def urlsplit()

in bleach/_vendor/parse.py [0:0]

• 50 lines of code
• 26 McCabe index (conditional complexity)

def urlsplit(url, scheme='', allow_fragments=True):
    """Parse a URL into 5 components:
    <scheme>://<netloc>/<path>?<query>#<fragment>
    Return a 5-tuple: (scheme, netloc, path, query, fragment).
    Note that we don't break the components up in smaller bits
    (e.g. netloc is a single string) and we don't expand % escapes."""
    url, scheme, _coerce_result = _coerce_args(url, scheme)
    url = _remove_unsafe_bytes_from_url(url)
    scheme = _remove_unsafe_bytes_from_url(scheme)
    allow_fragments = bool(allow_fragments)
    key = url, scheme, allow_fragments, type(url), type(scheme)
    cached = _parse_cache.get(key, None)
    if cached:
        return _coerce_result(cached)
    if len(_parse_cache) >= MAX_CACHE_SIZE: # avoid runaway growth
        clear_cache()
    netloc = query = fragment = ''
    i = url.find(':')
    if i > 0:
        if url[:i] == 'http': # optimize the common case
            scheme = url[:i].lower()
            url = url[i+1:]
            if url[:2] == '//':
                netloc, url = _splitnetloc(url, 2)
                if (('[' in netloc and ']' not in netloc) or
                        (']' in netloc and '[' not in netloc)):
                    raise ValueError("Invalid IPv6 URL")
            if allow_fragments and '#' in url:
                url, fragment = url.split('#', 1)
            if '?' in url:
                url, query = url.split('?', 1)
            _checknetloc(netloc)
            v = SplitResult(scheme, netloc, url, query, fragment)
            _parse_cache[key] = v
            return _coerce_result(v)
        for c in url[:i]:
            if c not in scheme_chars:
                break
        else:
            # make sure "url" is not actually a port number (in which case
            # "scheme" is really part of the path)
            rest = url[i+1:]
            if not rest or any(c not in '0123456789' for c in rest):
                # not a port number
                scheme, url = url[:i].lower(), rest

    if url[:2] == '//':
        netloc, url = _splitnetloc(url, 2)
        if (('[' in netloc and ']' not in netloc) or
                (']' in netloc and '[' not in netloc)):
            raise ValueError("Invalid IPv6 URL")
    if allow_fragments and '#' in url:
        url, fragment = url.split('#', 1)
    if '?' in url:
        url, query = url.split('?', 1)
    _checknetloc(netloc)
    v = SplitResult(scheme, netloc, url, query, fragment)
    _parse_cache[key] = v
    return _coerce_result(v)