예제 #1
0
def get_model():
    """Return a parser for apache2 access.log."""
    new_time_model = SequenceModelElement('time_model', [
        DateTimeModelElement('time', b'[%d/%b/%Y:%H:%M:%S '),
        FixedWordlistDataModelElement('sign', [b'+', b'-']),
        DecimalIntegerValueModelElement('tz'),
        FixedDataModelElement('bracket', b']')
    ])
    host_name_model = VariableByteDataModelElement(
        'host', b'-.01234567890abcdefghijklmnopqrstuvwxyz:')
    identity_model = VariableByteDataModelElement(
        'ident', b'-.01234567890abcdefghijklmnopqrstuvwxyz:')
    user_name_model = VariableByteDataModelElement(
        'user', b'0123456789abcdefghijklmnopqrstuvwxyz.-')
    request_method_model = FixedWordlistDataModelElement(
        'method', [
            b'GET', b'POST', b'PUT', b'HEAD', b'DELETE', b'CONNECT',
            b'OPTIONS', b'TRACE', b'PATCH'
        ])
    request_model = VariableByteDataModelElement(
        'request',
        b'0123456789abcdefghijklmnopqrstuvwxyzABCDEFGHIJKLMNOPQRSTUVWXYZ.-/()[]{}!$%&=<?*+'
    )
    version_model = VariableByteDataModelElement('version', b'0123456789.')
    status_code_model = DecimalIntegerValueModelElement('status')
    size_model = DecimalIntegerValueModelElement('size')
    user_agent_model = VariableByteDataModelElement(
        'useragent',
        b'0123456789abcdefghijklmnopqrstuvwxyzABCDEFGHIJKLMNOPQRSTUVWXYZ.-/()[]{}!$%&=<?*+;:_ '
    )

    whitespace_str = b' '
    model = SequenceModelElement('accesslog', [
        host_name_model,
        FixedDataModelElement('sp0', whitespace_str),
        identity_model,
        FixedDataModelElement('sp1', whitespace_str),
        user_name_model,
        FixedDataModelElement('sp2', whitespace_str),
        new_time_model,
        FixedDataModelElement('sp3', b' "'),
        request_method_model,
        FixedDataModelElement('sp4', whitespace_str),
        request_model,
        FixedDataModelElement('sp5', b' HTTP/'),
        version_model,
        FixedDataModelElement('sp6', b'" '),
        status_code_model,
        FixedDataModelElement('sp7', whitespace_str),
        size_model,
        FixedDataModelElement('sp8', b' "-" "'),
        user_agent_model,
        FixedDataModelElement('sp9', b'"'),
    ])
    return model
예제 #2
0
def get_model():
    """Return a model for su session information messages after any standard logging preamble, e.g. from syslog."""
    type_children = [
        SequenceModelElement('build-stack', [
            FixedDataModelElement('s0', b'building new pluginstance stack: \''),
            DelimitedDataModelElement('stack', b'\''),
            FixedDataModelElement('s1', b'\'')
        ]),
        SequenceModelElement('nfct-event', [
            FixedDataModelElement('s0', b'[DESTROY] ORIG: SRC='),
            IpAddressDataModelElement('osrcip'),
            FixedDataModelElement('s1', b' DST='),
            IpAddressDataModelElement('odstip'),
            FixedDataModelElement('s2', b' PROTO='),
            FixedWordlistDataModelElement('proto', [b'TCP', b'UDP']),
            FixedDataModelElement('s3', b' SPT='),
            DecimalIntegerValueModelElement('ospt'),
            FixedDataModelElement('s4', b' DPT='),
            DecimalIntegerValueModelElement('odpt'),
            FixedDataModelElement('s5', b' PKTS='),
            DecimalIntegerValueModelElement('opkts'),
            FixedDataModelElement('s6', b' BYTES='),
            DecimalIntegerValueModelElement('obytes'),
            FixedDataModelElement('s7', b' , REPLY: SRC='),
            IpAddressDataModelElement('rsrcip'),
            FixedDataModelElement('s8', b' DST='),
            IpAddressDataModelElement('rdstip'),
            FixedDataModelElement('s9', b' PROTO='),
            FixedWordlistDataModelElement('rproto', [b'TCP', b'UDP']),
            FixedDataModelElement('s10', b' SPT='),
            DecimalIntegerValueModelElement('rspt'),
            FixedDataModelElement('s11', b' DPT='),
            DecimalIntegerValueModelElement('rdpt'),
            FixedDataModelElement('s12', b' PKTS='),
            DecimalIntegerValueModelElement('rpkts'),
            FixedDataModelElement('s13', b' BYTES='),
            DecimalIntegerValueModelElement('rbytes'),
            # No additional whitespace from Ubuntu Trusty 14.04 on.
            OptionalMatchModelElement('tail', FixedDataModelElement('s0', b' '))
        ]),
        FixedDataModelElement('nfct-plugin', b'NFCT plugin working in event mode'),
        FixedDataModelElement('reopen', b'reopening capture file'),
        FixedDataModelElement('signal', b'signal received, calling pluginstances'),
        FixedDataModelElement('uidchange', b'Changing UID / GID')
    ]

    # Netflow entry
    model = SequenceModelElement('ulogd', [
        FixedDataModelElement('sname', b'ulogd['),
        DecimalIntegerValueModelElement('pid'),
        FixedDataModelElement('s0', b']: '),
        FirstMatchModelElement('msg', type_children)
    ])
    return model
class SequenceModelElementTest(unittest.TestCase):
    sequence_start = b'The sequence starts with a number: '
    fixed_data_model_element = FixedDataModelElement('fixed', sequence_start)
    decimal_integer_value_model_element = DecimalIntegerValueModelElement(
        'decimal', DecimalIntegerValueModelElement.SIGN_TYPE_NONE, DecimalIntegerValueModelElement.PAD_TYPE_NONE)
    fixed_wordlist_data_model_element = FixedWordlistDataModelElement('wordlist', [b' Euro', b' Dollar', b' Pfund'])
    sequence_model_element = SequenceModelElement(
        'sequence', [fixed_data_model_element, decimal_integer_value_model_element, fixed_wordlist_data_model_element])

    def test1sequence_of_matching_elements(self):
        """A normal sequence of matching elements is tested in this example test case"""
        match_context = MatchContext(b'The sequence starts with a number: 25538 Euro')
        self.assertEqual(self.sequence_model_element.get_match_element(
            'match', match_context).get_match_string(), b'The sequence starts with a number: 25538 Euro')
        self.assertEqual(match_context.match_data, b'')

    def test2sequence_not_matching(self):
        """A normal sequence of elements, which do not match with the expected sequence_model is tested."""
        match_context = MatchContext(b'The sequence starts with a number: 25538 US-Dollar')
        self.assertEqual(self.sequence_model_element.get_match_element('match', match_context), None)
        self.assertEqual(match_context.match_data, b'The sequence starts with a number: 25538 US-Dollar')

    def test3match_context_shorter_than_sequence(self):
        """This test case unit if the sequence_model returns None, when the match_context is too short for a match."""
        match_context = MatchContext(self.sequence_start)
        self.assertEqual(self.sequence_model_element.get_match_element('match', match_context), None)
        self.assertEqual(match_context.match_data, self.sequence_start)
def get_model():
    """Return a model to parse messages from kernel logging."""
    type_children = [
        SequenceModelElement("ipv4-martian", [
            FixedDataModelElement("s0", b"IPv4: martian "),
            FixedWordlistDataModelElement("direction", [b"source", b"destination"]),
            FixedDataModelElement("s1", b" "),
            IpAddressDataModelElement("destination"),
            FixedDataModelElement("s2", b" from "),
            IpAddressDataModelElement("source"),
            FixedDataModelElement("s3", b", on dev "),
            AnyByteDataModelElement("interface")]),
        SequenceModelElement("net-llheader", [
            FixedDataModelElement("s0", b"ll header: "),
            AnyByteDataModelElement("data")
        ]),
        AnyByteDataModelElement("unparsed")
    ]

    model = SequenceModelElement("kernel", [
        FixedDataModelElement("sname", b"kernel: "),
        OptionalMatchModelElement("opt", SequenceModelElement("seq", [
            FixedDataModelElement("opt_s0", b"]"),
            DelimitedDataModelElement("timestamp", b"]"),
            FixedDataModelElement("opt_s1", b"] "),
        ])),
        FirstMatchModelElement("msg", type_children)
    ])
    return model
def get_model():
    """Return a model to parse messages from kernel logging."""
    type_children = [
        SequenceModelElement('ipv4-martian', [
            FixedDataModelElement('s0', b'IPv4: martian '),
            FixedWordlistDataModelElement('direction',
                                          [b'source', b'destination']),
            FixedDataModelElement('s1', b' '),
            IpAddressDataModelElement('destination'),
            FixedDataModelElement('s2', b' from '),
            IpAddressDataModelElement('source'),
            FixedDataModelElement('s3', b', on dev '),
            AnyByteDataModelElement('interface')
        ]),
        SequenceModelElement('net-llheader', [
            FixedDataModelElement('s0', b'll header: '),
            AnyByteDataModelElement('data')
        ]),
        AnyByteDataModelElement('unparsed')
    ]

    model = SequenceModelElement('kernel', [
        FixedDataModelElement('sname', b'kernel: ['),
        DelimitedDataModelElement('timestamp', b']'),
        FixedDataModelElement('s0', b'] '),
        FirstMatchModelElement('msg', type_children)
    ])
    return model
예제 #6
0
def get_model():
    """Return a model to parse Apache Error logs from the AIT-LDS."""
    model = SequenceModelElement('model', [
        FixedDataModelElement('sp1', b'['),
        FixedWordlistDataModelElement('day', [b'Mon', b'Tue', b'Wed', b'Thu', b'Fri', b'Sat', b'Sun']),
        FixedDataModelElement('sp2', b' '),
        DateTimeModelElement('time', b'%b %d %H:%M:%S.%f %Y'),
        FixedDataModelElement('error_str', b'] [:error] [pid '),
        DecimalIntegerValueModelElement('pid'),
        FixedDataModelElement('sp3', b'] [client '),
        IpAddressDataModelElement('client_ip'),
        FixedDataModelElement('colon', b':'),
        DecimalIntegerValueModelElement('client_port'),
        FixedDataModelElement('php', b'] PHP '),
        FirstMatchModelElement('fphp', [
            SequenceModelElement('warning', [
                FixedDataModelElement('warning_str', b'Warning:  '),
                FirstMatchModelElement('warning', [
                    SequenceModelElement('declaration', [
                        FixedDataModelElement('declaration_str', b'Declaration of '),
                        DelimitedDataModelElement('function', b')'),
                        FixedDataModelElement('compatible_str', b') should be compatible with '),
                        DelimitedDataModelElement('function2', b')'),
                        FixedDataModelElement('compatible_str', b') in '),
                        DelimitedDataModelElement('path', b' '),
                        FixedDataModelElement('compatible_str', b' on line '),
                        DecimalIntegerValueModelElement('line'),
                        FixedDataModelElement('referer_str', b', referer: '),
                        AnyByteDataModelElement('referer')]),
                    SequenceModelElement('system', [
                        FixedDataModelElement('system_str', b'system(): Cannot execute a blank command in '),
                        DelimitedDataModelElement('path', b' '),
                        FixedDataModelElement('compatible_str', b' on line '),
                        DecimalIntegerValueModelElement('line')])])]),
            SequenceModelElement('notice', [
                FixedDataModelElement('notice_str', b'Notice:  Undefined index: '),
                DelimitedDataModelElement('command', b' '),
                FixedDataModelElement('sp', b' in '),
                DelimitedDataModelElement('path', b' '),
                FixedDataModelElement('compatible_str', b' on line '),
                DecimalIntegerValueModelElement('line')]),
            SequenceModelElement('deprecated', [
                FixedDataModelElement('deprecated_str', b'Deprecated:  Methods with the same name as their class '
                                      b'will not be constructors in a future version of PHP; '),
                DelimitedDataModelElement('class', b' '),
                FixedDataModelElement('constructor_str', b' has a deprecated constructor in '),
                DelimitedDataModelElement('path', b' '),
                FixedDataModelElement('compatible_str', b' on line '),
                DecimalIntegerValueModelElement('line'),
                FixedDataModelElement('referer_str', b', referer: '),
                AnyByteDataModelElement('referer'),
                ])])])

    return model
예제 #7
0
    def test7get_match_element_match_context_input_validation(self):
        """Check if an exception is raised, when other classes than MatchContext are used in get_match_element."""
        model_element = FixedWordlistDataModelElement(self.id_, self.wordlist)
        data = b"abcdefghijklmnopqrstuvwxyz.!?"
        model_element.get_match_element(self.path, DummyMatchContext(data))
        model_element.get_match_element(self.path, MatchContext(data))

        self.assertRaises(AttributeError, model_element.get_match_element,
                          self.path, MatchElement(None, data, None, None))
        self.assertRaises(AttributeError, model_element.get_match_element,
                          self.path, data)
        self.assertRaises(AttributeError, model_element.get_match_element,
                          self.path, data.decode())
        self.assertRaises(AttributeError, model_element.get_match_element,
                          self.path, 123)
        self.assertRaises(AttributeError, model_element.get_match_element,
                          self.path, 123.22)
        self.assertRaises(AttributeError, model_element.get_match_element,
                          self.path, True)
        self.assertRaises(AttributeError, model_element.get_match_element,
                          self.path, None)
        self.assertRaises(AttributeError, model_element.get_match_element,
                          self.path, [])
        self.assertRaises(AttributeError, model_element.get_match_element,
                          self.path, {"key": MatchContext(data)})
        self.assertRaises(AttributeError, model_element.get_match_element,
                          self.path, set())
        self.assertRaises(AttributeError, model_element.get_match_element,
                          self.path, ())
        self.assertRaises(AttributeError, model_element.get_match_element,
                          self.path, model_element)
예제 #8
0
    def test1sorted_list(self):
        """A valid wordlist is used in this test case. """
        match_context = MatchContext(b'wordlist started with "wordlist"')
        fixed_wordlist_data_model_element = FixedWordlistDataModelElement(
            'wordlist', [b'wordlist', b'word'])
        match_element = fixed_wordlist_data_model_element.get_match_element(
            'match', match_context)
        self.assertEqual(match_element.get_match_string(), b'wordlist')

        match_context = MatchContext(b'words started with "wordlist"')
        fixed_wordlist_data_model_element = FixedWordlistDataModelElement(
            'wordlist', [b'wordlist', b'word'])
        match_element = fixed_wordlist_data_model_element.get_match_element(
            'match', match_context)
        self.assertEqual(match_element.get_match_string(), b'word')

        match_context = MatchContext(b'list started with "wordlist"')
        fixed_wordlist_data_model_element = FixedWordlistDataModelElement(
            'wordlist', [b'wordlist', b'word'])
        match_element = fixed_wordlist_data_model_element.get_match_element(
            'match', match_context)
        self.assertEqual(match_element, None)
예제 #9
0
def get_model():
    """Return a parser for apache2 access.log."""
    new_time_model = DateTimeModelElement("time", b"[%d/%b/%Y:%H:%M:%S%z")
    host_name_model = VariableByteDataModelElement(
        "host", b"-.01234567890abcdefghijklmnopqrstuvwxyz:")
    identity_model = VariableByteDataModelElement(
        "ident", b"-.01234567890abcdefghijklmnopqrstuvwxyz:")
    user_name_model = VariableByteDataModelElement(
        "user", b"0123456789abcdefghijklmnopqrstuvwxyz.-")
    request_method_model = FirstMatchModelElement("fm", [
        FixedDataModelElement("dash", b"-"),
        SequenceModelElement("request", [
            FixedWordlistDataModelElement("method", [
                b"GET", b"POST", b"PUT", b"HEAD", b"DELETE", b"CONNECT",
                b"OPTIONS", b"TRACE", b"PATCH"
            ]),
            FixedDataModelElement("sp5", b" "),
            DelimitedDataModelElement("request", b" ", b"\\"),
            FixedDataModelElement("sp6", b" "),
            DelimitedDataModelElement("version", b'"'),
        ])
    ])
    status_code_model = DecimalIntegerValueModelElement("status")
    size_model = DecimalIntegerValueModelElement("size")

    whitespace_str = b" "
    model = SequenceModelElement("accesslog", [
        host_name_model,
        FixedDataModelElement("sp0", whitespace_str), identity_model,
        FixedDataModelElement("sp1", whitespace_str), user_name_model,
        FixedDataModelElement("sp2", whitespace_str), new_time_model,
        FixedDataModelElement("sp3", b'] "'), request_method_model,
        FixedDataModelElement("sp6", b'" '), status_code_model,
        FixedDataModelElement("sp7", whitespace_str), size_model,
        OptionalMatchModelElement(
            "combined",
            SequenceModelElement("combined", [
                FixedDataModelElement("sp9", b' "'),
                DelimitedDataModelElement("referer", b'"', b"\\"),
                FixedDataModelElement("sp10", b'" "'),
                DelimitedDataModelElement("user_agent", b'"', b"\\"),
                FixedDataModelElement("sp11", b'"')
            ]))
    ])
    return model
예제 #10
0
def get_model():
    """Return a model to parse Apache Access logs from the AIT-LDS."""
    alphabet = b"!'#$%&\"()*+,-./0123456789:;<>?@ABCDEFGHIJKLMNOPQRSTUVWXYZ\\^_`abcdefghijklmnopqrstuvwxyz{|}~=[]"

    model = SequenceModelElement("model", [
        FirstMatchModelElement("client_ip", [
            IpAddressDataModelElement("client_ip"),
            FixedDataModelElement("localhost", b"::1")
        ]),
        FixedDataModelElement("sp1", b" "),
        VariableByteDataModelElement("client_id", alphabet),
        FixedDataModelElement("sp2", b" "),
        VariableByteDataModelElement("user_id", alphabet),
        FixedDataModelElement("sp3", b" ["),
        DateTimeModelElement("time", b"%d/%b/%Y:%H:%M:%S%z"),
        FixedDataModelElement("sp4", b'] "'),
        FirstMatchModelElement("fm", [
            FixedDataModelElement("dash", b"-"),
            SequenceModelElement("request", [
                FixedWordlistDataModelElement("method", [
                    b"GET", b"POST", b"PUT", b"HEAD", b"DELETE", b"CONNECT",
                    b"OPTIONS", b"TRACE", b"PATCH"
                ]),
                FixedDataModelElement("sp5", b" "),
                DelimitedDataModelElement("request", b" ", b"\\"),
                FixedDataModelElement("sp6", b" "),
                DelimitedDataModelElement("version", b'"'),
            ])
        ]),
        FixedDataModelElement("sp7", b'" '),
        DecimalIntegerValueModelElement("status_code"),
        FixedDataModelElement("sp8", b" "),
        DecimalIntegerValueModelElement("content_size"),
        OptionalMatchModelElement(
            "combined",
            SequenceModelElement("combined", [
                FixedDataModelElement("sp9", b' "'),
                DelimitedDataModelElement("referer", b'"', b"\\"),
                FixedDataModelElement("sp10", b'" "'),
                DelimitedDataModelElement("user_agent", b'"', b"\\"),
                FixedDataModelElement("sp11", b'"'),
            ]))
    ])

    return model
예제 #11
0
def get_model():
    """Return a model to parse Apache Access logs from the AIT-LDS."""
    alphabet = b'!"#$%&\'()*+,-./0123456789:;<>?@ABCDEFGHIJKLMNOPQRSTUVWXYZ\\^_`abcdefghijklmnopqrstuvwxyz{|}~=[]'

    model = SequenceModelElement('model', [
        FirstMatchModelElement('client_ip', [
            IpAddressDataModelElement('client_ip'),
            FixedDataModelElement('localhost', b'::1')
            ]),
        FixedDataModelElement('sp1', b' '),
        VariableByteDataModelElement('client_id', alphabet),
        FixedDataModelElement('sp2', b' '),
        VariableByteDataModelElement('user_id', alphabet),
        FixedDataModelElement('sp3', b' ['),
        DateTimeModelElement('time', b'%d/%b/%Y:%H:%M:%S'),
        FixedDataModelElement('sp4', b' +'),
        DecimalIntegerValueModelElement('tz'),
        FixedDataModelElement('sp5', b'] "'),
        FirstMatchModelElement('fm', [
            FixedDataModelElement('dash', b'-'),
            SequenceModelElement('request', [
                FixedWordlistDataModelElement('method', [
                    b'GET', b'POST', b'PUT', b'HEAD', b'DELETE', b'CONNECT', b'OPTIONS', b'TRACE', b'PATCH']),
                FixedDataModelElement('sp6', b' '),
                DelimitedDataModelElement('request', b' ', b'\\'),
                FixedDataModelElement('sp7', b' '),
                DelimitedDataModelElement('version', b'"'),
                ])
            ]),
        FixedDataModelElement('sp8', b'" '),
        DecimalIntegerValueModelElement('status_code'),
        FixedDataModelElement('sp9', b' '),
        DecimalIntegerValueModelElement('content_size'),
        OptionalMatchModelElement(
            'combined', SequenceModelElement('combined', [
                FixedDataModelElement('sp10', b' "'),
                DelimitedDataModelElement('referer', b'"', b'\\'),
                FixedDataModelElement('sp11', b'" "'),
                DelimitedDataModelElement('user_agent', b'"', b'\\'),
                FixedDataModelElement('sp12', b'"'),
                ])),
        ])

    return model
def get_model(user_name_model=None):
    """Return a model to parse a su session information message after any standard logging preamble, e.g. from syslog."""
    if user_name_model is None:
        user_name_model = VariableByteDataModelElement(
            "user", b"0123456789abcdefghijklmnopqrstuvwxyz.-")
    srcuser_name_model = VariableByteDataModelElement(
        "srcuser", b"0123456789abcdefghijklmnopqrstuvwxyz.-")

    type_children = [
        SequenceModelElement("su-good", [
            FixedDataModelElement("s0", b"Successful su for "),
            user_name_model,
            FixedDataModelElement("s1", b" by "), srcuser_name_model
        ]),
        SequenceModelElement("su-good", [
            FixedDataModelElement("s0", b"+ "),
            DelimitedDataModelElement("terminal", b" "),
            FixedDataModelElement("s1", b" "), srcuser_name_model,
            FixedDataModelElement("s2", b":"), user_name_model
        ]),
        SequenceModelElement("pam", [
            FixedDataModelElement("s0", b"pam_unix(su:session): session "),
            FixedWordlistDataModelElement("change", [b"opened", b"closed"]),
            FixedDataModelElement("s1", b" for user "), user_name_model,
            OptionalMatchModelElement(
                "openby",
                SequenceModelElement("userinfo", [
                    FixedDataModelElement("s0", b" by (uid="),
                    DecimalIntegerValueModelElement("uid"),
                    FixedDataModelElement("s1", b")")
                ]))
        ])
    ]

    model = SequenceModelElement("su", [
        FixedDataModelElement("sname", b"su["),
        DecimalIntegerValueModelElement("pid"),
        FixedDataModelElement("s0", b"]: "),
        FirstMatchModelElement("msg", type_children)
    ])
    return model
def get_model(user_name_model=None):
    """Return a model to parse a su session information message after any standard logging preamble, e.g. from syslog."""
    if user_name_model is None:
        user_name_model = VariableByteDataModelElement(
            'user', b'0123456789abcdefghijklmnopqrstuvwxyz.-')
    srcuser_name_model = VariableByteDataModelElement(
        'srcuser', b'0123456789abcdefghijklmnopqrstuvwxyz.-')

    type_children = [
        SequenceModelElement('su-good', [
            FixedDataModelElement('s0', b'Successful su for '),
            user_name_model,
            FixedDataModelElement('s1', b' by '), srcuser_name_model
        ]),
        SequenceModelElement('su-good', [
            FixedDataModelElement('s0', b'+ '),
            DelimitedDataModelElement('terminal', b' '),
            FixedDataModelElement('s1', b' '), srcuser_name_model,
            FixedDataModelElement('s2', b':'), user_name_model
        ]),
        SequenceModelElement('pam', [
            FixedDataModelElement('s0', b'pam_unix(su:session): session '),
            FixedWordlistDataModelElement('change', [b'opened', b'closed']),
            FixedDataModelElement('s1', b' for user '), user_name_model,
            OptionalMatchModelElement(
                'openby',
                SequenceModelElement('userinfo', [
                    FixedDataModelElement('s0', b' by (uid='),
                    DecimalIntegerValueModelElement('uid'),
                    FixedDataModelElement('s1', b')')
                ]))
        ])
    ]

    model = SequenceModelElement('su', [
        FixedDataModelElement('sname', b'su['),
        DecimalIntegerValueModelElement('pid'),
        FixedDataModelElement('s0', b']: '),
        FirstMatchModelElement('msg', type_children)
    ])
    return model
 def test6null_value(self):
     """Test if null values are parsed to "null"."""
     key_parser_dict = {
         "works":
         VariableByteDataModelElement("id", b"abc123"),
         "problem":
         FixedWordlistDataModelElement("wordlist",
                                       [b"allowed value", b"null"])
     }
     data1 = b"""{
         "works": "abc",
         "problem": "allowed value"
     }"""
     data2 = b"""{
         "works": "123",
         "problem": null
     }"""
     json_model_element = JsonModelElement('json', key_parser_dict)
     self.assertIsNotNone(
         json_model_element.get_match_element('match', MatchContext(data1)))
     self.assertIsNotNone(
         json_model_element.get_match_element('match', MatchContext(data2)))
예제 #15
0
def get_model(user_name_model=None):
    """Return a model to parse a cron message logged via syslog after any standard logging preamble, e.g. from syslog."""
    if user_name_model is None:
        user_name_model = VariableByteDataModelElement(
            'user', b'0123456789abcdefghijklmnopqrstuvwxyz.-')

    type_children = [
        SequenceModelElement('exec', [
            FixedDataModelElement('s0', b'('), user_name_model,
            FixedDataModelElement('s1', b') CMD '),
            AnyByteDataModelElement('command')
        ]),
        SequenceModelElement('pam', [
            FixedDataModelElement('s0', b'pam_unix(cron:session): session '),
            FixedWordlistDataModelElement('change', [b'opened', b'closed']),
            FixedDataModelElement('s1', b' for user '), user_name_model,
            OptionalMatchModelElement(
                'openby', FixedDataModelElement('default', b' by (uid=0)'))
        ])
    ]

    model = FirstMatchModelElement('cron', [
        SequenceModelElement('std', [
            FixedDataModelElement('sname', b'CRON['),
            DecimalIntegerValueModelElement('pid'),
            FixedDataModelElement('s0', b']: '),
            FirstMatchModelElement('msgtype', type_children)
        ]),
        SequenceModelElement('low', [
            FixedDataModelElement('sname', b'cron['),
            DecimalIntegerValueModelElement('pid'),
            FixedDataModelElement('s0', b']: (*system*'),
            DelimitedDataModelElement('rname', b') RELOAD ('),
            FixedDataModelElement('s1', b') RELOAD ('),
            DelimitedDataModelElement('fname', b')'),
            FixedDataModelElement('s2', b')'),
        ])
    ])
    return model
예제 #16
0
    def test3get_match_element_valid_match(self):
        """Parse matching substring from MatchContext and check if the MatchContext was updated with all characters."""
        data = b"wordlist, word"
        index = 0
        value = b"wordlist"
        match_context = DummyMatchContext(data)
        fixed_wordlist_dme = FixedWordlistDataModelElement(
            self.id_, self.wordlist)
        match_element = fixed_wordlist_dme.get_match_element(
            self.path, match_context)
        self.compare_match_results(data, match_element, match_context,
                                   self.id_, self.path, value, index, None)

        data = b"word, wordlist"
        index = 1
        value = b"word"
        match_context = DummyMatchContext(data)
        fixed_wordlist_dme = FixedWordlistDataModelElement(
            self.id_, self.wordlist)
        match_element = fixed_wordlist_dme.get_match_element(
            self.path, match_context)
        self.compare_match_results(data, match_element, match_context,
                                   self.id_, self.path, value, index, None)
예제 #17
0
 def test2get_child_elements(self):
     """Test if get_child_elements returns None."""
     fixed_wordlist_dme = FixedWordlistDataModelElement(
         self.id_, self.wordlist)
     self.assertEqual(fixed_wordlist_dme.get_child_elements(), None)
def build_analysis_pipeline(analysis_context):
    """
    Define the function to create pipeline for parsing the log data.
    It has also to define an AtomizerFactory to instruct aminer how to process incoming data streams to create log atoms from them.
    """
    date_format_string = b'%Y-%m-%d %H:%M:%S'
    cron = b' cron['

    # Build the parsing model:

    service_children_disk_report = [
        FixedDataModelElement(
            'Space',
            b' Current Disk Data is: Filesystem     Type  Size  Used Avail Use%'
        ),
        DelimitedDataModelElement('Data', b'%'),
        AnyByteDataModelElement('Rest')
    ]

    service_children_login_details = [
        FixedDataModelElement('User', b'User '),
        DelimitedDataModelElement('Username', b' '),
        FixedWordlistDataModelElement('Status',
                                      [b' logged in', b' logged out']),
        OptionalMatchModelElement(
            'PastTime',
            SequenceModelElement('Time', [
                FixedDataModelElement('Blank', b' '),
                DecimalIntegerValueModelElement('Minutes'),
                FixedDataModelElement('Ago', b' minutes ago.')
            ]))
    ]

    service_children_cron_job = [
        DateTimeModelElement('DTM', date_format_string),
        FixedDataModelElement('UNameSpace1', b' '),
        DelimitedDataModelElement('UName', b' '),
        FixedDataModelElement('UNameSpace2', b' '),
        DelimitedDataModelElement('User', b' '),
        FixedDataModelElement('Cron', cron),
        DecimalIntegerValueModelElement('JobNumber'),
        FixedDataModelElement('Details', b']: Job `cron.daily` started.')
    ]

    service_children_random_time = [
        FixedDataModelElement('Space', b'Random: '),
        DecimalIntegerValueModelElement('Random')
    ]

    service_children_sensors = [
        SequenceModelElement('CPUTemp', [
            FixedDataModelElement('FixedTemp', b'CPU Temp: '),
            DecimalIntegerValueModelElement('Temp'),
            FixedDataModelElement('Degrees', b'\xc2\xb0C')
        ]),
        FixedDataModelElement('Space1', b', '),
        SequenceModelElement('CPUWorkload', [
            FixedDataModelElement('Fixed Workload', b'CPU Workload: '),
            DecimalIntegerValueModelElement('Workload'),
            FixedDataModelElement('Percent', b'%')
        ]),
        FixedDataModelElement('Space2', b', '),
        DateTimeModelElement('DTM', date_format_string)
    ]

    service_children_user_ip_address = [
        FixedDataModelElement('User', b'User '),
        DelimitedDataModelElement('Username', b' '),
        FixedDataModelElement('Action', b' changed IP address to '),
        IpAddressDataModelElement('IP')
    ]

    service_children_cron_job_announcement = [
        DateTimeModelElement('DTM', date_format_string),
        FixedDataModelElement('Space', b' '),
        DelimitedDataModelElement('UName', b' '),
        FixedDataModelElement('Cron', cron),
        DecimalIntegerValueModelElement('JobNumber'),
        FixedDataModelElement('Run', b']: Will run job `'),
        FixedWordlistDataModelElement(
            'CronType',
            [b'cron.daily', b'cron.hourly', b'cron.monthly', b'cron.weekly']),
        FixedDataModelElement('Start Time', b'\' in 5 min.')
    ]

    service_children_cron_job_execution = [
        DateTimeModelElement('DTM', date_format_string),
        FixedDataModelElement('Space1', b' '),
        DelimitedDataModelElement('UName', b' '),
        FixedDataModelElement('Cron', cron),
        DecimalIntegerValueModelElement('JobNumber'),
        FixedDataModelElement('Job', b']: Job `'),
        FixedWordlistDataModelElement(
            'CronType',
            [b'cron.daily', b'cron.hourly', b'cron.monthly', b'cron.weekly']),
        FixedDataModelElement('Started', b'\' started')
    ]

    service_children_parsing_model_element = [
        DateTimeModelElement('DateTimeModelElement',
                             b'Current DateTime: %d.%m.%Y %H:%M:%S'),
        DecimalFloatValueModelElement('DecimalFloatValueModelElement',
                                      value_sign_type='optional'),
        DecimalIntegerValueModelElement('DecimalIntegerValueModelElement',
                                        value_sign_type='optional',
                                        value_pad_type='blank'),
        SequenceModelElement('', [
            DelimitedDataModelElement('DelimitedDataModelElement', b';'),
            FixedDataModelElement('FixedDataModelElement', b';')
        ])
    ]

    # ElementValueBranchModelElement
    fixed_data_me1 = FixedDataModelElement("fixed1", b'match ')
    fixed_data_me2 = FixedDataModelElement("fixed2", b'fixed String')
    fixed_wordlist_data_model_element = FixedWordlistDataModelElement(
        "wordlist", [b'data: ', b'string: '])
    decimal_integer_value_model_element = DecimalIntegerValueModelElement(
        "decimal")

    service_children_parsing_model_element.append(
        ElementValueBranchModelElement(
            'ElementValueBranchModelElement',
            FirstMatchModelElement("first", [
                SequenceModelElement(
                    "seq1",
                    [fixed_data_me1, fixed_wordlist_data_model_element]),
                SequenceModelElement("seq2", [
                    fixed_data_me1, fixed_wordlist_data_model_element,
                    fixed_data_me2
                ])
            ]), "wordlist", {
                0: decimal_integer_value_model_element,
                1: fixed_data_me2
            }))
    service_children_parsing_model_element.append(
        HexStringModelElement('HexStringModelElement'))
    service_children_parsing_model_element.append(
        SequenceModelElement('', [
            FixedDataModelElement('FixedDataModelElement',
                                  b'Gateway IP-Address: '),
            IpAddressDataModelElement('IpAddressDataModelElement')
        ]))
    service_children_parsing_model_element.append(
        MultiLocaleDateTimeModelElement('MultiLocaleDateTimeModelElement',
                                        [(b'%b %d %Y', "de_AT.utf8", None)]))
    service_children_parsing_model_element.append(
        RepeatedElementDataModelElement(
            'RepeatedElementDataModelElement',
            SequenceModelElement('SequenceModelElement', [
                FixedDataModelElement('FixedDataModelElement',
                                      b'drawn number: '),
                DecimalIntegerValueModelElement(
                    'DecimalIntegerValueModelElement')
            ]), 1))
    service_children_parsing_model_element.append(
        VariableByteDataModelElement('VariableByteDataModelElement', b'-@#'))
    service_children_parsing_model_element.append(
        SequenceModelElement('', [
            WhiteSpaceLimitedDataModelElement(
                'WhiteSpaceLimitedDataModelElement'),
            FixedDataModelElement('', b' ')
        ]))

    # The Base64StringModelElement must be just before the AnyByteDataModelElement to avoid unexpected Matches.
    service_children_parsing_model_element.append(
        Base64StringModelElement('Base64StringModelElement'))

    # The OptionalMatchModelElement must be paired with a FirstMatchModelElement because it accepts all data and thus no data gets
    # to the AnyByteDataModelElement. The AnyByteDataModelElement must be last, because all bytes are accepted.
    service_children_parsing_model_element.append(
        OptionalMatchModelElement(
            'OptionalMatchModelElement',
            FirstMatchModelElement('FirstMatchModelElement', [
                FixedDataModelElement('FixedDataModelElement',
                                      b'The-searched-element-was-found!'),
                AnyByteDataModelElement('AnyByteDataModelElement')
            ])))

    parsing_model = FirstMatchModelElement('model', [
        SequenceModelElement('CronAnnouncement',
                             service_children_cron_job_announcement),
        SequenceModelElement('CronExecution',
                             service_children_cron_job_execution),
        SequenceModelElement('DailyCron', service_children_cron_job),
        SequenceModelElement('DiskReport', service_children_disk_report),
        SequenceModelElement('LoginDetails', service_children_login_details),
        DecimalIntegerValueModelElement('Random'),
        SequenceModelElement('RandomTime', service_children_random_time),
        SequenceModelElement('Sensors', service_children_sensors),
        SequenceModelElement('IPAddresses', service_children_user_ip_address),
        FirstMatchModelElement('ParsingME',
                               service_children_parsing_model_element)
    ])

    # Some generic imports.
    from aminer.analysis import AtomFilters

    # Create all global handler lists here and append the real handlers
    # later on.
    # Use this filter to distribute all atoms to the analysis handlers.
    atom_filter = AtomFilters.SubhandlerFilter(None)

    from aminer.analysis.TimestampCorrectionFilters import SimpleMonotonicTimestampAdjust
    simple_monotonic_timestamp_adjust = SimpleMonotonicTimestampAdjust(
        [atom_filter])
    analysis_context.register_component(
        simple_monotonic_timestamp_adjust,
        component_name="SimpleMonotonicTimestampAdjust")

    from aminer.events.StreamPrinterEventHandler import StreamPrinterEventHandler
    stream_printer_event_handler = StreamPrinterEventHandler(analysis_context)
    from aminer.events.SyslogWriterEventHandler import SyslogWriterEventHandler
    syslog_event_handler = SyslogWriterEventHandler(analysis_context)
    from aminer.events.DefaultMailNotificationEventHandler import DefaultMailNotificationEventHandler
    if DefaultMailNotificationEventHandler.CONFIG_KEY_MAIL_TARGET_ADDRESS in analysis_context.aminer_config.config_properties:
        mail_notification_handler = DefaultMailNotificationEventHandler(
            analysis_context)
        analysis_context.register_component(mail_notification_handler,
                                            component_name="MailHandler")
    anomaly_event_handlers = [
        stream_printer_event_handler, syslog_event_handler,
        mail_notification_handler
    ]

    # Now define the AtomizerFactory using the model. A simple line based one is usually sufficient.
    from aminer.input.SimpleByteStreamLineAtomizerFactory import SimpleByteStreamLineAtomizerFactory
    analysis_context.atomizer_factory = SimpleByteStreamLineAtomizerFactory(
        parsing_model, [simple_monotonic_timestamp_adjust],
        anomaly_event_handlers)

    # Just report all unparsed atoms to the event handlers.
    from aminer.analysis.UnparsedAtomHandlers import SimpleUnparsedAtomHandler
    simple_unparsed_atom_handler = SimpleUnparsedAtomHandler(
        anomaly_event_handlers)
    atom_filter.add_handler(simple_unparsed_atom_handler,
                            stop_when_handled_flag=True)
    analysis_context.register_component(simple_unparsed_atom_handler,
                                        component_name="UnparsedHandler")

    from aminer.analysis.TimestampsUnsortedDetector import TimestampsUnsortedDetector
    timestamps_unsorted_detector = TimestampsUnsortedDetector(
        analysis_context.aminer_config, anomaly_event_handlers)
    atom_filter.add_handler(timestamps_unsorted_detector)
    analysis_context.register_component(
        timestamps_unsorted_detector,
        component_name="TimestampsUnsortedDetector")

    from aminer.analysis import Rules
    from aminer.analysis.AllowlistViolationDetector import AllowlistViolationDetector
    allowlist_rules = [
        Rules.OrMatchRule([
            Rules.AndMatchRule([
                Rules.PathExistsMatchRule(
                    '/model/LoginDetails/PastTime/Time/Minutes'),
                Rules.NegationMatchRule(
                    Rules.ValueMatchRule('/model/LoginDetails/Username',
                                         b'root'))
            ]),
            Rules.AndMatchRule([
                Rules.NegationMatchRule(
                    Rules.PathExistsMatchRule(
                        '/model/LoginDetails/PastTime/Time/Minutes')),
                Rules.PathExistsMatchRule('/model/LoginDetails')
            ]),
            Rules.NegationMatchRule(
                Rules.PathExistsMatchRule('/model/LoginDetails'))
        ])
    ]

    # This rule list should trigger, when the line does not look like: User root (logged in, logged out)
    # or User 'username' (logged in, logged out) x minutes ago.
    allowlist_violation_detector = AllowlistViolationDetector(
        analysis_context.aminer_config, allowlist_rules,
        anomaly_event_handlers)
    analysis_context.register_component(allowlist_violation_detector,
                                        component_name="Allowlist")
    atom_filter.add_handler(allowlist_violation_detector)

    from aminer.analysis.NewMatchPathDetector import NewMatchPathDetector
    new_match_path_detector = NewMatchPathDetector(
        analysis_context.aminer_config,
        anomaly_event_handlers,
        auto_include_flag=True)
    analysis_context.register_component(new_match_path_detector,
                                        component_name="NewMatchPath")
    atom_filter.add_handler(new_match_path_detector)

    def tuple_transformation_function(match_value_list):
        """Only allow output of the EnhancedNewMatchPathValueComboDetector after every 10000th element."""
        extra_data = enhanced_new_match_path_value_combo_detector.known_values_dict.get(
            tuple(match_value_list))
        if extra_data is not None:
            mod = 10000
            if (extra_data[2] + 1) % mod == 0:
                enhanced_new_match_path_value_combo_detector.auto_include_flag = False
            else:
                enhanced_new_match_path_value_combo_detector.auto_include_flag = True
        return match_value_list

    from aminer.analysis.EnhancedNewMatchPathValueComboDetector import EnhancedNewMatchPathValueComboDetector
    enhanced_new_match_path_value_combo_detector = EnhancedNewMatchPathValueComboDetector(
        analysis_context.aminer_config,
        ['/model/DailyCron/UName', '/model/DailyCron/JobNumber'],
        anomaly_event_handlers,
        auto_include_flag=True,
        tuple_transformation_function=tuple_transformation_function)
    analysis_context.register_component(
        enhanced_new_match_path_value_combo_detector,
        component_name="EnhancedNewValueCombo")
    atom_filter.add_handler(enhanced_new_match_path_value_combo_detector)

    from aminer.analysis.HistogramAnalysis import HistogramAnalysis, LinearNumericBinDefinition, ModuloTimeBinDefinition, \
        PathDependentHistogramAnalysis
    modulo_time_bin_definition = ModuloTimeBinDefinition(
        86400, 3600, 0, 1, 24, True)
    linear_numeric_bin_definition = LinearNumericBinDefinition(50, 5, 20, True)
    histogram_analysis = HistogramAnalysis(
        analysis_context.aminer_config,
        [('/model/RandomTime/Random', modulo_time_bin_definition),
         ('/model/Random', linear_numeric_bin_definition)], 10,
        anomaly_event_handlers)
    analysis_context.register_component(histogram_analysis,
                                        component_name="HistogramAnalysis")
    atom_filter.add_handler(histogram_analysis)

    path_dependent_histogram_analysis = PathDependentHistogramAnalysis(
        analysis_context.aminer_config, '/model/RandomTime',
        modulo_time_bin_definition, 10, anomaly_event_handlers)
    analysis_context.register_component(
        path_dependent_histogram_analysis,
        component_name="PathDependentHistogramAnalysis")
    atom_filter.add_handler(path_dependent_histogram_analysis)

    from aminer.analysis.MatchValueAverageChangeDetector import MatchValueAverageChangeDetector
    match_value_average_change_detector = MatchValueAverageChangeDetector(
        analysis_context.aminer_config, anomaly_event_handlers, None,
        ['/model/Random'], 100, 10)
    analysis_context.register_component(
        match_value_average_change_detector,
        component_name="MatchValueAverageChange")
    atom_filter.add_handler(match_value_average_change_detector)

    import sys
    from aminer.analysis.MatchValueStreamWriter import MatchValueStreamWriter
    match_value_stream_writer = MatchValueStreamWriter(sys.stdout, [
        '/model/Sensors/CPUTemp', '/model/Sensors/CPUWorkload',
        '/model/Sensors/DTM'
    ], b';', b'')
    analysis_context.register_component(
        match_value_stream_writer, component_name="MatchValueStreamWriter")
    atom_filter.add_handler(match_value_stream_writer)

    from aminer.analysis.NewMatchPathValueComboDetector import NewMatchPathValueComboDetector
    new_match_path_value_combo_detector = NewMatchPathValueComboDetector(
        analysis_context.aminer_config,
        ['/model/IPAddresses/Username', '/model/IPAddresses/IP'],
        anomaly_event_handlers,
        auto_include_flag=True)
    analysis_context.register_component(
        new_match_path_value_combo_detector,
        component_name="NewMatchPathValueCombo")
    atom_filter.add_handler(new_match_path_value_combo_detector)

    from aminer.analysis.NewMatchPathValueDetector import NewMatchPathValueDetector
    new_match_path_value_detector = NewMatchPathValueDetector(
        analysis_context.aminer_config,
        ['/model/DailyCron/JobNumber', '/model/IPAddresses/Username'],
        anomaly_event_handlers,
        auto_include_flag=True)
    analysis_context.register_component(new_match_path_value_detector,
                                        component_name="NewMatchPathValue")
    atom_filter.add_handler(new_match_path_value_detector)

    from aminer.analysis.MissingMatchPathValueDetector import MissingMatchPathValueDetector
    missing_match_path_value_detector = MissingMatchPathValueDetector(
        analysis_context.aminer_config, ['/model/DiskReport/Space'],
        anomaly_event_handlers,
        auto_include_flag=True,
        default_interval=2,
        realert_interval=5)
    analysis_context.register_component(missing_match_path_value_detector,
                                        component_name="MissingMatch")
    atom_filter.add_handler(missing_match_path_value_detector)

    from aminer.analysis.TimeCorrelationDetector import TimeCorrelationDetector
    time_correlation_detector = TimeCorrelationDetector(
        analysis_context.aminer_config,
        anomaly_event_handlers,
        2,
        min_rule_attributes=1,
        max_rule_attributes=5,
        record_count_before_event=70000,
        output_log_line=True)
    analysis_context.register_component(
        time_correlation_detector, component_name="TimeCorrelationDetector")
    atom_filter.add_handler(time_correlation_detector)

    from aminer.analysis.TimeCorrelationViolationDetector import TimeCorrelationViolationDetector, CorrelationRule, EventClassSelector
    cron_job_announcement = CorrelationRule(
        'CronJobAnnouncement',
        5,
        6,
        max_artefacts_a_for_single_b=1,
        artefact_match_parameters=[('/model/CronAnnouncement/JobNumber',
                                    '/model/CronExecution/JobNumber')])
    a_class_selector = EventClassSelector('Announcement',
                                          [cron_job_announcement], None)
    b_class_selector = EventClassSelector('Execution', None,
                                          [cron_job_announcement])
    rules = [
        Rules.PathExistsMatchRule('/model/CronAnnouncement/Run',
                                  a_class_selector),
        Rules.PathExistsMatchRule('/model/CronExecution/Job', b_class_selector)
    ]

    time_correlation_violation_detector = TimeCorrelationViolationDetector(
        analysis_context.aminer_config, rules, anomaly_event_handlers)
    analysis_context.register_component(
        time_correlation_violation_detector,
        component_name="TimeCorrelationViolationDetector")
    atom_filter.add_handler(time_correlation_violation_detector)
class ElementValueBranchModelElementTest(unittest.TestCase):
    """Unittests for the ElementValueBranchModelElement."""

    match = b'match '
    fixed_string = b'fixed String'
    path_to_match = b'match path: /path/to/match'
    match_data = b'match data: 25000'
    match_string = b'match string: fixed String'
    string_path_to_match = b'match string: /path/to/match'

    fixed_data_me1 = FixedDataModelElement("fixed 1", match)
    fixed_data_me2 = FixedDataModelElement("fixed 2", fixed_string)
    fixed_wordlist_data_model_element = FixedWordlistDataModelElement(
        "wordlist", [b'data: ', b'string: '])
    decimal_integer_value_model_element = DecimalIntegerValueModelElement(
        "decimal")
    seq1 = SequenceModelElement(
        "seq1", [fixed_data_me1, fixed_wordlist_data_model_element])
    seq2 = SequenceModelElement(
        "seq2",
        [fixed_data_me1, fixed_wordlist_data_model_element, fixed_data_me2])
    first_match_me = FirstMatchModelElement("first", [seq1, seq2])
    fixed_data_me3 = FixedDataModelElement("fixed 3", path_to_match)

    def test1_match_element_found(self):
        """In this test case different possible parameters are used to obtain a MatchElement successfully."""
        match_context = MatchContext(self.match_data)
        element_value_branch_model_element = ElementValueBranchModelElement(
            "id", self.first_match_me, "wordlist", {
                0: self.decimal_integer_value_model_element,
                1: self.fixed_data_me2
            })
        match_element = element_value_branch_model_element.get_match_element(
            "elementValueBranchME match", match_context)
        self.assertEqual(match_element.get_path(),
                         'elementValueBranchME match/id')
        self.assertEqual(match_element.get_match_string(), self.match_data)
        self.assertEqual(match_element.get_match_object(), self.match_data)
        self.assertEqual(match_element.get_children()[0].get_path(),
                         'elementValueBranchME match/id/first/seq1')
        self.assertEqual(match_element.get_children()[0].get_match_string(),
                         b'match data: ')
        self.assertEqual(match_element.get_children()[0].get_match_object(),
                         b'match data: ')
        self.assertEqual(
            match_element.get_children()[0].get_children()[0].get_path(),
            'elementValueBranchME match/id/first/seq1/fixed 1')
        self.assertEqual(
            match_element.get_children()[0].get_children()
            [0].get_match_string(), self.match)
        self.assertEqual(
            match_element.get_children()[0].get_children()
            [0].get_match_object(), self.match)
        self.assertEqual(
            match_element.get_children()[0].get_children()[0].get_children(),
            None)
        self.assertEqual(
            match_element.get_children()[0].get_children()[1].get_path(),
            'elementValueBranchME match/id/first/seq1/wordlist')
        self.assertEqual(
            match_element.get_children()[0].get_children()
            [1].get_match_string(), b'data: ')
        self.assertEqual(
            match_element.get_children()[0].get_children()
            [1].get_match_object(), 0)
        self.assertEqual(
            match_element.get_children()[0].get_children()[1].get_children(),
            None)
        self.assertEqual(match_element.get_children()[1].get_path(),
                         'elementValueBranchME match/id/decimal')
        self.assertEqual(match_element.get_children()[1].get_match_string(),
                         b'25000')
        self.assertEqual(match_element.get_children()[1].get_match_object(),
                         25000)
        self.assertEqual(match_element.get_children()[1].get_children(), None)

        match_context = MatchContext(self.match_string)
        match_element = element_value_branch_model_element.get_match_element(
            "elementValueBranchME match", match_context)
        self.assertEqual(match_element.get_path(),
                         'elementValueBranchME match/id')
        self.assertEqual(match_element.get_match_string(), self.match_string)
        self.assertEqual(match_element.get_match_object(), self.match_string)
        self.assertEqual(match_element.get_children()[0].get_path(),
                         'elementValueBranchME match/id/first/seq1')
        self.assertEqual(match_element.get_children()[0].get_match_string(),
                         b'match string: ')
        self.assertEqual(match_element.get_children()[0].get_match_object(),
                         b'match string: ')
        self.assertEqual(
            match_element.get_children()[0].get_children()[0].get_path(),
            'elementValueBranchME match/id/first/seq1/fixed 1')
        self.assertEqual(
            match_element.get_children()[0].get_children()
            [0].get_match_string(), self.match)
        self.assertEqual(
            match_element.get_children()[0].get_children()
            [0].get_match_object(), self.match)
        self.assertEqual(
            match_element.get_children()[0].get_children()[0].get_children(),
            None)
        self.assertEqual(
            match_element.get_children()[0].get_children()[1].get_path(),
            'elementValueBranchME match/id/first/seq1/wordlist')
        self.assertEqual(
            match_element.get_children()[0].get_children()
            [1].get_match_string(), b'string: ')
        self.assertEqual(
            match_element.get_children()[0].get_children()
            [1].get_match_object(), 1)
        self.assertEqual(
            match_element.get_children()[0].get_children()[1].get_children(),
            None)
        self.assertEqual(match_element.get_children()[1].get_path(),
                         'elementValueBranchME match/id/fixed 2')
        self.assertEqual(match_element.get_children()[1].get_match_string(),
                         self.fixed_string)
        self.assertEqual(match_element.get_children()[1].get_match_object(),
                         self.fixed_string)
        self.assertEqual(match_element.get_children()[1].get_children(), None)

    def test2_match_element_not_found(self):
        """In this test case all possible ways of not getting a MatchElement successfully are tested."""
        # no modelMatch
        element_value_branch_model_element = ElementValueBranchModelElement(
            "id", self.first_match_me, "wordlist", {
                0: self.decimal_integer_value_model_element,
                1: self.fixed_data_me2
            })
        match_context = MatchContext(self.path_to_match)
        self.assertEqual(
            element_value_branch_model_element.get_match_element(
                'match', match_context), None)
        self.assertEqual(match_context.match_data, self.path_to_match)

        # no matchChildren
        element_value_branch_model_element = ElementValueBranchModelElement(
            "id", self.fixed_data_me3, "wordlist", {
                0: self.decimal_integer_value_model_element,
                1: self.fixed_data_me2
            })
        match_context = MatchContext(self.path_to_match)
        self.assertEqual(
            element_value_branch_model_element.get_match_element(
                'match', match_context), None)
        self.assertEqual(match_context.match_data, self.path_to_match)

        # no branchModel
        element_value_branch_model_element = ElementValueBranchModelElement(
            "id", self.first_match_me, "wordlist",
            {0: self.decimal_integer_value_model_element})
        match_context = MatchContext(self.string_path_to_match)
        self.assertEqual(
            element_value_branch_model_element.get_match_element(
                'match', match_context), None)
        self.assertEqual(match_context.match_data, self.string_path_to_match)

        # no branchMatch
        element_value_branch_model_element = ElementValueBranchModelElement(
            "id", self.first_match_me, "wordlist", {
                0: self.decimal_integer_value_model_element,
                1: self.fixed_data_me2
            })
        match_context = MatchContext(self.string_path_to_match)
        self.assertEqual(
            element_value_branch_model_element.get_match_element(
                'match', match_context), None)
        self.assertEqual(match_context.match_data, self.string_path_to_match)

    def test3_get_child_elements(self):
        """In this test case the functionality of the get_child_elements-method is tested."""
        element_value_branch_model_element = ElementValueBranchModelElement(
            "id", self.first_match_me, "wordlist", {
                0: self.decimal_integer_value_model_element,
                1: self.fixed_data_me2
            })
        self.assertEqual(
            element_value_branch_model_element.get_child_elements(), [
                self.first_match_me, self.decimal_integer_value_model_element,
                self.fixed_data_me2
            ])
예제 #20
0
def get_model(user_name_model=None):
    """Return a model to parse a sshd information message after any standard logging preamble, e.g. from syslog."""
    if user_name_model is None:
        user_name_model = VariableByteDataModelElement(
            "user", b"0123456789abcdefghijklmnopqrstuvwxyz.-")

    from_str = b" from "
    port = b" port "
    preauth = b" [preauth]"

    type_children = [
        SequenceModelElement("accepted key", [
            FixedDataModelElement("s0", b"Accepted publickey for "),
            user_name_model,
            FixedDataModelElement("s1", from_str),
            IpAddressDataModelElement("clientip"),
            FixedDataModelElement("s2", port),
            DecimalIntegerValueModelElement("port"),
            FixedDataModelElement("s3", b" ssh2: "),
            DelimitedDataModelElement(
                "asym-algorithm", b" ", consume_delimiter=True),
            VariableByteDataModelElement(
                "fingerprint",
                b"0123456789abcdefghijklmnopqrstuvwxyzABCDEFGHIJKLMNOPQRSTUVWXYZ+/:"
            ),
            OptionalMatchModelElement(
                "opt",
                SequenceModelElement("seq", [
                    FixedDataModelElement("s4", b" ID "),
                    DelimitedDataModelElement("id", b" "),
                    FixedDataModelElement("s5", b" (serial "),
                    DecimalIntegerValueModelElement("serial"),
                    FixedDataModelElement("s6", b") CA "),
                    AnyByteDataModelElement("algorithm_details")
                ]))
        ]),
        SequenceModelElement("btmp-perm", [
            FixedDataModelElement(
                "s0",
                b"Excess permission or bad ownership on file /var/log/btmp")
        ]),
        SequenceModelElement("close-sess", [
            FixedDataModelElement("s0", b"Close session: user "),
            user_name_model,
            FixedDataModelElement("s1", from_str),
            IpAddressDataModelElement("clientip"),
            FixedDataModelElement("s2", port),
            DecimalIntegerValueModelElement("port"),
            FixedDataModelElement("s3", b" id "),
            DecimalIntegerValueModelElement("userid")
        ]),
        SequenceModelElement("closing", [
            FixedDataModelElement("s0", b"Closing connection to "),
            IpAddressDataModelElement("clientip"),
            FixedDataModelElement("s1", port),
            DecimalIntegerValueModelElement("port")
        ]),
        SequenceModelElement("closed", [
            FixedDataModelElement("s0", b"Connection closed by "),
            FirstMatchModelElement("fm", [
                IpAddressDataModelElement("clientip"),
                SequenceModelElement("seq", [
                    FixedWordlistDataModelElement(
                        "user-type", [b"authenticating", b"invalid"]),
                    FixedDataModelElement("s1", b" user "),
                    DelimitedDataModelElement("user", b" "),
                    FixedDataModelElement("s2", b" "),
                    FirstMatchModelElement("fm", [
                        IpAddressDataModelElement("ip"),
                        IpAddressDataModelElement("ipv6", ipv6=True)
                    ]),
                    FixedDataModelElement("s3", b" port "),
                    DecimalIntegerValueModelElement("port"),
                    FixedDataModelElement("s4", b" [preauth]")
                ])
            ])
        ]),
        SequenceModelElement("connect", [
            FixedDataModelElement("s0", b"Connection from "),
            IpAddressDataModelElement("clientip"),
            FixedDataModelElement("s1", port),
            DecimalIntegerValueModelElement("port"),
            FixedDataModelElement("s2", b" on "),
            IpAddressDataModelElement("serverip"),
            FixedDataModelElement("s3", port),
            DecimalIntegerValueModelElement("sport")
        ]),
        SequenceModelElement("disconnectreq", [
            FixedDataModelElement("s0", b"Received disconnect from "),
            IpAddressDataModelElement("clientip"),
            FixedDataModelElement("s1", port),
            DecimalIntegerValueModelElement("port"),
            FixedDataModelElement("s2", b":"),
            DecimalIntegerValueModelElement("session"),
            FixedDataModelElement("s3", b": "),
            FixedWordlistDataModelElement("reason", [b"disconnected by user"])
        ]),
        SequenceModelElement("disconnected", [
            FixedDataModelElement("s0", b"Disconnected from "),
            IpAddressDataModelElement("clientip"),
            FixedDataModelElement("s1", port),
            DecimalIntegerValueModelElement("port")
        ]),
        FixedDataModelElement("error-bind",
                              b"error: bind: Cannot assign requested address"),
        SequenceModelElement("error-max-auth", [
            FixedDataModelElement(
                "s0", b"error: maximum authentication attempts exceeded for "),
            OptionalMatchModelElement(
                "opt", FixedDataModelElement("invalid", b"invalid user ")),
            DelimitedDataModelElement("user", b" "),
            FixedDataModelElement("s1", b" from "),
            FirstMatchModelElement("fm", [
                IpAddressDataModelElement("from_ip"),
                IpAddressDataModelElement("from_ip_v6", ipv6=True)
            ]),
            FixedDataModelElement("s2", b" port "),
            DecimalIntegerValueModelElement("port"),
            FixedDataModelElement("s3", b" ssh2 [preauth]")
        ]),
        FixedDataModelElement("error-cert-exp",
                              b"error: Certificate invalid: expired"),
        FixedDataModelElement("error-cert-not-yet-valid",
                              b"error: Certificate invalid: not yet valid"),
        FixedDataModelElement(
            "error-cert-not-listed-principal",
            b"error: Certificate invalid: name is not a listed principal"),
        FixedDataModelElement("error-refused-by-options",
                              b"error: Refused by certificate options"),
        SequenceModelElement("error-channel-setup", [
            FixedDataModelElement(
                "s0",
                b"error: channel_setup_fwd_listener: cannot listen to port: "),
            DecimalIntegerValueModelElement("port")
        ]),
        SequenceModelElement("error-auth-key", [
            FixedDataModelElement("s0", b"error: Authentication key "),
            DelimitedDataModelElement("asym-algorithm", b" "),
            FixedDataModelElement("s1", b" "),
            DelimitedDataModelElement("hash", b" "),
            FixedDataModelElement("s2", b" revoked by file "),
            AnyByteDataModelElement("file")
        ]),
        SequenceModelElement("error-load-key", [
            FixedDataModelElement("s0", b"error: Could not load host key: "),
            AnyByteDataModelElement("file")
        ]),
        SequenceModelElement("ident-missing", [
            FixedDataModelElement(
                "s0", b"Did not receive identification string from "),
            IpAddressDataModelElement("clientip")
        ]),
        SequenceModelElement("invalid-user", [
            FixedDataModelElement("s0", b"Invalid user "),
            DelimitedDataModelElement("user", from_str),
            FixedDataModelElement("s1", from_str),
            FirstMatchModelElement("fm", [
                IpAddressDataModelElement("from_ip"),
                IpAddressDataModelElement("from_ip_v6", ipv6=True)
            ]),
            FixedDataModelElement("s2", b" port "),
            DecimalIntegerValueModelElement("port")
        ]),
        SequenceModelElement("invalid-user-auth-req", [
            FixedDataModelElement("s0",
                                  b"input_userauth_request: invalid user "),
            DelimitedDataModelElement("user", preauth),
            FixedDataModelElement("s1", preauth)
        ]),
        SequenceModelElement("postppk", [
            FixedDataModelElement("s0", b"Postponed publickey for "),
            user_name_model,
            FixedDataModelElement("s1", from_str),
            IpAddressDataModelElement("clientip"),
            FixedDataModelElement("s2", port),
            DecimalIntegerValueModelElement("port"),
            FixedDataModelElement("s3", b" ssh2 [preauth]")
        ]),
        SequenceModelElement("readerr", [
            FixedDataModelElement("s0", b"Read error from remote host "),
            IpAddressDataModelElement("clientip"),
            FixedDataModelElement("s1", b": Connection timed out")
        ]),
        SequenceModelElement("disconnect", [
            FixedDataModelElement("s0", b"Received disconnect from "),
            FirstMatchModelElement("fm", [
                IpAddressDataModelElement("from_ip"),
                IpAddressDataModelElement("from_ip_v6", ipv6=True)
            ]),
            FixedDataModelElement("s1", b": 11: "),
            FirstMatchModelElement("reason", [
                FixedDataModelElement("disconnected", b"disconnected by user"),
                SequenceModelElement("remotemsg", [
                    DelimitedDataModelElement("msg", preauth),
                    FixedDataModelElement("s0", preauth)
                ])
            ])
        ]),
        SequenceModelElement("signal", [
            FixedDataModelElement("s0", b"Received signal "),
            DecimalIntegerValueModelElement("signal"),
            FixedDataModelElement("s1", b"; terminating.")
        ]),
        SequenceModelElement("server", [
            FixedDataModelElement("s0", b"Server listening on "),
            DelimitedDataModelElement("serverip", b" "),
            FixedDataModelElement("s1", port),
            DecimalIntegerValueModelElement("port"),
            FixedDataModelElement("s2", b".")
        ]),
        SequenceModelElement("oom-adjust", [
            FixedDataModelElement("s0", b"Set /proc/self/oom_score_adj "),
            OptionalMatchModelElement(
                "from", FixedDataModelElement("default", b"from 0 ")),
            FixedDataModelElement("s1", b"to "),
            DecimalIntegerValueModelElement(
                "newval",
                value_sign_type=DecimalIntegerValueModelElement.
                SIGN_TYPE_OPTIONAL)
        ]),
        SequenceModelElement("session-start", [
            FixedDataModelElement("s0", b"Starting session: "),
            FirstMatchModelElement("sess-info", [
                SequenceModelElement("shell", [
                    FixedDataModelElement("s0", b"shell on "),
                    DelimitedDataModelElement("terminal", b" ")
                ]),
                SequenceModelElement(
                    "subsystem",
                    [FixedDataModelElement("s0", b"subsystem \"sftp\"")]),
                SequenceModelElement("forced-command", [
                    FixedDataModelElement("s0",
                                          b"forced-command (key-option) \""),
                    DelimitedDataModelElement("command", b"\" for "),
                    FixedDataModelElement("s1", b"\"")
                ])
            ]),
            FixedDataModelElement("s1", b" for "), user_name_model,
            FixedDataModelElement("s2", from_str),
            IpAddressDataModelElement("clientip"),
            FixedDataModelElement("s3", port),
            DecimalIntegerValueModelElement("port"),
            OptionalMatchModelElement(
                "idinfo",
                SequenceModelElement("idinfo", [
                    FixedDataModelElement("s0", b" id "),
                    DecimalIntegerValueModelElement("id")
                ]))
        ]),
        SequenceModelElement("transferred", [
            FixedDataModelElement("s0", b"Transferred: sent "),
            DecimalIntegerValueModelElement("sent"),
            FixedDataModelElement("s1", b", received "),
            DecimalIntegerValueModelElement("received"),
            FixedDataModelElement("s1", b" bytes")
        ]),
        SequenceModelElement("pam", [
            FixedDataModelElement("s0", b"pam_unix(sshd:session): session "),
            FixedWordlistDataModelElement("change", [b"opened", b"closed"]),
            FixedDataModelElement("s1", b" for user "), user_name_model,
            OptionalMatchModelElement(
                "openby", FixedDataModelElement("default", b" by (uid=0)"))
        ]),
        SequenceModelElement("child", [
            FixedDataModelElement("s0", b"User child is on pid "),
            DecimalIntegerValueModelElement("pid")
        ]),
        SequenceModelElement("failed/accept", [
            FixedWordlistDataModelElement("s0", [b"Failed ", b"Accepted "]),
            FixedWordlistDataModelElement(
                "type", [b"password", b"none", b"publickey"]),
            FixedDataModelElement("s1", b" for "),
            OptionalMatchModelElement(
                "opt", FixedDataModelElement("invalid", b"invalid user ")),
            DelimitedDataModelElement("user", b" "),
            FixedDataModelElement("s2", b" from "),
            FirstMatchModelElement("fm", [
                IpAddressDataModelElement("from_ip"),
                IpAddressDataModelElement("from_ip_v6", ipv6=True)
            ]),
            FixedDataModelElement("s3", b" port "),
            DecimalIntegerValueModelElement("port"),
            AnyByteDataModelElement("service")
        ]),
        SequenceModelElement("disconnecting", [
            FixedDataModelElement("s0", b"Disconnecting "),
            FixedWordlistDataModelElement("type",
                                          [b"authenticating", b"invalid"]),
            FixedDataModelElement("s1", b" user "),
            DelimitedDataModelElement("user", b" "),
            FixedDataModelElement("s1", b" "),
            IpAddressDataModelElement("ip"),
            FixedDataModelElement("s2", b" port "),
            DecimalIntegerValueModelElement("port"),
            FixedDataModelElement(
                "s3", b": Too many authentication failures [preauth]")
        ]),
        SequenceModelElement("fatal", [
            FixedDataModelElement(
                "s0", b"fatal: Timeout before authentication for "),
            IpAddressDataModelElement("ip"),
            FixedDataModelElement("s1", b" port "),
            DecimalIntegerValueModelElement("port")
        ]),
        SequenceModelElement("cert-auth", [
            FixedDataModelElement("s0", b"cert: Authentication tried for "),
            DelimitedDataModelElement("user", b" "),
            FixedDataModelElement(
                "s1",
                b" with valid certificate but not from a permitted source address ("
            ),
            IpAddressDataModelElement("ip"),
            FixedDataModelElement("s2", b")."),
        ]),
        SequenceModelElement("change-root-dir", [
            FixedDataModelElement("s0", b"Changed root directory to \""),
            DelimitedDataModelElement("root-dir", b"\""),
            FixedDataModelElement("s1", b"\"")
        ]),
        FixedDataModelElement("subsystem-request",
                              b"subsystem request for sftp"),
        SequenceModelElement("conn-write-poll", [
            FixedDataModelElement("s0",
                                  b"packet_write_poll: Connection from "),
            IpAddressDataModelElement("from_ip"),
            FixedDataModelElement("s1", b" port "),
            DecimalIntegerValueModelElement("port"),
            FixedDataModelElement("s2", b": Host is down")
        ]),
        SequenceModelElement("debug", [
            FixedDataModelElement("s0", b"debug"),
            DecimalIntegerValueModelElement("debug-num"),
            FixedDataModelElement("s1", b": "),
            FirstMatchModelElement("fm", [
                SequenceModelElement("seq1", [
                    FixedDataModelElement("s2", b"Got "),
                    DecimalIntegerValueModelElement("num1"),
                    FixedDataModelElement("s3", b"/"),
                    DecimalIntegerValueModelElement("num2"),
                    FixedDataModelElement("s4", b" for keepalive")
                ]),
                SequenceModelElement("seq2", [
                    FixedDataModelElement("s2", b"channel "),
                    DecimalIntegerValueModelElement("channel-num"),
                    FixedDataModelElement("s3", b": request "),
                    DelimitedDataModelElement("mail", b" "),
                    FixedDataModelElement("s4", b" confirm "),
                    DecimalIntegerValueModelElement("num")
                ]),
                SequenceModelElement("seq3", [
                    FixedDataModelElement("s2", b"send packet: type "),
                    DecimalIntegerValueModelElement("packet-type")
                ]),
                SequenceModelElement("seq4", [
                    FixedDataModelElement("s2", b"receive packet: type "),
                    DecimalIntegerValueModelElement("packet-type")
                ]),
                FixedDataModelElement("do-cleanup", b"do_cleanup"),
                SequenceModelElement("seq5", [
                    FixedDataModelElement("s2",
                                          b"session_pty_cleanup: session "),
                    DecimalIntegerValueModelElement("sess-num"),
                    FixedDataModelElement("s3", b" release "),
                    AnyByteDataModelElement("file")
                ])
            ])
        ]),
        SequenceModelElement("pam_succeed_if", [
            FixedDataModelElement(
                "s0", b"pam_succeed_if(sshd:auth): requirement \"uid >= "),
            DecimalIntegerValueModelElement("uid"),
            FixedDataModelElement("s1", b"\" not met by user \""),
            DelimitedDataModelElement("user", b"\""),
            FixedDataModelElement("s2", b"\"")
        ]),
    ]

    model = SequenceModelElement("sshd", [
        FixedDataModelElement("sname", b"sshd["),
        DecimalIntegerValueModelElement("pid"),
        FixedDataModelElement("s0", b"]: "),
        FirstMatchModelElement("msg", type_children)
    ])
    return model
class JsonModelElementTest(unittest.TestCase):
    """Unittests for the JsonModelElement."""

    single_line_json = b'{"menu": {"id": "file", "value": "File", "popup": {"menuitem": [{"value": "New", "onclick": "CreateNewDoc()"}, {' \
                       b'"value": "Open", "onclick": "OpenDoc()"}, {"value": "Close", "onclick": "CloseDoc()"}]}}}'
    single_line_with_optional_key_json = b'{"menu": {"id": "file", "value": "File", "popup": {"menuitem": [{"value": "New", "onclick":' \
                                         b' "CreateNewDoc()", "clickable": false}, {"value": "Open", "onclick": "OpenDoc()"}, {"value": ' \
                                         b'"Close", "onclick": "CloseDoc()", "clickable": false}]}}}'
    single_line_missing_key_json = b'{"menu": {"id": "file", "popup": {"menuitem": [{"value": "New", "onclick": "CreateNewDoc()"}, {' \
                                   b'"value": "Open", "onclick": "OpenDoc()"}, {"value": "Close", "onclick": "CloseDoc()"}]}}}'
    single_line_different_order_with_optional_key_json = \
        b'{"menu": {"value": "File","popup": {"menuitem": [{"clickable": false, "value": "New", "onclick": "CreateNewDoc()"}, {' \
        b'"onclick": "OpenDoc()", "value": "Open"}, {"value": "Close", "onclick": "CloseDoc()", "clickable": false}]}, "id": "file"}}'
    multi_line_json = b"""{
  "menu": {
    "id": "file",
    "value": "File",
    "popup": {
      "menuitem": [
        {"value": "New", "onclick": "CreateNewDoc()"},
        {"value": "Open", "onclick": "OpenDoc()"},
        {"value": "Close", "onclick": "CloseDoc()"}
      ]
    }
  }
}"""
    everything_new_line_json = b"""{
  "menu":
  {
    "id": "file",
    "value": "File",
    "popup":
    {
      "menuitem":
      [
        {
          "value": "New",
          "onclick": "CreateNewDoc()"
        },
        {
          "value": "Open",
          "onclick": "OpenDoc()"
        },
        {
          "value": "Close",
          "onclick": "CloseDoc()"
        }
      ]
    }
  }
}"""
    alphabet = b'abcdefghijklmnopqrstuvwxyzABCDEFGHIJKLMNOPQRSTUVWXYZ 0123456789_-.'
    key_parser_dict = {
        'menu': {
            'id': VariableByteDataModelElement('id', alphabet),
            'value': VariableByteDataModelElement('value', alphabet),
            'popup': {
                'menuitem': [{
                    'value':
                    FixedWordlistDataModelElement('buttonNames',
                                                  [b'New', b'Open', b'Close']),
                    'onclick':
                    FixedWordlistDataModelElement(
                        'buttonOnclick',
                        [b'CreateNewDoc()', b'OpenDoc()', b'CloseDoc()']),
                    'optional_key_clickable':
                    FixedWordlistDataModelElement('clickable',
                                                  [b'true', b'false'])
                }]
            }
        }
    }
    key_parser_dict_allow_all = {
        'menu': {
            'id': VariableByteDataModelElement('id', alphabet),
            'value': VariableByteDataModelElement('value', alphabet),
            'popup': 'ALLOW_ALL'
        }
    }

    def test1get_valid_match_elements(self):
        """Get valid json elements with different formats."""
        json_model_element = JsonModelElement('json', self.key_parser_dict)
        match = json_model_element.get_match_element(
            'match', MatchContext(self.single_line_json))
        self.assertEqual(match.match_object, json.loads(self.single_line_json))

        match = json_model_element.get_match_element(
            'match', MatchContext(self.multi_line_json))
        self.assertEqual(match.match_object, json.loads(self.multi_line_json))

        match = json_model_element.get_match_element(
            'match', MatchContext(self.everything_new_line_json))
        self.assertEqual(match.match_object,
                         json.loads(self.everything_new_line_json))

    def test2optional_key_prefix(self):
        """Validate optional keys with the optional_key_prefix."""
        json_model_element = JsonModelElement('json', self.key_parser_dict)
        match = json_model_element.get_match_element(
            'match', MatchContext(self.single_line_with_optional_key_json))
        self.assertEqual(match.match_object,
                         json.loads(self.single_line_with_optional_key_json))

    def test3missing_key(self):
        """Check if no match is returned if a key is missing."""
        json_model_element = JsonModelElement('json', self.key_parser_dict)
        match = json_model_element.get_match_element(
            'match', MatchContext(self.single_line_missing_key_json))
        self.assertEqual(match, None)

    def test4allow_all_dict(self):
        """Test a simplified key_parser_dict with ALLOW_ALL."""
        json_model_element = JsonModelElement('json',
                                              self.key_parser_dict_allow_all)
        match = json_model_element.get_match_element(
            'match', MatchContext(self.single_line_json))
        self.assertEqual(match.match_object, json.loads(self.single_line_json))

        match = json_model_element.get_match_element(
            'match', MatchContext(self.multi_line_json))
        self.assertEqual(match.match_object, json.loads(self.multi_line_json))

        match = json_model_element.get_match_element(
            'match', MatchContext(self.everything_new_line_json))
        self.assertEqual(match.match_object,
                         json.loads(self.everything_new_line_json))

    def test5different_order_keys(self):
        """Test if keys differently ordered than in the key_parser_dict are parsed properly."""
        json_model_element = JsonModelElement('json', self.key_parser_dict)
        match = json_model_element.get_match_element(
            'match',
            MatchContext(
                self.single_line_different_order_with_optional_key_json))
        self.assertEqual(
            match.match_object,
            json.loads(
                self.single_line_different_order_with_optional_key_json))

        json_model_element = JsonModelElement('json',
                                              self.key_parser_dict_allow_all)
        match = json_model_element.get_match_element(
            'match',
            MatchContext(
                self.single_line_different_order_with_optional_key_json))
        self.assertEqual(
            match.match_object,
            json.loads(
                self.single_line_different_order_with_optional_key_json))

    def test6null_value(self):
        """Test if null values are parsed to "null"."""
        key_parser_dict = {
            "works":
            VariableByteDataModelElement("id", b"abc123"),
            "problem":
            FixedWordlistDataModelElement("wordlist",
                                          [b"allowed value", b"null"])
        }
        data1 = b"""{
            "works": "abc",
            "problem": "allowed value"
        }"""
        data2 = b"""{
            "works": "123",
            "problem": null
        }"""
        json_model_element = JsonModelElement('json', key_parser_dict)
        self.assertIsNotNone(
            json_model_element.get_match_element('match', MatchContext(data1)))
        self.assertIsNotNone(
            json_model_element.get_match_element('match', MatchContext(data2)))
예제 #22
0
def get_model():
    """Return a model to parse a audispd message logged via syslog after any standard logging preamble, e.g. from syslog."""
    class ExecArgumentDataModelElement():
        """This is a helper class for parsing the (encoded) exec argument strings found within audit logs."""
        def __init__(self, element_id):
            self.element_id = element_id

        @staticmethod
        def get_child_elements():
            """Get the children of this element (none)."""
            return None

        def get_match_element(self, path, match_context):
            """
            Find the maximum number of bytes belonging to an exec argument.
            @return a match when at least two bytes were found including the delimiters.
            """
            data = match_context.match_data
            match_len = 0
            match_value = b''
            if data[0] == ord(b'"'):
                match_len = data.find(b'"', 1)
                if match_len == -1:
                    return None
                match_value = data[1:match_len]
                match_len += 1
            elif data.startswith(b'(null)'):
                match_len = 6
                match_value = None
            else:
                # Must be upper case hex encoded:
                next_value = -1
                for d_byte in data:
                    if 0x30 <= d_byte <= 0x39:
                        d_byte -= 0x30
                    elif 0x41 <= d_byte <= 0x46:
                        d_byte -= 0x37
                    else:
                        break
                    if next_value == -1:
                        next_value = (d_byte << 4)
                    else:
                        match_value += bytearray(((next_value | d_byte), ))
                        next_value = -1
                    match_len += 1
                if next_value != -1:
                    return None

            match_data = data[:match_len]
            match_context.update(match_data)
            return MatchElement("%s/%s" % (path, self.element_id), match_data,
                                match_value, None)

    pam_status_word_list = FixedWordlistDataModelElement(
        'status', [b'failed', b'success'])

    pid = b' pid='
    uid = b' uid='
    auid = b' auid='
    ses = b' ses='
    exe = b' exe="'
    hostname = b'" hostname='
    addr = b' addr='
    terminal = b' terminal='
    success = b' res=success\''
    res = b' res='
    exe1 = b'" exe="'

    type_branches = {
        'ADD_USER':
        SequenceModelElement('adduser', [
            FixedDataModelElement('s0', pid),
            DecimalIntegerValueModelElement('pid'),
            FixedDataModelElement('s1', uid),
            DecimalIntegerValueModelElement('uid'),
            FixedDataModelElement('s2', auid),
            DecimalIntegerValueModelElement('auid'),
            FixedDataModelElement('s3', ses),
            DecimalIntegerValueModelElement('ses'),
            FixedDataModelElement('s4', b' msg=\'op=adding user id='),
            DecimalIntegerValueModelElement('newuserid'),
            FixedDataModelElement('s5', exe),
            DelimitedDataModelElement('exec', b'"'),
            FixedDataModelElement('s6', hostname),
            DelimitedDataModelElement('clientname', b' '),
            FixedDataModelElement('s7', addr),
            DelimitedDataModelElement('clientip', b' '),
            FixedDataModelElement('s8', terminal),
            WhiteSpaceLimitedDataModelElement('terminal'),
            FixedDataModelElement('s9', success)
        ]),
        'BPRM_FCAPS':
        SequenceModelElement('bprmfcaps', [
            FixedDataModelElement('s0', b' fver=0 fp='),
            HexStringModelElement('fp'),
            FixedDataModelElement('s1', b' fi='),
            HexStringModelElement('fi'),
            FixedDataModelElement('s2', b' fe='),
            HexStringModelElement('fe'),
            FixedDataModelElement('s3', b' old_pp='),
            HexStringModelElement('pp-old'),
            FixedDataModelElement('s4', b' old_pi='),
            HexStringModelElement('pi-old'),
            FixedDataModelElement('s5', b' old_pe='),
            HexStringModelElement('pe-old'),
            FixedDataModelElement('s6', b' new_pp='),
            HexStringModelElement('pp-new'),
            FixedDataModelElement('s7', b' new_pi='),
            HexStringModelElement('pi-new'),
            FixedDataModelElement('s8', b' new_pe='),
            HexStringModelElement('pe-new')
        ]),
        'CONFIG_CHANGE':
        SequenceModelElement('conf-change', [
            FixedDataModelElement('s0', auid),
            DecimalIntegerValueModelElement('auid'),
            FixedDataModelElement('s1', ses),
            DecimalIntegerValueModelElement('ses'),
            FixedDataModelElement('s2', b' op="add rule" key=(null) list='),
            DecimalIntegerValueModelElement('list'),
            FixedDataModelElement('s3', res),
            DecimalIntegerValueModelElement('result')
        ]),
        'CRED_ACQ':
        SequenceModelElement('credacq', [
            FixedDataModelElement('s0', pid),
            DecimalIntegerValueModelElement('pid'),
            FixedDataModelElement('s1', uid),
            DecimalIntegerValueModelElement('uid'),
            FixedDataModelElement('s2', auid),
            DecimalIntegerValueModelElement('auid'),
            FixedDataModelElement('s3', ses),
            DecimalIntegerValueModelElement('ses'),
            FixedDataModelElement('s4', b' msg=\'op=PAM:setcred acct="'),
            DelimitedDataModelElement('username', b'"'),
            FixedDataModelElement('s5', exe1),
            DelimitedDataModelElement('exec', b'"'),
            FixedDataModelElement('s6', hostname),
            DelimitedDataModelElement('clientname', b' '),
            FixedDataModelElement('s7', addr),
            DelimitedDataModelElement('clientip', b' '),
            FixedDataModelElement('s8', terminal),
            WhiteSpaceLimitedDataModelElement('terminal'),
            FixedDataModelElement('s9', success)
        ]),
        'CRED_DISP':
        SequenceModelElement('creddisp', [
            FixedDataModelElement('s0', pid),
            DecimalIntegerValueModelElement('pid'),
            FixedDataModelElement('s1', uid),
            DecimalIntegerValueModelElement('uid'),
            FixedDataModelElement('s2', auid),
            DecimalIntegerValueModelElement('auid'),
            FixedDataModelElement('s3', ses),
            DecimalIntegerValueModelElement('ses'),
            FixedDataModelElement('s4', b' msg=\'op=PAM:setcred acct="'),
            DelimitedDataModelElement('username', b'"'),
            FixedDataModelElement('s5', exe1),
            DelimitedDataModelElement('exec', b'"'),
            FixedDataModelElement('s6', hostname),
            DelimitedDataModelElement('clientname', b' '),
            FixedDataModelElement('s7', addr),
            DelimitedDataModelElement('clientip', b' '),
            FixedDataModelElement('s8', terminal),
            WhiteSpaceLimitedDataModelElement('terminal'),
            FixedDataModelElement('s9', success)
        ]),
        'CRED_REFR':
        SequenceModelElement('creddisp', [
            FixedDataModelElement('s0', pid),
            DecimalIntegerValueModelElement('pid'),
            FixedDataModelElement('s1', uid),
            DecimalIntegerValueModelElement('uid'),
            FixedDataModelElement('s2', auid),
            DecimalIntegerValueModelElement('auid'),
            FixedDataModelElement('s3', ses),
            DecimalIntegerValueModelElement('ses'),
            FixedDataModelElement(
                's4',
                b' msg=\'op=PAM:setcred acct="root" exe="/usr/sbin/sshd" hostname='
            ),
            IpAddressDataModelElement('clientname'),
            FixedDataModelElement('s5', addr),
            IpAddressDataModelElement('clientip'),
            FixedDataModelElement('s6', b' terminal=ssh res=success\'')
        ]),
        'CWD':
        SequenceModelElement('cwd', [
            FixedDataModelElement('s0', b'  cwd='),
            ExecArgumentDataModelElement('cwd')
        ]),
        'EOE':
        OptionalMatchModelElement('eoe', FixedDataModelElement('s0', b''))
    }

    # We need a type branch here also, but there is no additional
    # data in EOE records after Ubuntu Trusty any more.
    exec_arg_model = SequenceModelElement('execarg', [
        FixedDataModelElement('s0', b' a'),
        DecimalIntegerValueModelElement('argn'),
        FixedDataModelElement('s1', b'='),
        ExecArgumentDataModelElement('argval')
    ])

    type_branches['EXECVE'] = SequenceModelElement('execve', [
        FixedDataModelElement('s0', b' argc='),
        DecimalIntegerValueModelElement('argc'),
        RepeatedElementDataModelElement('arg', exec_arg_model)
    ])

    type_branches['FD_PAIR'] = SequenceModelElement('fdpair', [
        FixedDataModelElement('s0', b' fd0='),
        DecimalIntegerValueModelElement('fd0'),
        FixedDataModelElement('s1', b' fd1='),
        DecimalIntegerValueModelElement('fd1')
    ])

    # This message differs on Ubuntu 32/64 bit variants.
    type_branches['LOGIN'] = SequenceModelElement('login', [
        FixedDataModelElement('s0', pid),
        DecimalIntegerValueModelElement('pid'),
        FixedDataModelElement('s1', uid),
        DecimalIntegerValueModelElement('uid'),
        FixedWordlistDataModelElement('s2', [b' old auid=', b' old-auid=']),
        DecimalIntegerValueModelElement('auid-old'),
        FixedWordlistDataModelElement('s3', [b' new auid=', auid]),
        DecimalIntegerValueModelElement('auid-new'),
        FixedWordlistDataModelElement('s4', [b' old ses=', b' old-ses=']),
        DecimalIntegerValueModelElement('ses-old'),
        FixedWordlistDataModelElement('s5', [b' new ses=', ses]),
        DecimalIntegerValueModelElement('ses-new'),
        FixedDataModelElement('s6', res),
        DecimalIntegerValueModelElement('result')
    ])

    inode_info_model_element = SequenceModelElement(
        'inodeinfo',
        [
            FixedDataModelElement('s0', b' inode='),
            DecimalIntegerValueModelElement('inode'),
            FixedDataModelElement('s1', b' dev='),
            # A special major/minor device element could be better here.
            VariableByteDataModelElement('dev', b'0123456789abcdef:'),
            FixedDataModelElement('s2', b' mode='),
            # is octal
            DecimalIntegerValueModelElement('mode'),
            FixedDataModelElement('s3', b' ouid='),
            DecimalIntegerValueModelElement('ouid'),
            FixedDataModelElement('s4', b' ogid='),
            DecimalIntegerValueModelElement('ogid'),
            FixedDataModelElement('s5', b' rdev='),
            # A special major/minor device element could be better here (see above).
            VariableByteDataModelElement('rdev', b'0123456789abcdef:'),
            FixedDataModelElement('s6', b' nametype=')
        ])

    type_branches['NETFILTER_CFG'] = SequenceModelElement(
        'conf-change', [
            FixedDataModelElement('s0', b' table='),
            FixedWordlistDataModelElement('table',
                                          [b'filter', b'mangle', b'nat']),
            FixedDataModelElement('s1', b' family='),
            DecimalIntegerValueModelElement('family'),
            FixedDataModelElement('s2', b' entries='),
            DecimalIntegerValueModelElement('entries')
        ])

    type_branches['OBJ_PID'] = SequenceModelElement('objpid', [
        FixedDataModelElement('s0', b' opid='),
        DecimalIntegerValueModelElement('opid'),
        FixedDataModelElement('s1', b' oauid='),
        DecimalIntegerValueModelElement(
            'oauid',
            value_sign_type=DecimalIntegerValueModelElement.SIGN_TYPE_OPTIONAL
        ),
        FixedDataModelElement('s2', b' ouid='),
        DecimalIntegerValueModelElement('ouid'),
        FixedDataModelElement('s3', b' oses='),
        DecimalIntegerValueModelElement(
            'oses',
            value_sign_type=DecimalIntegerValueModelElement.SIGN_TYPE_OPTIONAL
        ),
        FixedDataModelElement('s4', b' ocomm='),
        ExecArgumentDataModelElement('ocomm')
    ])

    type_branches['PATH'] = SequenceModelElement('path', [
        FixedDataModelElement('s0', b' item='),
        DecimalIntegerValueModelElement('item'),
        FixedDataModelElement('s1', b' name='),
        ExecArgumentDataModelElement('name'),
        FirstMatchModelElement('fsinfo', [
            inode_info_model_element,
            FixedDataModelElement('noinfo', b' nametype=')
        ]),
        FixedWordlistDataModelElement(
            'nametype',
            [b'CREATE', b'DELETE', b'NORMAL', b'PARENT', b'UNKNOWN'])
    ])

    type_branches['PROCTITLE'] = SequenceModelElement('proctitle', [
        FixedDataModelElement('s1', b' proctitle='),
        ExecArgumentDataModelElement('proctitle')
    ])

    type_branches['SERVICE_START'] = SequenceModelElement(
        'service', [
            FixedDataModelElement('s0', pid),
            DecimalIntegerValueModelElement('pid'),
            FixedDataModelElement('s1', uid),
            DecimalIntegerValueModelElement('uid'),
            FixedDataModelElement('s2', auid),
            DecimalIntegerValueModelElement('auid'),
            FixedDataModelElement('s3', ses),
            DecimalIntegerValueModelElement('ses'),
            FixedDataModelElement('s4', b' msg=\'unit='),
            DelimitedDataModelElement('unit', b' '),
            FixedDataModelElement('s5', b' comm="systemd" exe="'),
            DelimitedDataModelElement('exec', b'"'),
            FixedDataModelElement('s6', hostname),
            DelimitedDataModelElement('clientname', b' '),
            FixedDataModelElement('s7', addr),
            DelimitedDataModelElement('clientip', b' '),
            FixedDataModelElement('s8', terminal),
            WhiteSpaceLimitedDataModelElement('terminal'),
            FixedDataModelElement('s9', res), pam_status_word_list,
            FixedDataModelElement('s10', b'\'')
        ])

    type_branches['SERVICE_STOP'] = type_branches['SERVICE_START']

    type_branches['SOCKADDR'] = SequenceModelElement('sockaddr', [
        FixedDataModelElement('s0', b' saddr='),
        HexStringModelElement('sockaddr', upper_case=True)
    ])

    type_branches['SYSCALL'] = SequenceModelElement('syscall', [
        FixedDataModelElement('s0', b' arch='),
        HexStringModelElement('arch'),
        FixedDataModelElement('s1', b' syscall='),
        DecimalIntegerValueModelElement('syscall'),
        OptionalMatchModelElement(
            'personality',
            SequenceModelElement('pseq', [
                FixedDataModelElement('s0', b' per='),
                DecimalIntegerValueModelElement('personality')
            ])),
        OptionalMatchModelElement(
            'result',
            SequenceModelElement('rseq', [
                FixedDataModelElement('s2', b' success='),
                FixedWordlistDataModelElement('succes', [b'no', b'yes']),
                FixedDataModelElement('s3', b' exit='),
                DecimalIntegerValueModelElement(
                    'exit',
                    value_sign_type=DecimalIntegerValueModelElement.
                    SIGN_TYPE_OPTIONAL)
            ])),
        FixedDataModelElement('s4', b' a0='),
        HexStringModelElement('arg0'),
        FixedDataModelElement('s5', b' a1='),
        HexStringModelElement('arg1'),
        FixedDataModelElement('s6', b' a2='),
        HexStringModelElement('arg2'),
        FixedDataModelElement('s7', b' a3='),
        HexStringModelElement('arg3'),
        FixedDataModelElement('s8', b' items='),
        DecimalIntegerValueModelElement('items'),
        FixedDataModelElement('s9', b' ppid='),
        DecimalIntegerValueModelElement('ppid'),
        FixedDataModelElement('s10', pid),
        DecimalIntegerValueModelElement('pid'),
        FixedDataModelElement('s11', auid),
        DecimalIntegerValueModelElement('auid'),
        FixedDataModelElement('s12', uid),
        DecimalIntegerValueModelElement('uid'),
        FixedDataModelElement('s13', b' gid='),
        DecimalIntegerValueModelElement('gid'),
        FixedDataModelElement('s14', b' euid='),
        DecimalIntegerValueModelElement('euid'),
        FixedDataModelElement('s15', b' suid='),
        DecimalIntegerValueModelElement('suid'),
        FixedDataModelElement('s16', b' fsuid='),
        DecimalIntegerValueModelElement('fsuid'),
        FixedDataModelElement('s17', b' egid='),
        DecimalIntegerValueModelElement('egid'),
        FixedDataModelElement('s18', b' sgid='),
        DecimalIntegerValueModelElement('sgid'),
        FixedDataModelElement('s19', b' fsgid='),
        DecimalIntegerValueModelElement('fsgid'),
        FixedDataModelElement('s20', b' tty='),
        DelimitedDataModelElement('tty', b' '),
        FixedDataModelElement('s21', ses),
        DecimalIntegerValueModelElement('sesid'),
        FixedDataModelElement('s22', b' comm='),
        ExecArgumentDataModelElement('command'),
        FixedDataModelElement('s23', exe),
        DelimitedDataModelElement('executable', b'"'),
        FixedDataModelElement('s24', b'" key='),
        AnyByteDataModelElement('key')
    ])

    # The UNKNOWN type is used then audispd does not know the type of the event, usually because the kernel is more recent than
    # audispd, thus emiting yet unknown event types.
    # * type=1327: procitle: see https://www.redhat.com/archives/linux-audit/2014-February/msg00047.html
    type_branches['UNKNOWN[1327]'] = SequenceModelElement(
        'unknown-proctitle', [
            FixedDataModelElement('s0', b' proctitle='),
            ExecArgumentDataModelElement('proctitle')
        ])

    type_branches['USER_ACCT'] = SequenceModelElement('useracct', [
        FixedDataModelElement('s0', pid),
        DecimalIntegerValueModelElement('pid'),
        FixedDataModelElement('s1', uid),
        DecimalIntegerValueModelElement('uid'),
        FixedDataModelElement('s2', auid),
        DecimalIntegerValueModelElement('auid'),
        FixedDataModelElement('s3', ses),
        DecimalIntegerValueModelElement('ses'),
        FixedDataModelElement('s4', b' msg=\'op=PAM:accounting acct="'),
        DelimitedDataModelElement('username', b'"'),
        FixedDataModelElement('s5', exe1),
        DelimitedDataModelElement('exec', b'"'),
        FixedDataModelElement('s6', hostname),
        DelimitedDataModelElement('clientname', b' '),
        FixedDataModelElement('s7', addr),
        DelimitedDataModelElement('clientip', b' '),
        FixedDataModelElement('s8', terminal),
        WhiteSpaceLimitedDataModelElement('terminal'),
        FixedDataModelElement('s9', success)
    ])

    type_branches['USER_AUTH'] = SequenceModelElement('userauth', [
        FixedDataModelElement('s0', pid),
        DecimalIntegerValueModelElement('pid'),
        FixedDataModelElement('s1', uid),
        DecimalIntegerValueModelElement('uid'),
        FixedDataModelElement('s2', auid),
        DecimalIntegerValueModelElement('auid'),
        FixedDataModelElement('s3', ses),
        DecimalIntegerValueModelElement('ses'),
        FixedDataModelElement('s4', b' msg=\'op=PAM:authentication acct="'),
        DelimitedDataModelElement('username', b'"'),
        FixedDataModelElement('s5', exe1),
        DelimitedDataModelElement('exec', b'"'),
        FixedDataModelElement('s6', hostname),
        DelimitedDataModelElement('clientname', b' '),
        FixedDataModelElement('s7', addr),
        DelimitedDataModelElement('clientip', b' '),
        FixedDataModelElement('s8', terminal),
        WhiteSpaceLimitedDataModelElement('terminal'),
        FixedDataModelElement('s9', success)
    ])

    type_branches['USER_START'] = SequenceModelElement('userstart', [
        FixedDataModelElement('s0', pid),
        DecimalIntegerValueModelElement('pid'),
        FixedDataModelElement('s1', uid),
        DecimalIntegerValueModelElement('uid'),
        FixedDataModelElement('s2', auid),
        DecimalIntegerValueModelElement('auid'),
        FixedDataModelElement('s3', ses),
        DecimalIntegerValueModelElement('ses'),
        FixedDataModelElement('s4', b' msg=\'op=PAM:session_open acct="'),
        DelimitedDataModelElement('username', b'"'),
        FixedDataModelElement('s5', exe1),
        DelimitedDataModelElement('exec', b'"'),
        FixedDataModelElement('s6', hostname),
        DelimitedDataModelElement('clientname', b' '),
        FixedDataModelElement('s7', addr),
        DelimitedDataModelElement('clientip', b' '),
        FixedDataModelElement('s8', terminal),
        WhiteSpaceLimitedDataModelElement('terminal'),
        FixedDataModelElement('s9', success)
    ])

    type_branches['USER_END'] = SequenceModelElement('userend', [
        FixedDataModelElement('s0', pid),
        DecimalIntegerValueModelElement('pid'),
        FixedDataModelElement('s1', uid),
        DecimalIntegerValueModelElement('uid'),
        FixedDataModelElement('s2', auid),
        DecimalIntegerValueModelElement('auid'),
        FixedDataModelElement('s3', ses),
        DecimalIntegerValueModelElement('ses'),
        FixedDataModelElement('s4', b' msg=\'op=PAM:session_close acct="'),
        DelimitedDataModelElement('username', b'"'),
        FixedDataModelElement('s5', exe1),
        DelimitedDataModelElement('exec', b'"'),
        FixedDataModelElement('s6', hostname),
        DelimitedDataModelElement('clientname', b' '),
        FixedDataModelElement('s7', addr),
        DelimitedDataModelElement('clientip', b' '),
        FixedDataModelElement('s8', terminal),
        WhiteSpaceLimitedDataModelElement('terminal'),
        FixedDataModelElement('s9', success)
    ])

    type_branches['USER_ERR'] = SequenceModelElement('usererr', [
        FixedDataModelElement('s0', pid),
        DecimalIntegerValueModelElement('pid'),
        FixedDataModelElement('s1', uid),
        DecimalIntegerValueModelElement('uid'),
        FixedDataModelElement('s2', auid),
        DecimalIntegerValueModelElement('auid'),
        FixedDataModelElement('s3', ses),
        DecimalIntegerValueModelElement('ses'),
        FixedDataModelElement('s4', b' msg=\'op=PAM:bad_ident acct="?" exe="'),
        DelimitedDataModelElement('exec', b'"'),
        FixedDataModelElement('s5', hostname),
        DelimitedDataModelElement('clientname', b' '),
        FixedDataModelElement('s6', addr),
        DelimitedDataModelElement('clientip', b' '),
        FixedDataModelElement('s7', terminal),
        WhiteSpaceLimitedDataModelElement('terminal'),
        FixedDataModelElement('s8', b' res=failed\'')
    ])

    type_branches['USER_LOGIN'] = SequenceModelElement('userlogin', [
        FixedDataModelElement('s0', pid),
        DecimalIntegerValueModelElement('pid'),
        FixedDataModelElement('s1', uid),
        DecimalIntegerValueModelElement('uid'),
        FixedDataModelElement('s2', auid),
        DecimalIntegerValueModelElement('auid'),
        FixedDataModelElement('s3', ses),
        DecimalIntegerValueModelElement('ses'),
        FixedDataModelElement('s4', b' msg=\'op=login '),
        FirstMatchModelElement('msgtype', [
            FixedDataModelElement('loginok', b'id=0'),
            SequenceModelElement('loginfail', [
                FixedDataModelElement('s0', b'acct='),
                ExecArgumentDataModelElement('account')
            ])
        ]),
        FixedDataModelElement('s5', exe),
        DelimitedDataModelElement('exec', b'"'),
        FixedDataModelElement('s6', hostname),
        DelimitedDataModelElement('clientname', b' '),
        FixedDataModelElement('s7', addr),
        DelimitedDataModelElement('clientip', b' '),
        FixedDataModelElement('s8', terminal),
        WhiteSpaceLimitedDataModelElement('terminal'),
        FixedDataModelElement('s9', res), pam_status_word_list,
        FixedDataModelElement('s10', b'\'')
    ])

    model = SequenceModelElement('audispd', [
        FixedDataModelElement('sname', b'audispd: '),
        FirstMatchModelElement('msg', [
            ElementValueBranchModelElement(
                'record',
                SequenceModelElement('preamble', [
                    FixedDataModelElement('s0', b'type='),
                    WhiteSpaceLimitedDataModelElement('type'),
                    FixedDataModelElement('s1', b' msg=audit('),
                    DecimalIntegerValueModelElement('time'),
                    FixedDataModelElement('s0', b'.'),
                    DecimalIntegerValueModelElement('ms'),
                    FixedDataModelElement('s1', b':'),
                    DecimalIntegerValueModelElement('seq'),
                    FixedDataModelElement('s2', b'):')
                ]),
                'type',
                type_branches,
                default_branch=None),
            FixedDataModelElement('queue-full',
                                  b'queue is full - dropping event')
        ])
    ])
    return model
예제 #23
0
def get_model():
    """Return a model to parse Syslogs from the AIT-LDS."""
    alphabet = b'!"#$%&\'()*+,-./0123456789:;<>?@ABCDEFGHIJKLMNOPQRSTUVWXYZ\\^_`abcdefghijklmnopqrstuvwxyz{|}~=[]'

    user_info = SequenceModelElement('user_info', [
        FixedDataModelElement('user_str', b'user=<'),
        OptionalMatchModelElement('user',
                                  DelimitedDataModelElement('user', b'>')),
        FixedDataModelElement('method_str', b'>'),
        OptionalMatchModelElement(
            'method',
            SequenceModelElement('method', [
                FixedDataModelElement('method_str', b', method='),
                DelimitedDataModelElement('method', b','),
            ])),
        FixedDataModelElement('rip_str', b', rip='),
        IpAddressDataModelElement('rip'),
        FixedDataModelElement('lip_str', b', lip='),
        IpAddressDataModelElement('lip'),
        OptionalMatchModelElement(
            'mpid',
            SequenceModelElement('mpid', [
                FixedDataModelElement('mpid_str', b', mpid='),
                DecimalIntegerValueModelElement('mpid'),
            ])),
        OptionalMatchModelElement(
            'secured', FixedDataModelElement('secured_str', b', secured')),
        FixedDataModelElement('session_str', b', session=<'),
        DelimitedDataModelElement('session', b'>'),
        FixedDataModelElement('bracket_str', b'>'),
    ])

    model = SequenceModelElement(
        'model',
        [
            DateTimeModelElement('time', b'%b %d %H:%M:%S', start_year=2020),
            FixedDataModelElement('sp1', b' '),
            DelimitedDataModelElement('host', b' '),
            FirstMatchModelElement(
                'service',
                [
                    SequenceModelElement('dovecot', [
                        FixedDataModelElement('dovecot_str', b' dovecot: '),
                        FirstMatchModelElement('imap', [
                            SequenceModelElement('imap', [
                                FixedDataModelElement('imap_str', b'imap('),
                                DelimitedDataModelElement('user', b')'),
                                FixedDataModelElement('bracket_str', b'): '),
                                FirstMatchModelElement('message', [
                                    SequenceModelElement(
                                        'logout', [
                                            FixedDataModelElement(
                                                'logout_str',
                                                b'Logged out in='),
                                            DecimalIntegerValueModelElement(
                                                'in'),
                                            FixedDataModelElement(
                                                'out_str', b' out='),
                                            DecimalIntegerValueModelElement(
                                                'out')
                                        ]),
                                    SequenceModelElement(
                                        'err_mail', [
                                            FixedDataModelElement(
                                                'mail_str',
                                                b'Error: Failed to autocreate mailbox INBOX: Internal error occurred. '
                                                b'Refer to server log for more information. ['
                                            ),
                                            DelimitedDataModelElement(
                                                'err_time', b']'),
                                            FixedDataModelElement(
                                                'brack', b']')
                                        ]),
                                    SequenceModelElement(
                                        'err_open', [
                                            FixedDataModelElement(
                                                'err_str', b'Error: '),
                                            DelimitedDataModelElement(
                                                'function_name', b'('),
                                            FixedDataModelElement(
                                                'brack_str1', b'('),
                                            DelimitedDataModelElement(
                                                'arg', b')'),
                                            FixedDataModelElement(
                                                'failed_str',
                                                b') failed: Permission denied (euid='
                                            ),
                                            DecimalIntegerValueModelElement(
                                                'euid'),
                                            FixedDataModelElement(
                                                'brack_str2', b'('),
                                            DelimitedDataModelElement(
                                                'euid_user', b')'),
                                            FixedDataModelElement(
                                                'egid_str', b') egid='),
                                            DecimalIntegerValueModelElement(
                                                'egid'),
                                            FixedDataModelElement(
                                                'brack_str3', b'('),
                                            DelimitedDataModelElement(
                                                'egid_user', b')'),
                                            FixedDataModelElement(
                                                'perm_str',
                                                b') missing +w perm: '),
                                            DelimitedDataModelElement(
                                                'mail_path', b','),
                                            FixedDataModelElement(
                                                'group_str',
                                                b', we\'re not in group '),
                                            DecimalIntegerValueModelElement(
                                                'group_id'),
                                            FixedDataModelElement(
                                                'brack_str4', b'('),
                                            DelimitedDataModelElement(
                                                'group_name', b')'),
                                            FixedDataModelElement(
                                                'owned_str',
                                                b'), dir owned by '),
                                            DelimitedDataModelElement(
                                                'owner', b' '),
                                            FixedDataModelElement(
                                                'mode_str', b' mode='),
                                            DelimitedDataModelElement(
                                                'mode', b')'),
                                            FixedDataModelElement(
                                                'brack_str5', b')'),
                                            OptionalMatchModelElement(
                                                'set',
                                                SequenceModelElement(
                                                    'set', [
                                                        FixedDataModelElement(
                                                            'set_str',
                                                            b' (set'),
                                                        DelimitedDataModelElement(
                                                            'param', b'='),
                                                        FixedDataModelElement(
                                                            'equal_str', b'='),
                                                        DelimitedDataModelElement(
                                                            'val', b')'),
                                                        FixedDataModelElement(
                                                            'brack_str6', b')')
                                                    ]))
                                        ]),
                                    SequenceModelElement(
                                        'err_mail', [
                                            FixedDataModelElement(
                                                'mail_str',
                                                b'Failed to autocreate mailbox INBOX: Internal error occurred. '
                                                b'Refer to server log for more information. ['
                                            ),
                                            DelimitedDataModelElement(
                                                'err_time', b']'),
                                            FixedDataModelElement(
                                                'brack', b']')
                                        ]),
                                ]),
                            ]),
                            SequenceModelElement('imap_login', [
                                FixedDataModelElement('imap_login_str',
                                                      b'imap-login: '******'login', [
                                    SequenceModelElement(
                                        'disconnected_str', [
                                            FixedDataModelElement(
                                                'disconnected_str',
                                                b'Disconnected '),
                                            FirstMatchModelElement(
                                                'auth', [
                                                    SequenceModelElement(
                                                        'auth_failed', [
                                                            FixedDataModelElement(
                                                                'auth_failed_str',
                                                                b'(auth failed, '
                                                            ),
                                                            DecimalIntegerValueModelElement(
                                                                'attempts'),
                                                            FixedDataModelElement(
                                                                'attempts_str',
                                                                b' attempts in '
                                                            ),
                                                        ]),
                                                    FixedDataModelElement(
                                                        'no_auth_str',
                                                        b'(no auth attempts in '
                                                    ),
                                                    FixedDataModelElement(
                                                        'no_auth_str',
                                                        b'(disconnected before auth was ready, waited '
                                                    ),
                                                ]),
                                            DecimalIntegerValueModelElement(
                                                'duration'),
                                            FixedDataModelElement(
                                                'secs_str', b' secs): '),
                                            user_info
                                        ]),
                                    SequenceModelElement(
                                        'login', [
                                            FixedDataModelElement(
                                                'login_str', b'Login: '******'anvil', [
                                            FixedDataModelElement(
                                                'anvil_str', b'Error: anvil:'),
                                            AnyByteDataModelElement(
                                                'anvil_msg')
                                        ]),
                                    SequenceModelElement(
                                        'auth_responding', [
                                            FixedDataModelElement(
                                                'auth_responding_str',
                                                b'Warning: Auth process not responding, '
                                                b'delayed sending initial response (greeting): '
                                            ), user_info
                                        ]),
                                ]),
                            ]),
                            SequenceModelElement('auth', [
                                FixedDataModelElement('auth_worker_str',
                                                      b'auth: '),
                                AnyByteDataModelElement('message')
                            ]),
                            SequenceModelElement('auth_worker', [
                                FixedDataModelElement('auth_worker_str',
                                                      b'auth-worker('),
                                DecimalIntegerValueModelElement('pid'),
                                FixedDataModelElement('brack', b'):'),
                                AnyByteDataModelElement('message')
                            ]),
                            SequenceModelElement('master', [
                                FixedDataModelElement('master_str',
                                                      b'master: '),
                                AnyByteDataModelElement('message')
                            ])
                        ]),
                    ]),
                    SequenceModelElement('horde', [
                        FixedDataModelElement('horde_str', b' HORDE: '),
                        FirstMatchModelElement('horde', [
                            SequenceModelElement('imp', [
                                FixedDataModelElement('succ_str', b'[imp] '),
                                FirstMatchModelElement('imp', [
                                    SequenceModelElement(
                                        'login', [
                                            FixedDataModelElement(
                                                'succ_str',
                                                b'Login success for '),
                                            DelimitedDataModelElement(
                                                'user', b' '),
                                            FixedDataModelElement(
                                                'brack_str1', b' ('),
                                            IpAddressDataModelElement('ip'),
                                            FixedDataModelElement(
                                                'to_str', b') to {'),
                                            DelimitedDataModelElement(
                                                'imap_addr', b'}'),
                                            FixedDataModelElement(
                                                'brack_str2', b'}'),
                                        ]),
                                    SequenceModelElement(
                                        'message_sent', [
                                            FixedDataModelElement(
                                                'message_sent_str',
                                                b'Message sent to '),
                                            VariableByteDataModelElement(
                                                'user',
                                                b'.0123456789@ABCDEFGHIJKLMNOPQRSTUVWXYZ_abcdefghijklmnopqrstuvwxyz'
                                            ),
                                            OptionalMatchModelElement(
                                                'mail',
                                                SequenceModelElement(
                                                    'mail', [
                                                        FixedDataModelElement(
                                                            'brack_mail1',
                                                            b' <'),
                                                        DelimitedDataModelElement(
                                                            'mail', b'>'),
                                                        FixedDataModelElement(
                                                            'brack_mail2',
                                                            b'>')
                                                    ])),
                                            RepeatedElementDataModelElement(
                                                'more_recepients_rep',
                                                SequenceModelElement(
                                                    'more_recepients', [
                                                        FixedDataModelElement(
                                                            'comma_str',
                                                            b', '),
                                                        VariableByteDataModelElement(
                                                            'more_recepients_mail',
                                                            b'.0123456789@ABCDEFGHIJKLMNOPQRSTUVWXYZ_abcdefghijklmnopqrstuvwxyz'
                                                        ),
                                                        OptionalMatchModelElement(
                                                            'more_recepients_mail',
                                                            SequenceModelElement(
                                                                'more_recepients',
                                                                [
                                                                    FixedDataModelElement(
                                                                        'brack_more_recepients1',
                                                                        b' <'),
                                                                    DelimitedDataModelElement(
                                                                        'more_recepients',
                                                                        b'>'),
                                                                    FixedDataModelElement(
                                                                        'brack_more_recepients2',
                                                                        b'>')
                                                                ])),
                                                    ])),
                                            FixedDataModelElement(
                                                'from_str', b' from '),
                                            DelimitedDataModelElement(
                                                'user', b' '),
                                            FixedDataModelElement(
                                                'brack_str1', b' ('),
                                            IpAddressDataModelElement('ip'),
                                            FixedDataModelElement(
                                                'brack_str2', b')'),
                                        ]),
                                    SequenceModelElement(
                                        'login_failed', [
                                            FixedDataModelElement(
                                                'succ_str',
                                                b'FAILED LOGIN for '),
                                            DelimitedDataModelElement(
                                                'user', b' '),
                                            FixedDataModelElement(
                                                'brack_str1', b' ('),
                                            IpAddressDataModelElement('ip'),
                                            FixedDataModelElement(
                                                'to_str', b') to {'),
                                            DelimitedDataModelElement(
                                                'imap_addr', b'}'),
                                            FixedDataModelElement(
                                                'brack_str2', b'}'),
                                        ]),
                                    SequenceModelElement(
                                        'status', [
                                            FixedDataModelElement(
                                                'status_str',
                                                b'[status] Could not open mailbox "INBOX".'
                                            ),
                                        ]),
                                    SequenceModelElement(
                                        'sync_token', [
                                            FixedDataModelElement(
                                                'sync_token_str',
                                                b'[getSyncToken] IMAP error reported by server.'
                                            ),
                                        ]),
                                    SequenceModelElement(
                                        'auth_failed', [
                                            FixedDataModelElement(
                                                'auth_failed_str',
                                                b'[login] Authentication failed.'
                                            ),
                                        ]),
                                ]),
                            ]),
                            SequenceModelElement('horde', [
                                FixedDataModelElement('succ_str', b'[horde] '),
                                FirstMatchModelElement('horde', [
                                    SequenceModelElement(
                                        'success', [
                                            FixedDataModelElement(
                                                'success_str',
                                                b'Login success for '),
                                            DelimitedDataModelElement(
                                                'user', b' '),
                                            FixedDataModelElement(
                                                'brack_str1', b' to horde ('),
                                            IpAddressDataModelElement('ip'),
                                            FixedDataModelElement(
                                                'brack_str2', b')'),
                                        ]),
                                    SequenceModelElement(
                                        'success', [
                                            FixedDataModelElement(
                                                'success_str', b'User '),
                                            DelimitedDataModelElement(
                                                'user', b' '),
                                            FixedDataModelElement(
                                                'brack_str1',
                                                b' logged out of Horde ('),
                                            IpAddressDataModelElement('ip'),
                                            FixedDataModelElement(
                                                'brack_str2', b')'),
                                        ]),
                                    SequenceModelElement(
                                        'login_failed', [
                                            FixedDataModelElement(
                                                'failed_str',
                                                b'FAILED LOGIN for '),
                                            DelimitedDataModelElement(
                                                'user', b' '),
                                            FixedDataModelElement(
                                                'to_horde_str',
                                                b' to horde ('),
                                            IpAddressDataModelElement('ip'),
                                            FixedDataModelElement(
                                                'brack_str', b')'),
                                        ]),
                                ])
                            ]),
                            SequenceModelElement('function', [
                                FixedWordlistDataModelElement(
                                    'horde_function',
                                    [b'[nag]', b'[turba]', b'[horde]']),
                                FixedDataModelElement('nag_str',
                                                      b' PHP ERROR: '),
                                FirstMatchModelElement('php_error', [
                                    SequenceModelElement(
                                        'declaration', [
                                            FixedDataModelElement(
                                                'declaration_str',
                                                b'Declaration of '),
                                            DelimitedDataModelElement(
                                                'function_name1', b'('),
                                            FixedDataModelElement(
                                                'brack_str1', b'('),
                                            OptionalMatchModelElement(
                                                'arg1',
                                                DelimitedDataModelElement(
                                                    'arg1', b')')),
                                            FixedDataModelElement(
                                                'failed_str',
                                                b') should be compatible with '
                                            ),
                                            DelimitedDataModelElement(
                                                'function_name2', b'('),
                                            FixedDataModelElement(
                                                'brack_str2', b'('),
                                            OptionalMatchModelElement(
                                                'arg2',
                                                DelimitedDataModelElement(
                                                    'arg2', b')')),
                                            FixedDataModelElement(
                                                'brack_str3', b')'),
                                        ]),
                                    FixedDataModelElement(
                                        'file_str',
                                        b'finfo_file(): Empty filename or path'
                                    ),
                                    FixedDataModelElement(
                                        'header_str',
                                        b'Cannot modify header information - headers already sent'
                                    )
                                ])
                            ]),
                            SequenceModelElement('guest', [
                                FixedDataModelElement(
                                    'guest_str',
                                    b'Guest user is not authorized for Horde (Host: '
                                ),
                                IpAddressDataModelElement('ip'),
                                FixedDataModelElement('brack_str', b').')
                            ]),
                            SequenceModelElement('php_error', [
                                FixedDataModelElement('php_error_str',
                                                      b'PHP ERROR: '),
                                DelimitedDataModelElement('msg', b' ['),
                            ]),
                            SequenceModelElement('free_msg', [
                                DelimitedDataModelElement('msg', b' ['),
                            ])
                        ]),
                        FixedDataModelElement('to_str', b' [pid '),
                        DecimalIntegerValueModelElement('pid'),
                        FixedDataModelElement('line_str', b' on line '),
                        DecimalIntegerValueModelElement('line'),
                        FixedDataModelElement('of_str', b' of "'),
                        DelimitedDataModelElement('path', b'"'),
                        FixedDataModelElement('brack_str', b'"]')
                    ]),
                    SequenceModelElement(
                        'cron',
                        [
                            FixedDataModelElement('cron_str', b' CRON['),
                            DecimalIntegerValueModelElement('pid'),
                            FixedDataModelElement('brack_str1', b']: '),
                            FirstMatchModelElement(
                                'cron',
                                [
                                    SequenceModelElement(
                                        'cmd', [
                                            FixedDataModelElement(
                                                'brack_str', b'('),
                                            DelimitedDataModelElement(
                                                'user', b')'),
                                            FixedDataModelElement(
                                                'cmd_str', b') CMD '),
                                            AnyByteDataModelElement('cmd_msg')
                                        ]),
                                    SequenceModelElement(
                                        'session',
                                        [  # This only occurs in auth.log
                                            DelimitedDataModelElement(
                                                'pam', b'('),
                                            FixedDataModelElement(
                                                'brack_str', b'('),
                                            DelimitedDataModelElement(
                                                'name', b')'),
                                            FixedDataModelElement(
                                                'session_str', b'): session '),
                                            FixedWordlistDataModelElement(
                                                'status',
                                                [b'opened', b'closed']),
                                            FixedDataModelElement(
                                                'user_str', b' for user '),
                                            VariableByteDataModelElement(
                                                'user', alphabet),
                                            OptionalMatchModelElement(
                                                'uid',
                                                SequenceModelElement(
                                                    'uid', [
                                                        FixedDataModelElement(
                                                            'uid_str',
                                                            b' by (uid='),
                                                        DecimalIntegerValueModelElement(
                                                            'uid'),
                                                        FixedDataModelElement(
                                                            'brack_str', b')')
                                                    ]))
                                        ])
                                ])
                        ]),
                    SequenceModelElement(
                        'auth',
                        [  # This only occurs in auth.log
                            FixedDataModelElement('auth_str', b' auth: '),
                            DelimitedDataModelElement('pam', b'('),
                            FixedDataModelElement('brack_str', b'('),
                            DelimitedDataModelElement('name', b')'),
                            FixedDataModelElement(
                                'session_str',
                                b'): authentication failure; logname='),
                            OptionalMatchModelElement(
                                'logname',
                                DelimitedDataModelElement('logname', b' ')),
                            FixedDataModelElement('uid_str', b' uid='),
                            DecimalIntegerValueModelElement('uid'),
                            FixedDataModelElement('euid_str', b' euid='),
                            DecimalIntegerValueModelElement('euid'),
                            FixedDataModelElement('tty_str', b' tty='),
                            DelimitedDataModelElement('tty', b' '),
                            FixedDataModelElement('ruser_str', b' ruser='******'ruser', b' '),
                            FixedDataModelElement('rhost_str', b' rhost='),
                            IpAddressDataModelElement('rhost'),
                            OptionalMatchModelElement(
                                'user',
                                SequenceModelElement('user', [
                                    FixedDataModelElement(
                                        'user_str', b'  user='******'user', alphabet)
                                ]))
                        ]),
                    SequenceModelElement('systemd', [
                        FixedDataModelElement('systemd_str', b' systemd['),
                        DecimalIntegerValueModelElement('pid'),
                        FixedDataModelElement('brack_str1', b']: '),
                        FirstMatchModelElement('systemd', [
                            FixedDataModelElement(
                                'php_starting_str',
                                b'Starting Clean php session files...'),
                            FixedDataModelElement(
                                'php_started_str',
                                b'Started Clean php session files.'),
                            FixedDataModelElement(
                                'php_starting_str',
                                b'Starting Cleanup of Temporary Directories...'
                            ),
                            FixedDataModelElement(
                                'php_started_str',
                                b'Started Cleanup of Temporary Directories.'),
                            FixedDataModelElement(
                                'php_started_str',
                                b'Starting Daily apt upgrade and clean activities...'
                            ),
                            FixedDataModelElement(
                                'php_started_str',
                                b'Started Daily apt upgrade and clean activities.'
                            ),
                            FixedDataModelElement(
                                'php_started_str',
                                b'Starting Daily apt download activities...'),
                            FixedDataModelElement(
                                'php_started_str',
                                b'Started Daily apt download activities.'),
                            FixedDataModelElement(
                                'php_started_str',
                                b'Starting Security Auditing Service...'),
                            FixedDataModelElement(
                                'php_started_str',
                                b'Started Security Auditing Service.'),
                            FixedDataModelElement(
                                'php_started_str',
                                b'Stopping Security Auditing Service...'),
                            FixedDataModelElement(
                                'php_started_str',
                                b'Stopped Security Auditing Service.'),
                            FixedDataModelElement(
                                'php_started_str',
                                b'Reloading The Apache HTTP Server.'),
                            FixedDataModelElement(
                                'php_started_str',
                                b'Reloaded The Apache HTTP Server.'),
                            FixedDataModelElement(
                                'php_started_str',
                                b'Mounting Arbitrary Executable File Formats File System...'
                            ),
                            FixedDataModelElement(
                                'php_started_str',
                                b'Mounted Arbitrary Executable File Formats File System.'
                            ),
                            SequenceModelElement('apt', [
                                FixedDataModelElement('apt_str', b'apt'),
                                AnyByteDataModelElement('apt_msg')
                            ]),
                            SequenceModelElement('service', [
                                DelimitedDataModelElement('service', b':'),
                                FixedDataModelElement('col_str', b': '),
                                AnyByteDataModelElement('_msg')
                            ])
                        ]),
                    ]),
                    SequenceModelElement('kernel', [
                        FixedDataModelElement('kernel_str', b' kernel'),
                        OptionalMatchModelElement(
                            'id',
                            SequenceModelElement('id', [
                                FixedDataModelElement('brack_str', b'['),
                                DecimalIntegerValueModelElement('id'),
                                FixedDataModelElement('brack_str2', b']')
                            ])),
                        FixedDataModelElement('col_str', b': '),
                        AnyByteDataModelElement('kernel_msg')
                    ]),
                    SequenceModelElement('augenrules', [
                        FixedDataModelElement('augenrules_str',
                                              b' augenrules['),
                        DecimalIntegerValueModelElement('id'),
                        FixedDataModelElement('brack_str1', b']: '),
                        AnyByteDataModelElement('augenrules_msg')
                    ]),
                    SequenceModelElement('auditd', [
                        FixedDataModelElement('auditd_str', b' auditd['),
                        DecimalIntegerValueModelElement('id'),
                        FixedDataModelElement('brack_str1', b']: '),
                        AnyByteDataModelElement('auditd_msg')
                    ]),
                    SequenceModelElement('auditd2', [
                        FixedDataModelElement('auditd2_str', b' auditd: '),
                        AnyByteDataModelElement('auditd_msg')
                    ]),
                    SequenceModelElement('audispd', [
                        FixedDataModelElement('audispd_str', b' audispd: '),
                        AnyByteDataModelElement('audispd_msg')
                    ]),
                    SequenceModelElement('liblogging', [
                        FixedDataModelElement('liblogging_str',
                                              b' liblogging-stdlog: '),
                        AnyByteDataModelElement('liblogging_msg')
                    ]),
                    SequenceModelElement('freshclam', [
                        FixedDataModelElement('freshclam_str', b' freshclam['),
                        DecimalIntegerValueModelElement('id'),
                        FixedDataModelElement('brack_str1', b']: '),
                        AnyByteDataModelElement('freshclam_msg')
                    ]),
                    SequenceModelElement('dhclient', [
                        FixedDataModelElement('dhclient_str', b' dhclient['),
                        DecimalIntegerValueModelElement('id'),
                        FixedDataModelElement('brack_str1', b']: '),
                        FirstMatchModelElement('dhclient', [
                            SequenceModelElement('dhcprequest', [
                                FixedDataModelElement('dhcprequest_str',
                                                      b'DHCPREQUEST of '),
                                IpAddressDataModelElement('src_ip'),
                                FixedDataModelElement('on_str', b' on '),
                                DelimitedDataModelElement(
                                    'network_interface', b' '),
                                FixedDataModelElement('to_str', b' to '),
                                IpAddressDataModelElement('dst_ip'),
                                FixedDataModelElement('port_str', b' port '),
                                DecimalIntegerValueModelElement('port')
                            ]),
                            SequenceModelElement('dhcpack', [
                                FixedDataModelElement('dhcpack_str',
                                                      b'DHCPACK of '),
                                IpAddressDataModelElement('dst_ip'),
                                FixedDataModelElement('on_str', b' from '),
                                IpAddressDataModelElement('src_ip')
                            ]),
                            SequenceModelElement('bound', [
                                FixedDataModelElement('bound_str',
                                                      b'bound to '),
                                IpAddressDataModelElement('ip'),
                                FixedDataModelElement('renewal_str',
                                                      b' -- renewal in '),
                                DecimalIntegerValueModelElement('seconds'),
                                FixedDataModelElement('seconds_str',
                                                      b' seconds.')
                            ]),
                        ]),
                    ]),
                ])
        ])

    return model
예제 #24
0
    def test4get_match_element_no_match(self):
        """Parse not matching substring from MatchContext and check if the MatchContext was not changed."""
        data = b"string wordlist"
        match_context = DummyMatchContext(data)
        fixed_wordlist_dme = FixedWordlistDataModelElement(
            self.id_, self.wordlist)
        match_element = fixed_wordlist_dme.get_match_element(
            self.path, match_context)
        self.compare_no_match_results(data, match_element, match_context)

        data = b"wor wordlist"
        match_context = DummyMatchContext(data)
        fixed_wordlist_dme = FixedWordlistDataModelElement(
            self.id_, self.wordlist)
        match_element = fixed_wordlist_dme.get_match_element(
            self.path, match_context)
        self.compare_no_match_results(data, match_element, match_context)

        data = b"0 wordlist"
        match_context = DummyMatchContext(data)
        fixed_wordlist_dme = FixedWordlistDataModelElement(
            self.id_, self.wordlist)
        match_element = fixed_wordlist_dme.get_match_element(
            self.path, match_context)
        self.compare_no_match_results(data, match_element, match_context)

        data = b"1 word"
        match_context = DummyMatchContext(data)
        fixed_wordlist_dme = FixedWordlistDataModelElement(
            self.id_, self.wordlist)
        match_element = fixed_wordlist_dme.get_match_element(
            self.path, match_context)
        self.compare_no_match_results(data, match_element, match_context)
예제 #25
0
def get_model():
    """Return a model for su session information messages after any standard logging preamble, e.g. from syslog."""
    type_children = [
        SequenceModelElement("build-stack", [
            FixedDataModelElement("s0",
                                  b"building new pluginstance stack: \""),
            DelimitedDataModelElement("stack", b"\""),
            FixedDataModelElement("s1", b"\"")
        ]),
        SequenceModelElement(
            "nfct-event",
            [
                FixedDataModelElement("s0", b"[DESTROY] ORIG: SRC="),
                IpAddressDataModelElement("osrcip"),
                FixedDataModelElement("s1", b" DST="),
                IpAddressDataModelElement("odstip"),
                FixedDataModelElement("s2", b" PROTO="),
                FixedWordlistDataModelElement("proto", [b"TCP", b"UDP"]),
                FixedDataModelElement("s3", b" SPT="),
                DecimalIntegerValueModelElement("ospt"),
                FixedDataModelElement("s4", b" DPT="),
                DecimalIntegerValueModelElement("odpt"),
                FixedDataModelElement("s5", b" PKTS="),
                DecimalIntegerValueModelElement("opkts"),
                FixedDataModelElement("s6", b" BYTES="),
                DecimalIntegerValueModelElement("obytes"),
                FixedDataModelElement("s7", b" , REPLY: SRC="),
                IpAddressDataModelElement("rsrcip"),
                FixedDataModelElement("s8", b" DST="),
                IpAddressDataModelElement("rdstip"),
                FixedDataModelElement("s9", b" PROTO="),
                FixedWordlistDataModelElement("rproto", [b"TCP", b"UDP"]),
                FixedDataModelElement("s10", b" SPT="),
                DecimalIntegerValueModelElement("rspt"),
                FixedDataModelElement("s11", b" DPT="),
                DecimalIntegerValueModelElement("rdpt"),
                FixedDataModelElement("s12", b" PKTS="),
                DecimalIntegerValueModelElement("rpkts"),
                FixedDataModelElement("s13", b" BYTES="),
                DecimalIntegerValueModelElement("rbytes"),
                # No additional whitespace from Ubuntu Trusty 14.04 on.
                OptionalMatchModelElement("tail",
                                          FixedDataModelElement("s0", b" "))
            ]),
        FixedDataModelElement("nfct-plugin",
                              b"NFCT plugin working in event mode"),
        FixedDataModelElement("reopen", b"reopening capture file"),
        FixedDataModelElement("signal",
                              b"signal received, calling pluginstances"),
        FixedDataModelElement("uidchange", b"Changing UID / GID"),
        SequenceModelElement("seq", [
            FixedDataModelElement("s0", b"id=\""),
            DecimalIntegerValueModelElement("id"),
            FixedDataModelElement("s1", b"\" severity=\""),
            DelimitedDataModelElement("severity", b"\""),
            FixedDataModelElement("s2", b"\" sys=\""),
            DelimitedDataModelElement("sys", b"\""),
            FixedDataModelElement("s3", b"\" sub=\""),
            DelimitedDataModelElement("sub", b"\""),
            FixedDataModelElement("s4", b"\" name=\""),
            DelimitedDataModelElement("name", b"\""),
            FixedDataModelElement("s5", b"\" action=\""),
            DelimitedDataModelElement("action", b"\""),
            FixedDataModelElement("s6", b"\" fwrule=\""),
            DelimitedDataModelElement("fwrule", b"\""),
            FixedDataModelElement("s7", b"\" initf=\""),
            DelimitedDataModelElement("initf", b"\""),
            FixedDataModelElement("s8", b"\" srcmac=\""),
            DelimitedDataModelElement("srcmac", b"\""),
            FixedDataModelElement("s9", b"\" dstmac=\""),
            DelimitedDataModelElement("dstmac", b"\""),
            FixedDataModelElement("s10", b"\" srcip=\""),
            DelimitedDataModelElement("srcip", b"\""),
            FixedDataModelElement("s11", b"\" dstip=\""),
            DelimitedDataModelElement("dstip", b"\""),
            FixedDataModelElement("s12", b"\" proto=\""),
            DelimitedDataModelElement("proto", b"\""),
            FixedDataModelElement("s13", b"\" length=\""),
            DelimitedDataModelElement("length", b"\""),
            FixedDataModelElement("s14", b"\" tos=\""),
            DelimitedDataModelElement("tos", b"\""),
            FixedDataModelElement("s15", b"\" prec=\""),
            DelimitedDataModelElement("prec", b"\""),
            FixedDataModelElement("s16", b"\" ttl=\""),
            DelimitedDataModelElement("ttl", b"\""),
            FixedDataModelElement("s17", b"\" srcport=\""),
            DelimitedDataModelElement("srcport", b"\""),
            FixedDataModelElement("s18", b"\" dstport=\""),
            DelimitedDataModelElement("dstport", b"\""),
            FixedDataModelElement("s19", b"\" tcpflags=\""),
            DelimitedDataModelElement("tcpflags", b"\""),
            FixedDataModelElement("s20", b"\"")
        ])
    ]

    # Netflow entry
    model = SequenceModelElement("ulogd", [
        FixedDataModelElement("sname", b"ulogd["),
        DecimalIntegerValueModelElement("pid"),
        FixedDataModelElement("s0", b"]: "),
        FirstMatchModelElement("msg", type_children)
    ])
    return model
def get_model():
    """Return a model to parse Suricata Event logs from the AIT-LDS."""
    conn = SequenceModelElement('conn', [
        FixedDataModelElement('src_ip_str', b'"src_ip":"'),
        FirstMatchModelElement('ip', [
            SequenceModelElement('ipv4', [
                IpAddressDataModelElement('src_ip'),
                FixedDataModelElement('src_port_str', b'","src_port":'),
                DecimalIntegerValueModelElement('src_port'),
                FixedDataModelElement('dest_ip_str', b',"dest_ip":"'),
                IpAddressDataModelElement('dest_ip'),
                FixedDataModelElement('dest_port_str', b'","dest_port":'),
                DecimalIntegerValueModelElement('dest_port'),
                FixedDataModelElement('proto_str', b',"proto":"'),
                DelimitedDataModelElement('proto', b'"'),
                FixedDataModelElement('quote', b'"')
            ]),
            SequenceModelElement('ipv6', [
                DelimitedDataModelElement('src_ip', b'"'),
                FixedDataModelElement('dest_ip_str', b'","dest_ip":"'),
                DelimitedDataModelElement('dest_ip', b'"'),
                FixedDataModelElement('proto_str', b'","proto":"'),
                DelimitedDataModelElement('proto', b'"'),
                FixedDataModelElement('icmp_type_str', b'","icmp_type":'),
                DecimalIntegerValueModelElement('icmp_type'),
                FixedDataModelElement('icmp_code_str', b',"icmp_code":'),
                DecimalIntegerValueModelElement('icmp_code'),
            ]),
        ])
    ])

    http = SequenceModelElement('http', [
        FixedDataModelElement('hostname_str', b',"http":{"hostname":"'),
        DelimitedDataModelElement('hostname', b'"'),
        FixedDataModelElement('url_str', b'","url":"'),
        DelimitedDataModelElement('url', b'"', escape=b'\\'),
        FixedDataModelElement('http_user_agent_str', b'","http_user_agent":"'),
        DelimitedDataModelElement('http_user_agent', b'"'),
        OptionalMatchModelElement(
            'content_type',
            SequenceModelElement('content_type', [
                FixedDataModelElement('http_content_type_str',
                                      b'","http_content_type":"'),
                DelimitedDataModelElement('http_content_type', b'"'),
            ])),
        OptionalMatchModelElement(
            'http_refer',
            SequenceModelElement('http_refer', [
                FixedDataModelElement('http_refer_str', b'","http_refer":"'),
                DelimitedDataModelElement('http_refer', b'"'),
            ])),
        FixedDataModelElement('http_method_str', b'","http_method":"'),
        DelimitedDataModelElement('http_method', b'"'),
        FixedDataModelElement('protocol_str', b'","protocol":"'),
        DelimitedDataModelElement('protocol', b'"'),
        FixedDataModelElement('quote_str', b'"'),
        OptionalMatchModelElement(
            'status',
            SequenceModelElement('status', [
                FixedDataModelElement('status_str', b',"status":'),
                DecimalIntegerValueModelElement('status'),
            ])),
        OptionalMatchModelElement(
            'redirect',
            SequenceModelElement('redirect', [
                FixedDataModelElement('redirect_str', b',"redirect":"'),
                DelimitedDataModelElement('redirect', b'"'),
                FixedDataModelElement('quote_str', b'"')
            ])),
        FixedDataModelElement('length_str', b',"length":'),
        DecimalIntegerValueModelElement('length'),
        FixedDataModelElement('brack_str', b'}')
    ])

    model = SequenceModelElement('model', [
        FixedDataModelElement('time_str', b'{"timestamp":"'),
        DateTimeModelElement('time', b'%Y-%m-%dT%H:%M:%S.%f'),
        FixedDataModelElement('plus_sign', b'+'),
        DecimalIntegerValueModelElement('tz'),
        FixedDataModelElement('comma_str', b'",'),
        OptionalMatchModelElement(
            'flow_id',
            SequenceModelElement('flow_id', [
                FixedDataModelElement('flow_id_str', b'"flow_id":'),
                DecimalIntegerValueModelElement('flow_id'),
                FixedDataModelElement('comma_str', b',')
            ])),
        OptionalMatchModelElement(
            'in_iface',
            SequenceModelElement('in_iface', [
                FixedDataModelElement('in_iface_str', b'"in_iface":"'),
                DelimitedDataModelElement('in_iface', b'"'),
                FixedDataModelElement('comma_str', b'",')
            ])),
        FixedDataModelElement('event_type_str', b'"event_type":"'),
        FirstMatchModelElement('event_type', [
            SequenceModelElement('dns', [
                FixedDataModelElement('dns_str', b'dns",'),
                conn,
                SequenceModelElement('dns', [
                    FixedDataModelElement('type_str', b',"dns":{"type":"'),
                    DelimitedDataModelElement('type', b'"'),
                    FixedDataModelElement('id_str', b'","id":'),
                    DecimalIntegerValueModelElement('id'),
                    OptionalMatchModelElement(
                        'rcode',
                        SequenceModelElement('rcode', [
                            FixedDataModelElement('rcode_str', b',"rcode":"'),
                            DelimitedDataModelElement('rcode', b'"'),
                            FixedDataModelElement('quote_str', b'"')
                        ])),
                    FixedDataModelElement('rrname_str', b',"rrname":"'),
                    DelimitedDataModelElement('rrname', b'"'),
                    OptionalMatchModelElement(
                        'rrtype',
                        SequenceModelElement('rrtype', [
                            FixedDataModelElement('rrtype_str',
                                                  b'","rrtype":"'),
                            DelimitedDataModelElement('rrtype', b'"')
                        ])),
                    FixedDataModelElement('quote', b'"'),
                    OptionalMatchModelElement(
                        'tx_id',
                        SequenceModelElement('tx_id', [
                            FixedDataModelElement('tx_id_str', b',"tx_id":'),
                            DecimalIntegerValueModelElement('tx_id')
                        ])),
                    OptionalMatchModelElement(
                        'ttl',
                        SequenceModelElement('ttl', [
                            FixedDataModelElement('ttl_str', b',"ttl":'),
                            DecimalIntegerValueModelElement('ttl')
                        ])),
                    OptionalMatchModelElement(
                        'rdata',
                        SequenceModelElement('rdata', [
                            FixedDataModelElement('rdata_str', b',"rdata":"'),
                            DelimitedDataModelElement('rdata', b'"'),
                            FixedDataModelElement('quote_str', b'"')
                        ])),
                    FixedDataModelElement('brack_str', b'}}')
                ]),
            ]),
            SequenceModelElement('flow', [
                FixedDataModelElement('flow_str', b'flow",'),
                conn,
                OptionalMatchModelElement(
                    'app_proto',
                    SequenceModelElement('app_proto', [
                        FixedDataModelElement('app_proto_str',
                                              b',"app_proto":"'),
                        DelimitedDataModelElement('app_proto', b'"'),
                        FixedDataModelElement('quote_str', b'"')
                    ])),
                OptionalMatchModelElement(
                    'app_proto_tc',
                    SequenceModelElement('app_proto_tc', [
                        FixedDataModelElement('app_proto_tc_str',
                                              b',"app_proto_tc":"'),
                        DelimitedDataModelElement('app_proto_tc', b'"'),
                        FixedDataModelElement('quote_str', b'"')
                    ])),
                SequenceModelElement('flow', [
                    FixedDataModelElement('pkts_toserver_str',
                                          b',"flow":{"pkts_toserver":'),
                    DecimalIntegerValueModelElement('pkts_toserver'),
                    FixedDataModelElement('pkts_toclient_str',
                                          b',"pkts_toclient":'),
                    DecimalIntegerValueModelElement('pkts_toclient'),
                    FixedDataModelElement('bytes_toserver_str',
                                          b',"bytes_toserver":'),
                    DecimalIntegerValueModelElement('bytes_toserver'),
                    FixedDataModelElement('bytes_toclient_str',
                                          b',"bytes_toclient":'),
                    DecimalIntegerValueModelElement('bytes_toclient'),
                    FixedDataModelElement('start_str', b',"start":"'),
                    DelimitedDataModelElement('start', b'"'),
                    FixedDataModelElement('end_str', b'","end":"'),
                    DelimitedDataModelElement('end', b'"'),
                    FixedDataModelElement('age_str', b'","age":'),
                    DecimalIntegerValueModelElement('age'),
                    FixedDataModelElement('state_str', b',"state":"'),
                    DelimitedDataModelElement('state', b'"'),
                    FixedDataModelElement('reason_str', b'","reason":"'),
                    DelimitedDataModelElement('reason', b'"'),
                    FixedDataModelElement('alerted_str', b'","alerted":'),
                    FixedWordlistDataModelElement('alerted',
                                                  [b'true', b'false']),
                    FixedDataModelElement('brack_str1', b'}'),
                    OptionalMatchModelElement(
                        'tcp',
                        SequenceModelElement('tcp', [
                            FixedDataModelElement('tcp_flags_str',
                                                  b',"tcp":{"tcp_flags":"'),
                            HexStringModelElement('tcp_flags'),
                            FixedDataModelElement('tcp_flags_ts_str',
                                                  b'","tcp_flags_ts":"'),
                            HexStringModelElement('tcp_flags_ts'),
                            FixedDataModelElement('tcp_flags_tc_str',
                                                  b'","tcp_flags_tc":"'),
                            HexStringModelElement('tcp_flags_tc'),
                            OptionalMatchModelElement(
                                'flags',
                                SequenceModelElement('flags', [
                                    FixedDataModelElement(
                                        'syn_str', b'","syn":'),
                                    FixedWordlistDataModelElement(
                                        'syn', [b'true', b'false']),
                                    OptionalMatchModelElement(
                                        'fin',
                                        SequenceModelElement(
                                            'fin', [
                                                FixedDataModelElement(
                                                    'fin_str', b',"fin":'),
                                                FixedWordlistDataModelElement(
                                                    'fin',
                                                    [b'true', b'false']),
                                            ])),
                                    OptionalMatchModelElement(
                                        'rst',
                                        SequenceModelElement(
                                            'rst', [
                                                FixedDataModelElement(
                                                    'rst_str', b',"rst":'),
                                                FixedWordlistDataModelElement(
                                                    'rst',
                                                    [b'true', b'false']),
                                            ])),
                                    OptionalMatchModelElement(
                                        'psh',
                                        SequenceModelElement(
                                            'psh', [
                                                FixedDataModelElement(
                                                    'psh_str', b',"psh":'),
                                                FixedWordlistDataModelElement(
                                                    'psh',
                                                    [b'true', b'false']),
                                            ])),
                                    FixedDataModelElement(
                                        'ack_str', b',"ack":'),
                                    FixedWordlistDataModelElement(
                                        'ack', [b'true', b'false']),
                                    FixedDataModelElement(
                                        'tcp_state_str', b',"state":"'),
                                    DelimitedDataModelElement(
                                        'tcp_state', b'"'),
                                ])),
                            FixedDataModelElement('tcp_brack_str', b'"}'),
                        ])),
                    FixedDataModelElement('brack_str2', b'}')
                ]),
            ]),
            SequenceModelElement('http', [
                FixedDataModelElement('http_str', b'http",'), conn,
                FixedDataModelElement('tx_id_str', b',"tx_id":'),
                DecimalIntegerValueModelElement('tx_id'), http,
                FixedDataModelElement('brack_str', b'}')
            ]),
            SequenceModelElement('fileinfo', [
                FixedDataModelElement('fileinfo_str', b'fileinfo",'),
                conn,
                http,
                FixedDataModelElement('app_proto_str', b',"app_proto":"'),
                DelimitedDataModelElement('app_proto', b'"'),
                SequenceModelElement('fileinfo', [
                    FixedDataModelElement('fileinfo_str', b'","fileinfo":{'),
                    OptionalMatchModelElement(
                        'filename',
                        SequenceModelElement('filename', [
                            FixedDataModelElement('filename_str',
                                                  b'"filename":"'),
                            DelimitedDataModelElement('filename', b'"'),
                            FixedDataModelElement('quote_str', b'",')
                        ])),
                    FixedDataModelElement('state_str', b'"state":"'),
                    DelimitedDataModelElement('state', b'"'),
                    FixedDataModelElement('stored_str', b'","stored":'),
                    FixedWordlistDataModelElement('stored',
                                                  [b'true', b'false']),
                    FixedDataModelElement('size_str', b',"size":'),
                    DecimalIntegerValueModelElement('size'),
                    FixedDataModelElement('tx_id_str', b',"tx_id":'),
                    DecimalIntegerValueModelElement('tx_id'),
                    FixedDataModelElement('brack_str', b'}}')
                ]),
            ]),
            SequenceModelElement('stats', [
                FixedDataModelElement('stats_str', b'stats",'),
                FixedDataModelElement('uptime_str', b'"stats":{"uptime":'),
                DecimalIntegerValueModelElement('uptime'),
                SequenceModelElement('capture', [
                    FixedDataModelElement('capture_str', b',"capture":{'),
                    FixedDataModelElement('kernel_packets_str',
                                          b'"kernel_packets":'),
                    DecimalIntegerValueModelElement('kernel_packets'),
                    FixedDataModelElement('kernel_drops_str',
                                          b',"kernel_drops":'),
                    DecimalIntegerValueModelElement('kernel_drops'),
                    FixedDataModelElement('brack_str', b'}')
                ]),
                SequenceModelElement('decoder', [
                    FixedDataModelElement('pkts_str', b',"decoder":{"pkts":'),
                    DecimalIntegerValueModelElement('pkts'),
                    FixedDataModelElement('bytes_str', b',"bytes":'),
                    DecimalIntegerValueModelElement('bytes'),
                    FixedDataModelElement('invalid_str', b',"invalid":'),
                    DecimalIntegerValueModelElement('invalid'),
                    FixedDataModelElement('ipv4_str', b',"ipv4":'),
                    DecimalIntegerValueModelElement('ipv4'),
                    FixedDataModelElement('ipv6_str', b',"ipv6":'),
                    DecimalIntegerValueModelElement('ipv6'),
                    FixedDataModelElement('ethernet_str', b',"ethernet":'),
                    DecimalIntegerValueModelElement('ethernet'),
                    FixedDataModelElement('raw_str', b',"raw":'),
                    DecimalIntegerValueModelElement('raw'),
                    FixedDataModelElement('null_str', b',"null":'),
                    DecimalIntegerValueModelElement('null'),
                    FixedDataModelElement('sll_str', b',"sll":'),
                    DecimalIntegerValueModelElement('sll'),
                    FixedDataModelElement('tcp_str', b',"tcp":'),
                    DecimalIntegerValueModelElement('tcp'),
                    FixedDataModelElement('udp_str', b',"udp":'),
                    DecimalIntegerValueModelElement('udp'),
                    FixedDataModelElement('sctp_str', b',"sctp":'),
                    DecimalIntegerValueModelElement('sctp'),
                    FixedDataModelElement('icmpv4_str', b',"icmpv4":'),
                    DecimalIntegerValueModelElement('icmpv4'),
                    FixedDataModelElement('icmpv6_str', b',"icmpv6":'),
                    DecimalIntegerValueModelElement('icmpv6'),
                    FixedDataModelElement('ppp_str', b',"ppp":'),
                    DecimalIntegerValueModelElement('ppp'),
                    FixedDataModelElement('pppoe_str', b',"pppoe":'),
                    DecimalIntegerValueModelElement('pppoe'),
                    FixedDataModelElement('gre_str', b',"gre":'),
                    DecimalIntegerValueModelElement('gre'),
                    FixedDataModelElement('vlan_str', b',"vlan":'),
                    DecimalIntegerValueModelElement('vlan'),
                    FixedDataModelElement('vlan_qinq_str', b',"vlan_qinq":'),
                    DecimalIntegerValueModelElement('vlan_qinq'),
                    FixedDataModelElement('teredo_str', b',"teredo":'),
                    DecimalIntegerValueModelElement('teredo'),
                    FixedDataModelElement('ipv4_in_ipv6_str',
                                          b',"ipv4_in_ipv6":'),
                    DecimalIntegerValueModelElement('ipv4_in_ipv6'),
                    FixedDataModelElement('ipv6_in_ipv6_str',
                                          b',"ipv6_in_ipv6":'),
                    DecimalIntegerValueModelElement('ipv6_in_ipv6'),
                    FixedDataModelElement('mpls_str', b',"mpls":'),
                    DecimalIntegerValueModelElement('mpls'),
                    FixedDataModelElement('avg_pkt_size_str',
                                          b',"avg_pkt_size":'),
                    DecimalIntegerValueModelElement('avg_pkt_size'),
                    FixedDataModelElement('max_pkt_size_str',
                                          b',"max_pkt_size":'),
                    DecimalIntegerValueModelElement('max_pkt_size'),
                    FixedDataModelElement('erspan_str', b',"erspan":'),
                    DecimalIntegerValueModelElement('erspan'),
                    SequenceModelElement('ipraw', [
                        FixedDataModelElement(
                            'invalid_ip_version_str',
                            b',"ipraw":{"invalid_ip_version":'),
                        DecimalIntegerValueModelElement('invalid_ip_version'),
                    ]),
                    SequenceModelElement('ltnull', [
                        FixedDataModelElement('ipraw_pkt_too_small_str',
                                              b'},"ltnull":{"pkt_too_small":'),
                        DecimalIntegerValueModelElement('ipraw_pkt_too_small'),
                        FixedDataModelElement('unsupported_type',
                                              b',"unsupported_type":'),
                        DecimalIntegerValueModelElement('unsupported_type'),
                    ]),
                    SequenceModelElement('dce', [
                        FixedDataModelElement('dce_pkt_too_small_str',
                                              b'},"dce":{"pkt_too_small":'),
                        DecimalIntegerValueModelElement('dce_pkt_too_small'),
                        FixedDataModelElement('brack_str', b'}')
                    ])
                ]),
                SequenceModelElement('flow', [
                    FixedDataModelElement('memcap_str',
                                          b'},"flow":{"memcap":'),
                    DecimalIntegerValueModelElement('memcap'),
                    FixedDataModelElement('spare_str', b',"spare":'),
                    DecimalIntegerValueModelElement('spare'),
                    FixedDataModelElement('emerg_mode_entered_str',
                                          b',"emerg_mode_entered":'),
                    DecimalIntegerValueModelElement('emerg_mode_entered'),
                    FixedDataModelElement('emerg_mode_over_str',
                                          b',"emerg_mode_over":'),
                    DecimalIntegerValueModelElement('emerg_mode_over'),
                    FixedDataModelElement('tcp_reuse_str', b',"tcp_reuse":'),
                    DecimalIntegerValueModelElement('tcp_reuse'),
                    FixedDataModelElement('memuse_str', b',"memuse":'),
                    DecimalIntegerValueModelElement('memuse'),
                ]),
                SequenceModelElement('defrag', [
                    SequenceModelElement('ipv4', [
                        FixedDataModelElement(
                            'fragments_str',
                            b'},"defrag":{"ipv4":{"fragments":'),
                        DecimalIntegerValueModelElement('fragments'),
                        FixedDataModelElement('reassembled_str',
                                              b',"reassembled":'),
                        DecimalIntegerValueModelElement('reassembled_str'),
                        FixedDataModelElement('timeouts_str', b',"timeouts":'),
                        DecimalIntegerValueModelElement('timeouts'),
                    ]),
                    SequenceModelElement('ipv6', [
                        FixedDataModelElement('fragments_str',
                                              b'},"ipv6":{"fragments":'),
                        DecimalIntegerValueModelElement('fragments'),
                        FixedDataModelElement('reassembled_str',
                                              b',"reassembled":'),
                        DecimalIntegerValueModelElement('reassembled_str'),
                        FixedDataModelElement('timeouts_str', b',"timeouts":'),
                        DecimalIntegerValueModelElement('timeouts'),
                    ]),
                    FixedDataModelElement('max_frag_hits_str',
                                          b'},"max_frag_hits":'),
                    DecimalIntegerValueModelElement('max_frag_hits'),
                ]),
                SequenceModelElement('tcp', [
                    FixedDataModelElement('sessions_str',
                                          b'},"tcp":{"sessions":'),
                    DecimalIntegerValueModelElement('sessions'),
                    FixedDataModelElement('ssn_memcap_drop_str',
                                          b',"ssn_memcap_drop":'),
                    DecimalIntegerValueModelElement('ssn_memcap_drop'),
                    FixedDataModelElement('pseudo_str', b',"pseudo":'),
                    DecimalIntegerValueModelElement('pseudo'),
                    FixedDataModelElement('pseudo_failed_str',
                                          b',"pseudo_failed":'),
                    DecimalIntegerValueModelElement('pseudo_failed'),
                    FixedDataModelElement('invalid_checksum_str',
                                          b',"invalid_checksum":'),
                    DecimalIntegerValueModelElement('invalid_checksum'),
                    FixedDataModelElement('no_flow_str', b',"no_flow":'),
                    DecimalIntegerValueModelElement('no_flow'),
                    FixedDataModelElement('syn_str', b',"syn":'),
                    DecimalIntegerValueModelElement('syn'),
                    FixedDataModelElement('synack_str', b',"synack":'),
                    DecimalIntegerValueModelElement('synack'),
                    FixedDataModelElement('rst_str', b',"rst":'),
                    DecimalIntegerValueModelElement('rst'),
                    FixedDataModelElement('segment_memcap_drop_str',
                                          b',"segment_memcap_drop":'),
                    DecimalIntegerValueModelElement('segment_memcap_drop'),
                    FixedDataModelElement('stream_depth_reached_str',
                                          b',"stream_depth_reached":'),
                    DecimalIntegerValueModelElement('stream_depth_reached'),
                    FixedDataModelElement('reassembly_gap_str',
                                          b',"reassembly_gap":'),
                    DecimalIntegerValueModelElement('reassembly_gap'),
                    FixedDataModelElement('memuse_str', b',"memuse":'),
                    DecimalIntegerValueModelElement('memuse'),
                    FixedDataModelElement('reassembly_memuse_str',
                                          b',"reassembly_memuse":'),
                    DecimalIntegerValueModelElement('reassembly_memuse'),
                ]),
                SequenceModelElement('detect', [
                    FixedDataModelElement('alert_str',
                                          b'},"detect":{"alert":'),
                    DecimalIntegerValueModelElement('alert')
                ]),
                SequenceModelElement('app_layer', [
                    SequenceModelElement('flow', [
                        FixedDataModelElement(
                            'http_str', b'},"app_layer":{"flow":{"http":'),
                        DecimalIntegerValueModelElement('http'),
                        FixedDataModelElement('ftp_str', b',"ftp":'),
                        DecimalIntegerValueModelElement('ftp'),
                        FixedDataModelElement('smtp_str', b',"smtp":'),
                        DecimalIntegerValueModelElement('smtp'),
                        FixedDataModelElement('tls_str', b',"tls":'),
                        DecimalIntegerValueModelElement('tls'),
                        FixedDataModelElement('ssh_str', b',"ssh":'),
                        DecimalIntegerValueModelElement('ssh'),
                        FixedDataModelElement('imap_str', b',"imap":'),
                        DecimalIntegerValueModelElement('imap'),
                        FixedDataModelElement('msn_str', b',"msn":'),
                        DecimalIntegerValueModelElement('msn'),
                        FixedDataModelElement('smb_str', b',"smb":'),
                        DecimalIntegerValueModelElement('smb'),
                        FixedDataModelElement('dcerpc_tcp_str',
                                              b',"dcerpc_tcp":'),
                        DecimalIntegerValueModelElement('dcerpc_tcp'),
                        FixedDataModelElement('dns_tcp_str', b',"dns_tcp":'),
                        DecimalIntegerValueModelElement('dns_tcp'),
                        FixedDataModelElement('failed_tcp_str',
                                              b',"failed_tcp":'),
                        DecimalIntegerValueModelElement('failed_tcp'),
                        FixedDataModelElement('dcerpc_udp_str',
                                              b',"dcerpc_udp":'),
                        DecimalIntegerValueModelElement('dcerpc_udp'),
                        FixedDataModelElement('dns_udp_str', b',"dns_udp":'),
                        DecimalIntegerValueModelElement('dns_udp'),
                        FixedDataModelElement('failed_udp_str',
                                              b',"failed_udp":'),
                        DecimalIntegerValueModelElement('failed_udp'),
                    ]),
                    SequenceModelElement('tx', [
                        FixedDataModelElement('http_str', b'},"tx":{"http":'),
                        DecimalIntegerValueModelElement('http'),
                        FixedDataModelElement('smtp_str', b',"smtp":'),
                        DecimalIntegerValueModelElement('smtp'),
                        FixedDataModelElement('tls_str', b',"tls":'),
                        DecimalIntegerValueModelElement('tls'),
                        FixedDataModelElement('dns_tcp_str', b',"dns_tcp":'),
                        DecimalIntegerValueModelElement('dns_tcp'),
                        FixedDataModelElement('dns_udp_str', b',"dns_udp":'),
                        DecimalIntegerValueModelElement('dns_udp'),
                    ])
                ]),
                SequenceModelElement('flow_mgr', [
                    FixedDataModelElement('closed_pruned_str',
                                          b'}},"flow_mgr":{"closed_pruned":'),
                    DecimalIntegerValueModelElement('closed_pruned'),
                    FixedDataModelElement('new_pruned_str', b',"new_pruned":'),
                    DecimalIntegerValueModelElement('new_pruned'),
                    FixedDataModelElement('est_pruned_str', b',"est_pruned":'),
                    DecimalIntegerValueModelElement('est_pruned'),
                    FixedDataModelElement('bypassed_pruned_str',
                                          b',"bypassed_pruned":'),
                    DecimalIntegerValueModelElement('bypassed_pruned'),
                    FixedDataModelElement('flows_checked_str',
                                          b',"flows_checked":'),
                    DecimalIntegerValueModelElement('flows_checked'),
                    FixedDataModelElement('flows_notimeout_str',
                                          b',"flows_notimeout":'),
                    DecimalIntegerValueModelElement('flows_notimeout'),
                    FixedDataModelElement('flows_timeout_str',
                                          b',"flows_timeout":'),
                    DecimalIntegerValueModelElement('flows_timeout'),
                    FixedDataModelElement('flows_timeout_inuse_str',
                                          b',"flows_timeout_inuse":'),
                    DecimalIntegerValueModelElement('flows_timeout_inuse'),
                    FixedDataModelElement('flows_removed_str',
                                          b',"flows_removed":'),
                    DecimalIntegerValueModelElement('flows_removed'),
                    FixedDataModelElement('rows_checked_str',
                                          b',"rows_checked":'),
                    DecimalIntegerValueModelElement('rows_checked'),
                    FixedDataModelElement('rows_skipped_str',
                                          b',"rows_skipped":'),
                    DecimalIntegerValueModelElement('rows_skipped'),
                    FixedDataModelElement('rows_empty_str', b',"rows_empty":'),
                    DecimalIntegerValueModelElement('rows_empty'),
                    FixedDataModelElement('rows_busy_str', b',"rows_busy":'),
                    DecimalIntegerValueModelElement('rows_busy'),
                    FixedDataModelElement('rows_maxlen_str',
                                          b',"rows_maxlen":'),
                    DecimalIntegerValueModelElement('rows_maxlen'),
                ]),
                SequenceModelElement('dns', [
                    FixedDataModelElement('memuse_str', b'},"dns":{"memuse":'),
                    DecimalIntegerValueModelElement('memuse'),
                    FixedDataModelElement('memcap_state_str',
                                          b',"memcap_state":'),
                    DecimalIntegerValueModelElement('memcap_state'),
                    FixedDataModelElement('memcap_global_str',
                                          b',"memcap_global":'),
                    DecimalIntegerValueModelElement('memcap_global'),
                ]),
                SequenceModelElement('http', [
                    FixedDataModelElement('memuse_str',
                                          b'},"http":{"memuse":'),
                    DecimalIntegerValueModelElement('memuse'),
                    FixedDataModelElement('memcap_str', b',"memcap":'),
                    DecimalIntegerValueModelElement('memcap'),
                ]),
                FixedDataModelElement('quote_str', b'}}}')
            ]),
            SequenceModelElement('tls', [
                FixedDataModelElement('tls_str', b'tls",'), conn,
                SequenceModelElement('tls', [
                    FixedDataModelElement('subject_str',
                                          b',"tls":{"subject":"'),
                    DelimitedDataModelElement('subject', b'"'),
                    FixedDataModelElement('issuerdn_str', b'","issuerdn":"'),
                    DelimitedDataModelElement('issuerdn', b'"'),
                    FixedDataModelElement('fingerprint_str',
                                          b'","fingerprint":"'),
                    DelimitedDataModelElement('fingerprint', b'"'),
                    OptionalMatchModelElement(
                        'sni',
                        SequenceModelElement('sni', [
                            FixedDataModelElement('sni_str', b'","sni":"'),
                            DelimitedDataModelElement('sni', b'"'),
                        ])),
                    FixedDataModelElement('version_str', b'","version":"'),
                    DelimitedDataModelElement('version', b'"'),
                    FixedDataModelElement('notbefore_str', b'","notbefore":"'),
                    DelimitedDataModelElement('notbefore', b'"'),
                    FixedDataModelElement('notafter_str', b'","notafter":"'),
                    DelimitedDataModelElement('notafter', b'"'),
                ]),
                FixedDataModelElement('brack_str', b'"}}')
            ]),
            SequenceModelElement('alert', [
                FixedDataModelElement('alert_str', b'alert",'), conn,
                OptionalMatchModelElement(
                    'tx_id',
                    SequenceModelElement('tx_id', [
                        FixedDataModelElement('tx_id', b',"tx_id":'),
                        DecimalIntegerValueModelElement('tx_id'),
                    ])),
                SequenceModelElement('alert', [
                    FixedDataModelElement('action_str',
                                          b',"alert":{"action":"'),
                    DelimitedDataModelElement('action', b'"'),
                    FixedDataModelElement('gid_str', b'","gid":'),
                    DecimalIntegerValueModelElement('gid'),
                    FixedDataModelElement('signature_id_str',
                                          b',"signature_id":'),
                    DecimalIntegerValueModelElement('signature_id'),
                    FixedDataModelElement('rev_str', b',"rev":'),
                    DecimalIntegerValueModelElement('rev'),
                    FixedDataModelElement('signature_str', b',"signature":"'),
                    DelimitedDataModelElement('signature', b'"'),
                    FixedDataModelElement('category_str', b'","category":"'),
                    DelimitedDataModelElement('category', b'"'),
                    FixedDataModelElement('severity_str', b'","severity":'),
                    DecimalIntegerValueModelElement('severity'),
                    FixedDataModelElement('brack_str', b'}')
                ]), http,
                FixedDataModelElement('brack_str', b'}')
            ]),
        ])
    ])

    return model
def build_analysis_pipeline(analysis_context):
    """
    Define the function to create pipeline for parsing the log data.
    It has also to define an AtomizerFactory to instruct aminer how to process incoming data streams to create log atoms from them.
    """
    date_format_string = b'%Y-%m-%d %H:%M:%S'
    cron = b' cron['

    # Build the parsing model:

    service_children_disk_report = [
        FixedDataModelElement('Space', b' Current Disk Data is: Filesystem     Type  Size  Used Avail Use%'),
        DelimitedDataModelElement('Data', b'%'), AnyByteDataModelElement('Rest')]

    service_children_login_details = [
        FixedDataModelElement('User/LoginDetails', b'User '), DelimitedDataModelElement('Username', b' '),
        FixedWordlistDataModelElement('Status', [b' logged in', b' logged out']),
        OptionalMatchModelElement('PastTime', SequenceModelElement('Time', [
            FixedDataModelElement('Blank', b' '), DecimalIntegerValueModelElement('Minutes'),
            FixedDataModelElement('Ago', b' minutes ago.')]))]

    service_children_cron_job = [
        DateTimeModelElement('DTM', date_format_string), FixedDataModelElement('UNameSpace1', b' '),
        DelimitedDataModelElement('UName', b' '), FixedDataModelElement('UNameSpace2', b' '), DelimitedDataModelElement('User', b' '),
        FixedDataModelElement('Cron', cron), DecimalIntegerValueModelElement('JobNumber'),
        FixedDataModelElement('Details', b']: Job `cron.daily` started.')]

    service_children_random_time = [FixedDataModelElement('Space', b'Random: '), DecimalIntegerValueModelElement('Random')]

    service_children_sensors = [SequenceModelElement('CPUTemp', [
        FixedDataModelElement('FixedTemp', b'CPU Temp: '), DecimalIntegerValueModelElement('Temp'),
        FixedDataModelElement('Degrees', b'\xc2\xb0C')]), FixedDataModelElement('Space1', b', '), SequenceModelElement('CPUWorkload', [
            FixedDataModelElement('FixedWorkload', b'CPU Workload: '), DecimalIntegerValueModelElement('Workload'),
            FixedDataModelElement('Percent', b'%')]), FixedDataModelElement('Space2', b', '),
        DateTimeModelElement('DTM', date_format_string)]

    service_children_user_ip_address = [
        FixedDataModelElement('User/UserIPAddress', b'User '), DelimitedDataModelElement('Username', b' '),
        FixedDataModelElement('Action', b' changed IP address to '), IpAddressDataModelElement('IP')]

    service_children_cron_job_announcement = [
        DateTimeModelElement('DTM', date_format_string), FixedDataModelElement('Space', b' '),
        DelimitedDataModelElement('UName', b' '), FixedDataModelElement('Cron', cron), DecimalIntegerValueModelElement('JobNumber'),
        FixedDataModelElement('Run', b']: Will run job `'),
        FixedWordlistDataModelElement('CronType', [b'cron.daily', b'cron.hourly', b'cron.monthly', b'cron.weekly']),
        FixedDataModelElement('StartTime', b'\' in 5 min.')]

    service_children_cron_job_execution = [
        DateTimeModelElement('DTM', date_format_string), FixedDataModelElement('Space1', b' '),
        DelimitedDataModelElement('UName', b' '), FixedDataModelElement('Cron', cron), DecimalIntegerValueModelElement('JobNumber'),
        FixedDataModelElement('Job', b']: Job `'),
        FixedWordlistDataModelElement('CronType', [b'cron.daily', b'cron.hourly', b'cron.monthly', b'cron.weekly']),
        FixedDataModelElement('Started', b'\' started')]

    service_children_audit = [SequenceModelElement('path', [
        FixedDataModelElement('type', b'type=PATH '), FixedDataModelElement('msg_audit', b'msg=audit('),
        DelimitedDataModelElement('msg', b':'), FixedDataModelElement('placeholder', b':'), DecimalIntegerValueModelElement('id'),
        FixedDataModelElement('item_string', b'): item='), DecimalIntegerValueModelElement('item'),
        FixedDataModelElement('name_string', b' name="'), DelimitedDataModelElement('name', b'"'),
        FixedDataModelElement('inode_string', b'" inode='), DecimalIntegerValueModelElement('inode'),
        FixedDataModelElement('dev_string', b' dev='), DelimitedDataModelElement('dev', b' '),
        FixedDataModelElement('mode_string', b' mode='),
        DecimalIntegerValueModelElement('mode', value_pad_type=DecimalIntegerValueModelElement.PAD_TYPE_ZERO),
        FixedDataModelElement('ouid_string', b' ouid='), DecimalIntegerValueModelElement('ouid'),
        FixedDataModelElement('ogid_string', b' ogid='), DecimalIntegerValueModelElement('ogid'),
        FixedDataModelElement('rdev_string', b' rdev='), DelimitedDataModelElement('rdev', b' '),
        FixedDataModelElement('nametype_string', b' nametype='), FixedWordlistDataModelElement('nametype', [b'NORMAL', b'ERROR'])]),
        SequenceModelElement('syscall', [
            FixedDataModelElement('type', b'type=SYSCALL '), FixedDataModelElement('msg_audit', b'msg=audit('),
            DelimitedDataModelElement('msg', b':'), FixedDataModelElement('placeholder', b':'), DecimalIntegerValueModelElement('id'),
            FixedDataModelElement('arch_string', b'): arch='), DelimitedDataModelElement('arch', b' '),
            FixedDataModelElement('syscall_string', b' syscall='), DecimalIntegerValueModelElement('syscall'),
            FixedDataModelElement('success_string', b' success='), FixedWordlistDataModelElement('success', [b'yes', b'no']),
            FixedDataModelElement('exit_string', b' exit='), DecimalIntegerValueModelElement('exit'),
            AnyByteDataModelElement('remainding_data')])]

    service_children_parsing_model_element = [
        DateTimeModelElement('DateTimeModelElement', b'Current DateTime: %d.%m.%Y %H:%M:%S'),
        DecimalFloatValueModelElement('DecimalFloatValueModelElement', value_sign_type='optional'),
        DecimalIntegerValueModelElement('DecimalIntegerValueModelElement', value_sign_type='optional', value_pad_type='blank'),
        SequenceModelElement('se', [
            DelimitedDataModelElement('DelimitedDataModelElement', b';'), FixedDataModelElement('FixedDataModelElement', b';')])]

    # ElementValueBranchModelElement
    fixed_data_me1 = FixedDataModelElement("fixed1", b'match ')
    fixed_data_me2 = FixedDataModelElement("fixed2", b'fixed String')
    fixed_wordlist_data_model_element = FixedWordlistDataModelElement("wordlist", [b'data: ', b'string: '])
    decimal_integer_value_model_element = DecimalIntegerValueModelElement("decimal")

    service_children_parsing_model_element.append(
        ElementValueBranchModelElement('ElementValueBranchModelElement', FirstMatchModelElement("first", [
            SequenceModelElement("seq1", [fixed_data_me1, fixed_wordlist_data_model_element]),
            SequenceModelElement("seq2", [fixed_data_me1, fixed_wordlist_data_model_element, fixed_data_me2])]), "wordlist",
                                 {0: decimal_integer_value_model_element, 1: fixed_data_me2}))
    service_children_parsing_model_element.append(HexStringModelElement('HexStringModelElement'))
    service_children_parsing_model_element.append(SequenceModelElement('se2', [
        FixedDataModelElement('FixedDataModelElement', b'Gateway IP-Address: '), IpAddressDataModelElement('IpAddressDataModelElement')]))
    import locale
    loc = locale.getlocale()
    if loc == (None, None):
        loc = ('en_US', 'utf8')
    service_children_parsing_model_element.append(
        MultiLocaleDateTimeModelElement('MultiLocaleDateTimeModelElement', [(b'%b %d %Y', None, '%s.%s' % loc)]))
    service_children_parsing_model_element.append(
        RepeatedElementDataModelElement('RepeatedElementDataModelElement', SequenceModelElement('SequenceModelElement', [
            FixedDataModelElement('FixedDataModelElement', b'[drawn number]: '),
            DecimalIntegerValueModelElement('DecimalIntegerValueModelElement')]), 1))
    service_children_parsing_model_element.append(VariableByteDataModelElement('VariableByteDataModelElement', b'-@#'))
    service_children_parsing_model_element.append(SequenceModelElement('se', [
        WhiteSpaceLimitedDataModelElement('WhiteSpaceLimitedDataModelElement'), FixedDataModelElement('fixed', b' ')]))

    # The Base64StringModelElement must be just before the AnyByteDataModelElement to avoid unexpected Matches.
    service_children_parsing_model_element.append(Base64StringModelElement('Base64StringModelElement'))

    # The OptionalMatchModelElement must be paired with a FirstMatchModelElement because it accepts all data and thus no data gets
    # to the AnyByteDataModelElement. The AnyByteDataModelElement must be last, because all bytes are accepted.
    service_children_parsing_model_element.append(
        OptionalMatchModelElement('/', FirstMatchModelElement('FirstMatchModelElement//optional', [
            FixedDataModelElement('FixedDataModelElement', b'The-searched-element-was-found!'), SequenceModelElement('se', [
                FixedDataModelElement('FixedDME', b'Any:'), AnyByteDataModelElement('AnyByteDataModelElement')])])))

    alphabet = b'ghijkl'
    service_children_ecd = []
    for _, char in enumerate(alphabet):
        char = bytes([char])
        service_children_ecd.append(FixedDataModelElement(char.decode(), char))

    parsing_model = FirstMatchModelElement('model', [
        SequenceModelElement('CronAnnouncement', service_children_cron_job_announcement),
        SequenceModelElement('CronExecution', service_children_cron_job_execution),
        SequenceModelElement('DailyCron', service_children_cron_job), SequenceModelElement('DiskReport', service_children_disk_report),
        SequenceModelElement('LoginDetails', service_children_login_details), DecimalIntegerValueModelElement('Random'),
        SequenceModelElement('RandomTime', service_children_random_time), SequenceModelElement('Sensors', service_children_sensors),
        SequenceModelElement('IPAddresses', service_children_user_ip_address), FirstMatchModelElement('type', service_children_audit),
        FirstMatchModelElement('ECD', service_children_ecd), FirstMatchModelElement('ParsingME', service_children_parsing_model_element)])

    # Some generic imports.
    from aminer.analysis import AtomFilters

    # Create all global handler lists here and append the real handlers later on.
    # Use this filter to distribute all atoms to the analysis handlers.
    atom_filter = AtomFilters.SubhandlerFilter(None)

    from aminer.analysis.TimestampCorrectionFilters import SimpleMonotonicTimestampAdjust
    simple_monotonic_timestamp_adjust = SimpleMonotonicTimestampAdjust([atom_filter])
    analysis_context.register_component(simple_monotonic_timestamp_adjust, component_name="SimpleMonotonicTimestampAdjust")

    from aminer.events.StreamPrinterEventHandler import StreamPrinterEventHandler
    from aminer.events.JsonConverterHandler import JsonConverterHandler
    stream_printer_event_handler = StreamPrinterEventHandler(analysis_context)
    json_converter_handler = JsonConverterHandler([stream_printer_event_handler], analysis_context)
    anomaly_event_handlers = [json_converter_handler]

    # Now define the AtomizerFactory using the model. A simple line based one is usually sufficient.
    from aminer.input.SimpleByteStreamLineAtomizerFactory import SimpleByteStreamLineAtomizerFactory
    analysis_context.atomizer_factory = SimpleByteStreamLineAtomizerFactory(parsing_model, [simple_monotonic_timestamp_adjust],
                                                                            anomaly_event_handlers)

    # Just report all unparsed atoms to the event handlers.
    from aminer.analysis.UnparsedAtomHandlers import SimpleUnparsedAtomHandler, VerboseUnparsedAtomHandler
    simple_unparsed_atom_handler = SimpleUnparsedAtomHandler(anomaly_event_handlers)
    atom_filter.add_handler(simple_unparsed_atom_handler, stop_when_handled_flag=False)
    analysis_context.register_component(simple_unparsed_atom_handler, component_name="SimpleUnparsedHandler")

    verbose_unparsed_atom_handler = VerboseUnparsedAtomHandler(anomaly_event_handlers, parsing_model)
    atom_filter.add_handler(verbose_unparsed_atom_handler, stop_when_handled_flag=True)
    analysis_context.register_component(verbose_unparsed_atom_handler, component_name="VerboseUnparsedHandler")

    from aminer.analysis.TimestampsUnsortedDetector import TimestampsUnsortedDetector
    timestamps_unsorted_detector = TimestampsUnsortedDetector(analysis_context.aminer_config, anomaly_event_handlers)
    atom_filter.add_handler(timestamps_unsorted_detector)
    analysis_context.register_component(timestamps_unsorted_detector, component_name="TimestampsUnsortedDetector")

    from aminer.analysis import Rules
    from aminer.analysis.AllowlistViolationDetector import AllowlistViolationDetector
    allowlist_rules = [
        Rules.OrMatchRule([
            Rules.AndMatchRule([
                Rules.PathExistsMatchRule('/model/LoginDetails/PastTime/Time/Minutes'),
                Rules.NegationMatchRule(Rules.ValueMatchRule('/model/LoginDetails/Username', b'root')),
                Rules.DebugMatchRule(debug_match_result=True)]),
            Rules.AndMatchRule([
                Rules.NegationMatchRule(Rules.PathExistsMatchRule('/model/LoginDetails/PastTime/Time/Minutes')),
                Rules.PathExistsMatchRule('/model/LoginDetails'),
                Rules.DebugMatchRule(debug_match_result=True)]),
            Rules.NegationMatchRule(Rules.PathExistsMatchRule('/model/LoginDetails'))])]

    # This rule list should trigger, when the line does not look like: User root (logged in, logged out)
    # or User 'username' (logged in, logged out) x minutes ago.
    allowlist_violation_detector = AllowlistViolationDetector(analysis_context.aminer_config, allowlist_rules, anomaly_event_handlers,
                                                              output_log_line=True)
    analysis_context.register_component(allowlist_violation_detector, component_name="Allowlist")
    atom_filter.add_handler(allowlist_violation_detector)

    from aminer.analysis.ParserCount import ParserCount
    parser_count = ParserCount(analysis_context.aminer_config, None, anomaly_event_handlers, 10)
    analysis_context.register_component(parser_count, component_name="ParserCount")
    atom_filter.add_handler(parser_count)

    from aminer.analysis.EventTypeDetector import EventTypeDetector
    etd = EventTypeDetector(analysis_context.aminer_config, anomaly_event_handlers)
    analysis_context.register_component(etd, component_name="EventTypeDetector")
    atom_filter.add_handler(etd)

    from aminer.analysis.VariableTypeDetector import VariableTypeDetector
    vtd = VariableTypeDetector(analysis_context.aminer_config, anomaly_event_handlers, etd, silence_output_except_indicator=False,
                               output_log_line=False, ignore_list=["/model/RandomTime"])
    analysis_context.register_component(vtd, component_name="VariableTypeDetector")
    atom_filter.add_handler(vtd)

    from aminer.analysis.VariableCorrelationDetector import VariableCorrelationDetector
    vtd = VariableCorrelationDetector(analysis_context.aminer_config, anomaly_event_handlers, etd, disc_div_thres=0.5,
                                      ignore_list=["/model/RandomTime"])
    analysis_context.register_component(vtd, component_name="VariableCorrelationDetector")
    atom_filter.add_handler(vtd)

    from aminer.analysis.EventCorrelationDetector import EventCorrelationDetector
    ecd = EventCorrelationDetector(analysis_context.aminer_config, anomaly_event_handlers, check_rules_flag=True,
                                   hypothesis_max_delta_time=1.0)
    analysis_context.register_component(ecd, component_name="EventCorrelationDetector")
    atom_filter.add_handler(ecd)

    from aminer.analysis.EventFrequencyDetector import EventFrequencyDetector
    efd = EventFrequencyDetector(analysis_context.aminer_config, anomaly_event_handlers, window_size=0.1)
    analysis_context.register_component(efd, component_name="EventFrequencyDetector")
    atom_filter.add_handler(efd)

    from aminer.analysis.EventSequenceDetector import EventSequenceDetector
    esd = EventSequenceDetector(analysis_context.aminer_config, anomaly_event_handlers, ['/model/ParsingME'], ignore_list=[
        '/model/ECD/g', '/model/ECD/h', '/model/ECD/i', '/model/ECD/j', '/model/ECD/k', '/model/ECD/l', '/model/Random',
        '/model/RandomTime', '/model/DailyCron'])
    analysis_context.register_component(esd, component_name="EventSequenceDetector")
    atom_filter.add_handler(esd)

    from aminer.analysis.MatchFilter import MatchFilter
    match_filter = MatchFilter(analysis_context.aminer_config, ['/model/Random'], anomaly_event_handlers, target_value_list=[
        1, 10, 100], output_log_line=True)
    analysis_context.register_component(match_filter, component_name="MatchFilter")
    atom_filter.add_handler(match_filter)

    from aminer.analysis.NewMatchPathDetector import NewMatchPathDetector
    new_match_path_detector = NewMatchPathDetector(analysis_context.aminer_config, anomaly_event_handlers, auto_include_flag=True,
                                                   output_log_line=True)
    analysis_context.register_component(new_match_path_detector, component_name="NewMatchPath")
    atom_filter.add_handler(new_match_path_detector)

    def tuple_transformation_function(match_value_list):
        """Only allow output of the EnhancedNewMatchPathValueComboDetector after every 10th element."""
        extra_data = enhanced_new_match_path_value_combo_detector.known_values_dict.get(tuple(match_value_list))
        if extra_data is not None:
            mod = 10
            if (extra_data[2] + 1) % mod == 0:
                enhanced_new_match_path_value_combo_detector.auto_include_flag = False
            else:
                enhanced_new_match_path_value_combo_detector.auto_include_flag = True
        return match_value_list

    from aminer.analysis.EnhancedNewMatchPathValueComboDetector import EnhancedNewMatchPathValueComboDetector
    enhanced_new_match_path_value_combo_detector = EnhancedNewMatchPathValueComboDetector(analysis_context.aminer_config, [
        '/model/DailyCron/UName', '/model/DailyCron/JobNumber'], anomaly_event_handlers, auto_include_flag=True,
        tuple_transformation_function=tuple_transformation_function, output_log_line=True)
    analysis_context.register_component(enhanced_new_match_path_value_combo_detector, component_name="EnhancedNewValueCombo")
    atom_filter.add_handler(enhanced_new_match_path_value_combo_detector)

    import re
    ip_match_action = Rules.EventGenerationMatchAction(
        "Analysis.Rules.IPv4InRFC1918MatchRule", "Private IP address occurred!", anomaly_event_handlers)

    vdmt = Rules.ValueDependentModuloTimeMatchRule(None, 3, ["/model/ECD/j", "/model/ECD/k", "/model/ECD/l"], {b"e": [0, 2.95]}, [0, 3])
    mt = Rules.ModuloTimeMatchRule(None, 3, 0, 3, None)
    time_allowlist_rules = [
        Rules.AndMatchRule([
            Rules.ParallelMatchRule([
                Rules.ValueDependentDelegatedMatchRule([
                    '/model/ECD/g', '/model/ECD/h', '/model/ECD/i', '/model/ECD/j', '/model/ECD/k', '/model/ECD/l'], {
                        (b"a",): mt, (b"b",): mt, (b"c",): mt, (b"d",): vdmt, (b"e",): vdmt, (b"f",): vdmt, None: mt}, mt),
                Rules.IPv4InRFC1918MatchRule("/model/ParsingME/se2/IpAddressDataModelElement", ip_match_action),
                Rules.DebugHistoryMatchRule(debug_match_result=True)
            ]),
            # IP addresses 8.8.8.8, 8.8.4.4 and 10.0.0.0 - 10.255.255.255 are not allowed
            Rules.NegationMatchRule(Rules.ValueListMatchRule("/model/ParsingME/se2/IpAddressDataModelElement", [134744072, 134743044])),
            Rules.NegationMatchRule(Rules.ValueRangeMatchRule("/model/ParsingME/se2/IpAddressDataModelElement", 167772160, 184549375)),
            Rules.NegationMatchRule(Rules.StringRegexMatchRule("/model/type/syscall/success", re.compile(b"^no$")))
        ])
    ]
    time_allowlist_violation_detector = AllowlistViolationDetector(
        analysis_context.aminer_config, time_allowlist_rules, anomaly_event_handlers, output_log_line=True)
    analysis_context.register_component(time_allowlist_violation_detector, component_name="TimeAllowlist")
    atom_filter.add_handler(time_allowlist_violation_detector)

    from aminer.analysis.HistogramAnalysis import HistogramAnalysis, LinearNumericBinDefinition, ModuloTimeBinDefinition, \
        PathDependentHistogramAnalysis
    modulo_time_bin_definition = ModuloTimeBinDefinition(86400, 3600, 0, 1, 24, True)
    linear_numeric_bin_definition = LinearNumericBinDefinition(50, 5, 20, True)
    histogram_analysis = HistogramAnalysis(analysis_context.aminer_config, [
        ('/model/RandomTime/Random', modulo_time_bin_definition), ('/model/Random', linear_numeric_bin_definition)], 10,
        anomaly_event_handlers, output_log_line=True)
    analysis_context.register_component(histogram_analysis, component_name="HistogramAnalysis")
    atom_filter.add_handler(histogram_analysis)

    path_dependent_histogram_analysis = PathDependentHistogramAnalysis(
        analysis_context.aminer_config, '/model/RandomTime', modulo_time_bin_definition, 10, anomaly_event_handlers, output_log_line=True)
    analysis_context.register_component(path_dependent_histogram_analysis, component_name="PathDependentHistogramAnalysis")
    atom_filter.add_handler(path_dependent_histogram_analysis)

    from aminer.analysis.MatchValueAverageChangeDetector import MatchValueAverageChangeDetector
    match_value_average_change_detector = MatchValueAverageChangeDetector(analysis_context.aminer_config, anomaly_event_handlers, None, [
        '/model/Random'], 100, 10, output_log_line=True)
    analysis_context.register_component(match_value_average_change_detector, component_name="MatchValueAverageChange")
    atom_filter.add_handler(match_value_average_change_detector)

    import sys
    from aminer.analysis.MatchValueStreamWriter import MatchValueStreamWriter
    match_value_stream_writer = MatchValueStreamWriter(
        sys.stdout, ['/model/Sensors/CPUTemp', '/model/Sensors/CPUWorkload', '/model/Sensors/DTM'], b';', b'')
    analysis_context.register_component(match_value_stream_writer, component_name="MatchValueStreamWriter")
    atom_filter.add_handler(match_value_stream_writer)

    from aminer.analysis.NewMatchPathValueComboDetector import NewMatchPathValueComboDetector
    new_match_path_value_combo_detector = NewMatchPathValueComboDetector(
        analysis_context.aminer_config, ['/model/IPAddresses/Username', '/model/IPAddresses/IP'],
        anomaly_event_handlers, output_log_line=True)
    analysis_context.register_component(new_match_path_value_combo_detector, component_name="NewMatchPathValueCombo")
    atom_filter.add_handler(new_match_path_value_combo_detector)

    from aminer.analysis.NewMatchIdValueComboDetector import NewMatchIdValueComboDetector
    new_match_id_value_combo_detector = NewMatchIdValueComboDetector(analysis_context.aminer_config, [
        '/model/type/path/name', '/model/type/syscall/syscall'], anomaly_event_handlers, id_path_list=[
        '/model/type/path/id', '/model/type/syscall/id'], min_allowed_time_diff=5, auto_include_flag=True, allow_missing_values_flag=True,
        output_log_line=True)
    analysis_context.register_component(new_match_id_value_combo_detector, component_name="NewMatchIdValueComboDetector")
    atom_filter.add_handler(new_match_id_value_combo_detector)

    from aminer.analysis.NewMatchPathValueDetector import NewMatchPathValueDetector
    new_match_path_value_detector = NewMatchPathValueDetector(analysis_context.aminer_config, [
        '/model/DailyCron/JobNumber', '/model/IPAddresses/Username'], anomaly_event_handlers, auto_include_flag=True, output_log_line=True)
    analysis_context.register_component(new_match_path_value_detector, component_name="NewMatchPathValue")
    atom_filter.add_handler(new_match_path_value_detector)

    from aminer.analysis.MissingMatchPathValueDetector import MissingMatchPathValueDetector
    missing_match_path_value_detector = MissingMatchPathValueDetector(
        analysis_context.aminer_config, ['/model/DiskReport/Space'], anomaly_event_handlers, auto_include_flag=True, default_interval=2,
        realert_interval=5, output_log_line=True)
    analysis_context.register_component(missing_match_path_value_detector, component_name="MissingMatch")
    atom_filter.add_handler(missing_match_path_value_detector)

    from aminer.analysis.TimeCorrelationDetector import TimeCorrelationDetector
    time_correlation_detector = TimeCorrelationDetector(
        analysis_context.aminer_config, anomaly_event_handlers, 2, min_rule_attributes=1, max_rule_attributes=5,
        record_count_before_event=10000, output_log_line=True)
    analysis_context.register_component(time_correlation_detector, component_name="TimeCorrelationDetector")
    atom_filter.add_handler(time_correlation_detector)

    from aminer.analysis.TimeCorrelationViolationDetector import TimeCorrelationViolationDetector, CorrelationRule, EventClassSelector
    cron_job_announcement = CorrelationRule('CronJobAnnouncement', 5, 6, max_artefacts_a_for_single_b=1, artefact_match_parameters=[
        ('/model/CronAnnouncement/JobNumber', '/model/CronExecution/JobNumber')])
    a_class_selector = EventClassSelector('Announcement', [cron_job_announcement], None)
    b_class_selector = EventClassSelector('Execution', None, [cron_job_announcement])
    rules = [Rules.PathExistsMatchRule('/model/CronAnnouncement/Run', a_class_selector),
             Rules.PathExistsMatchRule('/model/CronExecution/Job', b_class_selector)]

    time_correlation_violation_detector = TimeCorrelationViolationDetector(analysis_context.aminer_config, rules, anomaly_event_handlers,
                                                                           output_log_line=True)
    analysis_context.register_component(time_correlation_violation_detector, component_name="TimeCorrelationViolationDetector")
    atom_filter.add_handler(time_correlation_violation_detector)
def get_model():
    """Return a model to parse a su session information message after any standard logging preamble, e.g. from syslog."""
    type_children = [
        SequenceModelElement('queue', [
            FixedWordlistDataModelElement('type', [b'Start', b'End']),
            FixedDataModelElement('s0', b' queue run: pid='),
            DecimalIntegerValueModelElement('pid')
        ]),
        SequenceModelElement('rec-log', [
            WhiteSpaceLimitedDataModelElement('id'),
            FixedDataModelElement('s0', b' <= '),
            WhiteSpaceLimitedDataModelElement('env-from'),
            FirstMatchModelElement('source', [
                SequenceModelElement('network', [
                    FixedDataModelElement('s0', b' H=('),
                    DelimitedDataModelElement('hostname', b') '),
                    FixedDataModelElement('s1', b') ['),
                    IpAddressDataModelElement('hostip'),
                    FixedDataModelElement('s2', b']')
                ]),
                SequenceModelElement('user', [
                    FixedDataModelElement('s0', b' U='),
                    WhiteSpaceLimitedDataModelElement('user')
                ])
            ]),
            FixedDataModelElement('s2', b' P='),
            WhiteSpaceLimitedDataModelElement('proto'),
            FixedDataModelElement('s3', b' S='),
            DecimalIntegerValueModelElement('size'),
            OptionalMatchModelElement(
                'idopt',
                SequenceModelElement('iddata', [
                    FixedDataModelElement('s0', b' id='),
                    AnyByteDataModelElement('id')
                ]))
        ]),
        SequenceModelElement(
            'send-log',
            [
                WhiteSpaceLimitedDataModelElement('id'),
                # Strange: first address seems to use different separator than second one.
                FixedWordlistDataModelElement('s0', [b' => b', b' ->']),
                DelimitedDataModelElement('env-to', b' R='),
                FixedDataModelElement('s1', b' R='),
                WhiteSpaceLimitedDataModelElement('route'),
                FixedDataModelElement('s2', b' T='),
                WhiteSpaceLimitedDataModelElement('transport'),
                AnyByteDataModelElement('unparsed')
            ]),
        SequenceModelElement('sent', [
            WhiteSpaceLimitedDataModelElement('id'),
            FixedDataModelElement('s0', b' Completed')
        ]),
        SequenceModelElement('started', [
            FixedDataModelElement('s0', b' exim '),
            WhiteSpaceLimitedDataModelElement('version'),
            FixedDataModelElement('s1', b' daemon started: pid='),
            DecimalIntegerValueModelElement('pid'),
            FixedDataModelElement(
                's2', b', -q30m, listening for SMTP on [127.0.0.1]:25')
        ])
    ]

    model = SequenceModelElement('exim', [
        FixedDataModelElement('sname', b'exim['),
        DecimalIntegerValueModelElement('pid'),
        FixedDataModelElement('s0', b']: '),
        FirstMatchModelElement('msg', type_children)
    ])
    return model
예제 #29
0
def build_analysis_pipeline(analysis_context):
    """
    Define the function to create pipeline for parsing the log data.
    It has also to define an AtomizerFactory to instruct aminer how to process incoming data streams to create log atoms from them.
    """
    # Build the parsing model:

    service_children_disk_report = [
        FixedDataModelElement(
            'Space',
            b' Current Disk Data is: Filesystem     Type  Size  Used Avail Use%'
        ),
        DelimitedDataModelElement('Data', b'%'),
        AnyByteDataModelElement('Rest')
    ]

    service_children_login_details = [
        FixedDataModelElement('User', b'User '),
        DelimitedDataModelElement('Username', b' '),
        FixedWordlistDataModelElement('Status',
                                      [b' logged in', b' logged out']),
        OptionalMatchModelElement(
            'PastTime',
            SequenceModelElement('Time', [
                FixedDataModelElement('Blank', b' '),
                DecimalIntegerValueModelElement('Minutes'),
                FixedDataModelElement('Ago', b' minutes ago.')
            ]))
    ]

    service_children_cron_job = [
        DateTimeModelElement('DTM', b'%Y-%m-%d %H:%M:%S'),
        FixedDataModelElement('UNameSpace1', b' '),
        DelimitedDataModelElement('UName', b' '),
        FixedDataModelElement('UNameSpace2', b' '),
        DelimitedDataModelElement('User', b' '),
        FixedDataModelElement('Cron', b' cron['),
        DecimalIntegerValueModelElement('JobNumber'),
        FixedDataModelElement('Details', b']: Job `cron.daily` started.')
    ]

    service_children_random_time = [
        FixedDataModelElement('Space', b'Random: '),
        DecimalIntegerValueModelElement('Random')
    ]

    service_children_sensors = [
        SequenceModelElement('CPUTemp', [
            FixedDataModelElement('FixedTemp', b'CPU Temp: '),
            DecimalIntegerValueModelElement('Temp'),
            FixedDataModelElement('Degrees', b'\xc2\xb0C')
        ]),
        FixedDataModelElement('Space1', b', '),
        SequenceModelElement('CPUWorkload', [
            FixedDataModelElement('FixedWorkload', b'CPUWorkload: '),
            DecimalIntegerValueModelElement('Workload'),
            FixedDataModelElement('Percent', b'%')
        ]),
        FixedDataModelElement('Space2', b', '),
        DateTimeModelElement('DTM', b'%Y-%m-%d %H:%M:%S')
    ]

    service_children_user_ip_address = [
        FixedDataModelElement('User', b'User '),
        DelimitedDataModelElement('Username', b' '),
        FixedDataModelElement('Action', b' changed IP address to '),
        IpAddressDataModelElement('IP')
    ]

    service_children_cron_job_announcement = [
        DateTimeModelElement('DTM', b'%Y-%m-%d %H:%M:%S'),
        FixedDataModelElement('Space', b' '),
        DelimitedDataModelElement('UName', b' '),
        FixedDataModelElement('Cron', b' cron['),
        DecimalIntegerValueModelElement('JobNumber'),
        FixedDataModelElement('Run', b']: Will run job `'),
        FixedWordlistDataModelElement(
            'CronType',
            [b'cron.daily', b'cron.hourly', b'cron.monthly', b'cron.weekly']),
        FixedDataModelElement('StartTime', b'\' in 5 min.')
    ]

    service_children_cron_job_execution = [
        DateTimeModelElement('DTM', b'%Y-%m-%d %H:%M:%S'),
        FixedDataModelElement('Space1', b' '),
        DelimitedDataModelElement('UName', b' '),
        FixedDataModelElement('Cron', b' cron['),
        DecimalIntegerValueModelElement('JobNumber'),
        FixedDataModelElement('Job', b']: Job `'),
        FixedWordlistDataModelElement(
            'CronType',
            [b'cron.daily', b'cron.hourly', b'cron.monthly', b'cron.weekly']),
        FixedDataModelElement('Started', b'\' started')
    ]

    parsing_model = FirstMatchModelElement('model', [
        SequenceModelElement('CronAnnouncement',
                             service_children_cron_job_announcement),
        SequenceModelElement('CronExecution',
                             service_children_cron_job_execution),
        SequenceModelElement('DailyCron', service_children_cron_job),
        SequenceModelElement('DiskReport', service_children_disk_report),
        SequenceModelElement('LoginDetails', service_children_login_details),
        DecimalIntegerValueModelElement('Random'),
        SequenceModelElement('RandomTime', service_children_random_time),
        SequenceModelElement('Sensors', service_children_sensors),
        SequenceModelElement('IPAddresses', service_children_user_ip_address)
    ])

    # Some generic imports.
    from aminer.analysis import AtomFilters

    # Create all global handler lists here and append the real handlers later on.
    # Use this filter to distribute all atoms to the analysis handlers.
    atom_filters = AtomFilters.SubhandlerFilter(None)
    analysis_context.register_component(atom_filters,
                                        component_name="AtomFilter")

    from aminer.analysis.TimestampCorrectionFilters import SimpleMonotonicTimestampAdjust
    simple_monotonic_timestamp_adjust = SimpleMonotonicTimestampAdjust(
        [atom_filters])
    analysis_context.register_component(
        simple_monotonic_timestamp_adjust,
        component_name="SimpleMonotonicTimestampAdjust")

    from aminer.events.StreamPrinterEventHandler import StreamPrinterEventHandler
    stream_printer_event_handler = StreamPrinterEventHandler(
        analysis_context)  # skipcq: BAN-B108
    from aminer.events.Utils import VolatileLogarithmicBackoffEventHistory
    volatile_logarithmic_backoff_event_history = VolatileLogarithmicBackoffEventHistory(
        100)
    anomaly_event_handlers = [
        stream_printer_event_handler,
        volatile_logarithmic_backoff_event_history
    ]
    analysis_context.register_component(
        volatile_logarithmic_backoff_event_history,
        component_name="VolatileLogarithmicBackoffEventHistory")

    # Now define the AtomizerFactory using the model. A simple line based one is usually sufficient.
    from aminer.input.SimpleByteStreamLineAtomizerFactory import SimpleByteStreamLineAtomizerFactory
    analysis_context.atomizer_factory = SimpleByteStreamLineAtomizerFactory(
        parsing_model, [simple_monotonic_timestamp_adjust],
        anomaly_event_handlers)

    # Just report all unparsed atoms to the event handlers.
    from aminer.analysis.UnparsedAtomHandlers import SimpleUnparsedAtomHandler
    simple_unparsed_atom_handler = SimpleUnparsedAtomHandler(
        anomaly_event_handlers)
    atom_filters.add_handler(simple_unparsed_atom_handler,
                             stop_when_handled_flag=True)
    analysis_context.register_component(simple_unparsed_atom_handler,
                                        component_name="UnparsedHandler")

    from aminer.analysis.TimestampsUnsortedDetector import TimestampsUnsortedDetector
    timestamps_unsorted_detector = TimestampsUnsortedDetector(
        analysis_context.aminer_config, anomaly_event_handlers)
    atom_filters.add_handler(timestamps_unsorted_detector)
    analysis_context.register_component(
        timestamps_unsorted_detector,
        component_name="TimestampsUnsortedDetector")

    from aminer.analysis import Rules
    from aminer.analysis.AllowlistViolationDetector import AllowlistViolationDetector
    allowlist_rules = [
        Rules.OrMatchRule([
            Rules.AndMatchRule([
                Rules.PathExistsMatchRule(
                    '/model/LoginDetails/PastTime/Time/Minutes'),
                Rules.NegationMatchRule(
                    Rules.ValueMatchRule('/model/LoginDetails/Username',
                                         b'root'))
            ]),
            Rules.AndMatchRule([
                Rules.NegationMatchRule(
                    Rules.PathExistsMatchRule(
                        '/model/LoginDetails/PastTime/Time/Minutes')),
                Rules.PathExistsMatchRule('/model/LoginDetails')
            ]),
            Rules.NegationMatchRule(
                Rules.PathExistsMatchRule('/model/LoginDetails'))
        ])
    ]

    # This rule list should trigger, when the line does not look like: User root (logged in, logged out)
    # or User 'username' (logged in, logged out) x minutes ago.
    allowlist_violation_detector = AllowlistViolationDetector(
        analysis_context.aminer_config, allowlist_rules,
        anomaly_event_handlers)
    analysis_context.register_component(allowlist_violation_detector,
                                        component_name="Allowlist")
    atom_filters.add_handler(allowlist_violation_detector)

    from aminer.analysis.ParserCount import ParserCount
    parser_count = ParserCount(analysis_context.aminer_config, None,
                               anomaly_event_handlers, 10)
    analysis_context.register_component(parser_count,
                                        component_name="ParserCount")
    atom_filters.add_handler(parser_count)

    from aminer.analysis.EventCorrelationDetector import EventCorrelationDetector
    ecd = EventCorrelationDetector(analysis_context.aminer_config,
                                   anomaly_event_handlers,
                                   check_rules_flag=True,
                                   hypothesis_max_delta_time=1.0,
                                   auto_include_flag=True)
    analysis_context.register_component(
        ecd, component_name="EventCorrelationDetector")
    atom_filters.add_handler(ecd)

    from aminer.analysis.NewMatchPathDetector import NewMatchPathDetector
    new_match_path_detector = NewMatchPathDetector(
        analysis_context.aminer_config,
        anomaly_event_handlers,
        auto_include_flag=True)
    analysis_context.register_component(new_match_path_detector,
                                        component_name="NewMatchPath")
    atom_filters.add_handler(new_match_path_detector)

    def tuple_transformation_function(match_value_list):
        """Only allow output of the EnhancedNewMatchPathValueComboDetector after every 10000th element."""
        extra_data = enhanced_new_match_path_value_combo_detector.known_values_dict.get(
            tuple(match_value_list))
        if extra_data is not None:
            mod = 10000
            if (extra_data[2] + 1) % mod == 0:
                enhanced_new_match_path_value_combo_detector.auto_include_flag = False
            else:
                enhanced_new_match_path_value_combo_detector.auto_include_flag = True
        return match_value_list

    from aminer.analysis.EnhancedNewMatchPathValueComboDetector import EnhancedNewMatchPathValueComboDetector
    enhanced_new_match_path_value_combo_detector = EnhancedNewMatchPathValueComboDetector(
        analysis_context.aminer_config,
        ['/model/DailyCron/UName', '/model/DailyCron/JobNumber'],
        anomaly_event_handlers,
        auto_include_flag=False,
        tuple_transformation_function=tuple_transformation_function)
    analysis_context.register_component(
        enhanced_new_match_path_value_combo_detector,
        component_name="EnhancedNewValueCombo")
    atom_filters.add_handler(enhanced_new_match_path_value_combo_detector)

    from aminer.analysis.HistogramAnalysis import HistogramAnalysis, LinearNumericBinDefinition, ModuloTimeBinDefinition, \
        PathDependentHistogramAnalysis
    modulo_time_bin_definition = ModuloTimeBinDefinition(
        86400, 3600, 0, 1, 24, True)
    linear_numeric_bin_definition = LinearNumericBinDefinition(50, 5, 20, True)
    histogram_analysis = HistogramAnalysis(
        analysis_context.aminer_config,
        [('/model/RandomTime/Random', modulo_time_bin_definition),
         ('/model/Random', linear_numeric_bin_definition)], 10,
        anomaly_event_handlers)
    analysis_context.register_component(histogram_analysis,
                                        component_name="HistogramAnalysis")
    atom_filters.add_handler(histogram_analysis)

    path_dependent_histogram_analysis = PathDependentHistogramAnalysis(
        analysis_context.aminer_config, '/model/RandomTime',
        modulo_time_bin_definition, 10, anomaly_event_handlers)
    analysis_context.register_component(
        path_dependent_histogram_analysis,
        component_name="PathDependentHistogramAnalysis")
    atom_filters.add_handler(path_dependent_histogram_analysis)

    from aminer.analysis.MatchValueAverageChangeDetector import MatchValueAverageChangeDetector
    match_value_average_change_detector = MatchValueAverageChangeDetector(
        analysis_context.aminer_config, anomaly_event_handlers, None,
        ['/model/Random'], 100, 10)
    analysis_context.register_component(
        match_value_average_change_detector,
        component_name="MatchValueAverageChange")
    atom_filters.add_handler(match_value_average_change_detector)

    import sys
    from aminer.analysis.MatchValueStreamWriter import MatchValueStreamWriter
    match_value_stream_writer = MatchValueStreamWriter(sys.stdout, [
        '/model/Sensors/CPUTemp', '/model/Sensors/CPUWorkload',
        '/model/Sensors/DTM'
    ], b';', b'')
    analysis_context.register_component(
        match_value_stream_writer, component_name="MatchValueStreamWriter")
    atom_filters.add_handler(match_value_stream_writer)

    from aminer.analysis.NewMatchPathValueComboDetector import NewMatchPathValueComboDetector
    new_match_path_value_combo_detector = NewMatchPathValueComboDetector(
        analysis_context.aminer_config,
        ['/model/IPAddresses/Username', '/model/IPAddresses/IP'],
        anomaly_event_handlers,
        auto_include_flag=False)
    analysis_context.register_component(
        new_match_path_value_combo_detector,
        component_name="NewMatchPathValueCombo")
    atom_filters.add_handler(new_match_path_value_combo_detector)

    from aminer.analysis.NewMatchIdValueComboDetector import NewMatchIdValueComboDetector
    new_match_id_value_combo_detector = NewMatchIdValueComboDetector(
        analysis_context.aminer_config,
        ['/model/type/path/name', '/model/type/syscall/syscall'],
        anomaly_event_handlers,
        id_path_list=['/model/type/path/id', '/model/type/syscall/id'],
        min_allowed_time_diff=5,
        auto_include_flag=True,
        allow_missing_values_flag=True,
        output_log_line=True)
    analysis_context.register_component(
        new_match_id_value_combo_detector,
        component_name="NewMatchIdValueComboDetector")
    atom_filters.add_handler(new_match_id_value_combo_detector)

    from aminer.analysis.NewMatchPathValueDetector import NewMatchPathValueDetector
    new_match_path_value_detector = NewMatchPathValueDetector(
        analysis_context.aminer_config,
        ['/model/DailyCron/Job Number', '/model/IPAddresses/Username'],
        anomaly_event_handlers,
        auto_include_flag=False)
    analysis_context.register_component(new_match_path_value_detector,
                                        component_name="NewMatchPathValue")
    atom_filters.add_handler(new_match_path_value_detector)

    from aminer.analysis.MissingMatchPathValueDetector import MissingMatchPathValueDetector
    missing_match_path_value_detector = MissingMatchPathValueDetector(
        analysis_context.aminer_config, ['/model/DiskReport/Space'],
        anomaly_event_handlers,
        auto_include_flag=False,
        default_interval=2,
        realert_interval=5)
    analysis_context.register_component(missing_match_path_value_detector,
                                        component_name="MissingMatch")
    atom_filters.add_handler(missing_match_path_value_detector)

    from aminer.analysis.TimeCorrelationDetector import TimeCorrelationDetector
    time_correlation_detector = TimeCorrelationDetector(
        analysis_context.aminer_config,
        anomaly_event_handlers,
        2,
        min_rule_attributes=1,
        max_rule_attributes=5,
        record_count_before_event=70000,
        output_log_line=True)
    analysis_context.register_component(
        time_correlation_detector, component_name="TimeCorrelationDetector")
    atom_filters.add_handler(time_correlation_detector)

    from aminer.analysis.TimeCorrelationViolationDetector import TimeCorrelationViolationDetector, CorrelationRule, EventClassSelector
    cron_job_announcement = CorrelationRule(
        'CronJobAnnouncement',
        5,
        6,
        max_artefacts_a_for_single_b=1,
        artefact_match_parameters=[('/model/CronAnnouncement/JobNumber',
                                    '/model/CronExecution/JobNumber')])
    a_class_selector = EventClassSelector('Announcement',
                                          [cron_job_announcement], None)
    b_class_selector = EventClassSelector('Execution', None,
                                          [cron_job_announcement])
    rules = [
        Rules.PathExistsMatchRule('/model/CronAnnouncement/Run',
                                  a_class_selector),
        Rules.PathExistsMatchRule('/model/CronExecution/Job', b_class_selector)
    ]

    time_correlation_violation_detector = TimeCorrelationViolationDetector(
        analysis_context.aminer_config, rules, anomaly_event_handlers)
    analysis_context.register_component(
        time_correlation_violation_detector,
        component_name="TimeCorrelationViolationDetector")
    atom_filters.add_handler(time_correlation_violation_detector)

    from aminer.events.DefaultMailNotificationEventHandler import DefaultMailNotificationEventHandler
    if DefaultMailNotificationEventHandler.CONFIG_KEY_MAIL_TARGET_ADDRESS in analysis_context.aminer_config.config_properties:
        mail_notification_handler = DefaultMailNotificationEventHandler(
            analysis_context)
        analysis_context.register_component(mail_notification_handler,
                                            component_name="MailHandler")
        anomaly_event_handlers.append(mail_notification_handler)
class EventTypeDetectorTest(TestBase):
    """Unittests for the EventTypeDetector."""

    log_lines = [
        b'type=SYSCALL msg=audit(1580367384.000:1): arch=c000003e syscall=1 success=yes exit=21 a0=7ffda5863060 a1=0 a2=1b6 a3=4f items=1 '
        b'ppid=22913 pid=13187 auid=4294967295 uid=33 gid=33 euid=33 suid=33 fsuid=33 egid=33 sgid=33 fsgid=33 tty=(none) ses=4294967295 '
        b'comm="apache2" exe="/usr/sbin/apache2" key=(null)',
        b'type=PATH msg=audit(1580367385.000:1): item=0 name="one" inode=790106 dev=fe:01 mode=0100666 ouid=1000 ogid=1000 rdev=00:00 '
        b'nametype=NORMAL',
        b'type=SYSCALL msg=audit(1580367386.000:2): arch=c000003e syscall=2 success=yes exit=21 a0=7ffda5863060 a1=0 a2=1b6 a3=4f items=1 '
        b'ppid=22913 pid=13187 auid=4294967295 uid=33 gid=33 euid=33 suid=33 fsuid=33 egid=33 sgid=33 fsgid=33 tty=(none) ses=4294967295 '
        b'comm="apache2" exe="/usr/sbin/apache2" key=(null)',
        b'type=PATH msg=audit(1580367387.000:2): item=0 name="two" inode=790106 dev=fe:01 mode=0100666 ouid=1000 ogid=1000 rdev=00:00 '
        b'nametype=NORMAL',
        b'type=SYSCALL msg=audit(1580367388.000:3): arch=c000003e syscall=3 success=yes exit=21 a0=7ffda5863060 a1=0 a2=1b6 a3=4f items=1 '
        b'ppid=22913 pid=13187 auid=4294967295 uid=33 gid=33 euid=33 suid=33 fsuid=33 egid=33 sgid=33 fsgid=33 tty=(none) ses=4294967295 '
        b'comm="apache2" exe="/usr/sbin/apache2" key=(null)',
        b'type=PATH msg=audit(1580367389.000:3): item=0 name="three" inode=790106 dev=fe:01 mode=0100666 ouid=1000 ogid=1000 rdev=00:00 '
        b'nametype=NORMAL',
        b'type=SYSCALL msg=audit(1580367388.500:100): arch=c000003e syscall=1 success=yes exit=21 a0=7ffda5863060 a1=0 a2=1b6 a3=4f items=1'
        b' ppid=22913 pid=13187 auid=4294967295 uid=33 gid=33 euid=33 suid=33 fsuid=33 egid=33 sgid=33 fsgid=33 tty=(none) ses=4294967295 '
        b'comm="apache2" exe="/usr/sbin/apache2" key=(null)',
        b'type=SYSCALL msg=audit(1580367390.000:4): arch=c000003e syscall=1 success=yes exit=21 a0=7ffda5863060 a1=0 a2=1b6 a3=4f items=1 '
        b'ppid=22913 pid=13187 auid=4294967295 uid=33 gid=33 euid=33 suid=33 fsuid=33 egid=33 sgid=33 fsgid=33 tty=(none) ses=4294967295 '
        b'comm="apache2" exe="/usr/sbin/apache2" key=(null)',
        b'type=PATH msg=audit(1580367391.000:4): item=0 name="one" inode=790106 dev=fe:01 mode=0100666 ouid=1000 ogid=1000 rdev=00:00 '
        b'nametype=NORMAL',
        b'type=PATH msg=audit(1580367392.000:5): item=0 name="two" inode=790106 dev=fe:01 mode=0100666 ouid=1000 ogid=1000 rdev=00:00 '
        b'nametype=NORMAL',
        b'type=SYSCALL msg=audit(1580367393.000:5): arch=c000003e syscall=2 success=yes exit=21 a0=7ffda5863060 a1=0 a2=1b6 a3=4f items=1 '
        b'ppid=22913 pid=13187 auid=4294967295 uid=33 gid=33 euid=33 suid=33 fsuid=33 egid=33 sgid=33 fsgid=33 tty=(none) ses=4294967295 '
        b'comm="apache2" exe="/usr/sbin/apache2" key=(null)',
        b'type=SYSCALL msg=audit(1580367394.000:6): arch=c000003e syscall=4 success=yes exit=21 a0=7ffda5863060 a1=0 a2=1b6 a3=4f items=1 '
        b'ppid=22913 pid=13187 auid=4294967295 uid=33 gid=33 euid=33 suid=33 fsuid=33 egid=33 sgid=33 fsgid=33 tty=(none) ses=4294967295 '
        b'comm="apache2" exe="/usr/sbin/apache2" key=(null)',
        b'type=PATH msg=audit(1580367395.000:7): item=0 name="five" inode=790106 dev=fe:01 mode=0100666 ouid=1000 ogid=1000 rdev=00:00 '
        b'nametype=NORMAL',
        b'type=SYSCALL msg=audit(1580367396.000:8): arch=c000003e syscall=6 success=yes exit=21 a0=7ffda5863060 a1=0 a2=1b6 a3=4f items=1 '
        b'ppid=22913 pid=13187 auid=4294967295 uid=33 gid=33 euid=33 suid=33 fsuid=33 egid=33 sgid=33 fsgid=33 tty=(none) ses=4294967295 '
        b'comm="apache2" exe="/usr/sbin/apache2" key=(null)',
        b'type=PATH msg=audit(1580367397.000:6): item=0 name="four" inode=790106 dev=fe:01 mode=0100666 ouid=1000 ogid=1000 rdev=00:00 '
        b'nametype=NORMAL',
        b'type=SYSCALL msg=audit(1580367398.000:7): arch=c000003e syscall=5 success=yes exit=21 a0=7ffda5863060 a1=0 a2=1b6 a3=4f items=1 '
        b'ppid=22913 pid=13187 auid=4294967295 uid=33 gid=33 euid=33 suid=33 fsuid=33 egid=33 sgid=33 fsgid=33 tty=(none) ses=4294967295 '
        b'comm="apache2" exe="/usr/sbin/apache2" key=(null)',
        b'type=PATH msg=audit(1580367399.000:8): item=0 name="six" inode=790106 dev=fe:01 mode=0100666 ouid=1000 ogid=1000 rdev=00:00 '
        b'nametype=NORMAL',
        b'type=SYSCALL msg=audit(1580367400.000:9): arch=c000003e syscall=2 success=yes exit=21 a0=7ffda5863060 a1=0 a2=1b6 a3=4f items=1 '
        b'ppid=22913 pid=13187 auid=4294967295 uid=33 gid=33 euid=33 suid=33 fsuid=33 egid=33 sgid=33 fsgid=33 tty=(none) ses=4294967295 '
        b'comm="apache2" exe="/usr/sbin/apache2" key=(null)',
        b'type=PATH msg=audit(1580367401.000:9): item=0 name="three" inode=790106 dev=fe:01 mode=0100666 ouid=1000 ogid=1000 rdev=00:00 '
        b'nametype=NORMAL',
        b'type=PATH msg=audit(1580367402.000:10): item=0 name="one" inode=790106 dev=fe:01 mode=0100666 ouid=1000 ogid=1000 rdev=00:00 '
        b'nametype=NORMAL',
        b'type=SYSCALL msg=audit(1580367403.000:10): arch=c000003e syscall=3 success=yes exit=21 a0=7ffda5863060 a1=0 a2=1b6 a3=4f items=1 '
        b'ppid=22913 pid=13187 auid=4294967295 uid=33 gid=33 euid=33 suid=33 fsuid=33 egid=33 sgid=33 fsgid=33 tty=(none) ses=4294967295 '
        b'comm="apache2" exe="/usr/sbin/apache2" key=(null)']

    parsing_model = FirstMatchModelElement('type', [SequenceModelElement('path', [
        FixedDataModelElement('type', b'type=PATH '), FixedDataModelElement('msg_audit', b'msg=audit('),
        DelimitedDataModelElement('msg', b':'), FixedDataModelElement('placeholder', b':'), DecimalIntegerValueModelElement('id'),
        FixedDataModelElement('item_string', b'): item='), DecimalIntegerValueModelElement('item'),
        FixedDataModelElement('name_string', b' name="'), DelimitedDataModelElement('name', b'"'),
        FixedDataModelElement('inode_string', b'" inode='), DecimalIntegerValueModelElement('inode'),
        FixedDataModelElement('dev_string', b' dev='), DelimitedDataModelElement('dev', b' '),
        FixedDataModelElement('mode_string', b' mode='), DecimalIntegerValueModelElement('mode'),
        FixedDataModelElement('ouid_string', b' ouid='), DecimalIntegerValueModelElement('ouid'),
        FixedDataModelElement('ogid_string', b' ogid='), DecimalIntegerValueModelElement('ogid'),
        FixedDataModelElement('rdev_string', b' rdev='), DelimitedDataModelElement('rdev', b' '),
        FixedDataModelElement('nametype_string', b' nametype='), FixedWordlistDataModelElement('nametype', [b'NORMAL', b'ERROR'])]),
        SequenceModelElement('syscall', [
            FixedDataModelElement('type', b'type=SYSCALL '), FixedDataModelElement('msg_audit', b'msg=audit('),
            DelimitedDataModelElement('msg', b':'), FixedDataModelElement('placeholder', b':'), DecimalIntegerValueModelElement('id'),
            FixedDataModelElement('arch_string', b'): arch='), DelimitedDataModelElement('arch', b' '),
            FixedDataModelElement('syscall_string', b' syscall='), DecimalIntegerValueModelElement('syscall'),
            FixedDataModelElement('success_string', b' success='), FixedWordlistDataModelElement('success', [b'yes', b'no']),
            FixedDataModelElement('exit_string', b' exit='), DecimalIntegerValueModelElement('exit'),
            AnyByteDataModelElement('remainding_data')])])

    def test1receive_atoms_with_default_values(self):
        """
        In this test case multiple log_atoms are received with default values of the EventTypeDetector.
        path_list is empty and all paths are learned dynamically in variable_key_list.
        """
        event_type_detector = EventTypeDetector(self.aminer_config, [self.stream_printer_event_handler])
        log_atoms = []
        for line in self.log_lines:
            t = time.time()
            log_atoms.append(
                LogAtom(line, ParserMatch(self.parsing_model.get_match_element('parser', MatchContext(line))), t, self.__class__.__name__))
        for i, log_atom in enumerate(log_atoms):
            self.assertTrue(event_type_detector.receive_atom(log_atom))
            self.assertEqual(event_type_detector.total_records, i + 1)

    def test2receive_atoms_with_defined_path_list(self):
        """
        In this test case multiple log_atoms are received with default values of the EventTypeDetector.
        path_list is set to a static list of paths and variable_key_list should not be used.
        """
        event_type_detector = EventTypeDetector(
            self.aminer_config, [self.stream_printer_event_handler], path_list=['parser/type/path/nametype'])
        results = [True, False, True, False, True, False, True, True, False, False, True, True, False, True, False, True, False, True,
                   False, False, True]
        log_atoms = []
        for line in self.log_lines:
            t = time.time()
            log_atoms.append(
                LogAtom(line, ParserMatch(self.parsing_model.get_match_element('parser', MatchContext(line))), t, self.__class__.__name__))
        for i, log_atom in enumerate(log_atoms):
            old_vals = (event_type_detector.num_events, event_type_detector.num_eventlines,
                        event_type_detector.total_records, event_type_detector.longest_path)
            self.assertEqual(event_type_detector.receive_atom(log_atom), not results[i], i)
            if results[i]:
                self.assertEqual(old_vals, (
                    event_type_detector.num_events, event_type_detector.num_eventlines,
                    event_type_detector.total_records, event_type_detector.longest_path))

    def test3append_values_float(self):
        """This unittest checks the append_values method with raw_match_object being a float value."""
        event_type_detector = EventTypeDetector(self.aminer_config, [self.stream_printer_event_handler])
        # initialize all values.
        t = time.time()
        log_atom = LogAtom(b'22.2', ParserMatch(MatchElement('path', '22.2', 22.2, None)), t, self.__class__.__name__)
        event_type_detector.receive_atom(log_atom)

        event_type_detector.values = [[[]]]
        event_type_detector.append_values(log_atom, 0)
        self.assertEqual(event_type_detector.values, [[[22.2]]])

        log_atom = LogAtom(b'22', ParserMatch(MatchElement('path', '22', 22, None)), t, self.__class__.__name__)
        event_type_detector.values = [[[]]]
        event_type_detector.append_values(log_atom, 0)
        self.assertEqual(event_type_detector.values, [[[22]]])

        log_atom = LogAtom(b'22.2', ParserMatch(MatchElement('path', '22', b'22', None)), t, self.__class__.__name__)
        event_type_detector.values = [[[]]]
        event_type_detector.append_values(log_atom, 0)
        self.assertEqual(event_type_detector.values, [[[22]]])

    def test4append_values_bytestring(self):
        """
        This unittest checks the append_values method with raw_match_object being a bytestring.
        This should trigger a ValueError and append the match_string.
        """
        event_type_detector = EventTypeDetector(self.aminer_config, [self.stream_printer_event_handler])
        # initialize all values.
        t = time.time()
        log_atom = LogAtom(b'This is a string', ParserMatch(
            MatchElement('path', 'This is a string', b'This is a string', None)), t, self.__class__.__name__)
        event_type_detector.receive_atom(log_atom)

        event_type_detector.values = [[[]]]
        event_type_detector.append_values(log_atom, 0)
        self.assertEqual(event_type_detector.values, [[['This is a string']]])

        log_atom = LogAtom(b'24.05.', ParserMatch(MatchElement('path', '24.05.', b'24.05.', None)), t, self.__class__.__name__)
        event_type_detector.values = [[[]]]
        event_type_detector.append_values(log_atom, 0)
        self.assertEqual(event_type_detector.values, [[['24.05.']]])

    def test5check_value_reduction(self):
        """This unittest checks the functionality of reducing the values when the maxNumVals threshold is reached."""
        event_type_detector = EventTypeDetector(self.aminer_config, [self.stream_printer_event_handler])
        t = time.time()
        val_list = [[[]]]
        for i in range(1, event_type_detector.max_num_vals + 1, 1):
            log_atom = LogAtom(str(i).encode(), ParserMatch(MatchElement('path', str(i), i, None)), t, self.__class__.__name__)
            val_list[0][0].append(float(i))
            self.assertTrue(event_type_detector.receive_atom(log_atom))
            self.assertEqual(event_type_detector.values, val_list)
        i += 1
        log_atom = LogAtom(str(i).encode(), ParserMatch(MatchElement('path', str(i), i, None)), t, self.__class__.__name__)
        val_list[0][0].append(float(i))
        self.assertTrue(event_type_detector.receive_atom(log_atom))
        self.assertEqual(event_type_detector.values, [[val_list[0][0][-event_type_detector.min_num_vals:]]])

    def test6persist_and_load_data(self):
        """This unittest checks the functionality of the persistence by persisting and reloading values."""
        event_type_detector = EventTypeDetector(self.aminer_config, [self.stream_printer_event_handler])
        t = time.time()
        log_atom = LogAtom(b'22.2', ParserMatch(MatchElement('path', '22.2', 22.2, None)), t, self.__class__.__name__)
        event_type_detector.receive_atom(log_atom)
        event_type_detector.do_persist()
        event_type_detector_loaded = EventTypeDetector(self.aminer_config, [self.stream_printer_event_handler])
        self.assertEqual(event_type_detector.variable_key_list, event_type_detector_loaded.variable_key_list)
        self.assertEqual(event_type_detector.values, event_type_detector_loaded.values)
        self.assertEqual(event_type_detector.longest_path, event_type_detector_loaded.longest_path)
        self.assertEqual(event_type_detector.check_variables, event_type_detector_loaded.check_variables)
        self.assertEqual(event_type_detector.num_eventlines, event_type_detector_loaded.num_eventlines)