Python email.message_from_string() Examples

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, and is
        # documented as working this way.
        bytesdata = b'\xfa\xfb\xfc\xfd\xfe\xff'
        msg = MIMEApplication(bytesdata, _encoder=encoders.encode_noop)
        self.assertEqual(msg.get_payload(), bytesdata)
        self.assertEqual(msg.get_payload(decode=True), bytesdata)
        s = StringIO()
        g = Generator(s)
        g.flatten(msg)
        wireform = s.getvalue()
        msg2 = email.message_from_string(wireform)
        self.assertEqual(msg.get_payload(), bytesdata)
        self.assertEqual(msg2.get_payload(decode=True), bytesdata)


# Test the basic MIMEText class 

def test_boundary_with_leading_space(self):
        eq = self.assertEqual
        msg = email.message_from_string('''\
MIME-Version: 1.0
Content-Type: multipart/mixed; boundary="    XXXX"

--    XXXX
Content-Type: text/plain


--    XXXX
Content-Type: text/plain

--    XXXX--
''')
        self.assertTrue(msg.is_multipart())
        eq(msg.get_boundary(), '    XXXX')
        eq(len(msg.get_payload()), 2) 

def test_split_long_continuation(self):
        eq = self.ndiffAssertEqual
        msg = email.message_from_string("""\
Subject: bug demonstration
\t12345678911234567892123456789312345678941234567895123456789612345678971234567898112345678911234567892123456789112345678911234567892123456789
\tmore text

test
""")
        sfp = StringIO()
        g = Generator(sfp)
        g.flatten(msg)
        eq(sfp.getvalue(), """\
Subject: bug demonstration
 12345678911234567892123456789312345678941234567895123456789612345678971234567898112345678911234567892123456789112345678911234567892123456789
 more text

test
""") 

def test_message_from_string_with_class(self):
        fp = openfile('msg_01.txt')
        try:
            text = fp.read()
        finally:
            fp.close()
        # Create a subclass
        class MyMessage(Message):
            pass

        msg = email.message_from_string(text, MyMessage)
        self.assertIsInstance(msg, MyMessage)
        # Try something more complicated
        fp = openfile('msg_02.txt')
        try:
            text = fp.read()
        finally:
            fp.close()
        msg = email.message_from_string(text, MyMessage)
        for subpart in msg.walk():
            self.assertIsInstance(subpart, MyMessage) 

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_whitespace_continuation(self):
        eq = self.assertEqual
        # This message contains a line after the Subject: header that has only
        # whitespace, but it is not empty!
        msg = email.message_from_string("""\
From: aperson@dom.ain
To: bperson@dom.ain
Subject: the next line has a space on it
\x20
Date: Mon, 8 Apr 2002 15:09:19 -0400
Message-ID: spam

Here's the message body
""")
        eq(msg['subject'], 'the next line has a space on it\n ')
        eq(msg['message-id'], 'spam')
        eq(msg.get_payload(), "Here's the message body\n") 

def test_split_long_continuation(self):
        eq = self.ndiffAssertEqual
        msg = email.message_from_string("""\
Subject: bug demonstration
\t12345678911234567892123456789312345678941234567895123456789612345678971234567898112345678911234567892123456789112345678911234567892123456789
\tmore text

test
""")
        sfp = StringIO()
        g = Generator(sfp)
        g.flatten(msg)
        eq(sfp.getvalue(), """\
Subject: bug demonstration
 12345678911234567892123456789312345678941234567895123456789612345678971234567898112345678911234567892123456789112345678911234567892123456789
 more text

test
""") 

def test_whitespace_continuation_last_header(self):
        eq = self.assertEqual
        # Like the previous test, but the subject line is the last
        # header.
        msg = email.message_from_string("""\
From: aperson@dom.ain
To: bperson@dom.ain
Date: Mon, 8 Apr 2002 15:09:19 -0400
Message-ID: spam
Subject: the next line has a space on it
\x20

Here's the message body
""")
        eq(msg['subject'], 'the next line has a space on it\n ')
        eq(msg['message-id'], 'spam')
        eq(msg.get_payload(), "Here's the message body\n") 

def test_get_param(self):
        eq = self.assertEqual
        msg = email.message_from_string(
            "X-Header: foo=one; bar=two; baz=three\n")
        eq(msg.get_param('bar', header='x-header'), 'two')
        eq(msg.get_param('quuz', header='x-header'), None)
        eq(msg.get_param('quuz'), None)
        msg = email.message_from_string(
            'X-Header: foo; bar="one"; baz=two\n')
        eq(msg.get_param('foo', header='x-header'), '')
        eq(msg.get_param('bar', header='x-header'), 'one')
        eq(msg.get_param('baz', header='x-header'), 'two')
        # XXX: We are not RFC-2045 compliant!  We cannot parse:
        # msg["Content-Type"] = 'text/plain; weird="hey; dolly? [you] @ <\\"home\\">?"'
        # msg.get_param("weird")
        # yet. 

def test_CRLFLF_at_end_of_part(self):
        # issue 5610: feedparser should not eat two chars from body part ending
        # with "\r\n\n".
        m = (
            "From: foo@bar.com\n"
            "To: baz\n"
            "Mime-Version: 1.0\n"
            "Content-Type: multipart/mixed; boundary=BOUNDARY\n"
            "\n"
            "--BOUNDARY\n"
            "Content-Type: text/plain\n"
            "\n"
            "body ending with CRLF newline\r\n"
            "\n"
            "--BOUNDARY--\n"
          )
        msg = email.message_from_string(m)
        self.assertTrue(msg.get_payload(0).get_payload().endswith('\r\n')) 

def test_boundary_with_leading_space(self):
        eq = self.assertEqual
        msg = email.message_from_string('''\
MIME-Version: 1.0
Content-Type: multipart/mixed; boundary="    XXXX"

--    XXXX
Content-Type: text/plain


--    XXXX
Content-Type: text/plain

--    XXXX--
''')
        self.assertTrue(msg.is_multipart())
        eq(msg.get_boundary(), '    XXXX')
        eq(len(msg.get_payload()), 2) 

def test_binary_body_with_encode_7or8bit(self):
        # Issue 17171.
        bytesdata = b'\xfa\xfb\xfc\xfd\xfe\xff'
        msg = MIMEApplication(bytesdata, _encoder=encoders.encode_7or8bit)
        # Treated as a string, this will be invalid code points.
        self.assertEqual(msg.get_payload(), bytesdata)
        self.assertEqual(msg.get_payload(decode=True), bytesdata)
        self.assertEqual(msg['Content-Transfer-Encoding'], '8bit')
        s = StringIO()
        g = Generator(s)
        g.flatten(msg)
        wireform = s.getvalue()
        msg2 = email.message_from_string(wireform)
        self.assertEqual(msg.get_payload(), bytesdata)
        self.assertEqual(msg2.get_payload(decode=True), bytesdata)
        self.assertEqual(msg2['Content-Transfer-Encoding'], '8bit') 

def test_message_from_string_with_class(self):
        fp = openfile('msg_01.txt')
        try:
            text = fp.read()
        finally:
            fp.close()
        # Create a subclass
        class MyMessage(Message):
            pass

        msg = email.message_from_string(text, MyMessage)
        self.assertIsInstance(msg, MyMessage)
        # Try something more complicated
        fp = openfile('msg_02.txt')
        try:
            text = fp.read()
        finally:
            fp.close()
        msg = email.message_from_string(text, MyMessage)
        for subpart in msg.walk():
            self.assertIsInstance(subpart, MyMessage) 

def test_rfc2231_unencoded_then_encoded_segments(self):
        eq = self.assertEqual
        m = """\
Content-Type: application/x-foo;
\tname*0=\"us-ascii'en-us'My\";
\tname*1*=\" Document\";
\tname*2*=\" For You\"

"""
        msg = email.message_from_string(m)
        charset, language, s = msg.get_param('name')
        eq(charset, 'us-ascii')
        eq(language, 'en-us')
        eq(s, 'My Document For You')



# Tests to ensure that signed parts of an email are completely preserved, as
# required by RFC1847 section 2.1.  Note that these are incomplete, because the
# email package does not currently always preserve the body.  See issue 1670765. 

def test_whitespace_continuation(self):
        eq = self.assertEqual
        # This message contains a line after the Subject: header that has only
        # whitespace, but it is not empty!
        msg = email.message_from_string("""\
From: aperson@dom.ain
To: bperson@dom.ain
Subject: the next line has a space on it
\x20
Date: Mon, 8 Apr 2002 15:09:19 -0400
Message-ID: spam

Here's the message body
""")
        eq(msg['subject'], 'the next line has a space on it\n ')
        eq(msg['message-id'], 'spam')
        eq(msg.get_payload(), "Here's the message body\n") 

def test_rfc2231_bad_encoding_in_filename(self):
        m = '''\
Content-Disposition: inline;
\tfilename*0*="bogus'xx'This%20is%20even%20more%20";
\tfilename*1*="%2A%2A%2Afun%2A%2A%2A%20";
\tfilename*2="is it not.pdf"

'''
        msg = email.message_from_string(m)
        self.assertEqual(msg.get_filename(),
                         'This is even more ***fun*** is it not.pdf') 

def test_rfc2231_partly_nonencoded(self):
        m = '''\
Content-Disposition: inline;
\tfilename*0="This%20is%20even%20more%20";
\tfilename*1="%2A%2A%2Afun%2A%2A%2A%20";
\tfilename*2="is it not.pdf"

'''
        msg = email.message_from_string(m)
        self.assertEqual(
            msg.get_filename(),
            'This%20is%20even%20more%20%2A%2A%2Afun%2A%2A%2A%20is it not.pdf') 

def test_rfc2231_no_language_or_charset_in_boundary(self):
        m = '''\
Content-Type: multipart/alternative;
\tboundary*0*="''This%20is%20even%20more%20";
\tboundary*1*="%2A%2A%2Afun%2A%2A%2A%20";
\tboundary*2="is it not.pdf"

'''
        msg = email.message_from_string(m)
        self.assertEqual(msg.get_boundary(),
                         'This is even more ***fun*** is it not.pdf') 

def test_rfc2231_single_tick_in_filename(self):
        m = """\
Content-Type: application/x-foo; name*0=\"Frank's\"; name*1=\" Document\"

"""
        msg = email.message_from_string(m)
        param = msg.get_param('name')
        self.assertNotIsInstance(param, tuple)
        self.assertEqual(param, "Frank's Document") 

def test_another_long_multiline_header(self):
        eq = self.ndiffAssertEqual
        m = '''\
Received: from siimage.com ([172.25.1.3]) by zima.siliconimage.com with Microsoft SMTPSVC(5.0.2195.4905);
 Wed, 16 Oct 2002 07:41:11 -0700'''
        msg = email.message_from_string(m)
        eq(msg.as_string(), '''\
Received: from siimage.com ([172.25.1.3]) by zima.siliconimage.com with
 Microsoft SMTPSVC(5.0.2195.4905); Wed, 16 Oct 2002 07:41:11 -0700

''') 

def test_get_param_with_semis_in_quotes(self):
        msg = email.message_from_string(
            'Content-Type: image/pjpeg; name="Jim&&Jill"\n')
        self.assertEqual(msg.get_param('name'), 'Jim&&Jill')
        self.assertEqual(msg.get_param('name', unquote=False),
                         '"Jim&&Jill"') 

def test_get_params(self):
        eq = self.assertEqual
        msg = email.message_from_string(
            'X-Header: foo=one; bar=two; baz=three\n')
        eq(msg.get_params(header='x-header'),
           [('foo', 'one'), ('bar', 'two'), ('baz', 'three')])
        msg = email.message_from_string(
            'X-Header: foo; bar=one; baz=two\n')
        eq(msg.get_params(header='x-header'),
           [('foo', ''), ('bar', 'one'), ('baz', 'two')])
        eq(msg.get_params(), None)
        msg = email.message_from_string(
            'X-Header: foo; bar="one"; baz=two\n')
        eq(msg.get_params(header='x-header'),
           [('foo', ''), ('bar', 'one'), ('baz', 'two')]) 

def test_missing_boundary(self):
        msg = email.message_from_string("From: foo\n")
        self.assertEqual(msg.get_boundary(), None) 

def test_bogus_filename(self):
        msg = email.message_from_string(
        "Content-Disposition: blarg; filename\n")
        self.assertEqual(msg.get_filename(), '') 

def test_bad_param(self):
        msg = email.message_from_string("Content-Type: blarg; baz; boo\n")
        self.assertEqual(msg.get_param('baz'), '') 

def _msg_and_obj(self, filename):
        fp = openfile(findfile(filename))
        try:
            original = fp.read()
            msg = email.message_from_string(original)
        finally:
            fp.close()
        return original, msg 

def test_rfc2231_encoded_then_unencoded_segments(self):
        eq = self.assertEqual
        m = """\
Content-Type: application/x-foo;
\tname*0*=\"us-ascii'en-us'My\";
\tname*1=\" Document\";
\tname*2*=\" For You\"

"""
        msg = email.message_from_string(m)
        charset, language, s = msg.get_param('name')
        eq(charset, 'us-ascii')
        eq(language, 'en-us')
        eq(s, 'My Document For You') 

def test_rfc2231_no_extended_values(self):
        eq = self.assertEqual
        m = """\
Content-Type: application/x-foo; name=\"Frank's Document\"

"""
        msg = email.message_from_string(m)
        eq(msg.get_param('name'), "Frank's Document") 

def test_rfc2231_tick_attack_extended(self):
        eq = self.assertEqual
        m = """\
Content-Type: application/x-foo;
\tname*0*=\"us-ascii'en-us'Frank's\"; name*1*=\" Document\"

"""
        msg = email.message_from_string(m)
        charset, language, s = msg.get_param('name')
        eq(charset, 'us-ascii')
        eq(language, 'en-us')
        eq(s, "Frank's Document") 

def test_rfc2231_bad_encoding_in_charset(self):
        m = """\
Content-Type: text/plain; charset*=bogus''utf-8%E2%80%9D

"""
        msg = email.message_from_string(m)
        # This should return None because non-ascii characters in the charset
        # are not allowed.
        self.assertEqual(msg.get_content_charset(), None)