message.py

mallet是自然语言处理、机器学习领域的一个开源项目。

        split on the `=' sign.  The left hand side of the `=' is the key,
        while the right hand side is the value.  If there is no `=' sign in
        the parameter the value is the empty string.  The value is as
        described in the get_param() method.

        Optional failobj is the object to return if there is no Content-Type
        header.  Optional header is the header to search instead of
        Content-Type.  If unquote is True, the value is unquoted.
        """
        missing = []
        params = self._get_params_preserve(missing, header)
        if params is missing:
            return failobj
        if unquote:
            return [(k, _unquotevalue(v)) for k, v in params]
        else:
            return params

    def get_param(self, param, failobj=None, header='content-type',
                  unquote=True):
        """Return the parameter value if found in the Content-Type header.

        Optional failobj is the object to return if there is no Content-Type
        header, or the Content-Type header has no such parameter.  Optional
        header is the header to search instead of Content-Type.

        Parameter keys are always compared case insensitively.  The return
        value can either be a string, or a 3-tuple if the parameter was RFC
        2231 encoded.  When it's a 3-tuple, the elements of the value are of
        the form (CHARSET, LANGUAGE, VALUE), where LANGUAGE may be the empty
        string.  Your application should be prepared to deal with these, and
        can convert the parameter to a Unicode string like so:

            param = msg.get_param('foo')
            if isinstance(param, tuple):
                param = unicode(param[2], param[0])

        In any case, the parameter value (either the returned string, or the
        VALUE item in the 3-tuple) is always unquoted, unless unquote is set
        to False.
        """
        if not self.has_key(header):
            return failobj
        for k, v in self._get_params_preserve(failobj, header):
            if k.lower() == param.lower():
                if unquote:
                    return _unquotevalue(v)
                else:
                    return v
        return failobj

    def set_param(self, param, value, header='Content-Type', requote=True,
                  charset=None, language=''):
        """Set a parameter in the Content-Type header.

        If the parameter already exists in the header, its value will be
        replaced with the new value.

        If header is Content-Type and has not yet been defined for this
        message, it will be set to "text/plain" and the new parameter and
        value will be appended as per RFC 2045.

        An alternate header can specified in the header argument, and all
        parameters will be quoted as necessary unless requote is False.

        If charset is specified, the parameter will be encoded according to RFC
        2231.  Optional language specifies the RFC 2231 language, defaulting
        to the empty string.  Both charset and language should be strings.
        """
        if not isinstance(value, TupleType) and charset:
            value = (charset, language, value)

        if not self.has_key(header) and header.lower() == 'content-type':
            ctype = 'text/plain'
        else:
            ctype = self.get(header)
        if not self.get_param(param, header=header):
            if not ctype:
                ctype = _formatparam(param, value, requote)
            else:
                ctype = SEMISPACE.join(
                    [ctype, _formatparam(param, value, requote)])
        else:
            ctype = ''
            for old_param, old_value in self.get_params(header=header,
                                                        unquote=requote):
                append_param = ''
                if old_param.lower() == param.lower():
                    append_param = _formatparam(param, value, requote)
                else:
                    append_param = _formatparam(old_param, old_value, requote)
                if not ctype:
                    ctype = append_param
                else:
                    ctype = SEMISPACE.join([ctype, append_param])
        if ctype <> self.get(header):
            del self[header]
            self[header] = ctype

    def del_param(self, param, header='content-type', requote=True):
        """Remove the given parameter completely from the Content-Type header.

        The header will be re-written in place without the parameter or its
        value. All values will be quoted as necessary unless requote is
        False.  Optional header specifies an alternative to the Content-Type
        header.
        """
        if not self.has_key(header):
            return
        new_ctype = ''
        for p, v in self.get_params(header, unquote=requote):
            if p.lower() <> param.lower():
                if not new_ctype:
                    new_ctype = _formatparam(p, v, requote)
                else:
                    new_ctype = SEMISPACE.join([new_ctype,
                                                _formatparam(p, v, requote)])
        if new_ctype <> self.get(header):
            del self[header]
            self[header] = new_ctype

    def set_type(self, type, header='Content-Type', requote=True):
        """Set the main type and subtype for the Content-Type header.

        type must be a string in the form "maintype/subtype", otherwise a
        ValueError is raised.

        This method replaces the Content-Type header, keeping all the
        parameters in place.  If requote is False, this leaves the existing
        header's quoting as is.  Otherwise, the parameters will be quoted (the
        default).

        An alternative header can be specified in the header argument.  When
        the Content-Type header is set, we'll always also add a MIME-Version
        header.
        """
        # BAW: should we be strict?
        if not type.count('/') == 1:
            raise ValueError
        # Set the Content-Type, you get a MIME-Version
        if header.lower() == 'content-type':
            del self['mime-version']
            self['MIME-Version'] = '1.0'
        if not self.has_key(header):
            self[header] = type
            return
        params = self.get_params(header, unquote=requote)
        del self[header]
        self[header] = type
        # Skip the first param; it's the old type.
        for p, v in params[1:]:
            self.set_param(p, v, header, requote)

    def get_filename(self, failobj=None):
        """Return the filename associated with the payload if present.

        The filename is extracted from the Content-Disposition header's
        `filename' parameter, and it is unquoted.
        """
        missing = []
        filename = self.get_param('filename', missing, 'content-disposition')
        if filename is missing:
            return failobj
        if isinstance(filename, TupleType):
            # It's an RFC 2231 encoded parameter
            newvalue = _unquotevalue(filename)
            return unicode(newvalue[2], newvalue[0])
        else:
            newvalue = _unquotevalue(filename.strip())
            return newvalue

    def get_boundary(self, failobj=None):
        """Return the boundary associated with the payload if present.

        The boundary is extracted from the Content-Type header's `boundary'
        parameter, and it is unquoted.
        """
        missing = []
        boundary = self.get_param('boundary', missing)
        if boundary is missing:
            return failobj
        if isinstance(boundary, TupleType):
            # RFC 2231 encoded, so decode.  It better end up as ascii
            return unicode(boundary[2], boundary[0]).encode('us-ascii')
        return _unquotevalue(boundary.strip())

    def set_boundary(self, boundary):
        """Set the boundary parameter in Content-Type to 'boundary'.

        This is subtly different than deleting the Content-Type header and
        adding a new one with a new boundary parameter via add_header().  The
        main difference is that using the set_boundary() method preserves the
        order of the Content-Type header in the original message.

        HeaderParseError is raised if the message has no Content-Type header.
        """
        missing = []
        params = self._get_params_preserve(missing, 'content-type')
        if params is missing:
            # There was no Content-Type header, and we don't know what type
            # to set it to, so raise an exception.
            raise Errors.HeaderParseError, 'No Content-Type header found'
        newparams = []
        foundp = False
        for pk, pv in params:
            if pk.lower() == 'boundary':
                newparams.append(('boundary', '"%s"' % boundary))
                foundp = True
            else:
                newparams.append((pk, pv))
        if not foundp:
            # The original Content-Type header had no boundary attribute.
            # Tack one one the end.  BAW: should we raise an exception
            # instead???
            newparams.append(('boundary', '"%s"' % boundary))
        # Replace the existing Content-Type header with the new value
        newheaders = []
        for h, v in self._headers:
            if h.lower() == 'content-type':
                parts = []
                for k, v in newparams:
                    if v == '':
                        parts.append(k)
                    else:
                        parts.append('%s=%s' % (k, v))
                newheaders.append((h, SEMISPACE.join(parts)))

            else:
                newheaders.append((h, v))
        self._headers = newheaders

    try:
        from email._compat22 import walk
    except SyntaxError:
        # Must be using Python 2.1
        from email._compat21 import walk

    def get_content_charset(self, failobj=None):
        """Return the charset parameter of the Content-Type header.

        The returned string is always coerced to lower case.  If there is no
        Content-Type header, or if that header has no charset parameter,
        failobj is returned.
        """
        missing = []
        charset = self.get_param('charset', missing)
        if charset is missing:
            return failobj
        if isinstance(charset, TupleType):
            # RFC 2231 encoded, so decode it, and it better end up as ascii.
            charset = unicode(charset[2], charset[0]).encode('us-ascii')
        # RFC 2046, $4.1.2 says charsets are not case sensitive
        return charset.lower()

    def get_charsets(self, failobj=None):
        """Return a list containing the charset(s) used in this message.

        The returned list of items describes the Content-Type headers'
        charset parameter for this message and all the subparts in its
        payload.

        Each item will either be a string (the value of the charset parameter
        in the Content-Type header of that part) or the value of the
        'failobj' parameter (defaults to None), if the part does not have a
        main MIME type of "text", or the charset is not defined.

        The list will contain one string for each part of the message, plus
        one for the container message (i.e. self), so that a non-multipart
        message will still return a list of length 1.
        """
        return [part.get_content_charset(failobj) for part in self.walk()]