charset.py 文件源码

def __init__(self, input_charset=DEFAULT_CHARSET):
        # RFC 2046, $4.1.2 says charsets are not case sensitive.  We coerce to
        # unicode because its .lower() is locale insensitive.  If the argument
        # is already a unicode, we leave it at that, but ensure that the
        # charset is ASCII, as the standard (RFC XXX) requires.
        try:
            if isinstance(input_charset, unicode):
                input_charset.encode('ascii')
            else:
                input_charset = unicode(input_charset, 'ascii')
        except UnicodeError:
            raise errors.CharsetError(input_charset)
        input_charset = input_charset.lower().encode('ascii')
        # Set the input charset after filtering through the aliases and/or codecs
        if not (input_charset in ALIASES or input_charset in CHARSETS):
            try:
                input_charset = codecs.lookup(input_charset).name
            except LookupError:
                pass
        self.input_charset = ALIASES.get(input_charset, input_charset)
        # We can try to guess which encoding and conversion to use by the
        # charset_map dictionary.  Try that first, but let the user override
        # it.
        henc, benc, conv = CHARSETS.get(self.input_charset,
                                        (SHORTEST, BASE64, None))
        if not conv:
            conv = self.input_charset
        # Set the attributes, allowing the arguments to override the default.
        self.header_encoding = henc
        self.body_encoding = benc
        self.output_charset = ALIASES.get(conv, conv)
        # Now set the codecs.  If one isn't defined for input_charset,
        # guess and try a Unicode codec with the same name as input_codec.
        self.input_codec = CODEC_MAP.get(self.input_charset,
                                         self.input_charset)
        self.output_codec = CODEC_MAP.get(self.output_charset,
                                          self.output_charset)