Python email.charset.Charset() Examples

def addr_header_encode(text, header_name=None):
    """Encode and line-wrap the value of an email header field containing
    email addresses."""

    # Convert to unicode, if required.
    if not isinstance(text, unicode):
        text = unicode(text, "utf-8")

    text = ", ".join(
        formataddr((header_encode(name), emailaddr))
        for name, emailaddr in getaddresses([text])
    )

    if is_ascii(text):
        charset = "ascii"
    else:
        charset = "utf-8"

    return Header(
        text, header_name=header_name, charset=Charset(charset)
    ).encode() 

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 

def test_get_body_encoding_with_uppercase_charset(self):
        eq = self.assertEqual
        msg = Message()
        msg['Content-Type'] = 'text/plain; charset=UTF-8'
        eq(msg['content-type'], 'text/plain; charset=UTF-8')
        charsets = msg.get_charsets()
        eq(len(charsets), 1)
        eq(charsets[0], 'utf-8')
        charset = Charset(charsets[0])
        eq(charset.get_body_encoding(), 'base64')
        msg.set_payload('hello world', charset=charset)
        eq(msg.get_payload(), 'aGVsbG8gd29ybGQ=\n')
        eq(msg.get_payload(decode=True), 'hello world')
        eq(msg['content-transfer-encoding'], 'base64')
        # Try another one
        msg = Message()
        msg['Content-Type'] = 'text/plain; charset="US-ASCII"'
        charsets = msg.get_charsets()
        eq(len(charsets), 1)
        eq(charsets[0], 'us-ascii')
        charset = Charset(charsets[0])
        eq(charset.get_body_encoding(), encoders.encode_7or8bit)
        msg.set_payload('hello world', charset=charset)
        eq(msg.get_payload(), 'hello world')
        eq(msg['content-transfer-encoding'], '7bit') 

def test_getset_charset(self):
        eq = self.assertEqual
        msg = Message()
        eq(msg.get_charset(), None)
        charset = Charset('iso-8859-1')
        msg.set_charset(charset)
        eq(msg['mime-version'], '1.0')
        eq(msg.get_content_type(), 'text/plain')
        eq(msg['content-type'], 'text/plain; charset="iso-8859-1"')
        eq(msg.get_param('charset'), 'iso-8859-1')
        eq(msg['content-transfer-encoding'], 'quoted-printable')
        eq(msg.get_charset().input_charset, 'iso-8859-1')
        # Remove the charset
        msg.set_charset(None)
        eq(msg.get_charset(), None)
        eq(msg['content-type'], 'text/plain')
        # Try adding a charset when there's already MIME headers present
        msg = Message()
        msg['MIME-Version'] = '2.0'
        msg['Content-Type'] = 'text/x-weird'
        msg['Content-Transfer-Encoding'] = 'quinted-puntable'
        msg.set_charset(charset)
        eq(msg['mime-version'], '2.0')
        eq(msg['content-type'], 'text/x-weird; charset="iso-8859-1"')
        eq(msg['content-transfer-encoding'], 'quinted-puntable') 

def test__all__(self):
        module = __import__('email')
        # Can't use sorted() here due to Python 2.3 compatibility
        all = module.__all__[:]
        all.sort()
        self.assertEqual(all, [
            # Old names
            'Charset', 'Encoders', 'Errors', 'Generator',
            'Header', 'Iterators', 'MIMEAudio', 'MIMEBase',
            'MIMEImage', 'MIMEMessage', 'MIMEMultipart',
            'MIMENonMultipart', 'MIMEText', 'Message',
            'Parser', 'Utils', 'base64MIME',
            # new names
            'base64mime', 'charset', 'encoders', 'errors', 'generator',
            'header', 'iterators', 'message', 'message_from_file',
            'message_from_string', 'mime', 'parser',
            'quopriMIME', 'quoprimime', 'utils',
            ]) 

def test_charset_richcomparisons(self):
        eq = self.assertEqual
        ne = self.assertNotEqual
        cset1 = Charset()
        cset2 = Charset()
        eq(cset1, 'us-ascii')
        eq(cset1, 'US-ASCII')
        eq(cset1, 'Us-AsCiI')
        eq('us-ascii', cset1)
        eq('US-ASCII', cset1)
        eq('Us-AsCiI', cset1)
        ne(cset1, 'usascii')
        ne(cset1, 'USASCII')
        ne(cset1, 'UsAsCiI')
        ne('usascii', cset1)
        ne('USASCII', cset1)
        ne('UsAsCiI', cset1)
        eq(cset1, cset2)
        eq(cset2, cset1) 

def test_charset_richcomparisons(self):
        eq = self.assertEqual
        ne = self.assertNotEqual
        cset1 = Charset()
        cset2 = Charset()
        eq(cset1, 'us-ascii')
        eq(cset1, 'US-ASCII')
        eq(cset1, 'Us-AsCiI')
        eq('us-ascii', cset1)
        eq('US-ASCII', cset1)
        eq('Us-AsCiI', cset1)
        ne(cset1, 'usascii')
        ne(cset1, 'USASCII')
        ne(cset1, 'UsAsCiI')
        ne('usascii', cset1)
        ne('USASCII', cset1)
        ne('UsAsCiI', cset1)
        eq(cset1, cset2)
        eq(cset2, cset1) 

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 

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 

def test_get_body_encoding_with_uppercase_charset(self):
        eq = self.assertEqual
        msg = Message()
        msg['Content-Type'] = 'text/plain; charset=UTF-8'
        eq(msg['content-type'], 'text/plain; charset=UTF-8')
        charsets = msg.get_charsets()
        eq(len(charsets), 1)
        eq(charsets[0], 'utf-8')
        charset = Charset(charsets[0])
        eq(charset.get_body_encoding(), 'base64')
        msg.set_payload('hello world', charset=charset)
        eq(msg.get_payload(), 'aGVsbG8gd29ybGQ=\n')
        eq(msg.get_payload(decode=True), 'hello world')
        eq(msg['content-transfer-encoding'], 'base64')
        # Try another one
        msg = Message()
        msg['Content-Type'] = 'text/plain; charset="US-ASCII"'
        charsets = msg.get_charsets()
        eq(len(charsets), 1)
        eq(charsets[0], 'us-ascii')
        charset = Charset(charsets[0])
        eq(charset.get_body_encoding(), encoders.encode_7or8bit)
        msg.set_payload('hello world', charset=charset)
        eq(msg.get_payload(), 'hello world')
        eq(msg['content-transfer-encoding'], '7bit') 

def test_get_body_encoding_with_uppercase_charset(self):
        eq = self.assertEqual
        msg = Message()
        msg['Content-Type'] = 'text/plain; charset=UTF-8'
        eq(msg['content-type'], 'text/plain; charset=UTF-8')
        charsets = msg.get_charsets()
        eq(len(charsets), 1)
        eq(charsets[0], 'utf-8')
        charset = Charset(charsets[0])
        eq(charset.get_body_encoding(), 'base64')
        msg.set_payload('hello world', charset=charset)
        eq(msg.get_payload(), 'aGVsbG8gd29ybGQ=\n')
        eq(msg.get_payload(decode=True), 'hello world')
        eq(msg['content-transfer-encoding'], 'base64')
        # Try another one
        msg = Message()
        msg['Content-Type'] = 'text/plain; charset="US-ASCII"'
        charsets = msg.get_charsets()
        eq(len(charsets), 1)
        eq(charsets[0], 'us-ascii')
        charset = Charset(charsets[0])
        eq(charset.get_body_encoding(), encoders.encode_7or8bit)
        msg.set_payload('hello world', charset=charset)
        eq(msg.get_payload(), 'hello world')
        eq(msg['content-transfer-encoding'], '7bit') 

def test_charset_richcomparisons(self):
        eq = self.assertEqual
        ne = self.assertNotEqual
        cset1 = Charset()
        cset2 = Charset()
        eq(cset1, 'us-ascii')
        eq(cset1, 'US-ASCII')
        eq(cset1, 'Us-AsCiI')
        eq('us-ascii', cset1)
        eq('US-ASCII', cset1)
        eq('Us-AsCiI', cset1)
        ne(cset1, 'usascii')
        ne(cset1, 'USASCII')
        ne(cset1, 'UsAsCiI')
        ne('usascii', cset1)
        ne('USASCII', cset1)
        ne('UsAsCiI', cset1)
        eq(cset1, cset2)
        eq(cset2, cset1) 

def test__all__(self):
        module = __import__('email')
        # Can't use sorted() here due to Python 2.3 compatibility
        all = module.__all__[:]
        all.sort()
        self.assertEqual(all, [
            # Old names
            'Charset', 'Encoders', 'Errors', 'Generator',
            'Header', 'Iterators', 'MIMEAudio', 'MIMEBase',
            'MIMEImage', 'MIMEMessage', 'MIMEMultipart',
            'MIMENonMultipart', 'MIMEText', 'Message',
            'Parser', 'Utils', 'base64MIME',
            # new names
            'base64mime', 'charset', 'encoders', 'errors', 'generator',
            'header', 'iterators', 'message', 'message_from_file',
            'message_from_string', 'mime', 'parser',
            'quopriMIME', 'quoprimime', 'utils',
            ]) 

def test_getset_charset(self):
        eq = self.assertEqual
        msg = Message()
        eq(msg.get_charset(), None)
        charset = Charset('iso-8859-1')
        msg.set_charset(charset)
        eq(msg['mime-version'], '1.0')
        eq(msg.get_content_type(), 'text/plain')
        eq(msg['content-type'], 'text/plain; charset="iso-8859-1"')
        eq(msg.get_param('charset'), 'iso-8859-1')
        eq(msg['content-transfer-encoding'], 'quoted-printable')
        eq(msg.get_charset().input_charset, 'iso-8859-1')
        # Remove the charset
        msg.set_charset(None)
        eq(msg.get_charset(), None)
        eq(msg['content-type'], 'text/plain')
        # Try adding a charset when there's already MIME headers present
        msg = Message()
        msg['MIME-Version'] = '2.0'
        msg['Content-Type'] = 'text/x-weird'
        msg['Content-Transfer-Encoding'] = 'quinted-puntable'
        msg.set_charset(charset)
        eq(msg['mime-version'], '2.0')
        eq(msg['content-type'], 'text/x-weird; charset="iso-8859-1"')
        eq(msg['content-transfer-encoding'], 'quinted-puntable') 

def set_payload(self, payload, charset=None):
        """Set the payload to the given value.

        Optional charset sets the message's default character set.  See
        set_charset() for details.
        """
        if hasattr(payload, 'encode'):
            if charset is None:
                self._payload = payload
                return
            if not isinstance(charset, Charset):
                charset = Charset(charset)
            payload = payload.encode(charset.output_charset)
        if hasattr(payload, 'decode'):
            self._payload = payload.decode('ascii', 'surrogateescape')
        else:
            self._payload = payload
        if charset is not None:
            self.set_charset(charset) 

def test_getset_charset(self):
        eq = self.assertEqual
        msg = Message()
        eq(msg.get_charset(), None)
        charset = Charset('iso-8859-1')
        msg.set_charset(charset)
        eq(msg['mime-version'], '1.0')
        eq(msg.get_content_type(), 'text/plain')
        eq(msg['content-type'], 'text/plain; charset="iso-8859-1"')
        eq(msg.get_param('charset'), 'iso-8859-1')
        eq(msg['content-transfer-encoding'], 'quoted-printable')
        eq(msg.get_charset().input_charset, 'iso-8859-1')
        # Remove the charset
        msg.set_charset(None)
        eq(msg.get_charset(), None)
        eq(msg['content-type'], 'text/plain')
        # Try adding a charset when there's already MIME headers present
        msg = Message()
        msg['MIME-Version'] = '2.0'
        msg['Content-Type'] = 'text/x-weird'
        msg['Content-Transfer-Encoding'] = 'quinted-puntable'
        msg.set_charset(charset)
        eq(msg['mime-version'], '2.0')
        eq(msg['content-type'], 'text/x-weird; charset="iso-8859-1"')
        eq(msg['content-transfer-encoding'], 'quinted-puntable') 

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 

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 

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 

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 

def test__all__(self):
        module = __import__('email')
        # Can't use sorted() here due to Python 2.3 compatibility
        all = module.__all__[:]
        all.sort()
        self.assertEqual(all, [
            # Old names
            'Charset', 'Encoders', 'Errors', 'Generator',
            'Header', 'Iterators', 'MIMEAudio', 'MIMEBase',
            'MIMEImage', 'MIMEMessage', 'MIMEMultipart',
            'MIMENonMultipart', 'MIMEText', 'Message',
            'Parser', 'Utils', 'base64MIME',
            # new names
            'base64mime', 'charset', 'encoders', 'errors', 'generator',
            'header', 'iterators', 'message', 'message_from_file',
            'message_from_string', 'mime', 'parser',
            'quopriMIME', 'quoprimime', 'utils',
            ]) 

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 

def format(self, events, encoding="utf-8"):
        parts = list()
        data = templates.Template.format(self, parts, events)
        parsed = message_from_string(data.encode(encoding))

        charset = Charset(encoding)
        charset.header_encoding = QP

        msg = MIMEMultipart()
        msg.set_charset(charset)
        for key, value in msg.items():
            del parsed[key]
        for key, value in parsed.items():
            msg[key] = value

        for encoded in ["Subject", "Comment"]:
            if encoded not in msg:
                continue
            value = charset.header_encode(msg[encoded])
            del msg[encoded]
            msg[encoded] = value

        del msg['Content-Transfer-Encoding']
        msg['Content-Transfer-Encoding'] = '7bit'

        msg.attach(MIMEText(parsed.get_payload(), "plain", encoding))
        for part in parts:
            msg.attach(part)
        return msg 

def get_charset(self):
        """Return the Charset instance associated with the message's payload.
        """
        return self._charset

    #
    # MAPPING INTERFACE (partial)
    # 

def __init__(self, _text, _subtype='plain', _charset=None):
        """Create a text/* type MIME document.

        _text is the string for this message object.

        _subtype is the MIME sub content type, defaulting to "plain".

        _charset is the character set parameter added to the Content-Type
        header.  This defaults to "us-ascii".  Note that as a side-effect, the
        Content-Transfer-Encoding header will also be set.
        """

        # If no _charset was specified, check to see if there are non-ascii
        # characters present. If not, use 'us-ascii', otherwise use utf-8.
        # XXX: This can be removed once #7304 is fixed.
        if _charset is None:
            try:
                _text.encode('us-ascii')
                _charset = 'us-ascii'
            except UnicodeEncodeError:
                _charset = 'utf-8'
        if isinstance(_charset, Charset):
            _charset = str(_charset)

        MIMENonMultipart.__init__(self, 'text', _subtype,
                                  **{'charset': _charset})

        self.set_payload(_text, _charset) 

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 

def test_japanese_codecs(self):
        eq = self.ndiffAssertEqual
        jcode = "euc-jp"
        gcode = "iso-8859-1"
        j = Charset(jcode)
        g = Charset(gcode)
        h = Header("Hello World!")
        jhello = str(b'\xa5\xcf\xa5\xed\xa1\xbc\xa5\xef\xa1\xbc'
                     b'\xa5\xeb\xa5\xc9\xa1\xaa', jcode)
        ghello = str(b'Gr\xfc\xdf Gott!', gcode)
        h.append(jhello, j)
        h.append(ghello, g)
        # BAW: This used to -- and maybe should -- fold the two iso-8859-1
        # chunks into a single encoded word.  However it doesn't violate the
        # standard to have them as two encoded chunks and maybe it's
        # reasonable <wink> for each .append() call to result in a separate
        # encoded word.
        eq(h.encode(), """\
Hello World! =?iso-2022-jp?b?GyRCJU8lbSE8JW8hPCVrJUkhKhsoQg==?=
 =?iso-8859-1?q?Gr=FC=DF_Gott!?=""")
        eq(decode_header(h.encode()),
           [(b'Hello World! ', None),
            (b'\x1b$B%O%m!<%o!<%k%I!*\x1b(B', 'iso-2022-jp'),
            (b'Gr\xfc\xdf Gott!', gcode)])
        subject_bytes = (b'test-ja \xa4\xd8\xc5\xea\xb9\xc6\xa4\xb5'
            b'\xa4\xec\xa4\xbf\xa5\xe1\xa1\xbc\xa5\xeb\xa4\xcf\xbb\xca\xb2'
            b'\xf1\xbc\xd4\xa4\xce\xbe\xb5\xc7\xa7\xa4\xf2\xc2\xd4\xa4\xc3'
            b'\xa4\xc6\xa4\xa4\xa4\xde\xa4\xb9')
        subject = str(subject_bytes, jcode)
        h = Header(subject, j, header_name="Subject")
        # test a very long header
        enc = h.encode()
        # TK: splitting point may differ by codec design and/or Header encoding
        eq(enc , """\
=?iso-2022-jp?b?dGVzdC1qYSAbJEIkWEVqOUYkNSRsJD8lYSE8JWskTztKGyhC?=
 =?iso-2022-jp?b?GyRCMnE8VCROPjVHJyRyQlQkQyRGJCQkXiQ5GyhC?=""")
        # TK: full decode comparison
        eq(str(h).encode(jcode), subject_bytes) 

def test_japanese_codecs(self):
        eq = self.ndiffAssertEqual
        j = Charset("euc-jp")
        g = Charset("iso-8859-1")
        h = Header("Hello World!")
        jhello = '\xa5\xcf\xa5\xed\xa1\xbc\xa5\xef\xa1\xbc\xa5\xeb\xa5\xc9\xa1\xaa'
        ghello = 'Gr\xfc\xdf Gott!'
        h.append(jhello, j)
        h.append(ghello, g)
        # BAW: This used to -- and maybe should -- fold the two iso-8859-1
        # chunks into a single encoded word.  However it doesn't violate the
        # standard to have them as two encoded chunks and maybe it's
        # reasonable <wink> for each .append() call to result in a separate
        # encoded word.
        eq(h.encode(), """\
Hello World! =?iso-2022-jp?b?GyRCJU8lbSE8JW8hPCVrJUkhKhsoQg==?=
 =?iso-8859-1?q?Gr=FC=DF?= =?iso-8859-1?q?_Gott!?=""")
        eq(decode_header(h.encode()),
           [('Hello World!', None),
            ('\x1b$B%O%m!<%o!<%k%I!*\x1b(B', 'iso-2022-jp'),
            ('Gr\xfc\xdf Gott!', 'iso-8859-1')])
        long = 'test-ja \xa4\xd8\xc5\xea\xb9\xc6\xa4\xb5\xa4\xec\xa4\xbf\xa5\xe1\xa1\xbc\xa5\xeb\xa4\xcf\xbb\xca\xb2\xf1\xbc\xd4\xa4\xce\xbe\xb5\xc7\xa7\xa4\xf2\xc2\xd4\xa4\xc3\xa4\xc6\xa4\xa4\xa4\xde\xa4\xb9'
        h = Header(long, j, header_name="Subject")
        # test a very long header
        enc = h.encode()
        # TK: splitting point may differ by codec design and/or Header encoding
        eq(enc , """\
=?iso-2022-jp?b?dGVzdC1qYSAbJEIkWEVqOUYkNSRsJD8lYSE8JWskTztKGyhC?=
 =?iso-2022-jp?b?GyRCMnE8VCROPjVHJyRyQlQkQyRGJCQkXiQ5GyhC?=""")
        # TK: full decode comparison
        eq(h.__unicode__().encode('euc-jp'), long) 

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 

def test_get_body_encoding_with_bogus_charset(self):
        charset = Charset('not a charset')
        self.assertEqual(charset.get_body_encoding(), 'base64')