gistfile1.py

# Helpers for bytes handling
# For 3.2, we deliberately require applications that
# handle improperly quoted URLs to do their own
# decoding and encoding. If valid use cases are
# presented, we may relax this by using latin-1
# decoding internally for 3.3
_implicit_encoding = 'ascii'
_implicit_errors = 'strict'

def _noop(obj):
    return obj

def _encode_result(obj, encoding=_implicit_encoding,
                        errors=_implicit_errors):
    return obj.encode(encoding, errors)

def _decode_args(args, encoding=_implicit_encoding,
                       errors=_implicit_errors):
    return tuple(x.decode(encoding, errors) if x else '' for x in args)

def _coerce_args(*args):
    # Invokes decode if necessary to create str args
    # and returns the coerced inputs along with
    # an appropriate result coercion function
    #   - noop for str inputs
    #   - encoding function otherwise
    str_input = isinstance(args[0], str)
    for arg in args[1:]:
        # We special-case the empty string to support the
        # "scheme=''" default argument to some functions
        if arg and isinstance(arg, str) != str_input:
            raise TypeError("Cannot mix str and non-str arguments")
    if str_input:
        return args + (_noop,)
    return _decode_args(args) + (_encode_result,)

# Result objects are more helpful than simple tuples
class _ResultMixinStr(object):
    """Standard approach to encoding parsed results from str to bytes"""
    __slots__ = ()

    def encode(self, encoding='ascii', errors='strict'):
        return self._encoded_counterpart(*(x.encode(encoding, errors) for x in self))


class _ResultMixinBytes(object):
    """Standard approach to decoding parsed results from bytes to str"""
    __slots__ = ()

    def decode(self, encoding='ascii', errors='strict'):
        return self._decoded_counterpart(*(x.decode(encoding, errors) for x in self))


class _NetlocResultMixinBase(object):
    """Shared methods for the parsed result objects containing a netloc element"""
    __slots__ = ()

    @property
    def username(self):
        return self._userinfo[0]

    @property
    def password(self):
        return self._userinfo[1]

    @property
    def hostname(self):
        hostname = self._hostinfo[0]
        if not hostname:
            hostname = None
        elif hostname is not None:
            hostname = hostname.lower()
        return hostname

    @property
    def port(self):
        port = self._hostinfo[1]
        if port is not None:
            port = int(port, 10)
            # Return None on an illegal port
            if not ( 0 <= port <= 65535):
                return None
        return port


class _NetlocResultMixinStr(_NetlocResultMixinBase, _ResultMixinStr):
    __slots__ = ()

    @property
    def _userinfo(self):
        netloc = self.netloc
        userinfo, have_info, hostinfo = netloc.rpartition('@')
        if have_info:
            username, have_password, password = userinfo.partition(':')
            if not have_password:
                password = None
        else:
            username = password = None
        return username, password

    @property
    def _hostinfo(self):
        netloc = self.netloc
        _, _, hostinfo = netloc.rpartition('@')
        _, have_open_br, bracketed = hostinfo.partition('[')
        if have_open_br:
            hostname, _, port = bracketed.partition(']')
            _, have_port, port = port.partition(':')
        else:
            hostname, have_port, port = hostinfo.partition(':')
        if not have_port:
            port = None
        return hostname, port


class _NetlocResultMixinBytes(_NetlocResultMixinBase, _ResultMixinBytes):
    __slots__ = ()

    @property
    def _userinfo(self):
        netloc = self.netloc
        userinfo, have_info, hostinfo = netloc.rpartition(b'@')
        if have_info:
            username, have_password, password = userinfo.partition(b':')
            if not have_password:
                password = None
        else:
            username = password = None
        return username, password

    @property
    def _hostinfo(self):
        netloc = self.netloc
        _, _, hostinfo = netloc.rpartition(b'@')
        _, have_open_br, bracketed = hostinfo.partition(b'[')
        if have_open_br:
            hostname, _, port = bracketed.partition(b']')
            _, have_port, port = port.partition(b':')
        else:
            hostname, have_port, port = hostinfo.partition(b':')
        if not have_port:
            port = None
        return hostname, port


from collections import namedtuple

_DefragResultBase = namedtuple('DefragResult', 'url fragment')
_SplitResultBase = namedtuple('SplitResult', 'scheme netloc path query fragment')
_ParseResultBase = namedtuple('ParseResult', 'scheme netloc path params query fragment')

# For backwards compatibility, alias _NetlocResultMixinStr
# ResultBase is no longer part of the documented API, but it is
# retained since deprecating it isn't worth the hassle
ResultBase = _NetlocResultMixinStr

# Structured result objects for string data
class DefragResult(_DefragResultBase, _ResultMixinStr):
    __slots__ = ()
    def geturl(self):
        if self.fragment:
            return self.url + '#' + self.fragment
        else:
            return self.url

class SplitResult(_SplitResultBase, _NetlocResultMixinStr):
    __slots__ = ()
    def geturl(self):
        return urlunsplit(self)

class ParseResult(_ParseResultBase, _NetlocResultMixinStr):
    __slots__ = ()
    def geturl(self):
        return urlunparse(self)

# Structured result objects for bytes data
class DefragResultBytes(_DefragResultBase, _ResultMixinBytes):
    __slots__ = ()
    def geturl(self):
        if self.fragment:
            return self.url + b'#' + self.fragment
        else:
            return self.url

class SplitResultBytes(_SplitResultBase, _NetlocResultMixinBytes):
    __slots__ = ()
    def geturl(self):
        return urlunsplit(self)

class ParseResultBytes(_ParseResultBase, _NetlocResultMixinBytes):
    __slots__ = ()
    def geturl(self):
        return urlunparse(self)

# Set up the encode/decode result pairs
def _fix_result_transcoding():
    _result_pairs = (
        (DefragResult, DefragResultBytes),
        (SplitResult, SplitResultBytes),
        (ParseResult, ParseResultBytes),
    )
    for _decoded, _encoded in _result_pairs:
        _decoded._encoded_counterpart = _encoded
        _encoded._decoded_counterpart = _decoded

_fix_result_transcoding()
del _fix_result_transcoding