_RE.match(url).groups()
        normalize_uri = scheme is None or scheme.lower() in NORMALIZABLE_SCHEMES

        if scheme:
            scheme = scheme.lower()

        if authority:
            auth, _, host_port = authority.rpartition("@")
            auth = auth or None
            host, port = _HOST_PORT_RE.match(host_port).groups()
            if auth and normalize_uri:
                auth = _encode_invalid_chars(auth, USERINFO_CHARS)
            if port == "":
                port = None
        else:
            auth, host, port = None, None, None

        if port is not None:
            port = int(port)
            if not (0 <= port <= 65535):
                raise LocationParseError(url)

        host = _normalize_host(host, scheme)

        if normalize_uri and path:
            path = _remove_path_dot_segments(path)
            path = _encode_invalid_chars(path, PATH_CHARS)
        if normalize_uri and query:
            query = _encode_invalid_chars(query, QUERY_CHARS)
        if normalize_uri and fragment:
            fragment = _encode_invalid_chars(fragment, FRAGMENT_CHARS)

    except (ValueError, AttributeError):
        return six.raise_from(LocationParseError(source_url), None)

    # For the sake of backwards compatibility we put empty
    # string values for path if there are any defined values
    # beyond the path in the URL.
    # TODO: Remove this when we break backwards compatibility.
    if not path:
        if query is not None or fragment is not None:
            path = ""
        else:
            path = None

    # Ensure that each part of the URL is a `str` for
    # backwards compatibility.
    if isinstance(url, six.text_type):
        ensure_func = six.ensure_text
    else:
        ensure_func = six.ensure_str

    def ensure_type(x):
        return x if x is None else ensure_func(x)

    return Url(
        scheme=ensure_type(scheme),
        auth=ensure_type(auth),
        host=ensure_type(host),
        port=port,
        path=ensure_type(path),
        query=ensure_type(query),
        fragment=ensure_type(fragment),
    )