Python charset.Charset方法代码示例

# 需要导入模块: from future.backports.email import charset [as 别名]
# 或者: from future.backports.email.charset import Charset [as 别名]
def make_header(decoded_seq, maxlinelen=None, header_name=None,
                continuation_ws=' '):
    """Create a Header from a sequence of pairs as returned by decode_header()

    decode_header() takes a header value string and returns a sequence of
    pairs of the format (decoded_string, charset) where charset is the string
    name of the character set.

    This function takes one of those sequence of pairs and returns a Header
    instance.  Optional maxlinelen, header_name, and continuation_ws are as in
    the Header constructor.
    """
    h = Header(maxlinelen=maxlinelen, header_name=header_name,
               continuation_ws=continuation_ws)
    for s, charset in decoded_seq:
        # None means us-ascii but we can simply pass it on to h.append()
        if charset is not None and not isinstance(charset, Charset):
            charset = Charset(charset)
        h.append(s, charset)
    return h 

# 需要导入模块: from future.backports.email import charset [as 别名]
# 或者: from future.backports.email.charset import Charset [as 别名]
def formataddr(pair, charset='utf-8'):
    """The inverse of parseaddr(), this takes a 2-tuple of the form
    (realname, email_address) and returns the string value suitable
    for an RFC 2822 From, To or Cc header.

    If the first element of pair is false, then the second element is
    returned unmodified.

    Optional charset if given is the character set that is used to encode
    realname in case realname is not ASCII safe.  Can be an instance of str or
    a Charset-like object which has a header_encode method.  Default is
    'utf-8'.
    """
    name, address = pair
    # The address MUST (per RFC) be ascii, so raise an UnicodeError if it isn't.
    address.encode('ascii')
    if name:
        try:
            name.encode('ascii')
        except UnicodeEncodeError:
            if isinstance(charset, str):
                charset = Charset(charset)
            encoded_name = charset.header_encode(name)
            return "%s <%s>" % (encoded_name, address)
        else:
            quotes = ''
            if specialsre.search(name):
                quotes = '"'
            name = escapesre.sub(r'\\\g<0>', name)
            return '%s%s%s <%s>' % (quotes, name, quotes, address)
    return address 

# 需要导入模块: from future.backports.email import charset [as 别名]
# 或者: from future.backports.email.charset import Charset [as 别名]
def _formatparam(param, value=None, quote=True):
    """Convenience function to format and return a key=value pair.

    This will quote the value if needed or if quote is true.  If value is a
    three tuple (charset, language, value), it will be encoded according
    to RFC2231 rules.  If it contains non-ascii characters it will likewise
    be encoded according to RFC2231 rules, using the utf-8 charset and
    a null language.
    """
    if value is not None and len(value) > 0:
        # A tuple is used for RFC 2231 encoded parameter values where items
        # are (charset, language, value).  charset is a string, not a Charset
        # instance.  RFC 2231 encoded values are never quoted, per RFC.
        if isinstance(value, tuple):
            # Encode as per RFC 2231
            param += '*'
            value = utils.encode_rfc2231(value[2], value[0], value[1])
            return '%s=%s' % (param, value)
        else:
            try:
                value.encode('ascii')
            except UnicodeEncodeError:
                param += '*'
                value = utils.encode_rfc2231(value, 'utf-8', '')
                return '%s=%s' % (param, value)
        # BAW: Please check this.  I think that if quote is set it should
        # force quoting even if not necessary.
        if quote or tspecials.search(value):
            return '%s="%s"' % (param, utils.quote(value))
        else:
            return '%s=%s' % (param, value)
    else:
        return param 

# 需要导入模块: from future.backports.email import charset [as 别名]
# 或者: from future.backports.email.charset import Charset [as 别名]
def get_charset(self):
        """Return the Charset instance associated with the message's payload.
        """
        return self._charset

    #
    # MAPPING INTERFACE (partial)
    # 

# 需要导入模块: from future.backports.email import charset [as 别名]
# 或者: from future.backports.email.charset import Charset [as 别名]
def set_charset(self, charset):
        """Set the charset of the payload to a given character set.

        charset can be a Charset instance, a string naming a character set, or
        None.  If it is a string it will be converted to a Charset instance.
        If charset is None, the charset parameter will be removed from the
        Content-Type field.  Anything else will generate a TypeError.

        The message will be assumed to be of type text/* encoded with
        charset.input_charset.  It will be converted to charset.output_charset
        and encoded properly, if needed, when generating the plain text
        representation of the message.  MIME headers (MIME-Version,
        Content-Type, Content-Transfer-Encoding) will be added as needed.
        """
        if charset is None:
            self.del_param('charset')
            self._charset = None
            return
        if not isinstance(charset, Charset):
            charset = Charset(charset)
        self._charset = charset
        if 'MIME-Version' not in self:
            self.add_header('MIME-Version', '1.0')
        if 'Content-Type' not in self:
            self.add_header('Content-Type', 'text/plain',
                            charset=charset.get_output_charset())
        else:
            self.set_param('charset', charset.get_output_charset())
        if charset != charset.get_output_charset():
            self._payload = charset.body_encode(self._payload)
        if 'Content-Transfer-Encoding' not in self:
            cte = charset.get_body_encoding()
            try:
                cte(self)
            except TypeError:
                self._payload = charset.body_encode(self._payload)
                self.add_header('Content-Transfer-Encoding', cte)