Python email.message_from_bytes() Examples

def test_invalid_8bit_in_non_8bit_cte_uses_replace(self):
        # This is similar to the previous test, but proves that if the 8bit
        # byte is undecodeable in the specified charset, it gets replaced
        # by the unicode 'unknown' character.  Again, this may or may not
        # be the ideal behavior.  Note that if decode=False none of the
        # decoders will get involved, so this is the only test we need
        # for this behavior.
        m = self.bodytest_msg.format(charset='ascii',
                                     cte='quoted-printable',
                                     bodyline='p=C3=B6stál').encode('utf-8')
        msg = email.message_from_bytes(m)
        self.assertEqual(msg.get_payload(), 'p=C3=B6st\uFFFD\uFFFDl\n')
        self.assertEqual(msg.get_payload(decode=True),
                        'pöstál\n'.encode('utf-8'))

    # test_defect_handling:test_invalid_chars_in_base64_payload 

def test_binary_body_with_encode_noop(self):
        # Issue 16564: This does not produce an RFC valid message, since to be
        # valid it should have a CTE of binary.  But the below works in
        # Python2, and is documented as working this way.
        bytesdata = b'\xfa\xfb\xfc\xfd\xfe\xff'
        msg = MIMEApplication(bytesdata, _encoder=encoders.encode_noop)
        # Treated as a string, this will be invalid code points.
        self.assertEqual(msg.get_payload(), '\uFFFD' * len(bytesdata))
        self.assertEqual(msg.get_payload(decode=True), bytesdata)
        s = BytesIO()
        g = BytesGenerator(s)
        g.flatten(msg)
        wireform = s.getvalue()
        msg2 = email.message_from_bytes(wireform)
        self.assertEqual(msg.get_payload(), '\uFFFD' * len(bytesdata))
        self.assertEqual(msg2.get_payload(decode=True), bytesdata) 

def fetch_email(M, msg_id):
    """Returns the given email message as a unicode string."""
    res, data = M.fetch(msg_id, '(RFC822)')
    if res == 'OK':
        # Data here is a list with 1 element containing a tuple
        # whose 2nd element is a long string containing the email
        # The content is a bytes that must be decoded
        raw_msg_txt = data[0][1]
        # In Python3, we call message_from_bytes, but this function doesn't
        # exist in Python 2.
        try:
            msg = email.message_from_bytes(raw_msg_txt)
        except AttributeError:
            msg = email.message_from_string(raw_msg_txt)
        # At this point, we have a message containing bytes (not unicode)
        # fields that will still need to be decoded, ideally according to the
        # character set specified in the message.
        return msg
    else:
        return None 

def __init__(self, message=None):
        """Initialize a Message instance."""
        if isinstance(message, email.message.Message):
            self._become_message(copy.deepcopy(message))
            if isinstance(message, Message):
                message._explain_to(self)
        elif isinstance(message, bytes):
            self._become_message(email.message_from_bytes(message))
        elif isinstance(message, str):
            self._become_message(email.message_from_string(message))
        elif isinstance(message, io.TextIOWrapper):
            self._become_message(email.message_from_file(message))
        elif hasattr(message, "read"):
            self._become_message(email.message_from_binary_file(message))
        elif message is None:
            email.message.Message.__init__(self)
        else:
            raise TypeError('Invalid message type: %s' % type(message)) 

def test_mangled_from_with_bad_bytes(self):
        source = textwrap.dedent("""\
            Content-Type: text/plain; charset="utf-8"
            MIME-Version: 1.0
            Content-Transfer-Encoding: 8bit
            From: aaa@bbb.org

        """).encode('utf-8')
        msg = email.message_from_bytes(source + b'From R\xc3\xb6lli\n')
        b = BytesIO()
        g = BytesGenerator(b, mangle_from_=True)
        g.flatten(msg)
        self.assertEqual(b.getvalue(), source + b'>From R\xc3\xb6lli\n')


# Test the basic MIMEAudio class 

def decrypt(smime: bytes, key: rsa.RSAPrivateKey, serial: Optional[int] = None):
    """Decrypt an S/MIME message using the RSA Private Key given.

    The recipient can be hinted using the serial parameter, otherwise we assume single recipient = the given key.
    """
    string_content = smime.decode('utf8')
    msg: Message = email.message_from_string(string_content)
    assert msg.get_content_type() == 'application/pkcs7-mime'
    assert msg.get_filename() == 'smime.p7m'
    assert msg.get('Content-Description') == 'S/MIME Encrypted Message'

    b64payload = msg.get_payload()
    payload = b64decode(b64payload)
    decrypted_data = decrypt_smime_content(payload, key)
    decrypted_msg: Message = email.message_from_bytes(decrypted_data)

    return decrypted_msg.get_payload() 

def __init__(self, message=None):
        """Initialize a Message instance."""
        if isinstance(message, email.message.Message):
            self._become_message(copy.deepcopy(message))
            if isinstance(message, Message):
                message._explain_to(self)
        elif isinstance(message, bytes):
            self._become_message(email.message_from_bytes(message))
        elif isinstance(message, str):
            self._become_message(email.message_from_string(message))
        elif isinstance(message, io.TextIOWrapper):
            self._become_message(email.message_from_file(message))
        elif hasattr(message, "read"):
            self._become_message(email.message_from_binary_file(message))
        elif message is None:
            email.message.Message.__init__(self)
        else:
            raise TypeError('Invalid message type: %s' % type(message)) 

def test_8bit_in_quopri_body(self):
        # This is non-RFC compliant data...without 'decode' the library code
        # decodes the body using the charset from the headers, and because the
        # source byte really is utf-8 this works.  This is likely to fail
        # against real dirty data (ie: produce mojibake), but the data is
        # invalid anyway so it is as good a guess as any.  But this means that
        # this test just confirms the current behavior; that behavior is not
        # necessarily the best possible behavior.  With 'decode' it is
        # returning the raw bytes, so that test should be of correct behavior,
        # or at least produce the same result that email4 did.
        m = self.bodytest_msg.format(charset='utf-8',
                                     cte='quoted-printable',
                                     bodyline='p=C3=B6stál').encode('utf-8')
        msg = email.message_from_bytes(m)
        self.assertEqual(msg.get_payload(), 'p=C3=B6stál\n')
        self.assertEqual(msg.get_payload(decode=True),
                         'pöstál\n'.encode('utf-8')) 

def __init__(self, message=None):
        """Initialize a Message instance."""
        if isinstance(message, email.message.Message):
            self._become_message(copy.deepcopy(message))
            if isinstance(message, Message):
                message._explain_to(self)
        elif isinstance(message, bytes):
            self._become_message(email.message_from_bytes(message))
        elif isinstance(message, str):
            self._become_message(email.message_from_string(message))
        elif isinstance(message, io.TextIOWrapper):
            self._become_message(email.message_from_file(message))
        elif hasattr(message, "read"):
            self._become_message(email.message_from_binary_file(message))
        elif message is None:
            email.message.Message.__init__(self)
        else:
            raise TypeError('Invalid message type: %s' % type(message)) 

def __init__(self, message=None):
        """Initialize a Message instance."""
        if isinstance(message, email.message.Message):
            self._become_message(copy.deepcopy(message))
            if isinstance(message, Message):
                message._explain_to(self)
        elif isinstance(message, bytes):
            self._become_message(email.message_from_bytes(message))
        elif isinstance(message, str):
            self._become_message(email.message_from_string(message))
        elif isinstance(message, io.TextIOWrapper):
            self._become_message(email.message_from_file(message))
        elif hasattr(message, "read"):
            self._become_message(email.message_from_binary_file(message))
        elif message is None:
            email.message.Message.__init__(self)
        else:
            raise TypeError('Invalid message type: %s' % type(message)) 

def parse(self):
        try:
            if self.message_type == ParserMessageType.STRING:
                msg = email.message_from_string(self.raw_message, Message)
            elif self.message_type == ParserMessageType.BYTES:
                msg = email.message_from_bytes(self.raw_message, Message)
            elif self.message_type == ParserMessageType.BINARY_FILE:
                msg = email.message_from_binary_file(self.raw_message, Message)
            else:
                raise ValueError("Invalid message_type, could not parse message.")
        except Exception:
            raise ParseEmailException

        # Do basic post-processing of the message, checking it for defects or
        # other missing information.
        if msg.defects:
            raise DefectMessageException

        # Add headers used by LEGO
        msg.original_size = len(self.raw_message)
        msg["X-MailFrom"] = self.mail_from

        return msg 

def consume(self, event: Mapping[str, Any]) -> None:
        rcpt_to = event['rcpt_to']
        msg = email.message_from_bytes(
            base64.b64decode(event["msg_base64"]),
            policy=email.policy.default,
        )
        assert isinstance(msg, EmailMessage)  # https://github.com/python/typeshed/issues/2417
        if not is_missed_message_address(rcpt_to):
            # Missed message addresses are one-time use, so we don't need
            # to worry about emails to them resulting in message spam.
            recipient_realm = decode_stream_email_address(rcpt_to)[0].realm
            try:
                rate_limit_mirror_by_realm(recipient_realm)
            except RateLimited:
                logger.warning("MirrorWorker: Rejecting an email from: %s "
                               "to realm: %s - rate limited.",
                               msg['From'], recipient_realm.name)
                return

        mirror_email(msg, rcpt_to=rcpt_to) 

def append_literal(self, data):
        tag, mailbox_name, size = self.append_literal_command
        if data == CRLF:
            if 'UIDPLUS' in self.capabilities:
                self.send_tagged_line(tag, 'OK [APPENDUID %s %s] APPEND completed.' %
                                      (self.uidvalidity, self.server_state.max_uid(self.user_login, mailbox_name)))
            else:
                self.send_tagged_line(tag, 'OK APPEND completed.')
            self.append_literal_command = None
            return

        literal_data, rest = data[:size], data[size:]
        if len(literal_data) < size:
            self.send_tagged_line(self.append_literal_command[0],
                                  'BAD literal length : expected %s but was %s' % (size, len(literal_data)))
            self.append_literal_command = None
        elif rest and rest != CRLF:
            self.send_tagged_line(self.append_literal_command[0],
                                  'BAD literal trailing data : expected CRLF but got %s' % (rest))
        else:
            m = email.message_from_bytes(data)
            self.server_state.add_mail(self.user_login, Mail(m), mailbox_name)

            if rest:
                self.append_literal(rest) 

def handle_sender_email(envelope: Envelope):
    filename = (
        arrow.now().format("YYYY-MM-DD_HH-mm-ss") + "_" + random_string(10) + ".eml"
    )
    filepath = os.path.join(SENDER_DIR, filename)

    with open(filepath, "wb") as f:
        f.write(envelope.original_content)

    LOG.d("Write email to sender at %s", filepath)

    msg = email.message_from_bytes(envelope.original_content)
    orig = get_orig_message_from_bounce(msg)
    if orig:
        LOG.warning(
            "Original message %s -> %s saved at %s", orig["From"], orig["To"], filepath
        )

    return "250 email to sender accepted" 

def msg_as_input(self, msg):
        m = message_from_bytes(msg, policy=policy.SMTP)
        b = io.BytesIO()
        g = BytesGenerator(b)
        g.flatten(m)
        self.assertEqual(b.getvalue(), msg)

    # XXX: spaces are not preserved correctly here yet in the general case. 

def _msgobj(self, filename):
        with openfile(filename, 'rb') as fp:
            data = fp.read()
        data = self.normalize_linesep_regex.sub(self.blinesep, data)
        msg = email.message_from_bytes(data)
        return msg, data 

def test_crlf_flatten(self):
        with openfile('msg_26.txt', 'rb') as fp:
            text = fp.read()
        msg = email.message_from_bytes(text)
        s = BytesIO()
        g = email.generator.BytesGenerator(s)
        g.flatten(msg, linesep='\r\n')
        self.assertEqual(s.getvalue(), text) 

def _bytes_msg(self, bytestring, message=None, policy=None):
        if policy is None:
            policy = self.policy
        if message is None:
            message = self.message
        return email.message_from_bytes(bytestring, message, policy=policy) 

def parser(self, s, *args, **kw):
        return email.message_from_bytes(s.encode(), *args, **kw) 

def test_get_content_type_with_8bit(self):
        msg = email.message_from_bytes(textwrap.dedent("""\
            Content-Type: text/pl\xA7in; charset=utf-8
            """).encode('latin-1'))
        self.assertEqual(msg.get_content_type(), "text/pl\uFFFDin")
        self.assertEqual(msg.get_content_maintype(), "text")
        self.assertEqual(msg.get_content_subtype(), "pl\uFFFDin")

    # test_headerregistry.TestContentTypeHeader.non_ascii_in_params 

def test_decoded_generator_emits_unicode_body(self):
        m = email.message_from_bytes(self.latin_bin_msg)
        out = StringIO()
        email.generator.DecodedGenerator(out).flatten(m)
        #DecodedHeader output contains an extra blank line compared
        #to the input message.  RDM: not sure if this is a bug or not,
        #but it is not specific to the 8bit->7bit conversion.
        self.assertEqual(out.getvalue(),
            self.latin_bin_msg.decode('latin-1')+'\n') 

def test_string_generator_reencodes_to_quopri_when_appropriate(self):
        m = email.message_from_bytes(self.latin_bin_msg)
        self.assertEqual(str(m), self.latin_bin_msg_as7bit) 

def test_bytes_generator_with_unix_from(self):
        # The unixfrom contains a current date, so we can't check it
        # literally.  Just make sure the first word is 'From' and the
        # rest of the message matches the input.
        msg = email.message_from_bytes(self.non_latin_bin_msg)
        out = BytesIO()
        email.generator.BytesGenerator(out).flatten(msg, unixfrom=True)
        lines = out.getvalue().split(b'\n')
        self.assertEqual(lines[0].split()[0], b'From')
        self.assertEqual(b'\n'.join(lines[1:]), self.non_latin_bin_msg) 

def test_str_generator_should_not_mutate_msg_when_handling_8bit(self):
        msg = email.message_from_bytes(self.non_latin_bin_msg)
        out = BytesIO()
        BytesGenerator(out).flatten(msg)
        orig_value = out.getvalue()
        Generator(StringIO()).flatten(msg) # Should not mutate msg!
        out = BytesIO()
        BytesGenerator(out).flatten(msg)
        self.assertEqual(out.getvalue(), orig_value) 

def test_bytes_generator(self):
        msg = email.message_from_bytes(self.non_latin_bin_msg)
        out = BytesIO()
        email.generator.BytesGenerator(out).flatten(msg)
        self.assertEqual(out.getvalue(), self.non_latin_bin_msg) 

def test_get_payload_with_8bit_cte_header(self):
        msg = email.message_from_bytes(textwrap.dedent("""\
            Content-Transfer-Encoding: b\xa7se64
            Content-Type: text/plain; charset=latin-1

            payload
            """).encode('latin-1'))
        self.assertEqual(msg.get_payload(), 'payload\n')
        self.assertEqual(msg.get_payload(decode=True), b'payload\n') 

def test_del_rfc2231_params_with_8bit(self):
        msg = email.message_from_bytes(textwrap.dedent("""\
            Content-Type: text/plain; charset=us-ascii;
             title*=us-ascii'en'This%20is%20not%20f\xa7n"""
             ).encode('latin-1'))
        msg.del_param('title')
        self.assertEqual(msg.get_param('title'), None)
        self.assertEqual(msg.get_content_maintype(), 'text') 

def test_set_rfc2231_params_with_8bit(self):
        msg = email.message_from_bytes(textwrap.dedent("""\
            Content-Type: text/plain; charset=us-ascii;
             title*=us-ascii'en'This%20is%20not%20f\xa7n"""
             ).encode('latin-1'))
        msg.set_param('title', 'test')
        self.assertEqual(msg.get_param('title'), 'test') 

def test_get_rfc2231_params_with_8bit(self):
        msg = email.message_from_bytes(textwrap.dedent("""\
            Content-Type: text/plain; charset=us-ascii;
             title*=us-ascii'en'This%20is%20not%20f\xa7n"""
             ).encode('latin-1'))
        self.assertEqual(msg.get_param('title'),
            ('us-ascii', 'en', 'This is not f\uFFFDn')) 

def getSubject(self, i):
        conn = self.conn
        id_list = conn.search(None, '(UNSEEN)')[1][0].split()
        try:
            email_id = id_list[i]
        except IndexError:
            return None, -1
        data = conn.fetch(email_id, 'BODY.PEEK[HEADER.FIELDS (SUBJECT)]')[1]

        msg = message_from_bytes(data[0][1])
        s, encoding = decode_header(msg['Subject'])[0]
        subject = s if type(s) is str else s.decode(encoding or 'utf-8')
        return subject