NaxsiRules.parse_rule() - Code Metrics - Inspection of "The 90's called back, they want their <table> back..." - nbs-system/spike - Measure and Improve Code Quality continuously with Scrutinizer

Passed

Branch — master (bb419f)

by jvo

created 2016-03-16 11:32 UTC

NaxsiRules.parse_rule() F

↳ Parent: NaxsiRules

Complexity

Conditions

Size

Total Lines

Duplication

Lines	0
Ratio	0 %

Code Coverage

Tests	1
CRAP Score	218.8941

Metric	Value
cc	15
dl	0
loc	51
ccs	1
cts	31
cp	0.0323
crap	218.8941
rs	2.8426

How to fix Long Method Complexity

from time import strftime, localtime

from spike.model import db
from shlex import shlex


class NaxsiRules(db.Model):
    __bind_key__ = 'rules'
    __tablename__ = 'naxsi_rules'

    id = db.Column(db.Integer, primary_key=True)
    msg = db.Column(db.String(), nullable=False)
    detection = db.Column(db.String(1024), nullable=False)
    mz = db.Column(db.String(1024), nullable=False)
    score = db.Column(db.String(1024), nullable=False)
    sid = db.Column(db.Integer, nullable=False, unique=True)
    ruleset = db.Column(db.String(1024), nullable=False)
    rmks = db.Column(db.Text, nullable=True, server_default="")
    active = db.Column(db.Integer, nullable=False, server_default="1")
    negative = db.Column(db.Integer, nullable=False, server_default='0')
    timestamp = db.Column(db.Integer, nullable=False)

    warnings = []
    error = []
    mr_kw = ["MainRule", "BasicRule", "main_rule", "basic_rule"]
    static_mz = {"$ARGS_VAR", "$BODY_VAR", "$URL", "$HEADERS_VAR"}
    full_zones = {"ARGS", "BODY", "URL", "HEADERS", "FILE_EXT", "RAW_BODY"}
    rx_mz = {"$ARGS_VAR_X", "$BODY_VAR_X", "$URL_X", "$HEADERS_VAR_X"}
    sub_mz = list(static_mz) + list(full_zones) + list(rx_mz)

    def __init__(self, msg, detection, mz, score, sid, ruleset, rmks, active, negative, timestamp):
        self.msg = msg
        self.detection = detection
        self.mz = mz
        self.score = score
        self.sid = sid
        self.ruleset = ruleset
        self.rmks = rmks
        self.active = active
        self.negative = 1 if negative == 'checked' else 0
        self.timestamp = timestamp

    def fullstr(self):
        rdate = strftime("%F - %H:%M", localtime(float(str(self.timestamp))))
        rmks = "# ".join(self.rmks.strip().split("\n"))
        return "#\n# sid: {0} | date: {1}\n#\n# {2}\n#\n{3}".format(self.sid, rdate, rmks, self.__str__())

    def __str__(self):
        negate = 'negative' if self.negative == 1 else ''
        return 'MainRule {} "{}" "msg:{}" "mz:{}" "s:{}" id:{} ;'.format(
            negate, self.detection, self.msg, self.mz, self.score, self.sid)

    def validate(self):
        self.p_mz(self.mz)
        self.p_id(self.sid)
        self.p_detection(self.detection)

        if not self.msg:
            self.warnings.append("Rule has no 'msg:'.")
        if not self.score:
            self.error.append("Rule has no score.")

    def fail(self, msg):
        self.error.append(msg)
        return False

    # Bellow are parsers for specific parts of a rule
    def p_dummy(self, s, assign=False):
class Foo:
    def some_method(self, x, y):
        return x + y;
        return True

    def p_detection(self, s, assign=False):

        if not s.startswith("str:") and not s.startswith("rx:"):
            self.fail("detection {} is neither rx: or str:".format(s))
        if not s.islower():
            self.warnings.append("detection {} is not lower-case. naxsi is case-insensitive".format(s))
        if assign is True:
            self.detection = s
        return True

    def p_genericstr(self, s, assign=False):

        if s and not s.islower():
            self.warnings.append("Pattern ({0}) is not lower-case.".format(s))
        return True

    def p_mz(self, s, assign=False):

        has_zone = False
        mz_state = set()
        locs = s.split('|')
        for loc in locs:
            kw = loc
            arg = None
            if loc.startswith("$"):
                try:
                    kw, arg = loc.split(":")
                except ValueError:
                    return self.fail("Missing 2nd part after ':' in {0}".format(loc))
            # check it is a valid keyword
            if kw not in self.sub_mz:
                return self.fail("'{0}' no a known sub-part of mz : {1}".format(kw, self.sub_mz))
            mz_state.add(kw)
            # verify the rule doesn't attempt to target REGEX and STATIC _VAR/URL at the same time
            if len(self.rx_mz & mz_state) and len(self.static_mz & mz_state):
                return self.fail("You can't mix static $* with regex $*_X ({})".format(str(mz_state)))
            # just a gentle reminder
            if arg and arg.islower() is False:
                self.warnings.append("{0} in {1} is not lowercase. naxsi is case-insensitive".format(arg, loc))
            # the rule targets an actual zone
            if kw not in ["$URL", "$URL_X"] and kw in (self.rx_mz | self.full_zones | self.static_mz):

                has_zone = True
        if has_zone is False:
            return self.fail("The rule/whitelist doesn't target any zone.")
        if assign is True:
            self.mz = s
        return True

    def p_id(self, s, assign=False):

        try:
            x = int(s)

            if x < 10000:
                self.warnings.append("rule IDs below 10k are reserved ({0})".format(x))
        except ValueError:
            self.error.append("id:{0} is not numeric".format(s))
            return False
        if assign is True:
            self.sid = x
        return True

    @staticmethod
    def splitter(s):

        lexer = shlex(s)
        lexer.quotes = '"\''
        lexer.whitespace_split = True
        items = list(iter(lexer.get_token, ''))
        return ([i for i in items if i[0] in "\"'"] +
                [i for i in items if i[0] not in "\"'"])

    def parse_rule(self, x):

        """
        Parse and validate a full naxsi rule
        :param x: raw rule
        :return: [True|False, dict]
        """
        xfrag_kw = {"id:": self.p_id, "str:": self.p_genericstr,
                    "rx:": self.p_genericstr, "msg:": self.p_dummy, "mz:": self.p_mz,
                    "negative": self.p_dummy, "s:": self.p_dummy}

        split = self.splitter(x)  # parse string


        sect = set(self.mr_kw) & set(split) # check if it's a MainRule/BasicRule, store&delete kw

        if len(sect) != 1:
            return self.fail("no (or multiple) mainrule/basicrule keyword.")

        split.remove(sect.pop())

        if ";" in split:
            split.remove(";")

        while True:  # iterate while there is data, as handlers can defer

            if not split: # we are done
                break

            for kw in split:
                okw = kw
                kw = kw.strip()

                # clean-up quotes or semicolon
                if kw.endswith(";"):
                    kw = kw[:-1]
                if kw.startswith(('"', "'")) and (kw[0] == kw[-1]):
                    kw = kw[1:-1]
                for frag_kw in xfrag_kw:
                    ret = False
                    if kw.startswith(frag_kw):
                        # parser funcs returns True/False
                        ret = xfrag_kw[frag_kw](kw[len(frag_kw):])
                        if ret is False:
                            return self.fail("parsing of element '{0}' failed.".format(kw))
                        if ret is True:
                            split.remove(okw)
                        break
                # we have an item that wasn't successfully parsed
                if okw in split and ret is not None:
                    return False
        return True


1	1	from time import strftime, localtime
2
3	1	from spike.model import db
4	1	from shlex import shlex
5
6
7	1	class NaxsiRules(db.Model):
8	1	__bind_key__ = 'rules'
9	1	__tablename__ = 'naxsi_rules'
10
11	1	id = db.Column(db.Integer, primary_key=True)
12	1	msg = db.Column(db.String(), nullable=False)
13	1	detection = db.Column(db.String(1024), nullable=False)
14	1	mz = db.Column(db.String(1024), nullable=False)
15	1	score = db.Column(db.String(1024), nullable=False)
16	1	sid = db.Column(db.Integer, nullable=False, unique=True)
17	1	ruleset = db.Column(db.String(1024), nullable=False)
18	1	rmks = db.Column(db.Text, nullable=True, server_default="")
19	1	active = db.Column(db.Integer, nullable=False, server_default="1")
20	1	negative = db.Column(db.Integer, nullable=False, server_default='0')
21	1	timestamp = db.Column(db.Integer, nullable=False)
22
23	1	warnings = []
24	1	error = []
25	1	mr_kw = ["MainRule", "BasicRule", "main_rule", "basic_rule"]
26	1	static_mz = {"$ARGS_VAR", "$BODY_VAR", "$URL", "$HEADERS_VAR"}
27	1	full_zones = {"ARGS", "BODY", "URL", "HEADERS", "FILE_EXT", "RAW_BODY"}
28	1	rx_mz = {"$ARGS_VAR_X", "$BODY_VAR_X", "$URL_X", "$HEADERS_VAR_X"}
29	1	sub_mz = list(static_mz) + list(full_zones) + list(rx_mz)
30
31	1	def __init__(self, msg, detection, mz, score, sid, ruleset, rmks, active, negative, timestamp):
32	1	self.msg = msg
33	1	self.detection = detection
34	1	self.mz = mz
35	1	self.score = score
36	1	self.sid = sid
37	1	self.ruleset = ruleset
38	1	self.rmks = rmks
39	1	self.active = active
40	1	self.negative = 1 if negative == 'checked' else 0
41	1	self.timestamp = timestamp
42
43	1	def fullstr(self):
44	1	rdate = strftime("%F - %H:%M", localtime(float(str(self.timestamp))))
45	1	rmks = "# ".join(self.rmks.strip().split("\n"))
46	1	return "#\n# sid: {0} \| date: {1}\n#\n# {2}\n#\n{3}".format(self.sid, rdate, rmks, self.__str__())
47
48	1	def __str__(self):
49	1	negate = 'negative' if self.negative == 1 else ''
50	1	return 'MainRule {} "{}" "msg:{}" "mz:{}" "s:{}" id:{} ;'.format(
51		negate, self.detection, self.msg, self.mz, self.score, self.sid)
52
53	1	def validate(self):
54	1	self.p_mz(self.mz)
55	1	self.p_id(self.sid)
56	1	self.p_detection(self.detection)
57
58	1	if not self.msg:
59		self.warnings.append("Rule has no 'msg:'.")
60	1	if not self.score:
61		self.error.append("Rule has no score.")
62
63	1	def fail(self, msg):
64		self.error.append(msg)
65		return False
66
67		# Bellow are parsers for specific parts of a rule
68	1	def p_dummy(self, s, assign=False):
		0 ignored issues – show Coding Style Naming introduced 2016-03-15 16:16 UTC by Report Bug Copy Issue Report The name `s` does not conform to the argument naming conventions (`[a-z_][a-z0-9_]{1,30}$`). This check looks for invalid names for a range of different identifiers. You can set regular expressions to which the identifiers must conform if the defaults do not match your requirements. If your project includes a Pylint configuration file, the settings contained in that file take precedence. To find out more about Pylint, please refer to their site. Loading history... Unused Code introduced 2016-03-15 16:16 UTC by Report Bug Copy Issue Report The argument `s` seems to be unused. Loading history... Unused Code introduced 2016-03-15 16:16 UTC by Report Bug Copy Issue Report The argument `assign` seems to be unused. Loading history... Coding Style introduced 2016-03-15 16:16 UTC by Report Bug Copy Issue Report This method could be written as a function/class method. If a method does not access any attributes of the class, it could also be implemented as a function or static method. This can help improve readability. For example class Foo: def some_method(self, x, y): return x + y; could be written as class Foo: @classmethod def some_method(cls, x, y): return x + y; Loading history...
69		return True
70
71	1	def p_detection(self, s, assign=False):
		0 ignored issues – show Coding Style Naming introduced 2016-03-15 16:16 UTC by Report Bug Copy Issue Report The name `s` does not conform to the argument naming conventions (`[a-z_][a-z0-9_]{1,30}$`). This check looks for invalid names for a range of different identifiers. You can set regular expressions to which the identifiers must conform if the defaults do not match your requirements. If your project includes a Pylint configuration file, the settings contained in that file take precedence. To find out more about Pylint, please refer to their site. Loading history...
72	1	if not s.startswith("str:") and not s.startswith("rx:"):
73		self.fail("detection {} is neither rx: or str:".format(s))
74	1	if not s.islower():
75	1	self.warnings.append("detection {} is not lower-case. naxsi is case-insensitive".format(s))
76	1	if assign is True:
77		self.detection = s
78	1	return True
79
80	1	def p_genericstr(self, s, assign=False):
		0 ignored issues – show Coding Style Naming introduced 2016-03-15 16:16 UTC by Report Bug Copy Issue Report The name `s` does not conform to the argument naming conventions (`[a-z_][a-z0-9_]{1,30}$`). This check looks for invalid names for a range of different identifiers. You can set regular expressions to which the identifiers must conform if the defaults do not match your requirements. If your project includes a Pylint configuration file, the settings contained in that file take precedence. To find out more about Pylint, please refer to their site. Loading history... Unused Code introduced 2016-03-15 16:16 UTC by Report Bug Copy Issue Report The argument `assign` seems to be unused. Loading history...
81		if s and not s.islower():
82		self.warnings.append("Pattern ({0}) is not lower-case.".format(s))
83		return True
84
85	1	def p_mz(self, s, assign=False):
		0 ignored issues – show Coding Style Naming introduced 2016-03-15 16:16 UTC by Report Bug Copy Issue Report The name `s` does not conform to the argument naming conventions (`[a-z_][a-z0-9_]{1,30}$`). This check looks for invalid names for a range of different identifiers. You can set regular expressions to which the identifiers must conform if the defaults do not match your requirements. If your project includes a Pylint configuration file, the settings contained in that file take precedence. To find out more about Pylint, please refer to their site. Loading history...
86	1	has_zone = False
87	1	mz_state = set()
88	1	locs = s.split('\|')
89	1	for loc in locs:
90	1	kw = loc
91	1	arg = None
92	1	if loc.startswith("$"):
93		try:
94		kw, arg = loc.split(":")
95		except ValueError:
96		return self.fail("Missing 2nd part after ':' in {0}".format(loc))
97		# check it is a valid keyword
98	1	if kw not in self.sub_mz:
99		return self.fail("'{0}' no a known sub-part of mz : {1}".format(kw, self.sub_mz))
100	1	mz_state.add(kw)
101		# verify the rule doesn't attempt to target REGEX and STATIC _VAR/URL at the same time
102	1	if len(self.rx_mz & mz_state) and len(self.static_mz & mz_state):
103		return self.fail("You can't mix static $* with regex $*_X ({})".format(str(mz_state)))
104		# just a gentle reminder
105	1	if arg and arg.islower() is False:
106		self.warnings.append("{0} in {1} is not lowercase. naxsi is case-insensitive".format(arg, loc))
107		# the rule targets an actual zone
108	1	if kw not in ["$URL", "$URL_X"] and kw in (self.rx_mz \| self.full_zones \| self.static_mz):
		0 ignored issues – show Unused Code Coding Style introduced 2016-03-15 16:16 UTC by Report Bug Copy Issue Report There is an unnecessary parenthesis after `in`. Loading history...
109	1	has_zone = True
110	1	if has_zone is False:
111		return self.fail("The rule/whitelist doesn't target any zone.")
112	1	if assign is True:
113		self.mz = s
114	1	return True
115
116	1	def p_id(self, s, assign=False):
		0 ignored issues – show Coding Style Naming introduced 2016-03-15 16:16 UTC by Report Bug Copy Issue Report The name `s` does not conform to the argument naming conventions (`[a-z_][a-z0-9_]{1,30}$`). This check looks for invalid names for a range of different identifiers. You can set regular expressions to which the identifiers must conform if the defaults do not match your requirements. If your project includes a Pylint configuration file, the settings contained in that file take precedence. To find out more about Pylint, please refer to their site. Loading history...
117	1	try:
118	1	x = int(s)
		0 ignored issues – show Coding Style Naming introduced 2016-03-15 16:16 UTC by Report Bug Copy Issue Report The name `x` does not conform to the variable naming conventions (`[a-z_][a-z0-9_]{1,30}$`). This check looks for invalid names for a range of different identifiers. You can set regular expressions to which the identifiers must conform if the defaults do not match your requirements. If your project includes a Pylint configuration file, the settings contained in that file take precedence. To find out more about Pylint, please refer to their site. Loading history...
119	1	if x < 10000:
120	1	self.warnings.append("rule IDs below 10k are reserved ({0})".format(x))
121		except ValueError:
122		self.error.append("id:{0} is not numeric".format(s))
123		return False
124	1	if assign is True:
125		self.sid = x
126	1	return True
127
128	1	@staticmethod
129		def splitter(s):
		0 ignored issues – show Coding Style Naming introduced 2016-03-16 11:23 UTC by Report Bug Copy Issue Report The name `s` does not conform to the argument naming conventions (`[a-z_][a-z0-9_]{1,30}$`). This check looks for invalid names for a range of different identifiers. You can set regular expressions to which the identifiers must conform if the defaults do not match your requirements. If your project includes a Pylint configuration file, the settings contained in that file take precedence. To find out more about Pylint, please refer to their site. Loading history...
130		lexer = shlex(s)
131		lexer.quotes = '"\''
132		lexer.whitespace_split = True
133		items = list(iter(lexer.get_token, ''))
134		return ([i for i in items if i[0] in "\"'"] +
135		[i for i in items if i[0] not in "\"'"])
136
137	1	def parse_rule(self, x):
		0 ignored issues – show Coding Style Naming introduced 2016-03-15 16:16 UTC by Report Bug Copy Issue Report The name `x` does not conform to the argument naming conventions (`[a-z_][a-z0-9_]{1,30}$`). This check looks for invalid names for a range of different identifiers. You can set regular expressions to which the identifiers must conform if the defaults do not match your requirements. If your project includes a Pylint configuration file, the settings contained in that file take precedence. To find out more about Pylint, please refer to their site. Loading history...
138		"""
139		Parse and validate a full naxsi rule
140		:param x: raw rule
141		:return: [True\|False, dict]
142		"""
143		xfrag_kw = {"id:": self.p_id, "str:": self.p_genericstr,
144		"rx:": self.p_genericstr, "msg:": self.p_dummy, "mz:": self.p_mz,
145		"negative": self.p_dummy, "s:": self.p_dummy}
146
147		split = self.splitter(x) # parse string
148
149
150		sect = set(self.mr_kw) & set(split) # check if it's a MainRule/BasicRule, store&delete kw
151
152		if len(sect) != 1:
153		return self.fail("no (or multiple) mainrule/basicrule keyword.")
154
155		split.remove(sect.pop())
156
157		if ";" in split:
158		split.remove(";")
159
160		while True: # iterate while there is data, as handlers can defer
161
162		if not split: # we are done
163		break
164
165		for kw in split:
166		okw = kw
167		kw = kw.strip()
168
169		# clean-up quotes or semicolon
170		if kw.endswith(";"):
171		kw = kw[:-1]
172		if kw.startswith(('"', "'")) and (kw[0] == kw[-1]):
173		kw = kw[1:-1]
174		for frag_kw in xfrag_kw:
175		ret = False
176		if kw.startswith(frag_kw):
177		# parser funcs returns True/False
178		ret = xfrag_kw[frag_kw](kw[len(frag_kw):])
179		if ret is False:
180		return self.fail("parsing of element '{0}' failed.".format(kw))
181		if ret is True:
182		split.remove(okw)
183		break
184		# we have an item that wasn't successfully parsed
185		if okw in split and ret is not None:
186		return False
187		return True
188

nbs-system / spike

Branch — master (bb419f)

NaxsiRules.parse_rule() F

Complexity

Size

Duplication

Code Coverage

How to fix Long Method Complexity

Long Method

Complexity

Duplication Side-by-Side

Filter issues like