graph.xml_parser.xml_parser.get_data() - Code Metrics - Inspection of "501ddab7ee2f7e9c017917de63da77c6f398446d" - OpenSCAP/oval-graph - Measure and Improve Code Quality continuously with Scrutinizer

Passed

Branch — master (501dda)

by Jan

created 2019-09-27 13:57 UTC

graph.xml_parser.xml_parser.get_data() A

↳ Parent: graph.xml_parser

Complexity

Conditions

Size

Total Lines	11
Code Lines	10

Duplication

Lines	0
Ratio	0 %

Code Coverage

Tests	8
CRAP Score	3

Importance

Changes

Metric	Value
cc	3
eloc	10
nop	2
dl	0
loc	11
ccs	8
cts	8
cp	1
crap	3
rs	9.9
c	0
b	0
f	0

'''
    Modules for create node IDs and parsing xml
'''

from lxml import etree as ET
import uuid
import graph.oval_graph
import os
import py

ns = {
    'XMLSchema': 'http://oval.mitre.org/XMLSchema/oval-results-5',
    'xccdf': 'http://checklists.nist.gov/xccdf/1.2',
    'arf': 'http://scap.nist.gov/schema/asset-reporting-format/1.1',
    'oval-definitions': 'http://oval.mitre.org/XMLSchema/oval-definitions-5',
    'scap': 'http://scap.nist.gov/schema/scap/source/1.2',
}


class xml_parser():
    def __init__(self, src):
        self.src = src
        self.tree = ET.parse(self.src)
        self.root = self.tree.getroot()
        if not self.validate(
                '../schemas/arf/1.1/asset-reporting-format_1.1.0.xsd'):
            raise ValueError("err- This is not arf report file.")

    def get_src(self, src):
        _dir = os.path.dirname(os.path.realpath(__file__))
        FIXTURE_DIR = py.path.local(_dir) / src
        return str(FIXTURE_DIR)

    def validate(self, xsd_path):
        xsd_path = self.get_src(xsd_path)
        xmlschema_doc = ET.parse(xsd_path)
        xmlschema = ET.XMLSchema(xmlschema_doc)

        xml_doc = self.tree
        result = xmlschema.validate(xml_doc)

        return result

    def get_data(self, href):
        report_data = None
        reports = self.root.find('.//arf:reports', ns)
        for report in reports:
            if "#" + str(report.get("id")) == href:
                report_data = report

        trees_data = report_data.find(
            ('.//XMLSchema:oval_results/XMLSchema:results/'
             'XMLSchema:system/XMLSchema:definitions'), ns)
        return trees_data

    def get_used_rules(self):
        rulesResults = self.root.findall(
            './/xccdf:TestResult/xccdf:rule-result', ns)
        rules = []
        for ruleResult in rulesResults:
            result = ruleResult.find('.//xccdf:result', ns)
            if result.text != "notselected":
                check_content_ref = ruleResult.find(
                    './/xccdf:check/xccdf:check-content-ref', ns)
                if check_content_ref is not None:
                    rules.append(dict(
                        id_rule=ruleResult.get('idref'),
                        id_def=check_content_ref.attrib.get('name'),
                        href=check_content_ref.attrib.get('href'),
                        result=result.text,
                    ))
        return rules

    def get_notselected_rules(self):
        rulesResults = self.root.findall(
            './/xccdf:TestResult/xccdf:rule-result', ns)
        rules = []
        for ruleResult in rulesResults:
            result = ruleResult.find('.//xccdf:result', ns)
            if result.text == "notselected":
                rules.append(dict(id_rule=ruleResult.get('idref')))
        return rules

    def parse_data_to_dict(self, rule_id):
        scan = dict(definitions=[])
        used_rules = self.get_used_rules()
        for i in self.get_data(used_rules[0]['href']):
            scan['definitions'].append(self.build_graph(i))
        self.insert_comments(scan)
        definitions = self._fill_extend_definition(scan)
        for definition in definitions['definitions']:
            if self.get_def_id_by_rule_id(rule_id) == definition['id']:
                return dict(rule_id=rule_id, definition=definition)

    def _xml_dict_to_node(self, dict_of_definition):
        children = []
        for child in dict_of_definition['node']:
            if 'operator' in child and 'id':
                children.append(self._xml_dict_to_node(child))
            else:
                children.append(
                    graph.oval_graph.OvalNode(
                        child['value_id'],
                        'value',
                        child['value'],
                        child['negate'],
                        child['comment'],
                    ))

        if 'id' in dict_of_definition:
            children[0].node_id = dict_of_definition['id']
            return children[0]
        else:
            return graph.oval_graph.OvalNode(
                str(uuid.uuid4()),
                'operator',
                dict_of_definition['operator'],
                dict_of_definition['negate'],
                dict_of_definition['comment'],
                children,
            )

    def get_def_id_by_rule_id(self, rule_id):
        used_rules = self.get_used_rules()
        notselected_rules = self.get_notselected_rules()
        for rule in notselected_rules:
            if rule['id_rule'] == rule_id:
                raise ValueError(
                    'err- rule "{}" was not selected, so there are no results.'
                    .format(rule_id))
        for rule in used_rules:
            if rule['id_rule'] == rule_id:
                return rule['id_def']
        raise ValueError('err- 404 rule not found!')

    def get_rule_dict(self, rule_id):
        return self.parse_data_to_dict(rule_id)

    def xml_dict_of_rule_to_node(self, rule):
        dict_of_definition = rule['definition']
        return graph.oval_graph.OvalNode(
            rule['rule_id'],
            'operator',
            'and',
            False,
            dict_of_definition['comment'],
            [self._xml_dict_to_node(dict_of_definition)],
        )

    def get_oval_graph(self, rule_id=None):
        return self.xml_dict_of_rule_to_node(self.parse_data_to_dict(rule_id))

    def build_graph(self, tree_data):
        graph = dict(
            id=tree_data.get('definition_id'),
            node=[],
        )
        for tree in tree_data:
            negate_status = False
            if 'negate' in tree:
                negate_status = self._str_to_bool(tree.get('negate'))
            graph['negate'] = negate_status
            graph['node'].append(self._build_node(tree))
        return graph

    def _str_to_bool(self, s):
        if s == 'true':
            return True
        elif s == 'false':
            return False
        else:
            raise ValueError('err- negation is not bool')

    def _build_node(self, tree):
        negate_status = False
        if tree.get('negate') is not None:
            negate_status = self._str_to_bool(tree.get('negate'))

        node = dict(
            operator=tree.get('operator'),
            negate=negate_status,
            result=tree.get('result'),
            comment=None,
            node=[],
        )
        for child in tree:
            if child.get('operator') is not None:
                node['node'].append(self._build_node(child))
            else:
                negate_status = False
                if child.get('negate') is not None:
                    negate_status = self._str_to_bool(child.get('negate'))

                if child.get('definition_ref') is not None:
                    node['node'].append(
                        dict(
                            extend_definition=child.get('definition_ref'),
                            result=child.get('result'),
                            negate=negate_status,
                            comment=None,
                        ))
                else:
                    node['node'].append(
                        dict(
                            value_id=child.get('test_ref'),
                            value=child.get('result'),
                            negate=negate_status,
                            comment=None,
                        ))
        return node

    def _fill_extend_definition(self, scan):
        out = dict(definitions=[])
        for definition in scan['definitions']:
            nodes = []
            for value in definition['node']:
                nodes.append(self._operator_as_child(value, scan))
            out['definitions'].append(
                dict(
                    id=definition['id'],
                    comment=definition['comment'],
                    node=nodes,
                    ))
        return out

    def _operator_as_child(self, value, scan):
        out = dict(
            operator=value['operator'],
            negate=value['negate'],
            result=value['result'],
            comment=value['comment'],
            node=[],
        )
        for child in value['node']:
            if 'operator' in child:
                out['node'].append(self._operator_as_child(child, scan))
            elif 'extend_definition' in child:
                out['node'].append(
                    self._find_definition_by_id(
                        scan,
                        child['extend_definition'],
                        child['negate'],
                        child['comment'],
                    ))
            elif 'value_id' in child:
                out['node'].append(child)
            else:
                raise ValueError('error - unknown child')
        return out

    def _find_definition_by_id(self, scan, id, negate_status, comment):
        for definition in scan['definitions']:
            if definition['id'] == id:
                definition['node'][0]['negate'] = negate_status
                definition['node'][0]['comment'] = comment
                return self._operator_as_child(definition['node'][0], scan)

    def create_dict_form_criteria(self, criteria):
        comments = dict(
            operator='AND' if criteria.get('operator') is None else criteria.get('operator'),
            comment=criteria.get('comment'),
            node=[],
        )
        for criterion in criteria:
            if criterion.get('operator'):
                comments['node'].append(
                    self.create_dict_form_criteria(criterion))
            else:
                if criterion.get('definition_ref'):
                    comments['node'].append(
                        dict(
                            extend_definition=criterion.get('definition_ref'),
                            comment=criterion.get('comment'),
                        ))
                else:
                    comments['node'].append(
                        dict(
                            value_id=criterion.get('test_ref'),
                            comment=criterion.get('comment'),
                        ))
        return comments

    def prepare_definition_comments(self, oval_definitions):
        definitions = []
        for definition in oval_definitions:
            comment_definition = dict(
                id=definition.get('id'), comment=None, node=[])
            title = definition.find(
                './/oval-definitions:metadata/oval-definitions:title', ns)
            comment_definition['comment'] = title.text
            criteria = definition.find('.//oval-definitions:criteria', ns)
            comment_definition['node'].append(
                self.create_dict_form_criteria(criteria))
            definitions.append(comment_definition)
        return definitions

    def is_definition_in_array(self, definition_, array):
        for definition in array:
            if definition_['id'] == definition['id']:
                return True
        return False

    def recursive_help_fill_comments(self, comments, nodes):
        out = nodes
        out['comment'] = comments['comment']
        for node, comment in zip(out['node'], comments['node']):
            node['comment'] = comment['comment']
            if 'operator' in node:
                self.recursive_help_fill_comments(comment, node)

    def fill_comment(self, comment_definition, data_definition):
        comments = comment_definition['node'][0]
        nodes = data_definition['node'][0]
        data_definition['comment'] = comment_definition['comment']
        self.recursive_help_fill_comments(comments, nodes)

    def insert_comments(self, data):
        oval_def = self.root.find(
            './/arf:report-requests/arf:report-request/'
            'arf:content/scap:data-stream-collection/'
            'scap:component/oval-definitions:oval_definitions/'
            'oval-definitions:definitions', ns)
        comment_definitions = self.prepare_definition_comments(oval_def)

        for data_definition in data['definitions']:
            for comment_definition in comment_definitions:
                if comment_definition['id'] == data_definition['id']:
                    self.fill_comment(comment_definition, data_definition)


1		'''
2		Modules for create node IDs and parsing xml
3		'''
4
5	1	from lxml import etree as ET
6	1	import uuid
7	1	import graph.oval_graph
8	1	import os
9	1	import py
10
11	1	ns = {
12		'XMLSchema': 'http://oval.mitre.org/XMLSchema/oval-results-5',
13		'xccdf': 'http://checklists.nist.gov/xccdf/1.2',
14		'arf': 'http://scap.nist.gov/schema/asset-reporting-format/1.1',
15		'oval-definitions': 'http://oval.mitre.org/XMLSchema/oval-definitions-5',
16		'scap': 'http://scap.nist.gov/schema/scap/source/1.2',
17		}
18
19
20	1	class xml_parser():
21	1	def __init__(self, src):
22	1	self.src = src
23	1	self.tree = ET.parse(self.src)
24	1	self.root = self.tree.getroot()
25	1	if not self.validate(
26		'../schemas/arf/1.1/asset-reporting-format_1.1.0.xsd'):
27	1	raise ValueError("err- This is not arf report file.")
28
29	1	def get_src(self, src):
30	1	_dir = os.path.dirname(os.path.realpath(__file__))
31	1	FIXTURE_DIR = py.path.local(_dir) / src
32	1	return str(FIXTURE_DIR)
33
34	1	def validate(self, xsd_path):
35	1	xsd_path = self.get_src(xsd_path)
36	1	xmlschema_doc = ET.parse(xsd_path)
37	1	xmlschema = ET.XMLSchema(xmlschema_doc)
38
39	1	xml_doc = self.tree
40	1	result = xmlschema.validate(xml_doc)
41
42	1	return result
43
44	1	def get_data(self, href):
45	1	report_data = None
46	1	reports = self.root.find('.//arf:reports', ns)
47	1	for report in reports:
48	1	if "#" + str(report.get("id")) == href:
49	1	report_data = report
50
51	1	trees_data = report_data.find(
52		('.//XMLSchema:oval_results/XMLSchema:results/'
53		'XMLSchema:system/XMLSchema:definitions'), ns)
54	1	return trees_data
55
56	1	def get_used_rules(self):
57	1	rulesResults = self.root.findall(
58		'.//xccdf:TestResult/xccdf:rule-result', ns)
59	1	rules = []
60	1	for ruleResult in rulesResults:
61	1	result = ruleResult.find('.//xccdf:result', ns)
62	1	if result.text != "notselected":
63	1	check_content_ref = ruleResult.find(
64		'.//xccdf:check/xccdf:check-content-ref', ns)
65	1	if check_content_ref is not None:
66	1	rules.append(dict(
67		id_rule=ruleResult.get('idref'),
68		id_def=check_content_ref.attrib.get('name'),
69		href=check_content_ref.attrib.get('href'),
70		result=result.text,
71		))
72	1	return rules
73
74	1	def get_notselected_rules(self):
75	1	rulesResults = self.root.findall(
76		'.//xccdf:TestResult/xccdf:rule-result', ns)
77	1	rules = []
78	1	for ruleResult in rulesResults:
79	1	result = ruleResult.find('.//xccdf:result', ns)
80	1	if result.text == "notselected":
81	1	rules.append(dict(id_rule=ruleResult.get('idref')))
82	1	return rules
83
84	1	def parse_data_to_dict(self, rule_id):
85	1	scan = dict(definitions=[])
86	1	used_rules = self.get_used_rules()
87	1	for i in self.get_data(used_rules[0]['href']):
88	1	scan['definitions'].append(self.build_graph(i))
89	1	self.insert_comments(scan)
90	1	definitions = self._fill_extend_definition(scan)
91	1	for definition in definitions['definitions']:
92	1	if self.get_def_id_by_rule_id(rule_id) == definition['id']:
93	1	return dict(rule_id=rule_id, definition=definition)
94
95	1	def _xml_dict_to_node(self, dict_of_definition):
96	1	children = []
97	1	for child in dict_of_definition['node']:
98	1	if 'operator' in child and 'id':
99	1	children.append(self._xml_dict_to_node(child))
100		else:
101	1	children.append(
102		graph.oval_graph.OvalNode(
103		child['value_id'],
104		'value',
105		child['value'],
106		child['negate'],
107		child['comment'],
108		))
109
110	1	if 'id' in dict_of_definition:
111	1	children[0].node_id = dict_of_definition['id']
112	1	return children[0]
113		else:
114	1	return graph.oval_graph.OvalNode(
115		str(uuid.uuid4()),
116		'operator',
117		dict_of_definition['operator'],
118		dict_of_definition['negate'],
119		dict_of_definition['comment'],
120		children,
121		)
122
123	1	def get_def_id_by_rule_id(self, rule_id):
124	1	used_rules = self.get_used_rules()
125	1	notselected_rules = self.get_notselected_rules()
126	1	for rule in notselected_rules:
127	1	if rule['id_rule'] == rule_id:
128	1	raise ValueError(
129		'err- rule "{}" was not selected, so there are no results.'
130		.format(rule_id))
131	1	for rule in used_rules:
132	1	if rule['id_rule'] == rule_id:
133	1	return rule['id_def']
134	1	raise ValueError('err- 404 rule not found!')
135
136	1	def get_rule_dict(self, rule_id):
137	1	return self.parse_data_to_dict(rule_id)
138
139	1	def xml_dict_of_rule_to_node(self, rule):
140	1	dict_of_definition = rule['definition']
141	1	return graph.oval_graph.OvalNode(
142		rule['rule_id'],
143		'operator',
144		'and',
145		False,
146		dict_of_definition['comment'],
147		[self._xml_dict_to_node(dict_of_definition)],
148		)
149
150	1	def get_oval_graph(self, rule_id=None):
151	1	return self.xml_dict_of_rule_to_node(self.parse_data_to_dict(rule_id))
152
153	1	def build_graph(self, tree_data):
154	1	graph = dict(
155		id=tree_data.get('definition_id'),
156		node=[],
157		)
158	1	for tree in tree_data:
159	1	negate_status = False
160	1	if 'negate' in tree:
161		negate_status = self._str_to_bool(tree.get('negate'))
162	1	graph['negate'] = negate_status
163	1	graph['node'].append(self._build_node(tree))
164	1	return graph
165
166	1	def _str_to_bool(self, s):
167	1	if s == 'true':
168	1	return True
169	1	elif s == 'false':
170	1	return False
171		else:
172	1	raise ValueError('err- negation is not bool')
173
174	1	def _build_node(self, tree):
175	1	negate_status = False
176	1	if tree.get('negate') is not None:
177	1	negate_status = self._str_to_bool(tree.get('negate'))
178
179	1	node = dict(
180		operator=tree.get('operator'),
181		negate=negate_status,
182		result=tree.get('result'),
183		comment=None,
184		node=[],
185		)
186	1	for child in tree:
187	1	if child.get('operator') is not None:
188	1	node['node'].append(self._build_node(child))
189		else:
190	1	negate_status = False
191	1	if child.get('negate') is not None:
192	1	negate_status = self._str_to_bool(child.get('negate'))
193
194	1	if child.get('definition_ref') is not None:
195	1	node['node'].append(
196		dict(
197		extend_definition=child.get('definition_ref'),
198		result=child.get('result'),
199		negate=negate_status,
200		comment=None,
201		))
202		else:
203	1	node['node'].append(
204		dict(
205		value_id=child.get('test_ref'),
206		value=child.get('result'),
207		negate=negate_status,
208		comment=None,
209		))
210	1	return node
211
212	1	def _fill_extend_definition(self, scan):
213	1	out = dict(definitions=[])
214	1	for definition in scan['definitions']:
215	1	nodes = []
216	1	for value in definition['node']:
217	1	nodes.append(self._operator_as_child(value, scan))
218	1	out['definitions'].append(
219		dict(
220		id=definition['id'],
221		comment=definition['comment'],
222		node=nodes,
223		))
224	1	return out
225
226	1	def _operator_as_child(self, value, scan):
227	1	out = dict(
228		operator=value['operator'],
229		negate=value['negate'],
230		result=value['result'],
231		comment=value['comment'],
232		node=[],
233		)
234	1	for child in value['node']:
235	1	if 'operator' in child:
236	1	out['node'].append(self._operator_as_child(child, scan))
237	1	elif 'extend_definition' in child:
238	1	out['node'].append(
239		self._find_definition_by_id(
240		scan,
241		child['extend_definition'],
242		child['negate'],
243		child['comment'],
244		))
245	1	elif 'value_id' in child:
246	1	out['node'].append(child)
247		else:
248		raise ValueError('error - unknown child')
249	1	return out
250
251	1	def _find_definition_by_id(self, scan, id, negate_status, comment):
252	1	for definition in scan['definitions']:
253	1	if definition['id'] == id:
254	1	definition['node'][0]['negate'] = negate_status
255	1	definition['node'][0]['comment'] = comment
256	1	return self._operator_as_child(definition['node'][0], scan)
257
258	1	def create_dict_form_criteria(self, criteria):
259	1	comments = dict(
260		operator='AND' if criteria.get('operator') is None else criteria.get('operator'),
261		comment=criteria.get('comment'),
262		node=[],
263		)
264	1	for criterion in criteria:
265	1	if criterion.get('operator'):
266	1	comments['node'].append(
267		self.create_dict_form_criteria(criterion))
268		else:
269	1	if criterion.get('definition_ref'):
270	1	comments['node'].append(
271		dict(
272		extend_definition=criterion.get('definition_ref'),
273		comment=criterion.get('comment'),
274		))
275		else:
276	1	comments['node'].append(
277		dict(
278		value_id=criterion.get('test_ref'),
279		comment=criterion.get('comment'),
280		))
281	1	return comments
282
283	1	def prepare_definition_comments(self, oval_definitions):
284	1	definitions = []
285	1	for definition in oval_definitions:
286	1	comment_definition = dict(
287		id=definition.get('id'), comment=None, node=[])
288	1	title = definition.find(
289		'.//oval-definitions:metadata/oval-definitions:title', ns)
290	1	comment_definition['comment'] = title.text
291	1	criteria = definition.find('.//oval-definitions:criteria', ns)
292	1	comment_definition['node'].append(
293		self.create_dict_form_criteria(criteria))
294	1	definitions.append(comment_definition)
295	1	return definitions
296
297	1	def is_definition_in_array(self, definition_, array):
298		for definition in array:
299		if definition_['id'] == definition['id']:
300		return True
301		return False
302
303	1	def recursive_help_fill_comments(self, comments, nodes):
304	1	out = nodes
305	1	out['comment'] = comments['comment']
306	1	for node, comment in zip(out['node'], comments['node']):
307	1	node['comment'] = comment['comment']
308	1	if 'operator' in node:
309	1	self.recursive_help_fill_comments(comment, node)
310
311	1	def fill_comment(self, comment_definition, data_definition):
312	1	comments = comment_definition['node'][0]
313	1	nodes = data_definition['node'][0]
314	1	data_definition['comment'] = comment_definition['comment']
315	1	self.recursive_help_fill_comments(comments, nodes)
316
317	1	def insert_comments(self, data):
318	1	oval_def = self.root.find(
319		'.//arf:report-requests/arf:report-request/'
320		'arf:content/scap:data-stream-collection/'
321		'scap:component/oval-definitions:oval_definitions/'
322		'oval-definitions:definitions', ns)
323	1	comment_definitions = self.prepare_definition_comments(oval_def)
324
325	1	for data_definition in data['definitions']:
326	1	for comment_definition in comment_definitions:
327	1	if comment_definition['id'] == data_definition['id']:
328		self.fill_comment(comment_definition, data_definition)
329

OpenSCAP / oval-graph

Branch — master (501dda)

graph.xml_parser.xml_parser.get_data() A

Complexity

Size

Duplication

Code Coverage

Importance

Duplication Side-by-Side

Filter issues like